diff options
Diffstat (limited to 'drivers/net/ethernet')
532 files changed, 47464 insertions, 12943 deletions
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 1917da784191..323ec56e8a74 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -132,16 +132,6 @@ source "drivers/net/ethernet/mscc/Kconfig" source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" - -config FEALNX - tristate "Myson MTD-8xx PCI Ethernet support" - depends on PCI - select CRC32 - select MII - help - Say Y here to support the Myson MTD-800 family of PCI-based Ethernet - cards. <http://www.myson.com.tw/> - source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/natsemi/Kconfig" source "drivers/net/ethernet/neterion/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 0d872d4efcd1..2fedbaa545eb 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -64,7 +64,6 @@ obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/ obj-$(CONFIG_NET_VENDOR_MICROSEMI) += mscc/ obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/ obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/ -obj-$(CONFIG_FEALNX) += fealnx.o obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/ obj-$(CONFIG_NET_VENDOR_NETERION) += neterion/ obj-$(CONFIG_NET_VENDOR_NETRONOME) += netronome/ diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 606c97610808..0805f249fff2 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -196,7 +196,7 @@ static int adin1110_read_reg(struct adin1110_priv *priv, u16 reg, u32 *val) { u32 header_len = ADIN1110_RD_HEADER_LEN; u32 read_len = ADIN1110_REG_LEN; - struct spi_transfer t[2] = {0}; + struct spi_transfer t = {0}; int ret; priv->data[0] = ADIN1110_CD | FIELD_GET(GENMASK(12, 8), reg); @@ -209,17 +209,15 @@ static int adin1110_read_reg(struct adin1110_priv *priv, u16 reg, u32 *val) header_len++; } - t[0].tx_buf = &priv->data[0]; - t[0].len = header_len; - if (priv->append_crc) read_len++; memset(&priv->data[header_len], 0, read_len); - t[1].rx_buf = &priv->data[header_len]; - t[1].len = read_len; + t.tx_buf = &priv->data[0]; + t.rx_buf = &priv->data[0]; + t.len = read_len + header_len; - ret = spi_sync_transfer(priv->spidev, t, 2); + ret = spi_sync_transfer(priv->spidev, &t, 1); if (ret) return ret; @@ -296,7 +294,7 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv) { struct adin1110_priv *priv = port_priv->priv; u32 header_len = ADIN1110_RD_HEADER_LEN; - struct spi_transfer t[2] = {0}; + struct spi_transfer t; u32 frame_size_no_fcs; struct sk_buff *rxb; u32 frame_size; @@ -327,12 +325,7 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv) return ret; frame_size_no_fcs = frame_size - ADIN1110_FRAME_HEADER_LEN - ADIN1110_FEC_LEN; - - rxb = netdev_alloc_skb(port_priv->netdev, round_len); - if (!rxb) - return -ENOMEM; - - memset(priv->data, 0, round_len + ADIN1110_RD_HEADER_LEN); + memset(priv->data, 0, ADIN1110_RD_HEADER_LEN); priv->data[0] = ADIN1110_CD | FIELD_GET(GENMASK(12, 8), reg); priv->data[1] = FIELD_GET(GENMASK(7, 0), reg); @@ -342,21 +335,23 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv) header_len++; } - skb_put(rxb, frame_size_no_fcs + ADIN1110_FRAME_HEADER_LEN); + rxb = netdev_alloc_skb(port_priv->netdev, round_len + header_len); + if (!rxb) + return -ENOMEM; - t[0].tx_buf = &priv->data[0]; - t[0].len = header_len; + skb_put(rxb, frame_size_no_fcs + header_len + ADIN1110_FRAME_HEADER_LEN); - t[1].rx_buf = &rxb->data[0]; - t[1].len = round_len; + t.tx_buf = &priv->data[0]; + t.rx_buf = &rxb->data[0]; + t.len = header_len + round_len; - ret = spi_sync_transfer(priv->spidev, t, 2); + ret = spi_sync_transfer(priv->spidev, &t, 1); if (ret) { kfree_skb(rxb); return ret; } - skb_pull(rxb, ADIN1110_FRAME_HEADER_LEN); + skb_pull(rxb, header_len + ADIN1110_FRAME_HEADER_LEN); rxb->protocol = eth_type_trans(rxb, port_priv->netdev); if ((port_priv->flags & IFF_ALLMULTI && rxb->pkt_type == PACKET_MULTICAST) || @@ -1087,9 +1082,30 @@ static void adin1110_adjust_link(struct net_device *dev) */ static int adin1110_check_spi(struct adin1110_priv *priv) { + struct gpio_desc *reset_gpio; int ret; u32 val; + reset_gpio = devm_gpiod_get_optional(&priv->spidev->dev, "reset", + GPIOD_OUT_LOW); + if (reset_gpio) { + /* MISO pin is used for internal configuration, can't have + * anyone else disturbing the SDO line. + */ + spi_bus_lock(priv->spidev->controller); + + gpiod_set_value(reset_gpio, 1); + fsleep(10000); + gpiod_set_value(reset_gpio, 0); + + /* Need to wait 90 ms before interacting with + * the MAC after a HW reset. + */ + fsleep(90000); + + spi_bus_unlock(priv->spidev->controller); + } + ret = adin1110_read_reg(priv, ADIN1110_PHY_ID, &val); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/alacritech/slic.h b/drivers/net/ethernet/alacritech/slic.h index 4eecbdfff3ff..82071d0e5f7f 100644 --- a/drivers/net/ethernet/alacritech/slic.h +++ b/drivers/net/ethernet/alacritech/slic.h @@ -288,13 +288,13 @@ do { \ u64_stats_update_end(&(st)->syncp); \ } while (0) -#define SLIC_GET_STATS_COUNTER(newst, st, counter) \ -{ \ - unsigned int start; \ +#define SLIC_GET_STATS_COUNTER(newst, st, counter) \ +{ \ + unsigned int start; \ do { \ - start = u64_stats_fetch_begin_irq(&(st)->syncp); \ - newst = (st)->counter; \ - } while (u64_stats_fetch_retry_irq(&(st)->syncp, start)); \ + start = u64_stats_fetch_begin(&(st)->syncp); \ + newst = (st)->counter; \ + } while (u64_stats_fetch_retry(&(st)->syncp, start)); \ } struct slic_upr { diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 711d5b5a4c49..66e3af73ec41 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -1096,7 +1096,6 @@ static struct phylink_pcs *alt_tse_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops alt_tse_phylink_ops = { - .validate = phylink_generic_validate, .mac_an_restart = alt_tse_mac_an_restart, .mac_config = alt_tse_mac_config, .mac_link_down = alt_tse_mac_link_down, diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 98d6386b7f39..48ae6d810f8f 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -118,9 +118,9 @@ static void ena_safe_update_stat(u64 *src, u64 *dst, unsigned int start; do { - start = u64_stats_fetch_begin_irq(syncp); + start = u64_stats_fetch_begin(syncp); *(dst) = *src; - } while (u64_stats_fetch_retry_irq(syncp, start)); + } while (u64_stats_fetch_retry(syncp, start)); } static void ena_queue_stats(struct ena_adapter *adapter, u64 **data) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 5a454b58498f..a95529a69cbb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -3268,10 +3268,10 @@ static void ena_get_stats64(struct net_device *netdev, tx_ring = &adapter->tx_ring[i]; do { - start = u64_stats_fetch_begin_irq(&tx_ring->syncp); + start = u64_stats_fetch_begin(&tx_ring->syncp); packets = tx_ring->tx_stats.cnt; bytes = tx_ring->tx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start)); + } while (u64_stats_fetch_retry(&tx_ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; @@ -3279,20 +3279,20 @@ static void ena_get_stats64(struct net_device *netdev, rx_ring = &adapter->rx_ring[i]; do { - start = u64_stats_fetch_begin_irq(&rx_ring->syncp); + start = u64_stats_fetch_begin(&rx_ring->syncp); packets = rx_ring->rx_stats.cnt; bytes = rx_ring->rx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start)); + } while (u64_stats_fetch_retry(&rx_ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; } do { - start = u64_stats_fetch_begin_irq(&adapter->syncp); + start = u64_stats_fetch_begin(&adapter->syncp); rx_drops = adapter->dev_stats.rx_drops; tx_drops = adapter->dev_stats.tx_drops; - } while (u64_stats_fetch_retry_irq(&adapter->syncp, start)); + } while (u64_stats_fetch_retry(&adapter->syncp, start)); stats->rx_dropped = rx_drops; stats->tx_dropped = tx_drops; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c index d06d260cf1e2..7051bd7cf6dc 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c @@ -134,27 +134,15 @@ static u64 xgbe_cc_read(const struct cyclecounter *cc) return nsec; } -static int xgbe_adjfreq(struct ptp_clock_info *info, s32 delta) +static int xgbe_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data, ptp_clock_info); unsigned long flags; - u64 adjust; - u32 addend, diff; - unsigned int neg_adjust = 0; + u64 addend; - if (delta < 0) { - neg_adjust = 1; - delta = -delta; - } - - adjust = pdata->tstamp_addend; - adjust *= delta; - diff = div_u64(adjust, 1000000000UL); - - addend = (neg_adjust) ? pdata->tstamp_addend - diff : - pdata->tstamp_addend + diff; + addend = adjust_by_scaled_ppm(pdata->tstamp_addend, scaled_ppm); spin_lock_irqsave(&pdata->tstamp_lock, flags); @@ -235,7 +223,7 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata) netdev_name(pdata->netdev)); info->owner = THIS_MODULE; info->max_adj = pdata->ptpclk_rate; - info->adjfreq = xgbe_adjfreq; + info->adjfine = xgbe_adjfine; info->adjtime = xgbe_adjtime; info->gettime64 = xgbe_gettime; info->settime64 = xgbe_settime; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 25129e723b57..1e8d902e1c8e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -934,7 +934,7 @@ unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) /* This data should mimic aq_ethtool_queue_rx_stat_names structure */ do { count = 0; - start = u64_stats_fetch_begin_irq(&self->stats.rx.syncp); + start = u64_stats_fetch_begin(&self->stats.rx.syncp); data[count] = self->stats.rx.packets; data[++count] = self->stats.rx.jumbo_packets; data[++count] = self->stats.rx.lro_packets; @@ -951,15 +951,15 @@ unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) data[++count] = self->stats.rx.xdp_tx; data[++count] = self->stats.rx.xdp_invalid; data[++count] = self->stats.rx.xdp_redirect; - } while (u64_stats_fetch_retry_irq(&self->stats.rx.syncp, start)); + } while (u64_stats_fetch_retry(&self->stats.rx.syncp, start)); } else { /* This data should mimic aq_ethtool_queue_tx_stat_names structure */ do { count = 0; - start = u64_stats_fetch_begin_irq(&self->stats.tx.syncp); + start = u64_stats_fetch_begin(&self->stats.tx.syncp); data[count] = self->stats.tx.packets; data[++count] = self->stats.tx.queue_restarts; - } while (u64_stats_fetch_retry_irq(&self->stats.tx.syncp, start)); + } while (u64_stats_fetch_retry(&self->stats.tx.syncp, start)); } return ++count; diff --git a/drivers/net/ethernet/asix/ax88796c_main.c b/drivers/net/ethernet/asix/ax88796c_main.c index 8b7cdf015a16..21376c79f671 100644 --- a/drivers/net/ethernet/asix/ax88796c_main.c +++ b/drivers/net/ethernet/asix/ax88796c_main.c @@ -662,12 +662,12 @@ static void ax88796c_get_stats64(struct net_device *ndev, s = per_cpu_ptr(ax_local->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&s->syncp); + start = u64_stats_fetch_begin(&s->syncp); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); - } while (u64_stats_fetch_retry_irq(&s->syncp, start)); + } while (u64_stats_fetch_retry(&s->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 4a1efe9b37d0..ff1a5edf8df1 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1086,7 +1086,6 @@ static void ag71xx_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ag71xx_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = ag71xx_mac_config, .mac_link_down = ag71xx_mac_link_down, .mac_link_up = ag71xx_mac_link_up, diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 7f876721596c..b751dc8486dc 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1680,7 +1680,7 @@ static void b44_get_stats64(struct net_device *dev, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&hwstat->syncp); + start = u64_stats_fetch_begin(&hwstat->syncp); /* Convert HW stats into rtnl_link_stats64 stats. */ nstat->rx_packets = hwstat->rx_pkts; @@ -1714,7 +1714,7 @@ static void b44_get_stats64(struct net_device *dev, /* Carrier lost counter seems to be broken for some devices */ nstat->tx_carrier_errors = hwstat->tx_carrier_lost; #endif - } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start)); + } while (u64_stats_fetch_retry(&hwstat->syncp, start)); } @@ -2082,12 +2082,12 @@ static void b44_get_ethtool_stats(struct net_device *dev, do { data_src = &hwstat->tx_good_octets; data_dst = data; - start = u64_stats_fetch_begin_irq(&hwstat->syncp); + start = u64_stats_fetch_begin(&hwstat->syncp); for (i = 0; i < ARRAY_SIZE(b44_gstrings); i++) *data_dst++ = *data_src++; - } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start)); + } while (u64_stats_fetch_retry(&hwstat->syncp, start)); } static void b44_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index a737b1913cf9..33d86683af50 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -36,13 +36,24 @@ #define ENET_MAX_ETH_OVERHEAD (ETH_HLEN + BRCM_MAX_TAG_LEN + VLAN_HLEN + \ ETH_FCS_LEN + 4) /* 32 */ +#define ENET_RX_SKB_BUF_SIZE (NET_SKB_PAD + NET_IP_ALIGN + \ + ETH_HLEN + BRCM_MAX_TAG_LEN + VLAN_HLEN + \ + ENET_MTU_MAX + ETH_FCS_LEN + 4) +#define ENET_RX_SKB_BUF_ALLOC_SIZE (SKB_DATA_ALIGN(ENET_RX_SKB_BUF_SIZE) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define ENET_RX_BUF_DMA_OFFSET (NET_SKB_PAD + NET_IP_ALIGN) +#define ENET_RX_BUF_DMA_SIZE (ENET_RX_SKB_BUF_SIZE - ENET_RX_BUF_DMA_OFFSET) + struct bcm4908_enet_dma_ring_bd { __le32 ctl; __le32 addr; } __packed; struct bcm4908_enet_dma_ring_slot { - struct sk_buff *skb; + union { + void *buf; /* RX */ + struct sk_buff *skb; /* TX */ + }; unsigned int len; dma_addr_t dma_addr; }; @@ -260,22 +271,21 @@ static int bcm4908_enet_dma_alloc_rx_buf(struct bcm4908_enet *enet, unsigned int u32 tmp; int err; - slot->len = ENET_MTU_MAX + ENET_MAX_ETH_OVERHEAD; - - slot->skb = netdev_alloc_skb(enet->netdev, slot->len); - if (!slot->skb) + slot->buf = napi_alloc_frag(ENET_RX_SKB_BUF_ALLOC_SIZE); + if (!slot->buf) return -ENOMEM; - slot->dma_addr = dma_map_single(dev, slot->skb->data, slot->len, DMA_FROM_DEVICE); + slot->dma_addr = dma_map_single(dev, slot->buf + ENET_RX_BUF_DMA_OFFSET, + ENET_RX_BUF_DMA_SIZE, DMA_FROM_DEVICE); err = dma_mapping_error(dev, slot->dma_addr); if (err) { dev_err(dev, "Failed to map DMA buffer: %d\n", err); - kfree_skb(slot->skb); - slot->skb = NULL; + skb_free_frag(slot->buf); + slot->buf = NULL; return err; } - tmp = slot->len << DMA_CTL_LEN_DESC_BUFLENGTH_SHIFT; + tmp = ENET_RX_BUF_DMA_SIZE << DMA_CTL_LEN_DESC_BUFLENGTH_SHIFT; tmp |= DMA_CTL_STATUS_OWN; if (idx == enet->rx_ring.length - 1) tmp |= DMA_CTL_STATUS_WRAP; @@ -315,11 +325,11 @@ static void bcm4908_enet_dma_uninit(struct bcm4908_enet *enet) for (i = rx_ring->length - 1; i >= 0; i--) { slot = &rx_ring->slots[i]; - if (!slot->skb) + if (!slot->buf) continue; dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_FROM_DEVICE); - kfree_skb(slot->skb); - slot->skb = NULL; + skb_free_frag(slot->buf); + slot->buf = NULL; } } @@ -495,6 +505,7 @@ static int bcm4908_enet_stop(struct net_device *netdev) netif_carrier_off(netdev); napi_disable(&rx_ring->napi); napi_disable(&tx_ring->napi); + netdev_reset_queue(netdev); bcm4908_enet_dma_rx_ring_disable(enet, &enet->rx_ring); bcm4908_enet_dma_tx_ring_disable(enet, &enet->tx_ring); @@ -554,6 +565,8 @@ static netdev_tx_t bcm4908_enet_start_xmit(struct sk_buff *skb, struct net_devic if (ring->write_idx + 1 == ring->length - 1) tmp |= DMA_CTL_STATUS_WRAP; + netdev_sent_queue(enet->netdev, skb->len); + buf_desc->addr = cpu_to_le32((uint32_t)slot->dma_addr); buf_desc->ctl = cpu_to_le32(tmp); @@ -575,6 +588,7 @@ static int bcm4908_enet_poll_rx(struct napi_struct *napi, int weight) while (handled < weight) { struct bcm4908_enet_dma_ring_bd *buf_desc; struct bcm4908_enet_dma_ring_slot slot; + struct sk_buff *skb; u32 ctl; int len; int err; @@ -598,16 +612,24 @@ static int bcm4908_enet_poll_rx(struct napi_struct *napi, int weight) if (len < ETH_ZLEN || (ctl & (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) != (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) { - kfree_skb(slot.skb); + skb_free_frag(slot.buf); enet->netdev->stats.rx_dropped++; break; } - dma_unmap_single(dev, slot.dma_addr, slot.len, DMA_FROM_DEVICE); + dma_unmap_single(dev, slot.dma_addr, ENET_RX_BUF_DMA_SIZE, DMA_FROM_DEVICE); + + skb = build_skb(slot.buf, ENET_RX_SKB_BUF_ALLOC_SIZE); + if (unlikely(!skb)) { + skb_free_frag(slot.buf); + enet->netdev->stats.rx_dropped++; + break; + } + skb_reserve(skb, ENET_RX_BUF_DMA_OFFSET); + skb_put(skb, len - ETH_FCS_LEN); + skb->protocol = eth_type_trans(skb, enet->netdev); - skb_put(slot.skb, len - ETH_FCS_LEN); - slot.skb->protocol = eth_type_trans(slot.skb, enet->netdev); - netif_receive_skb(slot.skb); + netif_receive_skb(skb); enet->netdev->stats.rx_packets++; enet->netdev->stats.rx_bytes += len; @@ -652,6 +674,7 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight) tx_ring->read_idx = 0; } + netdev_completed_queue(enet->netdev, handled, bytes); enet->netdev->stats.tx_packets += handled; enet->netdev->stats.tx_bytes += bytes; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 425d6ccd5413..38d0cdaf22a5 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -295,6 +295,8 @@ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = { /* RBUF misc statistics */ STAT_RBUF("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt, RBUF_OVFL_DISC_CNTR), STAT_RBUF("rbuf_err_cnt", mib.rbuf_err_cnt, RBUF_ERR_PKT_CNTR), + /* RDMA misc statistics */ + STAT_RDMA("rdma_ovflow_cnt", mib.rdma_ovflow_cnt, RDMA_OVFL_DISC_CNTR), STAT_MIB_SOFT("alloc_rx_buff_failed", mib.alloc_rx_buff_failed), STAT_MIB_SOFT("rx_dma_failed", mib.rx_dma_failed), STAT_MIB_SOFT("tx_dma_failed", mib.tx_dma_failed), @@ -333,6 +335,7 @@ static inline bool bcm_sysport_lite_stat_valid(enum bcm_sysport_stat_type type) case BCM_SYSPORT_STAT_NETDEV64: case BCM_SYSPORT_STAT_RXCHK: case BCM_SYSPORT_STAT_RBUF: + case BCM_SYSPORT_STAT_RDMA: case BCM_SYSPORT_STAT_SOFT: return true; default: @@ -436,6 +439,14 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv) if (val == ~0) rbuf_writel(priv, 0, s->reg_offset); break; + case BCM_SYSPORT_STAT_RDMA: + if (!priv->is_lite) + continue; + + val = rdma_readl(priv, s->reg_offset); + if (val == ~0) + rdma_writel(priv, 0, s->reg_offset); + break; } j += s->stat_sizeof; @@ -457,10 +468,10 @@ static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv, for (q = 0; q < priv->netdev->num_tx_queues; q++) { ring = &priv->tx_rings[q]; do { - start = u64_stats_fetch_begin_irq(&priv->syncp); + start = u64_stats_fetch_begin(&priv->syncp); bytes = ring->bytes; packets = ring->packets; - } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); + } while (u64_stats_fetch_retry(&priv->syncp, start)); *tx_bytes += bytes; *tx_packets += packets; @@ -504,9 +515,9 @@ static void bcm_sysport_get_stats(struct net_device *dev, if (s->stat_sizeof == sizeof(u64) && s->type == BCM_SYSPORT_STAT_NETDEV64) { do { - start = u64_stats_fetch_begin_irq(syncp); + start = u64_stats_fetch_begin(syncp); data[i] = *(u64 *)p; - } while (u64_stats_fetch_retry_irq(syncp, start)); + } while (u64_stats_fetch_retry(syncp, start)); } else data[i] = *(u32 *)p; j++; @@ -1878,10 +1889,10 @@ static void bcm_sysport_get_stats64(struct net_device *dev, &stats->tx_packets); do { - start = u64_stats_fetch_begin_irq(&priv->syncp); + start = u64_stats_fetch_begin(&priv->syncp); stats->rx_packets = stats64->rx_packets; stats->rx_bytes = stats64->rx_bytes; - } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); + } while (u64_stats_fetch_retry(&priv->syncp, start)); } static void bcm_sysport_netif_start(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 5af16e5f9ad0..335cf6631db5 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -290,6 +290,7 @@ struct bcm_rsb { #define RDMA_WRITE_PTR_HI 0x1010 #define RDMA_WRITE_PTR_LO 0x1014 +#define RDMA_OVFL_DISC_CNTR 0x1018 #define RDMA_PROD_INDEX 0x1018 #define RDMA_PROD_INDEX_MASK 0xffff @@ -565,6 +566,7 @@ struct bcm_sysport_mib { u32 rxchk_other_pkt_disc; u32 rbuf_ovflow_cnt; u32 rbuf_err_cnt; + u32 rdma_ovflow_cnt; u32 alloc_rx_buff_failed; u32 rx_dma_failed; u32 tx_dma_failed; @@ -581,6 +583,7 @@ enum bcm_sysport_stat_type { BCM_SYSPORT_STAT_RUNT, BCM_SYSPORT_STAT_RXCHK, BCM_SYSPORT_STAT_RBUF, + BCM_SYSPORT_STAT_RDMA, BCM_SYSPORT_STAT_SOFT, }; @@ -627,6 +630,14 @@ enum bcm_sysport_stat_type { .reg_offset = ofs, \ } +#define STAT_RDMA(str, m, ofs) { \ + .stat_string = str, \ + .stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \ + .stat_offset = offsetof(struct bcm_sysport_priv, m), \ + .type = BCM_SYSPORT_STAT_RDMA, \ + .reg_offset = ofs, \ +} + /* TX bytes and packets */ #define NUM_SYSPORT_TXQ_STAT 2 diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index fec57f1982c8..9f473854b0f4 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -3045,7 +3045,7 @@ error: dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size, DMA_FROM_DEVICE); - skb = build_skb(data, 0); + skb = slab_build_skb(data); if (!skb) { kfree(data); goto error; @@ -5415,8 +5415,9 @@ bnx2_set_rx_ring_size(struct bnx2 *bp, u32 size) bp->rx_buf_use_size = rx_size; /* hw alignment + build_skb() overhead*/ - bp->rx_buf_size = SKB_DATA_ALIGN(bp->rx_buf_use_size + BNX2_RX_ALIGN) + - NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + bp->rx_buf_size = kmalloc_size_roundup( + SKB_DATA_ALIGN(bp->rx_buf_use_size + BNX2_RX_ALIGN) + + NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); bp->rx_jumbo_thresh = rx_size - BNX2_RX_OFFSET; bp->rx_ring_size = size; bp->rx_max_ring = bnx2_find_max_ring(size, BNX2_MAX_RX_RINGS); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 51b1690fd045..5d1e4fe335aa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13671,19 +13671,20 @@ static int bnx2x_send_update_drift_ramrod(struct bnx2x *bp, int drift_dir, return bnx2x_func_state_change(bp, &func_params); } -static int bnx2x_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int bnx2x_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); int rc; int drift_dir = 1; int val, period, period1, period2, dif, dif1, dif2; int best_dif = BNX2X_MAX_PHC_DRIFT, best_period = 0, best_val = 0; + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); - DP(BNX2X_MSG_PTP, "PTP adjfreq called, ppb = %d\n", ppb); + DP(BNX2X_MSG_PTP, "PTP adjfine called, ppb = %d\n", ppb); if (!netif_running(bp->dev)) { DP(BNX2X_MSG_PTP, - "PTP adjfreq called while the interface is down\n"); + "PTP adjfine called while the interface is down\n"); return -ENETDOWN; } @@ -13818,7 +13819,7 @@ void bnx2x_register_phc(struct bnx2x *bp) bp->ptp_clock_info.n_ext_ts = 0; bp->ptp_clock_info.n_per_out = 0; bp->ptp_clock_info.pps = 0; - bp->ptp_clock_info.adjfreq = bnx2x_ptp_adjfreq; + bp->ptp_clock_info.adjfine = bnx2x_ptp_adjfine; bp->ptp_clock_info.adjtime = bnx2x_ptp_adjtime; bp->ptp_clock_info.gettime64 = bnx2x_ptp_gettime; bp->ptp_clock_info.settime64 = bnx2x_ptp_settime; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9f8a6ce4b356..4c7d07c684c4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -389,6 +389,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto tx_free; + length = skb->len; len = skb_headlen(skb); last_frag = skb_shinfo(skb)->nr_frags; @@ -5250,7 +5253,7 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) return 1; } -static void __bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) { bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); u16 i, j; @@ -5263,8 +5266,8 @@ static void __bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) } } -static void __bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, - struct bnxt_vnic_info *vnic) +static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, + struct bnxt_vnic_info *vnic) { __le16 *ring_tbl = vnic->rss_table; struct bnxt_rx_ring_info *rxr; @@ -5285,12 +5288,27 @@ static void __bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, } } -static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +static void +__bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req, + struct bnxt_vnic_info *vnic) { if (bp->flags & BNXT_FLAG_CHIP_P5) - __bnxt_fill_hw_rss_tbl_p5(bp, vnic); + bnxt_fill_hw_rss_tbl_p5(bp, vnic); else - __bnxt_fill_hw_rss_tbl(bp, vnic); + bnxt_fill_hw_rss_tbl(bp, vnic); + + if (bp->rss_hash_delta) { + req->hash_type = cpu_to_le32(bp->rss_hash_delta); + if (bp->rss_hash_cfg & bp->rss_hash_delta) + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE; + else + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE; + } else { + req->hash_type = cpu_to_le32(bp->rss_hash_cfg); + } + req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; + req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); + req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); } static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) @@ -5307,14 +5325,8 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) if (rc) return rc; - if (set_rss) { - bnxt_fill_hw_rss_tbl(bp, vnic); - req->hash_type = cpu_to_le32(bp->rss_hash_cfg); - req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); - req->hash_key_tbl_addr = - cpu_to_le64(vnic->rss_hash_key_dma_addr); - } + if (set_rss) + __bnxt_hwrm_vnic_set_rss(bp, req, vnic); req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); return hwrm_req_send(bp, req); } @@ -5335,10 +5347,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss) if (!set_rss) return hwrm_req_send(bp, req); - bnxt_fill_hw_rss_tbl(bp, vnic); - req->hash_type = cpu_to_le32(bp->rss_hash_cfg); - req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); + __bnxt_hwrm_vnic_set_rss(bp, req, vnic); ring_tbl_map = vnic->rss_table_dma_addr; nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); @@ -5357,6 +5366,25 @@ exit: return rc; } +static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp) +{ + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; + struct hwrm_vnic_rss_qcfg_output *resp; + struct hwrm_vnic_rss_qcfg_input *req; + + if (hwrm_req_init(bp, req, HWRM_VNIC_RSS_QCFG)) + return; + + /* all contexts configured to same hash_type, zero always exists */ + req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); + resp = hwrm_req_hold(bp, req); + if (!hwrm_req_send(bp, req)) { + bp->rss_hash_cfg = le32_to_cpu(resp->hash_type) ?: bp->rss_hash_cfg; + bp->rss_hash_delta = 0; + } + hwrm_req_drop(bp, req); +} + static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; @@ -5614,6 +5642,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) (BNXT_CHIP_P5_THOR(bp) && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED))) bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP; + if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP) + bp->fw_cap |= BNXT_FW_CAP_RSS_HASH_TYPE_DELTA; bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported); if (bp->max_tpa_v2) { if (BNXT_CHIP_P5_THOR(bp)) @@ -6958,8 +6988,11 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED) bp->fw_cap |= BNXT_FW_CAP_DCBX_AGENT; } - if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) + if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) { bp->flags |= BNXT_FLAG_MULTI_HOST; + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + bp->fw_cap &= ~BNXT_FW_CAP_PTP_RTC; + } if (flags & FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED) bp->fw_cap |= BNXT_FW_CAP_RING_MONITOR; @@ -8808,6 +8841,8 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) rc = bnxt_setup_vnic(bp, 0); if (rc) goto err_out; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bnxt_hwrm_update_rss_hash_cfg(bp); if (bp->flags & BNXT_FLAG_RFS) { rc = bnxt_alloc_rfs_vnics(bp); @@ -11283,6 +11318,7 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off, u8 **nextp) { struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off); + struct hop_jumbo_hdr *jhdr; int hdr_count = 0; u8 *nexthdr; int start; @@ -11310,9 +11346,27 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off, if (hdrlen > 64) return false; + + /* The ext header may be a hop-by-hop header inserted for + * big TCP purposes. This will be removed before sending + * from NIC, so do not count it. + */ + if (*nexthdr == NEXTHDR_HOP) { + if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) + goto increment_hdr; + + jhdr = (struct hop_jumbo_hdr *)hp; + if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || + jhdr->nexthdr != IPPROTO_TCP) + goto increment_hdr; + + goto next_hdr; + } +increment_hdr: + hdr_count++; +next_hdr: nexthdr = &hp->nexthdr; start += hdrlen; - hdr_count++; } if (nextp) { /* Caller will check inner protocol */ @@ -12252,6 +12306,8 @@ static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp) VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 | VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 | VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bp->rss_hash_delta = bp->rss_hash_cfg; if (BNXT_CHIP_P4_PLUS(bp) && bp->hwrm_spec_code >= 0x10501) { bp->flags |= BNXT_FLAG_UDP_RSS_CAP; bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 | @@ -13082,13 +13138,6 @@ int bnxt_get_port_parent_id(struct net_device *dev, return 0; } -static struct devlink_port *bnxt_get_devlink_port(struct net_device *dev) -{ - struct bnxt *bp = netdev_priv(dev); - - return &bp->dl_port; -} - static const struct net_device_ops bnxt_netdev_ops = { .ndo_open = bnxt_open, .ndo_start_xmit = bnxt_start_xmit, @@ -13120,7 +13169,6 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_xdp_xmit = bnxt_xdp_xmit, .ndo_bridge_getlink = bnxt_bridge_getlink, .ndo_bridge_setlink = bnxt_bridge_setlink, - .ndo_get_devlink_port = bnxt_get_devlink_port, }; static void bnxt_remove_one(struct pci_dev *pdev) @@ -13131,9 +13179,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); - if (BNXT_PF(bp)) - devlink_port_type_clear(&bp->dl_port); - bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); @@ -13546,6 +13591,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENOMEM; bp = netdev_priv(dev); + SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port); bp->board_idx = ent->driver_data; bp->msg_enable = BNXT_DEF_MSG_ENABLE; bnxt_set_max_func_irqs(bp, max_irqs); @@ -13633,6 +13679,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->features &= ~NETIF_F_LRO; dev->priv_flags |= IFF_UNICAST_FLT; + netif_set_tso_max_size(dev, GSO_MAX_SIZE); + #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); #endif @@ -13721,8 +13769,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_cleanup; - if (BNXT_PF(bp)) - devlink_port_type_eth_set(&bp->dl_port, bp->dev); bnxt_dl_fw_reporters_create(bp); bnxt_print_device_info(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index d5fa43cfe524..41c6dd0ae447 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1901,6 +1901,7 @@ struct bnxt { u16 *rss_indir_tbl; u16 rss_indir_tbl_entries; u32 rss_hash_cfg; + u32 rss_hash_delta; u16 max_mtu; u8 max_tc; @@ -1966,6 +1967,7 @@ struct bnxt { #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2 0x00010000 #define BNXT_FW_CAP_PCIE_STATS_SUPPORTED 0x00020000 #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 + #define BNXT_FW_CAP_RSS_HASH_TYPE_DELTA 0x00080000 #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_FW_CAP_HOT_RESET 0x00200000 #define BNXT_FW_CAP_PTP_RTC 0x00400000 @@ -2117,6 +2119,7 @@ struct bnxt { #define BNXT_PHY_FL_NO_FCS PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS #define BNXT_PHY_FL_NO_PAUSE (PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED << 8) #define BNXT_PHY_FL_NO_PFC (PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED << 8) +#define BNXT_PHY_FL_BANK_SEL (PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED << 8) u8 num_tests; struct bnxt_test_info *test_info; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 8a6f788f6294..26913dc816d3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -892,10 +892,6 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, u32 ver = 0; int rc; - rc = devlink_info_driver_name_put(req, DRV_MODULE_NAME); - if (rc) - return rc; - if (BNXT_PF(bp) && (bp->flags & BNXT_FLAG_DSN_VALID)) { sprintf(buf, "%02X-%02X-%02X-%02X-%02X-%02X-%02X-%02X", bp->dsn[7], bp->dsn[6], bp->dsn[5], bp->dsn[4], diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8cad15c458b3..cbf17fcfb7ab 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1234,6 +1234,8 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) if (bp->rss_hash_cfg == rss_hash_cfg) return 0; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bp->rss_hash_delta = bp->rss_hash_cfg ^ rss_hash_cfg; bp->rss_hash_cfg = rss_hash_cfg; if (netif_running(bp->dev)) { bnxt_close_nic(bp, false, false); @@ -2005,6 +2007,14 @@ static void bnxt_get_fec_stats(struct net_device *dev, rx = bp->rx_port_stats_ext.sw_stats; fec_stats->corrected_bits.total = *(rx + BNXT_RX_STATS_EXT_OFFSET(rx_corrected_bits)); + + if (bp->fw_rx_stats_ext_size <= BNXT_RX_STATS_EXT_NUM_LEGACY) + return; + + fec_stats->corrected_blocks.total = + *(rx + BNXT_RX_STATS_EXT_OFFSET(rx_fec_corrected_blocks)); + fec_stats->uncorrectable_blocks.total = + *(rx + BNXT_RX_STATS_EXT_OFFSET(rx_fec_uncorrectable_blocks)); } static u32 bnxt_ethtool_forced_fec_to_fw(struct bnxt_link_info *link_info, @@ -2514,6 +2524,7 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev, #define MSG_INTERNAL_ERR "PKG install error : Internal error" #define MSG_NO_PKG_UPDATE_AREA_ERR "PKG update area not created in nvram" #define MSG_NO_SPACE_ERR "PKG insufficient update area in nvram" +#define MSG_RESIZE_UPDATE_ERR "Resize UPDATE entry error" #define MSG_ANTI_ROLLBACK_ERR "HWRM_NVM_INSTALL_UPDATE failure due to Anti-rollback detected" #define MSG_GENERIC_FAILURE_ERR "HWRM_NVM_INSTALL_UPDATE failure" @@ -2564,6 +2575,32 @@ static int nvm_update_err_to_stderr(struct net_device *dev, u8 result, #define BNXT_NVM_MORE_FLAG (cpu_to_le16(NVM_MODIFY_REQ_FLAGS_BATCH_MODE)) #define BNXT_NVM_LAST_FLAG (cpu_to_le16(NVM_MODIFY_REQ_FLAGS_BATCH_LAST)) +static int bnxt_resize_update_entry(struct net_device *dev, size_t fw_size, + struct netlink_ext_ack *extack) +{ + u32 item_len; + int rc; + + rc = bnxt_find_nvram_item(dev, BNX_DIR_TYPE_UPDATE, + BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, NULL, + &item_len, NULL); + if (rc) { + BNXT_NVM_ERR_MSG(dev, extack, MSG_NO_PKG_UPDATE_AREA_ERR); + return rc; + } + + if (fw_size > item_len) { + rc = bnxt_flash_nvram(dev, BNX_DIR_TYPE_UPDATE, + BNX_DIR_ORDINAL_FIRST, 0, 1, + round_up(fw_size, 4096), NULL, 0); + if (rc) { + BNXT_NVM_ERR_MSG(dev, extack, MSG_RESIZE_UPDATE_ERR); + return rc; + } + } + return 0; +} + int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw, u32 install_type, struct netlink_ext_ack *extack) { @@ -2580,6 +2617,11 @@ int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware u16 index; int rc; + /* resize before flashing larger image than available space */ + rc = bnxt_resize_update_entry(dev, fw->size, extack); + if (rc) + return rc; + bnxt_hwrm_fw_set_time(bp); rc = hwrm_req_init(bp, modify, HWRM_NVM_MODIFY); @@ -3146,8 +3188,9 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_eee *edata) } static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr, - u16 page_number, u16 start_addr, - u16 data_length, u8 *buf) + u16 page_number, u8 bank, + u16 start_addr, u16 data_length, + u8 *buf) { struct hwrm_port_phy_i2c_read_output *output; struct hwrm_port_phy_i2c_read_input *req; @@ -3168,8 +3211,13 @@ static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr, data_length -= xfer_size; req->page_offset = cpu_to_le16(start_addr + byte_offset); req->data_length = xfer_size; - req->enables = cpu_to_le32(start_addr + byte_offset ? - PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET : 0); + req->enables = + cpu_to_le32((start_addr + byte_offset ? + PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET : + 0) | + (bank ? + PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER : + 0)); rc = hwrm_req_send(bp, req); if (!rc) memcpy(buf + byte_offset, output->data, xfer_size); @@ -3199,7 +3247,7 @@ static int bnxt_get_module_info(struct net_device *dev, if (bp->hwrm_spec_code < 0x10202) return -EOPNOTSUPP; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, 0, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, 0, 0, SFF_DIAG_SUPPORT_OFFSET + 1, data); if (!rc) { @@ -3244,7 +3292,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, if (start < ETH_MODULE_SFF_8436_LEN) { if (start + eeprom->len > ETH_MODULE_SFF_8436_LEN) length = ETH_MODULE_SFF_8436_LEN - start; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, 0, start, length, data); if (rc) return rc; @@ -3256,12 +3304,68 @@ static int bnxt_get_module_eeprom(struct net_device *dev, /* Read A2 portion of the EEPROM */ if (length) { start -= ETH_MODULE_SFF_8436_LEN; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0, 0, start, length, data); } return rc; } +static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extack) +{ + if (bp->link_info.module_status <= + PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG) + return 0; + + switch (bp->link_info.module_status) { + case PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN: + NL_SET_ERR_MSG_MOD(extack, "Transceiver module is powering down"); + break; + case PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED: + NL_SET_ERR_MSG_MOD(extack, "Transceiver module not inserted"); + break; + case PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT: + NL_SET_ERR_MSG_MOD(extack, "Transceiver module disabled due to current fault"); + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown error"); + break; + } + return -EINVAL; +} + +static int bnxt_get_module_eeprom_by_page(struct net_device *dev, + const struct ethtool_module_eeprom *page_data, + struct netlink_ext_ack *extack) +{ + struct bnxt *bp = netdev_priv(dev); + int rc; + + rc = bnxt_get_module_status(bp, extack); + if (rc) + return rc; + + if (bp->hwrm_spec_code < 0x10202) { + NL_SET_ERR_MSG_MOD(extack, "Firmware version too old"); + return -EINVAL; + } + + if (page_data->bank && !(bp->phy_flags & BNXT_PHY_FL_BANK_SEL)) { + NL_SET_ERR_MSG_MOD(extack, "Firmware not capable for bank selection"); + return -EINVAL; + } + + rc = bnxt_read_sfp_module_eeprom_info(bp, page_data->i2c_address << 1, + page_data->page, page_data->bank, + page_data->offset, + page_data->length, + page_data->data); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Module`s eeprom read failed"); + return rc; + } + return page_data->length; +} + static int bnxt_nway_reset(struct net_device *dev) { int rc = 0; @@ -4018,6 +4122,20 @@ static void bnxt_get_rmon_stats(struct net_device *dev, *ranges = bnxt_rmon_ranges; } +static void bnxt_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats) +{ + struct bnxt *bp = netdev_priv(dev); + u64 *rx; + + if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) + return; + + rx = bp->rx_port_stats_ext.sw_stats; + stats->link_down_events = + *(rx + BNXT_RX_STATS_EXT_OFFSET(link_down_events)); +} + void bnxt_ethtool_free(struct bnxt *bp) { kfree(bp->test_info); @@ -4067,10 +4185,12 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_eeprom = bnxt_get_eeprom, .set_eeprom = bnxt_set_eeprom, .get_link = bnxt_get_link, + .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, .get_module_info = bnxt_get_module_info, .get_module_eeprom = bnxt_get_module_eeprom, + .get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page, .nway_reset = bnxt_nway_reset, .set_phys_id = bnxt_set_phys_id, .self_test = bnxt_self_test, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index b753032a1047..2686a714a59f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -254,6 +254,8 @@ struct cmd_nums { #define HWRM_PORT_DSC_DUMP 0xd9UL #define HWRM_PORT_EP_TX_QCFG 0xdaUL #define HWRM_PORT_EP_TX_CFG 0xdbUL + #define HWRM_PORT_CFG 0xdcUL + #define HWRM_PORT_QCFG 0xddUL #define HWRM_TEMP_MONITOR_QUERY 0xe0UL #define HWRM_REG_POWER_QUERY 0xe1UL #define HWRM_CORE_FREQUENCY_QUERY 0xe2UL @@ -379,6 +381,8 @@ struct cmd_nums { #define HWRM_FUNC_BACKING_STORE_QCAPS_V2 0x1a8UL #define HWRM_FUNC_DBR_PACING_NQLIST_QUERY 0x1a9UL #define HWRM_FUNC_DBR_RECOVERY_COMPLETED 0x1aaUL + #define HWRM_FUNC_SYNCE_CFG 0x1abUL + #define HWRM_FUNC_SYNCE_QCFG 0x1acUL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -417,6 +421,8 @@ struct cmd_nums { #define HWRM_TF_SESSION_RESC_FREE 0x2ceUL #define HWRM_TF_SESSION_RESC_FLUSH 0x2cfUL #define HWRM_TF_SESSION_RESC_INFO 0x2d0UL + #define HWRM_TF_SESSION_HOTUP_STATE_SET 0x2d1UL + #define HWRM_TF_SESSION_HOTUP_STATE_GET 0x2d2UL #define HWRM_TF_TBL_TYPE_GET 0x2daUL #define HWRM_TF_TBL_TYPE_SET 0x2dbUL #define HWRM_TF_TBL_TYPE_BULK_GET 0x2dcUL @@ -440,6 +446,25 @@ struct cmd_nums { #define HWRM_TF_GLOBAL_CFG_GET 0x2fdUL #define HWRM_TF_IF_TBL_SET 0x2feUL #define HWRM_TF_IF_TBL_GET 0x2ffUL + #define HWRM_TFC_TBL_SCOPE_QCAPS 0x380UL + #define HWRM_TFC_TBL_SCOPE_ID_ALLOC 0x381UL + #define HWRM_TFC_TBL_SCOPE_CONFIG 0x382UL + #define HWRM_TFC_TBL_SCOPE_DECONFIG 0x383UL + #define HWRM_TFC_TBL_SCOPE_FID_ADD 0x384UL + #define HWRM_TFC_TBL_SCOPE_FID_REM 0x385UL + #define HWRM_TFC_TBL_SCOPE_POOL_ALLOC 0x386UL + #define HWRM_TFC_TBL_SCOPE_POOL_FREE 0x387UL + #define HWRM_TFC_SESSION_ID_ALLOC 0x388UL + #define HWRM_TFC_SESSION_FID_ADD 0x389UL + #define HWRM_TFC_SESSION_FID_REM 0x38aUL + #define HWRM_TFC_IDENT_ALLOC 0x38bUL + #define HWRM_TFC_IDENT_FREE 0x38cUL + #define HWRM_TFC_IDX_TBL_ALLOC 0x38dUL + #define HWRM_TFC_IDX_TBL_ALLOC_SET 0x38eUL + #define HWRM_TFC_IDX_TBL_SET 0x38fUL + #define HWRM_TFC_IDX_TBL_GET 0x390UL + #define HWRM_TFC_IDX_TBL_FREE 0x391UL + #define HWRM_TFC_GLOBAL_ID_ALLOC 0x392UL #define HWRM_SV 0x400UL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL @@ -546,8 +571,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 95 -#define HWRM_VERSION_STR "1.10.2.95" +#define HWRM_VERSION_RSVD 118 +#define HWRM_VERSION_STR "1.10.2.118" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -1657,6 +1682,10 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED 0x8UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED 0x10UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED 0x20UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED 0x40UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED 0x80UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED 0x100UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED 0x200UL __le16 tunnel_disable_flag; #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN 0x1UL #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE 0x2UL @@ -1804,7 +1833,20 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED 0x4UL #define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED 0x8UL #define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED 0x10UL - u8 unused_2[3]; + u8 db_page_size; + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_4KB 0x0UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_8KB 0x1UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_16KB 0x2UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_32KB 0x3UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_64KB 0x4UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_128KB 0x5UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_256KB 0x6UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_512KB 0x7UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_1MB 0x8UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB 0x9UL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB 0xaUL + #define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB + u8 unused_2[2]; __le32 partition_min_bw; #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK 0xfffffffUL #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT 0 @@ -1876,6 +1918,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE 0x10000000UL #define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE 0x20000000UL #define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE 0x40000000UL + #define FUNC_CFG_REQ_FLAGS_KEY_CTX_ASSETS_TEST 0x80000000UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_ADMIN_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -2021,12 +2064,26 @@ struct hwrm_func_cfg_input { __le16 num_tx_key_ctxs; __le16 num_rx_key_ctxs; __le32 enables2; - #define FUNC_CFG_REQ_ENABLES2_KDNET 0x1UL + #define FUNC_CFG_REQ_ENABLES2_KDNET 0x1UL + #define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE 0x2UL u8 port_kdnet_mode; #define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL #define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED 0x1UL #define FUNC_CFG_REQ_PORT_KDNET_MODE_LAST FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED - u8 unused_0[7]; + u8 db_page_size; + #define FUNC_CFG_REQ_DB_PAGE_SIZE_4KB 0x0UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_8KB 0x1UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_16KB 0x2UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_32KB 0x3UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_64KB 0x4UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_128KB 0x5UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_256KB 0x6UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_512KB 0x7UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_1MB 0x8UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_2MB 0x9UL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_4MB 0xaUL + #define FUNC_CFG_REQ_DB_PAGE_SIZE_LAST FUNC_CFG_REQ_DB_PAGE_SIZE_4MB + u8 unused_0[6]; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -2060,10 +2117,9 @@ struct hwrm_func_qstats_input { __le64 resp_addr; __le16 fid; u8 flags; - #define FUNC_QSTATS_REQ_FLAGS_UNUSED 0x0UL - #define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY 0x1UL - #define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK 0x2UL - #define FUNC_QSTATS_REQ_FLAGS_LAST FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK + #define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY 0x1UL + #define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK 0x2UL + #define FUNC_QSTATS_REQ_FLAGS_L2_ONLY 0x4UL u8 unused_0[5]; }; @@ -2093,7 +2149,8 @@ struct hwrm_func_qstats_output { __le64 rx_agg_bytes; __le64 rx_agg_events; __le64 rx_agg_aborts; - u8 unused_0[7]; + u8 clear_seq; + u8 unused_0[6]; u8 valid; }; @@ -2106,10 +2163,8 @@ struct hwrm_func_qstats_ext_input { __le64 resp_addr; __le16 fid; u8 flags; - #define FUNC_QSTATS_EXT_REQ_FLAGS_UNUSED 0x0UL - #define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY 0x1UL - #define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x2UL - #define FUNC_QSTATS_EXT_REQ_FLAGS_LAST FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK + #define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY 0x1UL + #define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x2UL u8 unused_0[1]; __le32 enables; #define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID 0x1UL @@ -2210,6 +2265,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT 0x80UL #define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT 0x100UL #define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT 0x200UL + #define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT 0x400UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -3155,19 +3211,23 @@ struct hwrm_func_ptp_pin_qcfg_output { #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT u8 pin2_usage; - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE 0x0UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN 0x1UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT 0x2UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN 0x3UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT 0x4UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT 0x5UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT u8 pin3_usage; - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE 0x0UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN 0x1UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT 0x2UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN 0x3UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT 0x4UL - #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT 0x5UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT u8 unused_0; u8 valid; }; @@ -3215,23 +3275,27 @@ struct hwrm_func_ptp_pin_cfg_input { #define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED 0x1UL #define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED u8 pin2_usage; - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE 0x0UL - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN 0x1UL - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT 0x2UL - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN 0x3UL - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT 0x4UL - #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT 0x5UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT u8 pin3_state; #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED 0x1UL #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED u8 pin3_usage; - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE 0x0UL - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN 0x1UL - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT 0x2UL - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN 0x3UL - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT 0x4UL - #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT 0x5UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT u8 unused_0[4]; }; @@ -3319,9 +3383,9 @@ struct hwrm_func_ptp_ts_query_output { __le16 seq_id; __le16 resp_len; __le64 pps_event_ts; - __le64 ptm_res_local_ts; - __le64 ptm_pmstr_ts; - __le32 ptm_mstr_prop_dly; + __le64 ptm_local_ts; + __le64 ptm_system_ts; + __le32 ptm_link_delay; u8 unused_0[3]; u8 valid; }; @@ -3417,7 +3481,9 @@ struct hwrm_func_backing_store_cfg_v2_input { #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID __le16 instance; __le32 flags; - #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_EXTEND 0x4UL __le64 page_dir; __le32 num_entries; __le16 entry_size; @@ -3853,7 +3919,7 @@ struct hwrm_port_phy_qcfg_input { u8 unused_0[6]; }; -/* hwrm_port_phy_qcfg_output (size:768b/96B) */ +/* hwrm_port_phy_qcfg_output (size:832b/104B) */ struct hwrm_port_phy_qcfg_output { __le16 error_code; __le16 req_type; @@ -4150,6 +4216,9 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB 0x1UL #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB 0x2UL #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB 0x4UL + u8 link_down_reason; + #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF 0x1UL + u8 unused_0[7]; u8 valid; }; @@ -4422,9 +4491,7 @@ struct hwrm_port_qstats_input { __le64 resp_addr; __le16 port_id; u8 flags; - #define PORT_QSTATS_REQ_FLAGS_UNUSED 0x0UL - #define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL - #define PORT_QSTATS_REQ_FLAGS_LAST PORT_QSTATS_REQ_FLAGS_COUNTER_MASK + #define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL u8 unused_0[5]; __le64 tx_stat_host_addr; __le64 rx_stat_host_addr; @@ -4552,9 +4619,7 @@ struct hwrm_port_qstats_ext_input { __le16 tx_stat_size; __le16 rx_stat_size; u8 flags; - #define PORT_QSTATS_EXT_REQ_FLAGS_UNUSED 0x0UL - #define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x1UL - #define PORT_QSTATS_EXT_REQ_FLAGS_LAST PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK + #define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x1UL u8 unused_0; __le64 tx_stat_host_addr; __le64 rx_stat_host_addr; @@ -4613,9 +4678,7 @@ struct hwrm_port_ecn_qstats_input { __le16 port_id; __le16 ecn_stat_buf_size; u8 flags; - #define PORT_ECN_QSTATS_REQ_FLAGS_UNUSED 0x0UL - #define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL - #define PORT_ECN_QSTATS_REQ_FLAGS_LAST PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK + #define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL u8 unused_0[3]; __le64 ecn_stat_host_addr; }; @@ -4814,8 +4877,9 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G 0x2UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G 0x4UL __le16 flags2; - #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED 0x4UL u8 internal_port_cnt; u8 valid; }; @@ -4830,9 +4894,10 @@ struct hwrm_port_phy_i2c_read_input { __le32 flags; __le32 enables; #define PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET 0x1UL + #define PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER 0x2UL __le16 port_id; u8 i2c_slave_addr; - u8 unused_0; + u8 bank_number; __le16 page_number; __le16 page_offset; u8 data_length; @@ -6537,6 +6602,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP 0x400000UL #define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP 0x800000UL #define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP 0x1000000UL + #define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_TRUSTED_VF_CAP 0x2000000UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -6702,6 +6768,53 @@ struct hwrm_vnic_rss_cfg_cmd_err { u8 unused_0[7]; }; +/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */ +struct hwrm_vnic_rss_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 rss_ctx_idx; + __le16 vnic_id; + u8 unused_0[4]; +}; + +/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */ +struct hwrm_vnic_rss_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 hash_type; + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4 0x1UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4 0x2UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4 0x4UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6 0x8UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6 0x10UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL 0x40UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4 0x80UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4 0x100UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6 0x200UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6 0x400UL + u8 unused_0[4]; + __le32 hash_key[10]; + u8 hash_mode_flags; + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT 0x1UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4 0x2UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2 0x4UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4 0x8UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2 0x10UL + u8 ring_select_mode; + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ 0x0UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR 0x1UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM + u8 unused_1[5]; + u8 valid; +}; + /* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */ struct hwrm_vnic_plcmodes_cfg_input { __le16 req_type; @@ -6827,6 +6940,7 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD 0x1UL #define RING_ALLOC_REQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION 0x2UL #define RING_ALLOC_REQ_FLAGS_NQ_DBR_PACING 0x4UL + #define RING_ALLOC_REQ_FLAGS_TX_PKT_TS_CMPL_ENABLE 0x8UL __le64 page_tbl_addr; __le32 fbo; u8 page_size; @@ -7626,7 +7740,10 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP 0x6UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP 0x11UL - #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMP 0x1UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMPV6 0x3aUL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD 0xffUL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD __le16 dst_id; __le16 mirror_vnic_id; u8 tunnel_type; @@ -8337,6 +8454,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output { #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED 0x20000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED 0x40000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED 0x80000UL + #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED 0x100000UL u8 unused_0[3]; u8 valid; }; @@ -8355,7 +8473,9 @@ struct hwrm_tunnel_dst_port_query_input { #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI u8 unused_0[7]; }; @@ -8367,7 +8487,16 @@ struct hwrm_tunnel_dst_port_query_output { __le16 resp_len; __le16 tunnel_dst_port_id; __be16 tunnel_dst_port_val; - u8 unused_0[3]; + u8 upar_in_use; + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR0 0x1UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR1 0x2UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR2 0x4UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR3 0x8UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR4 0x10UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5 0x20UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6 0x40UL + #define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7 0x80UL + u8 unused_0[2]; u8 valid; }; @@ -8385,7 +8514,9 @@ struct hwrm_tunnel_dst_port_alloc_input { #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI u8 unused_0; __be16 tunnel_dst_port_val; u8 unused_1[4]; @@ -8398,7 +8529,21 @@ struct hwrm_tunnel_dst_port_alloc_output { __le16 seq_id; __le16 resp_len; __le16 tunnel_dst_port_id; - u8 unused_0[5]; + u8 error_info; + #define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS 0x0UL + #define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED 0x1UL + #define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL + #define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE + u8 upar_in_use; + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0 0x1UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1 0x2UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR2 0x4UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR3 0x8UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR4 0x10UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR5 0x20UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR6 0x40UL + #define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR7 0x80UL + u8 unused_0[3]; u8 valid; }; @@ -8416,7 +8561,9 @@ struct hwrm_tunnel_dst_port_free_input { #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI u8 unused_0; __le16 tunnel_dst_port_id; u8 unused_1[4]; @@ -8428,7 +8575,12 @@ struct hwrm_tunnel_dst_port_free_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - u8 unused_1[7]; + u8 error_info; + #define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_SUCCESS 0x0UL + #define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_OWNER 0x1UL + #define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED 0x2UL + #define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_LAST TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED + u8 unused_1[6]; u8 valid; }; @@ -8686,9 +8838,7 @@ struct hwrm_stat_generic_qstats_input { __le64 resp_addr; __le16 generic_stat_size; u8 flags; - #define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER 0x0UL - #define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL - #define STAT_GENERIC_QSTATS_REQ_FLAGS_LAST STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK + #define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL u8 unused_0[5]; __le64 generic_stat_host_addr; }; @@ -10202,6 +10352,7 @@ struct fw_status_reg { #define FW_STATUS_REG_SHUTDOWN 0x100000UL #define FW_STATUS_REG_CRASHED_NO_MASTER 0x200000UL #define FW_STATUS_REG_RECOVERING 0x400000UL + #define FW_STATUS_REG_MANU_DEBUG_STATUS 0x800000UL }; /* hcomm_status (size:64b/8B) */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 2132ce63193c..4ec8bba18cdd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -14,6 +14,7 @@ #include <linux/net_tstamp.h> #include <linux/timekeeping.h> #include <linux/ptp_classify.h> +#include <linux/clocksource.h> #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" @@ -204,24 +205,33 @@ static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) return 0; } -static int bnxt_ptp_adjfreq(struct ptp_clock_info *ptp_info, s32 ppb) +static int bnxt_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) { struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, ptp_info); struct hwrm_port_mac_cfg_input *req; struct bnxt *bp = ptp->bp; - int rc; + int rc = 0; - rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG); - if (rc) - return rc; + if (!(ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) { + spin_lock_bh(&ptp->ptp_lock); + timecounter_read(&ptp->tc); + ptp->cc.mult = adjust_by_scaled_ppm(ptp->cmult, scaled_ppm); + spin_unlock_bh(&ptp->ptp_lock); + } else { + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); - req->ptp_freq_adj_ppb = cpu_to_le32(ppb); - req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB); - rc = hwrm_req_send(ptp->bp, req); - if (rc) - netdev_err(ptp->bp->dev, - "ptp adjfreq failed. rc = %d\n", rc); + rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG); + if (rc) + return rc; + + req->ptp_freq_adj_ppb = cpu_to_le32(ppb); + req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB); + rc = hwrm_req_send(ptp->bp, req); + if (rc) + netdev_err(ptp->bp->dev, + "ptp adjfine failed. rc = %d\n", rc); + } return rc; } @@ -749,7 +759,7 @@ static const struct ptp_clock_info bnxt_ptp_caps = { .n_per_out = 0, .n_pins = 0, .pps = 0, - .adjfreq = bnxt_ptp_adjfreq, + .adjfine = bnxt_ptp_adjfine, .adjtime = bnxt_ptp_adjtime, .do_aux_work = bnxt_ptp_ts_aux_work, .gettimex64 = bnxt_ptp_gettimex, @@ -846,8 +856,9 @@ static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) memset(&ptp->cc, 0, sizeof(ptp->cc)); ptp->cc.read = bnxt_cc_read; ptp->cc.mask = CYCLECOUNTER_MASK(48); - ptp->cc.shift = 0; - ptp->cc.mult = 1; + ptp->cc.shift = BNXT_CYCLES_SHIFT; + ptp->cc.mult = clocksource_khz2mult(BNXT_DEVCLK_FREQ, ptp->cc.shift); + ptp->cmult = ptp->cc.mult; ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; } if (init_tc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 4ce0a14c1e23..34162e07a119 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -17,6 +17,8 @@ #define BNXT_PTP_GRC_WIN_BASE 0x6000 #define BNXT_MAX_PHC_DRIFT 31000000 +#define BNXT_CYCLES_SHIFT 23 +#define BNXT_DEVCLK_FREQ 1000000 #define BNXT_LO_TIMER_MASK 0x0000ffffffffUL #define BNXT_HI_TIMER_MASK 0xffff00000000UL @@ -88,8 +90,9 @@ struct bnxt_ptp_cfg { u64 old_time; unsigned long next_period; unsigned long next_overflow_check; - /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */ - #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) + u32 cmult; + /* a 23b shift cyclecounter will overflow in ~36 mins. Check overflow every 18 mins. */ + #define BNXT_PHC_OVERFLOW_PERIOD (18 * 60 * HZ) u16 tx_seqid; u16 tx_hdr_off; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 25c450606985..21973046b12b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -117,24 +117,6 @@ static inline void dmadesc_set(struct bcmgenet_priv *priv, dmadesc_set_length_status(priv, d, val); } -static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv, - void __iomem *d) -{ - dma_addr_t addr; - - addr = bcmgenet_readl(d + DMA_DESC_ADDRESS_LO); - - /* Register writes to GISB bus can take couple hundred nanoseconds - * and are done for each packet, save these expensive writes unless - * the platform is explicitly configured for 64-bits/LPAE. - */ -#ifdef CONFIG_PHYS_ADDR_T_64BIT - if (priv->hw_params->flags & GENET_HAS_40BITS) - addr |= (u64)bcmgenet_readl(d + DMA_DESC_ADDRESS_HI) << 32; -#endif - return addr; -} - #define GENET_VER_FMT "%1d.%1d EPHY: 0x%04x" #define GENET_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \ @@ -1387,7 +1369,8 @@ static int bcmgenet_validate_flow(struct net_device *dev, struct ethtool_usrip4_spec *l4_mask; struct ethhdr *eth_mask; - if (cmd->fs.location >= MAX_NUM_OF_FS_RULES) { + if (cmd->fs.location >= MAX_NUM_OF_FS_RULES && + cmd->fs.location != RX_CLS_LOC_ANY) { netdev_err(dev, "rxnfc: Invalid location (%d)\n", cmd->fs.location); return -EINVAL; @@ -1452,7 +1435,7 @@ static int bcmgenet_insert_flow(struct net_device *dev, { struct bcmgenet_priv *priv = netdev_priv(dev); struct bcmgenet_rxnfc_rule *loc_rule; - int err; + int err, i; if (priv->hw_params->hfb_filter_size < 128) { netdev_err(dev, "rxnfc: Not supported by this device\n"); @@ -1470,7 +1453,29 @@ static int bcmgenet_insert_flow(struct net_device *dev, if (err) return err; - loc_rule = &priv->rxnfc_rules[cmd->fs.location]; + if (cmd->fs.location == RX_CLS_LOC_ANY) { + list_for_each_entry(loc_rule, &priv->rxnfc_list, list) { + cmd->fs.location = loc_rule->fs.location; + err = memcmp(&loc_rule->fs, &cmd->fs, + sizeof(struct ethtool_rx_flow_spec)); + if (!err) + /* rule exists so return current location */ + return 0; + } + for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) { + loc_rule = &priv->rxnfc_rules[i]; + if (loc_rule->state == BCMGENET_RXNFC_STATE_UNUSED) { + cmd->fs.location = i; + break; + } + } + if (i == MAX_NUM_OF_FS_RULES) { + cmd->fs.location = RX_CLS_LOC_ANY; + return -ENOSPC; + } + } else { + loc_rule = &priv->rxnfc_rules[cmd->fs.location]; + } if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED) bcmgenet_hfb_disable_filter(priv, cmd->fs.location); if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) { @@ -1583,7 +1588,7 @@ static int bcmgenet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = bcmgenet_get_num_flows(priv); - cmd->data = MAX_NUM_OF_FS_RULES; + cmd->data = MAX_NUM_OF_FS_RULES | RX_CLS_LOC_SPECIAL; break; case ETHTOOL_GRXCLSRULE: err = bcmgenet_get_flow(dev, cmd, cmd->fs.location); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 7ded559842e8..b615176338b2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -72,7 +72,6 @@ static void bcmgenet_mac_config(struct net_device *dev) * Receive clock is provided by the PHY. */ reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); - reg &= ~OOB_DISABLE; reg |= RGMII_LINK; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); @@ -95,10 +94,18 @@ static void bcmgenet_mac_config(struct net_device *dev) */ void bcmgenet_mii_setup(struct net_device *dev) { + struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; + u32 reg; - if (phydev->link) + if (phydev->link) { bcmgenet_mac_config(dev); + } else { + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~RGMII_LINK; + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + } + phy_print_status(phydev); } @@ -266,18 +273,20 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); /* This is an external PHY (xMII), so we need to enable the RGMII - * block for the interface to work + * block for the interface to work, unconditionally clear the + * Out-of-band disable since we do not need it. */ + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~OOB_DISABLE; if (priv->ext_phy) { - reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); reg &= ~ID_MODE_DIS; reg |= id_mode_dis; if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) reg |= RGMII_MODE_EN_V123; else reg |= RGMII_MODE_EN; - bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); if (init) dev_info(kdev, "configuring instance for %s\n", phy_name); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 4179a12fc881..59debdc344a5 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6179,34 +6179,26 @@ static int tg3_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } -static int tg3_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int tg3_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct tg3 *tp = container_of(ptp, struct tg3, ptp_info); - bool neg_adj = false; - u32 correction = 0; - - if (ppb < 0) { - neg_adj = true; - ppb = -ppb; - } + u64 correction; + bool neg_adj; /* Frequency adjustment is performed using hardware with a 24 bit * accumulator and a programmable correction value. On each clk, the * correction value gets added to the accumulator and when it * overflows, the time counter is incremented/decremented. - * - * So conversion from ppb to correction value is - * ppb * (1 << 24) / 1000000000 */ - correction = div_u64((u64)ppb * (1 << 24), 1000000000ULL) & - TG3_EAV_REF_CLK_CORRECT_MASK; + neg_adj = diff_by_scaled_ppm(1 << 24, scaled_ppm, &correction); tg3_full_lock(tp, 0); if (correction) tw32(TG3_EAV_REF_CLK_CORRECT_CTL, TG3_EAV_REF_CLK_CORRECT_EN | - (neg_adj ? TG3_EAV_REF_CLK_CORRECT_NEG : 0) | correction); + (neg_adj ? TG3_EAV_REF_CLK_CORRECT_NEG : 0) | + ((u32)correction & TG3_EAV_REF_CLK_CORRECT_MASK)); else tw32(TG3_EAV_REF_CLK_CORRECT_CTL, 0); @@ -6330,7 +6322,7 @@ static const struct ptp_clock_info tg3_ptp_caps = { .n_per_out = 1, .n_pins = 0, .pps = 0, - .adjfreq = tg3_ptp_adjfreq, + .adjfine = tg3_ptp_adjfine, .adjtime = tg3_ptp_adjtime, .gettimex64 = tg3_ptp_gettimex, .settime64 = tg3_ptp_settime, diff --git a/drivers/net/ethernet/brocade/bna/bfa_cs.h b/drivers/net/ethernet/brocade/bna/bfa_cs.h index 8f0ac7b99973..858c92129451 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_cs.h +++ b/drivers/net/ethernet/brocade/bna/bfa_cs.h @@ -18,15 +18,43 @@ /* BFA state machine interfaces */ -typedef void (*bfa_sm_t)(void *sm, int event); - /* For converting from state machine function to state encoding. */ -struct bfa_sm_table { - bfa_sm_t sm; /*!< state machine function */ - int state; /*!< state machine encoding */ - char *name; /*!< state name for display */ -}; -#define BFA_SM(_sm) ((bfa_sm_t)(_sm)) +#define BFA_SM_TABLE(n, s, e, t) \ +struct s; \ +enum e; \ +typedef void (*t)(struct s *, enum e); \ + \ +struct n ## _sm_table_s { \ + t sm; /* state machine function */ \ + int state; /* state machine encoding */ \ + char *name; /* state name for display */ \ +}; \ + \ +static inline int \ +n ## _sm_to_state(struct n ## _sm_table_s *smt, t sm) \ +{ \ + int i = 0; \ + \ + while (smt[i].sm && smt[i].sm != sm) \ + i++; \ + return smt[i].state; \ +} + +BFA_SM_TABLE(iocpf, bfa_iocpf, iocpf_event, bfa_fsm_iocpf_t) +BFA_SM_TABLE(ioc, bfa_ioc, ioc_event, bfa_fsm_ioc_t) +BFA_SM_TABLE(cmdq, bfa_msgq_cmdq, cmdq_event, bfa_fsm_msgq_cmdq_t) +BFA_SM_TABLE(rspq, bfa_msgq_rspq, rspq_event, bfa_fsm_msgq_rspq_t) + +BFA_SM_TABLE(ioceth, bna_ioceth, bna_ioceth_event, bna_fsm_ioceth_t) +BFA_SM_TABLE(enet, bna_enet, bna_enet_event, bna_fsm_enet_t) +BFA_SM_TABLE(ethport, bna_ethport, bna_ethport_event, bna_fsm_ethport_t) +BFA_SM_TABLE(tx, bna_tx, bna_tx_event, bna_fsm_tx_t) +BFA_SM_TABLE(rxf, bna_rxf, bna_rxf_event, bna_fsm_rxf_t) +BFA_SM_TABLE(rx, bna_rx, bna_rx_event, bna_fsm_rx_t) + +#undef BFA_SM_TABLE + +#define BFA_SM(_sm) (_sm) /* State machine with entry actions. */ typedef void (*bfa_fsm_t)(void *fsm, int event); @@ -41,24 +69,12 @@ typedef void (*bfa_fsm_t)(void *fsm, int event); static void oc ## _sm_ ## st ## _entry(otype * fsm) #define bfa_fsm_set_state(_fsm, _state) do { \ - (_fsm)->fsm = (bfa_fsm_t)(_state); \ + (_fsm)->fsm = (_state); \ _state ## _entry(_fsm); \ } while (0) #define bfa_fsm_send_event(_fsm, _event) ((_fsm)->fsm((_fsm), (_event))) -#define bfa_fsm_cmp_state(_fsm, _state) \ - ((_fsm)->fsm == (bfa_fsm_t)(_state)) - -static inline int -bfa_sm_to_state(const struct bfa_sm_table *smt, bfa_sm_t sm) -{ - int i = 0; - - while (smt[i].sm && smt[i].sm != sm) - i++; - return smt[i].state; -} - +#define bfa_fsm_cmp_state(_fsm, _state) ((_fsm)->fsm == (_state)) /* Generic wait counter. */ typedef void (*bfa_wc_resume_t) (void *cbarg); diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index cd933817a0b8..b07522ac3e74 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -114,7 +114,7 @@ bfa_fsm_state_decl(bfa_ioc, disabling, struct bfa_ioc, enum ioc_event); bfa_fsm_state_decl(bfa_ioc, disabled, struct bfa_ioc, enum ioc_event); bfa_fsm_state_decl(bfa_ioc, hwfail, struct bfa_ioc, enum ioc_event); -static struct bfa_sm_table ioc_sm_table[] = { +static struct ioc_sm_table_s ioc_sm_table[] = { {BFA_SM(bfa_ioc_sm_uninit), BFA_IOC_UNINIT}, {BFA_SM(bfa_ioc_sm_reset), BFA_IOC_RESET}, {BFA_SM(bfa_ioc_sm_enabling), BFA_IOC_ENABLING}, @@ -183,7 +183,7 @@ bfa_fsm_state_decl(bfa_iocpf, disabling_sync, struct bfa_iocpf, enum iocpf_event); bfa_fsm_state_decl(bfa_iocpf, disabled, struct bfa_iocpf, enum iocpf_event); -static struct bfa_sm_table iocpf_sm_table[] = { +static struct iocpf_sm_table_s iocpf_sm_table[] = { {BFA_SM(bfa_iocpf_sm_reset), BFA_IOCPF_RESET}, {BFA_SM(bfa_iocpf_sm_fwcheck), BFA_IOCPF_FWMISMATCH}, {BFA_SM(bfa_iocpf_sm_mismatch), BFA_IOCPF_FWMISMATCH}, @@ -2860,12 +2860,12 @@ static enum bfa_ioc_state bfa_ioc_get_state(struct bfa_ioc *ioc) { enum bfa_iocpf_state iocpf_st; - enum bfa_ioc_state ioc_st = bfa_sm_to_state(ioc_sm_table, ioc->fsm); + enum bfa_ioc_state ioc_st = ioc_sm_to_state(ioc_sm_table, ioc->fsm); if (ioc_st == BFA_IOC_ENABLING || ioc_st == BFA_IOC_FAIL || ioc_st == BFA_IOC_INITFAIL) { - iocpf_st = bfa_sm_to_state(iocpf_sm_table, ioc->iocpf.fsm); + iocpf_st = iocpf_sm_to_state(iocpf_sm_table, ioc->iocpf.fsm); switch (iocpf_st) { case BFA_IOCPF_SEMWAIT: @@ -2983,7 +2983,7 @@ bfa_nw_iocpf_timeout(struct bfa_ioc *ioc) { enum bfa_iocpf_state iocpf_st; - iocpf_st = bfa_sm_to_state(iocpf_sm_table, ioc->iocpf.fsm); + iocpf_st = iocpf_sm_to_state(iocpf_sm_table, ioc->iocpf.fsm); if (iocpf_st == BFA_IOCPF_HWINIT) bfa_ioc_poll_fwinit(ioc); diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.h b/drivers/net/ethernet/brocade/bna/bfa_ioc.h index edd0ed5b5332..f30d06ec4ffe 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.h +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.h @@ -147,16 +147,20 @@ struct bfa_ioc_notify { (__notify)->cbarg = (__cbarg); \ } while (0) +enum iocpf_event; + struct bfa_iocpf { - bfa_fsm_t fsm; + void (*fsm)(struct bfa_iocpf *s, enum iocpf_event e); struct bfa_ioc *ioc; bool fw_mismatch_notified; bool auto_recover; u32 poll_time; }; +enum ioc_event; + struct bfa_ioc { - bfa_fsm_t fsm; + void (*fsm)(struct bfa_ioc *s, enum ioc_event e); struct bfa *bfa; struct bfa_pcidev pcidev; struct timer_list ioc_timer; diff --git a/drivers/net/ethernet/brocade/bna/bfa_msgq.c b/drivers/net/ethernet/brocade/bna/bfa_msgq.c index 47125f419530..fa40d5ec6f1c 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_msgq.c +++ b/drivers/net/ethernet/brocade/bna/bfa_msgq.c @@ -202,7 +202,6 @@ static void __cmd_copy(struct bfa_msgq_cmdq *cmdq, struct bfa_msgq_cmd_entry *cmd) { size_t len = cmd->msg_size; - int num_entries = 0; size_t to_copy; u8 *src, *dst; @@ -219,7 +218,6 @@ __cmd_copy(struct bfa_msgq_cmdq *cmdq, struct bfa_msgq_cmd_entry *cmd) BFA_MSGQ_INDX_ADD(cmdq->producer_index, 1, cmdq->depth); dst = (u8 *)cmdq->addr.kva; dst += (cmdq->producer_index * BFI_MSGQ_CMD_ENTRY_SIZE); - num_entries++; } } diff --git a/drivers/net/ethernet/brocade/bna/bfa_msgq.h b/drivers/net/ethernet/brocade/bna/bfa_msgq.h index 75343b535798..170a4b4bed96 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_msgq.h +++ b/drivers/net/ethernet/brocade/bna/bfa_msgq.h @@ -55,8 +55,10 @@ enum bfa_msgq_cmdq_flags { BFA_MSGQ_CMDQ_F_DB_UPDATE = 1, }; +enum cmdq_event; + struct bfa_msgq_cmdq { - bfa_fsm_t fsm; + void (*fsm)(struct bfa_msgq_cmdq *s, enum cmdq_event e); enum bfa_msgq_cmdq_flags flags; u16 producer_index; @@ -81,8 +83,10 @@ enum bfa_msgq_rspq_flags { typedef void (*bfa_msgq_mcfunc_t)(void *cbarg, struct bfi_msgq_mhdr *mhdr); +enum rspq_event; + struct bfa_msgq_rspq { - bfa_fsm_t fsm; + void (*fsm)(struct bfa_msgq_rspq *s, enum rspq_event e); enum bfa_msgq_rspq_flags flags; u16 producer_index; diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c index a2c983f56b00..883de0ac8de4 100644 --- a/drivers/net/ethernet/brocade/bna/bna_enet.c +++ b/drivers/net/ethernet/brocade/bna/bna_enet.c @@ -1257,7 +1257,7 @@ bna_enet_mtu_get(struct bna_enet *enet) void bna_enet_enable(struct bna_enet *enet) { - if (enet->fsm != (bfa_sm_t)bna_enet_sm_stopped) + if (enet->fsm != bna_enet_sm_stopped) return; enet->flags |= BNA_ENET_F_ENABLED; @@ -1751,12 +1751,12 @@ bna_ioceth_uninit(struct bna_ioceth *ioceth) void bna_ioceth_enable(struct bna_ioceth *ioceth) { - if (ioceth->fsm == (bfa_fsm_t)bna_ioceth_sm_ready) { + if (ioceth->fsm == bna_ioceth_sm_ready) { bnad_cb_ioceth_ready(ioceth->bna->bnad); return; } - if (ioceth->fsm == (bfa_fsm_t)bna_ioceth_sm_stopped) + if (ioceth->fsm == bna_ioceth_sm_stopped) bfa_fsm_send_event(ioceth, IOCETH_E_ENABLE); } diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 2623a0da4682..c05dc7a1c4a1 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -1956,7 +1956,7 @@ static void bna_rx_stop(struct bna_rx *rx) { rx->rx_flags &= ~BNA_RX_F_ENET_STARTED; - if (rx->fsm == (bfa_fsm_t) bna_rx_sm_stopped) + if (rx->fsm == bna_rx_sm_stopped) bna_rx_mod_cb_rx_stopped(&rx->bna->rx_mod, rx); else { rx->stop_cbfn = bna_rx_mod_cb_rx_stopped; @@ -2535,7 +2535,7 @@ bna_rx_destroy(struct bna_rx *rx) void bna_rx_enable(struct bna_rx *rx) { - if (rx->fsm != (bfa_sm_t)bna_rx_sm_stopped) + if (rx->fsm != bna_rx_sm_stopped) return; rx->rx_flags |= BNA_RX_F_ENABLED; @@ -3523,7 +3523,7 @@ bna_tx_destroy(struct bna_tx *tx) void bna_tx_enable(struct bna_tx *tx) { - if (tx->fsm != (bfa_sm_t)bna_tx_sm_stopped) + if (tx->fsm != bna_tx_sm_stopped) return; tx->flags |= BNA_TX_F_ENABLED; diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h index 666b6922e24d..a5ebd7110e07 100644 --- a/drivers/net/ethernet/brocade/bna/bna_types.h +++ b/drivers/net/ethernet/brocade/bna/bna_types.h @@ -312,8 +312,10 @@ struct bna_attr { /* IOCEth */ +enum bna_ioceth_event; + struct bna_ioceth { - bfa_fsm_t fsm; + void (*fsm)(struct bna_ioceth *s, enum bna_ioceth_event e); struct bfa_ioc ioc; struct bna_attr attr; @@ -334,8 +336,10 @@ struct bna_pause_config { enum bna_status rx_pause; }; +enum bna_enet_event; + struct bna_enet { - bfa_fsm_t fsm; + void (*fsm)(struct bna_enet *s, enum bna_enet_event e); enum bna_enet_flags flags; enum bna_enet_type type; @@ -360,8 +364,10 @@ struct bna_enet { /* Ethport */ +enum bna_ethport_event; + struct bna_ethport { - bfa_fsm_t fsm; + void (*fsm)(struct bna_ethport *s, enum bna_ethport_event e); enum bna_ethport_flags flags; enum bna_link_status link_status; @@ -454,13 +460,16 @@ struct bna_txq { }; /* Tx object */ + +enum bna_tx_event; + struct bna_tx { /* This should be the first one */ struct list_head qe; int rid; int hw_id; - bfa_fsm_t fsm; + void (*fsm)(struct bna_tx *s, enum bna_tx_event e); enum bna_tx_flags flags; enum bna_tx_type type; @@ -698,8 +707,11 @@ struct bna_rxp { }; /* RxF structure (hardware Rx Function) */ + +enum bna_rxf_event; + struct bna_rxf { - bfa_fsm_t fsm; + void (*fsm)(struct bna_rxf *s, enum bna_rxf_event e); struct bfa_msgq_cmd_entry msgq_cmd; union { @@ -769,13 +781,16 @@ struct bna_rxf { }; /* Rx object */ + +enum bna_rx_event; + struct bna_rx { /* This should be the first one */ struct list_head qe; int rid; int hw_id; - bfa_fsm_t fsm; + void (*fsm)(struct bna_rx *s, enum bna_rx_event e); enum bna_rx_type type; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4f63f1ba3161..95667b979fab 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -742,7 +742,6 @@ static struct phylink_pcs *macb_mac_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops macb_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = macb_mac_select_pcs, .mac_config = macb_mac_config, .mac_link_down = macb_mac_link_down, @@ -2947,6 +2946,18 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static int macb_set_mac_addr(struct net_device *dev, void *addr) +{ + int err; + + err = eth_mac_addr(dev, addr); + if (err < 0) + return err; + + macb_set_hwaddr(netdev_priv(dev)); + return 0; +} + static void gem_update_stats(struct macb *bp) { struct macb_queue *queue; @@ -3786,7 +3797,7 @@ static const struct net_device_ops macb_netdev_ops = { .ndo_eth_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = macb_change_mtu, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = macb_set_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macb_poll_controller, #endif @@ -4049,6 +4060,8 @@ static int macb_init(struct platform_device *pdev) dev->ethtool_ops = &macb_ethtool_ops; } + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + /* Set features */ dev->hw_features = NETIF_F_SG; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 98793b2ac2c7..fd7c80edb6e8 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1512,14 +1512,17 @@ static void free_netsgbuf_with_resp(void *buf) } /** - * liquidio_ptp_adjfreq - Adjust ptp frequency + * liquidio_ptp_adjfine - Adjust ptp frequency * @ptp: PTP clock info - * @ppb: how much to adjust by, in parts-per-billion + * @scaled_ppm: how much to adjust by, in scaled parts-per-million + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int liquidio_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int liquidio_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct lio *lio = container_of(ptp, struct lio, ptp_info); struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); u64 comp, delta; unsigned long flags; bool neg_adj = false; @@ -1643,7 +1646,7 @@ static void oct_ptp_open(struct net_device *netdev) lio->ptp_info.n_ext_ts = 0; lio->ptp_info.n_per_out = 0; lio->ptp_info.pps = 0; - lio->ptp_info.adjfreq = liquidio_ptp_adjfreq; + lio->ptp_info.adjfine = liquidio_ptp_adjfine; lio->ptp_info.adjtime = liquidio_ptp_adjtime; lio->ptp_info.gettime64 = liquidio_ptp_gettime; lio->ptp_info.settime64 = liquidio_ptp_settime; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index 28feabec8fbb..67c3570f875f 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -247,8 +247,7 @@ static const struct cvmx_bootmem_named_block_desc struct cvmx_bootmem_named_block_desc, size)); - strncpy(desc->name, name, sizeof(desc->name)); - desc->name[sizeof(desc->name) - 1] = 0; + strscpy(desc->name, name, sizeof(desc->name)); return &oct->bootmem_named_block_desc; } else { return NULL; @@ -471,8 +470,8 @@ static void output_console_line(struct octeon_device *oct, if (line != &console_buffer[bytes_read]) { console_buffer[bytes_read] = '\0'; len = strlen(console->leftover); - strncpy(&console->leftover[len], line, - sizeof(console->leftover) - len); + strscpy(&console->leftover[len], line, + sizeof(console->leftover) - len + 1); } } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 5bf117d2179f..cbd06d9b95d4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -194,17 +194,20 @@ int cxgb4_ptp_redirect_rx_packet(struct adapter *adapter, struct port_info *pi) } /** - * cxgb4_ptp_adjfreq - Adjust frequency of PHC cycle counter + * cxgb4_ptp_adjfine - Adjust frequency of PHC cycle counter * @ptp: ptp clock structure - * @ppb: Desired frequency change in parts per billion + * @scaled_ppm: Desired frequency in scaled parts per billion * - * Adjust the frequency of the PHC cycle counter by the indicated ppb from + * Adjust the frequency of the PHC cycle counter by the indicated amount from * the base frequency. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int cxgb4_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int cxgb4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct adapter *adapter = (struct adapter *)container_of(ptp, struct adapter, ptp_clock_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); struct fw_ptp_cmd c; int err; @@ -404,7 +407,7 @@ static const struct ptp_clock_info cxgb4_ptp_clock_info = { .n_ext_ts = 0, .n_per_out = 0, .pps = 0, - .adjfreq = cxgb4_ptp_adjfreq, + .adjfine = cxgb4_ptp_adjfine, .adjtime = cxgb4_ptp_adjtime, .gettime64 = cxgb4_ptp_gettime, .settime64 = cxgb4_ptp_settime, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c index 585590520076..ca21794281d6 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c @@ -283,6 +283,10 @@ static int ch_ipsec_xfrm_add_state(struct xfrm_state *x) pr_debug("Cannot offload xfrm states with geniv other than seqiv\n"); return -EINVAL; } + if (x->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { + pr_debug("Unsupported xfrm offload\n"); + return -EINVAL; + } sa_entry = kzalloc(sizeof(*sa_entry), GFP_KERNEL); if (!sa_entry) { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index da9973b711f4..1a5fdd755e9e 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -1839,9 +1839,7 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, */ if (prior_data_len) { int i = 0; - u8 *data = NULL; skb_frag_t *f; - u8 *vaddr; int frag_size = 0, frag_delta = 0; while (remaining > 0) { @@ -1853,24 +1851,24 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, i++; } f = &record->frags[i]; - vaddr = kmap_atomic(skb_frag_page(f)); - - data = vaddr + skb_frag_off(f) + remaining; frag_delta = skb_frag_size(f) - remaining; if (frag_delta >= prior_data_len) { - memcpy(prior_data, data, prior_data_len); - kunmap_atomic(vaddr); + memcpy_from_page(prior_data, skb_frag_page(f), + skb_frag_off(f) + remaining, + prior_data_len); } else { - memcpy(prior_data, data, frag_delta); - kunmap_atomic(vaddr); + memcpy_from_page(prior_data, skb_frag_page(f), + skb_frag_off(f) + remaining, + frag_delta); + /* get the next page */ f = &record->frags[i + 1]; - vaddr = kmap_atomic(skb_frag_page(f)); - data = vaddr + skb_frag_off(f); - memcpy(prior_data + frag_delta, - data, (prior_data_len - frag_delta)); - kunmap_atomic(vaddr); + + memcpy_from_page(prior_data + frag_delta, + skb_frag_page(f), + skb_frag_off(f), + prior_data_len - frag_delta); } /* reset tcp_seq as per the prior_data_required len */ tcp_seq -= prior_data_len; diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index a0964b629ffc..300ad05ee05b 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -226,21 +226,6 @@ static inline unsigned int enic_cq_wq(struct enic *enic, unsigned int wq) return enic->rq_count + wq; } -static inline unsigned int enic_legacy_io_intr(void) -{ - return 0; -} - -static inline unsigned int enic_legacy_err_intr(void) -{ - return 1; -} - -static inline unsigned int enic_legacy_notify_intr(void) -{ - return 2; -} - static inline unsigned int enic_msix_rq_intr(struct enic *enic, unsigned int rq) { @@ -258,6 +243,10 @@ static inline unsigned int enic_msix_err_intr(struct enic *enic) return enic->rq_count + enic->wq_count; } +#define ENIC_LEGACY_IO_INTR 0 +#define ENIC_LEGACY_ERR_INTR 1 +#define ENIC_LEGACY_NOTIFY_INTR 2 + static inline unsigned int enic_msix_notify_intr(struct enic *enic) { return enic->rq_count + enic->wq_count + 1; @@ -267,7 +256,7 @@ static inline bool enic_is_err_intr(struct enic *enic, int intr) { switch (vnic_dev_get_intr_mode(enic->vdev)) { case VNIC_DEV_INTR_MODE_INTX: - return intr == enic_legacy_err_intr(); + return intr == ENIC_LEGACY_ERR_INTR; case VNIC_DEV_INTR_MODE_MSIX: return intr == enic_msix_err_intr(enic); case VNIC_DEV_INTR_MODE_MSI: @@ -280,7 +269,7 @@ static inline bool enic_is_notify_intr(struct enic *enic, int intr) { switch (vnic_dev_get_intr_mode(enic->vdev)) { case VNIC_DEV_INTR_MODE_INTX: - return intr == enic_legacy_notify_intr(); + return intr == ENIC_LEGACY_NOTIFY_INTR; case VNIC_DEV_INTR_MODE_MSIX: return intr == enic_msix_notify_intr(enic); case VNIC_DEV_INTR_MODE_MSI: diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 29500d32e362..37bd38d772e8 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -448,9 +448,9 @@ static irqreturn_t enic_isr_legacy(int irq, void *data) { struct net_device *netdev = data; struct enic *enic = netdev_priv(netdev); - unsigned int io_intr = enic_legacy_io_intr(); - unsigned int err_intr = enic_legacy_err_intr(); - unsigned int notify_intr = enic_legacy_notify_intr(); + unsigned int io_intr = ENIC_LEGACY_IO_INTR; + unsigned int err_intr = ENIC_LEGACY_ERR_INTR; + unsigned int notify_intr = ENIC_LEGACY_NOTIFY_INTR; u32 pba; vnic_intr_mask(&enic->intr[io_intr]); @@ -1507,7 +1507,7 @@ static int enic_poll(struct napi_struct *napi, int budget) struct enic *enic = netdev_priv(netdev); unsigned int cq_rq = enic_cq_rq(enic, 0); unsigned int cq_wq = enic_cq_wq(enic, 0); - unsigned int intr = enic_legacy_io_intr(); + unsigned int intr = ENIC_LEGACY_IO_INTR; unsigned int rq_work_to_do = budget; unsigned int wq_work_to_do = ENIC_WQ_NAPI_BUDGET; unsigned int work_done, rq_work_done = 0, wq_work_done; @@ -1856,8 +1856,7 @@ static int enic_dev_notify_set(struct enic *enic) spin_lock_bh(&enic->devcmd_lock); switch (vnic_dev_get_intr_mode(enic->vdev)) { case VNIC_DEV_INTR_MODE_INTX: - err = vnic_dev_notify_set(enic->vdev, - enic_legacy_notify_intr()); + err = vnic_dev_notify_set(enic->vdev, ENIC_LEGACY_NOTIFY_INTR); break; case VNIC_DEV_INTR_MODE_MSIX: err = vnic_dev_notify_set(enic->vdev, diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index fdf10318758b..5715b9ab2712 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1919,7 +1919,7 @@ static void gmac_get_stats64(struct net_device *netdev, /* Racing with RX NAPI */ do { - start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); + start = u64_stats_fetch_begin(&port->rx_stats_syncp); stats->rx_packets = port->stats.rx_packets; stats->rx_bytes = port->stats.rx_bytes; @@ -1931,11 +1931,11 @@ static void gmac_get_stats64(struct net_device *netdev, stats->rx_crc_errors = port->stats.rx_crc_errors; stats->rx_frame_errors = port->stats.rx_frame_errors; - } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); /* Racing with MIB and TX completion interrupts */ do { - start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); + start = u64_stats_fetch_begin(&port->ir_stats_syncp); stats->tx_errors = port->stats.tx_errors; stats->tx_packets = port->stats.tx_packets; @@ -1945,15 +1945,15 @@ static void gmac_get_stats64(struct net_device *netdev, stats->rx_missed_errors = port->stats.rx_missed_errors; stats->rx_fifo_errors = port->stats.rx_fifo_errors; - } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); /* Racing with hard_start_xmit */ do { - start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); + start = u64_stats_fetch_begin(&port->tx_stats_syncp); stats->tx_dropped = port->stats.tx_dropped; - } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); stats->rx_dropped += stats->rx_missed_errors; } @@ -2031,18 +2031,18 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, /* Racing with MIB interrupt */ do { p = values; - start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); + start = u64_stats_fetch_begin(&port->ir_stats_syncp); for (i = 0; i < RX_STATS_NUM; i++) *p++ = port->hw_stats[i]; - } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); values = p; /* Racing with RX NAPI */ do { p = values; - start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); + start = u64_stats_fetch_begin(&port->rx_stats_syncp); for (i = 0; i < RX_STATUS_NUM; i++) *p++ = port->rx_stats[i]; @@ -2050,13 +2050,13 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, *p++ = port->rx_csum_stats[i]; *p++ = port->rx_napi_exits; - } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); values = p; /* Racing with TX start_xmit */ do { p = values; - start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); + start = u64_stats_fetch_begin(&port->tx_stats_syncp); for (i = 0; i < TX_MAX_FRAGS; i++) { *values++ = port->tx_frag_stats[i]; @@ -2065,7 +2065,7 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, *values++ = port->tx_frags_linearized; *values++ = port->tx_hw_csummed; - } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); + } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); } static int gmac_get_ksettings(struct net_device *netdev, diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 2c67a857a42f..db6615aa921b 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -814,7 +814,6 @@ rio_free_tx (struct net_device *dev, int irq) { struct netdev_private *np = netdev_priv(dev); int entry = np->old_tx % TX_RING_SIZE; - int tx_use = 0; unsigned long flag = 0; if (irq) @@ -839,7 +838,6 @@ rio_free_tx (struct net_device *dev, int irq) np->tx_skbuff[entry] = NULL; entry = (entry + 1) % TX_RING_SIZE; - tx_use++; } if (irq) spin_unlock(&np->tx_lock); diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 43def191f26f..aaf0eda96292 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -1414,7 +1414,6 @@ static void refill_rx (struct net_device *dev) { struct netdev_private *np = netdev_priv(dev); int entry; - int cnt = 0; /* Refill the Rx ring buffers. */ for (;(np->cur_rx - np->dirty_rx + RX_RING_SIZE) % RX_RING_SIZE > 0; @@ -1441,7 +1440,6 @@ static void refill_rx (struct net_device *dev) np->rx_ring[entry].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); np->rx_ring[entry].status = 0; - cnt++; } } static void netdev_error(struct net_device *dev, int intr_status) diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 77edc3d9b505..a29de29bdf23 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -389,10 +389,10 @@ static void be_get_ethtool_stats(struct net_device *netdev, struct be_rx_stats *stats = rx_stats(rxo); do { - start = u64_stats_fetch_begin_irq(&stats->sync); + start = u64_stats_fetch_begin(&stats->sync); data[base] = stats->rx_bytes; data[base + 1] = stats->rx_pkts; - } while (u64_stats_fetch_retry_irq(&stats->sync, start)); + } while (u64_stats_fetch_retry(&stats->sync, start)); for (i = 2; i < ETHTOOL_RXSTATS_NUM; i++) { p = (u8 *)stats + et_rx_stats[i].offset; @@ -405,19 +405,19 @@ static void be_get_ethtool_stats(struct net_device *netdev, struct be_tx_stats *stats = tx_stats(txo); do { - start = u64_stats_fetch_begin_irq(&stats->sync_compl); + start = u64_stats_fetch_begin(&stats->sync_compl); data[base] = stats->tx_compl; - } while (u64_stats_fetch_retry_irq(&stats->sync_compl, start)); + } while (u64_stats_fetch_retry(&stats->sync_compl, start)); do { - start = u64_stats_fetch_begin_irq(&stats->sync); + start = u64_stats_fetch_begin(&stats->sync); for (i = 1; i < ETHTOOL_TXSTATS_NUM; i++) { p = (u8 *)stats + et_tx_stats[i].offset; data[base + i] = (et_tx_stats[i].size == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } - } while (u64_stats_fetch_retry_irq(&stats->sync, start)); + } while (u64_stats_fetch_retry(&stats->sync, start)); base += ETHTOOL_TXSTATS_NUM; } } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index a92a74761546..46fe3d74e2e9 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -665,10 +665,10 @@ static void be_get_stats64(struct net_device *netdev, const struct be_rx_stats *rx_stats = rx_stats(rxo); do { - start = u64_stats_fetch_begin_irq(&rx_stats->sync); + start = u64_stats_fetch_begin(&rx_stats->sync); pkts = rx_stats(rxo)->rx_pkts; bytes = rx_stats(rxo)->rx_bytes; - } while (u64_stats_fetch_retry_irq(&rx_stats->sync, start)); + } while (u64_stats_fetch_retry(&rx_stats->sync, start)); stats->rx_packets += pkts; stats->rx_bytes += bytes; stats->multicast += rx_stats(rxo)->rx_mcast_pkts; @@ -680,10 +680,10 @@ static void be_get_stats64(struct net_device *netdev, const struct be_tx_stats *tx_stats = tx_stats(txo); do { - start = u64_stats_fetch_begin_irq(&tx_stats->sync); + start = u64_stats_fetch_begin(&tx_stats->sync); pkts = tx_stats(txo)->tx_pkts; bytes = tx_stats(txo)->tx_bytes; - } while (u64_stats_fetch_retry_irq(&tx_stats->sync, start)); + } while (u64_stats_fetch_retry(&tx_stats->sync, start)); stats->tx_packets += pkts; stats->tx_bytes += bytes; } @@ -2155,16 +2155,16 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) for_all_rx_queues_on_eq(adapter, eqo, rxo, i) { do { - start = u64_stats_fetch_begin_irq(&rxo->stats.sync); + start = u64_stats_fetch_begin(&rxo->stats.sync); rx_pkts += rxo->stats.rx_pkts; - } while (u64_stats_fetch_retry_irq(&rxo->stats.sync, start)); + } while (u64_stats_fetch_retry(&rxo->stats.sync, start)); } for_all_tx_queues_on_eq(adapter, eqo, txo, i) { do { - start = u64_stats_fetch_begin_irq(&txo->stats.sync); + start = u64_stats_fetch_begin(&txo->stats.sync); tx_pkts += txo->stats.tx_reqs; - } while (u64_stats_fetch_retry_irq(&txo->stats.sync, start)); + } while (u64_stats_fetch_retry(&txo->stats.sync, start)); } /* Skip, if wrapped around or first calculation */ diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index 09a723b827c7..f93ba48bac3f 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -18,6 +18,8 @@ #define TSNEP "tsnep" #define TSNEP_RING_SIZE 256 +#define TSNEP_RING_RX_REFILL 16 +#define TSNEP_RING_RX_REUSE (TSNEP_RING_SIZE - TSNEP_RING_SIZE / 4) #define TSNEP_RING_ENTRIES_PER_PAGE (PAGE_SIZE / TSNEP_DESC_SIZE) #define TSNEP_RING_PAGE_COUNT (TSNEP_RING_SIZE / TSNEP_RING_ENTRIES_PER_PAGE) @@ -110,6 +112,7 @@ struct tsnep_rx { dma_addr_t page_dma[TSNEP_RING_PAGE_COUNT]; struct tsnep_rx_entry entry[TSNEP_RING_SIZE]; + int write; int read; u32 owner_counter; int increment_owner_counter; @@ -119,6 +122,7 @@ struct tsnep_rx { u32 bytes; u32 dropped; u32 multicast; + u32 alloc_failed; }; struct tsnep_queue { @@ -132,6 +136,8 @@ struct tsnep_queue { int irq; u32 irq_mask; + void __iomem *irq_delay_addr; + u8 irq_delay; }; struct tsnep_adapter { @@ -223,5 +229,7 @@ static inline void tsnep_ethtool_self_test(struct net_device *dev, #endif /* CONFIG_TSNEP_SELFTESTS */ void tsnep_get_system_time(struct tsnep_adapter *adapter, u64 *time); +int tsnep_set_irq_coalesce(struct tsnep_queue *queue, u32 usecs); +u32 tsnep_get_irq_coalesce(struct tsnep_queue *queue); #endif /* _TSNEP_H */ diff --git a/drivers/net/ethernet/engleder/tsnep_ethtool.c b/drivers/net/ethernet/engleder/tsnep_ethtool.c index a713a126b227..716815dad7d2 100644 --- a/drivers/net/ethernet/engleder/tsnep_ethtool.c +++ b/drivers/net/ethernet/engleder/tsnep_ethtool.c @@ -8,6 +8,7 @@ static const char tsnep_stats_strings[][ETH_GSTRING_LEN] = { "rx_bytes", "rx_dropped", "rx_multicast", + "rx_alloc_failed", "rx_phy_errors", "rx_forwarded_phy_errors", "rx_invalid_frame_errors", @@ -21,6 +22,7 @@ struct tsnep_stats { u64 rx_bytes; u64 rx_dropped; u64 rx_multicast; + u64 rx_alloc_failed; u64 rx_phy_errors; u64 rx_forwarded_phy_errors; u64 rx_invalid_frame_errors; @@ -36,6 +38,7 @@ static const char tsnep_rx_queue_stats_strings[][ETH_GSTRING_LEN] = { "rx_%d_bytes", "rx_%d_dropped", "rx_%d_multicast", + "rx_%d_alloc_failed", "rx_%d_no_descriptor_errors", "rx_%d_buffer_too_small_errors", "rx_%d_fifo_overflow_errors", @@ -47,6 +50,7 @@ struct tsnep_rx_queue_stats { u64 rx_bytes; u64 rx_dropped; u64 rx_multicast; + u64 rx_alloc_failed; u64 rx_no_descriptor_errors; u64 rx_buffer_too_small_errors; u64 rx_fifo_overflow_errors; @@ -178,6 +182,7 @@ static void tsnep_ethtool_get_ethtool_stats(struct net_device *netdev, tsnep_stats.rx_bytes += adapter->rx[i].bytes; tsnep_stats.rx_dropped += adapter->rx[i].dropped; tsnep_stats.rx_multicast += adapter->rx[i].multicast; + tsnep_stats.rx_alloc_failed += adapter->rx[i].alloc_failed; } reg = ioread32(adapter->addr + ECM_STAT); tsnep_stats.rx_phy_errors = @@ -200,6 +205,8 @@ static void tsnep_ethtool_get_ethtool_stats(struct net_device *netdev, tsnep_rx_queue_stats.rx_bytes = adapter->rx[i].bytes; tsnep_rx_queue_stats.rx_dropped = adapter->rx[i].dropped; tsnep_rx_queue_stats.rx_multicast = adapter->rx[i].multicast; + tsnep_rx_queue_stats.rx_alloc_failed = + adapter->rx[i].alloc_failed; reg = ioread32(adapter->addr + TSNEP_QUEUE(i) + TSNEP_RX_STATISTIC); tsnep_rx_queue_stats.rx_no_descriptor_errors = @@ -250,10 +257,10 @@ static int tsnep_ethtool_get_sset_count(struct net_device *netdev, int sset) } } -static int tsnep_ethtool_get_rxnfc(struct net_device *dev, +static int tsnep_ethtool_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct tsnep_adapter *adapter = netdev_priv(dev); + struct tsnep_adapter *adapter = netdev_priv(netdev); switch (cmd->cmd) { case ETHTOOL_GRXRINGS: @@ -273,10 +280,10 @@ static int tsnep_ethtool_get_rxnfc(struct net_device *dev, } } -static int tsnep_ethtool_set_rxnfc(struct net_device *dev, +static int tsnep_ethtool_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) { - struct tsnep_adapter *adapter = netdev_priv(dev); + struct tsnep_adapter *adapter = netdev_priv(netdev); switch (cmd->cmd) { case ETHTOOL_SRXCLSRLINS: @@ -288,10 +295,21 @@ static int tsnep_ethtool_set_rxnfc(struct net_device *dev, } } -static int tsnep_ethtool_get_ts_info(struct net_device *dev, +static void tsnep_ethtool_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + + ch->max_rx = adapter->num_rx_queues; + ch->max_tx = adapter->num_tx_queues; + ch->rx_count = adapter->num_rx_queues; + ch->tx_count = adapter->num_tx_queues; +} + +static int tsnep_ethtool_get_ts_info(struct net_device *netdev, struct ethtool_ts_info *info) { - struct tsnep_adapter *adapter = netdev_priv(dev); + struct tsnep_adapter *adapter = netdev_priv(netdev); info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | @@ -313,7 +331,137 @@ static int tsnep_ethtool_get_ts_info(struct net_device *dev, return 0; } +static struct tsnep_queue *tsnep_get_queue_with_tx(struct tsnep_adapter *adapter, + int index) +{ + int i; + + for (i = 0; i < adapter->num_queues; i++) { + if (adapter->queue[i].tx) { + if (index == 0) + return &adapter->queue[i]; + + index--; + } + } + + return NULL; +} + +static struct tsnep_queue *tsnep_get_queue_with_rx(struct tsnep_adapter *adapter, + int index) +{ + int i; + + for (i = 0; i < adapter->num_queues; i++) { + if (adapter->queue[i].rx) { + if (index == 0) + return &adapter->queue[i]; + + index--; + } + } + + return NULL; +} + +static int tsnep_ethtool_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + struct tsnep_queue *queue; + + queue = tsnep_get_queue_with_rx(adapter, 0); + if (queue) + ec->rx_coalesce_usecs = tsnep_get_irq_coalesce(queue); + + queue = tsnep_get_queue_with_tx(adapter, 0); + if (queue) + ec->tx_coalesce_usecs = tsnep_get_irq_coalesce(queue); + + return 0; +} + +static int tsnep_ethtool_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + int i; + int retval; + + for (i = 0; i < adapter->num_queues; i++) { + /* RX coalesce has priority for queues with TX and RX */ + if (adapter->queue[i].rx) + retval = tsnep_set_irq_coalesce(&adapter->queue[i], + ec->rx_coalesce_usecs); + else + retval = tsnep_set_irq_coalesce(&adapter->queue[i], + ec->tx_coalesce_usecs); + if (retval != 0) + return retval; + } + + return 0; +} + +static int tsnep_ethtool_get_per_queue_coalesce(struct net_device *netdev, + u32 queue, + struct ethtool_coalesce *ec) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + struct tsnep_queue *queue_with_rx; + struct tsnep_queue *queue_with_tx; + + if (queue >= max(adapter->num_tx_queues, adapter->num_rx_queues)) + return -EINVAL; + + queue_with_rx = tsnep_get_queue_with_rx(adapter, queue); + if (queue_with_rx) + ec->rx_coalesce_usecs = tsnep_get_irq_coalesce(queue_with_rx); + + queue_with_tx = tsnep_get_queue_with_tx(adapter, queue); + if (queue_with_tx) + ec->tx_coalesce_usecs = tsnep_get_irq_coalesce(queue_with_tx); + + return 0; +} + +static int tsnep_ethtool_set_per_queue_coalesce(struct net_device *netdev, + u32 queue, + struct ethtool_coalesce *ec) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + struct tsnep_queue *queue_with_rx; + struct tsnep_queue *queue_with_tx; + int retval; + + if (queue >= max(adapter->num_tx_queues, adapter->num_rx_queues)) + return -EINVAL; + + queue_with_rx = tsnep_get_queue_with_rx(adapter, queue); + if (queue_with_rx) { + retval = tsnep_set_irq_coalesce(queue_with_rx, ec->rx_coalesce_usecs); + if (retval != 0) + return retval; + } + + /* RX coalesce has priority for queues with TX and RX */ + queue_with_tx = tsnep_get_queue_with_tx(adapter, queue); + if (queue_with_tx && !queue_with_tx->rx) { + retval = tsnep_set_irq_coalesce(queue_with_tx, ec->tx_coalesce_usecs); + if (retval != 0) + return retval; + } + + return 0; +} + const struct ethtool_ops tsnep_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .get_drvinfo = tsnep_ethtool_get_drvinfo, .get_regs_len = tsnep_ethtool_get_regs_len, .get_regs = tsnep_ethtool_get_regs, @@ -327,7 +475,12 @@ const struct ethtool_ops tsnep_ethtool_ops = { .get_sset_count = tsnep_ethtool_get_sset_count, .get_rxnfc = tsnep_ethtool_get_rxnfc, .set_rxnfc = tsnep_ethtool_set_rxnfc, + .get_channels = tsnep_ethtool_get_channels, .get_ts_info = tsnep_ethtool_get_ts_info, + .get_coalesce = tsnep_ethtool_get_coalesce, + .set_coalesce = tsnep_ethtool_set_coalesce, + .get_per_queue_coalesce = tsnep_ethtool_get_per_queue_coalesce, + .set_per_queue_coalesce = tsnep_ethtool_set_per_queue_coalesce, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/engleder/tsnep_hw.h b/drivers/net/ethernet/engleder/tsnep_hw.h index 315dada75323..55e1caf193a6 100644 --- a/drivers/net/ethernet/engleder/tsnep_hw.h +++ b/drivers/net/ethernet/engleder/tsnep_hw.h @@ -48,6 +48,13 @@ #define ECM_COUNTER_LOW 0x0028 #define ECM_COUNTER_HIGH 0x002C +/* interrupt delay */ +#define ECM_INT_DELAY 0x0030 +#define ECM_INT_DELAY_MASK 0xF0 +#define ECM_INT_DELAY_SHIFT 4 +#define ECM_INT_DELAY_BASE_US 16 +#define ECM_INT_DELAY_OFFSET 1 + /* control and status */ #define ECM_STATUS 0x0080 #define ECM_LINK_MODE_OFF 0x01000000 diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 13d5ff4e0e02..bf0190e1d2ea 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -39,6 +39,10 @@ #endif #define DMA_ADDR_LOW(dma_addr) ((u32)((dma_addr) & 0xFFFFFFFF)) +#define TSNEP_COALESCE_USECS_DEFAULT 64 +#define TSNEP_COALESCE_USECS_MAX ((ECM_INT_DELAY_MASK >> ECM_INT_DELAY_SHIFT) * \ + ECM_INT_DELAY_BASE_US + ECM_INT_DELAY_BASE_US - 1) + static void tsnep_enable_irq(struct tsnep_adapter *adapter, u32 mask) { iowrite32(mask, adapter->addr + ECM_INT_ENABLE); @@ -83,6 +87,33 @@ static irqreturn_t tsnep_irq_txrx(int irq, void *arg) return IRQ_HANDLED; } +int tsnep_set_irq_coalesce(struct tsnep_queue *queue, u32 usecs) +{ + if (usecs > TSNEP_COALESCE_USECS_MAX) + return -ERANGE; + + usecs /= ECM_INT_DELAY_BASE_US; + usecs <<= ECM_INT_DELAY_SHIFT; + usecs &= ECM_INT_DELAY_MASK; + + queue->irq_delay &= ~ECM_INT_DELAY_MASK; + queue->irq_delay |= usecs; + iowrite8(queue->irq_delay, queue->irq_delay_addr); + + return 0; +} + +u32 tsnep_get_irq_coalesce(struct tsnep_queue *queue) +{ + u32 usecs; + + usecs = (queue->irq_delay & ECM_INT_DELAY_MASK); + usecs >>= ECM_INT_DELAY_SHIFT; + usecs *= ECM_INT_DELAY_BASE_US; + + return usecs; +} + static int tsnep_mdiobus_read(struct mii_bus *bus, int addr, int regnum) { struct tsnep_adapter *adapter = bus->priv; @@ -629,23 +660,6 @@ static void tsnep_rx_ring_cleanup(struct tsnep_rx *rx) } } -static int tsnep_rx_alloc_buffer(struct tsnep_rx *rx, - struct tsnep_rx_entry *entry) -{ - struct page *page; - - page = page_pool_dev_alloc_pages(rx->page_pool); - if (unlikely(!page)) - return -ENOMEM; - - entry->page = page; - entry->len = TSNEP_MAX_RX_BUF_SIZE; - entry->dma = page_pool_get_dma_addr(entry->page); - entry->desc->rx = __cpu_to_le64(entry->dma + TSNEP_SKB_PAD); - - return 0; -} - static int tsnep_rx_ring_init(struct tsnep_rx *rx) { struct device *dmadev = rx->adapter->dmadev; @@ -692,10 +706,6 @@ static int tsnep_rx_ring_init(struct tsnep_rx *rx) entry = &rx->entry[i]; next_entry = &rx->entry[(i + 1) % TSNEP_RING_SIZE]; entry->desc->next = __cpu_to_le64(next_entry->desc_dma); - - retval = tsnep_rx_alloc_buffer(rx, entry); - if (retval) - goto failed; } return 0; @@ -705,6 +715,45 @@ failed: return retval; } +static int tsnep_rx_desc_available(struct tsnep_rx *rx) +{ + if (rx->read <= rx->write) + return TSNEP_RING_SIZE - rx->write + rx->read - 1; + else + return rx->read - rx->write - 1; +} + +static void tsnep_rx_set_page(struct tsnep_rx *rx, struct tsnep_rx_entry *entry, + struct page *page) +{ + entry->page = page; + entry->len = TSNEP_MAX_RX_BUF_SIZE; + entry->dma = page_pool_get_dma_addr(entry->page); + entry->desc->rx = __cpu_to_le64(entry->dma + TSNEP_SKB_PAD); +} + +static int tsnep_rx_alloc_buffer(struct tsnep_rx *rx, int index) +{ + struct tsnep_rx_entry *entry = &rx->entry[index]; + struct page *page; + + page = page_pool_dev_alloc_pages(rx->page_pool); + if (unlikely(!page)) + return -ENOMEM; + tsnep_rx_set_page(rx, entry, page); + + return 0; +} + +static void tsnep_rx_reuse_buffer(struct tsnep_rx *rx, int index) +{ + struct tsnep_rx_entry *entry = &rx->entry[index]; + struct tsnep_rx_entry *read = &rx->entry[rx->read]; + + tsnep_rx_set_page(rx, entry, read->page); + read->page = NULL; +} + static void tsnep_rx_activate(struct tsnep_rx *rx, int index) { struct tsnep_rx_entry *entry = &rx->entry[index]; @@ -732,6 +781,48 @@ static void tsnep_rx_activate(struct tsnep_rx *rx, int index) entry->desc->properties = __cpu_to_le32(entry->properties); } +static int tsnep_rx_refill(struct tsnep_rx *rx, int count, bool reuse) +{ + int index; + bool alloc_failed = false; + bool enable = false; + int i; + int retval; + + for (i = 0; i < count && !alloc_failed; i++) { + index = (rx->write + i) % TSNEP_RING_SIZE; + + retval = tsnep_rx_alloc_buffer(rx, index); + if (unlikely(retval)) { + rx->alloc_failed++; + alloc_failed = true; + + /* reuse only if no other allocation was successful */ + if (i == 0 && reuse) + tsnep_rx_reuse_buffer(rx, index); + else + break; + } + + tsnep_rx_activate(rx, index); + + enable = true; + } + + if (enable) { + rx->write = (rx->write + i) % TSNEP_RING_SIZE; + + /* descriptor properties shall be valid before hardware is + * notified + */ + dma_wmb(); + + iowrite32(TSNEP_CONTROL_RX_ENABLE, rx->addr + TSNEP_CONTROL); + } + + return i; +} + static struct sk_buff *tsnep_build_skb(struct tsnep_rx *rx, struct page *page, int length) { @@ -767,23 +858,42 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, int budget) { struct device *dmadev = rx->adapter->dmadev; + int desc_available; int done = 0; enum dma_data_direction dma_dir; struct tsnep_rx_entry *entry; - struct page *page; struct sk_buff *skb; int length; - bool enable = false; - int retval; + desc_available = tsnep_rx_desc_available(rx); dma_dir = page_pool_get_dma_dir(rx->page_pool); - while (likely(done < budget)) { + while (likely(done < budget) && (rx->read != rx->write)) { entry = &rx->entry[rx->read]; if ((__le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_OWNER_COUNTER_MASK) != (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) break; + done++; + + if (desc_available >= TSNEP_RING_RX_REFILL) { + bool reuse = desc_available >= TSNEP_RING_RX_REUSE; + + desc_available -= tsnep_rx_refill(rx, desc_available, + reuse); + if (!entry->page) { + /* buffer has been reused for refill to prevent + * empty RX ring, thus buffer cannot be used for + * RX processing + */ + rx->read = (rx->read + 1) % TSNEP_RING_SIZE; + desc_available++; + + rx->dropped++; + + continue; + } + } /* descriptor properties shall be read first, because valid data * is signaled there @@ -795,49 +905,30 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, TSNEP_DESC_LENGTH_MASK; dma_sync_single_range_for_cpu(dmadev, entry->dma, TSNEP_SKB_PAD, length, dma_dir); - page = entry->page; - /* forward skb only if allocation is successful, otherwise - * page is reused and frame dropped - */ - retval = tsnep_rx_alloc_buffer(rx, entry); - if (!retval) { - skb = tsnep_build_skb(rx, page, length); - if (skb) { - page_pool_release_page(rx->page_pool, page); - - rx->packets++; - rx->bytes += length - - TSNEP_RX_INLINE_METADATA_SIZE; - if (skb->pkt_type == PACKET_MULTICAST) - rx->multicast++; - - napi_gro_receive(napi, skb); - } else { - page_pool_recycle_direct(rx->page_pool, page); + rx->read = (rx->read + 1) % TSNEP_RING_SIZE; + desc_available++; - rx->dropped++; - } - done++; - } else { - rx->dropped++; - } + skb = tsnep_build_skb(rx, entry->page, length); + if (skb) { + page_pool_release_page(rx->page_pool, entry->page); - tsnep_rx_activate(rx, rx->read); + rx->packets++; + rx->bytes += length - TSNEP_RX_INLINE_METADATA_SIZE; + if (skb->pkt_type == PACKET_MULTICAST) + rx->multicast++; - enable = true; + napi_gro_receive(napi, skb); + } else { + page_pool_recycle_direct(rx->page_pool, entry->page); - rx->read = (rx->read + 1) % TSNEP_RING_SIZE; + rx->dropped++; + } + entry->page = NULL; } - if (enable) { - /* descriptor properties shall be valid before hardware is - * notified - */ - dma_wmb(); - - iowrite32(TSNEP_CONTROL_RX_ENABLE, rx->addr + TSNEP_CONTROL); - } + if (desc_available) + tsnep_rx_refill(rx, desc_available, false); return done; } @@ -846,11 +937,13 @@ static bool tsnep_rx_pending(struct tsnep_rx *rx) { struct tsnep_rx_entry *entry; - entry = &rx->entry[rx->read]; - if ((__le32_to_cpu(entry->desc_wb->properties) & - TSNEP_DESC_OWNER_COUNTER_MASK) == - (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) - return true; + if (rx->read != rx->write) { + entry = &rx->entry[rx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_DESC_OWNER_COUNTER_MASK) == + (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) + return true; + } return false; } @@ -859,7 +952,6 @@ static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_rx *rx) { dma_addr_t dma; - int i; int retval; memset(rx, 0, sizeof(*rx)); @@ -877,13 +969,7 @@ static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, rx->owner_counter = 1; rx->increment_owner_counter = TSNEP_RING_SIZE - 1; - for (i = 0; i < TSNEP_RING_SIZE; i++) - tsnep_rx_activate(rx, i); - - /* descriptor properties shall be valid before hardware is notified */ - dma_wmb(); - - iowrite32(TSNEP_CONTROL_RX_ENABLE, rx->addr + TSNEP_CONTROL); + tsnep_rx_refill(rx, tsnep_rx_desc_available(rx), false); return 0; } @@ -1371,6 +1457,11 @@ static int tsnep_queue_init(struct tsnep_adapter *adapter, int queue_count) adapter->queue[0].tx = &adapter->tx[0]; adapter->queue[0].rx = &adapter->rx[0]; adapter->queue[0].irq_mask = irq_mask; + adapter->queue[0].irq_delay_addr = adapter->addr + ECM_INT_DELAY; + retval = tsnep_set_irq_coalesce(&adapter->queue[0], + TSNEP_COALESCE_USECS_DEFAULT); + if (retval < 0) + return retval; adapter->netdev->irq = adapter->queue[0].irq; @@ -1391,6 +1482,12 @@ static int tsnep_queue_init(struct tsnep_adapter *adapter, int queue_count) adapter->queue[i].rx = &adapter->rx[i]; adapter->queue[i].irq_mask = irq_mask << (ECM_INT_TXRX_SHIFT * i); + adapter->queue[i].irq_delay_addr = + adapter->addr + ECM_INT_DELAY + ECM_INT_DELAY_OFFSET * i; + retval = tsnep_set_irq_coalesce(&adapter->queue[i], + TSNEP_COALESCE_USECS_DEFAULT); + if (retval < 0) + return retval; } return 0; diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index d95d78230828..6c8c78018ce6 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -11,6 +11,8 @@ #include <linux/dma-mapping.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -27,8 +29,8 @@ #define RX_QUEUE_ENTRIES 128 /* must be power of 2 */ #define TX_QUEUE_ENTRIES 16 /* must be power of 2 */ -#define MAX_PKT_SIZE 1518 #define RX_BUF_SIZE 2044 /* must be smaller than 0x7ff */ +#define MAX_PKT_SIZE RX_BUF_SIZE /* multi-segment not supported */ #if MAX_PKT_SIZE > 0x7ff #error invalid MAX_PKT_SIZE @@ -159,6 +161,7 @@ static void ftmac100_set_mac(struct ftmac100 *priv, const unsigned char *mac) static int ftmac100_start_hw(struct ftmac100 *priv) { struct net_device *netdev = priv->netdev; + unsigned int maccr = MACCR_ENABLE_ALL; if (ftmac100_reset(priv)) return -EIO; @@ -175,7 +178,11 @@ static int ftmac100_start_hw(struct ftmac100 *priv) ftmac100_set_mac(priv, netdev->dev_addr); - iowrite32(MACCR_ENABLE_ALL, priv->base + FTMAC100_OFFSET_MACCR); + /* See ftmac100_change_mtu() */ + if (netdev->mtu > ETH_DATA_LEN) + maccr |= FTMAC100_MACCR_RX_FTL; + + iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR); return 0; } @@ -218,11 +225,6 @@ static bool ftmac100_rxdes_crc_error(struct ftmac100_rxdes *rxdes) return rxdes->rxdes0 & cpu_to_le32(FTMAC100_RXDES0_CRC_ERR); } -static bool ftmac100_rxdes_frame_too_long(struct ftmac100_rxdes *rxdes) -{ - return rxdes->rxdes0 & cpu_to_le32(FTMAC100_RXDES0_FTL); -} - static bool ftmac100_rxdes_runt(struct ftmac100_rxdes *rxdes) { return rxdes->rxdes0 & cpu_to_le32(FTMAC100_RXDES0_RUNT); @@ -337,13 +339,7 @@ static bool ftmac100_rx_packet_error(struct ftmac100 *priv, error = true; } - if (unlikely(ftmac100_rxdes_frame_too_long(rxdes))) { - if (net_ratelimit()) - netdev_info(netdev, "rx frame too long\n"); - - netdev->stats.rx_length_errors++; - error = true; - } else if (unlikely(ftmac100_rxdes_runt(rxdes))) { + if (unlikely(ftmac100_rxdes_runt(rxdes))) { if (net_ratelimit()) netdev_info(netdev, "rx runt\n"); @@ -356,6 +352,11 @@ static bool ftmac100_rx_packet_error(struct ftmac100 *priv, netdev->stats.rx_length_errors++; error = true; } + /* + * FTMAC100_RXDES0_FTL is not an error, it just indicates that the + * frame is longer than 1518 octets. Receiving these is possible when + * we told the hardware not to drop them, via FTMAC100_MACCR_RX_FTL. + */ return error; } @@ -400,12 +401,13 @@ static bool ftmac100_rx_packet(struct ftmac100 *priv, int *processed) return true; } - /* - * It is impossible to get multi-segment packets - * because we always provide big enough receive buffers. - */ + /* We don't support multi-segment packets for now, so drop them. */ ret = ftmac100_rxdes_last_segment(rxdes); - BUG_ON(!ret); + if (unlikely(!ret)) { + netdev->stats.rx_length_errors++; + ftmac100_rx_drop_packet(priv); + return true; + } /* start processing */ skb = netdev_alloc_skb_ip_align(netdev, 128); @@ -1037,6 +1039,28 @@ static int ftmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int c return generic_mii_ioctl(&priv->mii, data, cmd, NULL); } +static int ftmac100_change_mtu(struct net_device *netdev, int mtu) +{ + struct ftmac100 *priv = netdev_priv(netdev); + unsigned int maccr; + + maccr = ioread32(priv->base + FTMAC100_OFFSET_MACCR); + if (mtu > ETH_DATA_LEN) { + /* process long packets in the driver */ + maccr |= FTMAC100_MACCR_RX_FTL; + } else { + /* Let the controller drop incoming packets greater + * than 1518 (that is 1500 + 14 Ethernet + 4 FCS). + */ + maccr &= ~FTMAC100_MACCR_RX_FTL; + } + iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR); + + netdev->mtu = mtu; + + return 0; +} + static const struct net_device_ops ftmac100_netdev_ops = { .ndo_open = ftmac100_open, .ndo_stop = ftmac100_stop, @@ -1044,6 +1068,7 @@ static const struct net_device_ops ftmac100_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = ftmac100_do_ioctl, + .ndo_change_mtu = ftmac100_change_mtu, }; /****************************************************************************** @@ -1075,7 +1100,7 @@ static int ftmac100_probe(struct platform_device *pdev) SET_NETDEV_DEV(netdev, &pdev->dev); netdev->ethtool_ops = &ftmac100_ethtool_ops; netdev->netdev_ops = &ftmac100_netdev_ops; - netdev->max_mtu = MAX_PKT_SIZE; + netdev->max_mtu = MAX_PKT_SIZE - VLAN_ETH_HLEN; err = platform_get_ethdev_address(&pdev->dev, netdev); if (err == -EPROBE_DEFER) diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c deleted file mode 100644 index ed18450fd2cc..000000000000 --- a/drivers/net/ethernet/fealnx.c +++ /dev/null @@ -1,1953 +0,0 @@ -/* - Written 1998-2000 by Donald Becker. - - This software may be used and distributed according to the terms of - the GNU General Public License (GPL), incorporated herein by reference. - Drivers based on or derived from this code fall under the GPL and must - retain the authorship, copyright and license notice. This file is not - a complete program and may only be used when the entire operating - system is licensed under the GPL. - - The author may be reached as becker@scyld.com, or C/O - Scyld Computing Corporation - 410 Severn Ave., Suite 210 - Annapolis MD 21403 - - Support information and updates available at - http://www.scyld.com/network/pci-skeleton.html - - Linux kernel updates: - - Version 2.51, Nov 17, 2001 (jgarzik): - - Add ethtool support - - Replace some MII-related magic numbers with constants - -*/ - -#define DRV_NAME "fealnx" - -static int debug; /* 1-> print debug message */ -static int max_interrupt_work = 20; - -/* Maximum number of multicast addresses to filter (vs. Rx-all-multicast). */ -static int multicast_filter_limit = 32; - -/* Set the copy breakpoint for the copy-only-tiny-frames scheme. */ -/* Setting to > 1518 effectively disables this feature. */ -static int rx_copybreak; - -/* Used to pass the media type, etc. */ -/* Both 'options[]' and 'full_duplex[]' should exist for driver */ -/* interoperability. */ -/* The media type is usually passed in 'options[]'. */ -#define MAX_UNITS 8 /* More are supported, limit only on options */ -static int options[MAX_UNITS] = { -1, -1, -1, -1, -1, -1, -1, -1 }; -static int full_duplex[MAX_UNITS] = { -1, -1, -1, -1, -1, -1, -1, -1 }; - -/* Operational parameters that are set at compile time. */ -/* Keep the ring sizes a power of two for compile efficiency. */ -/* The compiler will convert <unsigned>'%'<2^N> into a bit mask. */ -/* Making the Tx ring too large decreases the effectiveness of channel */ -/* bonding and packet priority. */ -/* There are no ill effects from too-large receive rings. */ -// 88-12-9 modify, -// #define TX_RING_SIZE 16 -// #define RX_RING_SIZE 32 -#define TX_RING_SIZE 6 -#define RX_RING_SIZE 12 -#define TX_TOTAL_SIZE TX_RING_SIZE*sizeof(struct fealnx_desc) -#define RX_TOTAL_SIZE RX_RING_SIZE*sizeof(struct fealnx_desc) - -/* Operational parameters that usually are not changed. */ -/* Time in jiffies before concluding the transmitter is hung. */ -#define TX_TIMEOUT (2*HZ) - -#define PKT_BUF_SZ 1536 /* Size of each temporary Rx buffer. */ - - -/* Include files, designed to support most kernel versions 2.0.0 and later. */ -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/timer.h> -#include <linux/errno.h> -#include <linux/ioport.h> -#include <linux/interrupt.h> -#include <linux/pci.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/mii.h> -#include <linux/ethtool.h> -#include <linux/crc32.h> -#include <linux/delay.h> -#include <linux/bitops.h> - -#include <asm/processor.h> /* Processor type for cache alignment. */ -#include <asm/io.h> -#include <linux/uaccess.h> -#include <asm/byteorder.h> - -/* This driver was written to use PCI memory space, however some x86 systems - work only with I/O space accesses. */ -#ifndef __alpha__ -#define USE_IO_OPS -#endif - -/* Kernel compatibility defines, some common to David Hinds' PCMCIA package. */ -/* This is only in the support-all-kernels source code. */ - -#define RUN_AT(x) (jiffies + (x)) - -MODULE_AUTHOR("Myson or whoever"); -MODULE_DESCRIPTION("Myson MTD-8xx 100/10M Ethernet PCI Adapter Driver"); -MODULE_LICENSE("GPL"); -module_param(max_interrupt_work, int, 0); -module_param(debug, int, 0); -module_param(rx_copybreak, int, 0); -module_param(multicast_filter_limit, int, 0); -module_param_array(options, int, NULL, 0); -module_param_array(full_duplex, int, NULL, 0); -MODULE_PARM_DESC(max_interrupt_work, "fealnx maximum events handled per interrupt"); -MODULE_PARM_DESC(debug, "fealnx enable debugging (0-1)"); -MODULE_PARM_DESC(rx_copybreak, "fealnx copy breakpoint for copy-only-tiny-frames"); -MODULE_PARM_DESC(multicast_filter_limit, "fealnx maximum number of filtered multicast addresses"); -MODULE_PARM_DESC(options, "fealnx: Bits 0-3: media type, bit 17: full duplex"); -MODULE_PARM_DESC(full_duplex, "fealnx full duplex setting(s) (1)"); - -enum { - MIN_REGION_SIZE = 136, -}; - -/* A chip capabilities table, matching the entries in pci_tbl[] above. */ -enum chip_capability_flags { - HAS_MII_XCVR, - HAS_CHIP_XCVR, -}; - -/* 89/6/13 add, */ -/* for different PHY */ -enum phy_type_flags { - MysonPHY = 1, - AhdocPHY = 2, - SeeqPHY = 3, - MarvellPHY = 4, - Myson981 = 5, - LevelOnePHY = 6, - OtherPHY = 10, -}; - -struct chip_info { - char *chip_name; - int flags; -}; - -static const struct chip_info skel_netdrv_tbl[] = { - { "100/10M Ethernet PCI Adapter", HAS_MII_XCVR }, - { "100/10M Ethernet PCI Adapter", HAS_CHIP_XCVR }, - { "1000/100/10M Ethernet PCI Adapter", HAS_MII_XCVR }, -}; - -/* Offsets to the Command and Status Registers. */ -enum fealnx_offsets { - PAR0 = 0x0, /* physical address 0-3 */ - PAR1 = 0x04, /* physical address 4-5 */ - MAR0 = 0x08, /* multicast address 0-3 */ - MAR1 = 0x0C, /* multicast address 4-7 */ - FAR0 = 0x10, /* flow-control address 0-3 */ - FAR1 = 0x14, /* flow-control address 4-5 */ - TCRRCR = 0x18, /* receive & transmit configuration */ - BCR = 0x1C, /* bus command */ - TXPDR = 0x20, /* transmit polling demand */ - RXPDR = 0x24, /* receive polling demand */ - RXCWP = 0x28, /* receive current word pointer */ - TXLBA = 0x2C, /* transmit list base address */ - RXLBA = 0x30, /* receive list base address */ - ISR = 0x34, /* interrupt status */ - IMR = 0x38, /* interrupt mask */ - FTH = 0x3C, /* flow control high/low threshold */ - MANAGEMENT = 0x40, /* bootrom/eeprom and mii management */ - TALLY = 0x44, /* tally counters for crc and mpa */ - TSR = 0x48, /* tally counter for transmit status */ - BMCRSR = 0x4c, /* basic mode control and status */ - PHYIDENTIFIER = 0x50, /* phy identifier */ - ANARANLPAR = 0x54, /* auto-negotiation advertisement and link - partner ability */ - ANEROCR = 0x58, /* auto-negotiation expansion and pci conf. */ - BPREMRPSR = 0x5c, /* bypass & receive error mask and phy status */ -}; - -/* Bits in the interrupt status/enable registers. */ -/* The bits in the Intr Status/Enable registers, mostly interrupt sources. */ -enum intr_status_bits { - RFCON = 0x00020000, /* receive flow control xon packet */ - RFCOFF = 0x00010000, /* receive flow control xoff packet */ - LSCStatus = 0x00008000, /* link status change */ - ANCStatus = 0x00004000, /* autonegotiation completed */ - FBE = 0x00002000, /* fatal bus error */ - FBEMask = 0x00001800, /* mask bit12-11 */ - ParityErr = 0x00000000, /* parity error */ - TargetErr = 0x00001000, /* target abort */ - MasterErr = 0x00000800, /* master error */ - TUNF = 0x00000400, /* transmit underflow */ - ROVF = 0x00000200, /* receive overflow */ - ETI = 0x00000100, /* transmit early int */ - ERI = 0x00000080, /* receive early int */ - CNTOVF = 0x00000040, /* counter overflow */ - RBU = 0x00000020, /* receive buffer unavailable */ - TBU = 0x00000010, /* transmit buffer unavilable */ - TI = 0x00000008, /* transmit interrupt */ - RI = 0x00000004, /* receive interrupt */ - RxErr = 0x00000002, /* receive error */ -}; - -/* Bits in the NetworkConfig register, W for writing, R for reading */ -/* FIXME: some names are invented by me. Marked with (name?) */ -/* If you have docs and know bit names, please fix 'em */ -enum rx_mode_bits { - CR_W_ENH = 0x02000000, /* enhanced mode (name?) */ - CR_W_FD = 0x00100000, /* full duplex */ - CR_W_PS10 = 0x00080000, /* 10 mbit */ - CR_W_TXEN = 0x00040000, /* tx enable (name?) */ - CR_W_PS1000 = 0x00010000, /* 1000 mbit */ - /* CR_W_RXBURSTMASK= 0x00000e00, Im unsure about this */ - CR_W_RXMODEMASK = 0x000000e0, - CR_W_PROM = 0x00000080, /* promiscuous mode */ - CR_W_AB = 0x00000040, /* accept broadcast */ - CR_W_AM = 0x00000020, /* accept mutlicast */ - CR_W_ARP = 0x00000008, /* receive runt pkt */ - CR_W_ALP = 0x00000004, /* receive long pkt */ - CR_W_SEP = 0x00000002, /* receive error pkt */ - CR_W_RXEN = 0x00000001, /* rx enable (unicast?) (name?) */ - - CR_R_TXSTOP = 0x04000000, /* tx stopped (name?) */ - CR_R_FD = 0x00100000, /* full duplex detected */ - CR_R_PS10 = 0x00080000, /* 10 mbit detected */ - CR_R_RXSTOP = 0x00008000, /* rx stopped (name?) */ -}; - -/* The Tulip Rx and Tx buffer descriptors. */ -struct fealnx_desc { - s32 status; - s32 control; - u32 buffer; - u32 next_desc; - struct fealnx_desc *next_desc_logical; - struct sk_buff *skbuff; - u32 reserved1; - u32 reserved2; -}; - -/* Bits in network_desc.status */ -enum rx_desc_status_bits { - RXOWN = 0x80000000, /* own bit */ - FLNGMASK = 0x0fff0000, /* frame length */ - FLNGShift = 16, - MARSTATUS = 0x00004000, /* multicast address received */ - BARSTATUS = 0x00002000, /* broadcast address received */ - PHYSTATUS = 0x00001000, /* physical address received */ - RXFSD = 0x00000800, /* first descriptor */ - RXLSD = 0x00000400, /* last descriptor */ - ErrorSummary = 0x80, /* error summary */ - RUNTPKT = 0x40, /* runt packet received */ - LONGPKT = 0x20, /* long packet received */ - FAE = 0x10, /* frame align error */ - CRC = 0x08, /* crc error */ - RXER = 0x04, /* receive error */ -}; - -enum rx_desc_control_bits { - RXIC = 0x00800000, /* interrupt control */ - RBSShift = 0, -}; - -enum tx_desc_status_bits { - TXOWN = 0x80000000, /* own bit */ - JABTO = 0x00004000, /* jabber timeout */ - CSL = 0x00002000, /* carrier sense lost */ - LC = 0x00001000, /* late collision */ - EC = 0x00000800, /* excessive collision */ - UDF = 0x00000400, /* fifo underflow */ - DFR = 0x00000200, /* deferred */ - HF = 0x00000100, /* heartbeat fail */ - NCRMask = 0x000000ff, /* collision retry count */ - NCRShift = 0, -}; - -enum tx_desc_control_bits { - TXIC = 0x80000000, /* interrupt control */ - ETIControl = 0x40000000, /* early transmit interrupt */ - TXLD = 0x20000000, /* last descriptor */ - TXFD = 0x10000000, /* first descriptor */ - CRCEnable = 0x08000000, /* crc control */ - PADEnable = 0x04000000, /* padding control */ - RetryTxLC = 0x02000000, /* retry late collision */ - PKTSMask = 0x3ff800, /* packet size bit21-11 */ - PKTSShift = 11, - TBSMask = 0x000007ff, /* transmit buffer bit 10-0 */ - TBSShift = 0, -}; - -/* BootROM/EEPROM/MII Management Register */ -#define MASK_MIIR_MII_READ 0x00000000 -#define MASK_MIIR_MII_WRITE 0x00000008 -#define MASK_MIIR_MII_MDO 0x00000004 -#define MASK_MIIR_MII_MDI 0x00000002 -#define MASK_MIIR_MII_MDC 0x00000001 - -/* ST+OP+PHYAD+REGAD+TA */ -#define OP_READ 0x6000 /* ST:01+OP:10+PHYAD+REGAD+TA:Z0 */ -#define OP_WRITE 0x5002 /* ST:01+OP:01+PHYAD+REGAD+TA:10 */ - -/* ------------------------------------------------------------------------- */ -/* Constants for Myson PHY */ -/* ------------------------------------------------------------------------- */ -#define MysonPHYID 0xd0000302 -/* 89-7-27 add, (begin) */ -#define MysonPHYID0 0x0302 -#define StatusRegister 18 -#define SPEED100 0x0400 // bit10 -#define FULLMODE 0x0800 // bit11 -/* 89-7-27 add, (end) */ - -/* ------------------------------------------------------------------------- */ -/* Constants for Seeq 80225 PHY */ -/* ------------------------------------------------------------------------- */ -#define SeeqPHYID0 0x0016 - -#define MIIRegister18 18 -#define SPD_DET_100 0x80 -#define DPLX_DET_FULL 0x40 - -/* ------------------------------------------------------------------------- */ -/* Constants for Ahdoc 101 PHY */ -/* ------------------------------------------------------------------------- */ -#define AhdocPHYID0 0x0022 - -#define DiagnosticReg 18 -#define DPLX_FULL 0x0800 -#define Speed_100 0x0400 - -/* 89/6/13 add, */ -/* -------------------------------------------------------------------------- */ -/* Constants */ -/* -------------------------------------------------------------------------- */ -#define MarvellPHYID0 0x0141 -#define LevelOnePHYID0 0x0013 - -#define MII1000BaseTControlReg 9 -#define MII1000BaseTStatusReg 10 -#define SpecificReg 17 - -/* for 1000BaseT Control Register */ -#define PHYAbletoPerform1000FullDuplex 0x0200 -#define PHYAbletoPerform1000HalfDuplex 0x0100 -#define PHY1000AbilityMask 0x300 - -// for phy specific status register, marvell phy. -#define SpeedMask 0x0c000 -#define Speed_1000M 0x08000 -#define Speed_100M 0x4000 -#define Speed_10M 0 -#define Full_Duplex 0x2000 - -// 89/12/29 add, for phy specific status register, levelone phy, (begin) -#define LXT1000_100M 0x08000 -#define LXT1000_1000M 0x0c000 -#define LXT1000_Full 0x200 -// 89/12/29 add, for phy specific status register, levelone phy, (end) - -/* for 3-in-1 case, BMCRSR register */ -#define LinkIsUp2 0x00040000 - -/* for PHY */ -#define LinkIsUp 0x0004 - - -struct netdev_private { - /* Descriptor rings first for alignment. */ - struct fealnx_desc *rx_ring; - struct fealnx_desc *tx_ring; - - dma_addr_t rx_ring_dma; - dma_addr_t tx_ring_dma; - - spinlock_t lock; - - /* Media monitoring timer. */ - struct timer_list timer; - - /* Reset timer */ - struct timer_list reset_timer; - int reset_timer_armed; - unsigned long crvalue_sv; - unsigned long imrvalue_sv; - - /* Frequently used values: keep some adjacent for cache effect. */ - int flags; - struct pci_dev *pci_dev; - unsigned long crvalue; - unsigned long bcrvalue; - unsigned long imrvalue; - struct fealnx_desc *cur_rx; - struct fealnx_desc *lack_rxbuf; - int really_rx_count; - struct fealnx_desc *cur_tx; - struct fealnx_desc *cur_tx_copy; - int really_tx_count; - int free_tx_count; - unsigned int rx_buf_sz; /* Based on MTU+slack. */ - - /* These values are keep track of the transceiver/media in use. */ - unsigned int linkok; - unsigned int line_speed; - unsigned int duplexmode; - unsigned int default_port:4; /* Last dev->if_port value. */ - unsigned int PHYType; - - /* MII transceiver section. */ - int mii_cnt; /* MII device addresses. */ - unsigned char phys[2]; /* MII device addresses. */ - struct mii_if_info mii; - void __iomem *mem; -}; - - -static int mdio_read(struct net_device *dev, int phy_id, int location); -static void mdio_write(struct net_device *dev, int phy_id, int location, int value); -static int netdev_open(struct net_device *dev); -static void getlinktype(struct net_device *dev); -static void getlinkstatus(struct net_device *dev); -static void netdev_timer(struct timer_list *t); -static void reset_timer(struct timer_list *t); -static void fealnx_tx_timeout(struct net_device *dev, unsigned int txqueue); -static void init_ring(struct net_device *dev); -static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev); -static irqreturn_t intr_handler(int irq, void *dev_instance); -static int netdev_rx(struct net_device *dev); -static void set_rx_mode(struct net_device *dev); -static void __set_rx_mode(struct net_device *dev); -static struct net_device_stats *get_stats(struct net_device *dev); -static int mii_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); -static const struct ethtool_ops netdev_ethtool_ops; -static int netdev_close(struct net_device *dev); -static void reset_rx_descriptors(struct net_device *dev); -static void reset_tx_descriptors(struct net_device *dev); - -static void stop_nic_rx(void __iomem *ioaddr, long crvalue) -{ - int delay = 0x1000; - iowrite32(crvalue & ~(CR_W_RXEN), ioaddr + TCRRCR); - while (--delay) { - if ( (ioread32(ioaddr + TCRRCR) & CR_R_RXSTOP) == CR_R_RXSTOP) - break; - } -} - - -static void stop_nic_rxtx(void __iomem *ioaddr, long crvalue) -{ - int delay = 0x1000; - iowrite32(crvalue & ~(CR_W_RXEN+CR_W_TXEN), ioaddr + TCRRCR); - while (--delay) { - if ( (ioread32(ioaddr + TCRRCR) & (CR_R_RXSTOP+CR_R_TXSTOP)) - == (CR_R_RXSTOP+CR_R_TXSTOP) ) - break; - } -} - -static const struct net_device_ops netdev_ops = { - .ndo_open = netdev_open, - .ndo_stop = netdev_close, - .ndo_start_xmit = start_tx, - .ndo_get_stats = get_stats, - .ndo_set_rx_mode = set_rx_mode, - .ndo_eth_ioctl = mii_ioctl, - .ndo_tx_timeout = fealnx_tx_timeout, - .ndo_set_mac_address = eth_mac_addr, - .ndo_validate_addr = eth_validate_addr, -}; - -static int fealnx_init_one(struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - struct netdev_private *np; - int i, option, err, irq; - static int card_idx = -1; - char boardname[12]; - void __iomem *ioaddr; - unsigned long len; - unsigned int chip_id = ent->driver_data; - struct net_device *dev; - void *ring_space; - dma_addr_t ring_dma; - u8 addr[ETH_ALEN]; -#ifdef USE_IO_OPS - int bar = 0; -#else - int bar = 1; -#endif - - card_idx++; - sprintf(boardname, "fealnx%d", card_idx); - - option = card_idx < MAX_UNITS ? options[card_idx] : 0; - - i = pci_enable_device(pdev); - if (i) return i; - pci_set_master(pdev); - - len = pci_resource_len(pdev, bar); - if (len < MIN_REGION_SIZE) { - dev_err(&pdev->dev, - "region size %ld too small, aborting\n", len); - return -ENODEV; - } - - i = pci_request_regions(pdev, boardname); - if (i) - return i; - - irq = pdev->irq; - - ioaddr = pci_iomap(pdev, bar, len); - if (!ioaddr) { - err = -ENOMEM; - goto err_out_res; - } - - dev = alloc_etherdev(sizeof(struct netdev_private)); - if (!dev) { - err = -ENOMEM; - goto err_out_unmap; - } - SET_NETDEV_DEV(dev, &pdev->dev); - - /* read ethernet id */ - for (i = 0; i < 6; ++i) - addr[i] = ioread8(ioaddr + PAR0 + i); - eth_hw_addr_set(dev, addr); - - /* Reset the chip to erase previous misconfiguration. */ - iowrite32(0x00000001, ioaddr + BCR); - - /* Make certain the descriptor lists are aligned. */ - np = netdev_priv(dev); - np->mem = ioaddr; - spin_lock_init(&np->lock); - np->pci_dev = pdev; - np->flags = skel_netdrv_tbl[chip_id].flags; - pci_set_drvdata(pdev, dev); - np->mii.dev = dev; - np->mii.mdio_read = mdio_read; - np->mii.mdio_write = mdio_write; - np->mii.phy_id_mask = 0x1f; - np->mii.reg_num_mask = 0x1f; - - ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, &ring_dma, - GFP_KERNEL); - if (!ring_space) { - err = -ENOMEM; - goto err_out_free_dev; - } - np->rx_ring = ring_space; - np->rx_ring_dma = ring_dma; - - ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, &ring_dma, - GFP_KERNEL); - if (!ring_space) { - err = -ENOMEM; - goto err_out_free_rx; - } - np->tx_ring = ring_space; - np->tx_ring_dma = ring_dma; - - /* find the connected MII xcvrs */ - if (np->flags == HAS_MII_XCVR) { - int phy, phy_idx = 0; - - for (phy = 1; phy < 32 && phy_idx < ARRAY_SIZE(np->phys); - phy++) { - int mii_status = mdio_read(dev, phy, 1); - - if (mii_status != 0xffff && mii_status != 0x0000) { - np->phys[phy_idx++] = phy; - dev_info(&pdev->dev, - "MII PHY found at address %d, status " - "0x%4.4x.\n", phy, mii_status); - /* get phy type */ - { - unsigned int data; - - data = mdio_read(dev, np->phys[0], 2); - if (data == SeeqPHYID0) - np->PHYType = SeeqPHY; - else if (data == AhdocPHYID0) - np->PHYType = AhdocPHY; - else if (data == MarvellPHYID0) - np->PHYType = MarvellPHY; - else if (data == MysonPHYID0) - np->PHYType = Myson981; - else if (data == LevelOnePHYID0) - np->PHYType = LevelOnePHY; - else - np->PHYType = OtherPHY; - } - } - } - - np->mii_cnt = phy_idx; - if (phy_idx == 0) - dev_warn(&pdev->dev, - "MII PHY not found -- this device may " - "not operate correctly.\n"); - } else { - np->phys[0] = 32; -/* 89/6/23 add, (begin) */ - /* get phy type */ - if (ioread32(ioaddr + PHYIDENTIFIER) == MysonPHYID) - np->PHYType = MysonPHY; - else - np->PHYType = OtherPHY; - } - np->mii.phy_id = np->phys[0]; - - if (dev->mem_start) - option = dev->mem_start; - - /* The lower four bits are the media type. */ - if (option > 0) { - if (option & 0x200) - np->mii.full_duplex = 1; - np->default_port = option & 15; - } - - if (card_idx < MAX_UNITS && full_duplex[card_idx] > 0) - np->mii.full_duplex = full_duplex[card_idx]; - - if (np->mii.full_duplex) { - dev_info(&pdev->dev, "Media type forced to Full Duplex.\n"); -/* 89/6/13 add, (begin) */ -// if (np->PHYType==MarvellPHY) - if ((np->PHYType == MarvellPHY) || (np->PHYType == LevelOnePHY)) { - unsigned int data; - - data = mdio_read(dev, np->phys[0], 9); - data = (data & 0xfcff) | 0x0200; - mdio_write(dev, np->phys[0], 9, data); - } -/* 89/6/13 add, (end) */ - if (np->flags == HAS_MII_XCVR) - mdio_write(dev, np->phys[0], MII_ADVERTISE, ADVERTISE_FULL); - else - iowrite32(ADVERTISE_FULL, ioaddr + ANARANLPAR); - np->mii.force_media = 1; - } - - dev->netdev_ops = &netdev_ops; - dev->ethtool_ops = &netdev_ethtool_ops; - dev->watchdog_timeo = TX_TIMEOUT; - - err = register_netdev(dev); - if (err) - goto err_out_free_tx; - - printk(KERN_INFO "%s: %s at %p, %pM, IRQ %d.\n", - dev->name, skel_netdrv_tbl[chip_id].chip_name, ioaddr, - dev->dev_addr, irq); - - return 0; - -err_out_free_tx: - dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring, - np->tx_ring_dma); -err_out_free_rx: - dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, np->rx_ring, - np->rx_ring_dma); -err_out_free_dev: - free_netdev(dev); -err_out_unmap: - pci_iounmap(pdev, ioaddr); -err_out_res: - pci_release_regions(pdev); - return err; -} - - -static void fealnx_remove_one(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata(pdev); - - if (dev) { - struct netdev_private *np = netdev_priv(dev); - - dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring, - np->tx_ring_dma); - dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, np->rx_ring, - np->rx_ring_dma); - unregister_netdev(dev); - pci_iounmap(pdev, np->mem); - free_netdev(dev); - pci_release_regions(pdev); - } else - printk(KERN_ERR "fealnx: remove for unknown device\n"); -} - - -static ulong m80x_send_cmd_to_phy(void __iomem *miiport, int opcode, int phyad, int regad) -{ - ulong miir; - int i; - unsigned int mask, data; - - /* enable MII output */ - miir = (ulong) ioread32(miiport); - miir &= 0xfffffff0; - - miir |= MASK_MIIR_MII_WRITE + MASK_MIIR_MII_MDO; - - /* send 32 1's preamble */ - for (i = 0; i < 32; i++) { - /* low MDC; MDO is already high (miir) */ - miir &= ~MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - - /* high MDC */ - miir |= MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - } - - /* calculate ST+OP+PHYAD+REGAD+TA */ - data = opcode | (phyad << 7) | (regad << 2); - - /* sent out */ - mask = 0x8000; - while (mask) { - /* low MDC, prepare MDO */ - miir &= ~(MASK_MIIR_MII_MDC + MASK_MIIR_MII_MDO); - if (mask & data) - miir |= MASK_MIIR_MII_MDO; - - iowrite32(miir, miiport); - /* high MDC */ - miir |= MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - udelay(30); - - /* next */ - mask >>= 1; - if (mask == 0x2 && opcode == OP_READ) - miir &= ~MASK_MIIR_MII_WRITE; - } - return miir; -} - - -static int mdio_read(struct net_device *dev, int phyad, int regad) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *miiport = np->mem + MANAGEMENT; - ulong miir; - unsigned int mask, data; - - miir = m80x_send_cmd_to_phy(miiport, OP_READ, phyad, regad); - - /* read data */ - mask = 0x8000; - data = 0; - while (mask) { - /* low MDC */ - miir &= ~MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - - /* read MDI */ - miir = ioread32(miiport); - if (miir & MASK_MIIR_MII_MDI) - data |= mask; - - /* high MDC, and wait */ - miir |= MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - udelay(30); - - /* next */ - mask >>= 1; - } - - /* low MDC */ - miir &= ~MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - - return data & 0xffff; -} - - -static void mdio_write(struct net_device *dev, int phyad, int regad, int data) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *miiport = np->mem + MANAGEMENT; - ulong miir; - unsigned int mask; - - miir = m80x_send_cmd_to_phy(miiport, OP_WRITE, phyad, regad); - - /* write data */ - mask = 0x8000; - while (mask) { - /* low MDC, prepare MDO */ - miir &= ~(MASK_MIIR_MII_MDC + MASK_MIIR_MII_MDO); - if (mask & data) - miir |= MASK_MIIR_MII_MDO; - iowrite32(miir, miiport); - - /* high MDC */ - miir |= MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); - - /* next */ - mask >>= 1; - } - - /* low MDC */ - miir &= ~MASK_MIIR_MII_MDC; - iowrite32(miir, miiport); -} - - -static int netdev_open(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - const int irq = np->pci_dev->irq; - int rc, i; - - iowrite32(0x00000001, ioaddr + BCR); /* Reset */ - - rc = request_irq(irq, intr_handler, IRQF_SHARED, dev->name, dev); - if (rc) - return -EAGAIN; - - for (i = 0; i < 3; i++) - iowrite16(((const unsigned short *)dev->dev_addr)[i], - ioaddr + PAR0 + i*2); - - init_ring(dev); - - iowrite32(np->rx_ring_dma, ioaddr + RXLBA); - iowrite32(np->tx_ring_dma, ioaddr + TXLBA); - - /* Initialize other registers. */ - /* Configure the PCI bus bursts and FIFO thresholds. - 486: Set 8 longword burst. - 586: no burst limit. - Burst length 5:3 - 0 0 0 1 - 0 0 1 4 - 0 1 0 8 - 0 1 1 16 - 1 0 0 32 - 1 0 1 64 - 1 1 0 128 - 1 1 1 256 - Wait the specified 50 PCI cycles after a reset by initializing - Tx and Rx queues and the address filter list. - FIXME (Ueimor): optimistic for alpha + posted writes ? */ - - np->bcrvalue = 0x10; /* little-endian, 8 burst length */ -#ifdef __BIG_ENDIAN - np->bcrvalue |= 0x04; /* big-endian */ -#endif - -#if defined(__i386__) && !defined(MODULE) && !defined(CONFIG_UML) - if (boot_cpu_data.x86 <= 4) - np->crvalue = 0xa00; - else -#endif - np->crvalue = 0xe00; /* rx 128 burst length */ - - -// 89/12/29 add, -// 90/1/16 modify, -// np->imrvalue=FBE|TUNF|CNTOVF|RBU|TI|RI; - np->imrvalue = TUNF | CNTOVF | RBU | TI | RI; - if (np->pci_dev->device == 0x891) { - np->bcrvalue |= 0x200; /* set PROG bit */ - np->crvalue |= CR_W_ENH; /* set enhanced bit */ - np->imrvalue |= ETI; - } - iowrite32(np->bcrvalue, ioaddr + BCR); - - if (dev->if_port == 0) - dev->if_port = np->default_port; - - iowrite32(0, ioaddr + RXPDR); -// 89/9/1 modify, -// np->crvalue = 0x00e40001; /* tx store and forward, tx/rx enable */ - np->crvalue |= 0x00e40001; /* tx store and forward, tx/rx enable */ - np->mii.full_duplex = np->mii.force_media; - getlinkstatus(dev); - if (np->linkok) - getlinktype(dev); - __set_rx_mode(dev); - - netif_start_queue(dev); - - /* Clear and Enable interrupts by setting the interrupt mask. */ - iowrite32(FBE | TUNF | CNTOVF | RBU | TI | RI, ioaddr + ISR); - iowrite32(np->imrvalue, ioaddr + IMR); - - if (debug) - printk(KERN_DEBUG "%s: Done netdev_open().\n", dev->name); - - /* Set the timer to check for link beat. */ - timer_setup(&np->timer, netdev_timer, 0); - np->timer.expires = RUN_AT(3 * HZ); - - /* timer handler */ - add_timer(&np->timer); - - timer_setup(&np->reset_timer, reset_timer, 0); - np->reset_timer_armed = 0; - return rc; -} - - -static void getlinkstatus(struct net_device *dev) -/* function: Routine will read MII Status Register to get link status. */ -/* input : dev... pointer to the adapter block. */ -/* output : none. */ -{ - struct netdev_private *np = netdev_priv(dev); - unsigned int i, DelayTime = 0x1000; - - np->linkok = 0; - - if (np->PHYType == MysonPHY) { - for (i = 0; i < DelayTime; ++i) { - if (ioread32(np->mem + BMCRSR) & LinkIsUp2) { - np->linkok = 1; - return; - } - udelay(100); - } - } else { - for (i = 0; i < DelayTime; ++i) { - if (mdio_read(dev, np->phys[0], MII_BMSR) & BMSR_LSTATUS) { - np->linkok = 1; - return; - } - udelay(100); - } - } -} - - -static void getlinktype(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - - if (np->PHYType == MysonPHY) { /* 3-in-1 case */ - if (ioread32(np->mem + TCRRCR) & CR_R_FD) - np->duplexmode = 2; /* full duplex */ - else - np->duplexmode = 1; /* half duplex */ - if (ioread32(np->mem + TCRRCR) & CR_R_PS10) - np->line_speed = 1; /* 10M */ - else - np->line_speed = 2; /* 100M */ - } else { - if (np->PHYType == SeeqPHY) { /* this PHY is SEEQ 80225 */ - unsigned int data; - - data = mdio_read(dev, np->phys[0], MIIRegister18); - if (data & SPD_DET_100) - np->line_speed = 2; /* 100M */ - else - np->line_speed = 1; /* 10M */ - if (data & DPLX_DET_FULL) - np->duplexmode = 2; /* full duplex mode */ - else - np->duplexmode = 1; /* half duplex mode */ - } else if (np->PHYType == AhdocPHY) { - unsigned int data; - - data = mdio_read(dev, np->phys[0], DiagnosticReg); - if (data & Speed_100) - np->line_speed = 2; /* 100M */ - else - np->line_speed = 1; /* 10M */ - if (data & DPLX_FULL) - np->duplexmode = 2; /* full duplex mode */ - else - np->duplexmode = 1; /* half duplex mode */ - } -/* 89/6/13 add, (begin) */ - else if (np->PHYType == MarvellPHY) { - unsigned int data; - - data = mdio_read(dev, np->phys[0], SpecificReg); - if (data & Full_Duplex) - np->duplexmode = 2; /* full duplex mode */ - else - np->duplexmode = 1; /* half duplex mode */ - data &= SpeedMask; - if (data == Speed_1000M) - np->line_speed = 3; /* 1000M */ - else if (data == Speed_100M) - np->line_speed = 2; /* 100M */ - else - np->line_speed = 1; /* 10M */ - } -/* 89/6/13 add, (end) */ -/* 89/7/27 add, (begin) */ - else if (np->PHYType == Myson981) { - unsigned int data; - - data = mdio_read(dev, np->phys[0], StatusRegister); - - if (data & SPEED100) - np->line_speed = 2; - else - np->line_speed = 1; - - if (data & FULLMODE) - np->duplexmode = 2; - else - np->duplexmode = 1; - } -/* 89/7/27 add, (end) */ -/* 89/12/29 add */ - else if (np->PHYType == LevelOnePHY) { - unsigned int data; - - data = mdio_read(dev, np->phys[0], SpecificReg); - if (data & LXT1000_Full) - np->duplexmode = 2; /* full duplex mode */ - else - np->duplexmode = 1; /* half duplex mode */ - data &= SpeedMask; - if (data == LXT1000_1000M) - np->line_speed = 3; /* 1000M */ - else if (data == LXT1000_100M) - np->line_speed = 2; /* 100M */ - else - np->line_speed = 1; /* 10M */ - } - np->crvalue &= (~CR_W_PS10) & (~CR_W_FD) & (~CR_W_PS1000); - if (np->line_speed == 1) - np->crvalue |= CR_W_PS10; - else if (np->line_speed == 3) - np->crvalue |= CR_W_PS1000; - if (np->duplexmode == 2) - np->crvalue |= CR_W_FD; - } -} - - -/* Take lock before calling this */ -static void allocate_rx_buffers(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - - /* allocate skb for rx buffers */ - while (np->really_rx_count != RX_RING_SIZE) { - struct sk_buff *skb; - - skb = netdev_alloc_skb(dev, np->rx_buf_sz); - if (skb == NULL) - break; /* Better luck next round. */ - - while (np->lack_rxbuf->skbuff) - np->lack_rxbuf = np->lack_rxbuf->next_desc_logical; - - np->lack_rxbuf->skbuff = skb; - np->lack_rxbuf->buffer = dma_map_single(&np->pci_dev->dev, - skb->data, - np->rx_buf_sz, - DMA_FROM_DEVICE); - np->lack_rxbuf->status = RXOWN; - ++np->really_rx_count; - } -} - - -static void netdev_timer(struct timer_list *t) -{ - struct netdev_private *np = from_timer(np, t, timer); - struct net_device *dev = np->mii.dev; - void __iomem *ioaddr = np->mem; - int old_crvalue = np->crvalue; - unsigned int old_linkok = np->linkok; - unsigned long flags; - - if (debug) - printk(KERN_DEBUG "%s: Media selection timer tick, status %8.8x " - "config %8.8x.\n", dev->name, ioread32(ioaddr + ISR), - ioread32(ioaddr + TCRRCR)); - - spin_lock_irqsave(&np->lock, flags); - - if (np->flags == HAS_MII_XCVR) { - getlinkstatus(dev); - if ((old_linkok == 0) && (np->linkok == 1)) { /* we need to detect the media type again */ - getlinktype(dev); - if (np->crvalue != old_crvalue) { - stop_nic_rxtx(ioaddr, np->crvalue); - iowrite32(np->crvalue, ioaddr + TCRRCR); - } - } - } - - allocate_rx_buffers(dev); - - spin_unlock_irqrestore(&np->lock, flags); - - np->timer.expires = RUN_AT(10 * HZ); - add_timer(&np->timer); -} - - -/* Take lock before calling */ -/* Reset chip and disable rx, tx and interrupts */ -static void reset_and_disable_rxtx(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - int delay=51; - - /* Reset the chip's Tx and Rx processes. */ - stop_nic_rxtx(ioaddr, 0); - - /* Disable interrupts by clearing the interrupt mask. */ - iowrite32(0, ioaddr + IMR); - - /* Reset the chip to erase previous misconfiguration. */ - iowrite32(0x00000001, ioaddr + BCR); - - /* Ueimor: wait for 50 PCI cycles (and flush posted writes btw). - We surely wait too long (address+data phase). Who cares? */ - while (--delay) { - ioread32(ioaddr + BCR); - rmb(); - } -} - - -/* Take lock before calling */ -/* Restore chip after reset */ -static void enable_rxtx(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - - reset_rx_descriptors(dev); - - iowrite32(np->tx_ring_dma + ((char*)np->cur_tx - (char*)np->tx_ring), - ioaddr + TXLBA); - iowrite32(np->rx_ring_dma + ((char*)np->cur_rx - (char*)np->rx_ring), - ioaddr + RXLBA); - - iowrite32(np->bcrvalue, ioaddr + BCR); - - iowrite32(0, ioaddr + RXPDR); - __set_rx_mode(dev); /* changes np->crvalue, writes it into TCRRCR */ - - /* Clear and Enable interrupts by setting the interrupt mask. */ - iowrite32(FBE | TUNF | CNTOVF | RBU | TI | RI, ioaddr + ISR); - iowrite32(np->imrvalue, ioaddr + IMR); - - iowrite32(0, ioaddr + TXPDR); -} - - -static void reset_timer(struct timer_list *t) -{ - struct netdev_private *np = from_timer(np, t, reset_timer); - struct net_device *dev = np->mii.dev; - unsigned long flags; - - printk(KERN_WARNING "%s: resetting tx and rx machinery\n", dev->name); - - spin_lock_irqsave(&np->lock, flags); - np->crvalue = np->crvalue_sv; - np->imrvalue = np->imrvalue_sv; - - reset_and_disable_rxtx(dev); - /* works for me without this: - reset_tx_descriptors(dev); */ - enable_rxtx(dev); - netif_start_queue(dev); /* FIXME: or netif_wake_queue(dev); ? */ - - np->reset_timer_armed = 0; - - spin_unlock_irqrestore(&np->lock, flags); -} - - -static void fealnx_tx_timeout(struct net_device *dev, unsigned int txqueue) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - unsigned long flags; - int i; - - printk(KERN_WARNING - "%s: Transmit timed out, status %8.8x, resetting...\n", - dev->name, ioread32(ioaddr + ISR)); - - { - printk(KERN_DEBUG " Rx ring %p: ", np->rx_ring); - for (i = 0; i < RX_RING_SIZE; i++) - printk(KERN_CONT " %8.8x", - (unsigned int) np->rx_ring[i].status); - printk(KERN_CONT "\n"); - printk(KERN_DEBUG " Tx ring %p: ", np->tx_ring); - for (i = 0; i < TX_RING_SIZE; i++) - printk(KERN_CONT " %4.4x", np->tx_ring[i].status); - printk(KERN_CONT "\n"); - } - - spin_lock_irqsave(&np->lock, flags); - - reset_and_disable_rxtx(dev); - reset_tx_descriptors(dev); - enable_rxtx(dev); - - spin_unlock_irqrestore(&np->lock, flags); - - netif_trans_update(dev); /* prevent tx timeout */ - dev->stats.tx_errors++; - netif_wake_queue(dev); /* or .._start_.. ?? */ -} - - -/* Initialize the Rx and Tx rings, along with various 'dev' bits. */ -static void init_ring(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - int i; - - /* initialize rx variables */ - np->rx_buf_sz = (dev->mtu <= 1500 ? PKT_BUF_SZ : dev->mtu + 32); - np->cur_rx = &np->rx_ring[0]; - np->lack_rxbuf = np->rx_ring; - np->really_rx_count = 0; - - /* initial rx descriptors. */ - for (i = 0; i < RX_RING_SIZE; i++) { - np->rx_ring[i].status = 0; - np->rx_ring[i].control = np->rx_buf_sz << RBSShift; - np->rx_ring[i].next_desc = np->rx_ring_dma + - (i + 1)*sizeof(struct fealnx_desc); - np->rx_ring[i].next_desc_logical = &np->rx_ring[i + 1]; - np->rx_ring[i].skbuff = NULL; - } - - /* for the last rx descriptor */ - np->rx_ring[i - 1].next_desc = np->rx_ring_dma; - np->rx_ring[i - 1].next_desc_logical = np->rx_ring; - - /* allocate skb for rx buffers */ - for (i = 0; i < RX_RING_SIZE; i++) { - struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz); - - if (skb == NULL) { - np->lack_rxbuf = &np->rx_ring[i]; - break; - } - - ++np->really_rx_count; - np->rx_ring[i].skbuff = skb; - np->rx_ring[i].buffer = dma_map_single(&np->pci_dev->dev, - skb->data, - np->rx_buf_sz, - DMA_FROM_DEVICE); - np->rx_ring[i].status = RXOWN; - np->rx_ring[i].control |= RXIC; - } - - /* initialize tx variables */ - np->cur_tx = &np->tx_ring[0]; - np->cur_tx_copy = &np->tx_ring[0]; - np->really_tx_count = 0; - np->free_tx_count = TX_RING_SIZE; - - for (i = 0; i < TX_RING_SIZE; i++) { - np->tx_ring[i].status = 0; - /* do we need np->tx_ring[i].control = XXX; ?? */ - np->tx_ring[i].next_desc = np->tx_ring_dma + - (i + 1)*sizeof(struct fealnx_desc); - np->tx_ring[i].next_desc_logical = &np->tx_ring[i + 1]; - np->tx_ring[i].skbuff = NULL; - } - - /* for the last tx descriptor */ - np->tx_ring[i - 1].next_desc = np->tx_ring_dma; - np->tx_ring[i - 1].next_desc_logical = &np->tx_ring[0]; -} - - -static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - unsigned long flags; - - spin_lock_irqsave(&np->lock, flags); - - np->cur_tx_copy->skbuff = skb; - -#define one_buffer -#define BPT 1022 -#if defined(one_buffer) - np->cur_tx_copy->buffer = dma_map_single(&np->pci_dev->dev, skb->data, - skb->len, DMA_TO_DEVICE); - np->cur_tx_copy->control = TXIC | TXLD | TXFD | CRCEnable | PADEnable; - np->cur_tx_copy->control |= (skb->len << PKTSShift); /* pkt size */ - np->cur_tx_copy->control |= (skb->len << TBSShift); /* buffer size */ -// 89/12/29 add, - if (np->pci_dev->device == 0x891) - np->cur_tx_copy->control |= ETIControl | RetryTxLC; - np->cur_tx_copy->status = TXOWN; - np->cur_tx_copy = np->cur_tx_copy->next_desc_logical; - --np->free_tx_count; -#elif defined(two_buffer) - if (skb->len > BPT) { - struct fealnx_desc *next; - - /* for the first descriptor */ - np->cur_tx_copy->buffer = dma_map_single(&np->pci_dev->dev, - skb->data, BPT, - DMA_TO_DEVICE); - np->cur_tx_copy->control = TXIC | TXFD | CRCEnable | PADEnable; - np->cur_tx_copy->control |= (skb->len << PKTSShift); /* pkt size */ - np->cur_tx_copy->control |= (BPT << TBSShift); /* buffer size */ - - /* for the last descriptor */ - next = np->cur_tx_copy->next_desc_logical; - next->skbuff = skb; - next->control = TXIC | TXLD | CRCEnable | PADEnable; - next->control |= (skb->len << PKTSShift); /* pkt size */ - next->control |= ((skb->len - BPT) << TBSShift); /* buf size */ -// 89/12/29 add, - if (np->pci_dev->device == 0x891) - np->cur_tx_copy->control |= ETIControl | RetryTxLC; - next->buffer = dma_map_single(&ep->pci_dev->dev, - skb->data + BPT, skb->len - BPT, - DMA_TO_DEVICE); - - next->status = TXOWN; - np->cur_tx_copy->status = TXOWN; - - np->cur_tx_copy = next->next_desc_logical; - np->free_tx_count -= 2; - } else { - np->cur_tx_copy->buffer = dma_map_single(&np->pci_dev->dev, - skb->data, skb->len, - DMA_TO_DEVICE); - np->cur_tx_copy->control = TXIC | TXLD | TXFD | CRCEnable | PADEnable; - np->cur_tx_copy->control |= (skb->len << PKTSShift); /* pkt size */ - np->cur_tx_copy->control |= (skb->len << TBSShift); /* buffer size */ -// 89/12/29 add, - if (np->pci_dev->device == 0x891) - np->cur_tx_copy->control |= ETIControl | RetryTxLC; - np->cur_tx_copy->status = TXOWN; - np->cur_tx_copy = np->cur_tx_copy->next_desc_logical; - --np->free_tx_count; - } -#endif - - if (np->free_tx_count < 2) - netif_stop_queue(dev); - ++np->really_tx_count; - iowrite32(0, np->mem + TXPDR); - - spin_unlock_irqrestore(&np->lock, flags); - return NETDEV_TX_OK; -} - - -/* Take lock before calling */ -/* Chip probably hosed tx ring. Clean up. */ -static void reset_tx_descriptors(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - struct fealnx_desc *cur; - int i; - - /* initialize tx variables */ - np->cur_tx = &np->tx_ring[0]; - np->cur_tx_copy = &np->tx_ring[0]; - np->really_tx_count = 0; - np->free_tx_count = TX_RING_SIZE; - - for (i = 0; i < TX_RING_SIZE; i++) { - cur = &np->tx_ring[i]; - if (cur->skbuff) { - dma_unmap_single(&np->pci_dev->dev, cur->buffer, - cur->skbuff->len, DMA_TO_DEVICE); - dev_kfree_skb_any(cur->skbuff); - cur->skbuff = NULL; - } - cur->status = 0; - cur->control = 0; /* needed? */ - /* probably not needed. We do it for purely paranoid reasons */ - cur->next_desc = np->tx_ring_dma + - (i + 1)*sizeof(struct fealnx_desc); - cur->next_desc_logical = &np->tx_ring[i + 1]; - } - /* for the last tx descriptor */ - np->tx_ring[TX_RING_SIZE - 1].next_desc = np->tx_ring_dma; - np->tx_ring[TX_RING_SIZE - 1].next_desc_logical = &np->tx_ring[0]; -} - - -/* Take lock and stop rx before calling this */ -static void reset_rx_descriptors(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - struct fealnx_desc *cur = np->cur_rx; - int i; - - allocate_rx_buffers(dev); - - for (i = 0; i < RX_RING_SIZE; i++) { - if (cur->skbuff) - cur->status = RXOWN; - cur = cur->next_desc_logical; - } - - iowrite32(np->rx_ring_dma + ((char*)np->cur_rx - (char*)np->rx_ring), - np->mem + RXLBA); -} - - -/* The interrupt handler does all of the Rx thread work and cleans up - after the Tx thread. */ -static irqreturn_t intr_handler(int irq, void *dev_instance) -{ - struct net_device *dev = (struct net_device *) dev_instance; - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - long boguscnt = max_interrupt_work; - unsigned int num_tx = 0; - int handled = 0; - - spin_lock(&np->lock); - - iowrite32(0, ioaddr + IMR); - - do { - u32 intr_status = ioread32(ioaddr + ISR); - - /* Acknowledge all of the current interrupt sources ASAP. */ - iowrite32(intr_status, ioaddr + ISR); - - if (debug) - printk(KERN_DEBUG "%s: Interrupt, status %4.4x.\n", dev->name, - intr_status); - - if (!(intr_status & np->imrvalue)) - break; - - handled = 1; - -// 90/1/16 delete, -// -// if (intr_status & FBE) -// { /* fatal error */ -// stop_nic_tx(ioaddr, 0); -// stop_nic_rx(ioaddr, 0); -// break; -// }; - - if (intr_status & TUNF) - iowrite32(0, ioaddr + TXPDR); - - if (intr_status & CNTOVF) { - /* missed pkts */ - dev->stats.rx_missed_errors += - ioread32(ioaddr + TALLY) & 0x7fff; - - /* crc error */ - dev->stats.rx_crc_errors += - (ioread32(ioaddr + TALLY) & 0x7fff0000) >> 16; - } - - if (intr_status & (RI | RBU)) { - if (intr_status & RI) - netdev_rx(dev); - else { - stop_nic_rx(ioaddr, np->crvalue); - reset_rx_descriptors(dev); - iowrite32(np->crvalue, ioaddr + TCRRCR); - } - } - - while (np->really_tx_count) { - long tx_status = np->cur_tx->status; - long tx_control = np->cur_tx->control; - - if (!(tx_control & TXLD)) { /* this pkt is combined by two tx descriptors */ - struct fealnx_desc *next; - - next = np->cur_tx->next_desc_logical; - tx_status = next->status; - tx_control = next->control; - } - - if (tx_status & TXOWN) - break; - - if (!(np->crvalue & CR_W_ENH)) { - if (tx_status & (CSL | LC | EC | UDF | HF)) { - dev->stats.tx_errors++; - if (tx_status & EC) - dev->stats.tx_aborted_errors++; - if (tx_status & CSL) - dev->stats.tx_carrier_errors++; - if (tx_status & LC) - dev->stats.tx_window_errors++; - if (tx_status & UDF) - dev->stats.tx_fifo_errors++; - if ((tx_status & HF) && np->mii.full_duplex == 0) - dev->stats.tx_heartbeat_errors++; - - } else { - dev->stats.tx_bytes += - ((tx_control & PKTSMask) >> PKTSShift); - - dev->stats.collisions += - ((tx_status & NCRMask) >> NCRShift); - dev->stats.tx_packets++; - } - } else { - dev->stats.tx_bytes += - ((tx_control & PKTSMask) >> PKTSShift); - dev->stats.tx_packets++; - } - - /* Free the original skb. */ - dma_unmap_single(&np->pci_dev->dev, - np->cur_tx->buffer, - np->cur_tx->skbuff->len, - DMA_TO_DEVICE); - dev_consume_skb_irq(np->cur_tx->skbuff); - np->cur_tx->skbuff = NULL; - --np->really_tx_count; - if (np->cur_tx->control & TXLD) { - np->cur_tx = np->cur_tx->next_desc_logical; - ++np->free_tx_count; - } else { - np->cur_tx = np->cur_tx->next_desc_logical; - np->cur_tx = np->cur_tx->next_desc_logical; - np->free_tx_count += 2; - } - num_tx++; - } /* end of for loop */ - - if (num_tx && np->free_tx_count >= 2) - netif_wake_queue(dev); - - /* read transmit status for enhanced mode only */ - if (np->crvalue & CR_W_ENH) { - long data; - - data = ioread32(ioaddr + TSR); - dev->stats.tx_errors += (data & 0xff000000) >> 24; - dev->stats.tx_aborted_errors += - (data & 0xff000000) >> 24; - dev->stats.tx_window_errors += - (data & 0x00ff0000) >> 16; - dev->stats.collisions += (data & 0x0000ffff); - } - - if (--boguscnt < 0) { - printk(KERN_WARNING "%s: Too much work at interrupt, " - "status=0x%4.4x.\n", dev->name, intr_status); - if (!np->reset_timer_armed) { - np->reset_timer_armed = 1; - np->reset_timer.expires = RUN_AT(HZ/2); - add_timer(&np->reset_timer); - stop_nic_rxtx(ioaddr, 0); - netif_stop_queue(dev); - /* or netif_tx_disable(dev); ?? */ - /* Prevent other paths from enabling tx,rx,intrs */ - np->crvalue_sv = np->crvalue; - np->imrvalue_sv = np->imrvalue; - np->crvalue &= ~(CR_W_TXEN | CR_W_RXEN); /* or simply = 0? */ - np->imrvalue = 0; - } - - break; - } - } while (1); - - /* read the tally counters */ - /* missed pkts */ - dev->stats.rx_missed_errors += ioread32(ioaddr + TALLY) & 0x7fff; - - /* crc error */ - dev->stats.rx_crc_errors += - (ioread32(ioaddr + TALLY) & 0x7fff0000) >> 16; - - if (debug) - printk(KERN_DEBUG "%s: exiting interrupt, status=%#4.4x.\n", - dev->name, ioread32(ioaddr + ISR)); - - iowrite32(np->imrvalue, ioaddr + IMR); - - spin_unlock(&np->lock); - - return IRQ_RETVAL(handled); -} - - -/* This routine is logically part of the interrupt handler, but separated - for clarity and better register allocation. */ -static int netdev_rx(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - - /* If EOP is set on the next entry, it's a new packet. Send it up. */ - while (!(np->cur_rx->status & RXOWN) && np->cur_rx->skbuff) { - s32 rx_status = np->cur_rx->status; - - if (np->really_rx_count == 0) - break; - - if (debug) - printk(KERN_DEBUG " netdev_rx() status was %8.8x.\n", rx_status); - - if ((!((rx_status & RXFSD) && (rx_status & RXLSD))) || - (rx_status & ErrorSummary)) { - if (rx_status & ErrorSummary) { /* there was a fatal error */ - if (debug) - printk(KERN_DEBUG - "%s: Receive error, Rx status %8.8x.\n", - dev->name, rx_status); - - dev->stats.rx_errors++; /* end of a packet. */ - if (rx_status & (LONGPKT | RUNTPKT)) - dev->stats.rx_length_errors++; - if (rx_status & RXER) - dev->stats.rx_frame_errors++; - if (rx_status & CRC) - dev->stats.rx_crc_errors++; - } else { - int need_to_reset = 0; - int desno = 0; - - if (rx_status & RXFSD) { /* this pkt is too long, over one rx buffer */ - struct fealnx_desc *cur; - - /* check this packet is received completely? */ - cur = np->cur_rx; - while (desno <= np->really_rx_count) { - ++desno; - if ((!(cur->status & RXOWN)) && - (cur->status & RXLSD)) - break; - /* goto next rx descriptor */ - cur = cur->next_desc_logical; - } - if (desno > np->really_rx_count) - need_to_reset = 1; - } else /* RXLSD did not find, something error */ - need_to_reset = 1; - - if (need_to_reset == 0) { - int i; - - dev->stats.rx_length_errors++; - - /* free all rx descriptors related this long pkt */ - for (i = 0; i < desno; ++i) { - if (!np->cur_rx->skbuff) { - printk(KERN_DEBUG - "%s: I'm scared\n", dev->name); - break; - } - np->cur_rx->status = RXOWN; - np->cur_rx = np->cur_rx->next_desc_logical; - } - continue; - } else { /* rx error, need to reset this chip */ - stop_nic_rx(ioaddr, np->crvalue); - reset_rx_descriptors(dev); - iowrite32(np->crvalue, ioaddr + TCRRCR); - } - break; /* exit the while loop */ - } - } else { /* this received pkt is ok */ - - struct sk_buff *skb; - /* Omit the four octet CRC from the length. */ - short pkt_len = ((rx_status & FLNGMASK) >> FLNGShift) - 4; - -#ifndef final_version - if (debug) - printk(KERN_DEBUG " netdev_rx() normal Rx pkt length %d" - " status %x.\n", pkt_len, rx_status); -#endif - - /* Check if the packet is long enough to accept without copying - to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak && - (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { - skb_reserve(skb, 2); /* 16 byte align the IP header */ - dma_sync_single_for_cpu(&np->pci_dev->dev, - np->cur_rx->buffer, - np->rx_buf_sz, - DMA_FROM_DEVICE); - /* Call copy + cksum if available. */ - -#if ! defined(__alpha__) - skb_copy_to_linear_data(skb, - np->cur_rx->skbuff->data, pkt_len); - skb_put(skb, pkt_len); -#else - skb_put_data(skb, np->cur_rx->skbuff->data, - pkt_len); -#endif - dma_sync_single_for_device(&np->pci_dev->dev, - np->cur_rx->buffer, - np->rx_buf_sz, - DMA_FROM_DEVICE); - } else { - dma_unmap_single(&np->pci_dev->dev, - np->cur_rx->buffer, - np->rx_buf_sz, - DMA_FROM_DEVICE); - skb_put(skb = np->cur_rx->skbuff, pkt_len); - np->cur_rx->skbuff = NULL; - --np->really_rx_count; - } - skb->protocol = eth_type_trans(skb, dev); - netif_rx(skb); - dev->stats.rx_packets++; - dev->stats.rx_bytes += pkt_len; - } - - np->cur_rx = np->cur_rx->next_desc_logical; - } /* end of while loop */ - - /* allocate skb for rx buffers */ - allocate_rx_buffers(dev); - - return 0; -} - - -static struct net_device_stats *get_stats(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - - /* The chip only need report frame silently dropped. */ - if (netif_running(dev)) { - dev->stats.rx_missed_errors += - ioread32(ioaddr + TALLY) & 0x7fff; - dev->stats.rx_crc_errors += - (ioread32(ioaddr + TALLY) & 0x7fff0000) >> 16; - } - - return &dev->stats; -} - - -/* for dev->set_multicast_list */ -static void set_rx_mode(struct net_device *dev) -{ - spinlock_t *lp = &((struct netdev_private *)netdev_priv(dev))->lock; - unsigned long flags; - spin_lock_irqsave(lp, flags); - __set_rx_mode(dev); - spin_unlock_irqrestore(lp, flags); -} - - -/* Take lock before calling */ -static void __set_rx_mode(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - u32 mc_filter[2]; /* Multicast hash filter */ - u32 rx_mode; - - if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ - memset(mc_filter, 0xff, sizeof(mc_filter)); - rx_mode = CR_W_PROM | CR_W_AB | CR_W_AM; - } else if ((netdev_mc_count(dev) > multicast_filter_limit) || - (dev->flags & IFF_ALLMULTI)) { - /* Too many to match, or accept all multicasts. */ - memset(mc_filter, 0xff, sizeof(mc_filter)); - rx_mode = CR_W_AB | CR_W_AM; - } else { - struct netdev_hw_addr *ha; - - memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(ha, dev) { - unsigned int bit; - bit = (ether_crc(ETH_ALEN, ha->addr) >> 26) ^ 0x3F; - mc_filter[bit >> 5] |= (1 << bit); - } - rx_mode = CR_W_AB | CR_W_AM; - } - - stop_nic_rxtx(ioaddr, np->crvalue); - - iowrite32(mc_filter[0], ioaddr + MAR0); - iowrite32(mc_filter[1], ioaddr + MAR1); - np->crvalue &= ~CR_W_RXMODEMASK; - np->crvalue |= rx_mode; - iowrite32(np->crvalue, ioaddr + TCRRCR); -} - -static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) -{ - struct netdev_private *np = netdev_priv(dev); - - strscpy(info->driver, DRV_NAME, sizeof(info->driver)); - strscpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); -} - -static int netdev_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct netdev_private *np = netdev_priv(dev); - - spin_lock_irq(&np->lock); - mii_ethtool_get_link_ksettings(&np->mii, cmd); - spin_unlock_irq(&np->lock); - - return 0; -} - -static int netdev_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct netdev_private *np = netdev_priv(dev); - int rc; - - spin_lock_irq(&np->lock); - rc = mii_ethtool_set_link_ksettings(&np->mii, cmd); - spin_unlock_irq(&np->lock); - - return rc; -} - -static int netdev_nway_reset(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - return mii_nway_restart(&np->mii); -} - -static u32 netdev_get_link(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - return mii_link_ok(&np->mii); -} - -static u32 netdev_get_msglevel(struct net_device *dev) -{ - return debug; -} - -static void netdev_set_msglevel(struct net_device *dev, u32 value) -{ - debug = value; -} - -static const struct ethtool_ops netdev_ethtool_ops = { - .get_drvinfo = netdev_get_drvinfo, - .nway_reset = netdev_nway_reset, - .get_link = netdev_get_link, - .get_msglevel = netdev_get_msglevel, - .set_msglevel = netdev_set_msglevel, - .get_link_ksettings = netdev_get_link_ksettings, - .set_link_ksettings = netdev_set_link_ksettings, -}; - -static int mii_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct netdev_private *np = netdev_priv(dev); - int rc; - - if (!netif_running(dev)) - return -EINVAL; - - spin_lock_irq(&np->lock); - rc = generic_mii_ioctl(&np->mii, if_mii(rq), cmd, NULL); - spin_unlock_irq(&np->lock); - - return rc; -} - - -static int netdev_close(struct net_device *dev) -{ - struct netdev_private *np = netdev_priv(dev); - void __iomem *ioaddr = np->mem; - int i; - - netif_stop_queue(dev); - - /* Disable interrupts by clearing the interrupt mask. */ - iowrite32(0x0000, ioaddr + IMR); - - /* Stop the chip's Tx and Rx processes. */ - stop_nic_rxtx(ioaddr, 0); - - del_timer_sync(&np->timer); - del_timer_sync(&np->reset_timer); - - free_irq(np->pci_dev->irq, dev); - - /* Free all the skbuffs in the Rx queue. */ - for (i = 0; i < RX_RING_SIZE; i++) { - struct sk_buff *skb = np->rx_ring[i].skbuff; - - np->rx_ring[i].status = 0; - if (skb) { - dma_unmap_single(&np->pci_dev->dev, - np->rx_ring[i].buffer, np->rx_buf_sz, - DMA_FROM_DEVICE); - dev_kfree_skb(skb); - np->rx_ring[i].skbuff = NULL; - } - } - - for (i = 0; i < TX_RING_SIZE; i++) { - struct sk_buff *skb = np->tx_ring[i].skbuff; - - if (skb) { - dma_unmap_single(&np->pci_dev->dev, - np->tx_ring[i].buffer, skb->len, - DMA_TO_DEVICE); - dev_kfree_skb(skb); - np->tx_ring[i].skbuff = NULL; - } - } - - return 0; -} - -static const struct pci_device_id fealnx_pci_tbl[] = { - {0x1516, 0x0800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {0x1516, 0x0803, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1}, - {0x1516, 0x0891, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 2}, - {} /* terminate list */ -}; -MODULE_DEVICE_TABLE(pci, fealnx_pci_tbl); - - -static struct pci_driver fealnx_driver = { - .name = "fealnx", - .id_table = fealnx_pci_tbl, - .probe = fealnx_init_one, - .remove = fealnx_remove_one, -}; - -module_pci_driver(fealnx_driver); diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index ce866ae3df03..f1e80d6996ef 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -29,6 +29,7 @@ config FEC select CRC32 select PHYLIB select PAGE_POOL + select PAGE_POOL_STATS imply NET_SELFTESTS help Say Y here if you want to use the built-in 10/100 Fast ethernet diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig index 0e1439fd00bd..2b560661c82a 100644 --- a/drivers/net/ethernet/freescale/dpaa/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa/Kconfig @@ -2,8 +2,8 @@ menuconfig FSL_DPAA_ETH tristate "DPAA Ethernet" depends on FSL_DPAA && FSL_FMAN - select PHYLIB - select FIXED_PHY + select PHYLINK + select PCS_LYNX help Data Path Acceleration Architecture Ethernet driver, supporting the Freescale QorIQ chips. diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index fc68a32ce2f7..3f8032947d86 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -264,8 +264,19 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->needed_headroom = priv->tx_headroom; net_dev->watchdog_timeo = msecs_to_jiffies(tx_timeout); - mac_dev->net_dev = net_dev; + /* The rest of the config is filled in by the mac device already */ + mac_dev->phylink_config.dev = &net_dev->dev; + mac_dev->phylink_config.type = PHYLINK_NETDEV; mac_dev->update_speed = dpaa_eth_cgr_set_speed; + mac_dev->phylink = phylink_create(&mac_dev->phylink_config, + dev_fwnode(mac_dev->dev), + mac_dev->phy_if, + mac_dev->phylink_ops); + if (IS_ERR(mac_dev->phylink)) { + err = PTR_ERR(mac_dev->phylink); + dev_err_probe(dev, err, "Could not create phylink\n"); + return err; + } /* start without the RUNNING flag, phylib controls it later */ netif_carrier_off(net_dev); @@ -273,6 +284,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, err = register_netdev(net_dev); if (err < 0) { dev_err(dev, "register_netdev() = %d\n", err); + phylink_destroy(mac_dev->phylink); return err; } @@ -294,8 +306,7 @@ static int dpaa_stop(struct net_device *net_dev) */ msleep(200); - if (mac_dev->phy_dev) - phy_stop(mac_dev->phy_dev); + phylink_stop(mac_dev->phylink); mac_dev->disable(mac_dev->fman_mac); for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { @@ -304,8 +315,7 @@ static int dpaa_stop(struct net_device *net_dev) err = error; } - if (net_dev->phydev) - phy_disconnect(net_dev->phydev); + phylink_disconnect_phy(mac_dev->phylink); net_dev->phydev = NULL; msleep(200); @@ -833,10 +843,10 @@ static int dpaa_eth_cgr_init(struct dpaa_priv *priv) /* Set different thresholds based on the configured MAC speed. * This may turn suboptimal if the MAC is reconfigured at another - * speed, so MACs must call dpaa_eth_cgr_set_speed in their adjust_link + * speed, so MACs must call dpaa_eth_cgr_set_speed in their link_up * callback. */ - if (priv->mac_dev->if_support & SUPPORTED_10000baseT_Full) + if (priv->mac_dev->phylink_config.mac_capabilities & MAC_10000FD) cs_th = DPAA_CS_THRESHOLD_10G; else cs_th = DPAA_CS_THRESHOLD_1G; @@ -865,7 +875,7 @@ out_error: static void dpaa_eth_cgr_set_speed(struct mac_device *mac_dev, int speed) { - struct net_device *net_dev = mac_dev->net_dev; + struct net_device *net_dev = to_net_dev(mac_dev->phylink_config.dev); struct dpaa_priv *priv = netdev_priv(net_dev); struct qm_mcc_initcgr opts = { }; u32 cs_th; @@ -2904,58 +2914,6 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) } } -static void dpaa_adjust_link(struct net_device *net_dev) -{ - struct mac_device *mac_dev; - struct dpaa_priv *priv; - - priv = netdev_priv(net_dev); - mac_dev = priv->mac_dev; - mac_dev->adjust_link(mac_dev); -} - -/* The Aquantia PHYs are capable of performing rate adaptation */ -#define PHY_VEND_AQUANTIA 0x03a1b400 -#define PHY_VEND_AQUANTIA2 0x31c31c00 - -static int dpaa_phy_init(struct net_device *net_dev) -{ - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - struct mac_device *mac_dev; - struct phy_device *phy_dev; - struct dpaa_priv *priv; - u32 phy_vendor; - - priv = netdev_priv(net_dev); - mac_dev = priv->mac_dev; - - phy_dev = of_phy_connect(net_dev, mac_dev->phy_node, - &dpaa_adjust_link, 0, - mac_dev->phy_if); - if (!phy_dev) { - netif_err(priv, ifup, net_dev, "init_phy() failed\n"); - return -ENODEV; - } - - phy_vendor = phy_dev->drv->phy_id & GENMASK(31, 10); - /* Unless the PHY is capable of rate adaptation */ - if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII || - (phy_vendor != PHY_VEND_AQUANTIA && - phy_vendor != PHY_VEND_AQUANTIA2)) { - /* remove any features not supported by the controller */ - ethtool_convert_legacy_u32_to_link_mode(mask, - mac_dev->if_support); - linkmode_and(phy_dev->supported, phy_dev->supported, mask); - } - - phy_support_asym_pause(phy_dev); - - mac_dev->phy_dev = phy_dev; - net_dev->phydev = phy_dev; - - return 0; -} - static int dpaa_open(struct net_device *net_dev) { struct mac_device *mac_dev; @@ -2966,7 +2924,8 @@ static int dpaa_open(struct net_device *net_dev) mac_dev = priv->mac_dev; dpaa_eth_napi_enable(priv); - err = dpaa_phy_init(net_dev); + err = phylink_of_phy_connect(mac_dev->phylink, + mac_dev->dev->of_node, 0); if (err) goto phy_init_failed; @@ -2981,7 +2940,7 @@ static int dpaa_open(struct net_device *net_dev) netif_err(priv, ifup, net_dev, "mac_dev->enable() = %d\n", err); goto mac_start_failed; } - phy_start(priv->mac_dev->phy_dev); + phylink_start(mac_dev->phylink); netif_tx_start_all_queues(net_dev); @@ -2990,6 +2949,7 @@ static int dpaa_open(struct net_device *net_dev) mac_start_failed: for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) fman_port_disable(mac_dev->port[i]); + phylink_disconnect_phy(mac_dev->phylink); phy_init_failed: dpaa_eth_napi_disable(priv); @@ -3145,10 +3105,12 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd) { int ret = -EINVAL; + struct dpaa_priv *priv = netdev_priv(net_dev); if (cmd == SIOCGMIIREG) { if (net_dev->phydev) - return phy_mii_ioctl(net_dev->phydev, rq, cmd); + return phylink_mii_ioctl(priv->mac_dev->phylink, rq, + cmd); } if (cmd == SIOCSHWTSTAMP) @@ -3551,6 +3513,7 @@ static int dpaa_remove(struct platform_device *pdev) dev_set_drvdata(dev, NULL); unregister_netdev(net_dev); + phylink_destroy(priv->mac_dev->phylink); err = dpaa_fq_free(dev, &priv->dpaa_fq_list); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 769e936a263c..9c71cbbb13d8 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -54,27 +54,19 @@ static char dpaa_stats_global[][ETH_GSTRING_LEN] = { static int dpaa_get_link_ksettings(struct net_device *net_dev, struct ethtool_link_ksettings *cmd) { - if (!net_dev->phydev) - return 0; + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; - phy_ethtool_ksettings_get(net_dev->phydev, cmd); - - return 0; + return phylink_ethtool_ksettings_get(mac_dev->phylink, cmd); } static int dpaa_set_link_ksettings(struct net_device *net_dev, const struct ethtool_link_ksettings *cmd) { - int err; - - if (!net_dev->phydev) - return -ENODEV; - - err = phy_ethtool_ksettings_set(net_dev->phydev, cmd); - if (err < 0) - netdev_err(net_dev, "phy_ethtool_ksettings_set() = %d\n", err); + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; - return err; + return phylink_ethtool_ksettings_set(mac_dev->phylink, cmd); } static void dpaa_get_drvinfo(struct net_device *net_dev, @@ -99,80 +91,28 @@ static void dpaa_set_msglevel(struct net_device *net_dev, static int dpaa_nway_reset(struct net_device *net_dev) { - int err; - - if (!net_dev->phydev) - return -ENODEV; - - err = 0; - if (net_dev->phydev->autoneg) { - err = phy_start_aneg(net_dev->phydev); - if (err < 0) - netdev_err(net_dev, "phy_start_aneg() = %d\n", - err); - } + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; - return err; + return phylink_ethtool_nway_reset(mac_dev->phylink); } static void dpaa_get_pauseparam(struct net_device *net_dev, struct ethtool_pauseparam *epause) { - struct mac_device *mac_dev; - struct dpaa_priv *priv; - - priv = netdev_priv(net_dev); - mac_dev = priv->mac_dev; - - if (!net_dev->phydev) - return; + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; - epause->autoneg = mac_dev->autoneg_pause; - epause->rx_pause = mac_dev->rx_pause_active; - epause->tx_pause = mac_dev->tx_pause_active; + phylink_ethtool_get_pauseparam(mac_dev->phylink, epause); } static int dpaa_set_pauseparam(struct net_device *net_dev, struct ethtool_pauseparam *epause) { - struct mac_device *mac_dev; - struct phy_device *phydev; - bool rx_pause, tx_pause; - struct dpaa_priv *priv; - int err; - - priv = netdev_priv(net_dev); - mac_dev = priv->mac_dev; - - phydev = net_dev->phydev; - if (!phydev) { - netdev_err(net_dev, "phy device not initialized\n"); - return -ENODEV; - } - - if (!phy_validate_pause(phydev, epause)) - return -EINVAL; - - /* The MAC should know how to handle PAUSE frame autonegotiation before - * adjust_link is triggered by a forced renegotiation of sym/asym PAUSE - * settings. - */ - mac_dev->autoneg_pause = !!epause->autoneg; - mac_dev->rx_pause_req = !!epause->rx_pause; - mac_dev->tx_pause_req = !!epause->tx_pause; - - /* Determine the sym/asym advertised PAUSE capabilities from the desired - * rx/tx pause settings. - */ - - phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); - - fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); - err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); - if (err < 0) - netdev_err(net_dev, "set_mac_active_pause() = %d\n", err); + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; - return err; + return phylink_ethtool_set_pauseparam(mac_dev->phylink, epause); } static int dpaa_get_sset_count(struct net_device *net_dev, int type) diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile index 3d9842af7f10..1b05ba8d1cbf 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Makefile +++ b/drivers/net/ethernet/freescale/dpaa2/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_FSL_DPAA2_ETH) += fsl-dpaa2-eth.o obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK) += fsl-dpaa2-ptp.o obj-$(CONFIG_FSL_DPAA2_SWITCH) += fsl-dpaa2-switch.o -fsl-dpaa2-eth-objs := dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpaa2-eth-devlink.o +fsl-dpaa2-eth-objs := dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpaa2-eth-devlink.o dpaa2-xsk.o fsl-dpaa2-eth-${CONFIG_FSL_DPAA2_ETH_DCB} += dpaa2-eth-dcb.o fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o fsl-dpaa2-ptp-objs := dpaa2-ptp.o dprtc.o diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index 8356af4631fd..1af254caeb0d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -98,14 +98,14 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset) int i; seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name); - seq_printf(file, "%s%16s%16s%16s%16s%16s%16s\n", - "CHID", "CPU", "Deq busy", "Frames", "CDANs", + seq_printf(file, "%s %5s%16s%16s%16s%16s%16s%16s\n", + "IDX", "CHID", "CPU", "Deq busy", "Frames", "CDANs", "Avg Frm/CDAN", "Buf count"); for (i = 0; i < priv->num_channels; i++) { ch = priv->channel[i]; - seq_printf(file, "%4d%16d%16llu%16llu%16llu%16llu%16d\n", - ch->ch_id, + seq_printf(file, "%3s%d%6d%16d%16llu%16llu%16llu%16llu%16d\n", + "CH#", i, ch->ch_id, ch->nctx.desired_cpu, ch->stats.dequeue_portal_busy, ch->stats.frames, @@ -119,6 +119,51 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset) DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_ch); +static int dpaa2_dbg_bp_show(struct seq_file *file, void *offset) +{ + struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private; + int i, j, num_queues, buf_cnt; + struct dpaa2_eth_bp *bp; + char ch_name[10]; + int err; + + /* Print out the header */ + seq_printf(file, "Buffer pool info for %s:\n", priv->net_dev->name); + seq_printf(file, "%s %10s%15s", "IDX", "BPID", "Buf count"); + num_queues = dpaa2_eth_queue_count(priv); + for (i = 0; i < num_queues; i++) { + snprintf(ch_name, sizeof(ch_name), "CH#%d", i); + seq_printf(file, "%10s", ch_name); + } + seq_printf(file, "\n"); + + /* For each buffer pool, print out its BPID, the number of buffers in + * that buffer pool and the channels which are using it. + */ + for (i = 0; i < priv->num_bps; i++) { + bp = priv->bp[i]; + + err = dpaa2_io_query_bp_count(NULL, bp->bpid, &buf_cnt); + if (err) { + netdev_warn(priv->net_dev, "Buffer count query error %d\n", err); + return err; + } + + seq_printf(file, "%3s%d%10d%15d", "BP#", i, bp->bpid, buf_cnt); + for (j = 0; j < num_queues; j++) { + if (priv->channel[j]->bp == bp) + seq_printf(file, "%10s", "x"); + else + seq_printf(file, "%10s", ""); + } + seq_printf(file, "\n"); + } + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_bp); + void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) { struct fsl_mc_device *dpni_dev; @@ -139,6 +184,10 @@ void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) /* per-fq stats file */ debugfs_create_file("ch_stats", 0444, dir, priv, &dpaa2_dbg_ch_fops); + + /* per buffer pool stats file */ + debugfs_create_file("bp_stats", 0444, dir, priv, &dpaa2_dbg_bp_fops); + } void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c index 7fefe1574b6a..76f808d38066 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c @@ -37,18 +37,9 @@ static int dpaa2_eth_dl_info_get(struct devlink *devlink, struct dpaa2_eth_devlink_priv *dl_priv = devlink_priv(devlink); struct dpaa2_eth_priv *priv = dl_priv->dpaa2_priv; char buf[10]; - int err; - - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; scnprintf(buf, 10, "%d.%d", priv->dpni_ver_major, priv->dpni_ver_minor); - err = devlink_info_version_running_put(req, "dpni", buf); - if (err) - return err; - - return 0; + return devlink_info_version_running_put(req, "dpni", buf); } static struct dpaa2_eth_trap_item * @@ -226,25 +217,16 @@ int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv) { struct devlink_port *devlink_port = &priv->devlink_port; struct devlink_port_attrs attrs = {}; - int err; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; devlink_port_attrs_set(devlink_port, &attrs); - - err = devlink_port_register(priv->devlink, devlink_port, 0); - if (err) - return err; - - devlink_port_type_eth_set(devlink_port, priv->net_dev); - - return 0; + return devlink_port_register(priv->devlink, devlink_port, 0); } void dpaa2_eth_dl_port_del(struct dpaa2_eth_priv *priv) { struct devlink_port *devlink_port = &priv->devlink_port; - devlink_port_type_clear(devlink_port); devlink_port_unregister(devlink_port); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h index 5fb5f14e01ec..9b43fadb9b11 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h @@ -73,6 +73,14 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_fd, TP_ARGS(netdev, fd) ); +/* Tx (egress) XSK fd */ +DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_xsk_fd, + TP_PROTO(struct net_device *netdev, + const struct dpaa2_fd *fd), + + TP_ARGS(netdev, fd) +); + /* Rx fd */ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_fd, TP_PROTO(struct net_device *netdev, @@ -81,6 +89,14 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_fd, TP_ARGS(netdev, fd) ); +/* Rx XSK fd */ +DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_xsk_fd, + TP_PROTO(struct net_device *netdev, + const struct dpaa2_fd *fd), + + TP_ARGS(netdev, fd) +); + /* Tx confirmation fd */ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_conf_fd, TP_PROTO(struct net_device *netdev, @@ -90,57 +106,81 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_conf_fd, ); /* Log data about raw buffers. Useful for tracing DPBP content. */ -TRACE_EVENT(dpaa2_eth_buf_seed, - /* Trace function prototype */ - TP_PROTO(struct net_device *netdev, - /* virtual address and size */ - void *vaddr, - size_t size, - /* dma map address and size */ - dma_addr_t dma_addr, - size_t map_size, - /* buffer pool id, if relevant */ - u16 bpid), - - /* Repeat argument list here */ - TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid), - - /* A structure containing the relevant information we want - * to record. Declare name and type for each normal element, - * name, type and size for arrays. Use __string for variable - * length strings. - */ - TP_STRUCT__entry( - __field(void *, vaddr) - __field(size_t, size) - __field(dma_addr_t, dma_addr) - __field(size_t, map_size) - __field(u16, bpid) - __string(name, netdev->name) - ), - - /* The function that assigns values to the above declared - * fields - */ - TP_fast_assign( - __entry->vaddr = vaddr; - __entry->size = size; - __entry->dma_addr = dma_addr; - __entry->map_size = map_size; - __entry->bpid = bpid; - __assign_str(name, netdev->name); - ), - - /* This is what gets printed when the trace event is - * triggered. - */ - TP_printk(TR_BUF_FMT, - __get_str(name), - __entry->vaddr, - __entry->size, - &__entry->dma_addr, - __entry->map_size, - __entry->bpid) +DECLARE_EVENT_CLASS(dpaa2_eth_buf, + /* Trace function prototype */ + TP_PROTO(struct net_device *netdev, + /* virtual address and size */ + void *vaddr, + size_t size, + /* dma map address and size */ + dma_addr_t dma_addr, + size_t map_size, + /* buffer pool id, if relevant */ + u16 bpid), + + /* Repeat argument list here */ + TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid), + + /* A structure containing the relevant information we want + * to record. Declare name and type for each normal element, + * name, type and size for arrays. Use __string for variable + * length strings. + */ + TP_STRUCT__entry( + __field(void *, vaddr) + __field(size_t, size) + __field(dma_addr_t, dma_addr) + __field(size_t, map_size) + __field(u16, bpid) + __string(name, netdev->name) + ), + + /* The function that assigns values to the above declared + * fields + */ + TP_fast_assign( + __entry->vaddr = vaddr; + __entry->size = size; + __entry->dma_addr = dma_addr; + __entry->map_size = map_size; + __entry->bpid = bpid; + __assign_str(name, netdev->name); + ), + + /* This is what gets printed when the trace event is + * triggered. + */ + TP_printk(TR_BUF_FMT, + __get_str(name), + __entry->vaddr, + __entry->size, + &__entry->dma_addr, + __entry->map_size, + __entry->bpid) +); + +/* Main memory buff seeding */ +DEFINE_EVENT(dpaa2_eth_buf, dpaa2_eth_buf_seed, + TP_PROTO(struct net_device *netdev, + void *vaddr, + size_t size, + dma_addr_t dma_addr, + size_t map_size, + u16 bpid), + + TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid) +); + +/* UMEM buff seeding on AF_XDP fast path */ +DEFINE_EVENT(dpaa2_eth_buf, dpaa2_xsk_buf_seed, + TP_PROTO(struct net_device *netdev, + void *vaddr, + size_t size, + dma_addr_t dma_addr, + size_t map_size, + u16 bpid), + + TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid) ); /* If only one event of a certain type needs to be declared, use TRACE_EVENT(). diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 8d029addddad..0c35abb7d065 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2014-2016 Freescale Semiconductor Inc. - * Copyright 2016-2020 NXP + * Copyright 2016-2022 NXP */ #include <linux/init.h> #include <linux/module.h> @@ -8,7 +8,6 @@ #include <linux/etherdevice.h> #include <linux/of_net.h> #include <linux/interrupt.h> -#include <linux/msi.h> #include <linux/kthread.h> #include <linux/iommu.h> #include <linux/fsl/mc.h> @@ -19,6 +18,7 @@ #include <net/pkt_cls.h> #include <net/sock.h> #include <net/tso.h> +#include <net/xdp_sock_drv.h> #include "dpaa2-eth.h" @@ -104,8 +104,8 @@ static void dpaa2_ptp_onestep_reg_update_method(struct dpaa2_eth_priv *priv) priv->dpaa2_set_onestep_params_cb = dpaa2_update_ptp_onestep_direct; } -static void *dpaa2_iova_to_virt(struct iommu_domain *domain, - dma_addr_t iova_addr) +void *dpaa2_iova_to_virt(struct iommu_domain *domain, + dma_addr_t iova_addr) { phys_addr_t phys_addr; @@ -279,23 +279,33 @@ static struct sk_buff *dpaa2_eth_build_frag_skb(struct dpaa2_eth_priv *priv, * be released in the pool */ static void dpaa2_eth_free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, - int count) + int count, bool xsk_zc) { struct device *dev = priv->net_dev->dev.parent; + struct dpaa2_eth_swa *swa; + struct xdp_buff *xdp_buff; void *vaddr; int i; for (i = 0; i < count; i++) { vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]); - dma_unmap_page(dev, buf_array[i], priv->rx_buf_size, - DMA_BIDIRECTIONAL); - free_pages((unsigned long)vaddr, 0); + + if (!xsk_zc) { + dma_unmap_page(dev, buf_array[i], priv->rx_buf_size, + DMA_BIDIRECTIONAL); + free_pages((unsigned long)vaddr, 0); + } else { + swa = (struct dpaa2_eth_swa *) + (vaddr + DPAA2_ETH_RX_HWA_SIZE); + xdp_buff = swa->xsk.xdp_buff; + xsk_buff_free(xdp_buff); + } } } -static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - dma_addr_t addr) +void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + dma_addr_t addr) { int retries = 0; int err; @@ -304,7 +314,7 @@ static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv, if (ch->recycled_bufs_cnt < DPAA2_ETH_BUFS_PER_CMD) return; - while ((err = dpaa2_io_service_release(ch->dpio, priv->bpid, + while ((err = dpaa2_io_service_release(ch->dpio, ch->bp->bpid, ch->recycled_bufs, ch->recycled_bufs_cnt)) == -EBUSY) { if (retries++ >= DPAA2_ETH_SWP_BUSY_RETRIES) @@ -313,7 +323,8 @@ static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv, } if (err) { - dpaa2_eth_free_bufs(priv, ch->recycled_bufs, ch->recycled_bufs_cnt); + dpaa2_eth_free_bufs(priv, ch->recycled_bufs, + ch->recycled_bufs_cnt, ch->xsk_zc); ch->buf_count -= ch->recycled_bufs_cnt; } @@ -377,10 +388,10 @@ static void dpaa2_eth_xdp_tx_flush(struct dpaa2_eth_priv *priv, fq->xdp_tx_fds.num = 0; } -static void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - struct dpaa2_fd *fd, - void *buf_start, u16 queue_id) +void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_fd *fd, + void *buf_start, u16 queue_id) { struct dpaa2_faead *faead; struct dpaa2_fd *dest_fd; @@ -485,19 +496,15 @@ out: return xdp_act; } -static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch, - const struct dpaa2_fd *fd, - void *fd_vaddr) +struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, u32 fd_length, + void *fd_vaddr) { u16 fd_offset = dpaa2_fd_get_offset(fd); - struct dpaa2_eth_priv *priv = ch->priv; - u32 fd_length = dpaa2_fd_get_len(fd); struct sk_buff *skb = NULL; unsigned int skb_len; - if (fd_length > priv->rx_copybreak) - return NULL; - skb_len = fd_length + dpaa2_eth_needed_headroom(NULL); skb = napi_alloc_skb(&ch->napi, skb_len); @@ -514,11 +521,66 @@ static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch, return skb; } +static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + void *fd_vaddr) +{ + struct dpaa2_eth_priv *priv = ch->priv; + u32 fd_length = dpaa2_fd_get_len(fd); + + if (fd_length > priv->rx_copybreak) + return NULL; + + return dpaa2_eth_alloc_skb(priv, ch, fd, fd_length, fd_vaddr); +} + +void dpaa2_eth_receive_skb(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, void *vaddr, + struct dpaa2_eth_fq *fq, + struct rtnl_link_stats64 *percpu_stats, + struct sk_buff *skb) +{ + struct dpaa2_fas *fas; + u32 status = 0; + + fas = dpaa2_get_fas(vaddr, false); + prefetch(fas); + prefetch(skb->data); + + /* Get the timestamp value */ + if (priv->rx_tstamp) { + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + __le64 *ts = dpaa2_get_ts(vaddr, false); + u64 ns; + + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + + ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts); + shhwtstamps->hwtstamp = ns_to_ktime(ns); + } + + /* Check if we need to validate the L4 csum */ + if (likely(dpaa2_fd_get_frc(fd) & DPAA2_FD_FRC_FASV)) { + status = le32_to_cpu(fas->status); + dpaa2_eth_validate_rx_csum(priv, status, skb); + } + + skb->protocol = eth_type_trans(skb, priv->net_dev); + skb_record_rx_queue(skb, fq->flowid); + + percpu_stats->rx_packets++; + percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); + ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd); + + list_add_tail(&skb->list, ch->rx_list); +} + /* Main Rx frame processing routine */ -static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - const struct dpaa2_fd *fd, - struct dpaa2_eth_fq *fq) +void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + struct dpaa2_eth_fq *fq) { dma_addr_t addr = dpaa2_fd_get_addr(fd); u8 fd_format = dpaa2_fd_get_format(fd); @@ -527,9 +589,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, struct rtnl_link_stats64 *percpu_stats; struct dpaa2_eth_drv_stats *percpu_extras; struct device *dev = priv->net_dev->dev.parent; - struct dpaa2_fas *fas; void *buf_data; - u32 status = 0; u32 xdp_act; /* Tracing point */ @@ -539,8 +599,6 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); - fas = dpaa2_get_fas(vaddr, false); - prefetch(fas); buf_data = vaddr + dpaa2_fd_get_offset(fd); prefetch(buf_data); @@ -578,35 +636,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, if (unlikely(!skb)) goto err_build_skb; - prefetch(skb->data); - - /* Get the timestamp value */ - if (priv->rx_tstamp) { - struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); - __le64 *ts = dpaa2_get_ts(vaddr, false); - u64 ns; - - memset(shhwtstamps, 0, sizeof(*shhwtstamps)); - - ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts); - shhwtstamps->hwtstamp = ns_to_ktime(ns); - } - - /* Check if we need to validate the L4 csum */ - if (likely(dpaa2_fd_get_frc(fd) & DPAA2_FD_FRC_FASV)) { - status = le32_to_cpu(fas->status); - dpaa2_eth_validate_rx_csum(priv, status, skb); - } - - skb->protocol = eth_type_trans(skb, priv->net_dev); - skb_record_rx_queue(skb, fq->flowid); - - percpu_stats->rx_packets++; - percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); - ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd); - - list_add_tail(&skb->list, ch->rx_list); - + dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb); return; err_build_skb: @@ -827,7 +857,7 @@ static void dpaa2_eth_enable_tx_tstamp(struct dpaa2_eth_priv *priv, } } -static void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv) +void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv) { struct dpaa2_eth_sgt_cache *sgt_cache; void *sgt_buf = NULL; @@ -849,7 +879,7 @@ static void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv) return sgt_buf; } -static void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf) +void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf) { struct dpaa2_eth_sgt_cache *sgt_cache; @@ -1084,9 +1114,10 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv, * This can be called either from dpaa2_eth_tx_conf() or on the error path of * dpaa2_eth_tx(). */ -static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_fq *fq, - const struct dpaa2_fd *fd, bool in_napi) +void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq *fq, + const struct dpaa2_fd *fd, bool in_napi) { struct device *dev = priv->net_dev->dev.parent; dma_addr_t fd_addr, sg_addr; @@ -1153,6 +1184,10 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, if (!swa->tso.is_last_fd) should_free_skb = 0; + } else if (swa->type == DPAA2_ETH_SWA_XSK) { + /* Unmap the SGT Buffer */ + dma_unmap_single(dev, fd_addr, swa->xsk.sgt_size, + DMA_BIDIRECTIONAL); } else { skb = swa->single.skb; @@ -1170,6 +1205,12 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, return; } + if (swa->type == DPAA2_ETH_SWA_XSK) { + ch->xsk_tx_pkts_sent++; + dpaa2_eth_sgt_recycle(priv, buffer_start); + return; + } + if (swa->type != DPAA2_ETH_SWA_XDP && in_napi) { fq->dq_frames++; fq->dq_bytes += fd_len; @@ -1344,7 +1385,7 @@ err_alloc_tso_hdr: err_sgt_get: /* Free all the other FDs that were already fully created */ for (i = 0; i < index; i++) - dpaa2_eth_free_tx_fd(priv, NULL, &fd_start[i], false); + dpaa2_eth_free_tx_fd(priv, NULL, NULL, &fd_start[i], false); return err; } @@ -1460,7 +1501,7 @@ static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb, if (unlikely(err < 0)) { percpu_stats->tx_errors++; /* Clean up everything, including freeing the skb */ - dpaa2_eth_free_tx_fd(priv, fq, fd, false); + dpaa2_eth_free_tx_fd(priv, NULL, fq, fd, false); netdev_tx_completed_queue(nq, 1, fd_len); } else { percpu_stats->tx_packets += total_enqueued; @@ -1553,7 +1594,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, /* Check frame errors in the FD field */ fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK; - dpaa2_eth_free_tx_fd(priv, fq, fd, true); + dpaa2_eth_free_tx_fd(priv, ch, fq, fd, true); if (likely(!fd_errors)) return; @@ -1631,44 +1672,76 @@ static int dpaa2_eth_set_tx_csum(struct dpaa2_eth_priv *priv, bool enable) * to the specified buffer pool */ static int dpaa2_eth_add_bufs(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, u16 bpid) + struct dpaa2_eth_channel *ch) { + struct xdp_buff *xdp_buffs[DPAA2_ETH_BUFS_PER_CMD]; struct device *dev = priv->net_dev->dev.parent; u64 buf_array[DPAA2_ETH_BUFS_PER_CMD]; + struct dpaa2_eth_swa *swa; struct page *page; dma_addr_t addr; int retries = 0; - int i, err; - - for (i = 0; i < DPAA2_ETH_BUFS_PER_CMD; i++) { - /* Allocate buffer visible to WRIOP + skb shared info + - * alignment padding - */ - /* allocate one page for each Rx buffer. WRIOP sees - * the entire page except for a tailroom reserved for - * skb shared info + int i = 0, err; + u32 batch; + + /* Allocate buffers visible to WRIOP */ + if (!ch->xsk_zc) { + for (i = 0; i < DPAA2_ETH_BUFS_PER_CMD; i++) { + /* Also allocate skb shared info and alignment padding. + * There is one page for each Rx buffer. WRIOP sees + * the entire page except for a tailroom reserved for + * skb shared info + */ + page = dev_alloc_pages(0); + if (!page) + goto err_alloc; + + addr = dma_map_page(dev, page, 0, priv->rx_buf_size, + DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(dev, addr))) + goto err_map; + + buf_array[i] = addr; + + /* tracing point */ + trace_dpaa2_eth_buf_seed(priv->net_dev, + page_address(page), + DPAA2_ETH_RX_BUF_RAW_SIZE, + addr, priv->rx_buf_size, + ch->bp->bpid); + } + } else if (xsk_buff_can_alloc(ch->xsk_pool, DPAA2_ETH_BUFS_PER_CMD)) { + /* Allocate XSK buffers for AF_XDP fast path in batches + * of DPAA2_ETH_BUFS_PER_CMD. Bail out if the UMEM cannot + * provide enough buffers at the moment */ - page = dev_alloc_pages(0); - if (!page) + batch = xsk_buff_alloc_batch(ch->xsk_pool, xdp_buffs, + DPAA2_ETH_BUFS_PER_CMD); + if (!batch) goto err_alloc; - addr = dma_map_page(dev, page, 0, priv->rx_buf_size, - DMA_BIDIRECTIONAL); - if (unlikely(dma_mapping_error(dev, addr))) - goto err_map; + for (i = 0; i < batch; i++) { + swa = (struct dpaa2_eth_swa *)(xdp_buffs[i]->data_hard_start + + DPAA2_ETH_RX_HWA_SIZE); + swa->xsk.xdp_buff = xdp_buffs[i]; + + addr = xsk_buff_xdp_get_frame_dma(xdp_buffs[i]); + if (unlikely(dma_mapping_error(dev, addr))) + goto err_map; - buf_array[i] = addr; + buf_array[i] = addr; - /* tracing point */ - trace_dpaa2_eth_buf_seed(priv->net_dev, page_address(page), - DPAA2_ETH_RX_BUF_RAW_SIZE, - addr, priv->rx_buf_size, - bpid); + trace_dpaa2_xsk_buf_seed(priv->net_dev, + xdp_buffs[i]->data_hard_start, + DPAA2_ETH_RX_BUF_RAW_SIZE, + addr, priv->rx_buf_size, + ch->bp->bpid); + } } release_bufs: /* In case the portal is busy, retry until successful */ - while ((err = dpaa2_io_service_release(ch->dpio, bpid, + while ((err = dpaa2_io_service_release(ch->dpio, ch->bp->bpid, buf_array, i)) == -EBUSY) { if (retries++ >= DPAA2_ETH_SWP_BUSY_RETRIES) break; @@ -1679,14 +1752,19 @@ release_bufs: * not much else we can do about it */ if (err) { - dpaa2_eth_free_bufs(priv, buf_array, i); + dpaa2_eth_free_bufs(priv, buf_array, i, ch->xsk_zc); return 0; } return i; err_map: - __free_pages(page, 0); + if (!ch->xsk_zc) { + __free_pages(page, 0); + } else { + for (; i < batch; i++) + xsk_buff_free(xdp_buffs[i]); + } err_alloc: /* If we managed to allocate at least some buffers, * release them to hardware @@ -1697,39 +1775,64 @@ err_alloc: return 0; } -static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv, u16 bpid) +static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch) { - int i, j; + int i; int new_count; - for (j = 0; j < priv->num_channels; j++) { - for (i = 0; i < DPAA2_ETH_NUM_BUFS; - i += DPAA2_ETH_BUFS_PER_CMD) { - new_count = dpaa2_eth_add_bufs(priv, priv->channel[j], bpid); - priv->channel[j]->buf_count += new_count; + for (i = 0; i < DPAA2_ETH_NUM_BUFS; i += DPAA2_ETH_BUFS_PER_CMD) { + new_count = dpaa2_eth_add_bufs(priv, ch); + ch->buf_count += new_count; - if (new_count < DPAA2_ETH_BUFS_PER_CMD) { - return -ENOMEM; - } - } + if (new_count < DPAA2_ETH_BUFS_PER_CMD) + return -ENOMEM; } return 0; } +static void dpaa2_eth_seed_pools(struct dpaa2_eth_priv *priv) +{ + struct net_device *net_dev = priv->net_dev; + struct dpaa2_eth_channel *channel; + int i, err = 0; + + for (i = 0; i < priv->num_channels; i++) { + channel = priv->channel[i]; + + err = dpaa2_eth_seed_pool(priv, channel); + + /* Not much to do; the buffer pool, though not filled up, + * may still contain some buffers which would enable us + * to limp on. + */ + if (err) + netdev_err(net_dev, "Buffer seeding failed for DPBP %d (bpid=%d)\n", + channel->bp->dev->obj_desc.id, + channel->bp->bpid); + } +} + /* - * Drain the specified number of buffers from the DPNI's private buffer pool. + * Drain the specified number of buffers from one of the DPNI's private buffer + * pools. * @count must not exceeed DPAA2_ETH_BUFS_PER_CMD */ -static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int count) +static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int bpid, + int count) { u64 buf_array[DPAA2_ETH_BUFS_PER_CMD]; + bool xsk_zc = false; int retries = 0; - int ret; + int i, ret; + + for (i = 0; i < priv->num_channels; i++) + if (priv->channel[i]->bp->bpid == bpid) + xsk_zc = priv->channel[i]->xsk_zc; do { - ret = dpaa2_io_service_acquire(NULL, priv->bpid, - buf_array, count); + ret = dpaa2_io_service_acquire(NULL, bpid, buf_array, count); if (ret < 0) { if (ret == -EBUSY && retries++ < DPAA2_ETH_SWP_BUSY_RETRIES) @@ -1737,28 +1840,40 @@ static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int count) netdev_err(priv->net_dev, "dpaa2_io_service_acquire() failed\n"); return; } - dpaa2_eth_free_bufs(priv, buf_array, ret); + dpaa2_eth_free_bufs(priv, buf_array, ret, xsk_zc); retries = 0; } while (ret); } -static void dpaa2_eth_drain_pool(struct dpaa2_eth_priv *priv) +static void dpaa2_eth_drain_pool(struct dpaa2_eth_priv *priv, int bpid) { int i; - dpaa2_eth_drain_bufs(priv, DPAA2_ETH_BUFS_PER_CMD); - dpaa2_eth_drain_bufs(priv, 1); + /* Drain the buffer pool */ + dpaa2_eth_drain_bufs(priv, bpid, DPAA2_ETH_BUFS_PER_CMD); + dpaa2_eth_drain_bufs(priv, bpid, 1); + /* Setup to zero the buffer count of all channels which were + * using this buffer pool. + */ for (i = 0; i < priv->num_channels; i++) - priv->channel[i]->buf_count = 0; + if (priv->channel[i]->bp->bpid == bpid) + priv->channel[i]->buf_count = 0; +} + +static void dpaa2_eth_drain_pools(struct dpaa2_eth_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_bps; i++) + dpaa2_eth_drain_pool(priv, priv->bp[i]->bpid); } /* Function is called from softirq context only, so we don't need to guard * the access to percpu count */ static int dpaa2_eth_refill_pool(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - u16 bpid) + struct dpaa2_eth_channel *ch) { int new_count; @@ -1766,7 +1881,7 @@ static int dpaa2_eth_refill_pool(struct dpaa2_eth_priv *priv, return 0; do { - new_count = dpaa2_eth_add_bufs(priv, ch, bpid); + new_count = dpaa2_eth_add_bufs(priv, ch); if (unlikely(!new_count)) { /* Out of memory; abort for now, we'll try later on */ break; @@ -1830,6 +1945,7 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) struct dpaa2_eth_fq *fq, *txc_fq = NULL; struct netdev_queue *nq; int store_cleaned, work_done; + bool work_done_zc = false; struct list_head rx_list; int retries = 0; u16 flowid; @@ -1842,13 +1958,22 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) INIT_LIST_HEAD(&rx_list); ch->rx_list = &rx_list; + if (ch->xsk_zc) { + work_done_zc = dpaa2_xsk_tx(priv, ch); + /* If we reached the XSK Tx per NAPI threshold, we're done */ + if (work_done_zc) { + work_done = budget; + goto out; + } + } + do { err = dpaa2_eth_pull_channel(ch); if (unlikely(err)) break; /* Refill pool if appropriate */ - dpaa2_eth_refill_pool(priv, ch, priv->bpid); + dpaa2_eth_refill_pool(priv, ch); store_cleaned = dpaa2_eth_consume_frames(ch, &fq); if (store_cleaned <= 0) @@ -1894,6 +2019,11 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) out: netif_receive_skb_list(ch->rx_list); + if (ch->xsk_tx_pkts_sent) { + xsk_tx_completed(ch->xsk_pool, ch->xsk_tx_pkts_sent); + ch->xsk_tx_pkts_sent = 0; + } + if (txc_fq && txc_fq->dq_frames) { nq = netdev_get_tx_queue(priv->net_dev, txc_fq->flowid); netdev_tx_completed_queue(nq, txc_fq->dq_frames, @@ -2017,8 +2147,11 @@ static int dpaa2_eth_link_state_update(struct dpaa2_eth_priv *priv) /* When we manage the MAC/PHY using phylink there is no need * to manually update the netif_carrier. + * We can avoid locking because we are called from the "link changed" + * IRQ handler, which is the same as the "endpoint changed" IRQ handler + * (the writer to priv->mac), so we cannot race with it. */ - if (dpaa2_eth_is_type_phy(priv)) + if (dpaa2_mac_is_type_phy(priv->mac)) goto out; /* Chech link state; speed / duplex changes are not treated yet */ @@ -2047,15 +2180,9 @@ static int dpaa2_eth_open(struct net_device *net_dev) struct dpaa2_eth_priv *priv = netdev_priv(net_dev); int err; - err = dpaa2_eth_seed_pool(priv, priv->bpid); - if (err) { - /* Not much to do; the buffer pool, though not filled up, - * may still contain some buffers which would enable us - * to limp on. - */ - netdev_err(net_dev, "Buffer seeding failed for DPBP %d (bpid=%d)\n", - priv->dpbp_dev->obj_desc.id, priv->bpid); - } + dpaa2_eth_seed_pools(priv); + + mutex_lock(&priv->mac_lock); if (!dpaa2_eth_is_type_phy(priv)) { /* We'll only start the txqs when the link is actually ready; @@ -2075,20 +2202,21 @@ static int dpaa2_eth_open(struct net_device *net_dev) err = dpni_enable(priv->mc_io, 0, priv->mc_token); if (err < 0) { + mutex_unlock(&priv->mac_lock); netdev_err(net_dev, "dpni_enable() failed\n"); goto enable_err; } - if (dpaa2_eth_is_type_phy(priv)) { + if (dpaa2_eth_is_type_phy(priv)) dpaa2_mac_start(priv->mac); - phylink_start(priv->mac->phylink); - } + + mutex_unlock(&priv->mac_lock); return 0; enable_err: dpaa2_eth_disable_ch_napi(priv); - dpaa2_eth_drain_pool(priv); + dpaa2_eth_drain_pools(priv); return err; } @@ -2155,14 +2283,17 @@ static int dpaa2_eth_stop(struct net_device *net_dev) int dpni_enabled = 0; int retries = 10; + mutex_lock(&priv->mac_lock); + if (dpaa2_eth_is_type_phy(priv)) { - phylink_stop(priv->mac->phylink); dpaa2_mac_stop(priv->mac); } else { netif_tx_stop_all_queues(net_dev); netif_carrier_off(net_dev); } + mutex_unlock(&priv->mac_lock); + /* On dpni_disable(), the MC firmware will: * - stop MAC Rx and wait for all Rx frames to be enqueued to software * - cut off WRIOP dequeues from egress FQs and wait until transmission @@ -2193,7 +2324,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) dpaa2_eth_disable_ch_napi(priv); /* Empty the buffer pool */ - dpaa2_eth_drain_pool(priv); + dpaa2_eth_drain_pools(priv); /* Empty the Scatter-Gather Buffer cache */ dpaa2_eth_sgt_cache_drain(priv); @@ -2488,12 +2619,20 @@ static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct dpaa2_eth_priv *priv = netdev_priv(dev); + int err; if (cmd == SIOCSHWTSTAMP) return dpaa2_eth_ts_ioctl(dev, rq, cmd); - if (dpaa2_eth_is_type_phy(priv)) - return phylink_mii_ioctl(priv->mac->phylink, rq, cmd); + mutex_lock(&priv->mac_lock); + + if (dpaa2_eth_is_type_phy(priv)) { + err = phylink_mii_ioctl(priv->mac->phylink, rq, cmd); + mutex_unlock(&priv->mac_lock); + return err; + } + + mutex_unlock(&priv->mac_lock); return -EOPNOTSUPP; } @@ -2602,7 +2741,7 @@ static int dpaa2_eth_setup_xdp(struct net_device *dev, struct bpf_prog *prog) need_update = (!!priv->xdp_prog != !!prog); if (up) - dpaa2_eth_stop(dev); + dev_close(dev); /* While in xdp mode, enforce a maximum Rx frame size based on MTU. * Also, when switching between xdp/non-xdp modes we need to reconfigure @@ -2630,7 +2769,7 @@ static int dpaa2_eth_setup_xdp(struct net_device *dev, struct bpf_prog *prog) } if (up) { - err = dpaa2_eth_open(dev); + err = dev_open(dev, NULL); if (err) return err; } @@ -2641,7 +2780,7 @@ out_err: if (prog) bpf_prog_sub(prog, priv->num_channels); if (up) - dpaa2_eth_open(dev); + dev_open(dev, NULL); return err; } @@ -2651,6 +2790,8 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return dpaa2_eth_setup_xdp(dev, xdp->prog); + case XDP_SETUP_XSK_POOL: + return dpaa2_xsk_setup_pool(dev, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; } @@ -2881,6 +3022,7 @@ static const struct net_device_ops dpaa2_eth_ops = { .ndo_change_mtu = dpaa2_eth_change_mtu, .ndo_bpf = dpaa2_eth_xdp, .ndo_xdp_xmit = dpaa2_eth_xdp_xmit, + .ndo_xsk_wakeup = dpaa2_xsk_wakeup, .ndo_setup_tc = dpaa2_eth_setup_tc, .ndo_vlan_rx_add_vid = dpaa2_eth_rx_add_vid, .ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid @@ -2895,7 +3037,11 @@ static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx) /* Update NAPI statistics */ ch->stats.cdan++; - napi_schedule(&ch->napi); + /* NAPI can also be scheduled from the AF_XDP Tx path. Mark a missed + * so that it can be rescheduled again. + */ + if (!napi_if_scheduled_mark_missed(&ch->napi)) + napi_schedule(&ch->napi); } /* Allocate and configure a DPCON object */ @@ -2908,10 +3054,12 @@ static struct fsl_mc_device *dpaa2_eth_setup_dpcon(struct dpaa2_eth_priv *priv) err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPCON, &dpcon); if (err) { - if (err == -ENXIO) + if (err == -ENXIO) { + dev_dbg(dev, "Waiting for DPCON\n"); err = -EPROBE_DEFER; - else + } else { dev_info(dev, "Not enough DPCONs, will go on as-is\n"); + } return ERR_PTR(err); } @@ -3021,7 +3169,9 @@ static int dpaa2_eth_setup_dpio(struct dpaa2_eth_priv *priv) channel = dpaa2_eth_alloc_channel(priv); if (IS_ERR_OR_NULL(channel)) { err = PTR_ERR_OR_ZERO(channel); - if (err != -EPROBE_DEFER) + if (err == -EPROBE_DEFER) + dev_dbg(dev, "waiting for affine channel\n"); + else dev_info(dev, "No affine channel for cpu %d and above\n", i); goto err_alloc_ch; @@ -3204,13 +3354,14 @@ static void dpaa2_eth_setup_fqs(struct dpaa2_eth_priv *priv) dpaa2_eth_set_fq_affinity(priv); } -/* Allocate and configure one buffer pool for each interface */ -static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv) +/* Allocate and configure a buffer pool */ +struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv) { - int err; - struct fsl_mc_device *dpbp_dev; struct device *dev = priv->net_dev->dev.parent; + struct fsl_mc_device *dpbp_dev; struct dpbp_attr dpbp_attrs; + struct dpaa2_eth_bp *bp; + int err; err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPBP, &dpbp_dev); @@ -3219,12 +3370,16 @@ static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv) err = -EPROBE_DEFER; else dev_err(dev, "DPBP device allocation failed\n"); - return err; + return ERR_PTR(err); } - priv->dpbp_dev = dpbp_dev; + bp = kzalloc(sizeof(*bp), GFP_KERNEL); + if (!bp) { + err = -ENOMEM; + goto err_alloc; + } - err = dpbp_open(priv->mc_io, 0, priv->dpbp_dev->obj_desc.id, + err = dpbp_open(priv->mc_io, 0, dpbp_dev->obj_desc.id, &dpbp_dev->mc_handle); if (err) { dev_err(dev, "dpbp_open() failed\n"); @@ -3249,9 +3404,11 @@ static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv) dev_err(dev, "dpbp_get_attributes() failed\n"); goto err_get_attr; } - priv->bpid = dpbp_attrs.bpid; - return 0; + bp->dev = dpbp_dev; + bp->bpid = dpbp_attrs.bpid; + + return bp; err_get_attr: dpbp_disable(priv->mc_io, 0, dpbp_dev->mc_handle); @@ -3259,17 +3416,58 @@ err_enable: err_reset: dpbp_close(priv->mc_io, 0, dpbp_dev->mc_handle); err_open: + kfree(bp); +err_alloc: fsl_mc_object_free(dpbp_dev); - return err; + return ERR_PTR(err); } -static void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv) +static int dpaa2_eth_setup_default_dpbp(struct dpaa2_eth_priv *priv) { - dpaa2_eth_drain_pool(priv); - dpbp_disable(priv->mc_io, 0, priv->dpbp_dev->mc_handle); - dpbp_close(priv->mc_io, 0, priv->dpbp_dev->mc_handle); - fsl_mc_object_free(priv->dpbp_dev); + struct dpaa2_eth_bp *bp; + int i; + + bp = dpaa2_eth_allocate_dpbp(priv); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + priv->bp[DPAA2_ETH_DEFAULT_BP_IDX] = bp; + priv->num_bps++; + + for (i = 0; i < priv->num_channels; i++) + priv->channel[i]->bp = bp; + + return 0; +} + +void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv, struct dpaa2_eth_bp *bp) +{ + int idx_bp; + + /* Find the index at which this BP is stored */ + for (idx_bp = 0; idx_bp < priv->num_bps; idx_bp++) + if (priv->bp[idx_bp] == bp) + break; + + /* Drain the pool and disable the associated MC object */ + dpaa2_eth_drain_pool(priv, bp->bpid); + dpbp_disable(priv->mc_io, 0, bp->dev->mc_handle); + dpbp_close(priv->mc_io, 0, bp->dev->mc_handle); + fsl_mc_object_free(bp->dev); + kfree(bp); + + /* Move the last in use DPBP over in this position */ + priv->bp[idx_bp] = priv->bp[priv->num_bps - 1]; + priv->num_bps--; +} + +static void dpaa2_eth_free_dpbps(struct dpaa2_eth_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_bps; i++) + dpaa2_eth_free_dpbp(priv, priv->bp[i]); } static int dpaa2_eth_set_buffer_layout(struct dpaa2_eth_priv *priv) @@ -3610,7 +3808,7 @@ static int dpaa2_eth_setup_dpni(struct fsl_mc_device *ls_dev) dev_err(dev, "DPNI version %u.%u not supported, need >= %u.%u\n", priv->dpni_ver_major, priv->dpni_ver_minor, DPNI_VER_MAJOR, DPNI_VER_MINOR); - err = -ENOTSUPP; + err = -EOPNOTSUPP; goto close; } @@ -4154,15 +4352,16 @@ out: */ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv) { + struct dpaa2_eth_bp *bp = priv->bp[DPAA2_ETH_DEFAULT_BP_IDX]; struct net_device *net_dev = priv->net_dev; + struct dpni_pools_cfg pools_params = { 0 }; struct device *dev = net_dev->dev.parent; - struct dpni_pools_cfg pools_params; struct dpni_error_cfg err_cfg; int err = 0; int i; pools_params.num_dpbp = 1; - pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id; + pools_params.pools[0].dpbp_id = bp->dev->obj_desc.id; pools_params.pools[0].backup_pool = 0; pools_params.pools[0].buffer_size = priv->rx_buf_size; err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); @@ -4426,8 +4625,10 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent); dpmac_dev = fsl_mc_get_endpoint(dpni_dev, 0); - if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER) + if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER) { + netdev_dbg(priv->net_dev, "waiting for mac\n"); return PTR_ERR(dpmac_dev); + } if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) return 0; @@ -4443,22 +4644,29 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) err = dpaa2_mac_open(mac); if (err) goto err_free_mac; - priv->mac = mac; - if (dpaa2_eth_is_type_phy(priv)) { + if (dpaa2_mac_is_type_phy(mac)) { err = dpaa2_mac_connect(mac); - if (err && err != -EPROBE_DEFER) - netdev_err(priv->net_dev, "Error connecting to the MAC endpoint: %pe", - ERR_PTR(err)); - if (err) + if (err) { + if (err == -EPROBE_DEFER) + netdev_dbg(priv->net_dev, + "could not connect to MAC\n"); + else + netdev_err(priv->net_dev, + "Error connecting to the MAC endpoint: %pe", + ERR_PTR(err)); goto err_close_mac; + } } + mutex_lock(&priv->mac_lock); + priv->mac = mac; + mutex_unlock(&priv->mac_lock); + return 0; err_close_mac: dpaa2_mac_close(mac); - priv->mac = NULL; err_free_mac: kfree(mac); return err; @@ -4466,15 +4674,21 @@ err_free_mac: static void dpaa2_eth_disconnect_mac(struct dpaa2_eth_priv *priv) { - if (dpaa2_eth_is_type_phy(priv)) - dpaa2_mac_disconnect(priv->mac); + struct dpaa2_mac *mac; + + mutex_lock(&priv->mac_lock); + mac = priv->mac; + priv->mac = NULL; + mutex_unlock(&priv->mac_lock); - if (!dpaa2_eth_has_mac(priv)) + if (!mac) return; - dpaa2_mac_close(priv->mac); - kfree(priv->mac); - priv->mac = NULL; + if (dpaa2_mac_is_type_phy(mac)) + dpaa2_mac_disconnect(mac); + + dpaa2_mac_close(mac); + kfree(mac); } static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) @@ -4484,6 +4698,7 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) struct fsl_mc_device *dpni_dev = to_fsl_mc_device(dev); struct net_device *net_dev = dev_get_drvdata(dev); struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + bool had_mac; int err; err = dpni_get_irq_status(dpni_dev->mc_io, 0, dpni_dev->mc_handle, @@ -4500,12 +4715,15 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) dpaa2_eth_set_mac_addr(netdev_priv(net_dev)); dpaa2_eth_update_tx_fqids(priv); - rtnl_lock(); - if (dpaa2_eth_has_mac(priv)) + /* We can avoid locking because the "endpoint changed" IRQ + * handler is the only one who changes priv->mac at runtime, + * so we are not racing with anyone. + */ + had_mac = !!priv->mac; + if (had_mac) dpaa2_eth_disconnect_mac(priv); else dpaa2_eth_connect_mac(priv); - rtnl_unlock(); } return IRQ_HANDLED; @@ -4601,6 +4819,9 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) priv = netdev_priv(net_dev); priv->net_dev = net_dev; + SET_NETDEV_DEVLINK_PORT(net_dev, &priv->devlink_port); + + mutex_init(&priv->mac_lock); priv->iommu_domain = iommu_get_domain_for_dev(dev); @@ -4623,10 +4844,12 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) err = fsl_mc_portal_allocate(dpni_dev, FSL_MC_IO_ATOMIC_CONTEXT_PORTAL, &priv->mc_io); if (err) { - if (err == -ENXIO) + if (err == -ENXIO) { + dev_dbg(dev, "waiting for MC portal\n"); err = -EPROBE_DEFER; - else + } else { dev_err(dev, "MC portal allocation failed\n"); + } goto err_portal_alloc; } @@ -4641,7 +4864,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) dpaa2_eth_setup_fqs(priv); - err = dpaa2_eth_setup_dpbp(priv); + err = dpaa2_eth_setup_default_dpbp(priv); if (err) goto err_dpbp_setup; @@ -4707,6 +4930,10 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) } #endif + err = dpaa2_eth_connect_mac(priv); + if (err) + goto err_connect_mac; + err = dpaa2_eth_setup_irqs(dpni_dev); if (err) { netdev_warn(net_dev, "Failed to set link interrupt, fall back to polling\n"); @@ -4719,10 +4946,6 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) priv->do_link_poll = true; } - err = dpaa2_eth_connect_mac(priv); - if (err) - goto err_connect_mac; - err = dpaa2_eth_dl_alloc(priv); if (err) goto err_dl_register; @@ -4756,13 +4979,13 @@ err_dl_port_add: err_dl_trap_register: dpaa2_eth_dl_free(priv); err_dl_register: - dpaa2_eth_disconnect_mac(priv); -err_connect_mac: if (priv->do_link_poll) kthread_stop(priv->poll_thread); else fsl_mc_free_irqs(dpni_dev); err_poll_thread: + dpaa2_eth_disconnect_mac(priv); +err_connect_mac: dpaa2_eth_free_rings(priv); err_alloc_rings: err_csum: @@ -4777,7 +5000,7 @@ err_alloc_percpu_extras: err_alloc_percpu_stats: dpaa2_eth_del_ch_napi(priv); err_bind: - dpaa2_eth_free_dpbp(priv); + dpaa2_eth_free_dpbps(priv); err_dpbp_setup: dpaa2_eth_free_dpio(priv); err_dpio_setup: @@ -4810,9 +5033,6 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) #endif unregister_netdev(net_dev); - rtnl_lock(); - dpaa2_eth_disconnect_mac(priv); - rtnl_unlock(); dpaa2_eth_dl_port_del(priv); dpaa2_eth_dl_traps_unregister(priv); @@ -4823,6 +5043,7 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) else fsl_mc_free_irqs(ls_dev); + dpaa2_eth_disconnect_mac(priv); dpaa2_eth_free_rings(priv); free_percpu(priv->fd); free_percpu(priv->sgt_cache); @@ -4830,7 +5051,7 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) free_percpu(priv->percpu_extras); dpaa2_eth_del_ch_napi(priv); - dpaa2_eth_free_dpbp(priv); + dpaa2_eth_free_dpbps(priv); dpaa2_eth_free_dpio(priv); dpaa2_eth_free_dpni(priv); if (priv->onestep_reg_base) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 447718483ef4..d56d7a13262e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ /* Copyright 2014-2016 Freescale Semiconductor Inc. - * Copyright 2016-2020 NXP + * Copyright 2016-2022 NXP */ #ifndef __DPAA2_ETH_H @@ -53,6 +53,12 @@ */ #define DPAA2_ETH_TXCONF_PER_NAPI 256 +/* Maximum number of Tx frames to be processed in a single NAPI + * call when AF_XDP is running. Bind it to DPAA2_ETH_TXCONF_PER_NAPI + * to maximize the throughput. + */ +#define DPAA2_ETH_TX_ZC_PER_NAPI DPAA2_ETH_TXCONF_PER_NAPI + /* Buffer qouta per channel. We want to keep in check number of ingress frames * in flight: for small sized frames, congestion group taildrop may kick in * first; for large sizes, Rx FQ taildrop threshold will ensure only a @@ -109,6 +115,14 @@ #define DPAA2_ETH_RX_BUF_ALIGN_REV1 256 #define DPAA2_ETH_RX_BUF_ALIGN 64 +/* The firmware allows assigning multiple buffer pools to a single DPNI - + * maximum 8 DPBP objects. By default, only the first DPBP (idx 0) is used for + * all queues. Thus, when enabling AF_XDP we must accommodate up to 9 DPBPs + * object: the default and 8 other distinct buffer pools, one for each queue. + */ +#define DPAA2_ETH_DEFAULT_BP_IDX 0 +#define DPAA2_ETH_MAX_BPS 9 + /* We are accommodating a skb backpointer and some S/G info * in the frame's software annotation. The hardware * options are either 0 or 64, so we choose the latter. @@ -122,6 +136,7 @@ enum dpaa2_eth_swa_type { DPAA2_ETH_SWA_SINGLE, DPAA2_ETH_SWA_SG, DPAA2_ETH_SWA_XDP, + DPAA2_ETH_SWA_XSK, DPAA2_ETH_SWA_SW_TSO, }; @@ -144,6 +159,10 @@ struct dpaa2_eth_swa { struct xdp_frame *xdpf; } xdp; struct { + struct xdp_buff *xdp_buff; + int sgt_size; + } xsk; + struct { struct sk_buff *skb; int num_sg; int sgt_size; @@ -421,12 +440,19 @@ enum dpaa2_eth_fq_type { }; struct dpaa2_eth_priv; +struct dpaa2_eth_channel; +struct dpaa2_eth_fq; struct dpaa2_eth_xdp_fds { struct dpaa2_fd fds[DEV_MAP_BULK_SIZE]; ssize_t num; }; +typedef void dpaa2_eth_consume_cb_t(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + struct dpaa2_eth_fq *fq); + struct dpaa2_eth_fq { u32 fqid; u32 tx_qdbin; @@ -439,10 +465,7 @@ struct dpaa2_eth_fq { struct dpaa2_eth_channel *channel; enum dpaa2_eth_fq_type type; - void (*consume)(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch, - const struct dpaa2_fd *fd, - struct dpaa2_eth_fq *fq); + dpaa2_eth_consume_cb_t *consume; struct dpaa2_eth_fq_stats stats; struct dpaa2_eth_xdp_fds xdp_redirect_fds; @@ -454,6 +477,11 @@ struct dpaa2_eth_ch_xdp { unsigned int res; }; +struct dpaa2_eth_bp { + struct fsl_mc_device *dev; + int bpid; +}; + struct dpaa2_eth_channel { struct dpaa2_io_notification_ctx nctx; struct fsl_mc_device *dpcon; @@ -472,6 +500,11 @@ struct dpaa2_eth_channel { /* Buffers to be recycled back in the buffer pool */ u64 recycled_bufs[DPAA2_ETH_BUFS_PER_CMD]; int recycled_bufs_cnt; + + bool xsk_zc; + int xsk_tx_pkts_sent; + struct xsk_buff_pool *xsk_pool; + struct dpaa2_eth_bp *bp; }; struct dpaa2_eth_dist_fields { @@ -506,7 +539,7 @@ struct dpaa2_eth_trap_data { #define DPAA2_ETH_DEFAULT_COPYBREAK 512 -#define DPAA2_ETH_ENQUEUE_MAX_FDS 200 +#define DPAA2_ETH_ENQUEUE_MAX_FDS 256 struct dpaa2_eth_fds { struct dpaa2_fd array[DPAA2_ETH_ENQUEUE_MAX_FDS]; }; @@ -535,14 +568,16 @@ struct dpaa2_eth_priv { u8 ptp_correction_off; void (*dpaa2_set_onestep_params_cb)(struct dpaa2_eth_priv *priv, u32 offset, u8 udp); - struct fsl_mc_device *dpbp_dev; u16 rx_buf_size; - u16 bpid; struct iommu_domain *iommu_domain; enum hwtstamp_tx_types tx_tstamp_type; /* Tx timestamping type */ bool rx_tstamp; /* Rx timestamping enabled */ + /* Buffer pool management */ + struct dpaa2_eth_bp *bp[DPAA2_ETH_MAX_BPS]; + int num_bps; + u16 tx_qdid; struct fsl_mc_io *mc_io; /* Cores which have an affine DPIO/DPCON. @@ -580,6 +615,8 @@ struct dpaa2_eth_priv { #endif struct dpaa2_mac *mac; + /* Serializes changes to priv->mac */ + struct mutex mac_lock; struct workqueue_struct *dpaa2_ptp_wq; struct work_struct tx_onestep_tstamp; struct sk_buff_head tx_skbs; @@ -733,16 +770,15 @@ static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv) static inline bool dpaa2_eth_is_type_phy(struct dpaa2_eth_priv *priv) { - if (priv->mac && - (priv->mac->attr.link_type == DPMAC_LINK_TYPE_PHY || - priv->mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE)) - return true; + lockdep_assert_held(&priv->mac_lock); - return false; + return dpaa2_mac_is_type_phy(priv->mac); } static inline bool dpaa2_eth_has_mac(struct dpaa2_eth_priv *priv) { + lockdep_assert_held(&priv->mac_lock); + return priv->mac ? true : false; } @@ -771,4 +807,54 @@ void dpaa2_eth_dl_traps_unregister(struct dpaa2_eth_priv *priv); struct dpaa2_eth_trap_item *dpaa2_eth_dl_get_trap(struct dpaa2_eth_priv *priv, struct dpaa2_fapr *fapr); + +struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv); +void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv, struct dpaa2_eth_bp *bp); + +struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, u32 fd_length, + void *fd_vaddr); + +void dpaa2_eth_receive_skb(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, void *vaddr, + struct dpaa2_eth_fq *fq, + struct rtnl_link_stats64 *percpu_stats, + struct sk_buff *skb); + +void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + struct dpaa2_eth_fq *fq); + +struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv); +void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_bp *bp); + +void *dpaa2_iova_to_virt(struct iommu_domain *domain, dma_addr_t iova_addr); +void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + dma_addr_t addr); + +void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_fd *fd, + void *buf_start, u16 queue_id); + +int dpaa2_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); +int dpaa2_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid); + +void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq *fq, + const struct dpaa2_fd *fd, bool in_napi); +bool dpaa2_xsk_tx(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch); + +/* SGT (Scatter-Gather Table) cache management */ +void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv); + +void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf); + #endif /* __DPAA2_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index eea7d7a07c00..e80e9388c71f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2014-2016 Freescale Semiconductor Inc. - * Copyright 2016 NXP - * Copyright 2020 NXP + * Copyright 2016-2022 NXP */ #include <linux/net_tstamp.h> @@ -86,11 +85,16 @@ static void dpaa2_eth_get_drvinfo(struct net_device *net_dev, static int dpaa2_eth_nway_reset(struct net_device *net_dev) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int err = -EOPNOTSUPP; + + mutex_lock(&priv->mac_lock); if (dpaa2_eth_is_type_phy(priv)) - return phylink_ethtool_nway_reset(priv->mac->phylink); + err = phylink_ethtool_nway_reset(priv->mac->phylink); + + mutex_unlock(&priv->mac_lock); - return -EOPNOTSUPP; + return err; } static int @@ -98,10 +102,18 @@ dpaa2_eth_get_link_ksettings(struct net_device *net_dev, struct ethtool_link_ksettings *link_settings) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int err; - if (dpaa2_eth_is_type_phy(priv)) - return phylink_ethtool_ksettings_get(priv->mac->phylink, - link_settings); + mutex_lock(&priv->mac_lock); + + if (dpaa2_eth_is_type_phy(priv)) { + err = phylink_ethtool_ksettings_get(priv->mac->phylink, + link_settings); + mutex_unlock(&priv->mac_lock); + return err; + } + + mutex_unlock(&priv->mac_lock); link_settings->base.autoneg = AUTONEG_DISABLE; if (!(priv->link_state.options & DPNI_LINK_OPT_HALF_DUPLEX)) @@ -116,11 +128,17 @@ dpaa2_eth_set_link_ksettings(struct net_device *net_dev, const struct ethtool_link_ksettings *link_settings) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int err = -EOPNOTSUPP; + + mutex_lock(&priv->mac_lock); + + if (dpaa2_eth_is_type_phy(priv)) + err = phylink_ethtool_ksettings_set(priv->mac->phylink, + link_settings); - if (!dpaa2_eth_is_type_phy(priv)) - return -ENOTSUPP; + mutex_unlock(&priv->mac_lock); - return phylink_ethtool_ksettings_set(priv->mac->phylink, link_settings); + return err; } static void dpaa2_eth_get_pauseparam(struct net_device *net_dev, @@ -129,11 +147,16 @@ static void dpaa2_eth_get_pauseparam(struct net_device *net_dev, struct dpaa2_eth_priv *priv = netdev_priv(net_dev); u64 link_options = priv->link_state.options; + mutex_lock(&priv->mac_lock); + if (dpaa2_eth_is_type_phy(priv)) { phylink_ethtool_get_pauseparam(priv->mac->phylink, pause); + mutex_unlock(&priv->mac_lock); return; } + mutex_unlock(&priv->mac_lock); + pause->rx_pause = dpaa2_eth_rx_pause_enabled(link_options); pause->tx_pause = dpaa2_eth_tx_pause_enabled(link_options); pause->autoneg = AUTONEG_DISABLE; @@ -152,9 +175,17 @@ static int dpaa2_eth_set_pauseparam(struct net_device *net_dev, return -EOPNOTSUPP; } - if (dpaa2_eth_is_type_phy(priv)) - return phylink_ethtool_set_pauseparam(priv->mac->phylink, - pause); + mutex_lock(&priv->mac_lock); + + if (dpaa2_eth_is_type_phy(priv)) { + err = phylink_ethtool_set_pauseparam(priv->mac->phylink, + pause); + mutex_unlock(&priv->mac_lock); + return err; + } + + mutex_unlock(&priv->mac_lock); + if (pause->autoneg) return -EOPNOTSUPP; @@ -186,7 +217,6 @@ static int dpaa2_eth_set_pauseparam(struct net_device *net_dev, static void dpaa2_eth_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - struct dpaa2_eth_priv *priv = netdev_priv(netdev); u8 *p = data; int i; @@ -200,22 +230,17 @@ static void dpaa2_eth_get_strings(struct net_device *netdev, u32 stringset, strscpy(p, dpaa2_ethtool_extras[i], ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - if (dpaa2_eth_has_mac(priv)) - dpaa2_mac_get_strings(p); + dpaa2_mac_get_strings(p); break; } } static int dpaa2_eth_get_sset_count(struct net_device *net_dev, int sset) { - int num_ss_stats = DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS; - struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - switch (sset) { case ETH_SS_STATS: /* ethtool_get_stats(), ethtool_get_drvinfo() */ - if (dpaa2_eth_has_mac(priv)) - num_ss_stats += dpaa2_mac_get_sset_count(); - return num_ss_stats; + return DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS + + dpaa2_mac_get_sset_count(); default: return -EOPNOTSUPP; } @@ -227,17 +252,8 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, struct ethtool_stats *stats, u64 *data) { - int i = 0; - int j, k, err; - int num_cnt; - union dpni_statistics dpni_stats; - u32 fcnt, bcnt; - u32 fcnt_rx_total = 0, fcnt_tx_total = 0; - u32 bcnt_rx_total = 0, bcnt_tx_total = 0; - u32 buf_cnt; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - struct dpaa2_eth_drv_stats *extras; - struct dpaa2_eth_ch_stats *ch_stats; + union dpni_statistics dpni_stats; int dpni_stats_page_size[DPNI_STATISTICS_CNT] = { sizeof(dpni_stats.page_0), sizeof(dpni_stats.page_1), @@ -247,6 +263,13 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, sizeof(dpni_stats.page_5), sizeof(dpni_stats.page_6), }; + u32 fcnt_rx_total = 0, fcnt_tx_total = 0; + u32 bcnt_rx_total = 0, bcnt_tx_total = 0; + struct dpaa2_eth_ch_stats *ch_stats; + struct dpaa2_eth_drv_stats *extras; + u32 buf_cnt, buf_cnt_total = 0; + int j, k, err, num_cnt, i = 0; + u32 fcnt, bcnt; memset(data, 0, sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS)); @@ -308,15 +331,22 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, *(data + i++) = fcnt_tx_total; *(data + i++) = bcnt_tx_total; - err = dpaa2_io_query_bp_count(NULL, priv->bpid, &buf_cnt); - if (err) { - netdev_warn(net_dev, "Buffer count query error %d\n", err); - return; + for (j = 0; j < priv->num_bps; j++) { + err = dpaa2_io_query_bp_count(NULL, priv->bp[j]->bpid, &buf_cnt); + if (err) { + netdev_warn(net_dev, "Buffer count query error %d\n", err); + return; + } + buf_cnt_total += buf_cnt; } - *(data + i++) = buf_cnt; + *(data + i++) = buf_cnt_total; + + mutex_lock(&priv->mac_lock); if (dpaa2_eth_has_mac(priv)) dpaa2_mac_get_ethtool_stats(priv->mac, data + i); + + mutex_unlock(&priv->mac_lock); } static int dpaa2_eth_prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask, @@ -876,6 +906,29 @@ restore_rx_usecs: return err; } +static void dpaa2_eth_get_channels(struct net_device *net_dev, + struct ethtool_channels *channels) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int queue_count = dpaa2_eth_queue_count(priv); + + channels->max_rx = queue_count; + channels->max_tx = queue_count; + channels->rx_count = queue_count; + channels->tx_count = queue_count; + + /* Tx confirmation and Rx error */ + channels->max_other = queue_count + 1; + channels->max_combined = channels->max_rx + + channels->max_tx + + channels->max_other; + /* Tx conf and Rx err */ + channels->other_count = queue_count + 1; + channels->combined_count = channels->rx_count + + channels->tx_count + + channels->other_count; +} + const struct ethtool_ops dpaa2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -896,4 +949,5 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .set_tunable = dpaa2_eth_set_tunable, .get_coalesce = dpaa2_eth_get_coalesce, .set_coalesce = dpaa2_eth_set_coalesce, + .get_channels = dpaa2_eth_get_channels, }; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 49ff85633783..c886f33f8c6f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -105,6 +105,7 @@ static struct fwnode_handle *dpaa2_mac_get_node(struct device *dev, * thus the fwnode field is not yet set. Defer probe if we are * facing this situation. */ + dev_dbg(dev, "dprc not finished probing\n"); return ERR_PTR(-EPROBE_DEFER); } @@ -235,7 +236,6 @@ static void dpaa2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = dpaa2_mac_select_pcs, .mac_config = dpaa2_mac_config, .mac_link_up = dpaa2_mac_link_up, @@ -264,8 +264,10 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, mdiodev = fwnode_mdio_find_device(node); fwnode_handle_put(node); - if (!mdiodev) + if (!mdiodev) { + netdev_dbg(mac->net_dev, "missing PCS device\n"); return -EPROBE_DEFER; + } mac->pcs = lynx_pcs_create(mdiodev); if (!mac->pcs) { @@ -336,12 +338,20 @@ static void dpaa2_mac_set_supported_interfaces(struct dpaa2_mac *mac) void dpaa2_mac_start(struct dpaa2_mac *mac) { + ASSERT_RTNL(); + if (mac->serdes_phy) phy_power_on(mac->serdes_phy); + + phylink_start(mac->phylink); } void dpaa2_mac_stop(struct dpaa2_mac *mac) { + ASSERT_RTNL(); + + phylink_stop(mac->phylink); + if (mac->serdes_phy) phy_power_off(mac->serdes_phy); } @@ -420,7 +430,9 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) } mac->phylink = phylink; + rtnl_lock(); err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); + rtnl_unlock(); if (err) { netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err); goto err_phylink_destroy; @@ -438,10 +450,10 @@ err_pcs_destroy: void dpaa2_mac_disconnect(struct dpaa2_mac *mac) { - if (!mac->phylink) - return; - + rtnl_lock(); phylink_disconnect_phy(mac->phylink); + rtnl_unlock(); + phylink_destroy(mac->phylink); dpaa2_pcs_destroy(mac); of_phy_put(mac->serdes_phy); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index a58cab188a99..c1ec9efd413a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -30,8 +30,14 @@ struct dpaa2_mac { struct phy *serdes_phy; }; -bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev, - struct fsl_mc_io *mc_io); +static inline bool dpaa2_mac_is_type_phy(struct dpaa2_mac *mac) +{ + if (!mac) + return false; + + return mac->attr.link_type == DPMAC_LINK_TYPE_PHY || + mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE; +} int dpaa2_mac_open(struct dpaa2_mac *mac); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index c8cb541572ff..90d23ab1ce9d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -8,7 +8,6 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/msi.h> #include <linux/fsl/mc.h> #include "dpaa2-ptp.h" diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c index 720c9230cab5..6bc1988be311 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c @@ -60,11 +60,18 @@ dpaa2_switch_get_link_ksettings(struct net_device *netdev, { struct ethsw_port_priv *port_priv = netdev_priv(netdev); struct dpsw_link_state state = {0}; - int err = 0; + int err; + + mutex_lock(&port_priv->mac_lock); + + if (dpaa2_switch_port_is_type_phy(port_priv)) { + err = phylink_ethtool_ksettings_get(port_priv->mac->phylink, + link_ksettings); + mutex_unlock(&port_priv->mac_lock); + return err; + } - if (dpaa2_switch_port_is_type_phy(port_priv)) - return phylink_ethtool_ksettings_get(port_priv->mac->phylink, - link_ksettings); + mutex_unlock(&port_priv->mac_lock); err = dpsw_if_get_link_state(port_priv->ethsw_data->mc_io, 0, port_priv->ethsw_data->dpsw_handle, @@ -99,9 +106,16 @@ dpaa2_switch_set_link_ksettings(struct net_device *netdev, bool if_running; int err = 0, ret; - if (dpaa2_switch_port_is_type_phy(port_priv)) - return phylink_ethtool_ksettings_set(port_priv->mac->phylink, - link_ksettings); + mutex_lock(&port_priv->mac_lock); + + if (dpaa2_switch_port_is_type_phy(port_priv)) { + err = phylink_ethtool_ksettings_set(port_priv->mac->phylink, + link_ksettings); + mutex_unlock(&port_priv->mac_lock); + return err; + } + + mutex_unlock(&port_priv->mac_lock); /* Interface needs to be down to change link settings */ if_running = netif_running(netdev); @@ -145,14 +159,9 @@ dpaa2_switch_set_link_ksettings(struct net_device *netdev, static int dpaa2_switch_ethtool_get_sset_count(struct net_device *netdev, int sset) { - struct ethsw_port_priv *port_priv = netdev_priv(netdev); - int num_ss_stats = DPAA2_SWITCH_NUM_COUNTERS; - switch (sset) { case ETH_SS_STATS: - if (port_priv->mac) - num_ss_stats += dpaa2_mac_get_sset_count(); - return num_ss_stats; + return DPAA2_SWITCH_NUM_COUNTERS + dpaa2_mac_get_sset_count(); default: return -EOPNOTSUPP; } @@ -161,7 +170,6 @@ dpaa2_switch_ethtool_get_sset_count(struct net_device *netdev, int sset) static void dpaa2_switch_ethtool_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - struct ethsw_port_priv *port_priv = netdev_priv(netdev); u8 *p = data; int i; @@ -172,8 +180,7 @@ static void dpaa2_switch_ethtool_get_strings(struct net_device *netdev, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - if (port_priv->mac) - dpaa2_mac_get_strings(p); + dpaa2_mac_get_strings(p); break; } } @@ -196,8 +203,12 @@ static void dpaa2_switch_ethtool_get_stats(struct net_device *netdev, dpaa2_switch_ethtool_counters[i].name, err); } - if (port_priv->mac) + mutex_lock(&port_priv->mac_lock); + + if (dpaa2_switch_port_has_mac(port_priv)) dpaa2_mac_get_ethtool_stats(port_priv->mac, data + i); + + mutex_unlock(&port_priv->mac_lock); } const struct ethtool_ops dpaa2_switch_port_ethtool_ops = { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 2b5909fa93cf..f4ae4289c41a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -10,7 +10,6 @@ #include <linux/module.h> #include <linux/interrupt.h> -#include <linux/msi.h> #include <linux/kthread.h> #include <linux/workqueue.h> #include <linux/iommu.h> @@ -603,8 +602,11 @@ static int dpaa2_switch_port_link_state_update(struct net_device *netdev) /* When we manage the MAC/PHY using phylink there is no need * to manually update the netif_carrier. + * We can avoid locking because we are called from the "link changed" + * IRQ handler, which is the same as the "endpoint changed" IRQ handler + * (the writer to port_priv->mac), so we cannot race with it. */ - if (dpaa2_switch_port_is_type_phy(port_priv)) + if (dpaa2_mac_is_type_phy(port_priv->mac)) return 0; /* Interrupts are received even though no one issued an 'ifconfig up' @@ -684,6 +686,8 @@ static int dpaa2_switch_port_open(struct net_device *netdev) struct ethsw_core *ethsw = port_priv->ethsw_data; int err; + mutex_lock(&port_priv->mac_lock); + if (!dpaa2_switch_port_is_type_phy(port_priv)) { /* Explicitly set carrier off, otherwise * netif_carrier_ok() will return true and cause 'ip link show' @@ -697,16 +701,17 @@ static int dpaa2_switch_port_open(struct net_device *netdev) port_priv->ethsw_data->dpsw_handle, port_priv->idx); if (err) { + mutex_unlock(&port_priv->mac_lock); netdev_err(netdev, "dpsw_if_enable err %d\n", err); return err; } dpaa2_switch_enable_ctrl_if_napi(ethsw); - if (dpaa2_switch_port_is_type_phy(port_priv)) { + if (dpaa2_switch_port_is_type_phy(port_priv)) dpaa2_mac_start(port_priv->mac); - phylink_start(port_priv->mac->phylink); - } + + mutex_unlock(&port_priv->mac_lock); return 0; } @@ -717,14 +722,17 @@ static int dpaa2_switch_port_stop(struct net_device *netdev) struct ethsw_core *ethsw = port_priv->ethsw_data; int err; + mutex_lock(&port_priv->mac_lock); + if (dpaa2_switch_port_is_type_phy(port_priv)) { - phylink_stop(port_priv->mac->phylink); dpaa2_mac_stop(port_priv->mac); } else { netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); } + mutex_unlock(&port_priv->mac_lock); + err = dpsw_if_disable(port_priv->ethsw_data->mc_io, 0, port_priv->ethsw_data->dpsw_handle, port_priv->idx); @@ -1453,9 +1461,8 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv) err = dpaa2_mac_open(mac); if (err) goto err_free_mac; - port_priv->mac = mac; - if (dpaa2_switch_port_is_type_phy(port_priv)) { + if (dpaa2_mac_is_type_phy(mac)) { err = dpaa2_mac_connect(mac); if (err) { netdev_err(port_priv->netdev, @@ -1465,11 +1472,14 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv) } } + mutex_lock(&port_priv->mac_lock); + port_priv->mac = mac; + mutex_unlock(&port_priv->mac_lock); + return 0; err_close_mac: dpaa2_mac_close(mac); - port_priv->mac = NULL; err_free_mac: kfree(mac); return err; @@ -1477,15 +1487,21 @@ err_free_mac: static void dpaa2_switch_port_disconnect_mac(struct ethsw_port_priv *port_priv) { - if (dpaa2_switch_port_is_type_phy(port_priv)) - dpaa2_mac_disconnect(port_priv->mac); + struct dpaa2_mac *mac; + + mutex_lock(&port_priv->mac_lock); + mac = port_priv->mac; + port_priv->mac = NULL; + mutex_unlock(&port_priv->mac_lock); - if (!dpaa2_switch_port_has_mac(port_priv)) + if (!mac) return; - dpaa2_mac_close(port_priv->mac); - kfree(port_priv->mac); - port_priv->mac = NULL; + if (dpaa2_mac_is_type_phy(mac)) + dpaa2_mac_disconnect(mac); + + dpaa2_mac_close(mac); + kfree(mac); } static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) @@ -1495,6 +1511,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) struct ethsw_port_priv *port_priv; u32 status = ~0; int err, if_id; + bool had_mac; err = dpsw_get_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, &status); @@ -1512,12 +1529,15 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) } if (status & DPSW_IRQ_EVENT_ENDPOINT_CHANGED) { - rtnl_lock(); - if (dpaa2_switch_port_has_mac(port_priv)) + /* We can avoid locking because the "endpoint changed" IRQ + * handler is the only one who changes priv->mac at runtime, + * so we are not racing with anyone. + */ + had_mac = !!port_priv->mac; + if (had_mac) dpaa2_switch_port_disconnect_mac(port_priv); else dpaa2_switch_port_connect_mac(port_priv); - rtnl_unlock(); } out: @@ -2935,9 +2955,7 @@ static void dpaa2_switch_remove_port(struct ethsw_core *ethsw, { struct ethsw_port_priv *port_priv = ethsw->ports[port_idx]; - rtnl_lock(); dpaa2_switch_port_disconnect_mac(port_priv); - rtnl_unlock(); free_netdev(port_priv->netdev); ethsw->ports[port_idx] = NULL; } @@ -3256,6 +3274,8 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw, port_priv->netdev = port_netdev; port_priv->ethsw_data = ethsw; + mutex_init(&port_priv->mac_lock); + port_priv->idx = port_idx; port_priv->stp_state = BR_STATE_FORWARDING; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h index 0002dca4d417..42b3ca73f55d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h @@ -161,6 +161,8 @@ struct ethsw_port_priv { struct dpaa2_switch_filter_block *filter_block; struct dpaa2_mac *mac; + /* Protects against changes to port_priv->mac */ + struct mutex mac_lock; }; /* Switch data */ @@ -230,12 +232,7 @@ static inline bool dpaa2_switch_supports_cpu_traffic(struct ethsw_core *ethsw) static inline bool dpaa2_switch_port_is_type_phy(struct ethsw_port_priv *port_priv) { - if (port_priv->mac && - (port_priv->mac->attr.link_type == DPMAC_LINK_TYPE_PHY || - port_priv->mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE)) - return true; - - return false; + return dpaa2_mac_is_type_phy(port_priv->mac); } static inline bool dpaa2_switch_port_has_mac(struct ethsw_port_priv *port_priv) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c new file mode 100644 index 000000000000..051748b997f3 --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2022 NXP + */ +#include <linux/filter.h> +#include <linux/compiler.h> +#include <linux/bpf_trace.h> +#include <net/xdp.h> +#include <net/xdp_sock_drv.h> + +#include "dpaa2-eth.h" + +static void dpaa2_eth_setup_consume_func(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + enum dpaa2_eth_fq_type type, + dpaa2_eth_consume_cb_t *consume) +{ + struct dpaa2_eth_fq *fq; + int i; + + for (i = 0; i < priv->num_fqs; i++) { + fq = &priv->fq[i]; + + if (fq->type != type) + continue; + if (fq->channel != ch) + continue; + + fq->consume = consume; + } +} + +static u32 dpaa2_xsk_run_xdp(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_eth_fq *rx_fq, + struct dpaa2_fd *fd, void *vaddr) +{ + dma_addr_t addr = dpaa2_fd_get_addr(fd); + struct bpf_prog *xdp_prog; + struct xdp_buff *xdp_buff; + struct dpaa2_eth_swa *swa; + u32 xdp_act = XDP_PASS; + int err; + + xdp_prog = READ_ONCE(ch->xdp.prog); + if (!xdp_prog) + goto out; + + swa = (struct dpaa2_eth_swa *)(vaddr + DPAA2_ETH_RX_HWA_SIZE + + ch->xsk_pool->umem->headroom); + xdp_buff = swa->xsk.xdp_buff; + + xdp_buff->data_hard_start = vaddr; + xdp_buff->data = vaddr + dpaa2_fd_get_offset(fd); + xdp_buff->data_end = xdp_buff->data + dpaa2_fd_get_len(fd); + xdp_set_data_meta_invalid(xdp_buff); + xdp_buff->rxq = &ch->xdp_rxq; + + xsk_buff_dma_sync_for_cpu(xdp_buff, ch->xsk_pool); + xdp_act = bpf_prog_run_xdp(xdp_prog, xdp_buff); + + /* xdp.data pointer may have changed */ + dpaa2_fd_set_offset(fd, xdp_buff->data - vaddr); + dpaa2_fd_set_len(fd, xdp_buff->data_end - xdp_buff->data); + + if (likely(xdp_act == XDP_REDIRECT)) { + err = xdp_do_redirect(priv->net_dev, xdp_buff, xdp_prog); + if (unlikely(err)) { + ch->stats.xdp_drop++; + dpaa2_eth_recycle_buf(priv, ch, addr); + } else { + ch->buf_count--; + ch->stats.xdp_redirect++; + } + + goto xdp_redir; + } + + switch (xdp_act) { + case XDP_PASS: + break; + case XDP_TX: + dpaa2_eth_xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid); + break; + default: + bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); + fallthrough; + case XDP_DROP: + dpaa2_eth_recycle_buf(priv, ch, addr); + ch->stats.xdp_drop++; + break; + } + +xdp_redir: + ch->xdp.res |= xdp_act; +out: + return xdp_act; +} + +/* Rx frame processing routine for the AF_XDP fast path */ +static void dpaa2_xsk_rx(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + const struct dpaa2_fd *fd, + struct dpaa2_eth_fq *fq) +{ + dma_addr_t addr = dpaa2_fd_get_addr(fd); + u8 fd_format = dpaa2_fd_get_format(fd); + struct rtnl_link_stats64 *percpu_stats; + u32 fd_length = dpaa2_fd_get_len(fd); + struct sk_buff *skb; + void *vaddr; + u32 xdp_act; + + trace_dpaa2_rx_xsk_fd(priv->net_dev, fd); + + vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); + percpu_stats = this_cpu_ptr(priv->percpu_stats); + + if (fd_format != dpaa2_fd_single) { + WARN_ON(priv->xdp_prog); + /* AF_XDP doesn't support any other formats */ + goto err_frame_format; + } + + xdp_act = dpaa2_xsk_run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr); + if (xdp_act != XDP_PASS) { + percpu_stats->rx_packets++; + percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); + return; + } + + /* Build skb */ + skb = dpaa2_eth_alloc_skb(priv, ch, fd, fd_length, vaddr); + if (!skb) + /* Nothing else we can do, recycle the buffer and + * drop the frame. + */ + goto err_alloc_skb; + + /* Send the skb to the Linux networking stack */ + dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb); + + return; + +err_alloc_skb: + dpaa2_eth_recycle_buf(priv, ch, addr); +err_frame_format: + percpu_stats->rx_dropped++; +} + +static void dpaa2_xsk_set_bp_per_qdbin(struct dpaa2_eth_priv *priv, + struct dpni_pools_cfg *pools_params) +{ + int curr_bp = 0, i, j; + + pools_params->pool_options = DPNI_POOL_ASSOC_QDBIN; + for (i = 0; i < priv->num_bps; i++) { + for (j = 0; j < priv->num_channels; j++) + if (priv->bp[i] == priv->channel[j]->bp) + pools_params->pools[curr_bp].priority_mask |= (1 << j); + if (!pools_params->pools[curr_bp].priority_mask) + continue; + + pools_params->pools[curr_bp].dpbp_id = priv->bp[i]->bpid; + pools_params->pools[curr_bp].buffer_size = priv->rx_buf_size; + pools_params->pools[curr_bp++].backup_pool = 0; + } + pools_params->num_dpbp = curr_bp; +} + +static int dpaa2_xsk_disable_pool(struct net_device *dev, u16 qid) +{ + struct xsk_buff_pool *pool = xsk_get_pool_from_qid(dev, qid); + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpni_pools_cfg pools_params = { 0 }; + struct dpaa2_eth_channel *ch; + int err; + bool up; + + ch = priv->channel[qid]; + if (!ch->xsk_pool) + return -EINVAL; + + up = netif_running(dev); + if (up) + dev_close(dev); + + xsk_pool_dma_unmap(pool, 0); + err = xdp_rxq_info_reg_mem_model(&ch->xdp_rxq, + MEM_TYPE_PAGE_ORDER0, NULL); + if (err) + netdev_err(dev, "xsk_rxq_info_reg_mem_model() failed (err = %d)\n", + err); + + dpaa2_eth_free_dpbp(priv, ch->bp); + + ch->xsk_zc = false; + ch->xsk_pool = NULL; + ch->xsk_tx_pkts_sent = 0; + ch->bp = priv->bp[DPAA2_ETH_DEFAULT_BP_IDX]; + + dpaa2_eth_setup_consume_func(priv, ch, DPAA2_RX_FQ, dpaa2_eth_rx); + + dpaa2_xsk_set_bp_per_qdbin(priv, &pools_params); + err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); + if (err) + netdev_err(dev, "dpni_set_pools() failed\n"); + + if (up) { + err = dev_open(dev, NULL); + if (err) + return err; + } + + return 0; +} + +static int dpaa2_xsk_enable_pool(struct net_device *dev, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpni_pools_cfg pools_params = { 0 }; + struct dpaa2_eth_channel *ch; + int err, err2; + bool up; + + if (priv->dpni_attrs.wriop_version < DPAA2_WRIOP_VERSION(3, 0, 0)) { + netdev_err(dev, "AF_XDP zero-copy not supported on devices <= WRIOP(3, 0, 0)\n"); + return -EOPNOTSUPP; + } + + if (priv->dpni_attrs.num_queues > 8) { + netdev_err(dev, "AF_XDP zero-copy not supported on DPNI with more then 8 queues\n"); + return -EOPNOTSUPP; + } + + up = netif_running(dev); + if (up) + dev_close(dev); + + err = xsk_pool_dma_map(pool, priv->net_dev->dev.parent, 0); + if (err) { + netdev_err(dev, "xsk_pool_dma_map() failed (err = %d)\n", + err); + goto err_dma_unmap; + } + + ch = priv->channel[qid]; + err = xdp_rxq_info_reg_mem_model(&ch->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); + if (err) { + netdev_err(dev, "xdp_rxq_info_reg_mem_model() failed (err = %d)\n", err); + goto err_mem_model; + } + xsk_pool_set_rxq_info(pool, &ch->xdp_rxq); + + priv->bp[priv->num_bps] = dpaa2_eth_allocate_dpbp(priv); + if (IS_ERR(priv->bp[priv->num_bps])) { + err = PTR_ERR(priv->bp[priv->num_bps]); + goto err_bp_alloc; + } + ch->xsk_zc = true; + ch->xsk_pool = pool; + ch->bp = priv->bp[priv->num_bps++]; + + dpaa2_eth_setup_consume_func(priv, ch, DPAA2_RX_FQ, dpaa2_xsk_rx); + + dpaa2_xsk_set_bp_per_qdbin(priv, &pools_params); + err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); + if (err) { + netdev_err(dev, "dpni_set_pools() failed\n"); + goto err_set_pools; + } + + if (up) { + err = dev_open(dev, NULL); + if (err) + return err; + } + + return 0; + +err_set_pools: + err2 = dpaa2_xsk_disable_pool(dev, qid); + if (err2) + netdev_err(dev, "dpaa2_xsk_disable_pool() failed %d\n", err2); +err_bp_alloc: + err2 = xdp_rxq_info_reg_mem_model(&priv->channel[qid]->xdp_rxq, + MEM_TYPE_PAGE_ORDER0, NULL); + if (err2) + netdev_err(dev, "xsk_rxq_info_reg_mem_model() failed with %d)\n", err2); +err_mem_model: + xsk_pool_dma_unmap(pool, 0); +err_dma_unmap: + if (up) + dev_open(dev, NULL); + + return err; +} + +int dpaa2_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid) +{ + return pool ? dpaa2_xsk_enable_pool(dev, pool, qid) : + dpaa2_xsk_disable_pool(dev, qid); +} + +int dpaa2_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpaa2_eth_channel *ch = priv->channel[qid]; + + if (!priv->link_state.up) + return -ENETDOWN; + + if (!priv->xdp_prog) + return -EINVAL; + + if (!ch->xsk_zc) + return -EINVAL; + + /* We do not have access to a per channel SW interrupt, so instead we + * schedule a NAPI instance. + */ + if (!napi_if_scheduled_mark_missed(&ch->napi)) + napi_schedule(&ch->napi); + + return 0; +} + +static int dpaa2_xsk_tx_build_fd(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch, + struct dpaa2_fd *fd, + struct xdp_desc *xdp_desc) +{ + struct device *dev = priv->net_dev->dev.parent; + struct dpaa2_sg_entry *sgt; + struct dpaa2_eth_swa *swa; + void *sgt_buf = NULL; + dma_addr_t sgt_addr; + int sgt_buf_size; + dma_addr_t addr; + int err = 0; + + /* Prepare the HW SGT structure */ + sgt_buf_size = priv->tx_data_offset + sizeof(struct dpaa2_sg_entry); + sgt_buf = dpaa2_eth_sgt_get(priv); + if (unlikely(!sgt_buf)) + return -ENOMEM; + sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset); + + /* Get the address of the XSK Tx buffer */ + addr = xsk_buff_raw_get_dma(ch->xsk_pool, xdp_desc->addr); + xsk_buff_raw_dma_sync_for_device(ch->xsk_pool, addr, xdp_desc->len); + + /* Fill in the HW SGT structure */ + dpaa2_sg_set_addr(sgt, addr); + dpaa2_sg_set_len(sgt, xdp_desc->len); + dpaa2_sg_set_final(sgt, true); + + /* Store the necessary info in the SGT buffer */ + swa = (struct dpaa2_eth_swa *)sgt_buf; + swa->type = DPAA2_ETH_SWA_XSK; + swa->xsk.sgt_size = sgt_buf_size; + + /* Separately map the SGT buffer */ + sgt_addr = dma_map_single(dev, sgt_buf, sgt_buf_size, DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(dev, sgt_addr))) { + err = -ENOMEM; + goto sgt_map_failed; + } + + /* Initialize FD fields */ + memset(fd, 0, sizeof(struct dpaa2_fd)); + dpaa2_fd_set_offset(fd, priv->tx_data_offset); + dpaa2_fd_set_format(fd, dpaa2_fd_sg); + dpaa2_fd_set_addr(fd, sgt_addr); + dpaa2_fd_set_len(fd, xdp_desc->len); + dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); + + return 0; + +sgt_map_failed: + dpaa2_eth_sgt_recycle(priv, sgt_buf); + + return err; +} + +bool dpaa2_xsk_tx(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_channel *ch) +{ + struct xdp_desc *xdp_descs = ch->xsk_pool->tx_descs; + struct dpaa2_eth_drv_stats *percpu_extras; + struct rtnl_link_stats64 *percpu_stats; + int budget = DPAA2_ETH_TX_ZC_PER_NAPI; + int total_enqueued, enqueued; + int retries, max_retries; + struct dpaa2_eth_fq *fq; + struct dpaa2_fd *fds; + int batch, i, err; + + percpu_stats = this_cpu_ptr(priv->percpu_stats); + percpu_extras = this_cpu_ptr(priv->percpu_extras); + fds = (this_cpu_ptr(priv->fd))->array; + + /* Use the FQ with the same idx as the affine CPU */ + fq = &priv->fq[ch->nctx.desired_cpu]; + + batch = xsk_tx_peek_release_desc_batch(ch->xsk_pool, budget); + if (!batch) + return false; + + /* Create a FD for each XSK frame to be sent */ + for (i = 0; i < batch; i++) { + err = dpaa2_xsk_tx_build_fd(priv, ch, &fds[i], &xdp_descs[i]); + if (err) { + batch = i; + break; + } + + trace_dpaa2_tx_xsk_fd(priv->net_dev, &fds[i]); + } + + /* Enqueue all the created FDs */ + max_retries = batch * DPAA2_ETH_ENQUEUE_RETRIES; + total_enqueued = 0; + enqueued = 0; + retries = 0; + while (total_enqueued < batch && retries < max_retries) { + err = priv->enqueue(priv, fq, &fds[total_enqueued], 0, + batch - total_enqueued, &enqueued); + if (err == -EBUSY) { + retries++; + continue; + } + + total_enqueued += enqueued; + } + percpu_extras->tx_portal_busy += retries; + + /* Update statistics */ + percpu_stats->tx_packets += total_enqueued; + for (i = 0; i < total_enqueued; i++) + percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]); + for (i = total_enqueued; i < batch; i++) { + dpaa2_eth_free_tx_fd(priv, ch, fq, &fds[i], false); + percpu_stats->tx_errors++; + } + + xsk_tx_release(ch->xsk_pool); + + return total_enqueued == budget; +} diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 828f538097af..be9492b8d5dc 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h @@ -13,10 +13,12 @@ #define DPNI_VER_MINOR 0 #define DPNI_CMD_BASE_VERSION 1 #define DPNI_CMD_2ND_VERSION 2 +#define DPNI_CMD_3RD_VERSION 3 #define DPNI_CMD_ID_OFFSET 4 #define DPNI_CMD(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_BASE_VERSION) #define DPNI_CMD_V2(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_2ND_VERSION) +#define DPNI_CMD_V3(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_3RD_VERSION) #define DPNI_CMDID_OPEN DPNI_CMD(0x801) #define DPNI_CMDID_CLOSE DPNI_CMD(0x800) @@ -39,7 +41,7 @@ #define DPNI_CMDID_GET_IRQ_STATUS DPNI_CMD(0x016) #define DPNI_CMDID_CLEAR_IRQ_STATUS DPNI_CMD(0x017) -#define DPNI_CMDID_SET_POOLS DPNI_CMD(0x200) +#define DPNI_CMDID_SET_POOLS DPNI_CMD_V3(0x200) #define DPNI_CMDID_SET_ERRORS_BEHAVIOR DPNI_CMD(0x20B) #define DPNI_CMDID_GET_QDID DPNI_CMD(0x210) @@ -115,14 +117,19 @@ struct dpni_cmd_open { }; #define DPNI_BACKUP_POOL(val, order) (((val) & 0x1) << (order)) + +struct dpni_cmd_pool { + __le16 dpbp_id; + u8 priority_mask; + u8 pad; +}; + struct dpni_cmd_set_pools { - /* cmd word 0 */ u8 num_dpbp; u8 backup_pool_mask; - __le16 pad; - /* cmd word 0..4 */ - __le32 dpbp_id[DPNI_MAX_DPBP]; - /* cmd word 4..6 */ + u8 pad; + u8 pool_options; + struct dpni_cmd_pool pool[DPNI_MAX_DPBP]; __le16 buffer_size[DPNI_MAX_DPBP]; }; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c index 6c3b36f20fb8..02601a283b59 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c @@ -173,8 +173,12 @@ int dpni_set_pools(struct fsl_mc_io *mc_io, token); cmd_params = (struct dpni_cmd_set_pools *)cmd.params; cmd_params->num_dpbp = cfg->num_dpbp; + cmd_params->pool_options = cfg->pool_options; for (i = 0; i < DPNI_MAX_DPBP; i++) { - cmd_params->dpbp_id[i] = cpu_to_le32(cfg->pools[i].dpbp_id); + cmd_params->pool[i].dpbp_id = + cpu_to_le16(cfg->pools[i].dpbp_id); + cmd_params->pool[i].priority_mask = + cfg->pools[i].priority_mask; cmd_params->buffer_size[i] = cpu_to_le16(cfg->pools[i].buffer_size); cmd_params->backup_pool_mask |= diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index 6fffd519aa00..5c0a1d5ac934 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h @@ -92,19 +92,28 @@ int dpni_close(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token); +#define DPNI_POOL_ASSOC_QPRI 0 +#define DPNI_POOL_ASSOC_QDBIN 1 + /** * struct dpni_pools_cfg - Structure representing buffer pools configuration * @num_dpbp: Number of DPBPs + * @pool_options: Buffer assignment options. + * This field is a combination of DPNI_POOL_ASSOC_flags * @pools: Array of buffer pools parameters; The number of valid entries * must match 'num_dpbp' value * @pools.dpbp_id: DPBP object ID + * @pools.priority: Priority mask that indicates TC's used with this buffer. + * If set to 0x00 MC will assume value 0xff. * @pools.buffer_size: Buffer size * @pools.backup_pool: Backup pool */ struct dpni_pools_cfg { u8 num_dpbp; + u8 pool_options; struct { int dpbp_id; + u8 priority_mask; u16 buffer_size; int backup_pool; } pools[DPNI_MAX_DPBP]; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index bdf94335ee99..9f6c4f5c0a6c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1111,7 +1111,6 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops enetc_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = enetc_pl_mac_select_pcs, .mac_config = enetc_pl_mac_config, .mac_link_up = enetc_pl_mac_link_up, diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 33f84a30e167..5ba1e0d71c68 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -348,7 +348,6 @@ struct bufdesc_ex { */ #define FEC_ENET_XDP_HEADROOM (XDP_PACKET_HEADROOM) - #define FEC_ENET_RX_PAGES 256 #define FEC_ENET_RX_FRSIZE (PAGE_SIZE - FEC_ENET_XDP_HEADROOM \ - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) @@ -527,6 +526,19 @@ struct fec_enet_priv_txrx_info { struct sk_buff *skb; }; +enum { + RX_XDP_REDIRECT = 0, + RX_XDP_PASS, + RX_XDP_DROP, + RX_XDP_TX, + RX_XDP_TX_ERRORS, + TX_XDP_XMIT, + TX_XDP_XMIT_ERRORS, + + /* The following must be the last one */ + XDP_STATS_TOTAL, +}; + struct fec_enet_priv_tx_q { struct bufdesc_prop bd; unsigned char *tx_bounce[TX_RING_SIZE]; @@ -547,6 +559,7 @@ struct fec_enet_priv_rx_q { /* page_pool */ struct page_pool *page_pool; struct xdp_rxq_info xdp_rxq; + u32 stats[XDP_STATS_TOTAL]; /* rx queue number, in the range 0-7 */ u8 id; @@ -658,9 +671,14 @@ struct fec_enet_private { unsigned int reload_period; int pps_enable; unsigned int next_counter; + struct hrtimer perout_timer; + u64 perout_stime; struct imx_sc_ipc *ipc_handle; + /* XDP BPF Program */ + struct bpf_prog *xdp_prog; + u64 ethtool_stats[]; }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 23e1a94b9ce4..5528b0af82ae 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -89,6 +89,11 @@ static const u16 fec_enet_vlan_pri_to_queue[8] = {0, 0, 1, 1, 1, 2, 2, 2}; #define FEC_ENET_OPD_V 0xFFF0 #define FEC_MDIO_PM_TIMEOUT 100 /* ms */ +#define FEC_ENET_XDP_PASS 0 +#define FEC_ENET_XDP_CONSUMED BIT(0) +#define FEC_ENET_XDP_TX BIT(1) +#define FEC_ENET_XDP_REDIR BIT(2) + struct fec_devinfo { u32 quirks; }; @@ -365,16 +370,6 @@ static void swap_buffer(void *bufaddr, int len) swab32s(buf); } -static void swap_buffer2(void *dst_buf, void *src_buf, int len) -{ - int i; - unsigned int *src = src_buf; - unsigned int *dst = dst_buf; - - for (i = 0; i < len; i += 4, src++, dst++) - *dst = swab32p(src); -} - static void fec_dump(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); @@ -428,13 +423,14 @@ static int fec_enet_create_page_pool(struct fec_enet_private *fep, struct fec_enet_priv_rx_q *rxq, int size) { + struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog); struct page_pool_params pp_params = { .order = 0, .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, .pool_size = size, .nid = dev_to_node(&fep->pdev->dev), .dev = &fep->pdev->dev, - .dma_dir = DMA_FROM_DEVICE, + .dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE, .offset = FEC_ENET_XDP_HEADROOM, .max_len = FEC_ENET_RX_FRSIZE, }; @@ -1494,53 +1490,6 @@ static void fec_enet_tx(struct net_device *ndev) fec_enet_tx_queue(ndev, i); } -static int __maybe_unused -fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff *skb) -{ - struct fec_enet_private *fep = netdev_priv(ndev); - int off; - - off = ((unsigned long)skb->data) & fep->rx_align; - if (off) - skb_reserve(skb, fep->rx_align + 1 - off); - - bdp->cbd_bufaddr = cpu_to_fec32(dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE)); - if (dma_mapping_error(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr))) { - if (net_ratelimit()) - netdev_err(ndev, "Rx DMA memory map failed\n"); - return -ENOMEM; - } - - return 0; -} - -static bool __maybe_unused -fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb, - struct bufdesc *bdp, u32 length, bool swap) -{ - struct fec_enet_private *fep = netdev_priv(ndev); - struct sk_buff *new_skb; - - if (length > fep->rx_copybreak) - return false; - - new_skb = netdev_alloc_skb(ndev, length); - if (!new_skb) - return false; - - dma_sync_single_for_cpu(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), - FEC_ENET_RX_FRSIZE - fep->rx_align, - DMA_FROM_DEVICE); - if (!swap) - memcpy(new_skb->data, (*skb)->data, length); - else - swap_buffer2(new_skb->data, (*skb)->data, length); - *skb = new_skb; - - return true; -} - static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, struct bufdesc *bdp, int index) { @@ -1556,6 +1505,62 @@ static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, bdp->cbd_bufaddr = cpu_to_fec32(phys_addr); } +static u32 +fec_enet_run_xdp(struct fec_enet_private *fep, struct bpf_prog *prog, + struct xdp_buff *xdp, struct fec_enet_priv_rx_q *rxq, int index) +{ + unsigned int sync, len = xdp->data_end - xdp->data; + u32 ret = FEC_ENET_XDP_PASS; + struct page *page; + int err; + u32 act; + + act = bpf_prog_run_xdp(prog, xdp); + + /* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */ + sync = xdp->data_end - xdp->data_hard_start - FEC_ENET_XDP_HEADROOM; + sync = max(sync, len); + + switch (act) { + case XDP_PASS: + rxq->stats[RX_XDP_PASS]++; + ret = FEC_ENET_XDP_PASS; + break; + + case XDP_REDIRECT: + rxq->stats[RX_XDP_REDIRECT]++; + err = xdp_do_redirect(fep->netdev, xdp, prog); + if (!err) { + ret = FEC_ENET_XDP_REDIR; + } else { + ret = FEC_ENET_XDP_CONSUMED; + page = virt_to_head_page(xdp->data); + page_pool_put_page(rxq->page_pool, page, sync, true); + } + break; + + default: + bpf_warn_invalid_xdp_action(fep->netdev, prog, act); + fallthrough; + + case XDP_TX: + bpf_warn_invalid_xdp_action(fep->netdev, prog, act); + fallthrough; + + case XDP_ABORTED: + fallthrough; /* handle aborts by dropping packet */ + + case XDP_DROP: + rxq->stats[RX_XDP_DROP]++; + ret = FEC_ENET_XDP_CONSUMED; + page = virt_to_head_page(xdp->data); + page_pool_put_page(rxq->page_pool, page, sync, true); + break; + } + + return ret; +} + /* During a receive, the bd_rx.cur points to the current incoming buffer. * When we update through the ring, if the next incoming buffer has * not been given to the system, we just set the empty indicator, @@ -1577,7 +1582,22 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) u16 vlan_tag; int index = 0; bool need_swap = fep->quirks & FEC_QUIRK_SWAP_FRAME; + struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog); + u32 ret, xdp_result = FEC_ENET_XDP_PASS; + u32 data_start = FEC_ENET_XDP_HEADROOM; + struct xdp_buff xdp; struct page *page; + u32 sub_len = 4; + +#if !defined(CONFIG_M5272) + /*If it has the FEC_QUIRK_HAS_RACC quirk property, the bit of + * FEC_RACC_SHIFT16 is set by default in the probe function. + */ + if (fep->quirks & FEC_QUIRK_HAS_RACC) { + data_start += 2; + sub_len += 2; + } +#endif #ifdef CONFIG_M532x flush_cache_all(); @@ -1588,6 +1608,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) * These get messed up if we get called due to a busy condition. */ bdp = rxq->bd.cur; + xdp_init_buff(&xdp, PAGE_SIZE, &rxq->xdp_rxq); while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) { @@ -1637,23 +1658,31 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) prefetch(page_address(page)); fec_enet_update_cbd(rxq, bdp, index); + if (xdp_prog) { + xdp_buff_clear_frags_flag(&xdp); + /* subtract 16bit shift and FCS */ + xdp_prepare_buff(&xdp, page_address(page), + data_start, pkt_len - sub_len, false); + ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, index); + xdp_result |= ret; + if (ret != FEC_ENET_XDP_PASS) + goto rx_processing_done; + } + /* The packet length includes FCS, but we don't want to * include that when passing upstream as it messes up * bridging applications. */ skb = build_skb(page_address(page), PAGE_SIZE); - skb_reserve(skb, FEC_ENET_XDP_HEADROOM); - skb_put(skb, pkt_len - 4); + skb_reserve(skb, data_start); + skb_put(skb, pkt_len - sub_len); skb_mark_for_recycle(skb); - data = skb->data; - if (need_swap) + if (unlikely(need_swap)) { + data = page_address(page) + FEC_ENET_XDP_HEADROOM; swap_buffer(data, pkt_len); - -#if !defined(CONFIG_M5272) - if (fep->quirks & FEC_QUIRK_HAS_RACC) - data = skb_pull_inline(skb, 2); -#endif + } + data = skb->data; /* Extract the enhanced buffer descriptor */ ebdp = NULL; @@ -1732,6 +1761,10 @@ rx_processing_done: writel(0, rxq->bd.reg_desc_active); } rxq->bd.cur = bdp; + + if (xdp_result & FEC_ENET_XDP_REDIR) + xdp_do_flush_map(); + return pkt_received; } @@ -2226,7 +2259,7 @@ static int fec_enet_mii_probe(struct net_device *ndev) fep->link = 0; fep->full_duplex = 0; - phy_dev->mac_managed_pm = 1; + phy_dev->mac_managed_pm = true; phy_attached_info(phy_dev); @@ -2671,6 +2704,16 @@ static const struct fec_stat { #define FEC_STATS_SIZE (ARRAY_SIZE(fec_stats) * sizeof(u64)) +static const char *fec_xdp_stat_strs[XDP_STATS_TOTAL] = { + "rx_xdp_redirect", /* RX_XDP_REDIRECT = 0, */ + "rx_xdp_pass", /* RX_XDP_PASS, */ + "rx_xdp_drop", /* RX_XDP_DROP, */ + "rx_xdp_tx", /* RX_XDP_TX, */ + "rx_xdp_tx_errors", /* RX_XDP_TX_ERRORS, */ + "tx_xdp_xmit", /* TX_XDP_XMIT, */ + "tx_xdp_xmit_errors", /* TX_XDP_XMIT_ERRORS, */ +}; + static void fec_enet_update_ethtool_stats(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); @@ -2680,6 +2723,40 @@ static void fec_enet_update_ethtool_stats(struct net_device *dev) fep->ethtool_stats[i] = readl(fep->hwp + fec_stats[i].offset); } +static void fec_enet_get_xdp_stats(struct fec_enet_private *fep, u64 *data) +{ + u64 xdp_stats[XDP_STATS_TOTAL] = { 0 }; + struct fec_enet_priv_rx_q *rxq; + int i, j; + + for (i = fep->num_rx_queues - 1; i >= 0; i--) { + rxq = fep->rx_queue[i]; + + for (j = 0; j < XDP_STATS_TOTAL; j++) + xdp_stats[j] += rxq->stats[j]; + } + + memcpy(data, xdp_stats, sizeof(xdp_stats)); +} + +static void fec_enet_page_pool_stats(struct fec_enet_private *fep, u64 *data) +{ + struct page_pool_stats stats = {}; + struct fec_enet_priv_rx_q *rxq; + int i; + + for (i = fep->num_rx_queues - 1; i >= 0; i--) { + rxq = fep->rx_queue[i]; + + if (!rxq->page_pool) + continue; + + page_pool_get_stats(rxq->page_pool, &stats); + } + + page_pool_ethtool_stats_get(data, &stats); +} + static void fec_enet_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { @@ -2689,6 +2766,12 @@ static void fec_enet_get_ethtool_stats(struct net_device *dev, fec_enet_update_ethtool_stats(dev); memcpy(data, fep->ethtool_stats, FEC_STATS_SIZE); + data += FEC_STATS_SIZE / sizeof(u64); + + fec_enet_get_xdp_stats(fep, data); + data += XDP_STATS_TOTAL; + + fec_enet_page_pool_stats(fep, data); } static void fec_enet_get_strings(struct net_device *netdev, @@ -2697,9 +2780,16 @@ static void fec_enet_get_strings(struct net_device *netdev, int i; switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(fec_stats); i++) - memcpy(data + i * ETH_GSTRING_LEN, - fec_stats[i].name, ETH_GSTRING_LEN); + for (i = 0; i < ARRAY_SIZE(fec_stats); i++) { + memcpy(data, fec_stats[i].name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + for (i = 0; i < ARRAY_SIZE(fec_xdp_stat_strs); i++) { + strncpy(data, fec_xdp_stat_strs[i], ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + page_pool_ethtool_stats_get_strings(data); + break; case ETH_SS_TEST: net_selftest_get_strings(data); @@ -2709,9 +2799,14 @@ static void fec_enet_get_strings(struct net_device *netdev, static int fec_enet_get_sset_count(struct net_device *dev, int sset) { + int count; + switch (sset) { case ETH_SS_STATS: - return ARRAY_SIZE(fec_stats); + count = ARRAY_SIZE(fec_stats) + XDP_STATS_TOTAL; + count += page_pool_ethtool_stats_get_count(); + return count; + case ETH_SS_TEST: return net_selftest_get_count(); default: @@ -2722,7 +2817,8 @@ static int fec_enet_get_sset_count(struct net_device *dev, int sset) static void fec_enet_clear_ethtool_stats(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); - int i; + struct fec_enet_priv_rx_q *rxq; + int i, j; /* Disable MIB statistics counters */ writel(FEC_MIB_CTRLSTAT_DISABLE, fep->hwp + FEC_MIB_CTRLSTAT); @@ -2730,6 +2826,12 @@ static void fec_enet_clear_ethtool_stats(struct net_device *dev) for (i = 0; i < ARRAY_SIZE(fec_stats); i++) writel(0, fep->hwp + fec_stats[i].offset); + for (i = fep->num_rx_queues - 1; i >= 0; i--) { + rxq = fep->rx_queue[i]; + for (j = 0; j < XDP_STATS_TOTAL; j++) + rxq->stats[j] = 0; + } + /* Don't disable MIB statistics counters */ writel(0, fep->hwp + FEC_MIB_CTRLSTAT); } @@ -3083,6 +3185,9 @@ static void fec_enet_free_buffers(struct net_device *ndev) for (i = 0; i < rxq->bd.ring_size; i++) page_pool_release_page(rxq->page_pool, rxq->rx_skb_info[i].page); + for (i = 0; i < XDP_STATS_TOTAL; i++) + rxq->stats[i] = 0; + if (xdp_rxq_info_is_reg(&rxq->xdp_rxq)) xdp_rxq_info_unreg(&rxq->xdp_rxq); page_pool_destroy(rxq->page_pool); @@ -3562,6 +3667,150 @@ static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb, return fec_enet_vlan_pri_to_queue[vlan_tag >> 13]; } +static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf) +{ + struct fec_enet_private *fep = netdev_priv(dev); + bool is_run = netif_running(dev); + struct bpf_prog *old_prog; + + switch (bpf->command) { + case XDP_SETUP_PROG: + /* No need to support the SoCs that require to + * do the frame swap because the performance wouldn't be + * better than the skb mode. + */ + if (fep->quirks & FEC_QUIRK_SWAP_FRAME) + return -EOPNOTSUPP; + + if (is_run) { + napi_disable(&fep->napi); + netif_tx_disable(dev); + } + + old_prog = xchg(&fep->xdp_prog, bpf->prog); + fec_restart(dev); + + if (is_run) { + napi_enable(&fep->napi); + netif_tx_start_all_queues(dev); + } + + if (old_prog) + bpf_prog_put(old_prog); + + return 0; + + case XDP_SETUP_XSK_POOL: + return -EOPNOTSUPP; + + default: + return -EOPNOTSUPP; + } +} + +static int +fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int index) +{ + if (unlikely(index < 0)) + return 0; + + return (index % fep->num_tx_queues); +} + +static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, + struct fec_enet_priv_tx_q *txq, + struct xdp_frame *frame) +{ + unsigned int index, status, estatus; + struct bufdesc *bdp, *last_bdp; + dma_addr_t dma_addr; + int entries_free; + + entries_free = fec_enet_get_free_txdesc_num(txq); + if (entries_free < MAX_SKB_FRAGS + 1) { + netdev_err(fep->netdev, "NOT enough BD for SG!\n"); + return NETDEV_TX_OK; + } + + /* Fill in a Tx ring entry */ + bdp = txq->bd.cur; + last_bdp = bdp; + status = fec16_to_cpu(bdp->cbd_sc); + status &= ~BD_ENET_TX_STATS; + + index = fec_enet_get_bd_index(bdp, &txq->bd); + + dma_addr = dma_map_single(&fep->pdev->dev, frame->data, + frame->len, DMA_TO_DEVICE); + if (dma_mapping_error(&fep->pdev->dev, dma_addr)) + return FEC_ENET_XDP_CONSUMED; + + status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST); + if (fep->bufdesc_ex) + estatus = BD_ENET_TX_INT; + + bdp->cbd_bufaddr = cpu_to_fec32(dma_addr); + bdp->cbd_datlen = cpu_to_fec16(frame->len); + + if (fep->bufdesc_ex) { + struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; + + if (fep->quirks & FEC_QUIRK_HAS_AVB) + estatus |= FEC_TX_BD_FTYPE(txq->bd.qid); + + ebdp->cbd_bdu = 0; + ebdp->cbd_esc = cpu_to_fec32(estatus); + } + + index = fec_enet_get_bd_index(last_bdp, &txq->bd); + txq->tx_skbuff[index] = NULL; + + /* Send it on its way. Tell FEC it's ready, interrupt when done, + * it's the last BD of the frame, and to put the CRC on the end. + */ + status |= (BD_ENET_TX_READY | BD_ENET_TX_TC); + bdp->cbd_sc = cpu_to_fec16(status); + + /* If this was the last BD in the ring, start at the beginning again. */ + bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd); + + txq->bd.cur = bdp; + + return 0; +} + +static int fec_enet_xdp_xmit(struct net_device *dev, + int num_frames, + struct xdp_frame **frames, + u32 flags) +{ + struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_priv_tx_q *txq; + int cpu = smp_processor_id(); + struct netdev_queue *nq; + unsigned int queue; + int i; + + queue = fec_enet_xdp_get_tx_queue(fep, cpu); + txq = fep->tx_queue[queue]; + nq = netdev_get_tx_queue(fep->netdev, queue); + + __netif_tx_lock(nq, cpu); + + for (i = 0; i < num_frames; i++) + fec_enet_txq_xmit_frame(fep, txq, frames[i]); + + /* Make sure the update to bdp and tx_skbuff are performed. */ + wmb(); + + /* Trigger transmission start */ + writel(0, txq->bd.reg_desc_active); + + __netif_tx_unlock(nq); + + return num_frames; +} + static const struct net_device_ops fec_netdev_ops = { .ndo_open = fec_enet_open, .ndo_stop = fec_enet_close, @@ -3576,6 +3825,8 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_poll_controller = fec_poll_controller, #endif .ndo_set_features = fec_set_features, + .ndo_bpf = fec_enet_bpf, + .ndo_xdp_xmit = fec_enet_xdp_xmit, }; static const unsigned short offset_des_active_rxq[] = { diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index cffd9ad499dd..ab86bb8562ef 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -88,6 +88,9 @@ #define FEC_CHANNLE_0 0 #define DEFAULT_PPS_CHANNEL FEC_CHANNLE_0 +#define FEC_PTP_MAX_NSEC_PERIOD 4000000000ULL +#define FEC_PTP_MAX_NSEC_COUNTER 0x80000000ULL + /** * fec_ptp_enable_pps * @fep: the fec_enet_private structure handle @@ -198,6 +201,78 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) return 0; } +static int fec_ptp_pps_perout(struct fec_enet_private *fep) +{ + u32 compare_val, ptp_hc, temp_val; + u64 curr_time; + unsigned long flags; + + spin_lock_irqsave(&fep->tmreg_lock, flags); + + /* Update time counter */ + timecounter_read(&fep->tc); + + /* Get the current ptp hardware time counter */ + temp_val = readl(fep->hwp + FEC_ATIME_CTRL); + temp_val |= FEC_T_CTRL_CAPTURE; + writel(temp_val, fep->hwp + FEC_ATIME_CTRL); + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) + udelay(1); + + ptp_hc = readl(fep->hwp + FEC_ATIME); + + /* Convert the ptp local counter to 1588 timestamp */ + curr_time = timecounter_cyc2time(&fep->tc, ptp_hc); + + /* If the pps start time less than current time add 100ms, just return. + * Because the software might not able to set the comparison time into + * the FEC_TCCR register in time and missed the start time. + */ + if (fep->perout_stime < curr_time + 100 * NSEC_PER_MSEC) { + dev_err(&fep->pdev->dev, "Current time is too close to the start time!\n"); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + return -1; + } + + compare_val = fep->perout_stime - curr_time + ptp_hc; + compare_val &= fep->cc.mask; + + writel(compare_val, fep->hwp + FEC_TCCR(fep->pps_channel)); + fep->next_counter = (compare_val + fep->reload_period) & fep->cc.mask; + + /* Enable compare event when overflow */ + temp_val = readl(fep->hwp + FEC_ATIME_CTRL); + temp_val |= FEC_T_CTRL_PINPER; + writel(temp_val, fep->hwp + FEC_ATIME_CTRL); + + /* Compare channel setting. */ + temp_val = readl(fep->hwp + FEC_TCSR(fep->pps_channel)); + temp_val |= (1 << FEC_T_TF_OFFSET | 1 << FEC_T_TIE_OFFSET); + temp_val &= ~(1 << FEC_T_TDRE_OFFSET); + temp_val &= ~(FEC_T_TMODE_MASK); + temp_val |= (FEC_TMODE_TOGGLE << FEC_T_TMODE_OFFSET); + writel(temp_val, fep->hwp + FEC_TCSR(fep->pps_channel)); + + /* Write the second compare event timestamp and calculate + * the third timestamp. Refer the TCCR register detail in the spec. + */ + writel(fep->next_counter, fep->hwp + FEC_TCCR(fep->pps_channel)); + fep->next_counter = (fep->next_counter + fep->reload_period) & fep->cc.mask; + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + + return 0; +} + +static enum hrtimer_restart fec_ptp_pps_perout_handler(struct hrtimer *timer) +{ + struct fec_enet_private *fep = container_of(timer, + struct fec_enet_private, perout_timer); + + fec_ptp_pps_perout(fep); + + return HRTIMER_NORESTART; +} + /** * fec_ptp_read - read raw cycle counter (to be used by time counter) * @cc: the cyclecounter structure @@ -263,18 +338,21 @@ void fec_ptp_start_cyclecounter(struct net_device *ndev) } /** - * fec_ptp_adjfreq - adjust ptp cycle frequency + * fec_ptp_adjfine - adjust ptp cycle frequency * @ptp: the ptp clock structure - * @ppb: parts per billion adjustment from base + * @scaled_ppm: scaled parts per million adjustment from base * * Adjust the frequency of the ptp cycle counter by the - * indicated ppb from the base frequency. + * indicated amount from the base frequency. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. * * Because ENET hardware frequency adjust is complex, * using software method to do that. */ -static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int fec_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); unsigned long flags; int neg_adj = 0; u32 i, tmp; @@ -425,6 +503,17 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, return 0; } +static int fec_ptp_pps_disable(struct fec_enet_private *fep, uint channel) +{ + unsigned long flags; + + spin_lock_irqsave(&fep->tmreg_lock, flags); + writel(0, fep->hwp + FEC_TCSR(channel)); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + + return 0; +} + /** * fec_ptp_enable * @ptp: the ptp clock structure @@ -437,14 +526,84 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, { struct fec_enet_private *fep = container_of(ptp, struct fec_enet_private, ptp_caps); + ktime_t timeout; + struct timespec64 start_time, period; + u64 curr_time, delta, period_ns; + unsigned long flags; int ret = 0; if (rq->type == PTP_CLK_REQ_PPS) { ret = fec_ptp_enable_pps(fep, on); return ret; + } else if (rq->type == PTP_CLK_REQ_PEROUT) { + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + + if (rq->perout.index != DEFAULT_PPS_CHANNEL) + return -EOPNOTSUPP; + + fep->pps_channel = DEFAULT_PPS_CHANNEL; + period.tv_sec = rq->perout.period.sec; + period.tv_nsec = rq->perout.period.nsec; + period_ns = timespec64_to_ns(&period); + + /* FEC PTP timer only has 31 bits, so if the period exceed + * 4s is not supported. + */ + if (period_ns > FEC_PTP_MAX_NSEC_PERIOD) { + dev_err(&fep->pdev->dev, "The period must equal to or less than 4s!\n"); + return -EOPNOTSUPP; + } + + fep->reload_period = div_u64(period_ns, 2); + if (on && fep->reload_period) { + /* Convert 1588 timestamp to ns*/ + start_time.tv_sec = rq->perout.start.sec; + start_time.tv_nsec = rq->perout.start.nsec; + fep->perout_stime = timespec64_to_ns(&start_time); + + mutex_lock(&fep->ptp_clk_mutex); + if (!fep->ptp_clk_on) { + dev_err(&fep->pdev->dev, "Error: PTP clock is closed!\n"); + mutex_unlock(&fep->ptp_clk_mutex); + return -EOPNOTSUPP; + } + spin_lock_irqsave(&fep->tmreg_lock, flags); + /* Read current timestamp */ + curr_time = timecounter_read(&fep->tc); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); + + /* Calculate time difference */ + delta = fep->perout_stime - curr_time; + + if (fep->perout_stime <= curr_time) { + dev_err(&fep->pdev->dev, "Start time must larger than current time!\n"); + return -EINVAL; + } + + /* Because the timer counter of FEC only has 31-bits, correspondingly, + * the time comparison register FEC_TCCR also only low 31 bits can be + * set. If the start time of pps signal exceeds current time more than + * 0x80000000 ns, a software timer is used and the timer expires about + * 1 second before the start time to be able to set FEC_TCCR. + */ + if (delta > FEC_PTP_MAX_NSEC_COUNTER) { + timeout = ns_to_ktime(delta - NSEC_PER_SEC); + hrtimer_start(&fep->perout_timer, timeout, HRTIMER_MODE_REL); + } else { + return fec_ptp_pps_perout(fep); + } + } else { + fec_ptp_pps_disable(fep, fep->pps_channel); + } + + return 0; + } else { + return -EOPNOTSUPP; } - return -EOPNOTSUPP; } /** @@ -583,10 +742,10 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) fep->ptp_caps.max_adj = 250000000; fep->ptp_caps.n_alarm = 0; fep->ptp_caps.n_ext_ts = 0; - fep->ptp_caps.n_per_out = 0; + fep->ptp_caps.n_per_out = 1; fep->ptp_caps.n_pins = 0; fep->ptp_caps.pps = 1; - fep->ptp_caps.adjfreq = fec_ptp_adjfreq; + fep->ptp_caps.adjfine = fec_ptp_adjfine; fep->ptp_caps.adjtime = fec_ptp_adjtime; fep->ptp_caps.gettime64 = fec_ptp_gettime; fep->ptp_caps.settime64 = fec_ptp_settime; @@ -605,6 +764,9 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep); + hrtimer_init(&fep->perout_timer, CLOCK_REALTIME, HRTIMER_MODE_REL); + fep->perout_timer.function = fec_ptp_pps_perout_handler; + irq = platform_get_irq_byname_optional(pdev, "pps"); if (irq < 0) irq = platform_get_irq_optional(pdev, irq_idx); @@ -634,6 +796,7 @@ void fec_ptp_stop(struct platform_device *pdev) struct fec_enet_private *fep = netdev_priv(ndev); cancel_delayed_work_sync(&fep->time_keep); + hrtimer_cancel(&fep->perout_timer); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); } diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index 48bf8088795d..a55542c1ad65 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -3,7 +3,8 @@ config FSL_FMAN tristate "FMan support" depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST select GENERIC_ALLOCATOR - select PHYLIB + select PHYLINK + select PCS_LYNX select CRC32 default n help diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 6617932fd3fd..d00bae15a901 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -17,6 +17,7 @@ #include <linux/crc32.h> #include <linux/of_mdio.h> #include <linux/mii.h> +#include <linux/netdevice.h> /* TBI register addresses */ #define MII_TBICON 0x11 @@ -29,9 +30,6 @@ #define TBICON_CLK_SELECT 0x0020 /* Clock select */ #define TBICON_MI_MODE 0x0010 /* GMII mode (TBI if not set) */ -#define TBIANA_SGMII 0x4001 -#define TBIANA_1000X 0x01a0 - /* Interrupt Mask Register (IMASK) */ #define DTSEC_IMASK_BREN 0x80000000 #define DTSEC_IMASK_RXCEN 0x40000000 @@ -92,9 +90,10 @@ #define DTSEC_ECNTRL_GMIIM 0x00000040 #define DTSEC_ECNTRL_TBIM 0x00000020 -#define DTSEC_ECNTRL_SGMIIM 0x00000002 #define DTSEC_ECNTRL_RPM 0x00000010 #define DTSEC_ECNTRL_R100M 0x00000008 +#define DTSEC_ECNTRL_RMM 0x00000004 +#define DTSEC_ECNTRL_SGMIIM 0x00000002 #define DTSEC_ECNTRL_QSGMIIM 0x00000001 #define TCTRL_TTSE 0x00000040 @@ -318,7 +317,8 @@ struct fman_mac { void *fm; struct fman_rev_info fm_rev_info; bool basex_if; - struct phy_device *tbiphy; + struct mdio_device *tbidev; + struct phylink_pcs pcs; }; static void set_dflts(struct dtsec_cfg *cfg) @@ -356,56 +356,14 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, phy_interface_t iface, u16 iface_speed, u64 addr, u32 exception_mask, u8 tbi_addr) { - bool is_rgmii, is_sgmii, is_qsgmii; enet_addr_t eth_addr; - u32 tmp; + u32 tmp = 0; int i; /* Soft reset */ iowrite32be(MACCFG1_SOFT_RESET, ®s->maccfg1); iowrite32be(0, ®s->maccfg1); - /* dtsec_id2 */ - tmp = ioread32be(®s->tsec_id2); - - /* check RGMII support */ - if (iface == PHY_INTERFACE_MODE_RGMII || - iface == PHY_INTERFACE_MODE_RGMII_ID || - iface == PHY_INTERFACE_MODE_RGMII_RXID || - iface == PHY_INTERFACE_MODE_RGMII_TXID || - iface == PHY_INTERFACE_MODE_RMII) - if (tmp & DTSEC_ID2_INT_REDUCED_OFF) - return -EINVAL; - - if (iface == PHY_INTERFACE_MODE_SGMII || - iface == PHY_INTERFACE_MODE_MII) - if (tmp & DTSEC_ID2_INT_REDUCED_OFF) - return -EINVAL; - - is_rgmii = iface == PHY_INTERFACE_MODE_RGMII || - iface == PHY_INTERFACE_MODE_RGMII_ID || - iface == PHY_INTERFACE_MODE_RGMII_RXID || - iface == PHY_INTERFACE_MODE_RGMII_TXID; - is_sgmii = iface == PHY_INTERFACE_MODE_SGMII; - is_qsgmii = iface == PHY_INTERFACE_MODE_QSGMII; - - tmp = 0; - if (is_rgmii || iface == PHY_INTERFACE_MODE_GMII) - tmp |= DTSEC_ECNTRL_GMIIM; - if (is_sgmii) - tmp |= (DTSEC_ECNTRL_SGMIIM | DTSEC_ECNTRL_TBIM); - if (is_qsgmii) - tmp |= (DTSEC_ECNTRL_SGMIIM | DTSEC_ECNTRL_TBIM | - DTSEC_ECNTRL_QSGMIIM); - if (is_rgmii) - tmp |= DTSEC_ECNTRL_RPM; - if (iface_speed == SPEED_100) - tmp |= DTSEC_ECNTRL_R100M; - - iowrite32be(tmp, ®s->ecntrl); - - tmp = 0; - if (cfg->tx_pause_time) tmp |= cfg->tx_pause_time; if (cfg->tx_pause_time_extd) @@ -446,17 +404,10 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, tmp = 0; - if (iface_speed < SPEED_1000) - tmp |= MACCFG2_NIBBLE_MODE; - else if (iface_speed == SPEED_1000) - tmp |= MACCFG2_BYTE_MODE; - tmp |= (cfg->preamble_len << MACCFG2_PREAMBLE_LENGTH_SHIFT) & MACCFG2_PREAMBLE_LENGTH_MASK; if (cfg->tx_pad_crc) tmp |= MACCFG2_PAD_CRC_EN; - /* Full Duplex */ - tmp |= MACCFG2_FULL_DUPLEX; iowrite32be(tmp, ®s->maccfg2); tmp = (((cfg->non_back_to_back_ipg1 << @@ -525,10 +476,6 @@ static void set_bucket(struct dtsec_regs __iomem *regs, int bucket, static int check_init_parameters(struct fman_mac *dtsec) { - if (dtsec->max_speed >= SPEED_10000) { - pr_err("1G MAC driver supports 1G or lower speeds\n"); - return -EINVAL; - } if ((dtsec->dtsec_drv_param)->rx_prepend > MAX_PACKET_ALIGNMENT) { pr_err("packetAlignmentPadding can't be > than %d\n", @@ -630,22 +577,10 @@ static int get_exception_flag(enum fman_mac_exceptions exception) return bit_mask; } -static bool is_init_done(struct dtsec_cfg *dtsec_drv_params) -{ - /* Checks if dTSEC driver parameters were initialized */ - if (!dtsec_drv_params) - return true; - - return false; -} - static u16 dtsec_get_max_frame_length(struct fman_mac *dtsec) { struct dtsec_regs __iomem *regs = dtsec->regs; - if (is_init_done(dtsec->dtsec_drv_param)) - return 0; - return (u16)ioread32be(®s->maxfrm); } @@ -682,6 +617,7 @@ static void dtsec_isr(void *handle) dtsec->exception_cb(dtsec->dev_id, FM_MAC_EX_1G_COL_RET_LMT); if (event & DTSEC_IMASK_XFUNEN) { /* FM_TX_LOCKUP_ERRATA_DTSEC6 Errata workaround */ + /* FIXME: This races with the rest of the driver! */ if (dtsec->fm_rev_info.major == 2) { u32 tpkt1, tmp_reg1, tpkt2, tmp_reg2, i; /* a. Write 0x00E0_0C00 to DTSEC_ID @@ -814,6 +750,43 @@ static void free_init_resources(struct fman_mac *dtsec) dtsec->unicast_addr_hash = NULL; } +static struct fman_mac *pcs_to_dtsec(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct fman_mac, pcs); +} + +static void dtsec_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct fman_mac *dtsec = pcs_to_dtsec(pcs); + + phylink_mii_c22_pcs_get_state(dtsec->tbidev, state); +} + +static int dtsec_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct fman_mac *dtsec = pcs_to_dtsec(pcs); + + return phylink_mii_c22_pcs_config(dtsec->tbidev, mode, interface, + advertising); +} + +static void dtsec_pcs_an_restart(struct phylink_pcs *pcs) +{ + struct fman_mac *dtsec = pcs_to_dtsec(pcs); + + phylink_mii_c22_pcs_an_restart(dtsec->tbidev); +} + +static const struct phylink_pcs_ops dtsec_pcs_ops = { + .pcs_get_state = dtsec_pcs_get_state, + .pcs_config = dtsec_pcs_config, + .pcs_an_restart = dtsec_pcs_an_restart, +}; + static void graceful_start(struct fman_mac *dtsec) { struct dtsec_regs __iomem *regs = dtsec->regs; @@ -854,36 +827,11 @@ static void graceful_stop(struct fman_mac *dtsec) static int dtsec_enable(struct fman_mac *dtsec) { - struct dtsec_regs __iomem *regs = dtsec->regs; - u32 tmp; - - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - - /* Enable */ - tmp = ioread32be(®s->maccfg1); - tmp |= MACCFG1_RX_EN | MACCFG1_TX_EN; - iowrite32be(tmp, ®s->maccfg1); - - /* Graceful start - clear the graceful Rx/Tx stop bit */ - graceful_start(dtsec); - return 0; } static void dtsec_disable(struct fman_mac *dtsec) { - struct dtsec_regs __iomem *regs = dtsec->regs; - u32 tmp; - - WARN_ON_ONCE(!is_init_done(dtsec->dtsec_drv_param)); - - /* Graceful stop - Assert the graceful Rx/Tx stop bit */ - graceful_stop(dtsec); - - tmp = ioread32be(®s->maccfg1); - tmp &= ~(MACCFG1_RX_EN | MACCFG1_TX_EN); - iowrite32be(tmp, ®s->maccfg1); } static int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, @@ -894,11 +842,6 @@ static int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, struct dtsec_regs __iomem *regs = dtsec->regs; u32 ptv = 0; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - - graceful_stop(dtsec); - if (pause_time) { /* FM_BAD_TX_TS_IN_B_2_B_ERRATA_DTSEC_A003 Errata workaround */ if (dtsec->fm_rev_info.major == 2 && pause_time <= 320) { @@ -919,8 +862,6 @@ static int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, iowrite32be(ioread32be(®s->maccfg1) & ~MACCFG1_TX_FLOW, ®s->maccfg1); - graceful_start(dtsec); - return 0; } @@ -929,11 +870,6 @@ static int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) struct dtsec_regs __iomem *regs = dtsec->regs; u32 tmp; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - - graceful_stop(dtsec); - tmp = ioread32be(®s->maccfg1); if (en) tmp |= MACCFG1_RX_FLOW; @@ -941,17 +877,124 @@ static int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) tmp &= ~MACCFG1_RX_FLOW; iowrite32be(tmp, ®s->maccfg1); + return 0; +} + +static struct phylink_pcs *dtsec_select_pcs(struct phylink_config *config, + phy_interface_t iface) +{ + struct fman_mac *dtsec = fman_config_to_mac(config)->fman_mac; + + switch (iface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + return &dtsec->pcs; + default: + return NULL; + } +} + +static void dtsec_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct mac_device *mac_dev = fman_config_to_mac(config); + struct dtsec_regs __iomem *regs = mac_dev->fman_mac->regs; + u32 tmp; + + switch (state->interface) { + case PHY_INTERFACE_MODE_RMII: + tmp = DTSEC_ECNTRL_RMM; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + tmp = DTSEC_ECNTRL_GMIIM | DTSEC_ECNTRL_RPM; + break; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + tmp = DTSEC_ECNTRL_TBIM | DTSEC_ECNTRL_SGMIIM; + break; + default: + dev_warn(mac_dev->dev, "cannot configure dTSEC for %s\n", + phy_modes(state->interface)); + return; + } + + iowrite32be(tmp, ®s->ecntrl); +} + +static void dtsec_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) +{ + struct mac_device *mac_dev = fman_config_to_mac(config); + struct fman_mac *dtsec = mac_dev->fman_mac; + struct dtsec_regs __iomem *regs = dtsec->regs; + u16 pause_time = tx_pause ? FSL_FM_PAUSE_TIME_ENABLE : + FSL_FM_PAUSE_TIME_DISABLE; + u32 tmp; + + dtsec_set_tx_pause_frames(dtsec, 0, pause_time, 0); + dtsec_accept_rx_pause_frames(dtsec, rx_pause); + + tmp = ioread32be(®s->ecntrl); + if (speed == SPEED_100) + tmp |= DTSEC_ECNTRL_R100M; + else + tmp &= ~DTSEC_ECNTRL_R100M; + iowrite32be(tmp, ®s->ecntrl); + + tmp = ioread32be(®s->maccfg2); + tmp &= ~(MACCFG2_NIBBLE_MODE | MACCFG2_BYTE_MODE | MACCFG2_FULL_DUPLEX); + if (speed >= SPEED_1000) + tmp |= MACCFG2_BYTE_MODE; + else + tmp |= MACCFG2_NIBBLE_MODE; + + if (duplex == DUPLEX_FULL) + tmp |= MACCFG2_FULL_DUPLEX; + + iowrite32be(tmp, ®s->maccfg2); + + mac_dev->update_speed(mac_dev, speed); + + /* Enable */ + tmp = ioread32be(®s->maccfg1); + tmp |= MACCFG1_RX_EN | MACCFG1_TX_EN; + iowrite32be(tmp, ®s->maccfg1); + + /* Graceful start - clear the graceful Rx/Tx stop bit */ graceful_start(dtsec); +} - return 0; +static void dtsec_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct fman_mac *dtsec = fman_config_to_mac(config)->fman_mac; + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + /* Graceful stop - Assert the graceful Rx/Tx stop bit */ + graceful_stop(dtsec); + + tmp = ioread32be(®s->maccfg1); + tmp &= ~(MACCFG1_RX_EN | MACCFG1_TX_EN); + iowrite32be(tmp, ®s->maccfg1); } +static const struct phylink_mac_ops dtsec_mac_ops = { + .mac_select_pcs = dtsec_select_pcs, + .mac_config = dtsec_mac_config, + .mac_link_up = dtsec_link_up, + .mac_link_down = dtsec_link_down, +}; + static int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr) { - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - graceful_stop(dtsec); /* Initialize MAC Station Address registers (1 & 2) @@ -975,9 +1018,6 @@ static int dtsec_add_hash_mac_address(struct fman_mac *dtsec, u32 crc = 0xFFFFFFFF; bool mcast, ghtx; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - addr = ENET_ADDR_TO_UINT64(*eth_addr); ghtx = (bool)((ioread32be(®s->rctrl) & RCTRL_GHTX) ? true : false); @@ -1037,9 +1077,6 @@ static int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable) u32 tmp; struct dtsec_regs __iomem *regs = dtsec->regs; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - tmp = ioread32be(®s->rctrl); if (enable) tmp |= RCTRL_MPROM; @@ -1056,9 +1093,6 @@ static int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable) struct dtsec_regs __iomem *regs = dtsec->regs; u32 rctrl, tctrl; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - rctrl = ioread32be(®s->rctrl); tctrl = ioread32be(®s->tctrl); @@ -1087,9 +1121,6 @@ static int dtsec_del_hash_mac_address(struct fman_mac *dtsec, u32 crc = 0xFFFFFFFF; bool mcast, ghtx; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - addr = ENET_ADDR_TO_UINT64(*eth_addr); ghtx = (bool)((ioread32be(®s->rctrl) & RCTRL_GHTX) ? true : false); @@ -1153,9 +1184,6 @@ static int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val) struct dtsec_regs __iomem *regs = dtsec->regs; u32 tmp; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - /* Set unicast promiscuous */ tmp = ioread32be(®s->rctrl); if (new_val) @@ -1177,90 +1205,12 @@ static int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val) return 0; } -static int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed) -{ - struct dtsec_regs __iomem *regs = dtsec->regs; - u32 tmp; - - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - - graceful_stop(dtsec); - - tmp = ioread32be(®s->maccfg2); - - /* Full Duplex */ - tmp |= MACCFG2_FULL_DUPLEX; - - tmp &= ~(MACCFG2_NIBBLE_MODE | MACCFG2_BYTE_MODE); - if (speed < SPEED_1000) - tmp |= MACCFG2_NIBBLE_MODE; - else if (speed == SPEED_1000) - tmp |= MACCFG2_BYTE_MODE; - iowrite32be(tmp, ®s->maccfg2); - - tmp = ioread32be(®s->ecntrl); - if (speed == SPEED_100) - tmp |= DTSEC_ECNTRL_R100M; - else - tmp &= ~DTSEC_ECNTRL_R100M; - iowrite32be(tmp, ®s->ecntrl); - - graceful_start(dtsec); - - return 0; -} - -static int dtsec_restart_autoneg(struct fman_mac *dtsec) -{ - u16 tmp_reg16; - - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - - tmp_reg16 = phy_read(dtsec->tbiphy, MII_BMCR); - - tmp_reg16 &= ~(BMCR_SPEED100 | BMCR_SPEED1000); - tmp_reg16 |= (BMCR_ANENABLE | BMCR_ANRESTART | - BMCR_FULLDPLX | BMCR_SPEED1000); - - phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); - - return 0; -} - -static void adjust_link_dtsec(struct mac_device *mac_dev) -{ - struct phy_device *phy_dev = mac_dev->phy_dev; - struct fman_mac *fman_mac; - bool rx_pause, tx_pause; - int err; - - fman_mac = mac_dev->fman_mac; - if (!phy_dev->link) { - dtsec_restart_autoneg(fman_mac); - - return; - } - - dtsec_adjust_link(fman_mac, phy_dev->speed); - mac_dev->update_speed(mac_dev, phy_dev->speed); - fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); - err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); - if (err < 0) - dev_err(mac_dev->dev, "fman_set_mac_active_pause() = %d\n", - err); -} - static int dtsec_set_exception(struct fman_mac *dtsec, enum fman_mac_exceptions exception, bool enable) { struct dtsec_regs __iomem *regs = dtsec->regs; u32 bit_mask = 0; - if (!is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - if (exception != FM_MAC_EX_1G_1588_TS_RX_ERR) { bit_mask = get_exception_flag(exception); if (bit_mask) { @@ -1310,12 +1260,9 @@ static int dtsec_init(struct fman_mac *dtsec) { struct dtsec_regs __iomem *regs = dtsec->regs; struct dtsec_cfg *dtsec_drv_param; - u16 max_frm_ln; + u16 max_frm_ln, tbicon; int err; - if (is_init_done(dtsec->dtsec_drv_param)) - return -EINVAL; - if (DEFAULT_RESET_ON_INIT && (fman_reset_mac(dtsec->fm, dtsec->mac_id) != 0)) { pr_err("Can't reset MAC!\n"); @@ -1330,38 +1277,19 @@ static int dtsec_init(struct fman_mac *dtsec) err = init(dtsec->regs, dtsec_drv_param, dtsec->phy_if, dtsec->max_speed, dtsec->addr, dtsec->exceptions, - dtsec->tbiphy->mdio.addr); + dtsec->tbidev->addr); if (err) { free_init_resources(dtsec); pr_err("DTSEC version doesn't support this i/f mode\n"); return err; } - if (dtsec->phy_if == PHY_INTERFACE_MODE_SGMII) { - u16 tmp_reg16; - - /* Configure the TBI PHY Control Register */ - tmp_reg16 = TBICON_CLK_SELECT | TBICON_SOFT_RESET; - phy_write(dtsec->tbiphy, MII_TBICON, tmp_reg16); + /* Configure the TBI PHY Control Register */ + tbicon = TBICON_CLK_SELECT | TBICON_SOFT_RESET; + mdiodev_write(dtsec->tbidev, MII_TBICON, tbicon); - tmp_reg16 = TBICON_CLK_SELECT; - phy_write(dtsec->tbiphy, MII_TBICON, tmp_reg16); - - tmp_reg16 = (BMCR_RESET | BMCR_ANENABLE | - BMCR_FULLDPLX | BMCR_SPEED1000); - phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); - - if (dtsec->basex_if) - tmp_reg16 = TBIANA_1000X; - else - tmp_reg16 = TBIANA_SGMII; - phy_write(dtsec->tbiphy, MII_ADVERTISE, tmp_reg16); - - tmp_reg16 = (BMCR_ANENABLE | BMCR_ANRESTART | - BMCR_FULLDPLX | BMCR_SPEED1000); - - phy_write(dtsec->tbiphy, MII_BMCR, tmp_reg16); - } + tbicon = TBICON_CLK_SELECT; + mdiodev_write(dtsec->tbidev, MII_TBICON, tbicon); /* Max Frame Length */ max_frm_ln = (u16)ioread32be(®s->maxfrm); @@ -1406,6 +1334,8 @@ static int dtsec_free(struct fman_mac *dtsec) kfree(dtsec->dtsec_drv_param); dtsec->dtsec_drv_param = NULL; + if (!IS_ERR_OR_NULL(dtsec->tbidev)) + put_device(&dtsec->tbidev->dev); kfree(dtsec); return 0; @@ -1434,7 +1364,6 @@ static struct fman_mac *dtsec_config(struct mac_device *mac_dev, dtsec->regs = mac_dev->vaddr; dtsec->addr = ENET_ADDR_TO_UINT64(mac_dev->addr); - dtsec->max_speed = params->max_speed; dtsec->phy_if = mac_dev->phy_if; dtsec->mac_id = params->mac_id; dtsec->exceptions = (DTSEC_IMASK_BREN | @@ -1457,7 +1386,6 @@ static struct fman_mac *dtsec_config(struct mac_device *mac_dev, dtsec->en_tsu_err_exception = dtsec->dtsec_drv_param->ptp_exception_en; dtsec->fm = params->fm; - dtsec->basex_if = params->basex_if; /* Save FMan revision */ fman_get_revision(dtsec->fm, &dtsec->fm_rev_info); @@ -1476,18 +1404,18 @@ int dtsec_initialization(struct mac_device *mac_dev, int err; struct fman_mac *dtsec; struct device_node *phy_node; + unsigned long capabilities; + unsigned long *supported; + mac_dev->phylink_ops = &dtsec_mac_ops; mac_dev->set_promisc = dtsec_set_promiscuous; mac_dev->change_addr = dtsec_modify_mac_address; mac_dev->add_hash_mac_addr = dtsec_add_hash_mac_address; mac_dev->remove_hash_mac_addr = dtsec_del_hash_mac_address; - mac_dev->set_tx_pause = dtsec_set_tx_pause_frames; - mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames; mac_dev->set_exception = dtsec_set_exception; mac_dev->set_allmulti = dtsec_set_allmulti; mac_dev->set_tstamp = dtsec_set_tstamp; mac_dev->set_multi = fman_set_multi; - mac_dev->adjust_link = adjust_link_dtsec; mac_dev->enable = dtsec_enable; mac_dev->disable = dtsec_disable; @@ -1502,19 +1430,56 @@ int dtsec_initialization(struct mac_device *mac_dev, dtsec->dtsec_drv_param->tx_pad_crc = true; phy_node = of_parse_phandle(mac_node, "tbi-handle", 0); - if (!phy_node) { - pr_err("TBI PHY node is not available\n"); + if (!phy_node || of_device_is_available(phy_node)) { + of_node_put(phy_node); err = -EINVAL; + dev_err_probe(mac_dev->dev, err, + "TBI PCS node is not available\n"); goto _return_fm_mac_free; } - dtsec->tbiphy = of_phy_find_device(phy_node); - if (!dtsec->tbiphy) { - pr_err("of_phy_find_device (TBI PHY) failed\n"); - err = -EINVAL; + dtsec->tbidev = of_mdio_find_device(phy_node); + of_node_put(phy_node); + if (!dtsec->tbidev) { + err = -EPROBE_DEFER; + dev_err_probe(mac_dev->dev, err, + "could not find mdiodev for PCS\n"); goto _return_fm_mac_free; } - put_device(&dtsec->tbiphy->mdio.dev); + dtsec->pcs.ops = &dtsec_pcs_ops; + dtsec->pcs.poll = true; + + supported = mac_dev->phylink_config.supported_interfaces; + + /* FIXME: Can we use DTSEC_ID2_INT_FULL_OFF to determine if these are + * supported? If not, we can determine support via the phy if SerDes + * support is added. + */ + if (mac_dev->phy_if == PHY_INTERFACE_MODE_SGMII || + mac_dev->phy_if == PHY_INTERFACE_MODE_1000BASEX) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + } else if (mac_dev->phy_if == PHY_INTERFACE_MODE_2500BASEX) { + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + } + + if (!(ioread32be(&dtsec->regs->tsec_id2) & DTSEC_ID2_INT_REDUCED_OFF)) { + phy_interface_set_rgmii(supported); + + /* DTSEC_ID2_INT_REDUCED_OFF indicates that the dTSEC supports + * RMII and RGMII. However, the only SoCs which support RMII + * are the P1017 and P1023. Avoid advertising this mode on + * other SoCs. This is a bit of a moot point, since there's no + * in-tree support for ethernet on these platforms... + */ + if (of_machine_is_compatible("fsl,P1023") || + of_machine_is_compatible("fsl,P1023RDB")) + __set_bit(PHY_INTERFACE_MODE_RMII, supported); + } + + capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE; + capabilities |= MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD; + mac_dev->phylink_config.mac_capabilities = capabilities; err = dtsec_init(dtsec); if (err < 0) diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h index 65887a3160d7..e5d6cddea731 100644 --- a/drivers/net/ethernet/freescale/fman/fman_mac.h +++ b/drivers/net/ethernet/freescale/fman/fman_mac.h @@ -170,20 +170,10 @@ struct fman_mac_params { * 0 - FM_MAX_NUM_OF_10G_MACS */ u8 mac_id; - /* Note that the speed should indicate the maximum rate that - * this MAC should support rather than the actual speed; - */ - u16 max_speed; /* A handle to the FM object this port related to */ void *fm; fman_mac_exception_cb *event_cb; /* MDIO Events Callback Routine */ fman_mac_exception_cb *exception_cb;/* Exception Callback Routine */ - /* SGMII/QSGII interface with 1000BaseX auto-negotiation between MAC - * and phy or backplane; Note: 1000BaseX auto-negotiation relates only - * to interface between MAC and phy/backplane, SGMII phy can still - * synchronize with far-end phy at 10Mbps, 100Mbps or 1000Mbps - */ - bool basex_if; }; struct eth_hash_t { diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 32d26cf17843..9349f841bd06 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -11,42 +11,12 @@ #include <linux/slab.h> #include <linux/io.h> +#include <linux/pcs-lynx.h> #include <linux/phy.h> #include <linux/phy_fixed.h> +#include <linux/phy/phy.h> #include <linux/of_mdio.h> -/* PCS registers */ -#define MDIO_SGMII_CR 0x00 -#define MDIO_SGMII_DEV_ABIL_SGMII 0x04 -#define MDIO_SGMII_LINK_TMR_L 0x12 -#define MDIO_SGMII_LINK_TMR_H 0x13 -#define MDIO_SGMII_IF_MODE 0x14 - -/* SGMII Control defines */ -#define SGMII_CR_AN_EN 0x1000 -#define SGMII_CR_RESTART_AN 0x0200 -#define SGMII_CR_FD 0x0100 -#define SGMII_CR_SPEED_SEL1_1G 0x0040 -#define SGMII_CR_DEF_VAL (SGMII_CR_AN_EN | SGMII_CR_FD | \ - SGMII_CR_SPEED_SEL1_1G) - -/* SGMII Device Ability for SGMII defines */ -#define MDIO_SGMII_DEV_ABIL_SGMII_MODE 0x4001 -#define MDIO_SGMII_DEV_ABIL_BASEX_MODE 0x01A0 - -/* Link timer define */ -#define LINK_TMR_L 0xa120 -#define LINK_TMR_H 0x0007 -#define LINK_TMR_L_BASEX 0xaf08 -#define LINK_TMR_H_BASEX 0x002f - -/* SGMII IF Mode defines */ -#define IF_MODE_USE_SGMII_AN 0x0002 -#define IF_MODE_SGMII_EN 0x0001 -#define IF_MODE_SGMII_SPEED_100M 0x0004 -#define IF_MODE_SGMII_SPEED_1G 0x0008 -#define IF_MODE_SGMII_DUPLEX_HALF 0x0010 - /* Num of additional exact match MAC adr regs */ #define MEMAC_NUM_OF_PADDRS 7 @@ -308,9 +278,6 @@ struct fman_mac { struct memac_regs __iomem *regs; /* MAC address of device */ u64 addr; - /* Ethernet physical interface */ - phy_interface_t phy_if; - u16 max_speed; struct mac_device *dev_id; /* device cookie used by the exception cbs */ fman_mac_exception_cb *exception_cb; fman_mac_exception_cb *event_cb; @@ -323,9 +290,12 @@ struct fman_mac { struct memac_cfg *memac_drv_param; void *fm; struct fman_rev_info fm_rev_info; - bool basex_if; - struct phy_device *pcsphy; + struct phy *serdes; + struct phylink_pcs *sgmii_pcs; + struct phylink_pcs *qsgmii_pcs; + struct phylink_pcs *xfi_pcs; bool allmulti_enabled; + bool rgmii_no_half_duplex; }; static void add_addr_in_paddr(struct memac_regs __iomem *regs, const u8 *adr, @@ -383,7 +353,6 @@ static void set_exception(struct memac_regs __iomem *regs, u32 val, } static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg, - phy_interface_t phy_if, u16 speed, bool slow_10g_if, u32 exceptions) { u32 tmp; @@ -411,41 +380,6 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg, iowrite32be((u32)cfg->pause_quanta, ®s->pause_quanta[0]); iowrite32be((u32)0, ®s->pause_thresh[0]); - /* IF_MODE */ - tmp = 0; - switch (phy_if) { - case PHY_INTERFACE_MODE_XGMII: - tmp |= IF_MODE_10G; - break; - case PHY_INTERFACE_MODE_MII: - tmp |= IF_MODE_MII; - break; - default: - tmp |= IF_MODE_GMII; - if (phy_if == PHY_INTERFACE_MODE_RGMII || - phy_if == PHY_INTERFACE_MODE_RGMII_ID || - phy_if == PHY_INTERFACE_MODE_RGMII_RXID || - phy_if == PHY_INTERFACE_MODE_RGMII_TXID) - tmp |= IF_MODE_RGMII | IF_MODE_RGMII_AUTO; - } - iowrite32be(tmp, ®s->if_mode); - - /* TX_FIFO_SECTIONS */ - tmp = 0; - if (phy_if == PHY_INTERFACE_MODE_XGMII) { - if (slow_10g_if) { - tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_SLOW_10G | - TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G); - } else { - tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_10G | - TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G); - } - } else { - tmp |= (TX_FIFO_SECTIONS_TX_AVAIL_1G | - TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_1G); - } - iowrite32be(tmp, ®s->tx_fifo_sections); - /* clear all pending events and set-up interrupts */ iowrite32be(0xffffffff, ®s->ievent); set_exception(regs, exceptions, true); @@ -485,93 +419,6 @@ static u32 get_mac_addr_hash_code(u64 eth_addr) return xor_val; } -static void setup_sgmii_internal_phy(struct fman_mac *memac, - struct fixed_phy_status *fixed_link) -{ - u16 tmp_reg16; - - if (WARN_ON(!memac->pcsphy)) - return; - - /* SGMII mode */ - tmp_reg16 = IF_MODE_SGMII_EN; - if (!fixed_link) - /* AN enable */ - tmp_reg16 |= IF_MODE_USE_SGMII_AN; - else { - switch (fixed_link->speed) { - case 10: - /* For 10M: IF_MODE[SPEED_10M] = 0 */ - break; - case 100: - tmp_reg16 |= IF_MODE_SGMII_SPEED_100M; - break; - case 1000: - default: - tmp_reg16 |= IF_MODE_SGMII_SPEED_1G; - break; - } - if (!fixed_link->duplex) - tmp_reg16 |= IF_MODE_SGMII_DUPLEX_HALF; - } - phy_write(memac->pcsphy, MDIO_SGMII_IF_MODE, tmp_reg16); - - /* Device ability according to SGMII specification */ - tmp_reg16 = MDIO_SGMII_DEV_ABIL_SGMII_MODE; - phy_write(memac->pcsphy, MDIO_SGMII_DEV_ABIL_SGMII, tmp_reg16); - - /* Adjust link timer for SGMII - - * According to Cisco SGMII specification the timer should be 1.6 ms. - * The link_timer register is configured in units of the clock. - * - When running as 1G SGMII, Serdes clock is 125 MHz, so - * unit = 1 / (125*10^6 Hz) = 8 ns. - * 1.6 ms in units of 8 ns = 1.6ms / 8ns = 2*10^5 = 0x30d40 - * - When running as 2.5G SGMII, Serdes clock is 312.5 MHz, so - * unit = 1 / (312.5*10^6 Hz) = 3.2 ns. - * 1.6 ms in units of 3.2 ns = 1.6ms / 3.2ns = 5*10^5 = 0x7a120. - * Since link_timer value of 1G SGMII will be too short for 2.5 SGMII, - * we always set up here a value of 2.5 SGMII. - */ - phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_H, LINK_TMR_H); - phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_L, LINK_TMR_L); - - if (!fixed_link) - /* Restart AN */ - tmp_reg16 = SGMII_CR_DEF_VAL | SGMII_CR_RESTART_AN; - else - /* AN disabled */ - tmp_reg16 = SGMII_CR_DEF_VAL & ~SGMII_CR_AN_EN; - phy_write(memac->pcsphy, 0x0, tmp_reg16); -} - -static void setup_sgmii_internal_phy_base_x(struct fman_mac *memac) -{ - u16 tmp_reg16; - - /* AN Device capability */ - tmp_reg16 = MDIO_SGMII_DEV_ABIL_BASEX_MODE; - phy_write(memac->pcsphy, MDIO_SGMII_DEV_ABIL_SGMII, tmp_reg16); - - /* Adjust link timer for SGMII - - * For Serdes 1000BaseX auto-negotiation the timer should be 10 ms. - * The link_timer register is configured in units of the clock. - * - When running as 1G SGMII, Serdes clock is 125 MHz, so - * unit = 1 / (125*10^6 Hz) = 8 ns. - * 10 ms in units of 8 ns = 10ms / 8ns = 1250000 = 0x1312d0 - * - When running as 2.5G SGMII, Serdes clock is 312.5 MHz, so - * unit = 1 / (312.5*10^6 Hz) = 3.2 ns. - * 10 ms in units of 3.2 ns = 10ms / 3.2ns = 3125000 = 0x2faf08. - * Since link_timer value of 1G SGMII will be too short for 2.5 SGMII, - * we always set up here a value of 2.5 SGMII. - */ - phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_H, LINK_TMR_H_BASEX); - phy_write(memac->pcsphy, MDIO_SGMII_LINK_TMR_L, LINK_TMR_L_BASEX); - - /* Restart AN */ - tmp_reg16 = SGMII_CR_DEF_VAL | SGMII_CR_RESTART_AN; - phy_write(memac->pcsphy, 0x0, tmp_reg16); -} - static int check_init_parameters(struct fman_mac *memac) { if (!memac->exception_cb) { @@ -677,41 +524,31 @@ static void free_init_resources(struct fman_mac *memac) memac->unicast_addr_hash = NULL; } -static bool is_init_done(struct memac_cfg *memac_drv_params) -{ - /* Checks if mEMAC driver parameters were initialized */ - if (!memac_drv_params) - return true; - - return false; -} - static int memac_enable(struct fman_mac *memac) { - struct memac_regs __iomem *regs = memac->regs; - u32 tmp; + int ret; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; + ret = phy_init(memac->serdes); + if (ret) { + dev_err(memac->dev_id->dev, + "could not initialize serdes: %pe\n", ERR_PTR(ret)); + return ret; + } - tmp = ioread32be(®s->command_config); - tmp |= CMD_CFG_RX_EN | CMD_CFG_TX_EN; - iowrite32be(tmp, ®s->command_config); + ret = phy_power_on(memac->serdes); + if (ret) { + dev_err(memac->dev_id->dev, + "could not power on serdes: %pe\n", ERR_PTR(ret)); + phy_exit(memac->serdes); + } - return 0; + return ret; } static void memac_disable(struct fman_mac *memac) - { - struct memac_regs __iomem *regs = memac->regs; - u32 tmp; - - WARN_ON_ONCE(!is_init_done(memac->memac_drv_param)); - - tmp = ioread32be(®s->command_config); - tmp &= ~(CMD_CFG_RX_EN | CMD_CFG_TX_EN); - iowrite32be(tmp, ®s->command_config); + phy_power_off(memac->serdes); + phy_exit(memac->serdes); } static int memac_set_promiscuous(struct fman_mac *memac, bool new_val) @@ -719,9 +556,6 @@ static int memac_set_promiscuous(struct fman_mac *memac, bool new_val) struct memac_regs __iomem *regs = memac->regs; u32 tmp; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - tmp = ioread32be(®s->command_config); if (new_val) tmp |= CMD_CFG_PROMIS_EN; @@ -733,73 +567,12 @@ static int memac_set_promiscuous(struct fman_mac *memac, bool new_val) return 0; } -static int memac_adjust_link(struct fman_mac *memac, u16 speed) -{ - struct memac_regs __iomem *regs = memac->regs; - u32 tmp; - - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - - tmp = ioread32be(®s->if_mode); - - /* Set full duplex */ - tmp &= ~IF_MODE_HD; - - if (phy_interface_mode_is_rgmii(memac->phy_if)) { - /* Configure RGMII in manual mode */ - tmp &= ~IF_MODE_RGMII_AUTO; - tmp &= ~IF_MODE_RGMII_SP_MASK; - /* Full duplex */ - tmp |= IF_MODE_RGMII_FD; - - switch (speed) { - case SPEED_1000: - tmp |= IF_MODE_RGMII_1000; - break; - case SPEED_100: - tmp |= IF_MODE_RGMII_100; - break; - case SPEED_10: - tmp |= IF_MODE_RGMII_10; - break; - default: - break; - } - } - - iowrite32be(tmp, ®s->if_mode); - - return 0; -} - -static void adjust_link_memac(struct mac_device *mac_dev) -{ - struct phy_device *phy_dev = mac_dev->phy_dev; - struct fman_mac *fman_mac; - bool rx_pause, tx_pause; - int err; - - fman_mac = mac_dev->fman_mac; - memac_adjust_link(fman_mac, phy_dev->speed); - mac_dev->update_speed(mac_dev, phy_dev->speed); - - fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); - err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); - if (err < 0) - dev_err(mac_dev->dev, "fman_set_mac_active_pause() = %d\n", - err); -} - static int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority, u16 pause_time, u16 thresh_time) { struct memac_regs __iomem *regs = memac->regs; u32 tmp; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - tmp = ioread32be(®s->tx_fifo_sections); GET_TX_EMPTY_DEFAULT_VALUE(tmp); @@ -834,9 +607,6 @@ static int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) struct memac_regs __iomem *regs = memac->regs; u32 tmp; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - tmp = ioread32be(®s->command_config); if (en) tmp &= ~CMD_CFG_PAUSE_IGNORE; @@ -848,12 +618,175 @@ static int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) return 0; } +static void memac_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct fman_mac *memac = fman_config_to_mac(config)->fman_mac; + unsigned long caps = config->mac_capabilities; + + if (phy_interface_mode_is_rgmii(state->interface) && + memac->rgmii_no_half_duplex) + caps &= ~(MAC_10HD | MAC_100HD); + + phylink_validate_mask_caps(supported, state, caps); +} + +/** + * memac_if_mode() - Convert an interface mode into an IF_MODE config + * @interface: A phy interface mode + * + * Return: A configuration word, suitable for programming into the lower bits + * of %IF_MODE. + */ +static u32 memac_if_mode(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_MII: + return IF_MODE_MII; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + return IF_MODE_GMII | IF_MODE_RGMII; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_QSGMII: + return IF_MODE_GMII; + case PHY_INTERFACE_MODE_10GBASER: + return IF_MODE_10G; + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static struct phylink_pcs *memac_select_pcs(struct phylink_config *config, + phy_interface_t iface) +{ + struct fman_mac *memac = fman_config_to_mac(config)->fman_mac; + + switch (iface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + return memac->sgmii_pcs; + case PHY_INTERFACE_MODE_QSGMII: + return memac->qsgmii_pcs; + case PHY_INTERFACE_MODE_10GBASER: + return memac->xfi_pcs; + default: + return NULL; + } +} + +static int memac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t iface) +{ + struct fman_mac *memac = fman_config_to_mac(config)->fman_mac; + + switch (iface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_10GBASER: + return phy_set_mode_ext(memac->serdes, PHY_MODE_ETHERNET, + iface); + default: + return 0; + } +} + +static void memac_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct mac_device *mac_dev = fman_config_to_mac(config); + struct memac_regs __iomem *regs = mac_dev->fman_mac->regs; + u32 tmp = ioread32be(®s->if_mode); + + tmp &= ~(IF_MODE_MASK | IF_MODE_RGMII); + tmp |= memac_if_mode(state->interface); + if (phylink_autoneg_inband(mode)) + tmp |= IF_MODE_RGMII_AUTO; + iowrite32be(tmp, ®s->if_mode); +} + +static void memac_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) +{ + struct mac_device *mac_dev = fman_config_to_mac(config); + struct fman_mac *memac = mac_dev->fman_mac; + struct memac_regs __iomem *regs = memac->regs; + u32 tmp = memac_if_mode(interface); + u16 pause_time = tx_pause ? FSL_FM_PAUSE_TIME_ENABLE : + FSL_FM_PAUSE_TIME_DISABLE; + + memac_set_tx_pause_frames(memac, 0, pause_time, 0); + memac_accept_rx_pause_frames(memac, rx_pause); + + if (duplex == DUPLEX_HALF) + tmp |= IF_MODE_HD; + + switch (speed) { + case SPEED_1000: + tmp |= IF_MODE_RGMII_1000; + break; + case SPEED_100: + tmp |= IF_MODE_RGMII_100; + break; + case SPEED_10: + tmp |= IF_MODE_RGMII_10; + break; + } + iowrite32be(tmp, ®s->if_mode); + + /* TODO: EEE? */ + + if (speed == SPEED_10000) { + if (memac->fm_rev_info.major == 6 && + memac->fm_rev_info.minor == 4) + tmp = TX_FIFO_SECTIONS_TX_AVAIL_SLOW_10G; + else + tmp = TX_FIFO_SECTIONS_TX_AVAIL_10G; + tmp |= TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_10G; + } else { + tmp = TX_FIFO_SECTIONS_TX_AVAIL_1G | + TX_FIFO_SECTIONS_TX_EMPTY_DEFAULT_1G; + } + iowrite32be(tmp, ®s->tx_fifo_sections); + + mac_dev->update_speed(mac_dev, speed); + + tmp = ioread32be(®s->command_config); + tmp |= CMD_CFG_RX_EN | CMD_CFG_TX_EN; + iowrite32be(tmp, ®s->command_config); +} + +static void memac_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct fman_mac *memac = fman_config_to_mac(config)->fman_mac; + struct memac_regs __iomem *regs = memac->regs; + u32 tmp; + + /* TODO: graceful */ + tmp = ioread32be(®s->command_config); + tmp &= ~(CMD_CFG_RX_EN | CMD_CFG_TX_EN); + iowrite32be(tmp, ®s->command_config); +} + +static const struct phylink_mac_ops memac_mac_ops = { + .validate = memac_validate, + .mac_select_pcs = memac_select_pcs, + .mac_prepare = memac_prepare, + .mac_config = memac_mac_config, + .mac_link_up = memac_link_up, + .mac_link_down = memac_link_down, +}; + static int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr) { - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - add_addr_in_paddr(memac->regs, (const u8 *)(*enet_addr), 0); return 0; @@ -867,9 +800,6 @@ static int memac_add_hash_mac_address(struct fman_mac *memac, u32 hash; u64 addr; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - addr = ENET_ADDR_TO_UINT64(*eth_addr); if (!(addr & GROUP_ADDRESS)) { @@ -898,9 +828,6 @@ static int memac_set_allmulti(struct fman_mac *memac, bool enable) u32 entry; struct memac_regs __iomem *regs = memac->regs; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - if (enable) { for (entry = 0; entry < HASH_TABLE_SIZE; entry++) iowrite32be(entry | HASH_CTRL_MCAST_EN, @@ -930,9 +857,6 @@ static int memac_del_hash_mac_address(struct fman_mac *memac, u32 hash; u64 addr; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - addr = ENET_ADDR_TO_UINT64(*eth_addr); hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK; @@ -960,9 +884,6 @@ static int memac_set_exception(struct fman_mac *memac, { u32 bit_mask = 0; - if (!is_init_done(memac->memac_drv_param)) - return -EINVAL; - bit_mask = get_exception_flag(exception); if (bit_mask) { if (enable) @@ -981,25 +902,16 @@ static int memac_set_exception(struct fman_mac *memac, static int memac_init(struct fman_mac *memac) { struct memac_cfg *memac_drv_param; - u8 i; enet_addr_t eth_addr; - bool slow_10g_if = false; - struct fixed_phy_status *fixed_link = NULL; int err; u32 reg32 = 0; - if (is_init_done(memac->memac_drv_param)) - return -EINVAL; - err = check_init_parameters(memac); if (err) return err; memac_drv_param = memac->memac_drv_param; - if (memac->fm_rev_info.major == 6 && memac->fm_rev_info.minor == 4) - slow_10g_if = true; - /* First, reset the MAC if desired. */ if (memac_drv_param->reset_on_init) { err = reset(memac->regs); @@ -1015,10 +927,7 @@ static int memac_init(struct fman_mac *memac) add_addr_in_paddr(memac->regs, (const u8 *)eth_addr, 0); } - fixed_link = memac_drv_param->fixed_link; - - init(memac->regs, memac->memac_drv_param, memac->phy_if, - memac->max_speed, slow_10g_if, memac->exceptions); + init(memac->regs, memac->memac_drv_param, memac->exceptions); /* FM_RX_FIFO_CORRUPT_ERRATA_10GMAC_A006320 errata workaround * Exists only in FMan 6.0 and 6.3. @@ -1034,33 +943,6 @@ static int memac_init(struct fman_mac *memac) iowrite32be(reg32, &memac->regs->command_config); } - if (memac->phy_if == PHY_INTERFACE_MODE_SGMII) { - /* Configure internal SGMII PHY */ - if (memac->basex_if) - setup_sgmii_internal_phy_base_x(memac); - else - setup_sgmii_internal_phy(memac, fixed_link); - } else if (memac->phy_if == PHY_INTERFACE_MODE_QSGMII) { - /* Configure 4 internal SGMII PHYs */ - for (i = 0; i < 4; i++) { - u8 qsmgii_phy_addr, phy_addr; - /* QSGMII PHY address occupies 3 upper bits of 5-bit - * phy_address; the lower 2 bits are used to extend - * register address space and access each one of 4 - * ports inside QSGMII. - */ - phy_addr = memac->pcsphy->mdio.addr; - qsmgii_phy_addr = (u8)((phy_addr << 2) | i); - memac->pcsphy->mdio.addr = qsmgii_phy_addr; - if (memac->basex_if) - setup_sgmii_internal_phy_base_x(memac); - else - setup_sgmii_internal_phy(memac, fixed_link); - - memac->pcsphy->mdio.addr = phy_addr; - } - } - /* Max Frame Length */ err = fman_set_mac_max_frame(memac->fm, memac->mac_id, memac_drv_param->max_frame_length); @@ -1089,19 +971,28 @@ static int memac_init(struct fman_mac *memac) fman_register_intr(memac->fm, FMAN_MOD_MAC, memac->mac_id, FMAN_INTR_TYPE_NORMAL, memac_exception, memac); - kfree(memac_drv_param); - memac->memac_drv_param = NULL; - return 0; } +static void pcs_put(struct phylink_pcs *pcs) +{ + struct mdio_device *mdiodev; + + if (IS_ERR_OR_NULL(pcs)) + return; + + mdiodev = lynx_get_mdio_device(pcs); + lynx_pcs_destroy(pcs); + mdio_device_free(mdiodev); +} + static int memac_free(struct fman_mac *memac) { free_init_resources(memac); - if (memac->pcsphy) - put_device(&memac->pcsphy->mdio.dev); - + pcs_put(memac->sgmii_pcs); + pcs_put(memac->qsgmii_pcs); + pcs_put(memac->xfi_pcs); kfree(memac->memac_drv_param); kfree(memac); @@ -1134,8 +1025,6 @@ static struct fman_mac *memac_config(struct mac_device *mac_dev, memac->addr = ENET_ADDR_TO_UINT64(mac_dev->addr); memac->regs = mac_dev->vaddr; - memac->max_speed = params->max_speed; - memac->phy_if = mac_dev->phy_if; memac->mac_id = params->mac_id; memac->exceptions = (MEMAC_IMASK_TSECC_ER | MEMAC_IMASK_TECC_ER | MEMAC_IMASK_RECC_ER | MEMAC_IMASK_MGI); @@ -1143,7 +1032,6 @@ static struct fman_mac *memac_config(struct mac_device *mac_dev, memac->event_cb = params->event_cb; memac->dev_id = mac_dev; memac->fm = params->fm; - memac->basex_if = params->basex_if; /* Save FMan revision */ fman_get_revision(memac->fm, &memac->fm_rev_info); @@ -1151,101 +1039,221 @@ static struct fman_mac *memac_config(struct mac_device *mac_dev, return memac; } +static struct phylink_pcs *memac_pcs_create(struct device_node *mac_node, + int index) +{ + struct device_node *node; + struct mdio_device *mdiodev = NULL; + struct phylink_pcs *pcs; + + node = of_parse_phandle(mac_node, "pcsphy-handle", index); + if (node && of_device_is_available(node)) + mdiodev = of_mdio_find_device(node); + of_node_put(node); + + if (!mdiodev) + return ERR_PTR(-EPROBE_DEFER); + + pcs = lynx_pcs_create(mdiodev); + return pcs; +} + +static bool memac_supports(struct mac_device *mac_dev, phy_interface_t iface) +{ + /* If there's no serdes device, assume that it's been configured for + * whatever the default interface mode is. + */ + if (!mac_dev->fman_mac->serdes) + return mac_dev->phy_if == iface; + /* Otherwise, ask the serdes */ + return !phy_validate(mac_dev->fman_mac->serdes, PHY_MODE_ETHERNET, + iface, NULL); +} + int memac_initialization(struct mac_device *mac_dev, struct device_node *mac_node, struct fman_mac_params *params) { int err; - struct device_node *phy_node; - struct fixed_phy_status *fixed_link; + struct device_node *fixed; + struct phylink_pcs *pcs; struct fman_mac *memac; + unsigned long capabilities; + unsigned long *supported; + mac_dev->phylink_ops = &memac_mac_ops; mac_dev->set_promisc = memac_set_promiscuous; mac_dev->change_addr = memac_modify_mac_address; mac_dev->add_hash_mac_addr = memac_add_hash_mac_address; mac_dev->remove_hash_mac_addr = memac_del_hash_mac_address; - mac_dev->set_tx_pause = memac_set_tx_pause_frames; - mac_dev->set_rx_pause = memac_accept_rx_pause_frames; mac_dev->set_exception = memac_set_exception; mac_dev->set_allmulti = memac_set_allmulti; mac_dev->set_tstamp = memac_set_tstamp; mac_dev->set_multi = fman_set_multi; - mac_dev->adjust_link = adjust_link_memac; mac_dev->enable = memac_enable; mac_dev->disable = memac_disable; - if (params->max_speed == SPEED_10000) - mac_dev->phy_if = PHY_INTERFACE_MODE_XGMII; - mac_dev->fman_mac = memac_config(mac_dev, params); - if (!mac_dev->fman_mac) { - err = -EINVAL; - goto _return; - } + if (!mac_dev->fman_mac) + return -EINVAL; memac = mac_dev->fman_mac; memac->memac_drv_param->max_frame_length = fman_get_max_frm(); memac->memac_drv_param->reset_on_init = true; - if (memac->phy_if == PHY_INTERFACE_MODE_SGMII || - memac->phy_if == PHY_INTERFACE_MODE_QSGMII) { - phy_node = of_parse_phandle(mac_node, "pcsphy-handle", 0); - if (!phy_node) { - pr_err("PCS PHY node is not available\n"); - err = -EINVAL; + + err = of_property_match_string(mac_node, "pcs-handle-names", "xfi"); + if (err >= 0) { + memac->xfi_pcs = memac_pcs_create(mac_node, err); + if (IS_ERR(memac->xfi_pcs)) { + err = PTR_ERR(memac->xfi_pcs); + dev_err_probe(mac_dev->dev, err, "missing xfi pcs\n"); goto _return_fm_mac_free; } + } else if (err != -EINVAL && err != -ENODATA) { + goto _return_fm_mac_free; + } - memac->pcsphy = of_phy_find_device(phy_node); - if (!memac->pcsphy) { - pr_err("of_phy_find_device (PCS PHY) failed\n"); - err = -EINVAL; + err = of_property_match_string(mac_node, "pcs-handle-names", "qsgmii"); + if (err >= 0) { + memac->qsgmii_pcs = memac_pcs_create(mac_node, err); + if (IS_ERR(memac->qsgmii_pcs)) { + err = PTR_ERR(memac->qsgmii_pcs); + dev_err_probe(mac_dev->dev, err, + "missing qsgmii pcs\n"); goto _return_fm_mac_free; } + } else if (err != -EINVAL && err != -ENODATA) { + goto _return_fm_mac_free; } - if (!mac_dev->phy_node && of_phy_is_fixed_link(mac_node)) { - struct phy_device *phy; + /* For compatibility, if pcs-handle-names is missing, we assume this + * phy is the first one in pcsphy-handle + */ + err = of_property_match_string(mac_node, "pcs-handle-names", "sgmii"); + if (err == -EINVAL || err == -ENODATA) + pcs = memac_pcs_create(mac_node, 0); + else if (err < 0) + goto _return_fm_mac_free; + else + pcs = memac_pcs_create(mac_node, err); - err = of_phy_register_fixed_link(mac_node); - if (err) - goto _return_fm_mac_free; + if (IS_ERR(pcs)) { + err = PTR_ERR(pcs); + dev_err_probe(mac_dev->dev, err, "missing pcs\n"); + goto _return_fm_mac_free; + } - fixed_link = kzalloc(sizeof(*fixed_link), GFP_KERNEL); - if (!fixed_link) { - err = -ENOMEM; - goto _return_fm_mac_free; - } + /* If err is set here, it means that pcs-handle-names was missing above + * (and therefore that xfi_pcs cannot be set). If we are defaulting to + * XGMII, assume this is for XFI. Otherwise, assume it is for SGMII. + */ + if (err && mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) + memac->xfi_pcs = pcs; + else + memac->sgmii_pcs = pcs; + + memac->serdes = devm_of_phy_get(mac_dev->dev, mac_node, "serdes"); + err = PTR_ERR(memac->serdes); + if (err == -ENODEV || err == -ENOSYS) { + dev_dbg(mac_dev->dev, "could not get (optional) serdes\n"); + memac->serdes = NULL; + } else if (IS_ERR(memac->serdes)) { + dev_err_probe(mac_dev->dev, err, "could not get serdes\n"); + goto _return_fm_mac_free; + } - mac_dev->phy_node = of_node_get(mac_node); - phy = of_phy_find_device(mac_dev->phy_node); - if (!phy) { - err = -EINVAL; - of_node_put(mac_dev->phy_node); - goto _return_fixed_link_free; - } + /* The internal connection to the serdes is XGMII, but this isn't + * really correct for the phy mode (which is the external connection). + * However, this is how all older device trees say that they want + * 10GBASE-R (aka XFI), so just convert it for them. + */ + if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) + mac_dev->phy_if = PHY_INTERFACE_MODE_10GBASER; + + /* TODO: The following interface modes are supported by (some) hardware + * but not by this driver: + * - 1000BASE-KX + * - 10GBASE-KR + * - XAUI/HiGig + */ + supported = mac_dev->phylink_config.supported_interfaces; - fixed_link->link = phy->link; - fixed_link->speed = phy->speed; - fixed_link->duplex = phy->duplex; - fixed_link->pause = phy->pause; - fixed_link->asym_pause = phy->asym_pause; + /* Note that half duplex is only supported on 10/100M interfaces. */ - put_device(&phy->mdio.dev); - memac->memac_drv_param->fixed_link = fixed_link; + if (memac->sgmii_pcs && + (memac_supports(mac_dev, PHY_INTERFACE_MODE_SGMII) || + memac_supports(mac_dev, PHY_INTERFACE_MODE_1000BASEX))) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); } + if (memac->sgmii_pcs && + memac_supports(mac_dev, PHY_INTERFACE_MODE_2500BASEX)) + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + + if (memac->qsgmii_pcs && + memac_supports(mac_dev, PHY_INTERFACE_MODE_QSGMII)) + __set_bit(PHY_INTERFACE_MODE_QSGMII, supported); + else if (mac_dev->phy_if == PHY_INTERFACE_MODE_QSGMII) + dev_warn(mac_dev->dev, "no QSGMII pcs specified\n"); + + if (memac->xfi_pcs && + memac_supports(mac_dev, PHY_INTERFACE_MODE_10GBASER)) { + __set_bit(PHY_INTERFACE_MODE_10GBASER, supported); + } else { + /* From what I can tell, no 10g macs support RGMII. */ + phy_interface_set_rgmii(supported); + __set_bit(PHY_INTERFACE_MODE_MII, supported); + } + + capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10 | MAC_100; + capabilities |= MAC_1000FD | MAC_2500FD | MAC_10000FD; + + /* These SoCs don't support half duplex at all; there's no different + * FMan version or compatible, so we just have to check the machine + * compatible instead + */ + if (of_machine_is_compatible("fsl,ls1043a") || + of_machine_is_compatible("fsl,ls1046a") || + of_machine_is_compatible("fsl,B4QDS")) + capabilities &= ~(MAC_10HD | MAC_100HD); + + mac_dev->phylink_config.mac_capabilities = capabilities; + + /* The T2080 and T4240 don't support half duplex RGMII. There is no + * other way to identify these SoCs, so just use the machine + * compatible. + */ + if (of_machine_is_compatible("fsl,T2080QDS") || + of_machine_is_compatible("fsl,T2080RDB") || + of_machine_is_compatible("fsl,T2081QDS") || + of_machine_is_compatible("fsl,T4240QDS") || + of_machine_is_compatible("fsl,T4240RDB")) + memac->rgmii_no_half_duplex = true; + + /* Most boards should use MLO_AN_INBAND, but existing boards don't have + * a managed property. Default to MLO_AN_INBAND if nothing else is + * specified. We need to be careful and not enable this if we have a + * fixed link or if we are using MII or RGMII, since those + * configurations modes don't use in-band autonegotiation. + */ + fixed = of_get_child_by_name(mac_node, "fixed-link"); + if (!fixed && !of_property_read_bool(mac_node, "fixed-link") && + !of_property_read_bool(mac_node, "managed") && + mac_dev->phy_if != PHY_INTERFACE_MODE_MII && + !phy_interface_mode_is_rgmii(mac_dev->phy_if)) + mac_dev->phylink_config.ovr_an_inband = true; + of_node_put(fixed); + err = memac_init(mac_dev->fman_mac); if (err < 0) - goto _return_fixed_link_free; + goto _return_fm_mac_free; dev_info(mac_dev->dev, "FMan MEMAC\n"); - goto _return; + return 0; -_return_fixed_link_free: - kfree(fixed_link); _return_fm_mac_free: memac_free(mac_dev->fman_mac); -_return: return err; } diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 5a4be54ad459..c2261d26db5b 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -13,6 +13,7 @@ #include <linux/bitrev.h> #include <linux/io.h> #include <linux/crc32.h> +#include <linux/netdevice.h> /* Transmit Inter-Packet Gap Length Register (TX_IPG_LENGTH) */ #define TGEC_TX_IPG_LENGTH_MASK 0x000003ff @@ -243,10 +244,6 @@ static int init(struct tgec_regs __iomem *regs, struct tgec_cfg *cfg, static int check_init_parameters(struct fman_mac *tgec) { - if (tgec->max_speed < SPEED_10000) { - pr_err("10G MAC driver only support 10G speed\n"); - return -EINVAL; - } if (!tgec->exception_cb) { pr_err("uninitialized exception_cb\n"); return -EINVAL; @@ -384,40 +381,13 @@ static void free_init_resources(struct fman_mac *tgec) tgec->unicast_addr_hash = NULL; } -static bool is_init_done(struct tgec_cfg *cfg) -{ - /* Checks if tGEC driver parameters were initialized */ - if (!cfg) - return true; - - return false; -} - static int tgec_enable(struct fman_mac *tgec) { - struct tgec_regs __iomem *regs = tgec->regs; - u32 tmp; - - if (!is_init_done(tgec->cfg)) - return -EINVAL; - - tmp = ioread32be(®s->command_config); - tmp |= CMD_CFG_RX_EN | CMD_CFG_TX_EN; - iowrite32be(tmp, ®s->command_config); - return 0; } static void tgec_disable(struct fman_mac *tgec) { - struct tgec_regs __iomem *regs = tgec->regs; - u32 tmp; - - WARN_ON_ONCE(!is_init_done(tgec->cfg)); - - tmp = ioread32be(®s->command_config); - tmp &= ~(CMD_CFG_RX_EN | CMD_CFG_TX_EN); - iowrite32be(tmp, ®s->command_config); } static int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val) @@ -425,9 +395,6 @@ static int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val) struct tgec_regs __iomem *regs = tgec->regs; u32 tmp; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - tmp = ioread32be(®s->command_config); if (new_val) tmp |= CMD_CFG_PROMIS_EN; @@ -444,9 +411,6 @@ static int tgec_set_tx_pause_frames(struct fman_mac *tgec, { struct tgec_regs __iomem *regs = tgec->regs; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - iowrite32be((u32)pause_time, ®s->pause_quant); return 0; @@ -457,9 +421,6 @@ static int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) struct tgec_regs __iomem *regs = tgec->regs; u32 tmp; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - tmp = ioread32be(®s->command_config); if (!en) tmp |= CMD_CFG_PAUSE_IGNORE; @@ -470,12 +431,52 @@ static int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) return 0; } +static void tgec_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ +} + +static void tgec_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) +{ + struct mac_device *mac_dev = fman_config_to_mac(config); + struct fman_mac *tgec = mac_dev->fman_mac; + struct tgec_regs __iomem *regs = tgec->regs; + u16 pause_time = tx_pause ? FSL_FM_PAUSE_TIME_ENABLE : + FSL_FM_PAUSE_TIME_DISABLE; + u32 tmp; + + tgec_set_tx_pause_frames(tgec, 0, pause_time, 0); + tgec_accept_rx_pause_frames(tgec, rx_pause); + mac_dev->update_speed(mac_dev, speed); + + tmp = ioread32be(®s->command_config); + tmp |= CMD_CFG_RX_EN | CMD_CFG_TX_EN; + iowrite32be(tmp, ®s->command_config); +} + +static void tgec_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct fman_mac *tgec = fman_config_to_mac(config)->fman_mac; + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + tmp = ioread32be(®s->command_config); + tmp &= ~(CMD_CFG_RX_EN | CMD_CFG_TX_EN); + iowrite32be(tmp, ®s->command_config); +} + +static const struct phylink_mac_ops tgec_mac_ops = { + .mac_config = tgec_mac_config, + .mac_link_up = tgec_link_up, + .mac_link_down = tgec_link_down, +}; + static int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *p_enet_addr) { - if (!is_init_done(tgec->cfg)) - return -EINVAL; - tgec->addr = ENET_ADDR_TO_UINT64(*p_enet_addr); set_mac_address(tgec->regs, (const u8 *)(*p_enet_addr)); @@ -490,9 +491,6 @@ static int tgec_add_hash_mac_address(struct fman_mac *tgec, u32 crc = 0xFFFFFFFF, hash; u64 addr; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - addr = ENET_ADDR_TO_UINT64(*eth_addr); if (!(addr & GROUP_ADDRESS)) { @@ -525,9 +523,6 @@ static int tgec_set_allmulti(struct fman_mac *tgec, bool enable) u32 entry; struct tgec_regs __iomem *regs = tgec->regs; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - if (enable) { for (entry = 0; entry < TGEC_HASH_TABLE_SIZE; entry++) iowrite32be(entry | TGEC_HASH_MCAST_EN, @@ -548,9 +543,6 @@ static int tgec_set_tstamp(struct fman_mac *tgec, bool enable) struct tgec_regs __iomem *regs = tgec->regs; u32 tmp; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - tmp = ioread32be(®s->command_config); if (enable) @@ -572,9 +564,6 @@ static int tgec_del_hash_mac_address(struct fman_mac *tgec, u32 crc = 0xFFFFFFFF, hash; u64 addr; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - addr = ((*(u64 *)eth_addr) >> 16); /* CRC calculation */ @@ -601,22 +590,12 @@ static int tgec_del_hash_mac_address(struct fman_mac *tgec, return 0; } -static void tgec_adjust_link(struct mac_device *mac_dev) -{ - struct phy_device *phy_dev = mac_dev->phy_dev; - - mac_dev->update_speed(mac_dev, phy_dev->speed); -} - static int tgec_set_exception(struct fman_mac *tgec, enum fman_mac_exceptions exception, bool enable) { struct tgec_regs __iomem *regs = tgec->regs; u32 bit_mask = 0; - if (!is_init_done(tgec->cfg)) - return -EINVAL; - bit_mask = get_exception_flag(exception); if (bit_mask) { if (enable) @@ -641,9 +620,6 @@ static int tgec_init(struct fman_mac *tgec) enet_addr_t eth_addr; int err; - if (is_init_done(tgec->cfg)) - return -EINVAL; - if (DEFAULT_RESET_ON_INIT && (fman_reset_mac(tgec->fm, tgec->mac_id) != 0)) { pr_err("Can't reset MAC!\n"); @@ -753,7 +729,6 @@ static struct fman_mac *tgec_config(struct mac_device *mac_dev, tgec->regs = mac_dev->vaddr; tgec->addr = ENET_ADDR_TO_UINT64(mac_dev->addr); - tgec->max_speed = params->max_speed; tgec->mac_id = params->mac_id; tgec->exceptions = (TGEC_IMASK_MDIO_SCAN_EVENT | TGEC_IMASK_REM_FAULT | @@ -788,17 +763,15 @@ int tgec_initialization(struct mac_device *mac_dev, int err; struct fman_mac *tgec; + mac_dev->phylink_ops = &tgec_mac_ops; mac_dev->set_promisc = tgec_set_promiscuous; mac_dev->change_addr = tgec_modify_mac_address; mac_dev->add_hash_mac_addr = tgec_add_hash_mac_address; mac_dev->remove_hash_mac_addr = tgec_del_hash_mac_address; - mac_dev->set_tx_pause = tgec_set_tx_pause_frames; - mac_dev->set_rx_pause = tgec_accept_rx_pause_frames; mac_dev->set_exception = tgec_set_exception; mac_dev->set_allmulti = tgec_set_allmulti; mac_dev->set_tstamp = tgec_set_tstamp; mac_dev->set_multi = fman_set_multi; - mac_dev->adjust_link = tgec_adjust_link; mac_dev->enable = tgec_enable; mac_dev->disable = tgec_disable; @@ -808,6 +781,19 @@ int tgec_initialization(struct mac_device *mac_dev, goto _return; } + /* The internal connection to the serdes is XGMII, but this isn't + * really correct for the phy mode (which is the external connection). + * However, this is how all older device trees say that they want + * XAUI, so just convert it for them. + */ + if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) + mac_dev->phy_if = PHY_INTERFACE_MODE_XAUI; + + __set_bit(PHY_INTERFACE_MODE_XAUI, + mac_dev->phylink_config.supported_interfaces); + mac_dev->phylink_config.mac_capabilities = + MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10000FD; + tgec = mac_dev->fman_mac; tgec->cfg->max_frame_length = fman_get_max_frm(); err = tgec_init(tgec); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 13e67f2864be..43665806c590 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -15,6 +15,7 @@ #include <linux/phy.h> #include <linux/netdevice.h> #include <linux/phy_fixed.h> +#include <linux/phylink.h> #include <linux/etherdevice.h> #include <linux/libfdt_env.h> @@ -93,130 +94,8 @@ int fman_set_multi(struct net_device *net_dev, struct mac_device *mac_dev) return 0; } -/** - * fman_set_mac_active_pause - * @mac_dev: A pointer to the MAC device - * @rx: Pause frame setting for RX - * @tx: Pause frame setting for TX - * - * Set the MAC RX/TX PAUSE frames settings - * - * Avoid redundant calls to FMD, if the MAC driver already contains the desired - * active PAUSE settings. Otherwise, the new active settings should be reflected - * in FMan. - * - * Return: 0 on success; Error code otherwise. - */ -int fman_set_mac_active_pause(struct mac_device *mac_dev, bool rx, bool tx) -{ - struct fman_mac *fman_mac = mac_dev->fman_mac; - int err = 0; - - if (rx != mac_dev->rx_pause_active) { - err = mac_dev->set_rx_pause(fman_mac, rx); - if (likely(err == 0)) - mac_dev->rx_pause_active = rx; - } - - if (tx != mac_dev->tx_pause_active) { - u16 pause_time = (tx ? FSL_FM_PAUSE_TIME_ENABLE : - FSL_FM_PAUSE_TIME_DISABLE); - - err = mac_dev->set_tx_pause(fman_mac, 0, pause_time, 0); - - if (likely(err == 0)) - mac_dev->tx_pause_active = tx; - } - - return err; -} -EXPORT_SYMBOL(fman_set_mac_active_pause); - -/** - * fman_get_pause_cfg - * @mac_dev: A pointer to the MAC device - * @rx_pause: Return value for RX setting - * @tx_pause: Return value for TX setting - * - * Determine the MAC RX/TX PAUSE frames settings based on PHY - * autonegotiation or values set by eththool. - * - * Return: Pointer to FMan device. - */ -void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, - bool *tx_pause) -{ - struct phy_device *phy_dev = mac_dev->phy_dev; - u16 lcl_adv, rmt_adv; - u8 flowctrl; - - *rx_pause = *tx_pause = false; - - if (!phy_dev->duplex) - return; - - /* If PAUSE autonegotiation is disabled, the TX/RX PAUSE settings - * are those set by ethtool. - */ - if (!mac_dev->autoneg_pause) { - *rx_pause = mac_dev->rx_pause_req; - *tx_pause = mac_dev->tx_pause_req; - return; - } - - /* Else if PAUSE autonegotiation is enabled, the TX/RX PAUSE - * settings depend on the result of the link negotiation. - */ - - /* get local capabilities */ - lcl_adv = linkmode_adv_to_lcl_adv_t(phy_dev->advertising); - - /* get link partner capabilities */ - rmt_adv = 0; - if (phy_dev->pause) - rmt_adv |= LPA_PAUSE_CAP; - if (phy_dev->asym_pause) - rmt_adv |= LPA_PAUSE_ASYM; - - /* Calculate TX/RX settings based on local and peer advertised - * symmetric/asymmetric PAUSE capabilities. - */ - flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); - if (flowctrl & FLOW_CTRL_RX) - *rx_pause = true; - if (flowctrl & FLOW_CTRL_TX) - *tx_pause = true; -} -EXPORT_SYMBOL(fman_get_pause_cfg); - -#define DTSEC_SUPPORTED \ - (SUPPORTED_10baseT_Half \ - | SUPPORTED_10baseT_Full \ - | SUPPORTED_100baseT_Half \ - | SUPPORTED_100baseT_Full \ - | SUPPORTED_Autoneg \ - | SUPPORTED_Pause \ - | SUPPORTED_Asym_Pause \ - | SUPPORTED_FIBRE \ - | SUPPORTED_MII) - static DEFINE_MUTEX(eth_lock); -static const u16 phy2speed[] = { - [PHY_INTERFACE_MODE_MII] = SPEED_100, - [PHY_INTERFACE_MODE_GMII] = SPEED_1000, - [PHY_INTERFACE_MODE_SGMII] = SPEED_1000, - [PHY_INTERFACE_MODE_TBI] = SPEED_1000, - [PHY_INTERFACE_MODE_RMII] = SPEED_100, - [PHY_INTERFACE_MODE_RGMII] = SPEED_1000, - [PHY_INTERFACE_MODE_RGMII_ID] = SPEED_1000, - [PHY_INTERFACE_MODE_RGMII_RXID] = SPEED_1000, - [PHY_INTERFACE_MODE_RGMII_TXID] = SPEED_1000, - [PHY_INTERFACE_MODE_RTBI] = SPEED_1000, - [PHY_INTERFACE_MODE_QSGMII] = SPEED_1000, - [PHY_INTERFACE_MODE_XGMII] = SPEED_10000 -}; - static struct platform_device *dpaa_eth_add_device(int fman_id, struct mac_device *mac_dev) { @@ -263,8 +142,8 @@ no_mem: } static const struct of_device_id mac_match[] = { - { .compatible = "fsl,fman-dtsec", .data = dtsec_initialization }, - { .compatible = "fsl,fman-xgec", .data = tgec_initialization }, + { .compatible = "fsl,fman-dtsec", .data = dtsec_initialization }, + { .compatible = "fsl,fman-xgec", .data = tgec_initialization }, { .compatible = "fsl,fman-memac", .data = memac_initialization }, {} }; @@ -295,6 +174,7 @@ static int mac_probe(struct platform_device *_of_dev) priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + platform_set_drvdata(_of_dev, mac_dev); /* Save private information */ mac_dev->priv = priv; @@ -424,57 +304,21 @@ static int mac_probe(struct platform_device *_of_dev) } mac_dev->phy_if = phy_if; - priv->speed = phy2speed[mac_dev->phy_if]; - params.max_speed = priv->speed; - mac_dev->if_support = DTSEC_SUPPORTED; - /* We don't support half-duplex in SGMII mode */ - if (mac_dev->phy_if == PHY_INTERFACE_MODE_SGMII) - mac_dev->if_support &= ~(SUPPORTED_10baseT_Half | - SUPPORTED_100baseT_Half); - - /* Gigabit support (no half-duplex) */ - if (params.max_speed == 1000) - mac_dev->if_support |= SUPPORTED_1000baseT_Full; - - /* The 10G interface only supports one mode */ - if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) - mac_dev->if_support = SUPPORTED_10000baseT_Full; - - /* Get the rest of the PHY information */ - mac_dev->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); - - params.basex_if = false; params.mac_id = priv->cell_index; params.fm = (void *)priv->fman; params.exception_cb = mac_exception; params.event_cb = mac_exception; err = init(mac_dev, mac_node, ¶ms); - if (err < 0) { - dev_err(dev, "mac_dev->init() = %d\n", err); - of_node_put(mac_dev->phy_node); - return err; - } - - /* pause frame autonegotiation enabled */ - mac_dev->autoneg_pause = true; - - /* By intializing the values to false, force FMD to enable PAUSE frames - * on RX and TX - */ - mac_dev->rx_pause_req = true; - mac_dev->tx_pause_req = true; - mac_dev->rx_pause_active = false; - mac_dev->tx_pause_active = false; - err = fman_set_mac_active_pause(mac_dev, true, true); if (err < 0) - dev_err(dev, "fman_set_mac_active_pause() = %d\n", err); + return err; if (!is_zero_ether_addr(mac_dev->addr)) dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr); priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev); if (IS_ERR(priv->eth_dev)) { + err = PTR_ERR(priv->eth_dev); dev_err(dev, "failed to add Ethernet platform device for MAC %d\n", priv->cell_index); priv->eth_dev = NULL; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 13b69ca5f00c..ad06f8d7924b 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/if_ether.h> #include <linux/phy.h> +#include <linux/phylink.h> #include <linux/list.h> #include "fman_port.h" @@ -24,32 +25,22 @@ struct mac_device { struct resource *res; u8 addr[ETH_ALEN]; struct fman_port *port[2]; - u32 if_support; - struct phy_device *phy_dev; + struct phylink *phylink; + struct phylink_config phylink_config; phy_interface_t phy_if; - struct device_node *phy_node; - struct net_device *net_dev; - bool autoneg_pause; - bool rx_pause_req; - bool tx_pause_req; - bool rx_pause_active; - bool tx_pause_active; bool promisc; bool allmulti; + const struct phylink_mac_ops *phylink_ops; int (*enable)(struct fman_mac *mac_dev); void (*disable)(struct fman_mac *mac_dev); - void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, const enet_addr_t *enet_addr); int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_tstamp)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, struct mac_device *mac_dev); - int (*set_rx_pause)(struct fman_mac *mac_dev, bool en); - int (*set_tx_pause)(struct fman_mac *mac_dev, u8 priority, - u16 pause_time, u16 thresh_time); int (*set_exception)(struct fman_mac *mac_dev, enum fman_mac_exceptions exception, bool enable); int (*add_hash_mac_addr)(struct fman_mac *mac_dev, @@ -63,6 +54,12 @@ struct mac_device { struct mac_priv_s *priv; }; +static inline struct mac_device +*fman_config_to_mac(struct phylink_config *config) +{ + return container_of(config, struct mac_device, phylink_config); +} + struct dpaa_eth_data { struct mac_device *mac_dev; int mac_hw_id; diff --git a/drivers/net/ethernet/fungible/funeth/funeth_devlink.c b/drivers/net/ethernet/fungible/funeth/funeth_devlink.c index d50c222948b4..4fbeb3fd71a8 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_devlink.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_devlink.c @@ -3,14 +3,7 @@ #include "funeth.h" #include "funeth_devlink.h" -static int fun_dl_info_get(struct devlink *dl, struct devlink_info_req *req, - struct netlink_ext_ack *extack) -{ - return devlink_info_driver_name_put(req, KBUILD_MODNAME); -} - static const struct devlink_ops fun_dl_ops = { - .info_get = fun_dl_info_get, }; struct devlink *fun_devlink_alloc(struct device *dev) diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c index 095f51c4d9d9..b4cce30e526a 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_main.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c @@ -1178,13 +1178,6 @@ static int fun_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static struct devlink_port *fun_get_devlink_port(struct net_device *netdev) -{ - struct funeth_priv *fp = netdev_priv(netdev); - - return &fp->dl_port; -} - static int fun_init_vports(struct fun_ethdev *ed, unsigned int n) { if (ed->num_vports) @@ -1350,7 +1343,6 @@ static const struct net_device_ops fun_netdev_ops = { .ndo_set_vf_vlan = fun_set_vf_vlan, .ndo_set_vf_rate = fun_set_vf_rate, .ndo_get_vf_config = fun_get_vf_config, - .ndo_get_devlink_port = fun_get_devlink_port, }; #define GSO_ENCAP_FLAGS (NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | \ @@ -1760,6 +1752,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid) goto free_rss; SET_NETDEV_DEV(netdev, fdev->dev); + SET_NETDEV_DEVLINK_PORT(netdev, &fp->dl_port); netdev->netdev_ops = &fun_netdev_ops; netdev->hw_features = NETIF_F_SG | NETIF_F_RXHASH | NETIF_F_RXCSUM; @@ -1800,9 +1793,6 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid) rc = register_netdev(netdev); if (rc) goto unreg_devlink; - - devlink_port_type_eth_set(&fp->dl_port, netdev); - return 0; unreg_devlink: @@ -1827,7 +1817,6 @@ static void fun_destroy_netdev(struct net_device *netdev) struct funeth_priv *fp; fp = netdev_priv(netdev); - devlink_port_type_clear(&fp->dl_port); unregister_netdev(netdev); devlink_port_unregister(&fp->dl_port); fun_ktls_cleanup(fp); diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h index 671f51135c26..53b7e95213a8 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h +++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h @@ -206,9 +206,9 @@ struct funeth_rxq { #define FUN_QSTAT_READ(q, seq, stats_copy) \ do { \ - seq = u64_stats_fetch_begin_irq(&(q)->syncp); \ + seq = u64_stats_fetch_begin(&(q)->syncp); \ stats_copy = (q)->stats; \ - } while (u64_stats_fetch_retry_irq(&(q)->syncp, (seq))) + } while (u64_stats_fetch_retry(&(q)->syncp, (seq))) #define FUN_INT_NAME_LEN (IFNAMSIZ + 16) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 160735484465..64eb0442c82f 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -60,7 +60,8 @@ struct gve_rx_slot_page_info { void *page_address; u32 page_offset; /* offset to write to in page */ int pagecnt_bias; /* expected pagecnt if only the driver has a ref */ - u8 can_flip; + u16 pad; /* adjustment for rx padding */ + u8 can_flip; /* tracks if the networking stack is using the page */ }; /* A list of pages registered with the device during setup and used by a queue @@ -149,10 +150,17 @@ struct gve_rx_ctx { /* head and tail of skb chain for the current packet or NULL if none */ struct sk_buff *skb_head; struct sk_buff *skb_tail; - u16 total_expected_size; - u8 expected_frag_cnt; - u8 curr_frag_cnt; - u8 reuse_frags; + u32 total_size; + u8 frag_cnt; + bool drop_pkt; +}; + +struct gve_rx_cnts { + u32 ok_pkt_bytes; + u16 ok_pkt_cnt; + u16 total_pkt_cnt; + u16 cont_pkt_cnt; + u16 desc_err_pkt_cnt; }; /* Contains datapath state used to represent an RX queue. */ @@ -167,6 +175,10 @@ struct gve_rx_ring { /* threshold for posting new buffs and descs */ u32 db_threshold; u16 packet_buffer_size; + + u32 qpl_copy_pool_mask; + u32 qpl_copy_pool_head; + struct gve_rx_slot_page_info *qpl_copy_pool; }; /* DQO fields. */ @@ -216,7 +228,9 @@ struct gve_rx_ring { u64 rx_desc_err_dropped_pkt; /* free-running count of packets dropped by descriptor error */ u64 rx_cont_packet_cnt; /* free-running multi-fragment packets received */ u64 rx_frag_flip_cnt; /* free-running count of rx segments where page_flip was used */ - u64 rx_frag_copy_cnt; /* free-running count of rx segments copied into skb linear portion */ + u64 rx_frag_copy_cnt; /* free-running count of rx segments copied */ + u64 rx_frag_alloc_cnt; /* free-running count of rx page allocations */ + u32 q_num; /* queue index */ u32 ntfy_id; /* notification block index */ struct gve_queue_resources *q_resources; /* head and tail pointer idx */ @@ -549,6 +563,7 @@ struct gve_priv { u32 adminq_report_stats_cnt; u32 adminq_report_link_speed_cnt; u32 adminq_get_ptype_map_cnt; + u32 adminq_verify_driver_compatibility_cnt; /* Global stats */ u32 interface_up_cnt; /* count of times interface turned up since last reset */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index f7621ab672b9..60061288ad9d 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -289,7 +289,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) case GVE_ADMINQ_COMMAND_ERROR_RESOURCE_EXHAUSTED: return -ENOMEM; case GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED: - return -ENOTSUPP; + return -EOPNOTSUPP; default: dev_err(&priv->pdev->dev, "parse_aq_err: unknown status code %d\n", status); return -EINVAL; @@ -407,6 +407,9 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_GET_PTYPE_MAP: priv->adminq_get_ptype_map_cnt++; break; + case GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY: + priv->adminq_verify_driver_compatibility_cnt++; + break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } @@ -878,6 +881,22 @@ int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, return gve_adminq_execute_cmd(priv, &cmd); } +int gve_adminq_verify_driver_compatibility(struct gve_priv *priv, + u64 driver_info_len, + dma_addr_t driver_info_addr) +{ + union gve_adminq_command cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY); + cmd.verify_driver_compatibility = (struct gve_adminq_verify_driver_compatibility) { + .driver_info_len = cpu_to_be64(driver_info_len), + .driver_info_addr = cpu_to_be64(driver_info_addr), + }; + + return gve_adminq_execute_cmd(priv, &cmd); +} + int gve_adminq_report_link_speed(struct gve_priv *priv) { union gve_adminq_command gvnic_cmd; diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 83c0b40cd2d9..cf29662e6ad1 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -24,6 +24,7 @@ enum gve_adminq_opcodes { GVE_ADMINQ_REPORT_STATS = 0xC, GVE_ADMINQ_REPORT_LINK_SPEED = 0xD, GVE_ADMINQ_GET_PTYPE_MAP = 0xE, + GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY = 0xF, }; /* Admin queue status codes */ @@ -146,6 +147,51 @@ enum gve_sup_feature_mask { #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 +#define GVE_VERSION_STR_LEN 128 + +enum gve_driver_capbility { + gve_driver_capability_gqi_qpl = 0, + gve_driver_capability_gqi_rda = 1, + gve_driver_capability_dqo_qpl = 2, /* reserved for future use */ + gve_driver_capability_dqo_rda = 3, + gve_driver_capability_alt_miss_compl = 4, +}; + +#define GVE_CAP1(a) BIT((int)a) +#define GVE_CAP2(a) BIT(((int)a) - 64) +#define GVE_CAP3(a) BIT(((int)a) - 128) +#define GVE_CAP4(a) BIT(((int)a) - 192) + +#define GVE_DRIVER_CAPABILITY_FLAGS1 \ + (GVE_CAP1(gve_driver_capability_gqi_qpl) | \ + GVE_CAP1(gve_driver_capability_gqi_rda) | \ + GVE_CAP1(gve_driver_capability_dqo_rda) | \ + GVE_CAP1(gve_driver_capability_alt_miss_compl)) + +#define GVE_DRIVER_CAPABILITY_FLAGS2 0x0 +#define GVE_DRIVER_CAPABILITY_FLAGS3 0x0 +#define GVE_DRIVER_CAPABILITY_FLAGS4 0x0 + +struct gve_driver_info { + u8 os_type; /* 0x01 = Linux */ + u8 driver_major; + u8 driver_minor; + u8 driver_sub; + __be32 os_version_major; + __be32 os_version_minor; + __be32 os_version_sub; + __be64 driver_capability_flags[4]; + u8 os_version_str1[GVE_VERSION_STR_LEN]; + u8 os_version_str2[GVE_VERSION_STR_LEN]; +}; + +struct gve_adminq_verify_driver_compatibility { + __be64 driver_info_len; + __be64 driver_info_addr; +}; + +static_assert(sizeof(struct gve_adminq_verify_driver_compatibility) == 16); + struct gve_adminq_configure_device_resources { __be64 counter_array; __be64 irq_db_addr; @@ -345,6 +391,8 @@ union gve_adminq_command { struct gve_adminq_report_stats report_stats; struct gve_adminq_report_link_speed report_link_speed; struct gve_adminq_get_ptype_map get_ptype_map; + struct gve_adminq_verify_driver_compatibility + verify_driver_compatibility; }; }; u8 reserved[64]; @@ -372,6 +420,9 @@ int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id); int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu); int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval); +int gve_adminq_verify_driver_compatibility(struct gve_priv *priv, + u64 driver_info_len, + dma_addr_t driver_info_addr); int gve_adminq_report_link_speed(struct gve_priv *priv); struct gve_ptype_lut; diff --git a/drivers/net/ethernet/google/gve/gve_desc_dqo.h b/drivers/net/ethernet/google/gve/gve_desc_dqo.h index e8fe9adef7f2..f79cd0591110 100644 --- a/drivers/net/ethernet/google/gve/gve_desc_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_desc_dqo.h @@ -176,6 +176,11 @@ static_assert(sizeof(struct gve_tx_compl_desc) == 8); #define GVE_COMPL_TYPE_DQO_MISS 0x1 /* Miss path completion */ #define GVE_COMPL_TYPE_DQO_REINJECTION 0x3 /* Re-injection completion */ +/* The most significant bit in the completion tag can change the completion + * type from packet completion to miss path completion. + */ +#define GVE_ALT_MISS_COMPL_BIT BIT(15) + /* Descriptor to post buffers to HW on buffer queue. */ struct gve_rx_desc_dqo { __le16 buf_id; /* ID returned in Rx completion descriptor */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 7b9a2d9d9624..ce574d097e28 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -45,6 +45,7 @@ static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = { static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_consumed_desc[%u]", "rx_bytes[%u]", "rx_cont_packet_cnt[%u]", "rx_frag_flip_cnt[%u]", "rx_frag_copy_cnt[%u]", + "rx_frag_alloc_cnt[%u]", "rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]", "rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]", "rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]", @@ -177,14 +178,14 @@ gve_get_ethtool_stats(struct net_device *netdev, struct gve_rx_ring *rx = &priv->rx[ring]; start = - u64_stats_fetch_begin_irq(&priv->rx[ring].statss); + u64_stats_fetch_begin(&priv->rx[ring].statss); tmp_rx_pkts = rx->rpackets; tmp_rx_bytes = rx->rbytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; - } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; rx_bytes += tmp_rx_bytes; @@ -198,10 +199,10 @@ gve_get_ethtool_stats(struct net_device *netdev, if (priv->tx) { do { start = - u64_stats_fetch_begin_irq(&priv->tx[ring].statss); + u64_stats_fetch_begin(&priv->tx[ring].statss); tmp_tx_pkts = priv->tx[ring].pkt_done; tmp_tx_bytes = priv->tx[ring].bytes_done; - } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry(&priv->tx[ring].statss, start)); tx_pkts += tmp_tx_pkts; tx_bytes += tmp_tx_bytes; @@ -259,18 +260,19 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx->fill_cnt - rx->cnt; do { start = - u64_stats_fetch_begin_irq(&priv->rx[ring].statss); + u64_stats_fetch_begin(&priv->rx[ring].statss); tmp_rx_bytes = rx->rbytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; - } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; data[i++] = rx->rx_cont_packet_cnt; data[i++] = rx->rx_frag_flip_cnt; data[i++] = rx->rx_frag_copy_cnt; + data[i++] = rx->rx_frag_alloc_cnt; /* rx dropped packets */ data[i++] = tmp_rx_skb_alloc_fail + tmp_rx_buf_alloc_fail + @@ -331,9 +333,9 @@ gve_get_ethtool_stats(struct net_device *netdev, } do { start = - u64_stats_fetch_begin_irq(&priv->tx[ring].statss); + u64_stats_fetch_begin(&priv->tx[ring].statss); tmp_tx_bytes = tx->bytes_done; - } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry(&priv->tx[ring].statss, start)); data[i++] = tmp_tx_bytes; data[i++] = tx->wake_queue; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index d3e3ac242bfc..5b40f9c53196 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -12,6 +12,8 @@ #include <linux/sched.h> #include <linux/timer.h> #include <linux/workqueue.h> +#include <linux/utsname.h> +#include <linux/version.h> #include <net/sch_generic.h> #include "gve.h" #include "gve_dqo.h" @@ -30,6 +32,49 @@ const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; +static int gve_verify_driver_compatibility(struct gve_priv *priv) +{ + int err; + struct gve_driver_info *driver_info; + dma_addr_t driver_info_bus; + + driver_info = dma_alloc_coherent(&priv->pdev->dev, + sizeof(struct gve_driver_info), + &driver_info_bus, GFP_KERNEL); + if (!driver_info) + return -ENOMEM; + + *driver_info = (struct gve_driver_info) { + .os_type = 1, /* Linux */ + .os_version_major = cpu_to_be32(LINUX_VERSION_MAJOR), + .os_version_minor = cpu_to_be32(LINUX_VERSION_SUBLEVEL), + .os_version_sub = cpu_to_be32(LINUX_VERSION_PATCHLEVEL), + .driver_capability_flags = { + cpu_to_be64(GVE_DRIVER_CAPABILITY_FLAGS1), + cpu_to_be64(GVE_DRIVER_CAPABILITY_FLAGS2), + cpu_to_be64(GVE_DRIVER_CAPABILITY_FLAGS3), + cpu_to_be64(GVE_DRIVER_CAPABILITY_FLAGS4), + }, + }; + strscpy(driver_info->os_version_str1, utsname()->release, + sizeof(driver_info->os_version_str1)); + strscpy(driver_info->os_version_str2, utsname()->version, + sizeof(driver_info->os_version_str2)); + + err = gve_adminq_verify_driver_compatibility(priv, + sizeof(struct gve_driver_info), + driver_info_bus); + + /* It's ok if the device doesn't support this */ + if (err == -EOPNOTSUPP) + err = 0; + + dma_free_coherent(&priv->pdev->dev, + sizeof(struct gve_driver_info), + driver_info, driver_info_bus); + return err; +} + static netdev_tx_t gve_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct gve_priv *priv = netdev_priv(dev); @@ -51,10 +96,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { do { start = - u64_stats_fetch_begin_irq(&priv->rx[ring].statss); + u64_stats_fetch_begin(&priv->rx[ring].statss); packets = priv->rx[ring].rpackets; bytes = priv->rx[ring].rbytes; - } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); s->rx_packets += packets; s->rx_bytes += bytes; @@ -64,10 +109,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { do { start = - u64_stats_fetch_begin_irq(&priv->tx[ring].statss); + u64_stats_fetch_begin(&priv->tx[ring].statss); packets = priv->tx[ring].pkt_done; bytes = priv->tx[ring].bytes_done; - } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry(&priv->tx[ring].statss, start)); s->tx_packets += packets; s->tx_bytes += bytes; @@ -1273,9 +1318,9 @@ void gve_handle_report_stats(struct gve_priv *priv) } do { - start = u64_stats_fetch_begin_irq(&priv->tx[idx].statss); + start = u64_stats_fetch_begin(&priv->tx[idx].statss); tx_bytes = priv->tx[idx].bytes_done; - } while (u64_stats_fetch_retry_irq(&priv->tx[idx].statss, start)); + } while (u64_stats_fetch_retry(&priv->tx[idx].statss, start)); stats[stats_idx++] = (struct stats) { .stat_name = cpu_to_be32(TX_WAKE_CNT), .value = cpu_to_be64(priv->tx[idx].wake_queue), @@ -1368,6 +1413,13 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) return err; } + err = gve_verify_driver_compatibility(priv); + if (err) { + dev_err(&priv->pdev->dev, + "Could not verify driver compatibility: err=%d\n", err); + goto err; + } + if (skip_describe_device) goto setup_device; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 021bbf308d68..1f55137722b0 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -35,6 +35,12 @@ static void gve_rx_unfill_pages(struct gve_priv *priv, struct gve_rx_ring *rx) rx->data.page_info[i].pagecnt_bias - 1); gve_unassign_qpl(priv, rx->data.qpl->id); rx->data.qpl = NULL; + + for (i = 0; i < rx->qpl_copy_pool_mask + 1; i++) { + page_ref_sub(rx->qpl_copy_pool[i].page, + rx->qpl_copy_pool[i].pagecnt_bias - 1); + put_page(rx->qpl_copy_pool[i].page); + } } kvfree(rx->data.page_info); rx->data.page_info = NULL; @@ -63,6 +69,10 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) dma_free_coherent(dev, bytes, rx->data.data_ring, rx->data.data_bus); rx->data.data_ring = NULL; + + kvfree(rx->qpl_copy_pool); + rx->qpl_copy_pool = NULL; + netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx); } @@ -101,6 +111,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) u32 slots; int err; int i; + int j; /* Allocate one page per Rx queue slot. Each page is split into two * packet buffers, when possible we "page flip" between the two. @@ -135,7 +146,33 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) goto alloc_err; } + if (!rx->data.raw_addressing) { + for (j = 0; j < rx->qpl_copy_pool_mask + 1; j++) { + struct page *page = alloc_page(GFP_KERNEL); + + if (!page) { + err = -ENOMEM; + goto alloc_err_qpl; + } + + rx->qpl_copy_pool[j].page = page; + rx->qpl_copy_pool[j].page_offset = 0; + rx->qpl_copy_pool[j].page_address = page_address(page); + + /* The page already has 1 ref. */ + page_ref_add(page, INT_MAX - 1); + rx->qpl_copy_pool[j].pagecnt_bias = INT_MAX; + } + } + return slots; + +alloc_err_qpl: + while (j--) { + page_ref_sub(rx->qpl_copy_pool[j].page, + rx->qpl_copy_pool[j].pagecnt_bias - 1); + put_page(rx->qpl_copy_pool[j].page); + } alloc_err: while (i--) gve_rx_free_buffer(&priv->pdev->dev, @@ -146,12 +183,11 @@ alloc_err: static void gve_rx_ctx_clear(struct gve_rx_ctx *ctx) { - ctx->curr_frag_cnt = 0; - ctx->total_expected_size = 0; - ctx->expected_frag_cnt = 0; ctx->skb_head = NULL; ctx->skb_tail = NULL; - ctx->reuse_frags = false; + ctx->total_size = 0; + ctx->frag_cnt = 0; + ctx->drop_pkt = false; } static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) @@ -181,10 +217,22 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) GFP_KERNEL); if (!rx->data.data_ring) return -ENOMEM; + + rx->qpl_copy_pool_mask = min_t(u32, U32_MAX, slots * 2) - 1; + rx->qpl_copy_pool_head = 0; + rx->qpl_copy_pool = kvcalloc(rx->qpl_copy_pool_mask + 1, + sizeof(rx->qpl_copy_pool[0]), + GFP_KERNEL); + + if (!rx->qpl_copy_pool) { + err = -ENOMEM; + goto abort_with_slots; + } + filled_pages = gve_prefill_rx_pages(rx); if (filled_pages < 0) { err = -ENOMEM; - goto abort_with_slots; + goto abort_with_copy_pool; } rx->fill_cnt = filled_pages; /* Ensure data ring slots (packet buffers) are visible. */ @@ -236,6 +284,9 @@ abort_with_q_resources: rx->q_resources = NULL; abort_filled: gve_rx_unfill_pages(priv, rx); +abort_with_copy_pool: + kvfree(rx->qpl_copy_pool); + rx->qpl_copy_pool = NULL; abort_with_slots: bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(hdev, bytes, rx->data.data_ring, rx->data.data_bus); @@ -292,30 +343,47 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) return PKT_HASH_TYPE_L2; } -static u16 gve_rx_ctx_padding(struct gve_rx_ctx *ctx) -{ - return (ctx->curr_frag_cnt == 0) ? GVE_RX_PAD : 0; -} - static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 packet_buffer_size, u16 len, struct gve_rx_ctx *ctx) { - u32 offset = page_info->page_offset + gve_rx_ctx_padding(ctx); - struct sk_buff *skb; + u32 offset = page_info->page_offset + page_info->pad; + struct sk_buff *skb = ctx->skb_tail; + int num_frags = 0; - if (!ctx->skb_head) - ctx->skb_head = napi_get_frags(napi); + if (!skb) { + skb = napi_get_frags(napi); + if (unlikely(!skb)) + return NULL; - if (unlikely(!ctx->skb_head)) - return NULL; + ctx->skb_head = skb; + ctx->skb_tail = skb; + } else { + num_frags = skb_shinfo(ctx->skb_tail)->nr_frags; + if (num_frags == MAX_SKB_FRAGS) { + skb = napi_alloc_skb(napi, 0); + if (!skb) + return NULL; - skb = ctx->skb_head; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page_info->page, + // We will never chain more than two SKBs: 2 * 16 * 2k > 64k + // which is why we do not need to chain by using skb->next + skb_shinfo(ctx->skb_tail)->frag_list = skb; + + ctx->skb_tail = skb; + num_frags = 0; + } + } + + if (skb != ctx->skb_head) { + ctx->skb_head->len += len; + ctx->skb_head->data_len += len; + ctx->skb_head->truesize += packet_buffer_size; + } + skb_add_rx_frag(skb, num_frags, page_info->page, offset, len, packet_buffer_size); - return skb; + return ctx->skb_head; } static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *slot_addr) @@ -363,6 +431,92 @@ gve_rx_raw_addressing(struct device *dev, struct net_device *netdev, return skb; } +static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx, + struct gve_rx_slot_page_info *page_info, + u16 len, struct napi_struct *napi) +{ + u32 pool_idx = rx->qpl_copy_pool_head & rx->qpl_copy_pool_mask; + void *src = page_info->page_address + page_info->page_offset; + struct gve_rx_slot_page_info *copy_page_info; + struct gve_rx_ctx *ctx = &rx->ctx; + bool alloc_page = false; + struct sk_buff *skb; + void *dst; + + copy_page_info = &rx->qpl_copy_pool[pool_idx]; + if (!copy_page_info->can_flip) { + int recycle = gve_rx_can_recycle_buffer(copy_page_info); + + if (unlikely(recycle < 0)) { + gve_schedule_reset(rx->gve); + return NULL; + } + alloc_page = !recycle; + } + + if (alloc_page) { + struct gve_rx_slot_page_info alloc_page_info; + struct page *page; + + /* The least recently used page turned out to be + * still in use by the kernel. Ignoring it and moving + * on alleviates head-of-line blocking. + */ + rx->qpl_copy_pool_head++; + + page = alloc_page(GFP_ATOMIC); + if (!page) + return NULL; + + alloc_page_info.page = page; + alloc_page_info.page_offset = 0; + alloc_page_info.page_address = page_address(page); + alloc_page_info.pad = page_info->pad; + + memcpy(alloc_page_info.page_address, src, page_info->pad + len); + skb = gve_rx_add_frags(napi, &alloc_page_info, + rx->packet_buffer_size, + len, ctx); + + u64_stats_update_begin(&rx->statss); + rx->rx_frag_copy_cnt++; + rx->rx_frag_alloc_cnt++; + u64_stats_update_end(&rx->statss); + + return skb; + } + + dst = copy_page_info->page_address + copy_page_info->page_offset; + memcpy(dst, src, page_info->pad + len); + copy_page_info->pad = page_info->pad; + + skb = gve_rx_add_frags(napi, copy_page_info, + rx->packet_buffer_size, len, ctx); + if (unlikely(!skb)) + return NULL; + + gve_dec_pagecnt_bias(copy_page_info); + copy_page_info->page_offset += rx->packet_buffer_size; + copy_page_info->page_offset &= (PAGE_SIZE - 1); + + if (copy_page_info->can_flip) { + /* We have used both halves of this copy page, it + * is time for it to go to the back of the queue. + */ + copy_page_info->can_flip = false; + rx->qpl_copy_pool_head++; + prefetch(rx->qpl_copy_pool[rx->qpl_copy_pool_head & rx->qpl_copy_pool_mask].page); + } else { + copy_page_info->can_flip = true; + } + + u64_stats_update_begin(&rx->statss); + rx->rx_frag_copy_cnt++; + u64_stats_update_end(&rx->statss); + + return skb; +} + static struct sk_buff * gve_rx_qpl(struct device *dev, struct net_device *netdev, struct gve_rx_ring *rx, struct gve_rx_slot_page_info *page_info, @@ -377,7 +531,7 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, * choice is to copy the data out of it so that we can return it to the * device. */ - if (ctx->reuse_frags) { + if (page_info->can_flip) { skb = gve_rx_add_frags(napi, page_info, rx->packet_buffer_size, len, ctx); /* No point in recycling if we didn't get the skb */ if (skb) { @@ -386,116 +540,23 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, gve_rx_flip_buff(page_info, &data_slot->qpl_offset); } } else { - const u16 padding = gve_rx_ctx_padding(ctx); - - skb = gve_rx_copy(netdev, napi, page_info, len, padding, ctx); - if (skb) { - u64_stats_update_begin(&rx->statss); - rx->rx_frag_copy_cnt++; - u64_stats_update_end(&rx->statss); - } + skb = gve_rx_copy_to_pool(rx, page_info, len, napi); } return skb; } -#define GVE_PKTCONT_BIT_IS_SET(x) (GVE_RXF_PKT_CONT & (x)) -static u16 gve_rx_get_fragment_size(struct gve_rx_ctx *ctx, struct gve_rx_desc *desc) -{ - return be16_to_cpu(desc->len) - gve_rx_ctx_padding(ctx); -} - -static bool gve_rx_ctx_init(struct gve_rx_ctx *ctx, struct gve_rx_ring *rx) -{ - bool qpl_mode = !rx->data.raw_addressing, packet_size_error = false; - bool buffer_error = false, desc_error = false, seqno_error = false; - struct gve_rx_slot_page_info *page_info; - struct gve_priv *priv = rx->gve; - u32 idx = rx->cnt & rx->mask; - bool reuse_frags, can_flip; - struct gve_rx_desc *desc; - u16 packet_size = 0; - u16 n_frags = 0; - int recycle; - - /** In QPL mode, we only flip buffers when all buffers containing the packet - * can be flipped. RDA can_flip decisions will be made later, per frag. - */ - can_flip = qpl_mode; - reuse_frags = can_flip; - do { - u16 frag_size; - - n_frags++; - desc = &rx->desc.desc_ring[idx]; - desc_error = unlikely(desc->flags_seq & GVE_RXF_ERR) || desc_error; - if (GVE_SEQNO(desc->flags_seq) != rx->desc.seqno) { - seqno_error = true; - netdev_warn(priv->dev, - "RX seqno error: want=%d, got=%d, dropping packet and scheduling reset.", - rx->desc.seqno, GVE_SEQNO(desc->flags_seq)); - } - frag_size = be16_to_cpu(desc->len); - packet_size += frag_size; - if (frag_size > rx->packet_buffer_size) { - packet_size_error = true; - netdev_warn(priv->dev, - "RX fragment error: packet_buffer_size=%d, frag_size=%d, dropping packet.", - rx->packet_buffer_size, be16_to_cpu(desc->len)); - } - page_info = &rx->data.page_info[idx]; - if (can_flip) { - recycle = gve_rx_can_recycle_buffer(page_info); - reuse_frags = reuse_frags && recycle > 0; - buffer_error = buffer_error || unlikely(recycle < 0); - } - idx = (idx + 1) & rx->mask; - rx->desc.seqno = gve_next_seqno(rx->desc.seqno); - } while (GVE_PKTCONT_BIT_IS_SET(desc->flags_seq)); - - prefetch(rx->desc.desc_ring + idx); - - ctx->curr_frag_cnt = 0; - ctx->total_expected_size = packet_size - GVE_RX_PAD; - ctx->expected_frag_cnt = n_frags; - ctx->skb_head = NULL; - ctx->reuse_frags = reuse_frags; - - if (ctx->expected_frag_cnt > 1) { - u64_stats_update_begin(&rx->statss); - rx->rx_cont_packet_cnt++; - u64_stats_update_end(&rx->statss); - } - if (ctx->total_expected_size > priv->rx_copybreak && !ctx->reuse_frags && qpl_mode) { - u64_stats_update_begin(&rx->statss); - rx->rx_copied_pkt++; - u64_stats_update_end(&rx->statss); - } - - if (unlikely(buffer_error || seqno_error || packet_size_error)) { - gve_schedule_reset(priv); - return false; - } - - if (unlikely(desc_error)) { - u64_stats_update_begin(&rx->statss); - rx->rx_desc_err_dropped_pkt++; - u64_stats_update_end(&rx->statss); - return false; - } - return true; -} - static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, struct gve_rx_slot_page_info *page_info, struct napi_struct *napi, - u16 len, union gve_rx_data_slot *data_slot) + u16 len, union gve_rx_data_slot *data_slot, + bool is_only_frag) { struct net_device *netdev = priv->dev; struct gve_rx_ctx *ctx = &rx->ctx; struct sk_buff *skb = NULL; - if (len <= priv->rx_copybreak && ctx->expected_frag_cnt == 1) { + if (len <= priv->rx_copybreak && is_only_frag) { /* Just copy small packets */ - skb = gve_rx_copy(netdev, napi, page_info, len, GVE_RX_PAD, ctx); + skb = gve_rx_copy(netdev, napi, page_info, len, GVE_RX_PAD); if (skb) { u64_stats_update_begin(&rx->statss); rx->rx_copied_pkt++; @@ -504,29 +565,25 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, u64_stats_update_end(&rx->statss); } } else { - if (rx->data.raw_addressing) { - int recycle = gve_rx_can_recycle_buffer(page_info); + int recycle = gve_rx_can_recycle_buffer(page_info); - if (unlikely(recycle < 0)) { - gve_schedule_reset(priv); - return NULL; - } - page_info->can_flip = recycle; - if (page_info->can_flip) { - u64_stats_update_begin(&rx->statss); - rx->rx_frag_flip_cnt++; - u64_stats_update_end(&rx->statss); - } + if (unlikely(recycle < 0)) { + gve_schedule_reset(priv); + return NULL; + } + page_info->can_flip = recycle; + if (page_info->can_flip) { + u64_stats_update_begin(&rx->statss); + rx->rx_frag_flip_cnt++; + u64_stats_update_end(&rx->statss); + } + + if (rx->data.raw_addressing) { skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev, page_info, len, napi, data_slot, rx->packet_buffer_size, ctx); } else { - if (ctx->reuse_frags) { - u64_stats_update_begin(&rx->statss); - rx->rx_frag_flip_cnt++; - u64_stats_update_end(&rx->statss); - } skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx, page_info, len, napi, data_slot); } @@ -534,101 +591,113 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, return skb; } -static bool gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, - u64 *packet_size_bytes, u32 *work_done) +#define GVE_PKTCONT_BIT_IS_SET(x) (GVE_RXF_PKT_CONT & (x)) +static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, + struct gve_rx_desc *desc, u32 idx, + struct gve_rx_cnts *cnts) { + bool is_last_frag = !GVE_PKTCONT_BIT_IS_SET(desc->flags_seq); struct gve_rx_slot_page_info *page_info; + u16 frag_size = be16_to_cpu(desc->len); struct gve_rx_ctx *ctx = &rx->ctx; union gve_rx_data_slot *data_slot; struct gve_priv *priv = rx->gve; - struct gve_rx_desc *first_desc; struct sk_buff *skb = NULL; - struct gve_rx_desc *desc; - struct napi_struct *napi; dma_addr_t page_bus; - u32 work_cnt = 0; void *va; - u32 idx; - u16 len; - idx = rx->cnt & rx->mask; - first_desc = &rx->desc.desc_ring[idx]; - desc = first_desc; - napi = &priv->ntfy_blocks[rx->ntfy_id].napi; + struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi; + bool is_first_frag = ctx->frag_cnt == 0; - if (unlikely(!gve_rx_ctx_init(ctx, rx))) - goto skb_alloc_fail; + bool is_only_frag = is_first_frag && is_last_frag; - while (ctx->curr_frag_cnt < ctx->expected_frag_cnt) { - /* Prefetch two packet buffers ahead, we will need it soon. */ - page_info = &rx->data.page_info[(idx + 2) & rx->mask]; - va = page_info->page_address + page_info->page_offset; + if (unlikely(ctx->drop_pkt)) + goto finish_frag; - prefetch(page_info->page); /* Kernel page struct. */ - prefetch(va); /* Packet header. */ - prefetch(va + 64); /* Next cacheline too. */ + if (desc->flags_seq & GVE_RXF_ERR) { + ctx->drop_pkt = true; + cnts->desc_err_pkt_cnt++; + napi_free_frags(napi); + goto finish_frag; + } - len = gve_rx_get_fragment_size(ctx, desc); + if (unlikely(frag_size > rx->packet_buffer_size)) { + netdev_warn(priv->dev, "Unexpected frag size %d, can't exceed %d, scheduling reset", + frag_size, rx->packet_buffer_size); + ctx->drop_pkt = true; + napi_free_frags(napi); + gve_schedule_reset(rx->gve); + goto finish_frag; + } - page_info = &rx->data.page_info[idx]; - data_slot = &rx->data.data_ring[idx]; - page_bus = rx->data.raw_addressing ? - be64_to_cpu(data_slot->addr) - page_info->page_offset : - rx->data.qpl->page_buses[idx]; - dma_sync_single_for_cpu(&priv->pdev->dev, page_bus, PAGE_SIZE, DMA_FROM_DEVICE); - - skb = gve_rx_skb(priv, rx, page_info, napi, len, data_slot); - if (!skb) { - u64_stats_update_begin(&rx->statss); - rx->rx_skb_alloc_fail++; - u64_stats_update_end(&rx->statss); - goto skb_alloc_fail; + /* Prefetch two packet buffers ahead, we will need it soon. */ + page_info = &rx->data.page_info[(idx + 2) & rx->mask]; + va = page_info->page_address + page_info->page_offset; + prefetch(page_info->page); /* Kernel page struct. */ + prefetch(va); /* Packet header. */ + prefetch(va + 64); /* Next cacheline too. */ + + page_info = &rx->data.page_info[idx]; + data_slot = &rx->data.data_ring[idx]; + page_bus = (rx->data.raw_addressing) ? + be64_to_cpu(data_slot->addr) - page_info->page_offset : + rx->data.qpl->page_buses[idx]; + dma_sync_single_for_cpu(&priv->pdev->dev, page_bus, + PAGE_SIZE, DMA_FROM_DEVICE); + page_info->pad = is_first_frag ? GVE_RX_PAD : 0; + frag_size -= page_info->pad; + + skb = gve_rx_skb(priv, rx, page_info, napi, frag_size, + data_slot, is_only_frag); + if (!skb) { + u64_stats_update_begin(&rx->statss); + rx->rx_skb_alloc_fail++; + u64_stats_update_end(&rx->statss); + + napi_free_frags(napi); + ctx->drop_pkt = true; + goto finish_frag; + } + ctx->total_size += frag_size; + + if (is_first_frag) { + if (likely(feat & NETIF_F_RXCSUM)) { + /* NIC passes up the partial sum */ + if (desc->csum) + skb->ip_summed = CHECKSUM_COMPLETE; + else + skb->ip_summed = CHECKSUM_NONE; + skb->csum = csum_unfold(desc->csum); } - ctx->curr_frag_cnt++; - rx->cnt++; - idx = rx->cnt & rx->mask; - work_cnt++; - desc = &rx->desc.desc_ring[idx]; + /* parse flags & pass relevant info up */ + if (likely(feat & NETIF_F_RXHASH) && + gve_needs_rss(desc->flags_seq)) + skb_set_hash(skb, be32_to_cpu(desc->rss_hash), + gve_rss_type(desc->flags_seq)); } - if (likely(feat & NETIF_F_RXCSUM)) { - /* NIC passes up the partial sum */ - if (first_desc->csum) - skb->ip_summed = CHECKSUM_COMPLETE; + if (is_last_frag) { + skb_record_rx_queue(skb, rx->q_num); + if (skb_is_nonlinear(skb)) + napi_gro_frags(napi); else - skb->ip_summed = CHECKSUM_NONE; - skb->csum = csum_unfold(first_desc->csum); + napi_gro_receive(napi, skb); + goto finish_ok_pkt; } - /* parse flags & pass relevant info up */ - if (likely(feat & NETIF_F_RXHASH) && - gve_needs_rss(first_desc->flags_seq)) - skb_set_hash(skb, be32_to_cpu(first_desc->rss_hash), - gve_rss_type(first_desc->flags_seq)); - - *packet_size_bytes = skb->len + (skb->protocol ? ETH_HLEN : 0); - *work_done = work_cnt; - skb_record_rx_queue(skb, rx->q_num); - if (skb_is_nonlinear(skb)) - napi_gro_frags(napi); - else - napi_gro_receive(napi, skb); - - gve_rx_ctx_clear(ctx); - return true; - -skb_alloc_fail: - if (napi->skb) - napi_free_frags(napi); - *packet_size_bytes = 0; - *work_done = ctx->expected_frag_cnt; - while (ctx->curr_frag_cnt < ctx->expected_frag_cnt) { - rx->cnt++; - ctx->curr_frag_cnt++; + goto finish_frag; + +finish_ok_pkt: + cnts->ok_pkt_bytes += ctx->total_size; + cnts->ok_pkt_cnt++; +finish_frag: + ctx->frag_cnt++; + if (is_last_frag) { + cnts->total_pkt_cnt++; + cnts->cont_pkt_cnt += (ctx->frag_cnt > 1); + gve_rx_ctx_clear(ctx); } - gve_rx_ctx_clear(ctx); - return false; } bool gve_rx_work_pending(struct gve_rx_ring *rx) @@ -704,36 +773,39 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, netdev_features_t feat) { - u32 work_done = 0, total_packet_cnt = 0, ok_packet_cnt = 0; + struct gve_rx_ctx *ctx = &rx->ctx; struct gve_priv *priv = rx->gve; + struct gve_rx_cnts cnts = {0}; + struct gve_rx_desc *next_desc; u32 idx = rx->cnt & rx->mask; - struct gve_rx_desc *desc; - u64 bytes = 0; + u32 work_done = 0; + + struct gve_rx_desc *desc = &rx->desc.desc_ring[idx]; - desc = &rx->desc.desc_ring[idx]; + // Exceed budget only if (and till) the inflight packet is consumed. while ((GVE_SEQNO(desc->flags_seq) == rx->desc.seqno) && - work_done < budget) { - u64 packet_size_bytes = 0; - u32 work_cnt = 0; - bool dropped; - - netif_info(priv, rx_status, priv->dev, - "[%d] idx=%d desc=%p desc->flags_seq=0x%x\n", - rx->q_num, idx, desc, desc->flags_seq); - netif_info(priv, rx_status, priv->dev, - "[%d] seqno=%d rx->desc.seqno=%d\n", - rx->q_num, GVE_SEQNO(desc->flags_seq), - rx->desc.seqno); - - dropped = !gve_rx(rx, feat, &packet_size_bytes, &work_cnt); - if (!dropped) { - bytes += packet_size_bytes; - ok_packet_cnt++; - } - total_packet_cnt++; + (work_done < budget || ctx->frag_cnt)) { + next_desc = &rx->desc.desc_ring[(idx + 1) & rx->mask]; + prefetch(next_desc); + + gve_rx(rx, feat, desc, idx, &cnts); + + rx->cnt++; idx = rx->cnt & rx->mask; desc = &rx->desc.desc_ring[idx]; - work_done += work_cnt; + rx->desc.seqno = gve_next_seqno(rx->desc.seqno); + work_done++; + } + + // The device will only send whole packets. + if (unlikely(ctx->frag_cnt)) { + struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi; + + napi_free_frags(napi); + gve_rx_ctx_clear(&rx->ctx); + netdev_warn(priv->dev, "Unexpected seq number %d with incomplete packet, expected %d, scheduling reset", + GVE_SEQNO(desc->flags_seq), rx->desc.seqno); + gve_schedule_reset(rx->gve); } if (!work_done && rx->fill_cnt - rx->cnt > rx->db_threshold) @@ -741,8 +813,10 @@ static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, if (work_done) { u64_stats_update_begin(&rx->statss); - rx->rpackets += ok_packet_cnt; - rx->rbytes += bytes; + rx->rpackets += cnts.ok_pkt_cnt; + rx->rbytes += cnts.ok_pkt_bytes; + rx->rx_cont_packet_cnt += cnts.cont_pkt_cnt; + rx->rx_desc_err_dropped_pkt += cnts.desc_err_pkt_cnt; u64_stats_update_end(&rx->statss); } @@ -767,7 +841,7 @@ static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, } gve_rx_write_doorbell(priv, rx); - return total_packet_cnt; + return cnts.total_pkt_cnt; } int gve_rx_poll(struct gve_notify_block *block, int budget) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 2e6461b0ea8b..630f42a3037b 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -568,7 +568,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, if (eop && buf_len <= priv->rx_copybreak) { rx->ctx.skb_head = gve_rx_copy(priv->dev, napi, - &buf_state->page_info, buf_len, 0, NULL); + &buf_state->page_info, buf_len, 0); if (unlikely(!rx->ctx.skb_head)) goto error; rx->ctx.skb_tail = rx->ctx.skb_head; diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index 588d64819ed5..b76143bfd594 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -953,12 +953,18 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, atomic_set_release(&tx->dqo_compl.hw_tx_head, tx_head); } else if (type == GVE_COMPL_TYPE_DQO_PKT) { u16 compl_tag = le16_to_cpu(compl_desc->completion_tag); - - gve_handle_packet_completion(priv, tx, !!napi, - compl_tag, - &pkt_compl_bytes, - &pkt_compl_pkts, - /*is_reinjection=*/false); + if (compl_tag & GVE_ALT_MISS_COMPL_BIT) { + compl_tag &= ~GVE_ALT_MISS_COMPL_BIT; + gve_handle_miss_completion(priv, tx, compl_tag, + &miss_compl_bytes, + &miss_compl_pkts); + } else { + gve_handle_packet_completion(priv, tx, !!napi, + compl_tag, + &pkt_compl_bytes, + &pkt_compl_pkts, + false); + } } else if (type == GVE_COMPL_TYPE_DQO_MISS) { u16 compl_tag = le16_to_cpu(compl_desc->completion_tag); @@ -972,7 +978,7 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, compl_tag, &reinject_compl_bytes, &reinject_compl_pkts, - /*is_reinjection=*/true); + true); } tx->dqo_compl.head = diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index d57508bc4307..6ba46adaaee3 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -50,34 +50,18 @@ void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len, - u16 padding, struct gve_rx_ctx *ctx) + u16 padding) { void *va = page_info->page_address + padding + page_info->page_offset; - int skb_linear_offset = 0; - bool set_protocol = false; struct sk_buff *skb; - if (ctx) { - if (!ctx->skb_head) - ctx->skb_head = napi_alloc_skb(napi, ctx->total_expected_size); - - if (unlikely(!ctx->skb_head)) - return NULL; - skb = ctx->skb_head; - skb_linear_offset = skb->len; - set_protocol = ctx->curr_frag_cnt == ctx->expected_frag_cnt - 1; - } else { - skb = napi_alloc_skb(napi, len); - - if (unlikely(!skb)) - return NULL; - set_protocol = true; - } - __skb_put(skb, len); - skb_copy_to_linear_data_offset(skb, skb_linear_offset, va, len); + skb = napi_alloc_skb(napi, len); + if (unlikely(!skb)) + return NULL; - if (set_protocol) - skb->protocol = eth_type_trans(skb, dev); + __skb_put(skb, len); + skb_copy_to_linear_data_offset(skb, 0, va, len); + skb->protocol = eth_type_trans(skb, dev); return skb; } diff --git a/drivers/net/ethernet/google/gve/gve_utils.h b/drivers/net/ethernet/google/gve/gve_utils.h index 6d98e69fd3b8..79595940b351 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.h +++ b/drivers/net/ethernet/google/gve/gve_utils.h @@ -19,7 +19,7 @@ void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx); struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len, - u16 pad, struct gve_rx_ctx *ctx); + u16 pad); /* Decrement pagecnt_bias. Set it back to INT_MAX if it reached zero. */ void gve_dec_pagecnt_bias(struct gve_rx_slot_page_info *page_info); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 430eccea8e5e..9b26f0f2c748 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -424,8 +424,6 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) return ret; } - __module_get(THIS_MODULE); - INIT_LIST_HEAD(&hdev->handle_list); spin_lock_init(&hdev->lock); @@ -445,7 +443,6 @@ EXPORT_SYMBOL(hnae_ae_register); void hnae_ae_unregister(struct hnae_ae_dev *hdev) { device_unregister(&hdev->cls_dev); - module_put(THIS_MODULE); } EXPORT_SYMBOL(hnae_ae_unregister); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 54faf0f2d1d8..b54f3706fb97 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -644,18 +644,15 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, { struct hns_nic_priv *priv = netdev_priv(net_dev); - strncpy(drvinfo->version, HNAE_DRIVER_VERSION, + strscpy(drvinfo->version, HNAE_DRIVER_VERSION, sizeof(drvinfo->version)); - drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; - strncpy(drvinfo->driver, HNAE_DRIVER_NAME, sizeof(drvinfo->driver)); - drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; + strscpy(drvinfo->driver, HNAE_DRIVER_NAME, sizeof(drvinfo->driver)); - strncpy(drvinfo->bus_info, priv->dev->bus->name, + strscpy(drvinfo->bus_info, priv->dev->bus->name, sizeof(drvinfo->bus_info)); - drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; - strncpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); + strscpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); drvinfo->eedump_len = 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 028577943ec5..0ec5730b1788 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2488,7 +2488,7 @@ static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); if (is_tx) { stats->tx_bytes += ring->stats.tx_bytes; stats->tx_packets += ring->stats.tx_pkts; @@ -2522,7 +2522,7 @@ static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, stats->multicast += ring->stats.rx_multicast; stats->rx_length_errors += ring->stats.err_pkt_len; } - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); } static void hns3_nic_get_stats64(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index cdf76fb58d45..55306fe8a540 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -639,13 +639,11 @@ static void hns3_get_drvinfo(struct net_device *netdev, return; } - strncpy(drvinfo->driver, dev_driver_string(&h->pdev->dev), + strscpy(drvinfo->driver, dev_driver_string(&h->pdev->dev), sizeof(drvinfo->driver)); - drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; - strncpy(drvinfo->bus_info, pci_name(h->pdev), + strscpy(drvinfo->bus_info, pci_name(h->pdev), sizeof(drvinfo->bus_info)); - drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; fw_version = priv->ae_handle->ae_algo->ops->get_fw_version(h); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index 4c441e6a5082..3d3b69605423 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -13,11 +13,6 @@ static int hclge_devlink_info_get(struct devlink *devlink, struct hclge_devlink_priv *priv = devlink_priv(devlink); char version_str[HCLGE_DEVLINK_FW_STRING_LEN]; struct hclge_dev *hdev = priv->hdev; - int ret; - - ret = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (ret) - return ret; snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu", hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index a40b1583f114..80a2a0073d97 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -22,28 +22,16 @@ static int hclge_ptp_get_cycle(struct hclge_dev *hdev) return 0; } -static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int hclge_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle; - u64 adj_val, adj_base, diff; + u64 adj_val, adj_base; unsigned long flags; - bool is_neg = false; u32 quo, numerator; - if (ppb < 0) { - ppb = -ppb; - is_neg = true; - } - adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer; - adj_val = adj_base * ppb; - diff = div_u64(adj_val, 1000000000ULL); - - if (is_neg) - adj_val = adj_base - diff; - else - adj_val = adj_base + diff; + adj_val = adjust_by_scaled_ppm(adj_base, scaled_ppm); /* This clock cycle is defined by three part: quotient, numerator * and denominator. For example, 2.5ns, the quotient is 2, @@ -446,7 +434,7 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev) ptp->info.max_adj = HCLGE_PTP_CYCLE_ADJ_MAX; ptp->info.n_ext_ts = 0; ptp->info.pps = 0; - ptp->info.adjfreq = hclge_ptp_adjfreq; + ptp->info.adjfine = hclge_ptp_adjfine; ptp->info.adjtime = hclge_ptp_adjtime; ptp->info.gettimex64 = hclge_ptp_gettimex; ptp->info.settime64 = hclge_ptp_settime; @@ -504,7 +492,7 @@ int hclge_ptp_init(struct hclge_dev *hdev) goto out; set_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); - ret = hclge_ptp_adjfreq(&hdev->ptp->info, 0); + ret = hclge_ptp_adjfine(&hdev->ptp->info, 0); if (ret) { dev_err(&hdev->pdev->dev, "failed to init freq, ret = %d\n", ret); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index fdc19868b818..a6c3c5e8f0ab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -13,11 +13,6 @@ static int hclgevf_devlink_info_get(struct devlink *devlink, struct hclgevf_devlink_priv *priv = devlink_priv(devlink); char version_str[HCLGEVF_DEVLINK_FW_STRING_LEN]; struct hclgevf_dev *hdev = priv->hdev; - int ret; - - ret = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (ret) - return ret; snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu", hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index a4fbf44f944c..52ea97c818b8 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -22,6 +22,10 @@ #define LP_PKT_CNT 64 +#define HINIC_MAX_JUMBO_FRAME_SIZE 15872 +#define HINIC_MAX_MTU_SIZE (HINIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN - ETH_FCS_LEN) +#define HINIC_MIN_MTU_SIZE 256 + enum hinic_flags { HINIC_LINK_UP = BIT(0), HINIC_INTF_UP = BIT(1), diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index d2d89b0a5ef0..6b5797e69781 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -46,104 +46,170 @@ enum hinic_port_cmd { HINIC_PORT_CMD_VF_REGISTER = 0x0, HINIC_PORT_CMD_VF_UNREGISTER = 0x1, - HINIC_PORT_CMD_CHANGE_MTU = 2, + HINIC_PORT_CMD_CHANGE_MTU = 0x2, - HINIC_PORT_CMD_ADD_VLAN = 3, - HINIC_PORT_CMD_DEL_VLAN = 4, + HINIC_PORT_CMD_ADD_VLAN = 0x3, + HINIC_PORT_CMD_DEL_VLAN = 0x4, - HINIC_PORT_CMD_SET_PFC = 5, + HINIC_PORT_CMD_SET_ETS = 0x7, + HINIC_PORT_CMD_GET_ETS = 0x8, - HINIC_PORT_CMD_SET_MAC = 9, - HINIC_PORT_CMD_GET_MAC = 10, - HINIC_PORT_CMD_DEL_MAC = 11, + HINIC_PORT_CMD_SET_PFC = 0x5, - HINIC_PORT_CMD_SET_RX_MODE = 12, + HINIC_PORT_CMD_SET_MAC = 0x9, + HINIC_PORT_CMD_GET_MAC = 0xA, + HINIC_PORT_CMD_DEL_MAC = 0xB, - HINIC_PORT_CMD_GET_PAUSE_INFO = 20, - HINIC_PORT_CMD_SET_PAUSE_INFO = 21, + HINIC_PORT_CMD_SET_RX_MODE = 0xC, - HINIC_PORT_CMD_GET_LINK_STATE = 24, + HINIC_PORT_CMD_SET_ANTI_ATTACK_RATE = 0xD, - HINIC_PORT_CMD_SET_LRO = 25, + HINIC_PORT_CMD_GET_PAUSE_INFO = 0x14, + HINIC_PORT_CMD_SET_PAUSE_INFO = 0x15, - HINIC_PORT_CMD_SET_RX_CSUM = 26, + HINIC_PORT_CMD_GET_LINK_STATE = 0x18, - HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD = 27, + HINIC_PORT_CMD_SET_LRO = 0x19, - HINIC_PORT_CMD_GET_PORT_STATISTICS = 28, + HINIC_PORT_CMD_SET_RX_CSUM = 0x1A, - HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 29, + HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD = 0x1B, - HINIC_PORT_CMD_GET_VPORT_STAT = 30, + HINIC_PORT_CMD_GET_PORT_STATISTICS = 0x1C, - HINIC_PORT_CMD_CLEAN_VPORT_STAT = 31, + HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 0x1D, - HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 37, + HINIC_PORT_CMD_GET_VPORT_STAT = 0x1E, - HINIC_PORT_CMD_SET_PORT_STATE = 41, + HINIC_PORT_CMD_CLEAN_VPORT_STAT = 0x1F, - HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL = 43, + HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 0x25, - HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL = 44, + HINIC_PORT_CMD_SET_PORT_STATE = 0x29, + HINIC_PORT_CMD_GET_PORT_STATE = 0x30, - HINIC_PORT_CMD_SET_RSS_HASH_ENGINE = 45, + HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL = 0x2B, - HINIC_PORT_CMD_GET_RSS_HASH_ENGINE = 46, + HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL = 0x2C, - HINIC_PORT_CMD_GET_RSS_CTX_TBL = 47, + HINIC_PORT_CMD_SET_RSS_HASH_ENGINE = 0x2D, - HINIC_PORT_CMD_SET_RSS_CTX_TBL = 48, + HINIC_PORT_CMD_GET_RSS_HASH_ENGINE = 0x2E, - HINIC_PORT_CMD_RSS_TEMP_MGR = 49, + HINIC_PORT_CMD_GET_RSS_CTX_TBL = 0x2F, - HINIC_PORT_CMD_RD_LINE_TBL = 57, + HINIC_PORT_CMD_SET_RSS_CTX_TBL = 0x30, - HINIC_PORT_CMD_RSS_CFG = 66, + HINIC_PORT_CMD_RSS_TEMP_MGR = 0x31, - HINIC_PORT_CMD_FWCTXT_INIT = 69, + HINIC_PORT_CMD_RD_LINE_TBL = 0x39, - HINIC_PORT_CMD_GET_LOOPBACK_MODE = 72, - HINIC_PORT_CMD_SET_LOOPBACK_MODE, + HINIC_PORT_CMD_RSS_CFG = 0x42, - HINIC_PORT_CMD_ENABLE_SPOOFCHK = 78, + HINIC_PORT_CMD_GET_PHY_TYPE = 0x44, - HINIC_PORT_CMD_GET_MGMT_VERSION = 88, + HINIC_PORT_CMD_FWCTXT_INIT = 0x45, - HINIC_PORT_CMD_SET_FUNC_STATE = 93, + HINIC_PORT_CMD_GET_LOOPBACK_MODE = 0x48, + HINIC_PORT_CMD_SET_LOOPBACK_MODE = 0x49, - HINIC_PORT_CMD_GET_GLOBAL_QPN = 102, + HINIC_PORT_CMD_GET_JUMBO_FRAME_SIZE = 0x4A, + HINIC_PORT_CMD_SET_JUMBO_FRAME_SIZE = 0x4B, - HINIC_PORT_CMD_SET_VF_RATE = 105, + HINIC_PORT_CMD_ENABLE_SPOOFCHK = 0x4E, - HINIC_PORT_CMD_SET_VF_VLAN = 106, + HINIC_PORT_CMD_GET_MGMT_VERSION = 0x58, - HINIC_PORT_CMD_CLR_VF_VLAN, + HINIC_PORT_CMD_GET_PORT_TYPE = 0x5B, - HINIC_PORT_CMD_SET_TSO = 112, + HINIC_PORT_CMD_SET_FUNC_STATE = 0x5D, - HINIC_PORT_CMD_UPDATE_FW = 114, + HINIC_PORT_CMD_GET_PORT_ID_BY_FUNC_ID = 0x5E, - HINIC_PORT_CMD_SET_RQ_IQ_MAP = 115, + HINIC_PORT_CMD_GET_DMA_CS = 0x64, + HINIC_PORT_CMD_SET_DMA_CS = 0x65, - HINIC_PORT_CMD_LINK_STATUS_REPORT = 160, + HINIC_PORT_CMD_GET_GLOBAL_QPN = 0x66, - HINIC_PORT_CMD_UPDATE_MAC = 164, + HINIC_PORT_CMD_SET_VF_RATE = 0x69, - HINIC_PORT_CMD_GET_CAP = 170, + HINIC_PORT_CMD_SET_VF_VLAN = 0x6A, - HINIC_PORT_CMD_GET_LINK_MODE = 217, + HINIC_PORT_CMD_CLR_VF_VLAN = 0x6B, - HINIC_PORT_CMD_SET_SPEED = 218, + HINIC_PORT_CMD_SET_TSO = 0x70, - HINIC_PORT_CMD_SET_AUTONEG = 219, + HINIC_PORT_CMD_UPDATE_FW = 0x72, - HINIC_PORT_CMD_GET_STD_SFP_INFO = 240, + HINIC_PORT_CMD_SET_RQ_IQ_MAP = 0x73, - HINIC_PORT_CMD_SET_LRO_TIMER = 244, + HINIC_PORT_CMD_SET_PFC_THD = 0x75, - HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 249, + HINIC_PORT_CMD_LINK_STATUS_REPORT = 0xA0, - HINIC_PORT_CMD_GET_SFP_ABS = 251, + HINIC_PORT_CMD_SET_LOSSLESS_ETH = 0xA3, + + HINIC_PORT_CMD_UPDATE_MAC = 0xA4, + + HINIC_PORT_CMD_GET_CAP = 0xAA, + + HINIC_PORT_CMD_UP_TC_ADD_FLOW = 0xAF, + HINIC_PORT_CMD_UP_TC_DEL_FLOW = 0xB0, + HINIC_PORT_CMD_UP_TC_GET_FLOW = 0xB1, + + HINIC_PORT_CMD_UP_TC_FLUSH_TCAM = 0xB2, + + HINIC_PORT_CMD_UP_TC_CTRL_TCAM_BLOCK = 0xB3, + + HINIC_PORT_CMD_UP_TC_ENABLE = 0xB4, + + HINIC_PORT_CMD_UP_TC_GET_TCAM_BLOCK = 0xB5, + + HINIC_PORT_CMD_SET_IPSU_MAC = 0xCB, + HINIC_PORT_CMD_GET_IPSU_MAC = 0xCC, + + HINIC_PORT_CMD_SET_XSFP_STATUS = 0xD4, + + HINIC_PORT_CMD_GET_LINK_MODE = 0xD9, + + HINIC_PORT_CMD_SET_SPEED = 0xDA, + + HINIC_PORT_CMD_SET_AUTONEG = 0xDB, + + HINIC_PORT_CMD_CLEAR_QP_RES = 0xDD, + + HINIC_PORT_CMD_SET_SUPER_CQE = 0xDE, + + HINIC_PORT_CMD_SET_VF_COS = 0xDF, + HINIC_PORT_CMD_GET_VF_COS = 0xE1, + + HINIC_PORT_CMD_CABLE_PLUG_EVENT = 0xE5, + + HINIC_PORT_CMD_LINK_ERR_EVENT = 0xE6, + + HINIC_PORT_CMD_SET_COS_UP_MAP = 0xE8, + + HINIC_PORT_CMD_RESET_LINK_CFG = 0xEB, + + HINIC_PORT_CMD_GET_STD_SFP_INFO = 0xF0, + + HINIC_PORT_CMD_FORCE_PKT_DROP = 0xF3, + + HINIC_PORT_CMD_SET_LRO_TIMER = 0xF4, + + HINIC_PORT_CMD_SET_VHD_CFG = 0xF7, + + HINIC_PORT_CMD_SET_LINK_FOLLOW = 0xF8, + + HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 0xF9, + + HINIC_PORT_CMD_GET_SFP_ABS = 0xFB, + + HINIC_PORT_CMD_Q_FILTER = 0xFC, + + HINIC_PORT_CMD_TCAM_FILTER = 0xFE, + + HINIC_PORT_CMD_SET_VLAN_FILTER = 0xFF, }; /* cmd of mgmt CPU message for HILINK module */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 2d6906aba2a2..499c657d37a9 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1092,6 +1092,16 @@ static int set_features(struct hinic_dev *nic_dev, } } + if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { + ret = hinic_set_vlan_fliter(nic_dev, + !!(features & + NETIF_F_HW_VLAN_CTAG_FILTER)); + if (ret) { + err = ret; + failed_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + } + } + if (err) { nic_dev->netdev->features = features ^ failed_features; return -EIO; @@ -1187,7 +1197,8 @@ static int nic_dev_init(struct pci_dev *pdev) else netdev->netdev_ops = &hinicvf_netdev_ops; - netdev->max_mtu = ETH_MAX_MTU; + netdev->max_mtu = HINIC_MAX_MTU_SIZE; + netdev->min_mtu = HINIC_MIN_MTU_SIZE; nic_dev = netdev_priv(netdev); nic_dev->netdev = netdev; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 28ae6f1201a8..9406237c461e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -17,9 +17,6 @@ #include "hinic_port.h" #include "hinic_dev.h" -#define HINIC_MIN_MTU_SIZE 256 -#define HINIC_MAX_JUMBO_FRAME_SIZE 15872 - enum mac_op { MAC_DEL, MAC_SET, @@ -147,24 +144,12 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr) **/ int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu) { - struct net_device *netdev = nic_dev->netdev; struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_port_mtu_cmd port_mtu_cmd; struct hinic_hwif *hwif = hwdev->hwif; u16 out_size = sizeof(port_mtu_cmd); struct pci_dev *pdev = hwif->pdev; - int err, max_frame; - - if (new_mtu < HINIC_MIN_MTU_SIZE) { - netif_err(nic_dev, drv, netdev, "mtu < MIN MTU size"); - return -EINVAL; - } - - max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - if (max_frame > HINIC_MAX_JUMBO_FRAME_SIZE) { - netif_err(nic_dev, drv, netdev, "mtu > MAX MTU size"); - return -EINVAL; - } + int err; port_mtu_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); port_mtu_cmd.mtu = new_mtu; @@ -462,6 +447,39 @@ int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en) return 0; } +int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_vlan_filter vlan_filter; + u16 out_size = sizeof(vlan_filter); + int err; + + if (!hwdev) + return -EINVAL; + + vlan_filter.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + vlan_filter.enable = en; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_VLAN_FILTER, + &vlan_filter, sizeof(vlan_filter), + &vlan_filter, &out_size); + if (vlan_filter.status == HINIC_MGMT_CMD_UNSUPPORTED) { + err = HINIC_MGMT_CMD_UNSUPPORTED; + } else if ((err == HINIC_MBOX_VF_CMD_ERROR) && + HINIC_IS_VF(hwif)) { + err = HINIC_MGMT_CMD_UNSUPPORTED; + } else if (err || !out_size || vlan_filter.status) { + dev_err(&pdev->dev, + "Failed to set vlan fliter, err: %d, status: 0x%x, out size: 0x%x\n", + err, vlan_filter.status, out_size); + err = -EINVAL; + } + + return err; +} + int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs) { struct hinic_hwdev *hwdev = nic_dev->hwdev; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h index c9ae3d4dc547..c8694ac7c702 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h @@ -351,6 +351,16 @@ struct hinic_vlan_cfg { u8 rsvd1[5]; }; +struct hinic_vlan_filter { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 rsvd1[2]; + u32 enable; +}; + struct hinic_rss_template_mgmt { u8 status; u8 version; @@ -831,6 +841,8 @@ int hinic_get_vport_stats(struct hinic_dev *nic_dev, int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en); +int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en); + int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver); int hinic_set_link_settings(struct hinic_hwdev *hwdev, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index d649c6e323c8..ceec8be2a73b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -74,14 +74,14 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats) unsigned int start; do { - start = u64_stats_fetch_begin_irq(&rxq_stats->syncp); + start = u64_stats_fetch_begin(&rxq_stats->syncp); stats->pkts = rxq_stats->pkts; stats->bytes = rxq_stats->bytes; stats->errors = rxq_stats->csum_errors + rxq_stats->other_errors; stats->csum_errors = rxq_stats->csum_errors; stats->other_errors = rxq_stats->other_errors; - } while (u64_stats_fetch_retry_irq(&rxq_stats->syncp, start)); + } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); } /** diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index f7e05b41385b..ee357088d021 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -489,6 +489,24 @@ static struct vf_cmd_check_handle nic_cmd_support_vf[] = { {HINIC_PORT_CMD_UPDATE_MAC, hinic_mbox_check_func_id_8B}, {HINIC_PORT_CMD_GET_CAP, hinic_mbox_check_func_id_8B}, {HINIC_PORT_CMD_GET_LINK_MODE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_GET_VF_COS, NULL}, + {HINIC_PORT_CMD_SET_VHD_CFG, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_VLAN_FILTER, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_Q_FILTER, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_TCAM_FILTER, NULL}, + {HINIC_PORT_CMD_UP_TC_ADD_FLOW, NULL}, + {HINIC_PORT_CMD_UP_TC_DEL_FLOW, NULL}, + {HINIC_PORT_CMD_UP_TC_FLUSH_TCAM, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_UP_TC_CTRL_TCAM_BLOCK, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_UP_TC_ENABLE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_CABLE_PLUG_EVENT, NULL}, + {HINIC_PORT_CMD_LINK_ERR_EVENT, NULL}, + {HINIC_PORT_CMD_SET_PORT_STATE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_ETS, NULL}, + {HINIC_PORT_CMD_SET_ANTI_ATTACK_RATE, NULL}, + {HINIC_PORT_CMD_RESET_LINK_CFG, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_LINK_FOLLOW, NULL}, + {HINIC_PORT_CMD_CLEAR_QP_RES, NULL}, }; #define CHECK_IPSU_15BIT 0X8000 diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index e91476c8ff8b..ad47ac51a139 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -99,14 +99,14 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats) unsigned int start; do { - start = u64_stats_fetch_begin_irq(&txq_stats->syncp); + start = u64_stats_fetch_begin(&txq_stats->syncp); stats->pkts = txq_stats->pkts; stats->bytes = txq_stats->bytes; stats->tx_busy = txq_stats->tx_busy; stats->tx_wake = txq_stats->tx_wake; stats->tx_dropped = txq_stats->tx_dropped; stats->big_frags_pkts = txq_stats->big_frags_pkts; - } while (u64_stats_fetch_retry_irq(&txq_stats->syncp, start)); + } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); } /** diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 5b96cd94dcd2..113fcb3e353e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -690,8 +690,7 @@ static int ibmveth_close(struct net_device *netdev) napi_disable(&adapter->napi); - if (!adapter->pool_config) - netif_tx_stop_all_queues(netdev); + netif_tx_stop_all_queues(netdev); h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE); @@ -799,9 +798,7 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data) if (netif_running(dev)) { restart = 1; - adapter->pool_config = 1; ibmveth_close(dev); - adapter->pool_config = 0; } set_attr = 0; @@ -883,9 +880,7 @@ static int ibmveth_set_tso(struct net_device *dev, u32 data) if (netif_running(dev)) { restart = 1; - adapter->pool_config = 1; ibmveth_close(dev); - adapter->pool_config = 0; } set_attr = 0; @@ -1535,9 +1530,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) only the buffer pools necessary to hold the new MTU */ if (netif_running(adapter->netdev)) { need_restart = 1; - adapter->pool_config = 1; ibmveth_close(adapter->netdev); - adapter->pool_config = 0; } /* Look for an active buffer pool that can hold the new MTU */ @@ -1701,7 +1694,6 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->vdev = dev; adapter->netdev = netdev; adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p); - adapter->pool_config = 0; ibmveth_init_link_settings(netdev); netif_napi_add_weight(netdev, &adapter->napi, ibmveth_poll, 16); @@ -1842,9 +1834,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, return -ENOMEM; } pool->active = 1; - adapter->pool_config = 1; ibmveth_close(netdev); - adapter->pool_config = 0; if ((rc = ibmveth_open(netdev))) return rc; } else { @@ -1870,10 +1860,8 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, } if (netif_running(netdev)) { - adapter->pool_config = 1; ibmveth_close(netdev); pool->active = 0; - adapter->pool_config = 0; if ((rc = ibmveth_open(netdev))) return rc; } @@ -1884,9 +1872,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, return -EINVAL; } else { if (netif_running(netdev)) { - adapter->pool_config = 1; ibmveth_close(netdev); - adapter->pool_config = 0; pool->size = value; if ((rc = ibmveth_open(netdev))) return rc; @@ -1899,9 +1885,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, return -EINVAL; } else { if (netif_running(netdev)) { - adapter->pool_config = 1; ibmveth_close(netdev); - adapter->pool_config = 0; pool->buff_size = value; if ((rc = ibmveth_open(netdev))) return rc; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 115d4c45aa77..8468e2c59d7a 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -147,7 +147,6 @@ struct ibmveth_adapter { dma_addr_t filter_list_dma; struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS]; struct ibmveth_rx_q rx_queue; - int pool_config; int rx_csum; int large_send; bool is_active_trunk; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 9282381a438f..e19a6bb3f444 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -68,6 +68,7 @@ #include <linux/workqueue.h> #include <linux/if_vlan.h> #include <linux/utsname.h> +#include <linux/cpu.h> #include "ibmvnic.h" @@ -171,6 +172,193 @@ static int send_version_xchg(struct ibmvnic_adapter *adapter) return ibmvnic_send_crq(adapter, &crq); } +static void ibmvnic_clean_queue_affinity(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *queue) +{ + if (!(queue && queue->irq)) + return; + + cpumask_clear(queue->affinity_mask); + + if (irq_set_affinity_and_hint(queue->irq, NULL)) + netdev_warn(adapter->netdev, + "%s: Clear affinity failed, queue addr = %p, IRQ = %d\n", + __func__, queue, queue->irq); +} + +static void ibmvnic_clean_affinity(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_sub_crq_queue **rxqs; + struct ibmvnic_sub_crq_queue **txqs; + int num_rxqs, num_txqs; + int rc, i; + + rc = 0; + rxqs = adapter->rx_scrq; + txqs = adapter->tx_scrq; + num_txqs = adapter->num_active_tx_scrqs; + num_rxqs = adapter->num_active_rx_scrqs; + + netdev_dbg(adapter->netdev, "%s: Cleaning irq affinity hints", __func__); + if (txqs) { + for (i = 0; i < num_txqs; i++) + ibmvnic_clean_queue_affinity(adapter, txqs[i]); + } + if (rxqs) { + for (i = 0; i < num_rxqs; i++) + ibmvnic_clean_queue_affinity(adapter, rxqs[i]); + } +} + +static int ibmvnic_set_queue_affinity(struct ibmvnic_sub_crq_queue *queue, + unsigned int *cpu, int *stragglers, + int stride) +{ + cpumask_var_t mask; + int i; + int rc = 0; + + if (!(queue && queue->irq)) + return rc; + + /* cpumask_var_t is either a pointer or array, allocation works here */ + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + /* while we have extra cpu give one extra to this irq */ + if (*stragglers) { + stride++; + (*stragglers)--; + } + /* atomic write is safer than writing bit by bit directly */ + for (i = 0; i < stride; i++) { + cpumask_set_cpu(*cpu, mask); + *cpu = cpumask_next_wrap(*cpu, cpu_online_mask, + nr_cpu_ids, false); + } + /* set queue affinity mask */ + cpumask_copy(queue->affinity_mask, mask); + rc = irq_set_affinity_and_hint(queue->irq, queue->affinity_mask); + free_cpumask_var(mask); + + return rc; +} + +/* assumes cpu read lock is held */ +static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter) +{ + struct ibmvnic_sub_crq_queue **rxqs = adapter->rx_scrq; + struct ibmvnic_sub_crq_queue **txqs = adapter->tx_scrq; + struct ibmvnic_sub_crq_queue *queue; + int num_rxqs = adapter->num_active_rx_scrqs; + int num_txqs = adapter->num_active_tx_scrqs; + int total_queues, stride, stragglers, i; + unsigned int num_cpu, cpu; + int rc = 0; + + netdev_dbg(adapter->netdev, "%s: Setting irq affinity hints", __func__); + if (!(adapter->rx_scrq && adapter->tx_scrq)) { + netdev_warn(adapter->netdev, + "%s: Set affinity failed, queues not allocated\n", + __func__); + return; + } + + total_queues = num_rxqs + num_txqs; + num_cpu = num_online_cpus(); + /* number of cpu's assigned per irq */ + stride = max_t(int, num_cpu / total_queues, 1); + /* number of leftover cpu's */ + stragglers = num_cpu >= total_queues ? num_cpu % total_queues : 0; + /* next available cpu to assign irq to */ + cpu = cpumask_next(-1, cpu_online_mask); + + for (i = 0; i < num_txqs; i++) { + queue = txqs[i]; + rc = ibmvnic_set_queue_affinity(queue, &cpu, &stragglers, + stride); + if (rc) + goto out; + + if (!queue) + continue; + + rc = __netif_set_xps_queue(adapter->netdev, + cpumask_bits(queue->affinity_mask), + i, XPS_CPUS); + if (rc) + netdev_warn(adapter->netdev, "%s: Set XPS on queue %d failed, rc = %d.\n", + __func__, i, rc); + } + + for (i = 0; i < num_rxqs; i++) { + queue = rxqs[i]; + rc = ibmvnic_set_queue_affinity(queue, &cpu, &stragglers, + stride); + if (rc) + goto out; + } + +out: + if (rc) { + netdev_warn(adapter->netdev, + "%s: Set affinity failed, queue addr = %p, IRQ = %d, rc = %d.\n", + __func__, queue, queue->irq, rc); + ibmvnic_clean_affinity(adapter); + } +} + +static int ibmvnic_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node); + ibmvnic_set_affinity(adapter); + return 0; +} + +static int ibmvnic_cpu_dead(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node_dead); + ibmvnic_set_affinity(adapter); + return 0; +} + +static int ibmvnic_cpu_down_prep(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node); + ibmvnic_clean_affinity(adapter); + return 0; +} + +static enum cpuhp_state ibmvnic_online; + +static int ibmvnic_cpu_notif_add(struct ibmvnic_adapter *adapter) +{ + int ret; + + ret = cpuhp_state_add_instance_nocalls(ibmvnic_online, &adapter->node); + if (ret) + return ret; + ret = cpuhp_state_add_instance_nocalls(CPUHP_IBMVNIC_DEAD, + &adapter->node_dead); + if (!ret) + return ret; + cpuhp_state_remove_instance_nocalls(ibmvnic_online, &adapter->node); + return ret; +} + +static void ibmvnic_cpu_notif_remove(struct ibmvnic_adapter *adapter) +{ + cpuhp_state_remove_instance_nocalls(ibmvnic_online, &adapter->node); + cpuhp_state_remove_instance_nocalls(CPUHP_IBMVNIC_DEAD, + &adapter->node_dead); +} + static long h_reg_sub_crq(unsigned long unit_address, unsigned long token, unsigned long length, unsigned long *number, unsigned long *irq) @@ -3626,6 +3814,8 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) if (!adapter->tx_scrq || !adapter->rx_scrq) return -EINVAL; + ibmvnic_clean_affinity(adapter); + for (i = 0; i < adapter->req_tx_queues; i++) { netdev_dbg(adapter->netdev, "Re-setting tx_scrq[%d]\n", i); rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]); @@ -3675,6 +3865,7 @@ static void release_sub_crq_queue(struct ibmvnic_adapter *adapter, dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); free_pages((unsigned long)scrq->msgs, 2); + free_cpumask_var(scrq->affinity_mask); kfree(scrq); } @@ -3695,6 +3886,8 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter dev_warn(dev, "Couldn't allocate crq queue messages page\n"); goto zero_page_failed; } + if (!zalloc_cpumask_var(&scrq->affinity_mask, GFP_KERNEL)) + goto cpumask_alloc_failed; scrq->msg_token = dma_map_single(dev, scrq->msgs, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -3747,6 +3940,8 @@ reg_failed: dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); map_failed: + free_cpumask_var(scrq->affinity_mask); +cpumask_alloc_failed: free_pages((unsigned long)scrq->msgs, 2); zero_page_failed: kfree(scrq); @@ -3758,6 +3953,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free) { int i; + ibmvnic_clean_affinity(adapter); if (adapter->tx_scrq) { for (i = 0; i < adapter->num_active_tx_scrqs; i++) { if (!adapter->tx_scrq[i]) @@ -4035,6 +4231,11 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) goto req_rx_irq_failed; } } + + cpus_read_lock(); + ibmvnic_set_affinity(adapter); + cpus_read_unlock(); + return rc; req_rx_irq_failed: @@ -6152,10 +6353,19 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } dev_info(&dev->dev, "ibmvnic registered\n"); + rc = ibmvnic_cpu_notif_add(adapter); + if (rc) { + netdev_err(netdev, "Registering cpu notifier failed\n"); + goto cpu_notif_add_failed; + } + complete(&adapter->probe_done); return 0; +cpu_notif_add_failed: + unregister_netdev(netdev); + ibmvnic_register_fail: device_remove_file(&dev->dev, &dev_attr_failover); @@ -6206,6 +6416,8 @@ static void ibmvnic_remove(struct vio_dev *dev) spin_unlock_irqrestore(&adapter->state_lock, flags); + ibmvnic_cpu_notif_remove(adapter); + flush_work(&adapter->ibmvnic_reset); flush_delayed_work(&adapter->ibmvnic_delayed_reset); @@ -6336,15 +6548,40 @@ static struct vio_driver ibmvnic_driver = { /* module functions */ static int __init ibmvnic_module_init(void) { + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/ibmvnic:online", + ibmvnic_cpu_online, + ibmvnic_cpu_down_prep); + if (ret < 0) + goto out; + ibmvnic_online = ret; + ret = cpuhp_setup_state_multi(CPUHP_IBMVNIC_DEAD, "net/ibmvnic:dead", + NULL, ibmvnic_cpu_dead); + if (ret) + goto err_dead; + + ret = vio_register_driver(&ibmvnic_driver); + if (ret) + goto err_vio_register; + pr_info("%s: %s %s\n", ibmvnic_driver_name, ibmvnic_driver_string, IBMVNIC_DRIVER_VERSION); - return vio_register_driver(&ibmvnic_driver); + return 0; +err_vio_register: + cpuhp_remove_multi_state(CPUHP_IBMVNIC_DEAD); +err_dead: + cpuhp_remove_multi_state(ibmvnic_online); +out: + return ret; } static void __exit ibmvnic_module_exit(void) { vio_unregister_driver(&ibmvnic_driver); + cpuhp_remove_multi_state(CPUHP_IBMVNIC_DEAD); + cpuhp_remove_multi_state(ibmvnic_online); } module_init(ibmvnic_module_init); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index e5c6ff3d0c47..b35c9b6f913b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -825,6 +825,7 @@ struct ibmvnic_sub_crq_queue { atomic_t used; char name[32]; u64 handle; + cpumask_var_t affinity_mask; } ____cacheline_aligned; struct ibmvnic_long_term_buff { @@ -983,6 +984,10 @@ struct ibmvnic_adapter { int reset_done_rc; bool wait_for_reset; + /* CPU hotplug instances for online & dead */ + struct hlist_node node; + struct hlist_node node_dead; + /* partner capabilities */ u64 min_tx_queues; u64 min_rx_queues; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 61e60e4de600..da6e303ad99b 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -4229,8 +4229,6 @@ process_skb: */ p = buffer_info->rxbuf.page; if (length <= copybreak) { - u8 *vaddr; - if (likely(!(netdev->features & NETIF_F_RXFCS))) length -= 4; skb = e1000_alloc_rx_skb(adapter, @@ -4238,10 +4236,9 @@ process_skb: if (!skb) break; - vaddr = kmap_atomic(p); - memcpy(skb_tail_pointer(skb), vaddr, - length); - kunmap_atomic(vaddr); + memcpy(skb_tail_pointer(skb), + page_address(p), length); + /* re-use the page, so don't erase * buffer_info->rxbuf.page */ diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile index 44e58b6e7660..0baa15503c38 100644 --- a/drivers/net/ethernet/intel/e1000e/Makefile +++ b/drivers/net/ethernet/intel/e1000e/Makefile @@ -5,6 +5,9 @@ # Makefile for the Intel(R) PRO/1000 ethernet driver # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_E1000E) += e1000e.o e1000e-objs := 82571.o ich8lan.o 80003es2lan.o \ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index e8a9a9610ac6..a187582d2299 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -116,7 +116,8 @@ enum e1000_boards { board_pch_spt, board_pch_cnp, board_pch_tgp, - board_pch_adp + board_pch_adp, + board_pch_mtp }; struct e1000_ps_page { @@ -504,6 +505,7 @@ extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_pch_adp_info; +extern const struct e1000_info e1000_pch_mtp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/e1000e_trace.h b/drivers/net/ethernet/intel/e1000e/e1000e_trace.h new file mode 100644 index 000000000000..19d3cf4d924e --- /dev/null +++ b/drivers/net/ethernet/intel/e1000e/e1000e_trace.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2022, Intel Corporation. */ +/* Modeled on trace-events-sample.h */ +/* The trace subsystem name for e1000e will be "e1000e_trace". + * + * This file is named e1000e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM e1000e_trace + +#if !defined(_TRACE_E1000E_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_E1000E_TRACE_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(e1000e_trace_mac_register, + TP_PROTO(uint32_t reg), + TP_ARGS(reg), + TP_STRUCT__entry(__field(uint32_t, reg)), + TP_fast_assign(__entry->reg = reg;), + TP_printk("event: TraceHub e1000e mac register: 0x%08x", + __entry->reg) +); + +#endif +/* This must be outside ifdef _E1000E_TRACE_H */ +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE e1000e_trace + +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 51a5afe9df2f..59e82d131d88 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -908,6 +908,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: mask |= BIT(18); break; default: @@ -1575,6 +1576,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: fext_nvm11 = er32(FEXTNVM11); fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index bcf680e83811..29f9fae35f42 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -114,6 +114,14 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_LNP_I219_V20 0x550F #define E1000_DEV_ID_PCH_LNP_I219_LM21 0x5510 #define E1000_DEV_ID_PCH_LNP_I219_V21 0x5511 +#define E1000_DEV_ID_PCH_ARL_I219_LM24 0x57A0 +#define E1000_DEV_ID_PCH_ARL_I219_V24 0x57A1 +#define E1000_DEV_ID_PCH_PTP_I219_LM25 0x57B3 +#define E1000_DEV_ID_PCH_PTP_I219_V25 0x57B4 +#define E1000_DEV_ID_PCH_PTP_I219_LM26 0x57B5 +#define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 +#define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 +#define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 #define E1000_REVISION_4 4 @@ -141,6 +149,7 @@ enum e1000_mac_type { e1000_pch_adp, e1000_pch_mtp, e1000_pch_lnp, + e1000_pch_ptp, }; enum e1000_media_type { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 9466f65a6da7..0c7fd10312c8 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -322,6 +322,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -468,6 +469,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: /* In case the PHY needs to be in mdio slow mode, * set slow mode and try to get the PHY id again. */ @@ -714,6 +716,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: case e1000_pchlan: /* check management mode */ mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan; @@ -1681,6 +1684,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: rc = e1000_init_phy_params_pchlan(hw); break; default: @@ -2137,6 +2141,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M; break; default: @@ -3182,6 +3187,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: bank1_offset = nvm->flash_bank_size; act_offset = E1000_ICH_NVM_SIG_WORD; @@ -4122,6 +4128,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: word = NVM_COMPAT; valid_csum_mask = NVM_COMPAT_VALID_CSUM; break; @@ -6041,3 +6048,23 @@ const struct e1000_info e1000_pch_adp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_mtp_info = { + .mac = e1000_pch_mtp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 55cf2f62bb30..04acd1a992fa 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -28,6 +28,8 @@ #include <linux/suspend.h> #include "e1000.h" +#define CREATE_TRACE_POINTS +#include "e1000e_trace.h" char e1000e_driver_name[] = "e1000e"; @@ -53,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_cnp] = &e1000_pch_cnp_info, [board_pch_tgp] = &e1000_pch_tgp_info, [board_pch_adp] = &e1000_pch_adp_info, + [board_pch_mtp] = &e1000_pch_mtp_info, }; struct e1000_reg_info { @@ -1388,26 +1391,18 @@ static bool e1000_clean_rx_irq_ps(struct e1000_ring *rx_ring, int *work_done, /* page alloc/put takes too long and effects small * packet throughput, so unsplit small packets and - * save the alloc/put only valid in softirq (napi) - * context to call kmap_* + * save the alloc/put */ if (l1 && (l1 <= copybreak) && ((length + l1) <= adapter->rx_ps_bsize0)) { - u8 *vaddr; - ps_page = &buffer_info->ps_pages[0]; - /* there is no documentation about how to call - * kmap_atomic, so we can't hold the mapping - * very long - */ dma_sync_single_for_cpu(&pdev->dev, ps_page->dma, PAGE_SIZE, DMA_FROM_DEVICE); - vaddr = kmap_atomic(ps_page->page); - memcpy(skb_tail_pointer(skb), vaddr, l1); - kunmap_atomic(vaddr); + memcpy(skb_tail_pointer(skb), + page_address(ps_page->page), l1); dma_sync_single_for_device(&pdev->dev, ps_page->dma, PAGE_SIZE, @@ -1607,11 +1602,9 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_ring *rx_ring, int *work_done, */ if (length <= copybreak && skb_tailroom(skb) >= length) { - u8 *vaddr; - vaddr = kmap_atomic(buffer_info->page); - memcpy(skb_tail_pointer(skb), vaddr, + memcpy(skb_tail_pointer(skb), + page_address(buffer_info->page), length); - kunmap_atomic(vaddr); /* re-use the page, so don't erase * buffer_info->page */ @@ -3552,6 +3545,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ incperiod = INCPERIOD_24MHZ; @@ -4067,6 +4061,7 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: fc->refresh_time = 0xFFFF; fc->pause_time = 0xFFFF; @@ -6348,6 +6343,7 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) mac_data = er32(H2ME); mac_data |= E1000_H2ME_START_DPG; mac_data &= ~E1000_H2ME_EXIT_DPG; + trace_e1000e_trace_mac_register(mac_data); ew32(H2ME, mac_data); } else { /* Request driver configure the device to S0ix */ @@ -6502,6 +6498,7 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; mac_data |= E1000_H2ME_EXIT_DPG; + trace_e1000e_trace_mac_register(mac_data); ew32(H2ME, mac_data); /* Poll up to 2.5 seconds for ME to unconfigure DPG. @@ -7905,14 +7902,22 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 0e488e4fa5c1..def4566a916f 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -29,17 +29,11 @@ static int e1000e_phc_adjfine(struct ptp_clock_info *ptp, long delta) struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); struct e1000_hw *hw = &adapter->hw; - bool neg_adj = false; unsigned long flags; - u64 adjustment; - u32 timinca, incvalue; + u64 incvalue; + u32 timinca; s32 ret_val; - if (delta < 0) { - neg_adj = true; - delta = -delta; - } - /* Get the System Time Register SYSTIM base frequency */ ret_val = e1000e_get_base_timinca(adapter, &timinca); if (ret_val) @@ -48,11 +42,7 @@ static int e1000e_phc_adjfine(struct ptp_clock_info *ptp, long delta) spin_lock_irqsave(&adapter->systim_lock, flags); incvalue = timinca & E1000_TIMINCA_INCVALUE_MASK; - - adjustment = mul_u64_u64_div_u64(incvalue, (u64)delta, - 1000000ULL << 16); - - incvalue = neg_adj ? (incvalue - adjustment) : (incvalue + adjustment); + incvalue = adjust_by_scaled_ppm(incvalue, delta); timinca &= ~E1000_TIMINCA_INCVALUE_MASK; timinca |= incvalue; @@ -297,6 +287,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if ((hw->mac.type < e1000_pch_lpt) || (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { adapter->ptp_clock_info.max_adj = 24000000 - 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 2cca9e84e31e..34ab5ff9823b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1229,10 +1229,10 @@ static void fm10k_get_stats64(struct net_device *netdev, continue; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; @@ -1245,10 +1245,10 @@ static void fm10k_get_stats64(struct net_device *netdev, continue; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 9a60d6b207f7..60e351665c70 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -992,6 +992,7 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; /* lan device */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 60f9e0a6aaca..3357d65a906b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1795,9 +1795,11 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_an_advt_reg); /* Set Loopback mode (0x0618) */ struct i40e_aqc_set_lb_mode { __le16 lb_mode; -#define I40E_AQ_LB_PHY_LOCAL 0x01 -#define I40E_AQ_LB_PHY_REMOTE 0x02 -#define I40E_AQ_LB_MAC_LOCAL 0x04 +#define I40E_LEGACY_LOOPBACK_NVM_VER 0x6000 +#define I40E_AQ_LB_MAC_LOCAL 0x01 +#define I40E_AQ_LB_PHY_LOCAL 0x05 +#define I40E_AQ_LB_PHY_REMOTE 0x06 +#define I40E_AQ_LB_MAC_LOCAL_LEGACY 0x04 u8 reserved[14]; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 4f01e2a6b6bb..8f764ff5c990 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1831,6 +1831,32 @@ i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw, } /** + * i40e_aq_set_mac_loopback + * @hw: pointer to the HW struct + * @ena_lpbk: Enable or Disable loopback + * @cmd_details: pointer to command details structure or NULL + * + * Enable/disable loopback on a given port + */ +i40e_status i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_set_lb_mode *cmd = + (struct i40e_aqc_set_lb_mode *)&desc.params.raw; + + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_lb_modes); + if (ena_lpbk) { + if (hw->nvm.version <= I40E_LEGACY_LOOPBACK_NVM_VER) + cmd->lb_mode = cpu_to_le16(I40E_AQ_LB_MAC_LOCAL_LEGACY); + else + cmd->lb_mode = cpu_to_le16(I40E_AQ_LB_MAC_LOCAL); + } + + return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); +} + +/** * i40e_aq_set_phy_debug * @hw: pointer to the hw struct * @cmd_flags: debug command flags diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index f6fa63e4253c..887a735fe2a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -154,7 +154,7 @@ __i40e_add_ethtool_stats(u64 **data, void *pointer, * @ring: the ring to copy * * Queue statistics must be copied while protected by - * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. + * u64_stats_fetch_begin, so we can't directly use i40e_add_ethtool_stats. * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the * ring pointer is null, zero out the queue stat values and update the data * pointer. Otherwise safely copy the stats from the ring into the supplied @@ -172,16 +172,16 @@ i40e_add_queue_stats(u64 **data, struct i40e_ring *ring) /* To avoid invalid statistics values, ensure that we keep retrying * the copy until we get a consistent value according to - * u64_stats_fetch_retry_irq. But first, make sure our ring is + * u64_stats_fetch_retry. But first, make sure our ring is * non-null before attempting to access its syncp. */ do { - start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + start = !ring ? 0 : u64_stats_fetch_begin(&ring->syncp); for (i = 0; i < size; i++) { i40e_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); } - } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (ring && u64_stats_fetch_retry(&ring->syncp, start)); /* Once we successfully copy the stats in, update the data pointer */ *data += size; @@ -1287,8 +1287,10 @@ static int i40e_set_link_ksettings(struct net_device *netdev, * trying to set something that we do not support. */ if (memcmp(©_ks.base, &safe_ks.base, - sizeof(struct ethtool_link_settings))) + sizeof(struct ethtool_link_settings))) { + netdev_err(netdev, "Only speed and autoneg are supported.\n"); return -EOPNOTSUPP; + } while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { timeout--; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e6e349f0c945..94feea3b2599 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -419,10 +419,10 @@ static void i40e_get_netdev_stats_struct_tx(struct i40e_ring *ring, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; @@ -472,10 +472,10 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, if (!ring) continue; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; @@ -897,10 +897,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) continue; do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); packets = p->stats.packets; bytes = p->stats.bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); tx_b += bytes; tx_p += packets; tx_restart += p->tx_stats.restart_queue; @@ -915,10 +915,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) continue; do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); packets = p->stats.packets; bytes = p->stats.bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); rx_b += bytes; rx_p += packets; rx_buf += p->rx_stats.alloc_buff_failed; @@ -935,10 +935,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) continue; do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); packets = p->stats.packets; bytes = p->stats.bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); tx_b += bytes; tx_p += packets; tx_restart += p->tx_stats.restart_queue; @@ -4135,6 +4135,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) } /* register for affinity change notifications */ + q_vector->irq_num = irq_num; q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); @@ -12949,6 +12950,29 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi) } /** + * i40e_set_loopback - turn on/off loopback mode on underlying PF + * @vsi: ptr to VSI + * @ena: flag to indicate the on/off setting + */ +static int i40e_set_loopback(struct i40e_vsi *vsi, bool ena) +{ + bool if_running = netif_running(vsi->netdev) && + !test_and_set_bit(__I40E_VSI_DOWN, vsi->state); + int ret; + + if (if_running) + i40e_down(vsi); + + ret = i40e_aq_set_mac_loopback(&vsi->back->hw, ena, NULL); + if (ret) + netdev_err(vsi->netdev, "Failed to toggle loopback state\n"); + if (if_running) + i40e_up(vsi); + + return ret; +} + +/** * i40e_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting @@ -12988,6 +13012,9 @@ static int i40e_set_features(struct net_device *netdev, if (need_reset) i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); + if ((features ^ netdev->features) & NETIF_F_LOOPBACK) + return i40e_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); + return 0; } @@ -13750,7 +13777,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - netdev->hw_features |= hw_features; + netdev->hw_features |= hw_features | NETIF_F_LOOPBACK; netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index ebdcde6f1aeb..9a71121420c3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -105,6 +105,9 @@ enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, bool atomic_reset); +i40e_status i40e_aq_set_mac_loopback(struct i40e_hw *hw, + bool ena_lpbk, + struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index ffea0c9c82f1..c37abbb3cd06 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -347,23 +347,12 @@ static int i40e_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); struct i40e_hw *hw = &pf->hw; - u64 adj, freq, diff; - int neg_adj = 0; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } + u64 adj, base_adj; smp_mb(); /* Force any pending update before accessing. */ - freq = I40E_PTP_40GB_INCVAL * READ_ONCE(pf->ptp_adj_mult); - diff = mul_u64_u64_div_u64(freq, (u64)scaled_ppm, - 1000000ULL << 16); + base_adj = I40E_PTP_40GB_INCVAL * READ_ONCE(pf->ptp_adj_mult); - if (neg_adj) - adj = I40E_PTP_40GB_INCVAL - diff; - else - adj = I40E_PTP_40GB_INCVAL + diff; + adj = adjust_by_scaled_ppm(base_adj, scaled_ppm); wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF); wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32); diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index b5b12299931f..79d587ad5409 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -55,6 +55,55 @@ * being built from shared code. */ +#define NO_DEV "(i40e no_device)" + +TRACE_EVENT(i40e_napi_poll, + + TP_PROTO(struct napi_struct *napi, struct i40e_q_vector *q, int budget, + int budget_per_ring, unsigned int rx_cleaned, unsigned int tx_cleaned, + bool rx_clean_complete, bool tx_clean_complete), + + TP_ARGS(napi, q, budget, budget_per_ring, rx_cleaned, tx_cleaned, + rx_clean_complete, tx_clean_complete), + + TP_STRUCT__entry( + __field(int, budget) + __field(int, budget_per_ring) + __field(unsigned int, rx_cleaned) + __field(unsigned int, tx_cleaned) + __field(int, rx_clean_complete) + __field(int, tx_clean_complete) + __field(int, irq_num) + __field(int, curr_cpu) + __string(qname, q->name) + __string(dev_name, napi->dev ? napi->dev->name : NO_DEV) + __bitmask(irq_affinity, nr_cpumask_bits) + ), + + TP_fast_assign( + __entry->budget = budget; + __entry->budget_per_ring = budget_per_ring; + __entry->rx_cleaned = rx_cleaned; + __entry->tx_cleaned = tx_cleaned; + __entry->rx_clean_complete = rx_clean_complete; + __entry->tx_clean_complete = tx_clean_complete; + __entry->irq_num = q->irq_num; + __entry->curr_cpu = get_cpu(); + __assign_str(qname, q->name); + __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); + __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), + nr_cpumask_bits); + ), + + TP_printk("i40e_napi_poll on dev %s q %s irq %d irq_mask %s curr_cpu %d " + "budget %d bpr %d rx_cleaned %u tx_cleaned %u " + "rx_clean_complete %d tx_clean_complete %d", + __get_str(dev_name), __get_str(qname), __entry->irq_num, + __get_bitmask(irq_affinity), __entry->curr_cpu, __entry->budget, + __entry->budget_per_ring, __entry->rx_cleaned, __entry->tx_cleaned, + __entry->rx_clean_complete, __entry->tx_clean_complete) +); + /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS( i40e_tx_template, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b97c95f89fa0..924f972b91fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -923,11 +923,13 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) * @vsi: the VSI we care about * @tx_ring: Tx ring to clean * @napi_budget: Used to determine if we are in netpoll + * @tx_cleaned: Out parameter set to the number of TXes cleaned * * Returns true if there's any budget left (e.g. the clean is finished) **/ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, - struct i40e_ring *tx_ring, int napi_budget) + struct i40e_ring *tx_ring, int napi_budget, + unsigned int *tx_cleaned) { int i = tx_ring->next_to_clean; struct i40e_tx_buffer *tx_buf; @@ -1048,6 +1050,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, } } + *tx_cleaned = total_packets; return !!budget; } @@ -2422,6 +2425,7 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring) * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process + * @rx_cleaned: Out parameter of the number of packets processed * * This function provides a "bounce buffer" approach to Rx interrupt * processing. The advantage to this is that on systems that have @@ -2430,7 +2434,8 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring) * * Returns amount of work completed **/ -static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) +static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, + unsigned int *rx_cleaned) { unsigned int total_rx_bytes = 0, total_rx_packets = 0, frame_sz = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); @@ -2567,6 +2572,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); + *rx_cleaned = total_rx_packets; + /* guarantee a trip back through this routine if there was a failure */ return failure ? budget : (int)total_rx_packets; } @@ -2689,6 +2696,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) container_of(napi, struct i40e_q_vector, napi); struct i40e_vsi *vsi = q_vector->vsi; struct i40e_ring *ring; + bool tx_clean_complete = true; + bool rx_clean_complete = true; + unsigned int tx_cleaned = 0; + unsigned int rx_cleaned = 0; bool clean_complete = true; bool arm_wb = false; int budget_per_ring; @@ -2705,10 +2716,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) i40e_for_each_ring(ring, q_vector->tx) { bool wd = ring->xsk_pool ? i40e_clean_xdp_tx_irq(vsi, ring) : - i40e_clean_tx_irq(vsi, ring, budget); + i40e_clean_tx_irq(vsi, ring, budget, &tx_cleaned); if (!wd) { - clean_complete = false; + clean_complete = tx_clean_complete = false; continue; } arm_wb |= ring->arm_wb; @@ -2733,14 +2744,18 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) i40e_for_each_ring(ring, q_vector->rx) { int cleaned = ring->xsk_pool ? i40e_clean_rx_irq_zc(ring, budget_per_ring) : - i40e_clean_rx_irq(ring, budget_per_ring); + i40e_clean_rx_irq(ring, budget_per_ring, &rx_cleaned); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ if (cleaned >= budget_per_ring) - clean_complete = false; + clean_complete = rx_clean_complete = false; } + if (!i40e_enabled_xdp_vsi(vsi)) + trace_i40e_napi_poll(napi, q_vector, budget, budget_per_ring, rx_cleaned, + tx_cleaned, rx_clean_complete, tx_clean_complete); + /* If work not completed, return budget and polling will return */ if (!clean_complete) { int cpu_id = smp_processor_id(); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index a056e1545615..d79ead5e8d0c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -147,7 +147,7 @@ __iavf_add_ethtool_stats(u64 **data, void *pointer, * @ring: the ring to copy * * Queue statistics must be copied while protected by - * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats. + * u64_stats_fetch_begin, so we can't directly use iavf_add_ethtool_stats. * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the * ring pointer is null, zero out the queue stat values and update the data * pointer. Otherwise safely copy the stats from the ring into the supplied @@ -165,14 +165,14 @@ iavf_add_queue_stats(u64 **data, struct iavf_ring *ring) /* To avoid invalid statistics values, ensure that we keep retrying * the copy until we get a consistent value according to - * u64_stats_fetch_retry_irq. But first, make sure our ring is + * u64_stats_fetch_retry. But first, make sure our ring is * non-null before attempting to access its syncp. */ do { - start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + start = !ring ? 0 : u64_stats_fetch_begin(&ring->syncp); for (i = 0; i < size; i++) iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); - } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (ring && u64_stats_fetch_retry(&ring->syncp, start)); /* Once we successfully copy the stats in, update the data pointer */ *data += size; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index f71e132ede09..c4e451ef7942 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4827,7 +4827,7 @@ static void iavf_shutdown(struct pci_dev *pdev) iavf_close(netdev); if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); + dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__); /* Prevent the watchdog from running. */ iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; @@ -5088,7 +5088,7 @@ static void iavf_remove(struct pci_dev *pdev) } mutex_lock(&adapter->crit_lock); - dev_info(&adapter->pdev->dev, "Remove device\n"); + dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); iavf_request_reset(adapter); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 001500afc4a6..2f0b604abc5e 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -137,6 +137,21 @@ */ #define ICE_BW_KBPS_DIVISOR 125 +/* Default recipes have priority 4 and below, hence priority values between 5..7 + * can be used as filter priority for advanced switch filter (advanced switch + * filters need new recipe to be created for specified extraction sequence + * because default recipe extraction sequence does not represent custom + * extraction) + */ +#define ICE_SWITCH_FLTR_PRIO_QUEUE 7 +/* prio 6 is reserved for future use (e.g. switch filter with L3 fields + + * (Optional: IP TOS/TTL) + L4 fields + (optionally: TCP fields such as + * SYN/FIN/RST)) + */ +#define ICE_SWITCH_FLTR_PRIO_RSVD 6 +#define ICE_SWITCH_FLTR_PRIO_VSI 5 +#define ICE_SWITCH_FLTR_PRIO_QGRP ICE_SWITCH_FLTR_PRIO_VSI + /* Macro for each VSI in a PF */ #define ice_for_each_vsi(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++) @@ -305,6 +320,11 @@ enum ice_vsi_state { ICE_VSI_STATE_NBITS /* must be last */ }; +struct ice_vsi_stats { + struct ice_ring_stats **tx_ring_stats; /* Tx ring stats array */ + struct ice_ring_stats **rx_ring_stats; /* Rx ring stats array */ +}; + /* struct that defines a VSI, associated with a dev */ struct ice_vsi { struct net_device *netdev; @@ -358,6 +378,7 @@ struct ice_vsi { /* VSI stats */ struct rtnl_link_stats64 net_stats; + struct rtnl_link_stats64 net_stats_prev; struct ice_eth_stats eth_stats; struct ice_eth_stats eth_stats_prev; @@ -525,6 +546,7 @@ struct ice_pf { u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ struct ice_vsi **vsi; /* VSIs created by the driver */ + struct ice_vsi_stats **vsi_stats; struct ice_sw *first_sw; /* first switch created by firmware */ u16 eswitch_mode; /* current mode of eswitch */ struct ice_vfs vfs; @@ -594,6 +616,8 @@ struct ice_pf { u16 num_dmac_chnl_fltrs; struct hlist_head tc_flower_fltr_list; + u64 supported_rxdids; + __le64 nvm_phy_type_lo; /* NVM PHY type low */ __le64 nvm_phy_type_hi; /* NVM PHY type high */ struct ice_link_default_override_tlv link_dflt_override; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 1bdc70aa979d..958c1e435232 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -848,9 +848,9 @@ struct ice_aqc_txsched_elem { u8 generic; #define ICE_AQC_ELEM_GENERIC_MODE_M 0x1 #define ICE_AQC_ELEM_GENERIC_PRIO_S 0x1 -#define ICE_AQC_ELEM_GENERIC_PRIO_M (0x7 << ICE_AQC_ELEM_GENERIC_PRIO_S) +#define ICE_AQC_ELEM_GENERIC_PRIO_M GENMASK(3, 1) #define ICE_AQC_ELEM_GENERIC_SP_S 0x4 -#define ICE_AQC_ELEM_GENERIC_SP_M (0x1 << ICE_AQC_ELEM_GENERIC_SP_S) +#define ICE_AQC_ELEM_GENERIC_SP_M GENMASK(4, 4) #define ICE_AQC_ELEM_GENERIC_ADJUST_VAL_S 0x5 #define ICE_AQC_ELEM_GENERIC_ADJUST_VAL_M \ (0x3 << ICE_AQC_ELEM_GENERIC_ADJUST_VAL_S) diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index e864634d66bc..554095b25f44 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -389,7 +389,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) * Indicates the starting address of the descriptor queue defined in * 128 Byte units. */ - rlan_ctx.base = ring->dma >> 7; + rlan_ctx.base = ring->dma >> ICE_RLAN_BASE_S; rlan_ctx.qlen = ring->count; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 039342a0ed15..d02b55b6aa9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1105,6 +1105,9 @@ int ice_init_hw(struct ice_hw *hw) hw->evb_veb = true; + /* init xarray for identifying scheduling nodes uniquely */ + xa_init_flags(&hw->port_info->sched_node_ids, XA_FLAGS_ALLOC); + /* Query the allocated resources for Tx scheduler */ status = ice_sched_query_res_alloc(hw); if (status) { @@ -2945,8 +2948,8 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw) * Note: In the structure of [phy_type_low, phy_type_high], there should * be one bit set, as this function will convert one PHY type to its * speed. - * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned - * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + * If no bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned + * If more than one bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned */ static u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) @@ -4600,7 +4603,7 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, q_ctx->q_teid = le32_to_cpu(node.node_teid); /* add a leaf node into scheduler tree queue layer */ - status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, &node); + status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, &node, NULL); if (!status) status = ice_sched_replay_q_bw(pi, q_ctx); @@ -4835,7 +4838,7 @@ ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, for (i = 0; i < num_qsets; i++) { node.node_teid = buf->rdma_qsets[i].qset_teid; ret = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, - &node); + &node, NULL); if (ret) break; qset_teid[i] = le32_to_cpu(node.node_teid); @@ -5512,3 +5515,40 @@ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) ICE_FW_API_REPORT_DFLT_CFG_MIN, ICE_FW_API_REPORT_DFLT_CFG_PATCH); } + +/* each of the indexes into the following array match the speed of a return + * value from the list of AQ returned speeds like the range: + * ICE_AQ_LINK_SPEED_10MB .. ICE_AQ_LINK_SPEED_100GB excluding + * ICE_AQ_LINK_SPEED_UNKNOWN which is BIT(15) and maps to BIT(14) in this + * array. The array is defined as 15 elements long because the link_speed + * returned by the firmware is a 16 bit * value, but is indexed + * by [fls(speed) - 1] + */ +static const u32 ice_aq_to_link_speed[15] = { + SPEED_10, /* BIT(0) */ + SPEED_100, + SPEED_1000, + SPEED_2500, + SPEED_5000, + SPEED_10000, + SPEED_20000, + SPEED_25000, + SPEED_40000, + SPEED_50000, + SPEED_100000, /* BIT(10) */ + 0, + 0, + 0, + 0 /* BIT(14) */ +}; + +/** + * ice_get_link_speed - get integer speed from table + * @index: array index from fls(aq speed) - 1 + * + * Returns: u32 value containing integer speed + */ +u32 ice_get_link_speed(u16 index) +{ + return ice_aq_to_link_speed[index]; +} diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 8b6712b92e84..4c6a0b5c9304 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -163,6 +163,7 @@ int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd); +u32 ice_get_link_speed(u16 index); int ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 0b146a0d4205..6be02f9b0b8c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -1580,7 +1580,7 @@ ice_update_port_tc_tree_cfg(struct ice_port_info *pi, /* new TC */ status = ice_sched_query_elem(pi->hw, teid2, &elem); if (!status) - status = ice_sched_add_node(pi, 1, &elem); + status = ice_sched_add_node(pi, 1, &elem, NULL); if (status) break; /* update the TC number */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index add90e75f05c..4f24d441c35e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -3,6 +3,7 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" +#include "ice_devlink.h" /** * ice_dcb_get_ena_tc - return bitmap of enabled TCs @@ -364,6 +365,12 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) /* Enable DCB tagging only when more than one TC */ if (ice_dcb_get_num_tc(new_cfg) > 1) { dev_dbg(dev, "DCB tagging enabled (num TC > 1)\n"); + if (pf->hw.port_info->is_custom_tx_enabled) { + dev_err(dev, "Custom Tx scheduler feature enabled, can't configure DCB\n"); + return -EBUSY; + } + ice_tear_down_devlink_rate_tree(pf); + set_bit(ICE_FLAG_DCB_ENA, pf->flags); } else { dev_dbg(dev, "DCB tagging disabled (num TC = 1)\n"); @@ -874,6 +881,9 @@ void ice_update_dcb_stats(struct ice_pf *pf) prev_ps = &pf->stats_prev; cur_ps = &pf->stats; + if (ice_is_reset_in_progress(pf->state)) + pf->stat_prev_loaded = false; + for (i = 0; i < 8; i++) { ice_stat_update32(hw, GLPRT_PXOFFRXC(port, i), pf->stat_prev_loaded, diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index e6ec20079ced..8286e47b4bae 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -8,6 +8,7 @@ #include "ice_devlink.h" #include "ice_eswitch.h" #include "ice_fw_update.h" +#include "ice_dcb_lib.h" static int ice_active_port_option = -1; @@ -310,12 +311,6 @@ static int ice_devlink_info_get(struct devlink *devlink, } } - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Unable to set driver name"); - goto out_free_ctx; - } - ice_info_get_dsn(pf, ctx); err = devlink_info_serial_number_put(req, ctx->buf); @@ -713,6 +708,490 @@ ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, return ice_devlink_port_split(devlink, port, 1, extack); } +/** + * ice_tear_down_devlink_rate_tree - removes devlink-rate exported tree + * @pf: pf struct + * + * This function tears down tree exported during VF's creation. + */ +void ice_tear_down_devlink_rate_tree(struct ice_pf *pf) +{ + struct devlink *devlink; + struct ice_vf *vf; + unsigned int bkt; + + devlink = priv_to_devlink(pf); + + devl_lock(devlink); + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { + if (vf->devlink_port.devlink_rate) + devl_rate_leaf_destroy(&vf->devlink_port); + } + mutex_unlock(&pf->vfs.table_lock); + + devl_rate_nodes_destroy(devlink); + devl_unlock(devlink); +} + +/** + * ice_enable_custom_tx - try to enable custom Tx feature + * @pf: pf struct + * + * This function tries to enable custom Tx feature, + * it's not possible to enable it, if DCB or ADQ is active. + */ +static bool ice_enable_custom_tx(struct ice_pf *pf) +{ + struct ice_port_info *pi = ice_get_main_vsi(pf)->port_info; + struct device *dev = ice_pf_to_dev(pf); + + if (pi->is_custom_tx_enabled) + /* already enabled, return true */ + return true; + + if (ice_is_adq_active(pf)) { + dev_err(dev, "ADQ active, can't modify Tx scheduler tree\n"); + return false; + } + + if (ice_is_dcb_active(pf)) { + dev_err(dev, "DCB active, can't modify Tx scheduler tree\n"); + return false; + } + + pi->is_custom_tx_enabled = true; + + return true; +} + +/** + * ice_traverse_tx_tree - traverse Tx scheduler tree + * @devlink: devlink struct + * @node: current node, used for recursion + * @tc_node: tc_node struct, that is treated as a root + * @pf: pf struct + * + * This function traverses Tx scheduler tree and exports + * entire structure to the devlink-rate. + */ +static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node *node, + struct ice_sched_node *tc_node, struct ice_pf *pf) +{ + struct devlink_rate *rate_node = NULL; + struct ice_vf *vf; + int i; + + if (node->parent == tc_node) { + /* create root node */ + rate_node = devl_rate_node_create(devlink, node, node->name, NULL); + } else if (node->vsi_handle && + pf->vsi[node->vsi_handle]->vf) { + vf = pf->vsi[node->vsi_handle]->vf; + if (!vf->devlink_port.devlink_rate) + /* leaf nodes doesn't have children + * so we don't set rate_node + */ + devl_rate_leaf_create(&vf->devlink_port, node, + node->parent->rate_node); + } else if (node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF && + node->parent->rate_node) { + rate_node = devl_rate_node_create(devlink, node, node->name, + node->parent->rate_node); + } + + if (rate_node && !IS_ERR(rate_node)) + node->rate_node = rate_node; + + for (i = 0; i < node->num_children; i++) + ice_traverse_tx_tree(devlink, node->children[i], tc_node, pf); +} + +/** + * ice_devlink_rate_init_tx_topology - export Tx scheduler tree to devlink rate + * @devlink: devlink struct + * @vsi: main vsi struct + * + * This function finds a root node, then calls ice_traverse_tx tree, which + * traverses the tree and exports it's contents to devlink rate. + */ +int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *vsi) +{ + struct ice_port_info *pi = vsi->port_info; + struct ice_sched_node *tc_node; + struct ice_pf *pf = vsi->back; + int i; + + tc_node = pi->root->children[0]; + mutex_lock(&pi->sched_lock); + devl_lock(devlink); + for (i = 0; i < tc_node->num_children; i++) + ice_traverse_tx_tree(devlink, tc_node->children[i], tc_node, pf); + devl_unlock(devlink); + mutex_unlock(&pi->sched_lock); + + return 0; +} + +/** + * ice_set_object_tx_share - sets node scheduling parameter + * @pi: devlink struct instance + * @node: node struct instance + * @bw: bandwidth in bytes per second + * @extack: extended netdev ack structure + * + * This function sets ICE_MIN_BW scheduling BW limit. + */ +static int ice_set_object_tx_share(struct ice_port_info *pi, struct ice_sched_node *node, + u64 bw, struct netlink_ext_ack *extack) +{ + int status; + + mutex_lock(&pi->sched_lock); + /* converts bytes per second to kilo bits per second */ + node->tx_share = div_u64(bw, 125); + status = ice_sched_set_node_bw_lmt(pi, node, ICE_MIN_BW, node->tx_share); + mutex_unlock(&pi->sched_lock); + + if (status) + NL_SET_ERR_MSG_MOD(extack, "Can't set scheduling node tx_share"); + + return status; +} + +/** + * ice_set_object_tx_max - sets node scheduling parameter + * @pi: devlink struct instance + * @node: node struct instance + * @bw: bandwidth in bytes per second + * @extack: extended netdev ack structure + * + * This function sets ICE_MAX_BW scheduling BW limit. + */ +static int ice_set_object_tx_max(struct ice_port_info *pi, struct ice_sched_node *node, + u64 bw, struct netlink_ext_ack *extack) +{ + int status; + + mutex_lock(&pi->sched_lock); + /* converts bytes per second value to kilo bits per second */ + node->tx_max = div_u64(bw, 125); + status = ice_sched_set_node_bw_lmt(pi, node, ICE_MAX_BW, node->tx_max); + mutex_unlock(&pi->sched_lock); + + if (status) + NL_SET_ERR_MSG_MOD(extack, "Can't set scheduling node tx_max"); + + return status; +} + +/** + * ice_set_object_tx_priority - sets node scheduling parameter + * @pi: devlink struct instance + * @node: node struct instance + * @priority: value representing priority for strict priority arbitration + * @extack: extended netdev ack structure + * + * This function sets priority of node among siblings. + */ +static int ice_set_object_tx_priority(struct ice_port_info *pi, struct ice_sched_node *node, + u32 priority, struct netlink_ext_ack *extack) +{ + int status; + + if (node->tx_priority >= 8) { + NL_SET_ERR_MSG_MOD(extack, "Priority should be less than 8"); + return -EINVAL; + } + + mutex_lock(&pi->sched_lock); + node->tx_priority = priority; + status = ice_sched_set_node_priority(pi, node, node->tx_priority); + mutex_unlock(&pi->sched_lock); + + if (status) + NL_SET_ERR_MSG_MOD(extack, "Can't set scheduling node tx_priority"); + + return status; +} + +/** + * ice_set_object_tx_weight - sets node scheduling parameter + * @pi: devlink struct instance + * @node: node struct instance + * @weight: value represeting relative weight for WFQ arbitration + * @extack: extended netdev ack structure + * + * This function sets node weight for WFQ algorithm. + */ +static int ice_set_object_tx_weight(struct ice_port_info *pi, struct ice_sched_node *node, + u32 weight, struct netlink_ext_ack *extack) +{ + int status; + + if (node->tx_weight > 200 || node->tx_weight < 1) { + NL_SET_ERR_MSG_MOD(extack, "Weight must be between 1 and 200"); + return -EINVAL; + } + + mutex_lock(&pi->sched_lock); + node->tx_weight = weight; + status = ice_sched_set_node_weight(pi, node, node->tx_weight); + mutex_unlock(&pi->sched_lock); + + if (status) + NL_SET_ERR_MSG_MOD(extack, "Can't set scheduling node tx_weight"); + + return status; +} + +/** + * ice_get_pi_from_dev_rate - get port info from devlink_rate + * @rate_node: devlink struct instance + * + * This function returns corresponding port_info struct of devlink_rate + */ +static struct ice_port_info *ice_get_pi_from_dev_rate(struct devlink_rate *rate_node) +{ + struct ice_pf *pf = devlink_priv(rate_node->devlink); + + return ice_get_main_vsi(pf)->port_info; +} + +static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node; + struct ice_port_info *pi; + + pi = ice_get_pi_from_dev_rate(rate_node); + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + /* preallocate memory for ice_sched_node */ + node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL); + *priv = node; + + return 0; +} + +static int ice_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node, *tc_node; + struct ice_port_info *pi; + + pi = ice_get_pi_from_dev_rate(rate_node); + tc_node = pi->root->children[0]; + node = priv; + + if (!rate_node->parent || !node || tc_node == node || !extack) + return 0; + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + /* can't allow to delete a node with children */ + if (node->num_children) + return -EINVAL; + + mutex_lock(&pi->sched_lock); + ice_free_sched_node(pi, node); + mutex_unlock(&pi->sched_lock); + + return 0; +} + +static int ice_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_leaf->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_max(ice_get_pi_from_dev_rate(rate_leaf), + node, tx_max, extack); +} + +static int ice_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_leaf->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_share(ice_get_pi_from_dev_rate(rate_leaf), node, + tx_share, extack); +} + +static int ice_devlink_rate_leaf_tx_priority_set(struct devlink_rate *rate_leaf, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_leaf->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_priority(ice_get_pi_from_dev_rate(rate_leaf), node, + tx_priority, extack); +} + +static int ice_devlink_rate_leaf_tx_weight_set(struct devlink_rate *rate_leaf, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_leaf->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_weight(ice_get_pi_from_dev_rate(rate_leaf), node, + tx_weight, extack); +} + +static int ice_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_max(ice_get_pi_from_dev_rate(rate_node), + node, tx_max, extack); +} + +static int ice_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_share(ice_get_pi_from_dev_rate(rate_node), + node, tx_share, extack); +} + +static int ice_devlink_rate_node_tx_priority_set(struct devlink_rate *rate_node, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_priority(ice_get_pi_from_dev_rate(rate_node), + node, tx_priority, extack); +} + +static int ice_devlink_rate_node_tx_weight_set(struct devlink_rate *rate_node, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack) +{ + struct ice_sched_node *node = priv; + + if (!ice_enable_custom_tx(devlink_priv(rate_node->devlink))) + return -EBUSY; + + if (!node) + return 0; + + return ice_set_object_tx_weight(ice_get_pi_from_dev_rate(rate_node), + node, tx_weight, extack); +} + +static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, + struct devlink_rate *parent, + void *priv, void *parent_priv, + struct netlink_ext_ack *extack) +{ + struct ice_port_info *pi = ice_get_pi_from_dev_rate(devlink_rate); + struct ice_sched_node *tc_node, *node, *parent_node; + u16 num_nodes_added; + u32 first_node_teid; + u32 node_teid; + int status; + + tc_node = pi->root->children[0]; + node = priv; + + if (!extack) + return 0; + + if (!ice_enable_custom_tx(devlink_priv(devlink_rate->devlink))) + return -EBUSY; + + if (!parent) { + if (!node || tc_node == node || node->num_children) + return -EINVAL; + + mutex_lock(&pi->sched_lock); + ice_free_sched_node(pi, node); + mutex_unlock(&pi->sched_lock); + + return 0; + } + + parent_node = parent_priv; + + /* if the node doesn't exist, create it */ + if (!node->parent) { + mutex_lock(&pi->sched_lock); + status = ice_sched_add_elems(pi, tc_node, parent_node, + parent_node->tx_sched_layer + 1, + 1, &num_nodes_added, &first_node_teid, + &node); + mutex_unlock(&pi->sched_lock); + + if (status) { + NL_SET_ERR_MSG_MOD(extack, "Can't add a new node"); + return status; + } + + if (devlink_rate->tx_share) + ice_set_object_tx_share(pi, node, devlink_rate->tx_share, extack); + if (devlink_rate->tx_max) + ice_set_object_tx_max(pi, node, devlink_rate->tx_max, extack); + if (devlink_rate->tx_priority) + ice_set_object_tx_priority(pi, node, devlink_rate->tx_priority, extack); + if (devlink_rate->tx_weight) + ice_set_object_tx_weight(pi, node, devlink_rate->tx_weight, extack); + } else { + node_teid = le32_to_cpu(node->info.node_teid); + mutex_lock(&pi->sched_lock); + status = ice_sched_move_nodes(pi, parent_node, 1, &node_teid); + mutex_unlock(&pi->sched_lock); + + if (status) + NL_SET_ERR_MSG_MOD(extack, "Can't move existing node to a new parent"); + } + + return status; +} + static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), @@ -725,6 +1204,22 @@ static const struct devlink_ops ice_devlink_ops = { .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, .flash_update = ice_devlink_flash_update, + + .rate_node_new = ice_devlink_rate_node_new, + .rate_node_del = ice_devlink_rate_node_del, + + .rate_leaf_tx_max_set = ice_devlink_rate_leaf_tx_max_set, + .rate_leaf_tx_share_set = ice_devlink_rate_leaf_tx_share_set, + .rate_leaf_tx_priority_set = ice_devlink_rate_leaf_tx_priority_set, + .rate_leaf_tx_weight_set = ice_devlink_rate_leaf_tx_weight_set, + + .rate_node_tx_max_set = ice_devlink_rate_node_tx_max_set, + .rate_node_tx_share_set = ice_devlink_rate_node_tx_share_set, + .rate_node_tx_priority_set = ice_devlink_rate_node_tx_priority_set, + .rate_node_tx_weight_set = ice_devlink_rate_node_tx_weight_set, + + .rate_leaf_parent_set = ice_devlink_set_parent, + .rate_node_parent_set = ice_devlink_set_parent, }; static int @@ -1033,12 +1528,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) */ void ice_devlink_destroy_pf_port(struct ice_pf *pf) { - struct devlink_port *devlink_port; - - devlink_port = &pf->devlink_port; - - devlink_port_type_clear(devlink_port); - devlink_port_unregister(devlink_port); + devlink_port_unregister(&pf->devlink_port); } /** @@ -1094,31 +1584,28 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) */ void ice_devlink_destroy_vf_port(struct ice_vf *vf) { - struct devlink_port *devlink_port; - - devlink_port = &vf->devlink_port; - - devlink_port_type_clear(devlink_port); - devlink_port_unregister(devlink_port); + devl_rate_leaf_destroy(&vf->devlink_port); + devlink_port_unregister(&vf->devlink_port); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) +static const struct devlink_region_ops ice_nvm_region_ops; +static const struct devlink_region_ops ice_sram_region_ops; + /** * ice_devlink_nvm_snapshot - Capture a snapshot of the NVM flash contents * @devlink: the devlink instance - * @ops: the devlink region being snapshotted + * @ops: the devlink region to snapshot * @extack: extended ACK response structure * @data: on exit points to snapshot data buffer * - * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for - * the nvm-flash devlink region. It captures a snapshot of the full NVM flash - * contents, including both banks of flash. This snapshot can later be viewed - * via the devlink-region interface. + * This function is called in response to a DEVLINK_CMD_REGION_NEW for either + * the nvm-flash or shadow-ram region. * - * It captures the flash using the FLASH_ONLY bit set when reading via - * firmware, so it does not read the current Shadow RAM contents. For that, - * use the shadow-ram region. + * It captures a snapshot of the NVM or Shadow RAM flash contents. This + * snapshot can then later be viewed via the DEVLINK_CMD_REGION_READ netlink + * interface. * * @returns zero on success, and updates the data pointer. Returns a non-zero * error code on failure. @@ -1130,17 +1617,27 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; + bool read_shadow_ram; u8 *nvm_data, *tmp, i; u32 nvm_size, left; s8 num_blks; int status; - nvm_size = hw->flash.flash_size; + if (ops == &ice_nvm_region_ops) { + read_shadow_ram = false; + nvm_size = hw->flash.flash_size; + } else if (ops == &ice_sram_region_ops) { + read_shadow_ram = true; + nvm_size = hw->flash.sr_words * 2u; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unexpected region in snapshot function"); + return -EOPNOTSUPP; + } + nvm_data = vzalloc(nvm_size); if (!nvm_data) return -ENOMEM; - num_blks = DIV_ROUND_UP(nvm_size, ICE_DEVLINK_READ_BLK_SIZE); tmp = nvm_data; left = nvm_size; @@ -1164,7 +1661,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, } status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE, - &read_sz, tmp, false); + &read_sz, tmp, read_shadow_ram); if (status) { dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", read_sz, status, hw->adminq.sq_last_status); @@ -1185,62 +1682,69 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, } /** - * ice_devlink_sram_snapshot - Capture a snapshot of the Shadow RAM contents + * ice_devlink_nvm_read - Read a portion of NVM flash contents * @devlink: the devlink instance - * @ops: the devlink region being snapshotted + * @ops: the devlink region to snapshot * @extack: extended ACK response structure - * @data: on exit points to snapshot data buffer + * @offset: the offset to start at + * @size: the amount to read + * @data: the data buffer to read into * - * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for - * the shadow-ram devlink region. It captures a snapshot of the shadow ram - * contents. This snapshot can later be viewed via the devlink-region - * interface. + * This function is called in response to DEVLINK_CMD_REGION_READ to directly + * read a section of the NVM contents. + * + * It reads from either the nvm-flash or shadow-ram region contents. * * @returns zero on success, and updates the data pointer. Returns a non-zero * error code on failure. */ -static int -ice_devlink_sram_snapshot(struct devlink *devlink, - const struct devlink_region_ops __always_unused *ops, - struct netlink_ext_ack *extack, u8 **data) +static int ice_devlink_nvm_read(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data) { struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - u8 *sram_data; - u32 sram_size; - int err; + bool read_shadow_ram; + u64 nvm_size; + int status; - sram_size = hw->flash.sr_words * 2u; - sram_data = vzalloc(sram_size); - if (!sram_data) - return -ENOMEM; + if (ops == &ice_nvm_region_ops) { + read_shadow_ram = false; + nvm_size = hw->flash.flash_size; + } else if (ops == &ice_sram_region_ops) { + read_shadow_ram = true; + nvm_size = hw->flash.sr_words * 2u; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unexpected region in snapshot function"); + return -EOPNOTSUPP; + } - err = ice_acquire_nvm(hw, ICE_RES_READ); - if (err) { + if (offset + size >= nvm_size) { + NL_SET_ERR_MSG_MOD(extack, "Cannot read beyond the region size"); + return -ERANGE; + } + + status = ice_acquire_nvm(hw, ICE_RES_READ); + if (status) { dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", - err, hw->adminq.sq_last_status); + status, hw->adminq.sq_last_status); NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); - vfree(sram_data); - return err; + return -EIO; } - /* Read from the Shadow RAM, rather than directly from NVM */ - err = ice_read_flat_nvm(hw, 0, &sram_size, sram_data, true); - if (err) { + status = ice_read_flat_nvm(hw, (u32)offset, &size, data, + read_shadow_ram); + if (status) { dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", - sram_size, err, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, - "Failed to read Shadow RAM contents"); + size, status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); ice_release_nvm(hw); - vfree(sram_data); - return err; + return -EIO; } - ice_release_nvm(hw); - *data = sram_data; - return 0; } @@ -1292,12 +1796,14 @@ static const struct devlink_region_ops ice_nvm_region_ops = { .name = "nvm-flash", .destructor = vfree, .snapshot = ice_devlink_nvm_snapshot, + .read = ice_devlink_nvm_read, }; static const struct devlink_region_ops ice_sram_region_ops = { .name = "shadow-ram", .destructor = vfree, - .snapshot = ice_devlink_sram_snapshot, + .snapshot = ice_devlink_nvm_snapshot, + .read = ice_devlink_nvm_read, }; static const struct devlink_region_ops ice_devcaps_region_ops = { diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/ice_devlink.h index fe006d9946f8..6ec96779f52e 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/ice_devlink.h @@ -18,4 +18,7 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf); void ice_devlink_init_regions(struct ice_pf *pf); void ice_devlink_destroy_regions(struct ice_pf *pf); +int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *vsi); +void ice_tear_down_devlink_rate_tree(struct ice_pf *pf); + #endif /* _ICE_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index b7be84bbe72d..4191994d8f3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -151,6 +151,175 @@ static const u32 ice_regs_dump_list[] = { QINT_RQCTL(0), PFINT_OICR_ENA, QRX_ITR(0), +#define GLDCB_TLPM_PCI_DM 0x000A0180 + GLDCB_TLPM_PCI_DM, +#define GLDCB_TLPM_TC2PFC 0x000A0194 + GLDCB_TLPM_TC2PFC, +#define TCDCB_TLPM_WAIT_DM(_i) (0x000A0080 + ((_i) * 4)) + TCDCB_TLPM_WAIT_DM(0), + TCDCB_TLPM_WAIT_DM(1), + TCDCB_TLPM_WAIT_DM(2), + TCDCB_TLPM_WAIT_DM(3), + TCDCB_TLPM_WAIT_DM(4), + TCDCB_TLPM_WAIT_DM(5), + TCDCB_TLPM_WAIT_DM(6), + TCDCB_TLPM_WAIT_DM(7), + TCDCB_TLPM_WAIT_DM(8), + TCDCB_TLPM_WAIT_DM(9), + TCDCB_TLPM_WAIT_DM(10), + TCDCB_TLPM_WAIT_DM(11), + TCDCB_TLPM_WAIT_DM(12), + TCDCB_TLPM_WAIT_DM(13), + TCDCB_TLPM_WAIT_DM(14), + TCDCB_TLPM_WAIT_DM(15), + TCDCB_TLPM_WAIT_DM(16), + TCDCB_TLPM_WAIT_DM(17), + TCDCB_TLPM_WAIT_DM(18), + TCDCB_TLPM_WAIT_DM(19), + TCDCB_TLPM_WAIT_DM(20), + TCDCB_TLPM_WAIT_DM(21), + TCDCB_TLPM_WAIT_DM(22), + TCDCB_TLPM_WAIT_DM(23), + TCDCB_TLPM_WAIT_DM(24), + TCDCB_TLPM_WAIT_DM(25), + TCDCB_TLPM_WAIT_DM(26), + TCDCB_TLPM_WAIT_DM(27), + TCDCB_TLPM_WAIT_DM(28), + TCDCB_TLPM_WAIT_DM(29), + TCDCB_TLPM_WAIT_DM(30), + TCDCB_TLPM_WAIT_DM(31), +#define GLPCI_WATMK_CLNT_PIPEMON 0x000BFD90 + GLPCI_WATMK_CLNT_PIPEMON, +#define GLPCI_CUR_CLNT_COMMON 0x000BFD84 + GLPCI_CUR_CLNT_COMMON, +#define GLPCI_CUR_CLNT_PIPEMON 0x000BFD88 + GLPCI_CUR_CLNT_PIPEMON, +#define GLPCI_PCIERR 0x0009DEB0 + GLPCI_PCIERR, +#define GLPSM_DEBUG_CTL_STATUS 0x000B0600 + GLPSM_DEBUG_CTL_STATUS, +#define GLPSM0_DEBUG_FIFO_OVERFLOW_DETECT 0x000B0680 + GLPSM0_DEBUG_FIFO_OVERFLOW_DETECT, +#define GLPSM0_DEBUG_FIFO_UNDERFLOW_DETECT 0x000B0684 + GLPSM0_DEBUG_FIFO_UNDERFLOW_DETECT, +#define GLPSM0_DEBUG_DT_OUT_OF_WINDOW 0x000B0688 + GLPSM0_DEBUG_DT_OUT_OF_WINDOW, +#define GLPSM0_DEBUG_INTF_HW_ERROR_DETECT 0x000B069C + GLPSM0_DEBUG_INTF_HW_ERROR_DETECT, +#define GLPSM0_DEBUG_MISC_HW_ERROR_DETECT 0x000B06A0 + GLPSM0_DEBUG_MISC_HW_ERROR_DETECT, +#define GLPSM1_DEBUG_FIFO_OVERFLOW_DETECT 0x000B0E80 + GLPSM1_DEBUG_FIFO_OVERFLOW_DETECT, +#define GLPSM1_DEBUG_FIFO_UNDERFLOW_DETECT 0x000B0E84 + GLPSM1_DEBUG_FIFO_UNDERFLOW_DETECT, +#define GLPSM1_DEBUG_SRL_FIFO_OVERFLOW_DETECT 0x000B0E88 + GLPSM1_DEBUG_SRL_FIFO_OVERFLOW_DETECT, +#define GLPSM1_DEBUG_SRL_FIFO_UNDERFLOW_DETECT 0x000B0E8C + GLPSM1_DEBUG_SRL_FIFO_UNDERFLOW_DETECT, +#define GLPSM1_DEBUG_MISC_HW_ERROR_DETECT 0x000B0E90 + GLPSM1_DEBUG_MISC_HW_ERROR_DETECT, +#define GLPSM2_DEBUG_FIFO_OVERFLOW_DETECT 0x000B1680 + GLPSM2_DEBUG_FIFO_OVERFLOW_DETECT, +#define GLPSM2_DEBUG_FIFO_UNDERFLOW_DETECT 0x000B1684 + GLPSM2_DEBUG_FIFO_UNDERFLOW_DETECT, +#define GLPSM2_DEBUG_MISC_HW_ERROR_DETECT 0x000B1688 + GLPSM2_DEBUG_MISC_HW_ERROR_DETECT, +#define GLTDPU_TCLAN_COMP_BOB(_i) (0x00049ADC + ((_i) * 4)) + GLTDPU_TCLAN_COMP_BOB(1), + GLTDPU_TCLAN_COMP_BOB(2), + GLTDPU_TCLAN_COMP_BOB(3), + GLTDPU_TCLAN_COMP_BOB(4), + GLTDPU_TCLAN_COMP_BOB(5), + GLTDPU_TCLAN_COMP_BOB(6), + GLTDPU_TCLAN_COMP_BOB(7), + GLTDPU_TCLAN_COMP_BOB(8), +#define GLTDPU_TCB_CMD_BOB(_i) (0x0004975C + ((_i) * 4)) + GLTDPU_TCB_CMD_BOB(1), + GLTDPU_TCB_CMD_BOB(2), + GLTDPU_TCB_CMD_BOB(3), + GLTDPU_TCB_CMD_BOB(4), + GLTDPU_TCB_CMD_BOB(5), + GLTDPU_TCB_CMD_BOB(6), + GLTDPU_TCB_CMD_BOB(7), + GLTDPU_TCB_CMD_BOB(8), +#define GLTDPU_PSM_UPDATE_BOB(_i) (0x00049B5C + ((_i) * 4)) + GLTDPU_PSM_UPDATE_BOB(1), + GLTDPU_PSM_UPDATE_BOB(2), + GLTDPU_PSM_UPDATE_BOB(3), + GLTDPU_PSM_UPDATE_BOB(4), + GLTDPU_PSM_UPDATE_BOB(5), + GLTDPU_PSM_UPDATE_BOB(6), + GLTDPU_PSM_UPDATE_BOB(7), + GLTDPU_PSM_UPDATE_BOB(8), +#define GLTCB_CMD_IN_BOB(_i) (0x000AE288 + ((_i) * 4)) + GLTCB_CMD_IN_BOB(1), + GLTCB_CMD_IN_BOB(2), + GLTCB_CMD_IN_BOB(3), + GLTCB_CMD_IN_BOB(4), + GLTCB_CMD_IN_BOB(5), + GLTCB_CMD_IN_BOB(6), + GLTCB_CMD_IN_BOB(7), + GLTCB_CMD_IN_BOB(8), +#define GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(_i) (0x000FC148 + ((_i) * 4)) + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(1), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(2), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(3), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(4), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(5), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(6), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(7), + GLLAN_TCLAN_FETCH_CTL_FBK_BOB_CTL(8), +#define GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(_i) (0x000FC248 + ((_i) * 4)) + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(1), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(2), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(3), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(4), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(5), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(6), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(7), + GLLAN_TCLAN_FETCH_CTL_SCHED_BOB_CTL(8), +#define GLLAN_TCLAN_CACHE_CTL_BOB_CTL(_i) (0x000FC1C8 + ((_i) * 4)) + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(1), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(2), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(3), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(4), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(5), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(6), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(7), + GLLAN_TCLAN_CACHE_CTL_BOB_CTL(8), +#define GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(_i) (0x000FC188 + ((_i) * 4)) + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(1), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(2), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(3), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(4), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(5), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(6), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(7), + GLLAN_TCLAN_FETCH_CTL_PROC_BOB_CTL(8), +#define GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(_i) (0x000FC288 + ((_i) * 4)) + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(1), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(2), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(3), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(4), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(5), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(6), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(7), + GLLAN_TCLAN_FETCH_CTL_PCIE_RD_BOB_CTL(8), +#define PRTDCB_TCUPM_REG_CM(_i) (0x000BC360 + ((_i) * 4)) + PRTDCB_TCUPM_REG_CM(0), + PRTDCB_TCUPM_REG_CM(1), + PRTDCB_TCUPM_REG_CM(2), + PRTDCB_TCUPM_REG_CM(3), +#define PRTDCB_TCUPM_REG_DM(_i) (0x000BC3A0 + ((_i) * 4)) + PRTDCB_TCUPM_REG_DM(0), + PRTDCB_TCUPM_REG_DM(1), + PRTDCB_TCUPM_REG_DM(2), + PRTDCB_TCUPM_REG_DM(3), +#define PRTDCB_TLPM_REG_DM(_i) (0x000A0000 + ((_i) * 4)) + PRTDCB_TLPM_REG_DM(0), + PRTDCB_TLPM_REG_DM(1), + PRTDCB_TLPM_REG_DM(2), + PRTDCB_TLPM_REG_DM(3), }; struct ice_priv_flag { @@ -1375,9 +1544,9 @@ __ice_get_ethtool_stats(struct net_device *netdev, ice_for_each_alloc_txq(vsi, j) { tx_ring = READ_ONCE(vsi->tx_rings[j]); - if (tx_ring) { - data[i++] = tx_ring->stats.pkts; - data[i++] = tx_ring->stats.bytes; + if (tx_ring && tx_ring->ring_stats) { + data[i++] = tx_ring->ring_stats->stats.pkts; + data[i++] = tx_ring->ring_stats->stats.bytes; } else { data[i++] = 0; data[i++] = 0; @@ -1386,9 +1555,9 @@ __ice_get_ethtool_stats(struct net_device *netdev, ice_for_each_alloc_rxq(vsi, j) { rx_ring = READ_ONCE(vsi->rx_rings[j]); - if (rx_ring) { - data[i++] = rx_ring->stats.pkts; - data[i++] = rx_ring->stats.bytes; + if (rx_ring && rx_ring->ring_stats) { + data[i++] = rx_ring->ring_stats->stats.pkts; + data[i++] = rx_ring->ring_stats->stats.bytes; } else { data[i++] = 0; data[i++] = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index d16738a3d3a7..a92dc9a16035 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -110,6 +110,9 @@ #define PRTDCB_TUP2TC 0x001D26C0 #define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4)) #define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4)) +#define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0 #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index b3baf7c3f910..89f986a75cc8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -908,17 +908,5 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) return ice_ptype_lkup[ptype]; } -#define ICE_LINK_SPEED_UNKNOWN 0 -#define ICE_LINK_SPEED_10MBPS 10 -#define ICE_LINK_SPEED_100MBPS 100 -#define ICE_LINK_SPEED_1000MBPS 1000 -#define ICE_LINK_SPEED_2500MBPS 2500 -#define ICE_LINK_SPEED_5000MBPS 5000 -#define ICE_LINK_SPEED_10000MBPS 10000 -#define ICE_LINK_SPEED_20000MBPS 20000 -#define ICE_LINK_SPEED_25000MBPS 25000 -#define ICE_LINK_SPEED_40000MBPS 40000 -#define ICE_LINK_SPEED_50000MBPS 50000 -#define ICE_LINK_SPEED_100000MBPS 100000 #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 7276badfa19e..94aa834cd9a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -448,6 +448,49 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d } /** + * ice_vsi_alloc_stat_arrays - Allocate statistics arrays + * @vsi: VSI pointer + */ +static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + + if (vsi->type == ICE_VSI_CHNL) + return 0; + if (!pf->vsi_stats) + return -ENOENT; + + vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL); + if (!vsi_stat) + return -ENOMEM; + + vsi_stat->tx_ring_stats = + kcalloc(vsi->alloc_txq, sizeof(*vsi_stat->tx_ring_stats), + GFP_KERNEL); + if (!vsi_stat->tx_ring_stats) + goto err_alloc_tx; + + vsi_stat->rx_ring_stats = + kcalloc(vsi->alloc_rxq, sizeof(*vsi_stat->rx_ring_stats), + GFP_KERNEL); + if (!vsi_stat->rx_ring_stats) + goto err_alloc_rx; + + pf->vsi_stats[vsi->idx] = vsi_stat; + + return 0; + +err_alloc_rx: + kfree(vsi_stat->rx_ring_stats); +err_alloc_tx: + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; + return -ENOMEM; +} + +/** * ice_vsi_alloc - Allocates the next available struct VSI in the PF * @pf: board private structure * @vsi_type: type of VSI @@ -560,6 +603,11 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, if (vsi->type == ICE_VSI_CTRL && vf) vf->ctrl_vsi_idx = vsi->idx; + + /* allocate memory for Tx/Rx ring stat pointers */ + if (ice_vsi_alloc_stat_arrays(vsi)) + goto err_rings; + goto unlock_pf; err_rings: @@ -1536,6 +1584,106 @@ err_out: } /** + * ice_vsi_free_stats - Free the ring statistics structures + * @vsi: VSI pointer + */ +static void ice_vsi_free_stats(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (vsi->type == ICE_VSI_CHNL) + return; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + ice_for_each_alloc_txq(vsi, i) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + + ice_for_each_alloc_rxq(vsi, i) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat->rx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; +} + +/** + * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI + * @vsi: VSI which is having stats allocated + */ +static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) +{ + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; + struct ice_vsi_stats *vsi_stats; + struct ice_pf *pf = vsi->back; + u16 i; + + vsi_stats = pf->vsi_stats[vsi->idx]; + tx_ring_stats = vsi_stats->tx_ring_stats; + rx_ring_stats = vsi_stats->rx_ring_stats; + + /* Allocate Tx ring stats */ + ice_for_each_alloc_txq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_tx_ring *ring; + + ring = vsi->tx_rings[i]; + ring_stats = tx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(tx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + /* Allocate Rx ring stats */ + ice_for_each_alloc_rxq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_rx_ring *ring; + + ring = vsi->rx_rings[i]; + ring_stats = rx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(rx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + return 0; + +err_out: + ice_vsi_free_stats(vsi); + return -ENOMEM; +} + +/** * ice_vsi_manage_rss_lut - disable/enable RSS * @vsi: the VSI being changed * @ena: boolean value indicating if this is an enable or disable request @@ -1795,11 +1943,15 @@ void ice_update_eth_stats(struct ice_vsi *vsi) { struct ice_eth_stats *prev_es, *cur_es; struct ice_hw *hw = &vsi->back->hw; + struct ice_pf *pf = vsi->back; u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ prev_es = &vsi->eth_stats_prev; cur_es = &vsi->eth_stats; + if (ice_is_reset_in_progress(pf->state)) + vsi->stat_offsets_loaded = false; + ice_stat_update40(hw, GLV_GORCL(vsi_num), vsi->stat_offsets_loaded, &prev_es->rx_bytes, &cur_es->rx_bytes); @@ -2576,6 +2728,10 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; + ice_vsi_map_rings_to_vectors(vsi); /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -2614,6 +2770,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2627,6 +2786,11 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ret = ice_vsi_alloc_rings(vsi); if (ret) goto unroll_vsi_init; + + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; + break; default: /* clean up the resources and exit */ @@ -2686,6 +2850,7 @@ unroll_vector_base: unroll_alloc_q_vector: ice_vsi_free_q_vectors(vsi); unroll_vsi_init: + ice_vsi_free_stats(vsi); ice_vsi_delete(vsi); unroll_get_qs: ice_vsi_put_qs(vsi); @@ -3077,7 +3242,7 @@ int ice_vsi_release(struct ice_vsi *vsi) vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; ice_vsi_clear_rings(vsi); - + ice_vsi_free_stats(vsi); ice_vsi_put_qs(vsi); /* retain SW VSI data structure since it is needed to unregister and @@ -3205,6 +3370,47 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, } /** + * ice_vsi_realloc_stat_arrays - Frees unused stat structures + * @vsi: VSI pointer + * @prev_txq: Number of Tx rings before ring reallocation + * @prev_rxq: Number of Rx rings before ring reallocation + */ +static int +ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (!prev_txq || !prev_rxq) + return 0; + if (vsi->type == ICE_VSI_CHNL) + return 0; + + vsi_stat = pf->vsi_stats[vsi->idx]; + + if (vsi->num_txq < prev_txq) { + for (i = vsi->num_txq; i < prev_txq; i++) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + } + + if (vsi->num_rxq < prev_rxq) { + for (i = vsi->num_rxq; i < prev_rxq; i++) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + } + + return 0; +} + +/** * ice_vsi_rebuild - Rebuild VSI after reset * @vsi: VSI to be rebuild * @init_vsi: is this an initialization or a reconfigure of the VSI @@ -3215,10 +3421,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_coalesce_stored *coalesce; + int ret, i, prev_txq, prev_rxq; int prev_num_q_vectors = 0; enum ice_vsi_type vtype; struct ice_pf *pf; - int ret, i; if (!vsi) return -EINVAL; @@ -3237,6 +3443,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); + prev_txq = vsi->num_txq; + prev_rxq = vsi->num_rxq; + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); if (ret) @@ -3303,7 +3512,13 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret) goto err_vectors; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto err_vectors; + ice_vsi_map_rings_to_vectors(vsi); + + vsi->stat_offsets_loaded = false; if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -3340,6 +3555,11 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret) goto err_vectors; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto err_vectors; + + vsi->stat_offsets_loaded = false; break; case ICE_VSI_CHNL: if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { @@ -3387,6 +3607,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) return ice_schedule_reset(pf, ICE_RESET_PFR); } } + + if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq)) + goto err_vectors; + ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); kfree(coalesce); @@ -3728,9 +3952,9 @@ static void ice_update_ring_stats(struct ice_q_stats *stats, u64 pkts, u64 bytes */ void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) { - u64_stats_update_begin(&tx_ring->syncp); - ice_update_ring_stats(&tx_ring->stats, pkts, bytes); - u64_stats_update_end(&tx_ring->syncp); + u64_stats_update_begin(&tx_ring->ring_stats->syncp); + ice_update_ring_stats(&tx_ring->ring_stats->stats, pkts, bytes); + u64_stats_update_end(&tx_ring->ring_stats->syncp); } /** @@ -3741,9 +3965,9 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) */ void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) { - u64_stats_update_begin(&rx_ring->syncp); - ice_update_ring_stats(&rx_ring->stats, pkts, bytes); - u64_stats_update_end(&rx_ring->syncp); + u64_stats_update_begin(&rx_ring->ring_stats->syncp); + ice_update_ring_stats(&rx_ring->ring_stats->stats, pkts, bytes); + u64_stats_update_end(&rx_ring->ring_stats->syncp); } /** @@ -3850,33 +4074,11 @@ int ice_clear_dflt_vsi(struct ice_vsi *vsi) */ int ice_get_link_speed_mbps(struct ice_vsi *vsi) { - switch (vsi->port_info->phy.link_info.link_speed) { - case ICE_AQ_LINK_SPEED_100GB: - return SPEED_100000; - case ICE_AQ_LINK_SPEED_50GB: - return SPEED_50000; - case ICE_AQ_LINK_SPEED_40GB: - return SPEED_40000; - case ICE_AQ_LINK_SPEED_25GB: - return SPEED_25000; - case ICE_AQ_LINK_SPEED_20GB: - return SPEED_20000; - case ICE_AQ_LINK_SPEED_10GB: - return SPEED_10000; - case ICE_AQ_LINK_SPEED_5GB: - return SPEED_5000; - case ICE_AQ_LINK_SPEED_2500MB: - return SPEED_2500; - case ICE_AQ_LINK_SPEED_1000MB: - return SPEED_1000; - case ICE_AQ_LINK_SPEED_100MB: - return SPEED_100; - case ICE_AQ_LINK_SPEED_10MB: - return SPEED_10; - case ICE_AQ_LINK_SPEED_UNKNOWN: - default: - return 0; - } + unsigned int link_speed; + + link_speed = vsi->port_info->phy.link_info.link_speed; + + return (int)ice_get_link_speed(fls(link_speed) - 1); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ca2898467dcb..a9a7f8b52140 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -130,12 +130,17 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) ice_for_each_txq(vsi, i) { struct ice_tx_ring *tx_ring = vsi->tx_rings[i]; + struct ice_ring_stats *ring_stats; if (!tx_ring) continue; if (ice_ring_ch_enabled(tx_ring)) continue; + ring_stats = tx_ring->ring_stats; + if (!ring_stats) + continue; + if (tx_ring->desc) { /* If packet counter has not changed the queue is * likely stalled, so force an interrupt for this @@ -144,8 +149,8 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) * prev_pkt would be negative if there was no * pending work. */ - packets = tx_ring->stats.pkts & INT_MAX; - if (tx_ring->tx_stats.prev_pkt == packets) { + packets = ring_stats->stats.pkts & INT_MAX; + if (ring_stats->tx_stats.prev_pkt == packets) { /* Trigger sw interrupt to revive the queue */ ice_trigger_sw_intr(hw, tx_ring->q_vector); continue; @@ -155,7 +160,7 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) * to ice_get_tx_pending() */ smp_rmb(); - tx_ring->tx_stats.prev_pkt = + ring_stats->tx_stats.prev_pkt = ice_get_tx_pending(tx_ring) ? packets : -1; } } @@ -299,20 +304,6 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) } /** - * ice_get_devlink_port - Get devlink port from netdev - * @netdev: the netdevice structure - */ -static struct devlink_port *ice_get_devlink_port(struct net_device *netdev) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - - if (!ice_is_switchdev_running(pf)) - return NULL; - - return &pf->devlink_port; -} - -/** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -1120,8 +1111,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return 0; - if (!ice_is_e810(&pf->hw)) - ice_ptp_link_change(pf, pf->hw.pf_id, link_up); + ice_ptp_link_change(pf, pf->hw.pf_id, link_up); if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -2560,13 +2550,20 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) ice_for_each_xdp_txq(vsi, i) { u16 xdp_q_idx = vsi->alloc_txq + i; + struct ice_ring_stats *ring_stats; struct ice_tx_ring *xdp_ring; xdp_ring = kzalloc(sizeof(*xdp_ring), GFP_KERNEL); - if (!xdp_ring) goto free_xdp_rings; + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) { + ice_free_tx_ring(xdp_ring); + goto free_xdp_rings; + } + + xdp_ring->ring_stats = ring_stats; xdp_ring->q_index = xdp_q_idx; xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx]; xdp_ring->vsi = vsi; @@ -2589,9 +2586,13 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) return 0; free_xdp_rings: - for (; i >= 0; i--) - if (vsi->xdp_rings[i] && vsi->xdp_rings[i]->desc) + for (; i >= 0; i--) { + if (vsi->xdp_rings[i] && vsi->xdp_rings[i]->desc) { + kfree_rcu(vsi->xdp_rings[i]->ring_stats, rcu); + vsi->xdp_rings[i]->ring_stats = NULL; ice_free_tx_ring(vsi->xdp_rings[i]); + } + } return -ENOMEM; } @@ -2792,6 +2793,8 @@ free_qmap: synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); } + kfree_rcu(vsi->xdp_rings[i]->ring_stats, rcu); + vsi->xdp_rings[i]->ring_stats = NULL; kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -4603,6 +4606,7 @@ static int ice_register_netdev(struct ice_pf *pf) if (err) goto err_devlink_create; + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); err = register_netdev(vsi->netdev); if (err) goto err_register_netdev; @@ -4611,8 +4615,6 @@ static int ice_register_netdev(struct ice_pf *pf) netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); - devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev); - return 0; err_register_netdev: ice_devlink_destroy_pf_port(pf); @@ -4771,11 +4773,18 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_init_pf_unroll; } + pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, + sizeof(*pf->vsi_stats), GFP_KERNEL); + if (!pf->vsi_stats) { + err = -ENOMEM; + goto err_init_vsi_unroll; + } + err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_vsi_unroll; + goto err_init_vsi_stats_unroll; } /* In case of MSIX we are going to setup the misc vector right here @@ -4956,6 +4965,9 @@ err_msix_misc_unroll: ice_free_irq_msix_misc(pf); err_init_interrupt_unroll: ice_clear_interrupt_scheme(pf); +err_init_vsi_stats_unroll: + devm_kfree(dev, pf->vsi_stats); + pf->vsi_stats = NULL; err_init_vsi_unroll: devm_kfree(dev, pf->vsi); err_init_pf_unroll: @@ -5078,6 +5090,8 @@ static void ice_remove(struct pci_dev *pdev) continue; ice_vsi_free_q_vectors(pf->vsi[i]); } + devm_kfree(&pdev->dev, pf->vsi_stats); + pf->vsi_stats = NULL; ice_deinit_pf(pf); ice_devlink_destroy_regions(pf); ice_deinit_hw(&pf->hw); @@ -6325,8 +6339,7 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - if (!ice_is_e810(&pf->hw)) - ice_ptp_link_change(pf, pf->hw.pf_id, true); + ice_ptp_link_change(pf, pf->hw.pf_id, true); } /* Perform an initial read of the statistics registers now to @@ -6370,10 +6383,10 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, unsigned int start; do { - start = u64_stats_fetch_begin_irq(syncp); + start = u64_stats_fetch_begin(syncp); *pkts = stats.pkts; *bytes = stats.bytes; - } while (u64_stats_fetch_retry_irq(syncp, start)); + } while (u64_stats_fetch_retry(syncp, start)); } /** @@ -6395,14 +6408,16 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, u64 pkts = 0, bytes = 0; ring = READ_ONCE(rings[i]); - if (!ring) + if (!ring || !ring->ring_stats) continue; - ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); + ice_fetch_u64_stats_per_ring(&ring->ring_stats->syncp, + ring->ring_stats->stats, &pkts, + &bytes); vsi_stats->tx_packets += pkts; vsi_stats->tx_bytes += bytes; - vsi->tx_restart += ring->tx_stats.restart_q; - vsi->tx_busy += ring->tx_stats.tx_busy; - vsi->tx_linearize += ring->tx_stats.tx_linearize; + vsi->tx_restart += ring->ring_stats->tx_stats.restart_q; + vsi->tx_busy += ring->ring_stats->tx_stats.tx_busy; + vsi->tx_linearize += ring->ring_stats->tx_stats.tx_linearize; } } @@ -6412,6 +6427,7 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, */ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { + struct rtnl_link_stats64 *net_stats, *stats_prev; struct rtnl_link_stats64 *vsi_stats; u64 pkts, bytes; int i; @@ -6436,12 +6452,16 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { struct ice_rx_ring *ring = READ_ONCE(vsi->rx_rings[i]); + struct ice_ring_stats *ring_stats; - ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); + ring_stats = ring->ring_stats; + ice_fetch_u64_stats_per_ring(&ring_stats->syncp, + ring_stats->stats, &pkts, + &bytes); vsi_stats->rx_packets += pkts; vsi_stats->rx_bytes += bytes; - vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed; - vsi->rx_page_failed += ring->rx_stats.alloc_page_failed; + vsi->rx_buf_failed += ring_stats->rx_stats.alloc_buf_failed; + vsi->rx_page_failed += ring_stats->rx_stats.alloc_page_failed; } /* update XDP Tx rings counters */ @@ -6451,10 +6471,28 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) rcu_read_unlock(); - vsi->net_stats.tx_packets = vsi_stats->tx_packets; - vsi->net_stats.tx_bytes = vsi_stats->tx_bytes; - vsi->net_stats.rx_packets = vsi_stats->rx_packets; - vsi->net_stats.rx_bytes = vsi_stats->rx_bytes; + net_stats = &vsi->net_stats; + stats_prev = &vsi->net_stats_prev; + + /* clear prev counters after reset */ + if (vsi_stats->tx_packets < stats_prev->tx_packets || + vsi_stats->rx_packets < stats_prev->rx_packets) { + stats_prev->tx_packets = 0; + stats_prev->tx_bytes = 0; + stats_prev->rx_packets = 0; + stats_prev->rx_bytes = 0; + } + + /* update netdev counters */ + net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets; + net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes; + net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets; + net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes; + + stats_prev->tx_packets = vsi_stats->tx_packets; + stats_prev->tx_bytes = vsi_stats->tx_bytes; + stats_prev->rx_packets = vsi_stats->rx_packets; + stats_prev->rx_bytes = vsi_stats->rx_bytes; kfree(vsi_stats); } @@ -6516,6 +6554,9 @@ void ice_update_pf_stats(struct ice_pf *pf) prev_ps = &pf->stats_prev; cur_ps = &pf->stats; + if (ice_is_reset_in_progress(pf->state)) + pf->stat_prev_loaded = false; + ice_stat_update40(hw, GLPRT_GORCL(port), pf->stat_prev_loaded, &prev_ps->eth.rx_bytes, &cur_ps->eth.rx_bytes); @@ -6730,8 +6771,7 @@ int ice_down(struct ice_vsi *vsi) if (vsi->netdev && vsi->type == ICE_VSI_PF) { vlan_err = ice_vsi_del_vlan_zero(vsi); - if (!ice_is_e810(&vsi->back->hw)) - ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); + ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); } else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { @@ -8283,7 +8323,7 @@ static void ice_rem_all_chnl_fltrs(struct ice_pf *pf) rule.rid = fltr->rid; rule.rule_id = fltr->rule_id; - rule.vsi_handle = fltr->dest_id; + rule.vsi_handle = fltr->dest_vsi_handle; status = ice_rem_adv_rule_by_id(&pf->hw, &rule); if (status) { if (status == -ENOENT) @@ -8595,6 +8635,12 @@ static int ice_setup_tc_mqprio_qdisc(struct net_device *netdev, void *type_data) switch (mode) { case TC_MQPRIO_MODE_CHANNEL: + if (pf->hw.port_info->is_custom_tx_enabled) { + dev_err(dev, "Custom Tx scheduler feature enabled, can't configure ADQ\n"); + return -EBUSY; + } + ice_tear_down_devlink_rate_tree(pf); + ret = ice_validate_mqprio_qopt(vsi, mqprio_qopt); if (ret) { netdev_err(netdev, "failed to validate_mqprio_qopt(), ret %d\n", @@ -9108,5 +9154,4 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_bpf = ice_xdp, .ndo_xdp_xmit = ice_xdp_xmit, .ndo_xsk_wakeup = ice_xsk_wakeup, - .ndo_get_devlink_port = ice_get_devlink_port, }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 0f668468d141..d63161d73eb1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -600,6 +600,23 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) } /** + * ice_ptp_is_tx_tracker_up - Check if Tx tracker is ready for new timestamps + * @tx: the PTP Tx timestamp tracker to check + * + * Check that a given PTP Tx timestamp tracker is up, i.e. that it is ready + * to accept new timestamp requests. + * + * Assumes the tx->lock spinlock is already held. + */ +static bool +ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) +{ + lockdep_assert_held(&tx->lock); + + return tx->init && !tx->calibrating; +} + +/** * ice_ptp_tx_tstamp - Process Tx timestamps for a port * @tx: the PTP Tx timestamp tracker * @@ -608,11 +625,13 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) * * If a given index has a valid timestamp, perform the following steps: * - * 1) copy the timestamp out of the PHY register - * 4) clear the timestamp valid bit in the PHY register - * 5) unlock the index by clearing the associated in_use bit. - * 2) extend the 40b timestamp value to get a 64bit timestamp - * 3) send that timestamp to the stack + * 1) check that the timestamp request is not stale + * 2) check that a timestamp is ready and available in the PHY memory bank + * 3) read and copy the timestamp out of the PHY register + * 4) unlock the index by clearing the associated in_use bit + * 5) check if the timestamp is stale, and discard if so + * 6) extend the 40 bit timestamp value to get a 64 bit timestamp value + * 7) send this 64 bit timestamp to the stack * * Returns true if all timestamps were handled, and false if any slots remain * without a timestamp. @@ -623,24 +642,45 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) * interrupt. In some cases hardware might not interrupt us again when the * timestamp is captured. * - * Note that we only take the tracking lock when clearing the bit and when - * checking if we need to re-queue this task. The only place where bits can be - * set is the hard xmit routine where an SKB has a request flag set. The only - * places where we clear bits are this work function, or the periodic cleanup - * thread. If the cleanup thread clears a bit we're processing we catch it - * when we lock to clear the bit and then grab the SKB pointer. If a Tx thread - * starts a new timestamp, we might not begin processing it right away but we - * will notice it at the end when we re-queue the task. If a Tx thread starts - * a new timestamp just after this function exits without re-queuing, - * the interrupt when the timestamp finishes should trigger. Avoiding holding - * the lock for the entire function is important in order to ensure that Tx - * threads do not get blocked while waiting for the lock. + * Note that we do not hold the tracking lock while reading the Tx timestamp. + * This is because reading the timestamp requires taking a mutex that might + * sleep. + * + * The only place where we set in_use is when a new timestamp is initiated + * with a slot index. This is only called in the hard xmit routine where an + * SKB has a request flag set. The only places where we clear this bit is this + * function, or during teardown when the Tx timestamp tracker is being + * removed. A timestamp index will never be re-used until the in_use bit for + * that index is cleared. + * + * If a Tx thread starts a new timestamp, we might not begin processing it + * right away but we will notice it at the end when we re-queue the task. + * + * If a Tx thread starts a new timestamp just after this function exits, the + * interrupt for that timestamp should re-trigger this function once + * a timestamp is ready. + * + * In cases where the PTP hardware clock was directly adjusted, some + * timestamps may not be able to safely use the timestamp extension math. In + * this case, software will set the stale bit for any outstanding Tx + * timestamps when the clock is adjusted. Then this function will discard + * those captured timestamps instead of sending them to the stack. + * + * If a Tx packet has been waiting for more than 2 seconds, it is not possible + * to correctly extend the timestamp using the cached PHC time. It is + * extremely unlikely that a packet will ever take this long to timestamp. If + * we detect a Tx timestamp request that has waited for this long we assume + * the packet will never be sent by hardware and discard it without reading + * the timestamp register. */ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) { struct ice_ptp_port *ptp_port; - bool ts_handled = true; + bool more_timestamps; struct ice_pf *pf; + struct ice_hw *hw; + u64 tstamp_ready; + int err; u8 idx; if (!tx->init) @@ -648,44 +688,86 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + hw = &pf->hw; + + /* Read the Tx ready status first */ + err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); + if (err) + return false; for_each_set_bit(idx, tx->in_use, tx->len) { struct skb_shared_hwtstamps shhwtstamps = {}; - u8 phy_idx = idx + tx->quad_offset; - u64 raw_tstamp, tstamp; + u8 phy_idx = idx + tx->offset; + u64 raw_tstamp = 0, tstamp; + bool drop_ts = false; struct sk_buff *skb; - int err; + + /* Drop packets which have waited for more than 2 seconds */ + if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { + drop_ts = true; + + /* Count the number of Tx timestamps that timed out */ + pf->ptp.tx_hwtstamp_timeouts++; + } + + /* Only read a timestamp from the PHY if its marked as ready + * by the tstamp_ready register. This avoids unnecessary + * reading of timestamps which are not yet valid. This is + * important as we must read all timestamps which are valid + * and only timestamps which are valid during each interrupt. + * If we do not, the hardware logic for generating a new + * interrupt can get stuck on some devices. + */ + if (!(tstamp_ready & BIT_ULL(phy_idx))) { + if (drop_ts) + goto skip_ts_read; + + continue; + } ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); - err = ice_read_phy_tstamp(&pf->hw, tx->quad, phy_idx, - &raw_tstamp); + err = ice_read_phy_tstamp(hw, tx->block, phy_idx, &raw_tstamp); if (err) continue; ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); - /* Check if the timestamp is invalid or stale */ - if (!(raw_tstamp & ICE_PTP_TS_VALID) || + /* For PHYs which don't implement a proper timestamp ready + * bitmap, verify that the timestamp value is different + * from the last cached timestamp. If it is not, skip this for + * now assuming it hasn't yet been captured by hardware. + */ + if (!drop_ts && tx->verify_cached && raw_tstamp == tx->tstamps[idx].cached_tstamp) continue; - /* The timestamp is valid, so we'll go ahead and clear this - * index and then send the timestamp up to the stack. - */ + /* Discard any timestamp value without the valid bit set */ + if (!(raw_tstamp & ICE_PTP_TS_VALID)) + drop_ts = true; + +skip_ts_read: spin_lock(&tx->lock); - tx->tstamps[idx].cached_tstamp = raw_tstamp; + if (tx->verify_cached && raw_tstamp) + tx->tstamps[idx].cached_tstamp = raw_tstamp; clear_bit(idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; + if (test_and_clear_bit(idx, tx->stale)) + drop_ts = true; spin_unlock(&tx->lock); - /* it's (unlikely but) possible we raced with the cleanup - * thread for discarding old timestamp requests. + /* It is unlikely but possible that the SKB will have been + * flushed at this point due to link change or teardown. */ if (!skb) continue; + if (drop_ts) { + dev_kfree_skb_any(skb); + continue; + } + /* Extend the timestamp using cached PHC time */ tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp); if (tstamp) { @@ -701,11 +783,10 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) * poll for remaining timestamps. */ spin_lock(&tx->lock); - if (!bitmap_empty(tx->in_use, tx->len)) - ts_handled = false; + more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len); spin_unlock(&tx->lock); - return ts_handled; + return !more_timestamps; } /** @@ -713,26 +794,33 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) * @tx: Tx tracking structure to initialize * * Assumes that the length has already been initialized. Do not call directly, - * use the ice_ptp_init_tx_e822 or ice_ptp_init_tx_e810 instead. + * use the ice_ptp_init_tx_* instead. */ static int ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) { - tx->tstamps = kcalloc(tx->len, sizeof(*tx->tstamps), GFP_KERNEL); - if (!tx->tstamps) - return -ENOMEM; + unsigned long *in_use, *stale; + struct ice_tx_tstamp *tstamps; + + tstamps = kcalloc(tx->len, sizeof(*tstamps), GFP_KERNEL); + in_use = bitmap_zalloc(tx->len, GFP_KERNEL); + stale = bitmap_zalloc(tx->len, GFP_KERNEL); + + if (!tstamps || !in_use || !stale) { + kfree(tstamps); + bitmap_free(in_use); + bitmap_free(stale); - tx->in_use = bitmap_zalloc(tx->len, GFP_KERNEL); - if (!tx->in_use) { - kfree(tx->tstamps); - tx->tstamps = NULL; return -ENOMEM; } - spin_lock_init(&tx->lock); - + tx->tstamps = tstamps; + tx->in_use = in_use; + tx->stale = stale; tx->init = 1; + spin_lock_init(&tx->lock); + return 0; } @@ -740,31 +828,71 @@ ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker * @pf: Board private structure * @tx: the tracker to flush + * + * Called during teardown when a Tx tracker is being removed. */ static void ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) { + struct ice_hw *hw = &pf->hw; + u64 tstamp_ready; + int err; u8 idx; - for (idx = 0; idx < tx->len; idx++) { - u8 phy_idx = idx + tx->quad_offset; + err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); + if (err) { + dev_dbg(ice_pf_to_dev(pf), "Failed to get the Tx tstamp ready bitmap for block %u, err %d\n", + tx->block, err); + + /* If we fail to read the Tx timestamp ready bitmap just + * skip clearing the PHY timestamps. + */ + tstamp_ready = 0; + } + + for_each_set_bit(idx, tx->in_use, tx->len) { + u8 phy_idx = idx + tx->offset; + struct sk_buff *skb; + + /* In case this timestamp is ready, we need to clear it. */ + if (!hw->reset_ongoing && (tstamp_ready & BIT_ULL(phy_idx))) + ice_clear_phy_tstamp(hw, tx->block, phy_idx); spin_lock(&tx->lock); - if (tx->tstamps[idx].skb) { - dev_kfree_skb_any(tx->tstamps[idx].skb); - tx->tstamps[idx].skb = NULL; - pf->ptp.tx_hwtstamp_flushed++; - } + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; clear_bit(idx, tx->in_use); + clear_bit(idx, tx->stale); spin_unlock(&tx->lock); - /* Clear any potential residual timestamp in the PHY block */ - if (!pf->hw.reset_ongoing) - ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); + /* Count the number of Tx timestamps flushed */ + pf->ptp.tx_hwtstamp_flushed++; + + /* Free the SKB after we've cleared the bit */ + dev_kfree_skb_any(skb); } } /** + * ice_ptp_mark_tx_tracker_stale - Mark unfinished timestamps as stale + * @tx: the tracker to mark + * + * Mark currently outstanding Tx timestamps as stale. This prevents sending + * their timestamp value to the stack. This is required to prevent extending + * the 40bit hardware timestamp incorrectly. + * + * This should be called when the PTP clock is modified such as after a set + * time request. + */ +static void +ice_ptp_mark_tx_tracker_stale(struct ice_ptp_tx *tx) +{ + spin_lock(&tx->lock); + bitmap_or(tx->stale, tx->stale, tx->in_use, tx->len); + spin_unlock(&tx->lock); +} + +/** * ice_ptp_release_tx_tracker - Release allocated memory for Tx tracker * @pf: Board private structure * @tx: Tx tracking structure to release @@ -774,7 +902,12 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) static void ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) { + spin_lock(&tx->lock); tx->init = 0; + spin_unlock(&tx->lock); + + /* wait for potentially outstanding interrupt to complete */ + synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); ice_ptp_flush_tx_tracker(pf, tx); @@ -784,6 +917,9 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) bitmap_free(tx->in_use); tx->in_use = NULL; + bitmap_free(tx->stale); + tx->stale = NULL; + tx->len = 0; } @@ -801,9 +937,10 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) static int ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) { - tx->quad = port / ICE_PORTS_PER_QUAD; - tx->quad_offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT; - tx->len = INDEX_PER_PORT; + tx->block = port / ICE_PORTS_PER_QUAD; + tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E822; + tx->len = INDEX_PER_PORT_E822; + tx->verify_cached = 0; return ice_ptp_alloc_tx_tracker(tx); } @@ -819,59 +956,19 @@ ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) static int ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) { - tx->quad = pf->hw.port_info->lport; - tx->quad_offset = 0; - tx->len = INDEX_PER_QUAD; + tx->block = pf->hw.port_info->lport; + tx->offset = 0; + tx->len = INDEX_PER_PORT_E810; + /* The E810 PHY does not provide a timestamp ready bitmap. Instead, + * verify new timestamps against cached copy of the last read + * timestamp. + */ + tx->verify_cached = 1; return ice_ptp_alloc_tx_tracker(tx); } /** - * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped - * @pf: pointer to the PF struct - * @tx: PTP Tx tracker to clean up - * - * Loop through the Tx timestamp requests and see if any of them have been - * waiting for a long time. Discard any SKBs that have been waiting for more - * than 2 seconds. This is long enough to be reasonably sure that the - * timestamp will never be captured. This might happen if the packet gets - * discarded before it reaches the PHY timestamping block. - */ -static void ice_ptp_tx_tstamp_cleanup(struct ice_pf *pf, struct ice_ptp_tx *tx) -{ - struct ice_hw *hw = &pf->hw; - u8 idx; - - if (!tx->init) - return; - - for_each_set_bit(idx, tx->in_use, tx->len) { - struct sk_buff *skb; - u64 raw_tstamp; - - /* Check if this SKB has been waiting for too long */ - if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) - continue; - - /* Read tstamp to be able to use this register again */ - ice_read_phy_tstamp(hw, tx->quad, idx + tx->quad_offset, - &raw_tstamp); - - spin_lock(&tx->lock); - skb = tx->tstamps[idx].skb; - tx->tstamps[idx].skb = NULL; - clear_bit(idx, tx->in_use); - spin_unlock(&tx->lock); - - /* Count the number of Tx timestamps which have timed out */ - pf->ptp.tx_hwtstamp_timeouts++; - - /* Free the SKB after we've cleared the bit */ - dev_kfree_skb_any(skb); - } -} - -/** * ice_ptp_update_cached_phctime - Update the cached PHC time values * @pf: Board specific private structure * @@ -941,20 +1038,13 @@ static int ice_ptp_update_cached_phctime(struct ice_pf *pf) * @pf: Board specific private structure * * This function must be called when the cached PHC time is no longer valid, - * such as after a time adjustment. It discards any outstanding Tx timestamps, - * and updates the cached PHC time for both the PF and Rx rings. If updating - * the PHC time cannot be done immediately, a warning message is logged and - * the work item is scheduled. - * - * These steps are required in order to ensure that we do not accidentally - * report a timestamp extended by the wrong PHC cached copy. Note that we - * do not directly update the cached timestamp here because it is possible - * this might produce an error when ICE_CFG_BUSY is set. If this occurred, we - * would have to try again. During that time window, timestamps might be - * requested and returned with an invalid extension. Thus, on failure to - * immediately update the cached PHC time we would need to zero the value - * anyways. For this reason, we just zero the value immediately and queue the - * update work item. + * such as after a time adjustment. It marks any currently outstanding Tx + * timestamps as stale and updates the cached PHC time for both the PF and Rx + * rings. + * + * If updating the PHC time cannot be done immediately, a warning message is + * logged and the work item is scheduled immediately to minimize the window + * with a wrong cached timestamp. */ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf) { @@ -978,8 +1068,12 @@ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf) msecs_to_jiffies(10)); } - /* Flush any outstanding Tx timestamps */ - ice_ptp_flush_tx_tracker(pf, &pf->ptp.port.tx); + /* Mark any outstanding timestamps as stale, since they might have + * been captured in hardware before the time update. This could lead + * to us extending them with the wrong cached value resulting in + * incorrect timestamp values. + */ + ice_ptp_mark_tx_tracker_stale(&pf->ptp.port.tx); } /** @@ -1060,19 +1154,6 @@ static u64 ice_base_incval(struct ice_pf *pf) } /** - * ice_ptp_reset_ts_memory_quad - Reset timestamp memory for one quad - * @pf: The PF private data structure - * @quad: The quad (0-4) - */ -static void ice_ptp_reset_ts_memory_quad(struct ice_pf *pf, int quad) -{ - struct ice_hw *hw = &pf->hw; - - ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M); - ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M); -} - -/** * ice_ptp_check_tx_fifo - Check whether Tx FIFO is in an OK state * @port: PTP port for which Tx FIFO is checked */ @@ -1124,7 +1205,7 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) dev_dbg(ice_pf_to_dev(pf), "Port %d Tx FIFO still not empty; resetting quad %d\n", port->port_num, quad); - ice_ptp_reset_ts_memory_quad(pf, quad); + ice_ptp_reset_ts_memory_quad_e822(hw, quad); port->tx_fifo_busy_cnt = FIFO_OK; return 0; } @@ -1133,130 +1214,49 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) } /** - * ice_ptp_check_tx_offset_valid - Check if the Tx PHY offset is valid - * @port: the PTP port to check - * - * Checks whether the Tx offset for the PHY associated with this port is - * valid. Returns 0 if the offset is valid, and a non-zero error code if it is - * not. - */ -static int ice_ptp_check_tx_offset_valid(struct ice_ptp_port *port) -{ - struct ice_pf *pf = ptp_port_to_pf(port); - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - u32 val; - int err; - - err = ice_ptp_check_tx_fifo(port); - if (err) - return err; - - err = ice_read_phy_reg_e822(hw, port->port_num, P_REG_TX_OV_STATUS, - &val); - if (err) { - dev_err(dev, "Failed to read TX_OV_STATUS for port %d, err %d\n", - port->port_num, err); - return -EAGAIN; - } - - if (!(val & P_REG_TX_OV_STATUS_OV_M)) - return -EAGAIN; - - return 0; -} - -/** - * ice_ptp_check_rx_offset_valid - Check if the Rx PHY offset is valid - * @port: the PTP port to check - * - * Checks whether the Rx offset for the PHY associated with this port is - * valid. Returns 0 if the offset is valid, and a non-zero error code if it is - * not. - */ -static int ice_ptp_check_rx_offset_valid(struct ice_ptp_port *port) -{ - struct ice_pf *pf = ptp_port_to_pf(port); - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - int err; - u32 val; - - err = ice_read_phy_reg_e822(hw, port->port_num, P_REG_RX_OV_STATUS, - &val); - if (err) { - dev_err(dev, "Failed to read RX_OV_STATUS for port %d, err %d\n", - port->port_num, err); - return err; - } - - if (!(val & P_REG_RX_OV_STATUS_OV_M)) - return -EAGAIN; - - return 0; -} - -/** - * ice_ptp_check_offset_valid - Check port offset valid bit - * @port: Port for which offset valid bit is checked - * - * Returns 0 if both Tx and Rx offset are valid, and -EAGAIN if one of the - * offset is not ready. - */ -static int ice_ptp_check_offset_valid(struct ice_ptp_port *port) -{ - int tx_err, rx_err; - - /* always check both Tx and Rx offset validity */ - tx_err = ice_ptp_check_tx_offset_valid(port); - rx_err = ice_ptp_check_rx_offset_valid(port); - - if (tx_err || rx_err) - return -EAGAIN; - - return 0; -} - -/** - * ice_ptp_wait_for_offset_valid - Check for valid Tx and Rx offsets + * ice_ptp_wait_for_offsets - Check for valid Tx and Rx offsets * @work: Pointer to the kthread_work structure for this task * - * Check whether both the Tx and Rx offsets are valid for enabling the vernier - * calibration. + * Check whether hardware has completed measuring the Tx and Rx offset values + * used to configure and enable vernier timestamp calibration. + * + * Once the offset in either direction is measured, configure the associated + * registers with the calibrated offset values and enable timestamping. The Tx + * and Rx directions are configured independently as soon as their associated + * offsets are known. * - * Once we have valid offsets from hardware, update the total Tx and Rx - * offsets, and exit bypass mode. This enables more precise timestamps using - * the extra data measured during the vernier calibration process. + * This function reschedules itself until both Tx and Rx calibration have + * completed. */ -static void ice_ptp_wait_for_offset_valid(struct kthread_work *work) +static void ice_ptp_wait_for_offsets(struct kthread_work *work) { struct ice_ptp_port *port; - int err; - struct device *dev; struct ice_pf *pf; struct ice_hw *hw; + int tx_err; + int rx_err; port = container_of(work, struct ice_ptp_port, ov_work.work); pf = ptp_port_to_pf(port); hw = &pf->hw; - dev = ice_pf_to_dev(pf); - if (ice_is_reset_in_progress(pf->state)) - return; - - if (ice_ptp_check_offset_valid(port)) { - /* Offsets not ready yet, try again later */ + if (ice_is_reset_in_progress(pf->state)) { + /* wait for device driver to complete reset */ kthread_queue_delayed_work(pf->ptp.kworker, &port->ov_work, msecs_to_jiffies(100)); return; } - /* Offsets are valid, so it is safe to exit bypass mode */ - err = ice_phy_exit_bypass_e822(hw, port->port_num); - if (err) { - dev_warn(dev, "Failed to exit bypass mode for PHY port %u, err %d\n", - port->port_num, err); + tx_err = ice_ptp_check_tx_fifo(port); + if (!tx_err) + tx_err = ice_phy_cfg_tx_offset_e822(hw, port->port_num); + rx_err = ice_phy_cfg_rx_offset_e822(hw, port->port_num); + if (tx_err || rx_err) { + /* Tx and/or Rx offset not yet configured, try again later */ + kthread_queue_delayed_work(pf->ptp.kworker, + &port->ov_work, + msecs_to_jiffies(100)); return; } } @@ -1317,16 +1317,20 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) kthread_cancel_delayed_work_sync(&ptp_port->ov_work); /* temporarily disable Tx timestamps while calibrating PHY offset */ + spin_lock(&ptp_port->tx.lock); ptp_port->tx.calibrating = true; + spin_unlock(&ptp_port->tx.lock); ptp_port->tx_fifo_busy_cnt = 0; - /* Start the PHY timer in bypass mode */ - err = ice_start_phy_timer_e822(hw, port, true); + /* Start the PHY timer in Vernier mode */ + err = ice_start_phy_timer_e822(hw, port); if (err) goto out_unlock; /* Enable Tx timestamps right away */ + spin_lock(&ptp_port->tx.lock); ptp_port->tx.calibrating = false; + spin_unlock(&ptp_port->tx.lock); kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); @@ -1341,45 +1345,33 @@ out_unlock: } /** - * ice_ptp_link_change - Set or clear port registers for timestamping + * ice_ptp_link_change - Reconfigure PTP after link status change * @pf: Board private structure * @port: Port for which the PHY start is set * @linkup: Link is up or down */ -int ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) { struct ice_ptp_port *ptp_port; - if (!test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - return 0; + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return; - if (port >= ICE_NUM_EXTERNAL_PORTS) - return -EINVAL; + if (WARN_ON_ONCE(port >= ICE_NUM_EXTERNAL_PORTS)) + return; ptp_port = &pf->ptp.port; - if (ptp_port->port_num != port) - return -EINVAL; + if (WARN_ON_ONCE(ptp_port->port_num != port)) + return; - /* Update cached link err for this port immediately */ + /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; - if (!test_bit(ICE_FLAG_PTP, pf->flags)) - /* PTP is not setup */ - return -EAGAIN; - - return ice_ptp_port_phy_restart(ptp_port); -} - -/** - * ice_ptp_reset_ts_memory - Reset timestamp memory for all quads - * @pf: The PF private data structure - */ -static void ice_ptp_reset_ts_memory(struct ice_pf *pf) -{ - int quad; + /* E810 devices do not need to reconfigure the PHY */ + if (ice_is_e810(&pf->hw)) + return; - quad = pf->hw.port_info->lport / ICE_PORTS_PER_QUAD; - ice_ptp_reset_ts_memory_quad(pf, quad); + ice_ptp_port_phy_restart(ptp_port); } /** @@ -1397,7 +1389,7 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold) int quad; u32 val; - ice_ptp_reset_ts_memory(pf); + ice_ptp_reset_ts_memory(hw); for (quad = 0; quad < ICE_MAX_QUAD; quad++) { err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEM_GBL_CFG, @@ -1447,24 +1439,10 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct ice_pf *pf = ptp_info_to_pf(info); struct ice_hw *hw = &pf->hw; - u64 incval, diff; - int neg_adj = 0; + u64 incval; int err; - incval = ice_base_incval(pf); - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - diff = mul_u64_u64_div_u64(incval, (u64)scaled_ppm, - 1000000ULL << 16); - if (neg_adj) - incval -= diff; - else - incval += diff; - + incval = adjust_by_scaled_ppm(ice_base_incval(pf), scaled_ppm); err = ice_ptp_write_incval_locked(hw, incval); if (err) { dev_err(ice_pf_to_dev(pf), "PTP failed to set incval, err %d\n", @@ -2346,11 +2324,14 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) { u8 idx; - /* Check if this tracker is initialized */ - if (!tx->init || tx->calibrating) + spin_lock(&tx->lock); + + /* Check that this tracker is accepting new timestamp requests */ + if (!ice_ptp_is_tx_tracker_up(tx)) { + spin_unlock(&tx->lock); return -1; + } - spin_lock(&tx->lock); /* Find and set the first available index */ idx = find_first_zero_bit(tx->in_use, tx->len); if (idx < tx->len) { @@ -2359,6 +2340,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) * requests. */ set_bit(idx, tx->in_use); + clear_bit(idx, tx->stale); tx->tstamps[idx].start = jiffies; tx->tstamps[idx].skb = skb_get(skb); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; @@ -2373,7 +2355,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) if (idx >= tx->len) return -1; else - return idx + tx->quad_offset; + return idx + tx->offset; } /** @@ -2398,8 +2380,6 @@ static void ice_ptp_periodic_work(struct kthread_work *work) err = ice_ptp_update_cached_phctime(pf); - ice_ptp_tx_tstamp_cleanup(pf, &pf->ptp.port.tx); - /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, msecs_to_jiffies(err ? 10 : 500)); @@ -2476,7 +2456,7 @@ pfr: err = ice_ptp_init_tx_e810(pf, &ptp->port.tx); } else { kthread_init_delayed_work(&ptp->port.ov_work, - ice_ptp_wait_for_offset_valid); + ice_ptp_wait_for_offsets); err = ice_ptp_init_tx_e822(pf, &ptp->port.tx, ptp->port.port_num); } @@ -2639,7 +2619,7 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) return ice_ptp_init_tx_e810(pf, &ptp_port->tx); kthread_init_delayed_work(&ptp_port->ov_work, - ice_ptp_wait_for_offset_valid); + ice_ptp_wait_for_offsets); return ice_ptp_init_tx_e822(pf, &ptp_port->tx, ptp_port->port_num); } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 028349295b71..9cda2f43e0e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -93,9 +93,14 @@ struct ice_perout_channel { * we discard old requests that were not fulfilled within a 2 second time * window. * Timestamp values in the PHY are read only and do not get cleared except at - * hardware reset or when a new timestamp value is captured. The cached_tstamp - * field is used to detect the case where a new timestamp has not yet been - * captured, ensuring that we avoid sending stale timestamp data to the stack. + * hardware reset or when a new timestamp value is captured. + * + * Some PHY types do not provide a "ready" bitmap indicating which timestamp + * indexes are valid. In these cases, we use a cached_tstamp to keep track of + * the last timestamp we read for a given index. If the current timestamp + * value is the same as the cached value, we assume a new timestamp hasn't + * been captured. This avoids reporting stale timestamps to the stack. This is + * only done if the verify_cached flag is set in ice_ptp_tx structure. */ struct ice_tx_tstamp { struct sk_buff *skb; @@ -105,30 +110,35 @@ struct ice_tx_tstamp { /** * struct ice_ptp_tx - Tracking structure for all Tx timestamp requests on a port - * @lock: lock to prevent concurrent write to in_use bitmap + * @lock: lock to prevent concurrent access to fields of this struct * @tstamps: array of len to store outstanding requests * @in_use: bitmap of len to indicate which slots are in use - * @quad: which quad the timestamps are captured in - * @quad_offset: offset into timestamp block of the quad to get the real index + * @stale: bitmap of len to indicate slots which have stale timestamps + * @block: which memory block (quad or port) the timestamps are captured in + * @offset: offset into timestamp block to get the real index * @len: length of the tstamps and in_use fields. * @init: if true, the tracker is initialized; * @calibrating: if true, the PHY is calibrating the Tx offset. During this * window, timestamps are temporarily disabled. + * @verify_cached: if true, verify new timestamp differs from last read value */ struct ice_ptp_tx { spinlock_t lock; /* lock protecting in_use bitmap */ struct ice_tx_tstamp *tstamps; unsigned long *in_use; - u8 quad; - u8 quad_offset; + unsigned long *stale; + u8 block; + u8 offset; u8 len; - u8 init; - u8 calibrating; + u8 init : 1; + u8 calibrating : 1; + u8 verify_cached : 1; }; /* Quad and port information for initializing timestamp blocks */ #define INDEX_PER_QUAD 64 -#define INDEX_PER_PORT (INDEX_PER_QUAD / ICE_PORTS_PER_QUAD) +#define INDEX_PER_PORT_E822 16 +#define INDEX_PER_PORT_E810 64 /** * struct ice_ptp_port - data used to initialize an external port for PTP @@ -256,7 +266,7 @@ void ice_ptp_reset(struct ice_pf *pf); void ice_ptp_prepare_for_reset(struct ice_pf *pf); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); -int ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); +void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) { @@ -291,7 +301,8 @@ static inline void ice_ptp_reset(struct ice_pf *pf) { } static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { } static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } -static inline int ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) -{ return 0; } +static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +{ +} #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ #endif /* _ICE_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 772b1f566d6e..a38614d21ea8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -656,6 +656,32 @@ ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx) } /** + * ice_ptp_reset_ts_memory_quad_e822 - Clear all timestamps from the quad block + * @hw: pointer to the HW struct + * @quad: the quad to read from + * + * Clear all timestamps from the PHY quad block that is shared between the + * internal PHYs on the E822 devices. + */ +void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad) +{ + ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, Q_REG_TS_CTRL_M); + ice_write_quad_reg_e822(hw, quad, Q_REG_TS_CTRL, ~(u32)Q_REG_TS_CTRL_M); +} + +/** + * ice_ptp_reset_ts_memory_e822 - Clear all timestamps from all quad blocks + * @hw: pointer to the HW struct + */ +static void ice_ptp_reset_ts_memory_e822(struct ice_hw *hw) +{ + unsigned int quad; + + for (quad = 0; quad < ICE_MAX_QUAD; quad++) + ice_ptp_reset_ts_memory_quad_e822(hw, quad); +} + +/** * ice_read_cgu_reg_e822 - Read a CGU register * @hw: pointer to the HW struct * @addr: Register address to read @@ -1715,21 +1741,48 @@ ice_calc_fixed_tx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) * adjust Tx timestamps by. This is calculated by combining some known static * latency along with the Vernier offset computations done by hardware. * - * This function must be called only after the offset registers are valid, - * i.e. after the Vernier calibration wait has passed, to ensure that the PHY - * has measured the offset. + * This function will not return successfully until the Tx offset calculations + * have been completed, which requires waiting until at least one packet has + * been transmitted by the device. It is safe to call this function + * periodically until calibration succeeds, as it will only program the offset + * once. * * To avoid overflow, when calculating the offset based on the known static * latency values, we use measurements in 1/100th of a nanosecond, and divide * the TUs per second up front. This avoids overflow while allowing * calculation of the adjustment using integer arithmetic. + * + * Returns zero on success, -EBUSY if the hardware vernier offset + * calibration has not completed, or another error code on failure. */ -static int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) +int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) { enum ice_ptp_link_spd link_spd; enum ice_ptp_fec_mode fec_mode; u64 total_offset, val; int err; + u32 reg; + + /* Nothing to do if we've already programmed the offset */ + err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OR, ®); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OR for port %u, err %d\n", + port, err); + return err; + } + + if (reg) + return 0; + + err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OV_STATUS, ®); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OV_STATUS for port %u, err %d\n", + port, err); + return err; + } + + if (!(reg & P_REG_TX_OV_STATUS_OV_M)) + return -EBUSY; err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); if (err) @@ -1783,46 +1836,8 @@ static int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port) if (err) return err; - return 0; -} - -/** - * ice_phy_cfg_fixed_tx_offset_e822 - Configure Tx offset for bypass mode - * @hw: pointer to the HW struct - * @port: the PHY port to configure - * - * Calculate and program the fixed Tx offset, and indicate that the offset is - * ready. This can be used when operating in bypass mode. - */ -static int -ice_phy_cfg_fixed_tx_offset_e822(struct ice_hw *hw, u8 port) -{ - enum ice_ptp_link_spd link_spd; - enum ice_ptp_fec_mode fec_mode; - u64 total_offset; - int err; - - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); - if (err) - return err; - - total_offset = ice_calc_fixed_tx_offset_e822(hw, link_spd); - - /* Program the fixed Tx offset into the P_REG_TOTAL_TX_OFFSET_L - * register, then indicate that the Tx offset is ready. After this, - * timestamps will be enabled. - * - * Note that this skips including the more precise offsets generated - * by the Vernier calibration. - */ - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_TX_OFFSET_L, - total_offset); - if (err) - return err; - - err = ice_write_phy_reg_e822(hw, port, P_REG_TX_OR, 1); - if (err) - return err; + dev_info(ice_hw_to_dev(hw), "Port=%d Tx vernier offset calibration complete\n", + port); return 0; } @@ -2026,6 +2041,11 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) * measurements taken in hardware with some data about known fixed delay as * well as adjusting for multi-lane alignment delay. * + * This function will not return successfully until the Rx offset calculations + * have been completed, which requires waiting until at least one packet has + * been received by the device. It is safe to call this function periodically + * until calibration succeeds, as it will only program the offset once. + * * This function must be called only after the offset registers are valid, * i.e. after the Vernier calibration wait has passed, to ensure that the PHY * has measured the offset. @@ -2034,13 +2054,38 @@ ice_calc_fixed_rx_offset_e822(struct ice_hw *hw, enum ice_ptp_link_spd link_spd) * latency values, we use measurements in 1/100th of a nanosecond, and divide * the TUs per second up front. This avoids overflow while allowing * calculation of the adjustment using integer arithmetic. + * + * Returns zero on success, -EBUSY if the hardware vernier offset + * calibration has not completed, or another error code on failure. */ -static int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) +int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) { enum ice_ptp_link_spd link_spd; enum ice_ptp_fec_mode fec_mode; u64 total_offset, pmd, val; int err; + u32 reg; + + /* Nothing to do if we've already programmed the offset */ + err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OR, ®); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OR for port %u, err %d\n", + port, err); + return err; + } + + if (reg) + return 0; + + err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OV_STATUS, ®); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OV_STATUS for port %u, err %d\n", + port, err); + return err; + } + + if (!(reg & P_REG_RX_OV_STATUS_OV_M)) + return -EBUSY; err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); if (err) @@ -2101,46 +2146,8 @@ static int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) if (err) return err; - return 0; -} - -/** - * ice_phy_cfg_fixed_rx_offset_e822 - Configure fixed Rx offset for bypass mode - * @hw: pointer to the HW struct - * @port: the PHY port to configure - * - * Calculate and program the fixed Rx offset, and indicate that the offset is - * ready. This can be used when operating in bypass mode. - */ -static int -ice_phy_cfg_fixed_rx_offset_e822(struct ice_hw *hw, u8 port) -{ - enum ice_ptp_link_spd link_spd; - enum ice_ptp_fec_mode fec_mode; - u64 total_offset; - int err; - - err = ice_phy_get_speed_and_fec_e822(hw, port, &link_spd, &fec_mode); - if (err) - return err; - - total_offset = ice_calc_fixed_rx_offset_e822(hw, link_spd); - - /* Program the fixed Rx offset into the P_REG_TOTAL_RX_OFFSET_L - * register, then indicate that the Rx offset is ready. After this, - * timestamps will be enabled. - * - * Note that this skips including the more precise offsets generated - * by Vernier calibration. - */ - err = ice_write_64b_phy_reg_e822(hw, port, P_REG_TOTAL_RX_OFFSET_L, - total_offset); - if (err) - return err; - - err = ice_write_phy_reg_e822(hw, port, P_REG_RX_OR, 1); - if (err) - return err; + dev_info(ice_hw_to_dev(hw), "Port=%d Rx vernier offset calibration complete\n", + port); return 0; } @@ -2323,20 +2330,14 @@ ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset) * ice_start_phy_timer_e822 - Start the PHY clock timer * @hw: pointer to the HW struct * @port: the PHY port to start - * @bypass: if true, start the PHY in bypass mode * * Start the clock of a PHY port. This must be done as part of the flow to * re-calibrate Tx and Rx timestamping offsets whenever the clock time is * initialized or when link speed changes. * - * Bypass mode enables timestamps immediately without waiting for Vernier - * calibration to complete. Hardware will still continue taking Vernier - * measurements on Tx or Rx of packets, but they will not be applied to - * timestamps. Use ice_phy_exit_bypass_e822 to exit bypass mode once hardware - * has completed offset calculation. + * Hardware will take Vernier measurements on Tx or Rx of packets. */ -int -ice_start_phy_timer_e822(struct ice_hw *hw, u8 port, bool bypass) +int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) { u32 lo, hi, val; u64 incval; @@ -2414,110 +2415,42 @@ ice_start_phy_timer_e822(struct ice_hw *hw, u8 port, bool bypass) if (err) return err; - if (bypass) { - val |= P_REG_PS_BYPASS_MODE_M; - /* Enter BYPASS mode, enabling timestamps immediately. */ - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); - if (err) - return err; - - /* Program the fixed Tx offset */ - err = ice_phy_cfg_fixed_tx_offset_e822(hw, port); - if (err) - return err; - - /* Program the fixed Rx offset */ - err = ice_phy_cfg_fixed_rx_offset_e822(hw, port); - if (err) - return err; - } - ice_debug(hw, ICE_DBG_PTP, "Enabled clock on PHY port %u\n", port); return 0; } /** - * ice_phy_exit_bypass_e822 - Exit bypass mode, after vernier calculations + * ice_get_phy_tx_tstamp_ready_e822 - Read Tx memory status register * @hw: pointer to the HW struct - * @port: the PHY port to configure - * - * After hardware finishes vernier calculations for the Tx and Rx offset, this - * function can be used to exit bypass mode by updating the total Tx and Rx - * offsets, and then disabling bypass. This will enable hardware to include - * the more precise offset calibrations, increasing precision of the generated - * timestamps. + * @quad: the timestamp quad to read from + * @tstamp_ready: contents of the Tx memory status register * - * This cannot be done until hardware has measured the offsets, which requires - * waiting until at least one packet has been sent and received by the device. + * Read the Q_REG_TX_MEMORY_STATUS register indicating which timestamps in + * the PHY are ready. A set bit means the corresponding timestamp is valid and + * ready to be captured from the PHY timestamp block. */ -int ice_phy_exit_bypass_e822(struct ice_hw *hw, u8 port) +static int +ice_get_phy_tx_tstamp_ready_e822(struct ice_hw *hw, u8 quad, u64 *tstamp_ready) { + u32 hi, lo; int err; - u32 val; - - err = ice_read_phy_reg_e822(hw, port, P_REG_TX_OV_STATUS, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_OV_STATUS for port %u, err %d\n", - port, err); - return err; - } - - if (!(val & P_REG_TX_OV_STATUS_OV_M)) { - ice_debug(hw, ICE_DBG_PTP, "Tx offset is not yet valid for port %u\n", - port); - return -EBUSY; - } - - err = ice_read_phy_reg_e822(hw, port, P_REG_RX_OV_STATUS, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_OV_STATUS for port %u, err %d\n", - port, err); - return err; - } - - if (!(val & P_REG_TX_OV_STATUS_OV_M)) { - ice_debug(hw, ICE_DBG_PTP, "Rx offset is not yet valid for port %u\n", - port); - return -EBUSY; - } - err = ice_phy_cfg_tx_offset_e822(hw, port); + err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_U, &hi); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to program total Tx offset for port %u, err %d\n", - port, err); + ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_U for quad %u, err %d\n", + quad, err); return err; } - err = ice_phy_cfg_rx_offset_e822(hw, port); + err = ice_read_quad_reg_e822(hw, quad, Q_REG_TX_MEMORY_STATUS_L, &lo); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to program total Rx offset for port %u, err %d\n", - port, err); + ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS_L for quad %u, err %d\n", + quad, err); return err; } - /* Exit bypass mode now that the offset has been updated */ - err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read P_REG_PS for port %u, err %d\n", - port, err); - return err; - } - - if (!(val & P_REG_PS_BYPASS_MODE_M)) - ice_debug(hw, ICE_DBG_PTP, "Port %u not in bypass mode\n", - port); - - val &= ~P_REG_PS_BYPASS_MODE_M; - err = ice_write_phy_reg_e822(hw, port, P_REG_PS, val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to disable bypass for port %u, err %d\n", - port, err); - return err; - } - - dev_info(ice_hw_to_dev(hw), "Exiting bypass mode on PHY port %u\n", - port); + *tstamp_ready = (u64)hi << 32 | (u64)lo; return 0; } @@ -2963,16 +2896,18 @@ bool ice_ptp_lock(struct ice_hw *hw) u32 hw_lock; int i; -#define MAX_TRIES 5 +#define MAX_TRIES 15 for (i = 0; i < MAX_TRIES; i++) { hw_lock = rd32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); hw_lock = hw_lock & PFTSYN_SEM_BUSY_M; - if (!hw_lock) - break; + if (hw_lock) { + /* Somebody is holding the lock */ + usleep_range(5000, 6000); + continue; + } - /* Somebody is holding the lock */ - usleep_range(10000, 20000); + break; } return !hw_lock; @@ -3194,6 +3129,22 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) return ice_clear_phy_tstamp_e822(hw, block, idx); } +/** + * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + * + * E810 devices do not use a Tx memory status register. Instead simply + * indicate that all timestamps are currently ready. + */ +static int +ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) +{ + *tstamp_ready = 0xFFFFFFFFFFFFFFFF; + return 0; +} + /* E810T SMA functions * * The following functions operate specifically on E810T hardware and are used @@ -3377,6 +3328,18 @@ bool ice_is_pca9575_present(struct ice_hw *hw) } /** + * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks + * @hw: pointer to the HW struct + */ +void ice_ptp_reset_ts_memory(struct ice_hw *hw) +{ + if (ice_is_e810(hw)) + return; + + ice_ptp_reset_ts_memory_e822(hw); +} + +/** * ice_ptp_init_phc - Initialize PTP hardware clock * @hw: pointer to the HW struct * @@ -3397,3 +3360,24 @@ int ice_ptp_init_phc(struct ice_hw *hw) else return ice_ptp_init_phc_e822(hw); } + +/** + * ice_get_phy_tx_tstamp_ready - Read PHY Tx memory status indication + * @hw: pointer to the HW struct + * @block: the timestamp block to check + * @tstamp_ready: storage for the PHY Tx memory status information + * + * Check the PHY for Tx timestamp memory status. This reports a 64 bit value + * which indicates which timestamps in the block may be captured. A set bit + * means the timestamp can be read. An unset bit means the timestamp is not + * ready and software should avoid reading the register. + */ +int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) +{ + if (ice_is_e810(hw)) + return ice_get_phy_tx_tstamp_ready_e810(hw, block, + tstamp_ready); + else + return ice_get_phy_tx_tstamp_ready_e822(hw, block, + tstamp_ready); +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 2bda64c76abc..3b68cb91bd81 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -133,7 +133,9 @@ int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval); int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj); int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp); int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); +void ice_ptp_reset_ts_memory(struct ice_hw *hw); int ice_ptp_init_phc(struct ice_hw *hw); +int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); /* E822 family functions */ int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val); @@ -141,6 +143,7 @@ int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val); int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val); int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time); +void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad); /** * ice_e822_time_ref - Get the current TIME_REF from capabilities @@ -184,8 +187,9 @@ static inline u64 ice_e822_pps_delay(enum ice_time_ref_freq time_ref) /* E822 Vernier calibration functions */ int ice_stop_phy_timer_e822(struct ice_hw *hw, u8 port, bool soft_reset); -int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port, bool bypass); -int ice_phy_exit_bypass_e822(struct ice_hw *hw, u8 port); +int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port); +int ice_phy_cfg_tx_offset_e822(struct ice_hw *hw, u8 port); +int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port); /* E810 family functions */ int ice_ptp_init_phy_e810(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index bd31748aae1b..fd1f8b0ad0ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -6,6 +6,7 @@ #include "ice_devlink.h" #include "ice_sriov.h" #include "ice_tc_lib.h" +#include "ice_dcb_lib.h" /** * ice_repr_get_sw_port_id - get port ID associated with representor @@ -134,14 +135,6 @@ static int ice_repr_stop(struct net_device *netdev) return 0; } -static struct devlink_port * -ice_repr_get_devlink_port(struct net_device *netdev) -{ - struct ice_repr *repr = ice_netdev_to_repr(netdev); - - return &repr->vf->devlink_port; -} - /** * ice_repr_sp_stats64 - get slow path stats for port representor * @dev: network interface device structure @@ -163,18 +156,20 @@ ice_repr_sp_stats64(const struct net_device *dev, u64 pkts, bytes; tx_ring = np->vsi->tx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&tx_ring->syncp, tx_ring->stats, + ice_fetch_u64_stats_per_ring(&tx_ring->ring_stats->syncp, + tx_ring->ring_stats->stats, &pkts, &bytes); stats->rx_packets = pkts; stats->rx_bytes = bytes; rx_ring = np->vsi->rx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&rx_ring->syncp, rx_ring->stats, + ice_fetch_u64_stats_per_ring(&rx_ring->ring_stats->syncp, + rx_ring->ring_stats->stats, &pkts, &bytes); stats->tx_packets = pkts; stats->tx_bytes = bytes; - stats->tx_dropped = rx_ring->rx_stats.alloc_page_failed + - rx_ring->rx_stats.alloc_buf_failed; + stats->tx_dropped = rx_ring->ring_stats->rx_stats.alloc_page_failed + + rx_ring->ring_stats->rx_stats.alloc_buf_failed; return 0; } @@ -250,7 +245,6 @@ static const struct net_device_ops ice_repr_netdev_ops = { .ndo_open = ice_repr_open, .ndo_stop = ice_repr_stop, .ndo_start_xmit = ice_eswitch_port_start_xmit, - .ndo_get_devlink_port = ice_repr_get_devlink_port, .ndo_setup_tc = ice_repr_setup_tc, .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, .ndo_get_offload_stats = ice_repr_ndo_get_offload_stats, @@ -339,12 +333,11 @@ static int ice_repr_add(struct ice_vf *vf) repr->netdev->max_mtu = ICE_MAX_MTU; SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(vf->pf)); + SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port); err = ice_repr_reg_netdev(repr->netdev); if (err) goto err_netdev; - devlink_port_type_eth_set(&vf->devlink_port, repr->netdev); - ice_virtchnl_set_repr_ops(vf); return 0; @@ -399,6 +392,7 @@ static void ice_repr_rem(struct ice_vf *vf) */ void ice_repr_rem_from_all_vfs(struct ice_pf *pf) { + struct devlink *devlink; struct ice_vf *vf; unsigned int bkt; @@ -406,6 +400,14 @@ void ice_repr_rem_from_all_vfs(struct ice_pf *pf) ice_for_each_vf(pf, bkt, vf) ice_repr_rem(vf); + + /* since all port representors are destroyed, there is + * no point in keeping the nodes + */ + devlink = priv_to_devlink(pf); + devl_lock(devlink); + devl_rate_nodes_destroy(devlink); + devl_unlock(devlink); } /** @@ -414,6 +416,7 @@ void ice_repr_rem_from_all_vfs(struct ice_pf *pf) */ int ice_repr_add_for_all_vfs(struct ice_pf *pf) { + struct devlink *devlink; struct ice_vf *vf; unsigned int bkt; int err; @@ -426,6 +429,13 @@ int ice_repr_add_for_all_vfs(struct ice_pf *pf) goto err; } + /* only export if ADQ and DCB disabled */ + if (ice_is_adq_active(pf) || ice_is_dcb_active(pf)) + return 0; + + devlink = priv_to_devlink(pf); + ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf)); + return 0; err: diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 118595763bba..6d08b397df2a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ +#include <net/devlink.h> #include "ice_sched.h" /** @@ -142,12 +143,14 @@ ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, * @pi: port information structure * @layer: Scheduler layer of the node * @info: Scheduler element information from firmware + * @prealloc_node: preallocated ice_sched_node struct for SW DB * * This function inserts a scheduler node to the SW DB. */ int ice_sched_add_node(struct ice_port_info *pi, u8 layer, - struct ice_aqc_txsched_elem_data *info) + struct ice_aqc_txsched_elem_data *info, + struct ice_sched_node *prealloc_node) { struct ice_aqc_txsched_elem_data elem; struct ice_sched_node *parent; @@ -176,7 +179,10 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, if (status) return status; - node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); + if (prealloc_node) + node = prealloc_node; + else + node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; if (hw->max_children[layer]) { @@ -355,6 +361,9 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) /* leaf nodes have no children */ if (node->children) devm_kfree(ice_hw_to_dev(hw), node->children); + + kfree(node->name); + xa_erase(&pi->sched_node_ids, node->id); devm_kfree(ice_hw_to_dev(hw), node); } @@ -872,13 +881,15 @@ void ice_sched_cleanup_all(struct ice_hw *hw) * @num_nodes: number of nodes * @num_nodes_added: pointer to num nodes added * @first_node_teid: if new nodes are added then return the TEID of first node + * @prealloc_nodes: preallocated nodes struct for software DB * * This function add nodes to HW as well as to SW DB for a given layer */ -static int +int ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, u16 num_nodes, - u16 *num_nodes_added, u32 *first_node_teid) + u16 *num_nodes_added, u32 *first_node_teid, + struct ice_sched_node **prealloc_nodes) { struct ice_sched_node *prev, *new_node; struct ice_aqc_add_elem *buf; @@ -924,7 +935,11 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, *num_nodes_added = num_nodes; /* add nodes to the SW DB */ for (i = 0; i < num_nodes; i++) { - status = ice_sched_add_node(pi, layer, &buf->generic[i]); + if (prealloc_nodes) + status = ice_sched_add_node(pi, layer, &buf->generic[i], prealloc_nodes[i]); + else + status = ice_sched_add_node(pi, layer, &buf->generic[i], NULL); + if (status) { ice_debug(hw, ICE_DBG_SCHED, "add nodes in SW DB failed status =%d\n", status); @@ -940,6 +955,22 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, new_node->sibling = NULL; new_node->tc_num = tc_node->tc_num; + new_node->tx_weight = ICE_SCHED_DFLT_BW_WT; + new_node->tx_share = ICE_SCHED_DFLT_BW; + new_node->tx_max = ICE_SCHED_DFLT_BW; + new_node->name = kzalloc(SCHED_NODE_NAME_MAX_LEN, GFP_KERNEL); + if (!new_node->name) + return -ENOMEM; + + status = xa_alloc(&pi->sched_node_ids, &new_node->id, NULL, XA_LIMIT(0, UINT_MAX), + GFP_KERNEL); + if (status) { + ice_debug(hw, ICE_DBG_SCHED, "xa_alloc failed for sched node status =%d\n", + status); + break; + } + + snprintf(new_node->name, SCHED_NODE_NAME_MAX_LEN, "node_%u", new_node->id); /* add it to previous node sibling pointer */ /* Note: siblings are not linked across branches */ @@ -1003,7 +1034,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, } return ice_sched_add_elems(pi, tc_node, parent, layer, num_nodes, - num_nodes_added, first_node_teid); + num_nodes_added, first_node_teid, NULL); } /** @@ -1268,7 +1299,7 @@ int ice_sched_init_port(struct ice_port_info *pi) ICE_AQC_ELEM_TYPE_ENTRY_POINT) hw->sw_entry_point_layer = j; - status = ice_sched_add_node(pi, j, &buf[i].generic[j]); + status = ice_sched_add_node(pi, j, &buf[i].generic[j], NULL); if (status) goto err_init_port; } @@ -2154,7 +2185,7 @@ ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, * This function removes the child from the old parent and adds it to a new * parent */ -static void +void ice_sched_update_parent(struct ice_sched_node *new_parent, struct ice_sched_node *node) { @@ -2188,7 +2219,7 @@ ice_sched_update_parent(struct ice_sched_node *new_parent, * * This function move the child nodes to a given parent. */ -static int +int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { @@ -3560,7 +3591,7 @@ ice_sched_set_eir_srl_excl(struct ice_port_info *pi, * node's RL profile ID of type CIR, EIR, or SRL, and removes old profile * ID from local database. The caller needs to hold scheduler lock. */ -static int +int ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type, u32 bw, u8 layer_num) { @@ -3597,6 +3628,57 @@ ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, } /** + * ice_sched_set_node_priority - set node's priority + * @pi: port information structure + * @node: tree node + * @priority: number 0-7 representing priority among siblings + * + * This function sets priority of a node among it's siblings. + */ +int +ice_sched_set_node_priority(struct ice_port_info *pi, struct ice_sched_node *node, + u16 priority) +{ + struct ice_aqc_txsched_elem_data buf; + struct ice_aqc_txsched_elem *data; + + buf = node->info; + data = &buf.data; + + data->valid_sections |= ICE_AQC_ELEM_VALID_GENERIC; + data->generic |= FIELD_PREP(ICE_AQC_ELEM_GENERIC_PRIO_M, priority); + + return ice_sched_update_elem(pi->hw, node, &buf); +} + +/** + * ice_sched_set_node_weight - set node's weight + * @pi: port information structure + * @node: tree node + * @weight: number 1-200 representing weight for WFQ + * + * This function sets weight of the node for WFQ algorithm. + */ +int +ice_sched_set_node_weight(struct ice_port_info *pi, struct ice_sched_node *node, u16 weight) +{ + struct ice_aqc_txsched_elem_data buf; + struct ice_aqc_txsched_elem *data; + + buf = node->info; + data = &buf.data; + + data->valid_sections = ICE_AQC_ELEM_VALID_CIR | ICE_AQC_ELEM_VALID_EIR | + ICE_AQC_ELEM_VALID_GENERIC; + data->cir_bw.bw_alloc = cpu_to_le16(weight); + data->eir_bw.bw_alloc = cpu_to_le16(weight); + + data->generic |= FIELD_PREP(ICE_AQC_ELEM_GENERIC_SP_M, 0x0); + + return ice_sched_update_elem(pi->hw, node, &buf); +} + +/** * ice_sched_set_node_bw_lmt - set node's BW limit * @pi: port information structure * @node: tree node @@ -3606,7 +3688,7 @@ ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, * It updates node's BW limit parameters like BW RL profile ID of type CIR, * EIR, or SRL. The caller needs to hold scheduler lock. */ -static int +int ice_sched_set_node_bw_lmt(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type, u32 bw) { diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 4f91577fed56..9c100747445a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -6,6 +6,8 @@ #include "ice_common.h" +#define SCHED_NODE_NAME_MAX_LEN 32 + #define ICE_QGRP_LAYER_OFFSET 2 #define ICE_VSI_LAYER_OFFSET 4 #define ICE_AGG_LAYER_OFFSET 6 @@ -69,6 +71,29 @@ int ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, struct ice_aqc_txsched_elem_data *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd); + +int +ice_sched_set_node_bw_lmt(struct ice_port_info *pi, struct ice_sched_node *node, + enum ice_rl_type rl_type, u32 bw); + +int +ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, + enum ice_rl_type rl_type, u32 bw, u8 layer_num); + +int +ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, u16 num_nodes, + u16 *num_nodes_added, u32 *first_node_teid, + struct ice_sched_node **prealloc_node); + +int +ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, + u16 num_items, u32 *list); + +int ice_sched_set_node_priority(struct ice_port_info *pi, struct ice_sched_node *node, + u16 priority); +int ice_sched_set_node_weight(struct ice_port_info *pi, struct ice_sched_node *node, u16 weight); + int ice_sched_init_port(struct ice_port_info *pi); int ice_sched_query_res_alloc(struct ice_hw *hw); void ice_sched_get_psm_clk_freq(struct ice_hw *hw); @@ -81,7 +106,11 @@ struct ice_sched_node * ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid); int ice_sched_add_node(struct ice_port_info *pi, u8 layer, - struct ice_aqc_txsched_elem_data *info); + struct ice_aqc_txsched_elem_data *info, + struct ice_sched_node *prealloc_node); +void +ice_sched_update_parent(struct ice_sched_node *new_parent, + struct ice_sched_node *node); void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node); struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc); struct ice_sched_node * diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index f68c555be4e9..faba0f857cd9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -724,7 +724,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) */ fltr->rid = rule_added.rid; fltr->rule_id = rule_added.rule_id; - fltr->dest_id = rule_added.vsi_handle; + fltr->dest_vsi_handle = rule_added.vsi_handle; exit: kfree(list); @@ -732,6 +732,116 @@ exit: } /** + * ice_locate_vsi_using_queue - locate VSI using queue (forward to queue action) + * @vsi: Pointer to VSI + * @tc_fltr: Pointer to tc_flower_filter + * + * Locate the VSI using specified queue. When ADQ is not enabled, always + * return input VSI, otherwise locate corresponding VSI based on per channel + * offset and qcount + */ +static struct ice_vsi * +ice_locate_vsi_using_queue(struct ice_vsi *vsi, + struct ice_tc_flower_fltr *tc_fltr) +{ + int num_tc, tc, queue; + + /* if ADQ is not active, passed VSI is the candidate VSI */ + if (!ice_is_adq_active(vsi->back)) + return vsi; + + /* Locate the VSI (it could still be main PF VSI or CHNL_VSI depending + * upon queue number) + */ + num_tc = vsi->mqprio_qopt.qopt.num_tc; + queue = tc_fltr->action.fwd.q.queue; + + for (tc = 0; tc < num_tc; tc++) { + int qcount = vsi->mqprio_qopt.qopt.count[tc]; + int offset = vsi->mqprio_qopt.qopt.offset[tc]; + + if (queue >= offset && queue < offset + qcount) { + /* for non-ADQ TCs, passed VSI is the candidate VSI */ + if (tc < ICE_CHNL_START_TC) + return vsi; + else + return vsi->tc_map_vsi[tc]; + } + } + return NULL; +} + +static struct ice_rx_ring * +ice_locate_rx_ring_using_queue(struct ice_vsi *vsi, + struct ice_tc_flower_fltr *tc_fltr) +{ + u16 queue = tc_fltr->action.fwd.q.queue; + + return queue < vsi->num_rxq ? vsi->rx_rings[queue] : NULL; +} + +/** + * ice_tc_forward_action - Determine destination VSI and queue for the action + * @vsi: Pointer to VSI + * @tc_fltr: Pointer to TC flower filter structure + * + * Validates the tc forward action and determines the destination VSI and queue + * for the forward action. + */ +static struct ice_vsi * +ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) +{ + struct ice_rx_ring *ring = NULL; + struct ice_vsi *ch_vsi = NULL; + struct ice_pf *pf = vsi->back; + struct device *dev; + u32 tc_class; + + dev = ice_pf_to_dev(pf); + + /* Get the destination VSI and/or destination queue and validate them */ + switch (tc_fltr->action.fltr_act) { + case ICE_FWD_TO_VSI: + tc_class = tc_fltr->action.fwd.tc.tc_class; + /* Select the destination VSI */ + if (tc_class < ICE_CHNL_START_TC) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, + "Unable to add filter because of unsupported destination"); + return ERR_PTR(-EOPNOTSUPP); + } + /* Locate ADQ VSI depending on hw_tc number */ + ch_vsi = vsi->tc_map_vsi[tc_class]; + break; + case ICE_FWD_TO_Q: + /* Locate the Rx queue */ + ring = ice_locate_rx_ring_using_queue(vsi, tc_fltr); + if (!ring) { + dev_err(dev, + "Unable to locate Rx queue for action fwd_to_queue: %u\n", + tc_fltr->action.fwd.q.queue); + return ERR_PTR(-EINVAL); + } + /* Determine destination VSI even though the action is + * FWD_TO_QUEUE, because QUEUE is associated with VSI + */ + ch_vsi = tc_fltr->dest_vsi; + break; + default: + dev_err(dev, + "Unable to add filter because of unsupported action %u (supported actions: fwd to tc, fwd to queue)\n", + tc_fltr->action.fltr_act); + return ERR_PTR(-EINVAL); + } + /* Must have valid ch_vsi (it could be main VSI or ADQ VSI) */ + if (!ch_vsi) { + dev_err(dev, + "Unable to add filter because specified destination VSI doesn't exist\n"); + return ERR_PTR(-EINVAL); + } + return ch_vsi; +} + +/** * ice_add_tc_flower_adv_fltr - add appropriate filter rules * @vsi: Pointer to VSI * @tc_fltr: Pointer to TC flower filter structure @@ -772,11 +882,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, return -EOPNOTSUPP; } - /* get the channel (aka ADQ VSI) */ - if (tc_fltr->dest_vsi) - ch_vsi = tc_fltr->dest_vsi; - else - ch_vsi = vsi->tc_map_vsi[tc_fltr->action.tc_class]; + /* validate forwarding action VSI and queue */ + ch_vsi = ice_tc_forward_action(vsi, tc_fltr); + if (IS_ERR(ch_vsi)) + return PTR_ERR(ch_vsi); lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); @@ -790,30 +899,40 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, } rule_info.sw_act.fltr_act = tc_fltr->action.fltr_act; - if (tc_fltr->action.tc_class >= ICE_CHNL_START_TC) { - if (!ch_vsi) { - NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter because specified destination doesn't exist"); - ret = -EINVAL; - goto exit; - } + /* specify the cookie as filter_rule_id */ + rule_info.fltr_rule_id = tc_fltr->cookie; - rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + switch (tc_fltr->action.fltr_act) { + case ICE_FWD_TO_VSI: rule_info.sw_act.vsi_handle = ch_vsi->idx; - rule_info.priority = 7; + rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; rule_info.sw_act.src = hw->pf_id; rule_info.rx = true; dev_dbg(dev, "add switch rule for TC:%u vsi_idx:%u, lkups_cnt:%u\n", - tc_fltr->action.tc_class, + tc_fltr->action.fwd.tc.tc_class, rule_info.sw_act.vsi_handle, lkups_cnt); - } else { + break; + case ICE_FWD_TO_Q: + /* HW queue number in global space */ + rule_info.sw_act.fwd_id.q_id = tc_fltr->action.fwd.q.hw_queue; + rule_info.sw_act.vsi_handle = ch_vsi->idx; + rule_info.priority = ICE_SWITCH_FLTR_PRIO_QUEUE; + rule_info.sw_act.src = hw->pf_id; + rule_info.rx = true; + dev_dbg(dev, "add switch rule action to forward to queue:%u (HW queue %u), lkups_cnt:%u\n", + tc_fltr->action.fwd.q.queue, + tc_fltr->action.fwd.q.hw_queue, lkups_cnt); + break; + default: rule_info.sw_act.flag |= ICE_FLTR_TX; + /* In case of Tx (LOOKUP_TX), src needs to be src VSI */ rule_info.sw_act.src = vsi->idx; + /* 'Rx' is false, direction of rule(LOOKUPTRX) */ rule_info.rx = false; + rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; + break; } - /* specify the cookie as filter_rule_id */ - rule_info.fltr_rule_id = tc_fltr->cookie; - ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { NL_SET_ERR_MSG_MOD(tc_fltr->extack, @@ -831,19 +950,14 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, */ tc_fltr->rid = rule_added.rid; tc_fltr->rule_id = rule_added.rule_id; - if (tc_fltr->action.tc_class > 0 && ch_vsi) { - /* For PF ADQ, VSI type is set as ICE_VSI_CHNL, and - * for PF ADQ filter, it is not yet set in tc_fltr, - * hence store the dest_vsi ptr in tc_fltr - */ - if (ch_vsi->type == ICE_VSI_CHNL) - tc_fltr->dest_vsi = ch_vsi; + tc_fltr->dest_vsi_handle = rule_added.vsi_handle; + if (tc_fltr->action.fltr_act == ICE_FWD_TO_VSI || + tc_fltr->action.fltr_act == ICE_FWD_TO_Q) { + tc_fltr->dest_vsi = ch_vsi; /* keep track of advanced switch filter for - * destination VSI (channel VSI) + * destination VSI */ ch_vsi->num_chnl_fltr++; - /* in this case, dest_id is VSI handle (sw handle) */ - tc_fltr->dest_id = rule_added.vsi_handle; /* keeps track of channel filters for PF VSI */ if (vsi->type == ICE_VSI_PF && @@ -851,10 +965,22 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, ICE_TC_FLWR_FIELD_ENC_DST_MAC))) pf->num_dmac_chnl_fltrs++; } - dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x) for TC %u, rid %u, rule_id %u, vsi_idx %u\n", - lkups_cnt, flags, - tc_fltr->action.tc_class, rule_added.rid, - rule_added.rule_id, rule_added.vsi_handle); + switch (tc_fltr->action.fltr_act) { + case ICE_FWD_TO_VSI: + dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x), action is forward to TC %u, rid %u, rule_id %u, vsi_idx %u\n", + lkups_cnt, flags, + tc_fltr->action.fwd.tc.tc_class, rule_added.rid, + rule_added.rule_id, rule_added.vsi_handle); + break; + case ICE_FWD_TO_Q: + dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x), action is forward to queue: %u (HW queue %u) , rid %u, rule_id %u\n", + lkups_cnt, flags, tc_fltr->action.fwd.q.queue, + tc_fltr->action.fwd.q.hw_queue, rule_added.rid, + rule_added.rule_id); + break; + default: + break; + } exit: kfree(list); return ret; @@ -1455,43 +1581,15 @@ ice_add_switch_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) } /** - * ice_handle_tclass_action - Support directing to a traffic class + * ice_prep_adq_filter - Prepare ADQ filter with the required additional headers * @vsi: Pointer to VSI - * @cls_flower: Pointer to TC flower offload structure * @fltr: Pointer to TC flower filter structure * - * Support directing traffic to a traffic class + * Prepare ADQ filter with the required additional header fields */ static int -ice_handle_tclass_action(struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower, - struct ice_tc_flower_fltr *fltr) +ice_prep_adq_filter(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) { - int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid); - struct ice_vsi *main_vsi; - - if (tc < 0) { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified destination is invalid"); - return -EINVAL; - } - if (!tc) { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of invalid destination"); - return -EINVAL; - } - - if (!(vsi->all_enatc & BIT(tc))) { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of non-existence destination"); - return -EINVAL; - } - - /* Redirect to a TC class or Queue Group */ - main_vsi = ice_get_main_vsi(vsi->back); - if (!main_vsi || !main_vsi->netdev) { - NL_SET_ERR_MSG_MOD(fltr->extack, - "Unable to add filter because of invalid netdevice"); - return -EINVAL; - } - if ((fltr->flags & ICE_TC_FLWR_FIELD_TENANT_ID) && (fltr->flags & (ICE_TC_FLWR_FIELD_DST_MAC | ICE_TC_FLWR_FIELD_SRC_MAC))) { @@ -1503,9 +1601,8 @@ ice_handle_tclass_action(struct ice_vsi *vsi, /* For ADQ, filter must include dest MAC address, otherwise unwanted * packets with unrelated MAC address get delivered to ADQ VSIs as long * as remaining filter criteria is satisfied such as dest IP address - * and dest/src L4 port. Following code is trying to handle: - * 1. For non-tunnel, if user specify MAC addresses, use them (means - * this code won't do anything + * and dest/src L4 port. Below code handles the following cases: + * 1. For non-tunnel, if user specify MAC addresses, use them. * 2. For non-tunnel, if user didn't specify MAC address, add implicit * dest MAC to be lower netdev's active unicast MAC address * 3. For tunnel, as of now TC-filter through flower classifier doesn't @@ -1528,35 +1625,97 @@ ice_handle_tclass_action(struct ice_vsi *vsi, eth_broadcast_addr(fltr->outer_headers.l2_mask.dst_mac); } - /* validate specified dest MAC address, make sure either it belongs to - * lower netdev or any of MACVLAN. MACVLANs MAC address are added as - * unicast MAC filter destined to main VSI. - */ - if (!ice_mac_fltr_exist(&main_vsi->back->hw, - fltr->outer_headers.l2_key.dst_mac, - main_vsi->idx)) { - NL_SET_ERR_MSG_MOD(fltr->extack, - "Unable to add filter because legacy MAC filter for specified destination doesn't exist"); - return -EINVAL; - } - /* Make sure VLAN is already added to main VSI, before allowing ADQ to * add a VLAN based filter such as MAC + VLAN + L4 port. */ if (fltr->flags & ICE_TC_FLWR_FIELD_VLAN) { u16 vlan_id = be16_to_cpu(fltr->outer_headers.vlan_hdr.vlan_id); - if (!ice_vlan_fltr_exist(&main_vsi->back->hw, vlan_id, - main_vsi->idx)) { + if (!ice_vlan_fltr_exist(&vsi->back->hw, vlan_id, vsi->idx)) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because legacy VLAN filter for specified destination doesn't exist"); return -EINVAL; } } + return 0; +} + +/** + * ice_handle_tclass_action - Support directing to a traffic class + * @vsi: Pointer to VSI + * @cls_flower: Pointer to TC flower offload structure + * @fltr: Pointer to TC flower filter structure + * + * Support directing traffic to a traffic class/queue-set + */ +static int +ice_handle_tclass_action(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) +{ + int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid); + + /* user specified hw_tc (must be non-zero for ADQ TC), action is forward + * to hw_tc (i.e. ADQ channel number) + */ + if (tc < ICE_CHNL_START_TC) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because of unsupported destination"); + return -EOPNOTSUPP; + } + if (!(vsi->all_enatc & BIT(tc))) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because of non-existence destination"); + return -EINVAL; + } fltr->action.fltr_act = ICE_FWD_TO_VSI; - fltr->action.tc_class = tc; + fltr->action.fwd.tc.tc_class = tc; - return 0; + return ice_prep_adq_filter(vsi, fltr); +} + +static int +ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + struct ice_vsi *ch_vsi = NULL; + u16 queue = act->rx_queue; + + if (queue > vsi->num_rxq) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because specified queue is invalid"); + return -EINVAL; + } + fltr->action.fltr_act = ICE_FWD_TO_Q; + fltr->action.fwd.q.queue = queue; + /* determine corresponding HW queue */ + fltr->action.fwd.q.hw_queue = vsi->rxq_map[queue]; + + /* If ADQ is configured, and the queue belongs to ADQ VSI, then prepare + * ADQ switch filter + */ + ch_vsi = ice_locate_vsi_using_queue(vsi, fltr); + if (!ch_vsi) + return -EINVAL; + fltr->dest_vsi = ch_vsi; + if (!ice_is_chnl_fltr(fltr)) + return 0; + + return ice_prep_adq_filter(vsi, fltr); +} + +static int +ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + switch (act->id) { + case FLOW_ACTION_RX_QUEUE_MAPPING: + /* forward to queue */ + return ice_tc_forward_to_queue(vsi, fltr, act); + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported TC action"); + return -EOPNOTSUPP; + } } /** @@ -1575,7 +1734,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi, struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); struct flow_action *flow_action = &rule->action; struct flow_action_entry *act; - int i; + int i, err; if (cls_flower->classid) return ice_handle_tclass_action(vsi, cls_flower, fltr); @@ -1584,21 +1743,13 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi, return -EINVAL; flow_action_for_each(i, act, flow_action) { - if (ice_is_eswitch_mode_switchdev(vsi->back)) { - int err = ice_eswitch_tc_parse_action(fltr, act); - - if (err) - return err; - continue; - } - /* Allow only one rule per filter */ - - /* Drop action */ - if (act->id == FLOW_ACTION_DROP) { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action DROP"); - return -EINVAL; - } - fltr->action.fltr_act = ICE_FWD_TO_VSI; + if (ice_is_eswitch_mode_switchdev(vsi->back)) + err = ice_eswitch_tc_parse_action(fltr, act); + else + err = ice_tc_parse_action(vsi, fltr, act); + if (err) + return err; + continue; } return 0; } @@ -1618,7 +1769,7 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_rem.rid = fltr->rid; rule_rem.rule_id = fltr->rule_id; - rule_rem.vsi_handle = fltr->dest_id; + rule_rem.vsi_handle = fltr->dest_vsi_handle; err = ice_rem_adv_rule_by_id(&pf->hw, &rule_rem); if (err) { if (err == -ENOENT) { diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 92642faad595..d916d1e92aa3 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -45,7 +45,20 @@ struct ice_indr_block_priv { }; struct ice_tc_flower_action { - u32 tc_class; + /* forward action specific params */ + union { + struct { + u32 tc_class; /* forward to hw_tc */ + u32 rsvd; + } tc; + struct { + u16 queue; /* forward to queue */ + /* To add filter in HW, absolute queue number in global + * space of queues (between 0...N) is needed + */ + u16 hw_queue; + } q; + } fwd; enum ice_sw_fwd_act_type fltr_act; }; @@ -131,11 +144,11 @@ struct ice_tc_flower_fltr { */ u16 rid; u16 rule_id; - /* this could be queue/vsi_idx (sw handle)/queue_group, depending upon - * destination type + /* VSI handle of the destination VSI (it could be main PF VSI, CHNL_VSI, + * VF VSI) */ - u16 dest_id; - /* if dest_id is vsi_idx, then need to store destination VSI ptr */ + u16 dest_vsi_handle; + /* ptr to destination VSI */ struct ice_vsi *dest_vsi; /* direction of fltr for eswitch use case */ enum ice_eswitch_fltr_direction direction; @@ -162,12 +175,23 @@ struct ice_tc_flower_fltr { * @f: Pointer to tc-flower filter * * Criteria to determine of given filter is valid channel filter - * or not is based on its "destination". If destination is hw_tc (aka tc_class) - * and it is non-zero, then it is valid channel (aka ADQ) filter + * or not is based on its destination. + * For forward to VSI action, if destination is valid hw_tc (aka tc_class) + * and in supported range of TCs for ADQ, then return true. + * For forward to queue, as long as dest_vsi is valid and it is of type + * VSI_CHNL (PF ADQ VSI is of type VSI_CHNL), return true. + * NOTE: For forward to queue, correct dest_vsi is still set in tc_fltr based + * on destination queue specified. */ static inline bool ice_is_chnl_fltr(struct ice_tc_flower_fltr *f) { - return !!f->action.tc_class; + if (f->action.fltr_act == ICE_FWD_TO_VSI) + return f->action.fwd.tc.tc_class >= ICE_CHNL_START_TC && + f->action.fwd.tc.tc_class < ICE_CHNL_MAX_TC; + else if (f->action.fltr_act == ICE_FWD_TO_Q) + return f->dest_vsi && f->dest_vsi->type == ICE_VSI_CHNL; + + return false; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index dbe80e5053a8..086f0b3ab68d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -325,7 +325,7 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) if (netif_tx_queue_stopped(txring_txq(tx_ring)) && !test_bit(ICE_VSI_DOWN, vsi->state)) { netif_tx_wake_queue(txring_txq(tx_ring)); - ++tx_ring->tx_stats.restart_q; + ++tx_ring->ring_stats->tx_stats.restart_q; } } @@ -367,7 +367,7 @@ int ice_setup_tx_ring(struct ice_tx_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - tx_ring->tx_stats.prev_pkt = -1; + tx_ring->ring_stats->tx_stats.prev_pkt = -1; return 0; err: @@ -667,7 +667,7 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) /* alloc new page for storage */ page = dev_alloc_pages(ice_rx_pg_order(rx_ring)); if (unlikely(!page)) { - rx_ring->rx_stats.alloc_page_failed++; + rx_ring->ring_stats->rx_stats.alloc_page_failed++; return false; } @@ -680,7 +680,7 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) */ if (dma_mapping_error(rx_ring->dev, dma)) { __free_pages(page, ice_rx_pg_order(rx_ring)); - rx_ring->rx_stats.alloc_page_failed++; + rx_ring->ring_stats->rx_stats.alloc_page_failed++; return false; } @@ -1091,7 +1091,7 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF))) return false; - rx_ring->rx_stats.non_eop_descs++; + rx_ring->ring_stats->rx_stats.non_eop_descs++; return true; } @@ -1222,7 +1222,7 @@ construct_skb: } /* exit if we failed to retrieve a buffer */ if (!skb) { - rx_ring->rx_stats.alloc_buf_failed++; + rx_ring->ring_stats->rx_stats.alloc_buf_failed++; if (rx_buf) rx_buf->pagecnt_bias++; break; @@ -1275,7 +1275,9 @@ construct_skb: ice_finalize_xdp_rx(xdp_ring, xdp_xmit); rx_ring->skb = skb; - ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes); + if (rx_ring->ring_stats) + ice_update_rx_ring_stats(rx_ring, total_rx_pkts, + total_rx_bytes); /* guarantee a trip back through this routine if there was a failure */ return failure ? budget : (int)total_rx_pkts; @@ -1292,15 +1294,25 @@ static void __ice_update_sample(struct ice_q_vector *q_vector, struct ice_tx_ring *tx_ring; ice_for_each_tx_ring(tx_ring, *rc) { - packets += tx_ring->stats.pkts; - bytes += tx_ring->stats.bytes; + struct ice_ring_stats *ring_stats; + + ring_stats = tx_ring->ring_stats; + if (!ring_stats) + continue; + packets += ring_stats->stats.pkts; + bytes += ring_stats->stats.bytes; } } else { struct ice_rx_ring *rx_ring; ice_for_each_rx_ring(rx_ring, *rc) { - packets += rx_ring->stats.pkts; - bytes += rx_ring->stats.bytes; + struct ice_ring_stats *ring_stats; + + ring_stats = rx_ring->ring_stats; + if (!ring_stats) + continue; + packets += ring_stats->stats.pkts; + bytes += ring_stats->stats.bytes; } } @@ -1549,7 +1561,7 @@ static int __ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) /* A reprieve! - use start_queue because it doesn't call schedule */ netif_tx_start_queue(txring_txq(tx_ring)); - ++tx_ring->tx_stats.restart_q; + ++tx_ring->ring_stats->tx_stats.restart_q; return 0; } @@ -2293,7 +2305,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) if (__skb_linearize(skb)) goto out_drop; count = ice_txd_use_count(skb->len); - tx_ring->tx_stats.tx_linearize++; + tx_ring->ring_stats->tx_stats.tx_linearize++; } /* need: 1 descriptor per page * PAGE_SIZE/ICE_MAX_DATA_PER_TXD, @@ -2304,7 +2316,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) */ if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_CTX_DESC)) { - tx_ring->tx_stats.tx_busy++; + tx_ring->ring_stats->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 932b5661ec4d..4fd0e5d0a313 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -191,6 +191,16 @@ struct ice_rxq_stats { u64 alloc_buf_failed; }; +struct ice_ring_stats { + struct rcu_head rcu; /* to avoid race on free */ + struct ice_q_stats stats; + struct u64_stats_sync syncp; + union { + struct ice_txq_stats tx_stats; + struct ice_rxq_stats rx_stats; + }; +}; + enum ice_ring_state_t { ICE_TX_XPS_INIT_DONE, ICE_TX_NBITS, @@ -283,9 +293,7 @@ struct ice_rx_ring { u16 rx_buf_len; /* stats structs */ - struct ice_rxq_stats rx_stats; - struct ice_q_stats stats; - struct u64_stats_sync syncp; + struct ice_ring_stats *ring_stats; struct rcu_head rcu; /* to avoid race on free */ /* CL4 - 3rd cacheline starts here */ @@ -325,10 +333,8 @@ struct ice_tx_ring { u16 count; /* Number of descriptors */ u16 q_index; /* Queue number of ring */ /* stats structs */ - struct ice_txq_stats tx_stats; + struct ice_ring_stats *ring_stats; /* CL3 - 3rd cacheline starts here */ - struct ice_q_stats stats; - struct u64_stats_sync syncp; struct rcu_head rcu; /* to avoid race on free */ DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ struct ice_channel *ch; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 7ee38d02d1e5..25f04266c668 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -285,7 +285,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) ice_clean_xdp_irq(xdp_ring); if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { - xdp_ring->tx_stats.tx_busy++; + xdp_ring->ring_stats->tx_stats.tx_busy++; return ICE_XDP_CONSUMED; } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index e1abfcee96dc..e3f622cad425 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -524,7 +524,14 @@ struct ice_sched_node { struct ice_sched_node *sibling; /* next sibling in the same layer */ struct ice_sched_node **children; struct ice_aqc_txsched_elem_data info; + char *name; + struct devlink_rate *rate_node; + u64 tx_max; + u64 tx_share; u32 agg_id; /* aggregator group ID */ + u32 id; + u32 tx_priority; + u32 tx_weight; u16 vsi_handle; u8 in_use; /* suspended or in use */ u8 tx_sched_layer; /* Logical Layer (1-9) */ @@ -706,7 +713,9 @@ struct ice_port_info { /* List contain profile ID(s) and other params per layer */ struct list_head rl_prof_list[ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct ice_qos_cfg qos_cfg; + struct xarray sched_node_ids; u8 is_vf:1; + u8 is_custom_tx_enabled:1; }; struct ice_switch_info { diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 1c51778db951..375eb6493f0f 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -700,6 +700,30 @@ void ice_dis_vf_qs(struct ice_vf *vf) } /** + * ice_err_to_virt_err - translate errors for VF return code + * @err: error return code + */ +enum virtchnl_status_code ice_err_to_virt_err(int err) +{ + switch (err) { + case 0: + return VIRTCHNL_STATUS_SUCCESS; + case -EINVAL: + case -ENODEV: + return VIRTCHNL_STATUS_ERR_PARAM; + case -ENOMEM: + return VIRTCHNL_STATUS_ERR_NO_MEMORY; + case -EALREADY: + case -EBUSY: + case -EIO: + case -ENOSPC: + return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; + default: + return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + } +} + +/** * ice_check_vf_init - helper to check if VF init complete * @vf: the pointer to the VF to check */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 15887e772c76..9c8ef2b01f0f 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -25,6 +25,7 @@ void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); +enum virtchnl_status_code ice_err_to_virt_err(int err); struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf); int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable); bool ice_is_vf_trusted(struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index fc8c93fa4455..d4a4001b6e5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -39,6 +39,24 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); } +static const u32 ice_legacy_aq_to_vc_speed[15] = { + VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */ + VIRTCHNL_LINK_SPEED_100MB, + VIRTCHNL_LINK_SPEED_1GB, + VIRTCHNL_LINK_SPEED_1GB, + VIRTCHNL_LINK_SPEED_1GB, + VIRTCHNL_LINK_SPEED_10GB, + VIRTCHNL_LINK_SPEED_20GB, + VIRTCHNL_LINK_SPEED_25GB, + VIRTCHNL_LINK_SPEED_40GB, + VIRTCHNL_LINK_SPEED_40GB, + VIRTCHNL_LINK_SPEED_40GB, + VIRTCHNL_LINK_SPEED_UNKNOWN, + VIRTCHNL_LINK_SPEED_UNKNOWN, + VIRTCHNL_LINK_SPEED_UNKNOWN, + VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */ +}; + /** * ice_conv_link_speed_to_virtchnl * @adv_link_support: determines the format of the returned link speed @@ -55,79 +73,17 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) { u32 speed; - if (adv_link_support) - switch (link_speed) { - case ICE_AQ_LINK_SPEED_10MB: - speed = ICE_LINK_SPEED_10MBPS; - break; - case ICE_AQ_LINK_SPEED_100MB: - speed = ICE_LINK_SPEED_100MBPS; - break; - case ICE_AQ_LINK_SPEED_1000MB: - speed = ICE_LINK_SPEED_1000MBPS; - break; - case ICE_AQ_LINK_SPEED_2500MB: - speed = ICE_LINK_SPEED_2500MBPS; - break; - case ICE_AQ_LINK_SPEED_5GB: - speed = ICE_LINK_SPEED_5000MBPS; - break; - case ICE_AQ_LINK_SPEED_10GB: - speed = ICE_LINK_SPEED_10000MBPS; - break; - case ICE_AQ_LINK_SPEED_20GB: - speed = ICE_LINK_SPEED_20000MBPS; - break; - case ICE_AQ_LINK_SPEED_25GB: - speed = ICE_LINK_SPEED_25000MBPS; - break; - case ICE_AQ_LINK_SPEED_40GB: - speed = ICE_LINK_SPEED_40000MBPS; - break; - case ICE_AQ_LINK_SPEED_50GB: - speed = ICE_LINK_SPEED_50000MBPS; - break; - case ICE_AQ_LINK_SPEED_100GB: - speed = ICE_LINK_SPEED_100000MBPS; - break; - default: - speed = ICE_LINK_SPEED_UNKNOWN; - break; - } - else + if (adv_link_support) { + /* convert a BIT() value into an array index */ + speed = ice_get_link_speed(fls(link_speed) - 1); + } else { /* Virtchnl speeds are not defined for every speed supported in * the hardware. To maintain compatibility with older AVF * drivers, while reporting the speed the new speed values are * resolved to the closest known virtchnl speeds */ - switch (link_speed) { - case ICE_AQ_LINK_SPEED_10MB: - case ICE_AQ_LINK_SPEED_100MB: - speed = (u32)VIRTCHNL_LINK_SPEED_100MB; - break; - case ICE_AQ_LINK_SPEED_1000MB: - case ICE_AQ_LINK_SPEED_2500MB: - case ICE_AQ_LINK_SPEED_5GB: - speed = (u32)VIRTCHNL_LINK_SPEED_1GB; - break; - case ICE_AQ_LINK_SPEED_10GB: - speed = (u32)VIRTCHNL_LINK_SPEED_10GB; - break; - case ICE_AQ_LINK_SPEED_20GB: - speed = (u32)VIRTCHNL_LINK_SPEED_20GB; - break; - case ICE_AQ_LINK_SPEED_25GB: - speed = (u32)VIRTCHNL_LINK_SPEED_25GB; - break; - case ICE_AQ_LINK_SPEED_40GB: - case ICE_AQ_LINK_SPEED_50GB: - case ICE_AQ_LINK_SPEED_100GB: - speed = (u32)VIRTCHNL_LINK_SPEED_40GB; - break; - default: - speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; - break; - } + speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1]; + } return speed; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 2b4c791b6cba..dab3cd5d300e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -462,6 +462,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; } + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; @@ -1658,6 +1661,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* copy Rx queue info from VF into VSI */ if (qpi->rxq.ring_len > 0) { u16 max_frame_size = ice_vc_get_max_frame_size(vf); + u32 rxdid; vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; @@ -1685,6 +1689,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) vf->vf_id, i); goto error_param; } + + /* If Rx flex desc is supported, select RXDID for Rx + * queues. Otherwise, use legacy 32byte descriptor + * format. Legacy 16byte descriptor is not supported. + * If this RXDID is selected, return error. + */ + if (vf->driver_caps & + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) { + rxdid = qpi->rxq.rxdid; + if (!(BIT(rxdid) & pf->supported_rxdids)) + goto error_param; + } else { + rxdid = ICE_RXDID_LEGACY_1; + } + + ice_write_qrxflxp_cntxt(&vsi->back->hw, + vsi->rxq_map[q_idx], + rxdid, 0x03, false); } } @@ -2457,6 +2479,164 @@ error_param: } /** + * ice_vc_get_rss_hena - return the RSS HENA bits allowed by the hardware + * @vf: pointer to the VF info + */ +static int ice_vc_get_rss_hena(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_rss_hena *vrh = NULL; + int len = 0, ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + dev_err(ice_pf_to_dev(vf->pf), "RSS not supported by PF\n"); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_rss_hena); + vrh = kzalloc(len, GFP_KERNEL); + if (!vrh) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + len = 0; + goto err; + } + + vrh->hena = ICE_DEFAULT_RSS_HENA; +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HENA_CAPS, v_ret, + (u8 *)vrh, len); + kfree(vrh); + return ret; +} + +/** + * ice_vc_set_rss_hena - set RSS HENA bits for the VF + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + */ +static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + struct device *dev; + int status; + + dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + dev_err(dev, "RSS not supported by PF\n"); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + /* clear all previously programmed RSS configuration to allow VF drivers + * the ability to customize the RSS configuration and/or completely + * disable RSS + */ + status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx); + if (status && !vrh->hena) { + /* only report failure to clear the current RSS configuration if + * that was clearly the VF's intention (i.e. vrh->hena = 0) + */ + v_ret = ice_err_to_virt_err(status); + goto err; + } else if (status) { + /* allow the VF to update the RSS configuration even on failure + * to clear the current RSS confguration in an attempt to keep + * RSS in a working state + */ + dev_warn(dev, "Failed to clear the RSS configuration for VF %u\n", + vf->vf_id); + } + + if (vrh->hena) { + status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, vrh->hena); + v_ret = ice_err_to_virt_err(status); + } + + /* send the response to the VF */ +err: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_SET_RSS_HENA, v_ret, + NULL, 0); +} + +/** + * ice_vc_query_rxdid - query RXDID supported by DDP package + * @vf: pointer to VF info + * + * Called from VF to query a bitmap of supported flexible + * descriptor RXDIDs of a DDP package. + */ +static int ice_vc_query_rxdid(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_supported_rxdids *rxdid = NULL; + struct ice_hw *hw = &vf->pf->hw; + struct ice_pf *pf = vf->pf; + int len = 0; + int ret, i; + u32 regval; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_supported_rxdids); + rxdid = kzalloc(len, GFP_KERNEL); + if (!rxdid) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + len = 0; + goto err; + } + + /* Read flexiflag registers to determine whether the + * corresponding RXDID is configured and supported or not. + * Since Legacy 16byte descriptor format is not supported, + * start from Legacy 32byte descriptor. + */ + for (i = ICE_RXDID_LEGACY_1; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); + if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) + & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) + rxdid->supported_rxdids |= BIT(i); + } + + pf->supported_rxdids = rxdid->supported_rxdids; + +err: + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + v_ret, (u8 *)rxdid, len); + kfree(rxdid); + return ret; +} + +/** * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization * @vf: VF to enable/disable VLAN stripping for on initialization * @@ -3490,6 +3670,9 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, .add_vlan_msg = ice_vc_add_vlan_msg, .remove_vlan_msg = ice_vc_remove_vlan_msg, + .query_rxdid = ice_vc_query_rxdid, + .get_rss_hena = ice_vc_get_rss_hena, + .set_rss_hena_msg = ice_vc_set_rss_hena, .ena_vlan_stripping = ice_vc_ena_vlan_stripping, .dis_vlan_stripping = ice_vc_dis_vlan_stripping, .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, @@ -3624,6 +3807,9 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode, .add_vlan_msg = ice_vc_add_vlan_msg, .remove_vlan_msg = ice_vc_remove_vlan_msg, + .query_rxdid = ice_vc_query_rxdid, + .get_rss_hena = ice_vc_get_rss_hena, + .set_rss_hena_msg = ice_vc_set_rss_hena, .ena_vlan_stripping = ice_vc_ena_vlan_stripping, .dis_vlan_stripping = ice_vc_dis_vlan_stripping, .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, @@ -3764,6 +3950,15 @@ error_handler: case VIRTCHNL_OP_DEL_VLAN: err = ops->remove_vlan_msg(vf, msg); break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + err = ops->query_rxdid(vf); + break; + case VIRTCHNL_OP_GET_RSS_HENA_CAPS: + err = ops->get_rss_hena(vf); + break; + case VIRTCHNL_OP_SET_RSS_HENA: + err = ops->set_rss_hena_msg(vf, msg); + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: err = ops->ena_vlan_stripping(vf); break; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index b5a3fd8adbb4..b454654d7b0c 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -17,6 +17,7 @@ * broadcast, and 16 for additional unicast/multicast filters */ #define ICE_MAX_MACADDR_PER_VF 18 +#define ICE_FLEX_DESC_RXDID_MAX_NUM 64 struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); @@ -35,6 +36,9 @@ struct ice_virtchnl_ops { int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*query_rxdid)(struct ice_vf *vf); + int (*get_rss_hena)(struct ice_vf *vf); + int (*set_rss_hena_msg)(struct ice_vf *vf, u8 *msg); int (*ena_vlan_stripping)(struct ice_vf *vf); int (*dis_vlan_stripping)(struct ice_vf *vf); int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5a82216e7d03..7d547fa616fa 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -70,6 +70,11 @@ static const u32 rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA, }; +/* VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC */ +static const u32 rx_flex_desc_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, +}; + /* VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF */ static const u32 adv_rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_RSS_CFG, VIRTCHNL_OP_DEL_RSS_CFG, @@ -96,6 +101,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_REQ_QUEUES, req_queues_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN, vlan_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RSS_PF, rss_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, rx_flex_desc_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 056c904b83cc..907055b77af0 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -24,13 +24,24 @@ static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx) */ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) { - memset(&vsi->rx_rings[q_idx]->rx_stats, 0, - sizeof(vsi->rx_rings[q_idx]->rx_stats)); - memset(&vsi->tx_rings[q_idx]->stats, 0, - sizeof(vsi->tx_rings[q_idx]->stats)); + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf; + + pf = vsi->back; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + memset(&vsi_stat->rx_ring_stats[q_idx]->rx_stats, 0, + sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats)); + memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0, + sizeof(vsi_stat->tx_ring_stats[q_idx]->stats)); if (ice_is_xdp_ena_vsi(vsi)) - memset(&vsi->xdp_rings[q_idx]->stats, 0, - sizeof(vsi->xdp_rings[q_idx]->stats)); + memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0, + sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats)); } /** @@ -722,7 +733,7 @@ construct_skb: /* XDP_PASS path */ skb = ice_construct_skb_zc(rx_ring, xdp); if (!skb) { - rx_ring->rx_stats.alloc_buf_failed++; + rx_ring->ring_stats->rx_stats.alloc_buf_failed++; break; } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index ff911af16a4b..7d60da1b7bf4 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2313,15 +2313,15 @@ static void igb_get_ethtool_stats(struct net_device *netdev, ring = adapter->tx_ring[j]; do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp); + start = u64_stats_fetch_begin(&ring->tx_syncp); data[i] = ring->tx_stats.packets; data[i+1] = ring->tx_stats.bytes; data[i+2] = ring->tx_stats.restart_queue; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp2); + start = u64_stats_fetch_begin(&ring->tx_syncp2); restart2 = ring->tx_stats.restart_queue2; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp2, start)); data[i+2] += restart2; i += IGB_TX_QUEUE_STATS_LEN; @@ -2329,13 +2329,13 @@ static void igb_get_ethtool_stats(struct net_device *netdev, for (j = 0; j < adapter->num_rx_queues; j++) { ring = adapter->rx_ring[j]; do { - start = u64_stats_fetch_begin_irq(&ring->rx_syncp); + start = u64_stats_fetch_begin(&ring->rx_syncp); data[i] = ring->rx_stats.packets; data[i+1] = ring->rx_stats.bytes; data[i+2] = ring->rx_stats.drops; data[i+3] = ring->rx_stats.csum_err; data[i+4] = ring->rx_stats.alloc_failed; - } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); i += IGB_RX_QUEUE_STATS_LEN; } spin_unlock(&adapter->stats64_lock); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index f8e32833226c..97290fc0fddd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1195,15 +1195,19 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, return -ENOMEM; ring_count = txr_count + rxr_count; - size = struct_size(q_vector, ring, ring_count); + size = kmalloc_size_roundup(struct_size(q_vector, ring, ring_count)); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; if (!q_vector) { q_vector = kzalloc(size, GFP_KERNEL); } else if (size > ksize(q_vector)) { - kfree_rcu(q_vector, rcu); - q_vector = kzalloc(size, GFP_KERNEL); + struct igb_q_vector *new_q_vector; + + new_q_vector = kzalloc(size, GFP_KERNEL); + if (new_q_vector) + kfree_rcu(q_vector, rcu); + q_vector = new_q_vector; } else { memset(q_vector, 0, size); } @@ -6632,10 +6636,10 @@ void igb_update_stats(struct igb_adapter *adapter) } do { - start = u64_stats_fetch_begin_irq(&ring->rx_syncp); + start = u64_stats_fetch_begin(&ring->rx_syncp); _bytes = ring->rx_stats.bytes; _packets = ring->rx_stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); bytes += _bytes; packets += _packets; } @@ -6648,10 +6652,10 @@ void igb_update_stats(struct igb_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) { struct igb_ring *ring = adapter->tx_ring[i]; do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp); + start = u64_stats_fetch_begin(&ring->tx_syncp); _bytes = ring->tx_stats.bytes; _packets = ring->tx_stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); bytes += _bytes; packets += _packets; } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 15e57460e19e..6f471b91f562 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -195,23 +195,9 @@ static int igb_ptp_adjfine_82576(struct ptp_clock_info *ptp, long scaled_ppm) struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); struct e1000_hw *hw = &igb->hw; - int neg_adj = 0; - u64 rate; - u32 incvalue; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - incvalue = INCVALUE_82576; - rate = mul_u64_u64_div_u64(incvalue, (u64)scaled_ppm, - 1000000ULL << 16); + u64 incvalue; - if (neg_adj) - incvalue -= rate; - else - incvalue += rate; + incvalue = adjust_by_scaled_ppm(INCVALUE_82576, scaled_ppm); wr32(E1000_TIMINCA, INCPERIOD_82576 | (incvalue & INCVALUE_82576_MASK)); diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 4f9d7f013a95..f7311aeb293b 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -400,6 +400,15 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Transmit Scheduling Latency */ +/* Latency between transmission scheduling (LaunchTime) and the time + * the packet is transmitted to the network in nanosecond. + */ +#define IGC_TXOFFSET_SPEED_10 0x000034BC +#define IGC_TXOFFSET_SPEED_100 0x00000578 +#define IGC_TXOFFSET_SPEED_1000 0x0000012C +#define IGC_TXOFFSET_SPEED_2500 0x00000578 + /* Time Sync Interrupt Causes */ #define IGC_TSICR_SYS_WRAP BIT(0) /* SYSTIM Wrap around. */ #define IGC_TSICR_TXTS BIT(1) /* Transmit Timestamp. */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 8cc077b712ad..5a26a7805ef8 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -839,15 +839,15 @@ static void igc_ethtool_get_stats(struct net_device *netdev, ring = adapter->tx_ring[j]; do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp); + start = u64_stats_fetch_begin(&ring->tx_syncp); data[i] = ring->tx_stats.packets; data[i + 1] = ring->tx_stats.bytes; data[i + 2] = ring->tx_stats.restart_queue; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp2); + start = u64_stats_fetch_begin(&ring->tx_syncp2); restart2 = ring->tx_stats.restart_queue2; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp2, start)); data[i + 2] += restart2; i += IGC_TX_QUEUE_STATS_LEN; @@ -855,13 +855,13 @@ static void igc_ethtool_get_stats(struct net_device *netdev, for (j = 0; j < adapter->num_rx_queues; j++) { ring = adapter->rx_ring[j]; do { - start = u64_stats_fetch_begin_irq(&ring->rx_syncp); + start = u64_stats_fetch_begin(&ring->rx_syncp); data[i] = ring->rx_stats.packets; data[i + 1] = ring->rx_stats.bytes; data[i + 2] = ring->rx_stats.drops; data[i + 3] = ring->rx_stats.csum_err; data[i + 4] = ring->rx_stats.alloc_failed; - } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); i += IGC_RX_QUEUE_STATS_LEN; } spin_unlock(&adapter->stats64_lock); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 34889be63e78..1586e1e435c6 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4682,10 +4682,10 @@ void igc_update_stats(struct igc_adapter *adapter) } do { - start = u64_stats_fetch_begin_irq(&ring->rx_syncp); + start = u64_stats_fetch_begin(&ring->rx_syncp); _bytes = ring->rx_stats.bytes; _packets = ring->rx_stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); bytes += _bytes; packets += _packets; } @@ -4699,10 +4699,10 @@ void igc_update_stats(struct igc_adapter *adapter) struct igc_ring *ring = adapter->tx_ring[i]; do { - start = u64_stats_fetch_begin_irq(&ring->tx_syncp); + start = u64_stats_fetch_begin(&ring->tx_syncp); _bytes = ring->tx_stats.bytes; _packets = ring->tx_stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); + } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); bytes += _bytes; packets += _packets; } @@ -5381,6 +5381,13 @@ static void igc_watchdog_task(struct work_struct *work) break; } + /* Once the launch time has been set on the wire, there + * is a delay before the link speed can be determined + * based on link-up activity. Write into the register + * as soon as we know the correct link speed. + */ + igc_tsn_adjust_txtime_offset(adapter); + if (adapter->link_speed != SPEED_1000) goto no_wait; diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index c0d8214148d1..01c86d36856d 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -224,6 +224,7 @@ /* Transmit Scheduling Registers */ #define IGC_TQAVCTRL 0x3570 #define IGC_TXQCTL(_n) (0x3344 + 0x4 * (_n)) +#define IGC_GTXOFFSET 0x3310 #define IGC_BASET_L 0x3314 #define IGC_BASET_H 0x3318 #define IGC_QBVCYCLET 0x331C diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 0fce22de2ab8..f975ed807da1 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -48,6 +48,35 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u16 txoffset; + + if (!is_any_launchtime(adapter)) + return; + + switch (adapter->link_speed) { + case SPEED_10: + txoffset = IGC_TXOFFSET_SPEED_10; + break; + case SPEED_100: + txoffset = IGC_TXOFFSET_SPEED_100; + break; + case SPEED_1000: + txoffset = IGC_TXOFFSET_SPEED_1000; + break; + case SPEED_2500: + txoffset = IGC_TXOFFSET_SPEED_2500; + break; + default: + txoffset = 0; + break; + } + + wr32(IGC_GTXOFFSET, txoffset); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -57,6 +86,7 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) u32 tqavctrl; int i; + wr32(IGC_GTXOFFSET, 0); wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index 1512307f5a52..b53e6af560b7 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -6,5 +6,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); +void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 5369a97ff5ec..bc68b8f2176d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -39,7 +39,10 @@ /* TX/RX descriptor defines */ #define IXGBE_DEFAULT_TXD 512 #define IXGBE_DEFAULT_TX_WORK 256 -#define IXGBE_MAX_TXD 4096 +#define IXGBE_MAX_TXD_82598 4096 +#define IXGBE_MAX_TXD_82599 8192 +#define IXGBE_MAX_TXD_X540 8192 +#define IXGBE_MAX_TXD_X550 32768 #define IXGBE_MIN_TXD 64 #if (PAGE_SIZE < 8192) @@ -47,7 +50,10 @@ #else #define IXGBE_DEFAULT_RXD 128 #endif -#define IXGBE_MAX_RXD 4096 +#define IXGBE_MAX_RXD_82598 4096 +#define IXGBE_MAX_RXD_82599 8192 +#define IXGBE_MAX_RXD_X540 8192 +#define IXGBE_MAX_RXD_X550 32768 #define IXGBE_MIN_RXD 64 /* flow control */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index e88e3dfac8c2..6cfc9dc16537 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1117,6 +1117,42 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, drvinfo->n_priv_flags = IXGBE_PRIV_FLAGS_STR_LEN; } +static u32 ixgbe_get_max_rxd(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + return IXGBE_MAX_RXD_82598; + case ixgbe_mac_82599EB: + return IXGBE_MAX_RXD_82599; + case ixgbe_mac_X540: + return IXGBE_MAX_RXD_X540; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return IXGBE_MAX_RXD_X550; + default: + return IXGBE_MAX_RXD_82598; + } +} + +static u32 ixgbe_get_max_txd(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + return IXGBE_MAX_TXD_82598; + case ixgbe_mac_82599EB: + return IXGBE_MAX_TXD_82599; + case ixgbe_mac_X540: + return IXGBE_MAX_TXD_X540; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return IXGBE_MAX_TXD_X550; + default: + return IXGBE_MAX_TXD_82598; + } +} + static void ixgbe_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, @@ -1126,8 +1162,8 @@ static void ixgbe_get_ringparam(struct net_device *netdev, struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; struct ixgbe_ring *rx_ring = adapter->rx_ring[0]; - ring->rx_max_pending = IXGBE_MAX_RXD; - ring->tx_max_pending = IXGBE_MAX_TXD; + ring->rx_max_pending = ixgbe_get_max_rxd(adapter); + ring->tx_max_pending = ixgbe_get_max_txd(adapter); ring->rx_pending = rx_ring->count; ring->tx_pending = tx_ring->count; } @@ -1146,11 +1182,11 @@ static int ixgbe_set_ringparam(struct net_device *netdev, return -EINVAL; new_tx_count = clamp_t(u32, ring->tx_pending, - IXGBE_MIN_TXD, IXGBE_MAX_TXD); + IXGBE_MIN_TXD, ixgbe_get_max_txd(adapter)); new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); new_rx_count = clamp_t(u32, ring->rx_pending, - IXGBE_MIN_RXD, IXGBE_MAX_RXD); + IXGBE_MIN_RXD, ixgbe_get_max_rxd(adapter)); new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); if ((new_tx_count == adapter->tx_ring_count) && @@ -1335,10 +1371,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, } do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); data[i] = ring->stats.packets; data[i+1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); i += 2; } for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { @@ -1351,10 +1387,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, } do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); data[i] = ring->stats.packets; data[i+1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); i += 2; } @@ -1960,18 +1996,13 @@ static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer, unsigned int frame_size) { unsigned char *data; - bool match = true; frame_size >>= 1; data = page_address(rx_buffer->page) + rx_buffer->page_offset; - if (data[3] != 0xFF || - data[frame_size + 10] != 0xBE || - data[frame_size + 12] != 0xAF) - match = false; - - return match; + return data[3] == 0xFF && data[frame_size + 10] == 0xBE && + data[frame_size + 12] == 0xAF; } static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 774de63dd93a..53a969e34883 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -585,6 +585,11 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs) return -EINVAL; } + if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { + netdev_err(dev, "Unsupported ipsec offload type\n"); + return -EINVAL; + } + if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) { struct rx_sa rsa; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 298cfbfcb7b6..ab8370c413f3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9041,10 +9041,10 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, if (ring) { do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } @@ -9064,10 +9064,10 @@ static void ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index f8605f57bd06..0310af851086 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -451,21 +451,11 @@ static int ixgbe_ptp_adjfine_82599(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; - u64 incval, diff; - int neg_adj = 0; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } + u64 incval; smp_mb(); incval = READ_ONCE(adapter->base_incval); - - diff = mul_u64_u64_div_u64(incval, scaled_ppm, - 1000000ULL << 16); - - incval = neg_adj ? (incval - diff) : (incval + diff); + incval = adjust_by_scaled_ppm(incval, scaled_ppm); switch (hw->mac.type) { case ixgbe_mac_X540: @@ -502,17 +492,11 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; - int neg_adj = 0; + bool neg_adj; u64 rate; u32 inca; - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - rate = mul_u64_u64_div_u64(IXGBE_X550_BASE_PERIOD, scaled_ppm, - 1000000ULL << 16); + neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate); /* warn if rate is too large */ if (rate >= INCVALUE_MASK) @@ -1318,7 +1302,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) default: /* Other devices aren't supported */ return; - }; + } IXGBE_WRITE_FLUSH(hw); } diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index ccfa6b91aac6..296915414a7c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -458,10 +458,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, } do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); data[i] = ring->stats.packets; data[i + 1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); i += 2; } @@ -475,10 +475,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, } do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); data[i] = ring->stats.packets; data[i + 1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); i += 2; } @@ -492,10 +492,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, } do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); data[i] = ring->stats.packets; data[i + 1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); i += 2; } } diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index 9984ebc62d78..c1cf540d162a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -280,6 +280,11 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) return -EINVAL; } + if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { + netdev_err(dev, "Unsupported ipsec offload type\n"); + return -EINVAL; + } + if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) { struct rx_sa rsa; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index e338fa572793..ea0a230c1153 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2044,12 +2044,16 @@ static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, spin_unlock_bh(&adapter->mbx_lock); - /* translate error return types so error makes sense */ - if (err == IXGBE_ERR_MBX) - return -EIO; + if (err) { + netdev_err(netdev, "VF could not set VLAN %d\n", vid); + + /* translate error return types so error makes sense */ + if (err == IXGBE_ERR_MBX) + return -EIO; - if (err == IXGBE_ERR_INVALID_ARGUMENT) - return -EACCES; + if (err == IXGBE_ERR_INVALID_ARGUMENT) + return -EACCES; + } set_bit(vid, adapter->active_vlans); @@ -2070,6 +2074,9 @@ static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, spin_unlock_bh(&adapter->mbx_lock); + if (err) + netdev_err(netdev, "Could not remove VLAN %d\n", vid); + clear_bit(vid, adapter->active_vlans); return err; @@ -4350,10 +4357,10 @@ static void ixgbevf_get_tx_ring_stats(struct rtnl_link_stats64 *stats, if (ring) { do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); bytes = ring->stats.bytes; packets = ring->stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->tx_bytes += bytes; stats->tx_packets += packets; } @@ -4376,10 +4383,10 @@ static void ixgbevf_get_stats(struct net_device *netdev, for (i = 0; i < adapter->num_rx_queues; i++) { ring = adapter->rx_ring[i]; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); bytes = ring->stats.bytes; packets = ring->stats.packets; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->rx_bytes += bytes; stats->rx_packets += packets; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 8941f69d93e9..3b129a1c3381 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -108,6 +108,7 @@ static char mv643xx_eth_driver_version[] = "1.4"; #define TXQ_COMMAND 0x0048 #define TXQ_FIX_PRIO_CONF 0x004c #define PORT_SERIAL_CONTROL1 0x004c +#define RGMII_EN 0x00000008 #define CLK125_BYPASS_EN 0x00000010 #define TX_BW_RATE 0x0050 #define TX_BW_MTU 0x0058 @@ -2762,6 +2763,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, mv643xx_eth_property(pnp, "rx-sram-addr", ppd.rx_sram_addr); mv643xx_eth_property(pnp, "rx-sram-size", ppd.rx_sram_size); + of_get_phy_mode(pnp, &ppd.interface); + ppd.phy_node = of_parse_phandle(pnp, "phy-handle", 0); if (!ppd.phy_node) { ppd.phy_addr = MV643XX_ETH_PHY_NONE; @@ -3093,6 +3096,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev) struct mv643xx_eth_private *mp; struct net_device *dev; struct phy_device *phydev = NULL; + u32 psc1r; int err, irq; pd = dev_get_platdata(&pdev->dev); @@ -3120,14 +3124,45 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->dev = dev; - /* Kirkwood resets some registers on gated clocks. Especially - * CLK125_BYPASS_EN must be cleared but is not available on - * all other SoCs/System Controllers using this driver. - */ if (of_device_is_compatible(pdev->dev.of_node, - "marvell,kirkwood-eth-port")) - wrlp(mp, PORT_SERIAL_CONTROL1, - rdlp(mp, PORT_SERIAL_CONTROL1) & ~CLK125_BYPASS_EN); + "marvell,kirkwood-eth-port")) { + psc1r = rdlp(mp, PORT_SERIAL_CONTROL1); + + /* Kirkwood resets some registers on gated clocks. Especially + * CLK125_BYPASS_EN must be cleared but is not available on + * all other SoCs/System Controllers using this driver. + */ + psc1r &= ~CLK125_BYPASS_EN; + + /* On Kirkwood with two Ethernet controllers, if both of them + * have RGMII_EN disabled, the first controller will be in GMII + * mode and the second one is effectively disabled, instead of + * two MII interfaces. + * + * To enable GMII in the first controller, the second one must + * also be configured (and may be enabled) with RGMII_EN + * disabled too, even though it cannot be used at all. + */ + switch (pd->interface) { + /* Use internal to denote second controller being disabled */ + case PHY_INTERFACE_MODE_INTERNAL: + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_GMII: + psc1r &= ~RGMII_EN; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + psc1r |= RGMII_EN; + break; + default: + /* Unknown; don't touch */ + break; + } + + wrlp(mp, PORT_SERIAL_CONTROL1, psc1r); + } /* * Start with a default rate, and if there is a clock, allow diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5aefaaff0871..f8925cac61e4 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -813,14 +813,14 @@ mvneta_get_stats64(struct net_device *dev, cpu_stats = per_cpu_ptr(pp->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); rx_packets = cpu_stats->es.ps.rx_packets; rx_bytes = cpu_stats->es.ps.rx_bytes; rx_dropped = cpu_stats->rx_dropped; rx_errors = cpu_stats->rx_errors; tx_packets = cpu_stats->es.ps.tx_packets; tx_bytes = cpu_stats->es.ps.tx_bytes; - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -4228,7 +4228,6 @@ static void mvneta_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mvneta_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvneta_mac_select_pcs, .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, @@ -4266,7 +4265,7 @@ static void mvneta_mdio_remove(struct mvneta_port *pp) */ static void mvneta_percpu_elect(struct mvneta_port *pp) { - int elected_cpu = 0, max_cpu, cpu, i = 0; + int elected_cpu = 0, max_cpu, cpu; /* Use the cpu associated to the rxq when it is online, in all * the other cases, use the cpu 0 which can't be offline. @@ -4306,8 +4305,6 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) */ smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt, pp, true); - i++; - } }; @@ -4762,7 +4759,7 @@ mvneta_ethtool_update_pcpu_stats(struct mvneta_port *pp, stats = per_cpu_ptr(pp->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&stats->syncp); + start = u64_stats_fetch_begin(&stats->syncp); skb_alloc_error = stats->es.skb_alloc_error; refill_error = stats->es.refill_error; xdp_redirect = stats->es.ps.xdp_redirect; @@ -4772,7 +4769,7 @@ mvneta_ethtool_update_pcpu_stats(struct mvneta_port *pp, xdp_xmit_err = stats->es.ps.xdp_xmit_err; xdp_tx = stats->es.ps.xdp_tx; xdp_tx_err = stats->es.ps.xdp_tx_err; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->syncp, start)); es->skb_alloc_error += skb_alloc_error; es->refill_error += refill_error; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index b399bdb1ca36..4da45c5abba5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2008,7 +2008,7 @@ mvpp2_get_xdp_stats(struct mvpp2_port *port, struct mvpp2_pcpu_stats *xdp_stats) cpu_stats = per_cpu_ptr(port->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); xdp_redirect = cpu_stats->xdp_redirect; xdp_pass = cpu_stats->xdp_pass; xdp_drop = cpu_stats->xdp_drop; @@ -2016,7 +2016,7 @@ mvpp2_get_xdp_stats(struct mvpp2_port *port, struct mvpp2_pcpu_stats *xdp_stats) xdp_xmit_err = cpu_stats->xdp_xmit_err; xdp_tx = cpu_stats->xdp_tx; xdp_tx_err = cpu_stats->xdp_tx_err; - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); xdp_stats->xdp_redirect += xdp_redirect; xdp_stats->xdp_pass += xdp_pass; @@ -5115,12 +5115,12 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) cpu_stats = per_cpu_ptr(port->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); rx_packets = cpu_stats->rx_packets; rx_bytes = cpu_stats->rx_bytes; tx_packets = cpu_stats->tx_packets; tx_bytes = cpu_stats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -6104,6 +6104,13 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, } } + /* Only valid on OF enabled platforms */ + if (!of_get_mac_address_nvmem(to_of_node(fwnode), fw_mac_addr)) { + *mac_from = "nvmem cell"; + eth_hw_addr_set(dev, fw_mac_addr); + return; + } + *mac_from = "random"; eth_hw_addr_random(dev); } @@ -6603,7 +6610,6 @@ static void mvpp2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops mvpp2_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, .mac_config = mvpp2_mac_config, diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index b45dd7f04e21..5a898fb88e37 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -23,6 +23,7 @@ struct workqueue_struct *octep_wq; /* Supported Devices */ static const struct pci_device_id octep_pci_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_PF)}, + {PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CNF95N_PF)}, {0, }, }; MODULE_DEVICE_TABLE(pci, octep_pci_id_tbl); @@ -905,6 +906,18 @@ static void octep_ctrl_mbox_task(struct work_struct *work) } } +static const char *octep_devid_to_str(struct octep_device *oct) +{ + switch (oct->chip_id) { + case OCTEP_PCI_DEVICE_ID_CN93_PF: + return "CN93XX"; + case OCTEP_PCI_DEVICE_ID_CNF95N_PF: + return "CNF95N"; + default: + return "Unsupported"; + } +} + /** * octep_device_setup() - Setup Octeon Device. * @@ -937,9 +950,10 @@ int octep_device_setup(struct octep_device *oct) switch (oct->chip_id) { case OCTEP_PCI_DEVICE_ID_CN93_PF: - dev_info(&pdev->dev, - "Setting up OCTEON CN93XX PF PASS%d.%d\n", - OCTEP_MAJOR_REV(oct), OCTEP_MINOR_REV(oct)); + case OCTEP_PCI_DEVICE_ID_CNF95N_PF: + dev_info(&pdev->dev, "Setting up OCTEON %s PF PASS%d.%d\n", + octep_devid_to_str(oct), OCTEP_MAJOR_REV(oct), + OCTEP_MINOR_REV(oct)); octep_device_setup_cn93_pf(oct); break; default: diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h index 025626a61383..123ffc13754d 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h @@ -21,6 +21,8 @@ #define OCTEP_PCI_DEVICE_ID_CN93_PF 0xB200 #define OCTEP_PCI_DEVICE_ID_CN93_VF 0xB203 +#define OCTEP_PCI_DEVICE_ID_CNF95N_PF 0xB400 //95N PF + #define OCTEP_MAX_QUEUES 63 #define OCTEP_MAX_IQ OCTEP_MAX_QUEUES #define OCTEP_MAX_OQ OCTEP_MAX_QUEUES diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index c8724bfa86b0..b2b71fe80d61 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -64,6 +64,7 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en); static const struct pci_device_id cgx_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) }, { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM) }, + { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM) }, { 0, } /* end of table */ }; @@ -73,12 +74,13 @@ static bool is_dev_rpm(void *cgxd) { struct cgx *cgx = cgxd; - return (cgx->pdev->device == PCI_DEVID_CN10K_RPM); + return (cgx->pdev->device == PCI_DEVID_CN10K_RPM) || + (cgx->pdev->device == PCI_DEVID_CN10KB_RPM); } bool is_lmac_valid(struct cgx *cgx, int lmac_id) { - if (!cgx || lmac_id < 0 || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id < 0 || lmac_id >= cgx->max_lmac_per_mac) return false; return test_bit(lmac_id, &cgx->lmac_bmap); } @@ -90,7 +92,7 @@ static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id) { int tmp, id = 0; - for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(tmp, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { if (tmp == lmac_id) break; id++; @@ -121,7 +123,7 @@ u64 cgx_read(struct cgx *cgx, u64 lmac, u64 offset) struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx) { - if (!cgx || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id >= cgx->max_lmac_per_mac) return NULL; return cgx->lmac_idmap[lmac_id]; @@ -485,7 +487,7 @@ int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind) if (!is_lmac_valid(cgx, lmac_id)) return -ENODEV; - cgx_write(cgx, lmac_id, CGXX_CMRX_RX_ID_MAP, (pkind & 0x3F)); + cgx_write(cgx, lmac_id, cgx->mac_ops->rxid_map_offset, (pkind & 0x3F)); return 0; } @@ -740,6 +742,10 @@ int cgx_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp) if (!cgx || lmac_id >= cgx->lmac_count) return -ENODEV; + + if (cgx->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_NONE) + return 0; + fec_stats_count = cgx_set_fec_stats_count(&cgx->lmac_idmap[lmac_id]->link_info); if (cgx->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_BASER) { @@ -1224,7 +1230,7 @@ static inline void link_status_user_format(u64 lstat, linfo->speed = cgx_speed_mbps[FIELD_GET(RESP_LINKSTAT_SPEED, lstat)]; linfo->an = FIELD_GET(RESP_LINKSTAT_AN, lstat); linfo->fec = FIELD_GET(RESP_LINKSTAT_FEC, lstat); - linfo->lmac_type_id = cgx_get_lmac_type(cgx, lmac_id); + linfo->lmac_type_id = FIELD_GET(RESP_LINKSTAT_LMAC_TYPE, lstat); lmac_string = cgx_lmactype_string[linfo->lmac_type_id]; strncpy(linfo->lmac_type, lmac_string, LMACTYPE_STR_LEN - 1); } @@ -1395,7 +1401,7 @@ int cgx_get_fwdata_base(u64 *base) if (!cgx) return -ENXIO; - first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FWD_BASE, req); err = cgx_fwi_cmd_generic(req, &resp, cgx, first_lmac); if (!err) @@ -1484,7 +1490,7 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable) static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx) { - int first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + int first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); u64 req = 0; req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FW_VER, req); @@ -1522,7 +1528,7 @@ static void cgx_lmac_linkup_work(struct work_struct *work) int i, err; /* Do Link up for all the enabled lmacs */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { err = cgx_fwi_link_change(cgx, i, true); if (err) dev_info(dev, "cgx port %d:%d Link up command failed\n", @@ -1542,14 +1548,6 @@ int cgx_lmac_linkup_start(void *cgxd) return 0; } -static void cgx_lmac_get_fifolen(struct cgx *cgx) -{ - u64 cfg; - - cfg = cgx_read(cgx, 0, CGX_CONST); - cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); -} - static int cgx_configure_interrupt(struct cgx *cgx, struct lmac *lmac, int cnt, bool req_free) { @@ -1604,17 +1602,20 @@ static int cgx_lmac_init(struct cgx *cgx) u64 lmac_list; int i, err; - cgx_lmac_get_fifolen(cgx); - - cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx); /* lmac_list specifies which lmacs are enabled * when bit n is set to 1, LMAC[n] is enabled */ - if (cgx->mac_ops->non_contiguous_serdes_lane) - lmac_list = cgx_read(cgx, 0, CGXX_CMRX_RX_LMACS) & 0xFULL; + if (cgx->mac_ops->non_contiguous_serdes_lane) { + if (is_dev_rpm2(cgx)) + lmac_list = + cgx_read(cgx, 0, RPM2_CMRX_RX_LMACS) & 0xFFULL; + else + lmac_list = + cgx_read(cgx, 0, CGXX_CMRX_RX_LMACS) & 0xFULL; + } - if (cgx->lmac_count > MAX_LMAC_PER_CGX) - cgx->lmac_count = MAX_LMAC_PER_CGX; + if (cgx->lmac_count > cgx->max_lmac_per_mac) + cgx->lmac_count = cgx->max_lmac_per_mac; for (i = 0; i < cgx->lmac_count; i++) { lmac = kzalloc(sizeof(struct lmac), GFP_KERNEL); @@ -1635,7 +1636,9 @@ static int cgx_lmac_init(struct cgx *cgx) lmac->cgx = cgx; lmac->mac_to_index_bmap.max = - MAX_DMAC_ENTRIES_PER_CGX / cgx->lmac_count; + cgx->mac_ops->dmac_filter_count / + cgx->lmac_count; + err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap); if (err) goto err_name_free; @@ -1692,7 +1695,7 @@ static int cgx_lmac_exit(struct cgx *cgx) } /* Free all lmac related resources */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { lmac = cgx->lmac_idmap[i]; if (!lmac) continue; @@ -1708,6 +1711,12 @@ static int cgx_lmac_exit(struct cgx *cgx) static void cgx_populate_features(struct cgx *cgx) { + u64 cfg; + + cfg = cgx_read(cgx, 0, CGX_CONST); + cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); + cgx->max_lmac_per_mac = FIELD_GET(CGX_CONST_MAX_LMACS, cfg); + if (is_dev_rpm(cgx)) cgx->hw_features = (RVU_LMAC_FEAT_DMACF | RVU_MAC_RPM | RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_PTP); @@ -1716,6 +1725,15 @@ static void cgx_populate_features(struct cgx *cgx) RVU_LMAC_FEAT_PTP | RVU_LMAC_FEAT_DMACF); } +static u8 cgx_get_rxid_mapoffset(struct cgx *cgx) +{ + if (cgx->pdev->subsystem_device == PCI_SUBSYS_DEVID_CNF10KB_RPM || + is_dev_rpm2(cgx)) + return 0x80; + else + return 0x60; +} + static struct mac_ops cgx_mac_ops = { .name = "cgx", .csr_offset = 0, @@ -1728,12 +1746,14 @@ static struct mac_ops cgx_mac_ops = { .non_contiguous_serdes_lane = false, .rx_stats_cnt = 9, .tx_stats_cnt = 18, + .dmac_filter_count = 32, .get_nr_lmacs = cgx_get_nr_lmacs, .get_lmac_type = cgx_get_lmac_type, .lmac_fifo_len = cgx_get_lmac_fifo_len, .mac_lmac_intl_lbk = cgx_lmac_internal_loopback, .mac_get_rx_stats = cgx_get_rx_stats, .mac_get_tx_stats = cgx_get_tx_stats, + .get_fec_stats = cgx_get_fec_stats, .mac_enadis_rx_pause_fwding = cgx_lmac_enadis_rx_pause_fwding, .mac_get_pause_frm_status = cgx_lmac_get_pause_frm_status, .mac_enadis_pause_frm = cgx_lmac_enadis_pause_frm, @@ -1759,11 +1779,13 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_drvdata(pdev, cgx); /* Use mac_ops to get MAC specific features */ - if (pdev->device == PCI_DEVID_CN10K_RPM) - cgx->mac_ops = rpm_get_mac_ops(); + if (is_dev_rpm(cgx)) + cgx->mac_ops = rpm_get_mac_ops(cgx); else cgx->mac_ops = &cgx_mac_ops; + cgx->mac_ops->rxid_map_offset = cgx_get_rxid_mapoffset(cgx); + err = pci_enable_device(pdev); if (err) { dev_err(dev, "Failed to enable PCI device\n"); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 0b06788b8d80..fb2d37676d84 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -18,11 +18,7 @@ /* PCI BAR nos */ #define PCI_CFG_REG_BAR_NUM 0 -#define CGX_ID_MASK 0x7 -#define MAX_LMAC_PER_CGX 4 -#define MAX_DMAC_ENTRIES_PER_CGX 32 -#define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */ -#define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX) +#define CGX_ID_MASK 0xF /* Registers */ #define CGXX_CMRX_CFG 0x00 @@ -56,7 +52,8 @@ #define CGXX_SCRATCH0_REG 0x1050 #define CGXX_SCRATCH1_REG 0x1058 #define CGX_CONST 0x2000 -#define CGX_CONST_RXFIFO_SIZE GENMASK_ULL(23, 0) +#define CGX_CONST_RXFIFO_SIZE GENMASK_ULL(55, 32) +#define CGX_CONST_MAX_LMACS GENMASK_ULL(31, 24) #define CGXX_SPUX_CONTROL1 0x10000 #define CGXX_SPUX_LNX_FEC_CORR_BLOCKS 0x10700 #define CGXX_SPUX_LNX_FEC_UNCORR_BLOCKS 0x10800 diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index 52b6016789fa..39aaf0e4467d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -75,6 +75,11 @@ struct mac_ops { /* RPM & CGX differs in number of Receive/transmit stats */ u8 rx_stats_cnt; u8 tx_stats_cnt; + /* Unlike CN10K which shares same CSR offset with CGX + * CNF10KB has different csr offset + */ + u64 rxid_map_offset; + u8 dmac_filter_count; /* Incase of RPM get number of lmacs from RPMX_CMR_RX_LMACS[LMAC_EXIST] * number of setbits in lmac_exist tells number of lmacs */ @@ -121,6 +126,9 @@ struct mac_ops { int (*mac_get_pfc_frm_cfg)(void *cgxd, int lmac_id, u8 *tx_pause, u8 *rx_pause); + /* FEC stats */ + int (*get_fec_stats)(void *cgxd, int lmac_id, + struct cgx_fec_stats_rsp *rsp); }; struct cgx { @@ -128,7 +136,10 @@ struct cgx { struct pci_dev *pdev; u8 cgx_id; u8 lmac_count; - struct lmac *lmac_idmap[MAX_LMAC_PER_CGX]; + /* number of LMACs per MAC could be 4 or 8 */ + u8 max_lmac_per_mac; +#define MAX_LMAC_COUNT 8 + struct lmac *lmac_idmap[MAX_LMAC_COUNT]; struct work_struct cgx_cmd_work; struct workqueue_struct *cgx_cmd_workq; struct list_head cgx_list; @@ -150,6 +161,6 @@ struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx); int cgx_fwi_cmd_send(u64 req, u64 *resp, struct lmac *lmac); int cgx_fwi_cmd_generic(u64 req, u64 *resp, struct cgx *cgx, int lmac_id); bool is_lmac_valid(struct cgx *cgx, int lmac_id); -struct mac_ops *rpm_get_mac_ops(void); +struct mac_ops *rpm_get_mac_ops(struct cgx *cgx); #endif /* LMAC_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 8d5d5a0f68c4..d2584ebb7a70 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -245,6 +245,9 @@ M(NPC_MCAM_GET_STATS, 0x6012, npc_mcam_entry_stats, \ M(NPC_GET_SECRET_KEY, 0x6013, npc_get_secret_key, \ npc_get_secret_key_req, \ npc_get_secret_key_rsp) \ +M(NPC_GET_FIELD_STATUS, 0x6014, npc_get_field_status, \ + npc_get_field_status_req, \ + npc_get_field_status_rsp) \ /* NIX mbox IDs (range 0x8000 - 0xFFFF) */ \ M(NIX_LF_ALLOC, 0x8000, nix_lf_alloc, \ nix_lf_alloc_req, nix_lf_alloc_rsp) \ @@ -1437,6 +1440,10 @@ struct flow_msg { u8 tc; __be16 sport; __be16 dport; + union { + u8 ip_flag; + u8 next_header; + }; }; struct npc_install_flow_req { @@ -1541,6 +1548,17 @@ struct ptp_rsp { u64 clk; }; +struct npc_get_field_status_req { + struct mbox_msghdr hdr; + u8 intf; + u8 field; +}; + +struct npc_get_field_status_rsp { + struct mbox_msghdr hdr; + u8 enable; +}; + struct set_vf_perm { struct mbox_msghdr hdr; u16 vf; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index f187293e3e08..9beeead56d7b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -185,8 +185,10 @@ enum key_fields { NPC_VLAN_ETYPE_STAG, /* 0x88A8 */ NPC_OUTER_VID, NPC_TOS, + NPC_IPFRAG_IPV4, NPC_SIP_IPV4, NPC_DIP_IPV4, + NPC_IPFRAG_IPV6, NPC_SIP_IPV6, NPC_DIP_IPV6, NPC_IPPROTO_TCP, @@ -620,6 +622,7 @@ struct rvu_npc_mcam_rule { bool vfvlan_cfg; u16 chan; u16 chan_mask; + u8 lxmb; }; #endif /* NPC_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index a70e1153fa04..de0d88dd10d6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -8,7 +8,7 @@ #include "cgx.h" #include "lmac_common.h" -static struct mac_ops rpm_mac_ops = { +static struct mac_ops rpm_mac_ops = { .name = "rpm", .csr_offset = 0x4e00, .lmac_offset = 20, @@ -20,12 +20,14 @@ static struct mac_ops rpm_mac_ops = { .non_contiguous_serdes_lane = true, .rx_stats_cnt = 43, .tx_stats_cnt = 34, + .dmac_filter_count = 32, .get_nr_lmacs = rpm_get_nr_lmacs, .get_lmac_type = rpm_get_lmac_type, .lmac_fifo_len = rpm_get_lmac_fifo_len, .mac_lmac_intl_lbk = rpm_lmac_internal_loopback, .mac_get_rx_stats = rpm_get_rx_stats, .mac_get_tx_stats = rpm_get_tx_stats, + .get_fec_stats = rpm_get_fec_stats, .mac_enadis_rx_pause_fwding = rpm_lmac_enadis_rx_pause_fwding, .mac_get_pause_frm_status = rpm_lmac_get_pause_frm_status, .mac_enadis_pause_frm = rpm_lmac_enadis_pause_frm, @@ -37,9 +39,50 @@ static struct mac_ops rpm_mac_ops = { .mac_get_pfc_frm_cfg = rpm_lmac_get_pfc_frm_cfg, }; -struct mac_ops *rpm_get_mac_ops(void) +static struct mac_ops rpm2_mac_ops = { + .name = "rpm", + .csr_offset = RPM2_CSR_OFFSET, + .lmac_offset = 20, + .int_register = RPM2_CMRX_SW_INT, + .int_set_reg = RPM2_CMRX_SW_INT_ENA_W1S, + .irq_offset = 1, + .int_ena_bit = BIT_ULL(0), + .lmac_fwi = RPM_LMAC_FWI, + .non_contiguous_serdes_lane = true, + .rx_stats_cnt = 43, + .tx_stats_cnt = 34, + .dmac_filter_count = 64, + .get_nr_lmacs = rpm2_get_nr_lmacs, + .get_lmac_type = rpm_get_lmac_type, + .lmac_fifo_len = rpm2_get_lmac_fifo_len, + .mac_lmac_intl_lbk = rpm_lmac_internal_loopback, + .mac_get_rx_stats = rpm_get_rx_stats, + .mac_get_tx_stats = rpm_get_tx_stats, + .get_fec_stats = rpm_get_fec_stats, + .mac_enadis_rx_pause_fwding = rpm_lmac_enadis_rx_pause_fwding, + .mac_get_pause_frm_status = rpm_lmac_get_pause_frm_status, + .mac_enadis_pause_frm = rpm_lmac_enadis_pause_frm, + .mac_pause_frm_config = rpm_lmac_pause_frm_config, + .mac_enadis_ptp_config = rpm_lmac_ptp_config, + .mac_rx_tx_enable = rpm_lmac_rx_tx_enable, + .mac_tx_enable = rpm_lmac_tx_enable, + .pfc_config = rpm_lmac_pfc_config, + .mac_get_pfc_frm_cfg = rpm_lmac_get_pfc_frm_cfg, +}; + +bool is_dev_rpm2(void *rpmd) +{ + rpm_t *rpm = rpmd; + + return (rpm->pdev->device == PCI_DEVID_CN10KB_RPM); +} + +struct mac_ops *rpm_get_mac_ops(rpm_t *rpm) { - return &rpm_mac_ops; + if (is_dev_rpm2(rpm)) + return &rpm2_mac_ops; + else + return &rpm_mac_ops; } static void rpm_write(rpm_t *rpm, u64 lmac, u64 offset, u64 val) @@ -52,6 +95,16 @@ static u64 rpm_read(rpm_t *rpm, u64 lmac, u64 offset) return cgx_read(rpm, lmac, offset); } +/* Read HW major version to determine RPM + * MAC type 100/USX + */ +static bool is_mac_rpmusx(void *rpmd) +{ + rpm_t *rpm = rpmd; + + return rpm_read(rpm, 0, RPMX_CONST1) & 0x700ULL; +} + int rpm_get_nr_lmacs(void *rpmd) { rpm_t *rpm = rpmd; @@ -59,6 +112,13 @@ int rpm_get_nr_lmacs(void *rpmd) return hweight8(rpm_read(rpm, 0, CGXX_CMRX_RX_LMACS) & 0xFULL); } +int rpm2_get_nr_lmacs(void *rpmd) +{ + rpm_t *rpm = rpmd; + + return hweight8(rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS) & 0xFFULL); +} + int rpm_lmac_tx_enable(void *rpmd, int lmac_id, bool enable) { rpm_t *rpm = rpmd; @@ -222,6 +282,46 @@ static void rpm_cfg_pfc_quanta_thresh(rpm_t *rpm, int lmac_id, } } +static void rpm2_lmac_cfg_bp(rpm_t *rpm, int lmac_id, u8 tx_pause, u8 rx_pause) +{ + u64 cfg; + + cfg = rpm_read(rpm, lmac_id, RPM2_CMR_RX_OVR_BP); + if (tx_pause) { + /* Configure CL0 Pause Quanta & threshold + * for 802.3X frames + */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 1, true); + cfg &= ~RPM2_CMR_RX_OVR_BP_EN; + } else { + /* Disable all Pause Quanta & threshold values */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false); + cfg |= RPM2_CMR_RX_OVR_BP_EN; + cfg &= ~RPM2_CMR_RX_OVR_BP_BP; + } + rpm_write(rpm, lmac_id, RPM2_CMR_RX_OVR_BP, cfg); +} + +static void rpm_lmac_cfg_bp(rpm_t *rpm, int lmac_id, u8 tx_pause, u8 rx_pause) +{ + u64 cfg; + + cfg = rpm_read(rpm, 0, RPMX_CMR_RX_OVR_BP); + if (tx_pause) { + /* Configure CL0 Pause Quanta & threshold for + * 802.3X frames + */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 1, true); + cfg &= ~RPMX_CMR_RX_OVR_BP_EN(lmac_id); + } else { + /* Disable all Pause Quanta & threshold values */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false); + cfg |= RPMX_CMR_RX_OVR_BP_EN(lmac_id); + cfg &= ~RPMX_CMR_RX_OVR_BP_BP(lmac_id); + } + rpm_write(rpm, 0, RPMX_CMR_RX_OVR_BP, cfg); +} + int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause) { @@ -243,18 +343,11 @@ int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, cfg |= tx_pause ? 0x0 : RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - cfg = rpm_read(rpm, 0, RPMX_CMR_RX_OVR_BP); - if (tx_pause) { - /* Configure CL0 Pause Quanta & threshold for 802.3X frames */ - rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 1, true); - cfg &= ~RPMX_CMR_RX_OVR_BP_EN(lmac_id); - } else { - /* Disable all Pause Quanta & threshold values */ - rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false); - cfg |= RPMX_CMR_RX_OVR_BP_EN(lmac_id); - cfg &= ~RPMX_CMR_RX_OVR_BP_BP(lmac_id); - } - rpm_write(rpm, 0, RPMX_CMR_RX_OVR_BP, cfg); + if (is_dev_rpm2(rpm)) + rpm2_lmac_cfg_bp(rpm, lmac_id, tx_pause, rx_pause); + else + rpm_lmac_cfg_bp(rpm, lmac_id, tx_pause, rx_pause); + return 0; } @@ -278,13 +371,16 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ + if (is_dev_rpm2(rpm)) + rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff); + else + rpm_write(rpm, 0, RPMX_CMR_CHAN_MSK_OR, ~0ULL); + /* Disable all PFC classes */ cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL); cfg = FIELD_SET(RPM_PFC_CLASS_MASK, 0, cfg); rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg); - - /* Enable channel mask for all LMACS */ - rpm_write(rpm, 0, RPMX_CMR_CHAN_MSK_OR, ~0ULL); } int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat) @@ -292,7 +388,7 @@ int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat) rpm_t *rpm = rpmd; u64 val_lo, val_hi; - if (!rpm || lmac_id >= rpm->lmac_count) + if (!is_lmac_valid(rpm, lmac_id)) return -ENODEV; mutex_lock(&rpm->lock); @@ -320,7 +416,7 @@ int rpm_get_tx_stats(void *rpmd, int lmac_id, int idx, u64 *tx_stat) rpm_t *rpm = rpmd; u64 val_lo, val_hi; - if (!rpm || lmac_id >= rpm->lmac_count) + if (!is_lmac_valid(rpm, lmac_id)) return -ENODEV; mutex_lock(&rpm->lock); @@ -380,13 +476,71 @@ u32 rpm_get_lmac_fifo_len(void *rpmd, int lmac_id) return 0; } +static int rpmusx_lmac_internal_loopback(rpm_t *rpm, int lmac_id, bool enable) +{ + u64 cfg; + + cfg = rpm_read(rpm, lmac_id, RPM2_USX_PCSX_CONTROL1); + + if (enable) + cfg |= RPM2_USX_PCS_LBK; + else + cfg &= ~RPM2_USX_PCS_LBK; + rpm_write(rpm, lmac_id, RPM2_USX_PCSX_CONTROL1, cfg); + + return 0; +} + +u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id) +{ + u64 hi_perf_lmac, lmac_info; + rpm_t *rpm = rpmd; + u8 num_lmacs; + u32 fifo_len; + + lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS); + /* LMACs are divided into two groups and each group + * gets half of the FIFO + * Group0 lmac_id range {0..3} + * Group1 lmac_id range {4..7} + */ + fifo_len = rpm->mac_ops->fifo_len / 2; + + if (lmac_id < 4) { + num_lmacs = hweight8(lmac_info & 0xF); + hi_perf_lmac = (lmac_info >> 8) & 0x3ULL; + } else { + num_lmacs = hweight8(lmac_info & 0xF0); + hi_perf_lmac = (lmac_info >> 10) & 0x3ULL; + hi_perf_lmac += 4; + } + + switch (num_lmacs) { + case 1: + return fifo_len; + case 2: + return fifo_len / 2; + case 3: + /* LMAC marked as hi_perf gets half of the FIFO + * and rest 1/4th + */ + if (lmac_id == hi_perf_lmac) + return fifo_len / 2; + return fifo_len / 4; + case 4: + default: + return fifo_len / 4; + } + return 0; +} + int rpm_lmac_internal_loopback(void *rpmd, int lmac_id, bool enable) { rpm_t *rpm = rpmd; u8 lmac_type; u64 cfg; - if (!rpm || lmac_id >= rpm->lmac_count) + if (!is_lmac_valid(rpm, lmac_id)) return -ENODEV; lmac_type = rpm->mac_ops->get_lmac_type(rpm, lmac_id); @@ -395,6 +549,9 @@ int rpm_lmac_internal_loopback(void *rpmd, int lmac_id, bool enable) return 0; } + if (is_dev_rpm2(rpm) && is_mac_rpmusx(rpm)) + return rpmusx_lmac_internal_loopback(rpm, lmac_id, enable); + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_PCS100X_CONTROL1); if (enable) @@ -439,8 +596,8 @@ void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable) int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 pfc_en) { + u64 cfg, class_en, pfc_class_mask_cfg; rpm_t *rpm = rpmd; - u64 cfg, class_en; if (!is_lmac_valid(rpm, lmac_id)) return -ENODEV; @@ -476,7 +633,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, class_en); + pfc_class_mask_cfg = is_dev_rpm2(rpm) ? RPM2_CMRX_PRT_CBFC_CTL : + RPMX_CMRX_PRT_CBFC_CTL; + + rpm_write(rpm, lmac_id, pfc_class_mask_cfg, class_en); return 0; } @@ -497,3 +657,59 @@ int rpm_lmac_get_pfc_frm_cfg(void *rpmd, int lmac_id, u8 *tx_pause, u8 *rx_paus return 0; } + +int rpm_get_fec_stats(void *rpmd, int lmac_id, struct cgx_fec_stats_rsp *rsp) +{ + u64 val_lo, val_hi; + rpm_t *rpm = rpmd; + u64 cfg; + + if (!is_lmac_valid(rpm, lmac_id)) + return -ENODEV; + + if (rpm->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_NONE) + return 0; + + if (rpm->lmac_idmap[lmac_id]->link_info.fec == OTX2_FEC_BASER) { + val_lo = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_VL0_CCW_LO); + val_hi = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_CW_HI); + rsp->fec_corr_blks = (val_hi << 16 | val_lo); + + val_lo = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_VL0_NCCW_LO); + val_hi = rpm_read(rpm, lmac_id, RPMX_MTI_FCFECX_CW_HI); + rsp->fec_uncorr_blks = (val_hi << 16 | val_lo); + + /* 50G uses 2 Physical serdes lines */ + if (rpm->lmac_idmap[lmac_id]->link_info.lmac_type_id == + LMAC_MODE_50G_R) { + val_lo = rpm_read(rpm, lmac_id, + RPMX_MTI_FCFECX_VL1_CCW_LO); + val_hi = rpm_read(rpm, lmac_id, + RPMX_MTI_FCFECX_CW_HI); + rsp->fec_corr_blks += (val_hi << 16 | val_lo); + + val_lo = rpm_read(rpm, lmac_id, + RPMX_MTI_FCFECX_VL1_NCCW_LO); + val_hi = rpm_read(rpm, lmac_id, + RPMX_MTI_FCFECX_CW_HI); + rsp->fec_uncorr_blks += (val_hi << 16 | val_lo); + } + } else { + /* enable RS-FEC capture */ + cfg = rpm_read(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL); + cfg |= RPMX_RSFEC_RX_CAPTURE | BIT(lmac_id); + rpm_write(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL, cfg); + + val_lo = rpm_read(rpm, 0, + RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2); + val_hi = rpm_read(rpm, 0, RPMX_MTI_STAT_DATA_HI_CDC); + rsp->fec_corr_blks = (val_hi << 32 | val_lo); + + val_lo = rpm_read(rpm, 0, + RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3); + val_hi = rpm_read(rpm, 0, RPMX_MTI_STAT_DATA_HI_CDC); + rsp->fec_uncorr_blks = (val_hi << 32 | val_lo); + } + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h index 77f2ef9e1425..22147b4c2137 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h @@ -12,17 +12,19 @@ /* PCI device IDs */ #define PCI_DEVID_CN10K_RPM 0xA060 +#define PCI_SUBSYS_DEVID_CNF10KB_RPM 0xBC00 +#define PCI_DEVID_CN10KB_RPM 0xA09F /* Registers */ #define RPMX_CMRX_CFG 0x00 #define RPMX_RX_TS_PREPEND BIT_ULL(22) #define RPMX_TX_PTP_1S_SUPPORT BIT_ULL(17) +#define RPMX_CMRX_RX_ID_MAP 0x80 #define RPMX_CMRX_SW_INT 0x180 #define RPMX_CMRX_SW_INT_W1S 0x188 #define RPMX_CMRX_SW_INT_ENA_W1S 0x198 #define RPMX_CMRX_LINK_CFG 0x1070 #define RPMX_MTI_PCS100X_CONTROL1 0x20000 -#define RPMX_MTI_LPCSX_CONTROL1 0x30000 #define RPMX_MTI_PCS_LBK BIT_ULL(14) #define RPMX_MTI_LPCSX_CONTROL(id) (0x30000 | ((id) * 0x100)) @@ -76,11 +78,40 @@ #define RPMX_MTI_MAC100X_XIF_MODE 0x8100 #define RPMX_ONESTEP_ENABLE BIT_ULL(5) #define RPMX_TS_BINARY_MODE BIT_ULL(11) +#define RPMX_CONST1 0x2008 + +/* FEC stats */ +#define RPMX_MTI_STAT_STATN_CONTROL 0x10018 +#define RPMX_MTI_STAT_DATA_HI_CDC 0x10038 +#define RPMX_RSFEC_RX_CAPTURE BIT_ULL(27) +#define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2 0x40050 +#define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3 0x40058 +#define RPMX_MTI_FCFECX_VL0_CCW_LO 0x38618 +#define RPMX_MTI_FCFECX_VL0_NCCW_LO 0x38620 +#define RPMX_MTI_FCFECX_VL1_CCW_LO 0x38628 +#define RPMX_MTI_FCFECX_VL1_NCCW_LO 0x38630 +#define RPMX_MTI_FCFECX_CW_HI 0x38638 + +/* CN10KB CSR Declaration */ +#define RPM2_CMRX_SW_INT 0x1b0 +#define RPM2_CMRX_SW_INT_ENA_W1S 0x1b8 +#define RPM2_CMR_CHAN_MSK_OR 0x3120 +#define RPM2_CMR_RX_OVR_BP_EN BIT_ULL(2) +#define RPM2_CMR_RX_OVR_BP_BP BIT_ULL(1) +#define RPM2_CMR_RX_OVR_BP 0x3130 +#define RPM2_CSR_OFFSET 0x3e00 +#define RPM2_CMRX_PRT_CBFC_CTL 0x6510 +#define RPM2_CMRX_RX_LMACS 0x100 +#define RPM2_CMRX_RX_LOGL_XON 0x3100 +#define RPM2_CMRX_RX_STAT2 0x3010 +#define RPM2_USX_PCSX_CONTROL1 0x80000 +#define RPM2_USX_PCS_LBK BIT_ULL(14) /* Function Declarations */ int rpm_get_nr_lmacs(void *rpmd); u8 rpm_get_lmac_type(void *rpmd, int lmac_id); u32 rpm_get_lmac_fifo_len(void *rpmd, int lmac_id); +u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id); int rpm_lmac_internal_loopback(void *rpmd, int lmac_id, bool enable); void rpm_lmac_enadis_rx_pause_fwding(void *rpmd, int lmac_id, bool enable); int rpm_lmac_get_pause_frm_status(void *cgxd, int lmac_id, u8 *tx_pause, @@ -97,4 +128,7 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 pfc_en); int rpm_lmac_get_pfc_frm_cfg(void *rpmd, int lmac_id, u8 *tx_pause, u8 *rx_pause); +int rpm2_get_nr_lmacs(void *rpmd); +bool is_dev_rpm2(void *rpmd); +int rpm_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp); #endif /* RPM_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 76474385a602..7f0a64731c67 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -410,9 +410,15 @@ struct rvu_fwdata { u32 ptp_ext_tstamp; #define FWDATA_RESERVED_MEM 1022 u64 reserved[FWDATA_RESERVED_MEM]; -#define CGX_MAX 5 +#define CGX_MAX 9 #define CGX_LMACS_MAX 4 - struct cgx_lmac_fwdata_s cgx_fw_data[CGX_MAX][CGX_LMACS_MAX]; +#define CGX_LMACS_USX 8 + union { + struct cgx_lmac_fwdata_s + cgx_fw_data[CGX_MAX][CGX_LMACS_MAX]; + struct cgx_lmac_fwdata_s + cgx_fw_data_usx[CGX_MAX][CGX_LMACS_USX]; + }; /* Do not add new fields below this line */ }; @@ -478,7 +484,7 @@ struct rvu { u8 cgx_mapped_pfs; u8 cgx_cnt_max; /* CGX port count max */ u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */ - u16 *cgxlmac2pf_map; /* bitmap of mapped pfs for + u64 *cgxlmac2pf_map; /* bitmap of mapped pfs for * every cgx lmac port */ unsigned long pf_notify_bmap; /* Flags for PF notification */ @@ -851,6 +857,7 @@ int npc_install_mcam_drop_rule(struct rvu *rvu, int mcam_idx, u16 *counter_idx, u64 chan_val, u64 chan_mask, u64 exact_val, u64 exact_mask, u64 bcast_mcast_val, u64 bcast_mcast_mask); void npc_mcam_rsrcs_reserve(struct rvu *rvu, int blkaddr, int entry_idx); +bool npc_is_feature_supported(struct rvu *rvu, u64 features, u8 intf); /* CPT APIs */ int rvu_cpt_register_interrupts(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index addc69f4b65c..438b212fb54a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -55,8 +55,9 @@ bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature) return (cgx_features_get(cgxd) & feature); } +#define CGX_OFFSET(x) ((x) * rvu->hw->lmac_per_cgx) /* Returns bitmap of mapped PFs */ -static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) +static u64 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) { return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id]; } @@ -71,7 +72,8 @@ int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) if (!pfmap) return -ENODEV; else - return find_first_bit(&pfmap, 16); + return find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); } static u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id) @@ -129,14 +131,14 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!cgx_cnt_max) return 0; - if (cgx_cnt_max > 0xF || MAX_LMAC_PER_CGX > 0xF) + if (cgx_cnt_max > 0xF || rvu->hw->lmac_per_cgx > 0xF) return -EINVAL; /* Alloc map table * An additional entry is required since PF id starts from 1 and * hence entry at offset 0 is invalid. */ - size = (cgx_cnt_max * MAX_LMAC_PER_CGX + 1) * sizeof(u8); + size = (cgx_cnt_max * rvu->hw->lmac_per_cgx + 1) * sizeof(u8); rvu->pf2cgxlmac_map = devm_kmalloc(rvu->dev, size, GFP_KERNEL); if (!rvu->pf2cgxlmac_map) return -ENOMEM; @@ -145,9 +147,10 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) memset(rvu->pf2cgxlmac_map, 0xFF, size); /* Reverse map table */ - rvu->cgxlmac2pf_map = devm_kzalloc(rvu->dev, - cgx_cnt_max * MAX_LMAC_PER_CGX * sizeof(u16), - GFP_KERNEL); + rvu->cgxlmac2pf_map = + devm_kzalloc(rvu->dev, + cgx_cnt_max * rvu->hw->lmac_per_cgx * sizeof(u64), + GFP_KERNEL); if (!rvu->cgxlmac2pf_map) return -ENOMEM; @@ -156,7 +159,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!rvu_cgx_pdata(cgx, rvu)) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); @@ -235,7 +238,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); do { - pfid = find_first_bit(&pfmap, 16); + pfid = find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); clear_bit(pfid, &pfmap); /* check if notification is enabled */ @@ -310,7 +314,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) { err = cgx_lmac_evh_register(&cb, cgxd, lmac); if (err) dev_err(rvu->dev, @@ -396,7 +400,7 @@ int rvu_cgx_exit(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) cgx_lmac_evh_unregister(cgxd, lmac); } @@ -468,6 +472,7 @@ void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) { int pf = rvu_get_pf(pcifunc); int i = 0, lmac_count = 0; + struct mac_ops *mac_ops; u8 max_dmac_filters; u8 cgx_id, lmac_id; void *cgx_dev; @@ -483,7 +488,12 @@ void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); cgx_dev = cgx_get_pdata(cgx_id); lmac_count = cgx_get_lmac_cnt(cgx_dev); - max_dmac_filters = MAX_DMAC_ENTRIES_PER_CGX / lmac_count; + + mac_ops = get_mac_ops(cgx_dev); + if (!mac_ops) + return; + + max_dmac_filters = mac_ops->dmac_filter_count / lmac_count; for (i = 0; i < max_dmac_filters; i++) cgx_lmac_addr_del(cgx_id, lmac_id, i); @@ -569,6 +579,7 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu, struct cgx_fec_stats_rsp *rsp) { int pf = rvu_get_pf(req->hdr.pcifunc); + struct mac_ops *mac_ops; u8 cgx_idx, lmac; void *cgxd; @@ -577,7 +588,8 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu, rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac); cgxd = rvu_cgx_pdata(cgx_idx, rvu); - return cgx_get_fec_stats(cgxd, lmac, rsp); + mac_ops = get_mac_ops(cgxd); + return mac_ops->get_fec_stats(cgxd, lmac, rsp); } int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu, @@ -1110,8 +1122,15 @@ int rvu_mbox_handler_cgx_get_aux_link_info(struct rvu *rvu, struct msg_req *req, rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - memcpy(&rsp->fwdata, &rvu->fwdata->cgx_fw_data[cgx_id][lmac_id], - sizeof(struct cgx_lmac_fwdata_s)); + if (rvu->hw->lmac_per_cgx == CGX_LMACS_USX) + memcpy(&rsp->fwdata, + &rvu->fwdata->cgx_fw_data_usx[cgx_id][lmac_id], + sizeof(struct cgx_lmac_fwdata_s)); + else + memcpy(&rsp->fwdata, + &rvu->fwdata->cgx_fw_data[cgx_id][lmac_id], + sizeof(struct cgx_lmac_fwdata_s)); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index f66dde2b0f92..fa280ebd3052 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2613,7 +2613,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) rvu->rvu_dbg.cgx = debugfs_create_dir(dname, rvu->rvu_dbg.cgx_root); - for_each_set_bit(lmac_id, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac_id, &lmac_bmap, rvu->hw->lmac_per_cgx) { /* lmac debugfs dir */ sprintf(dname, "lmac%d", lmac_id); rvu->rvu_dbg.lmac = @@ -2759,6 +2759,12 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s, for_each_set_bit(bit, (unsigned long *)&rule->features, 64) { seq_printf(s, "\t%s ", npc_get_field_name(bit)); switch (bit) { + case NPC_LXMB: + if (rule->lxmb == 1) + seq_puts(s, "\tL2M nibble is set\n"); + else + seq_puts(s, "\tL2B nibble is set\n"); + break; case NPC_DMAC: seq_printf(s, "%pM ", rule->packet.dmac); seq_printf(s, "mask %pM\n", rule->mask.dmac); @@ -2796,6 +2802,14 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s, seq_printf(s, "%pI6 ", rule->packet.ip6dst); seq_printf(s, "mask %pI6\n", rule->mask.ip6dst); break; + case NPC_IPFRAG_IPV6: + seq_printf(s, "0x%x ", rule->packet.next_header); + seq_printf(s, "mask 0x%x\n", rule->mask.next_header); + break; + case NPC_IPFRAG_IPV4: + seq_printf(s, "0x%x ", rule->packet.ip_flag); + seq_printf(s, "mask 0x%x\n", rule->mask.ip_flag); + break; case NPC_SPORT_TCP: case NPC_SPORT_UDP: case NPC_SPORT_SCTP: diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 88dee589cb21..bda1a6fa2ec4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1547,14 +1547,7 @@ static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, return 0; } -static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, - struct netlink_ext_ack *extack) -{ - return devlink_info_driver_name_put(req, DRV_NAME); -} - static const struct devlink_ops rvu_devlink_ops = { - .info_get = rvu_devlink_info_get, .eswitch_mode_get = rvu_devlink_eswitch_mode_get, .eswitch_mode_set = rvu_devlink_eswitch_mode_set, }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index a62c1b322012..6b8747ebc08c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3197,8 +3197,12 @@ static void rvu_get_lbk_link_max_frs(struct rvu *rvu, u16 *max_mtu) static void rvu_get_lmac_link_max_frs(struct rvu *rvu, u16 *max_mtu) { - /* RPM supports FIFO len 128 KB */ - if (rvu_cgx_get_fifolen(rvu) == 0x20000) + int fifo_size = rvu_cgx_get_fifolen(rvu); + + /* RPM supports FIFO len 128 KB and RPM2 supports double the + * FIFO len to accommodate 8 LMACS + */ + if (fifo_size == 0x20000 || fifo_size == 0x40000) *max_mtu = CN10K_LMAC_LINK_MAX_FRS; else *max_mtu = NIC_HW_MAX_FRS; @@ -4109,7 +4113,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, /* Get LMAC id's from bitmap */ lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, iter); if (!lmac_fifo_len) { dev_err(rvu->dev, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 1e348fd0d930..16cfc802e348 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -617,6 +617,12 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, if (blkaddr < 0) return; + /* Ucast rule should not be installed if DMAC + * extraction is not supported by the profile. + */ + if (!npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC), pfvf->nix_rx_intf)) + return; + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_UCAST_ENTRY); @@ -778,6 +784,14 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, /* Get 'pcifunc' of PF device */ pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; pfvf = rvu_get_pfvf(rvu, pcifunc); + + /* Bcast rule should not be installed if both DMAC + * and LXMB extraction is not supported by the profile. + */ + if (!npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC), pfvf->nix_rx_intf) && + !npc_is_feature_supported(rvu, BIT_ULL(NPC_LXMB), pfvf->nix_rx_intf)) + return; + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_BCAST_ENTRY); @@ -848,6 +862,14 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, vf_func = pcifunc & RVU_PFVF_FUNC_MASK; pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; pfvf = rvu_get_pfvf(rvu, pcifunc); + + /* Mcast rule should not be installed if both DMAC + * and LXMB extraction is not supported by the profile. + */ + if (!npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC), pfvf->nix_rx_intf) && + !npc_is_feature_supported(rvu, BIT_ULL(NPC_LXMB), pfvf->nix_rx_intf)) + return; + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_ALLMULTI_ENTRY); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 7c4e1acd0f77..006beb5cf98d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -26,8 +26,10 @@ static const char * const npc_flow_names[] = { [NPC_VLAN_ETYPE_STAG] = "vlan ether type stag", [NPC_OUTER_VID] = "outer vlan id", [NPC_TOS] = "tos", + [NPC_IPFRAG_IPV4] = "fragmented IPv4 header ", [NPC_SIP_IPV4] = "ipv4 source ip", [NPC_DIP_IPV4] = "ipv4 destination ip", + [NPC_IPFRAG_IPV6] = "fragmented IPv6 header ", [NPC_SIP_IPV6] = "ipv6 source ip", [NPC_DIP_IPV6] = "ipv6 destination ip", [NPC_IPPROTO_TCP] = "ip proto tcp", @@ -43,9 +45,23 @@ static const char * const npc_flow_names[] = { [NPC_DPORT_UDP] = "udp destination port", [NPC_SPORT_SCTP] = "sctp source port", [NPC_DPORT_SCTP] = "sctp destination port", + [NPC_LXMB] = "Mcast/Bcast header ", [NPC_UNKNOWN] = "unknown", }; +bool npc_is_feature_supported(struct rvu *rvu, u64 features, u8 intf) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + u64 mcam_features; + u64 unsupported; + + mcam_features = is_npc_intf_tx(intf) ? mcam->tx_features : mcam->rx_features; + unsupported = (mcam_features ^ features) & ~mcam_features; + + /* Return false if at least one of the input flows is not extracted */ + return !unsupported; +} + const char *npc_get_field_name(u8 hdr) { if (hdr >= ARRAY_SIZE(npc_flow_names)) @@ -340,8 +356,10 @@ static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf) vlan_tag2 = &key_fields[NPC_VLAN_TAG2]; /* if key profile programmed does not extract Ethertype at all */ - if (!etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws) + if (!etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws) { + dev_err(rvu->dev, "mkex: Ethertype is not extracted.\n"); goto vlan_tci; + } /* if key profile programmed extracts Ethertype from one layer */ if (etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws) @@ -354,35 +372,45 @@ static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf) /* if key profile programmed extracts Ethertype from multiple layers */ if (etype_ether->nr_kws && etype_tag1->nr_kws) { for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) { - if (etype_ether->kw_mask[i] != etype_tag1->kw_mask[i]) + if (etype_ether->kw_mask[i] != etype_tag1->kw_mask[i]) { + dev_err(rvu->dev, "mkex: Etype pos is different for untagged and tagged pkts.\n"); goto vlan_tci; + } } key_fields[NPC_ETYPE] = *etype_tag1; } if (etype_ether->nr_kws && etype_tag2->nr_kws) { for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) { - if (etype_ether->kw_mask[i] != etype_tag2->kw_mask[i]) + if (etype_ether->kw_mask[i] != etype_tag2->kw_mask[i]) { + dev_err(rvu->dev, "mkex: Etype pos is different for untagged and double tagged pkts.\n"); goto vlan_tci; + } } key_fields[NPC_ETYPE] = *etype_tag2; } if (etype_tag1->nr_kws && etype_tag2->nr_kws) { for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) { - if (etype_tag1->kw_mask[i] != etype_tag2->kw_mask[i]) + if (etype_tag1->kw_mask[i] != etype_tag2->kw_mask[i]) { + dev_err(rvu->dev, "mkex: Etype pos is different for tagged and double tagged pkts.\n"); goto vlan_tci; + } } key_fields[NPC_ETYPE] = *etype_tag2; } /* check none of higher layers overwrite Ethertype */ start_lid = key_fields[NPC_ETYPE].layer_mdata.lid + 1; - if (npc_check_overlap(rvu, blkaddr, NPC_ETYPE, start_lid, intf)) + if (npc_check_overlap(rvu, blkaddr, NPC_ETYPE, start_lid, intf)) { + dev_err(rvu->dev, "mkex: Ethertype is overwritten by higher layers.\n"); goto vlan_tci; + } *features |= BIT_ULL(NPC_ETYPE); vlan_tci: /* if key profile does not extract outer vlan tci at all */ - if (!vlan_tag1->nr_kws && !vlan_tag2->nr_kws) + if (!vlan_tag1->nr_kws && !vlan_tag2->nr_kws) { + dev_err(rvu->dev, "mkex: Outer vlan tci is not extracted.\n"); goto done; + } /* if key profile extracts outer vlan tci from one layer */ if (vlan_tag1->nr_kws && !vlan_tag2->nr_kws) @@ -393,15 +421,19 @@ vlan_tci: /* if key profile extracts outer vlan tci from multiple layers */ if (vlan_tag1->nr_kws && vlan_tag2->nr_kws) { for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) { - if (vlan_tag1->kw_mask[i] != vlan_tag2->kw_mask[i]) + if (vlan_tag1->kw_mask[i] != vlan_tag2->kw_mask[i]) { + dev_err(rvu->dev, "mkex: Out vlan tci pos is different for tagged and double tagged pkts.\n"); goto done; + } } key_fields[NPC_OUTER_VID] = *vlan_tag2; } /* check none of higher layers overwrite outer vlan tci */ start_lid = key_fields[NPC_OUTER_VID].layer_mdata.lid + 1; - if (npc_check_overlap(rvu, blkaddr, NPC_OUTER_VID, start_lid, intf)) + if (npc_check_overlap(rvu, blkaddr, NPC_OUTER_VID, start_lid, intf)) { + dev_err(rvu->dev, "mkex: Outer vlan tci is overwritten by higher layers.\n"); goto done; + } *features |= BIT_ULL(NPC_OUTER_VID); done: return; @@ -419,8 +451,6 @@ static void npc_scan_ldata(struct rvu *rvu, int blkaddr, u8 lid, nr_bytes = FIELD_GET(NPC_BYTESM, cfg) + 1; hdr = FIELD_GET(NPC_HDR_OFFSET, cfg); key = FIELD_GET(NPC_KEY_OFFSET, cfg); - start_kwi = key / 8; - offset = (key * 8) % 64; /* For Tx, Layer A has NIX_INST_HDR_S(64 bytes) preceding * ethernet header. @@ -435,13 +465,18 @@ static void npc_scan_ldata(struct rvu *rvu, int blkaddr, u8 lid, #define NPC_SCAN_HDR(name, hlid, hlt, hstart, hlen) \ do { \ + start_kwi = key / 8; \ + offset = (key * 8) % 64; \ if (lid == (hlid) && lt == (hlt)) { \ if ((hstart) >= hdr && \ ((hstart) + (hlen)) <= (hdr + nr_bytes)) { \ bit_offset = (hdr + nr_bytes - (hstart) - (hlen)) * 8; \ npc_set_layer_mdata(mcam, (name), cfg, lid, lt, intf); \ + offset += bit_offset; \ + start_kwi += offset / 64; \ + offset %= 64; \ npc_set_kw_masks(mcam, (name), (hlen) * 8, \ - start_kwi, offset + bit_offset, intf);\ + start_kwi, offset, intf); \ } \ } \ } while (0) @@ -451,8 +486,10 @@ do { \ * Example: Source IP is 4 bytes and starts at 12th byte of IP header */ NPC_SCAN_HDR(NPC_TOS, NPC_LID_LC, NPC_LT_LC_IP, 1, 1); + NPC_SCAN_HDR(NPC_IPFRAG_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 6, 1); NPC_SCAN_HDR(NPC_SIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 12, 4); NPC_SCAN_HDR(NPC_DIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 16, 4); + NPC_SCAN_HDR(NPC_IPFRAG_IPV6, NPC_LID_LC, NPC_LT_LC_IP6_EXT, 6, 1); NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 16); NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 16); NPC_SCAN_HDR(NPC_SPORT_UDP, NPC_LID_LD, NPC_LT_LD_UDP, 0, 2); @@ -522,6 +559,10 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) if (npc_check_field(rvu, blkaddr, NPC_LB, intf)) *features |= BIT_ULL(NPC_VLAN_ETYPE_CTAG) | BIT_ULL(NPC_VLAN_ETYPE_STAG); + + /* for L2M/L2B/L3M/L3B, check if the type is present in the key */ + if (npc_check_field(rvu, blkaddr, NPC_LXMB, intf)) + *features |= BIT_ULL(NPC_LXMB); } /* Scan key extraction profile and record how fields of our interest @@ -599,16 +640,6 @@ static int npc_scan_verify_kex(struct rvu *rvu, int blkaddr) dev_err(rvu->dev, "Channel cannot be overwritten\n"); return -EINVAL; } - /* DMAC should be present in key for unicast filter to work */ - if (!npc_is_field_present(rvu, NPC_DMAC, NIX_INTF_RX)) { - dev_err(rvu->dev, "DMAC not present in Key\n"); - return -EINVAL; - } - /* check that none of the fields overwrite DMAC */ - if (npc_check_overlap(rvu, blkaddr, NPC_DMAC, 0, NIX_INTF_RX)) { - dev_err(rvu->dev, "DMAC cannot be overwritten\n"); - return -EINVAL; - } npc_set_features(rvu, blkaddr, NIX_INTF_TX); npc_set_features(rvu, blkaddr, NIX_INTF_RX); @@ -639,9 +670,9 @@ static int npc_check_unsupported_flows(struct rvu *rvu, u64 features, u8 intf) unsupported = (*mcam_features ^ features) & ~(*mcam_features); if (unsupported) { - dev_info(rvu->dev, "Unsupported flow(s):\n"); + dev_warn(rvu->dev, "Unsupported flow(s):\n"); for_each_set_bit(bit, (unsigned long *)&unsupported, 64) - dev_info(rvu->dev, "%s ", npc_get_field_name(bit)); + dev_warn(rvu->dev, "%s ", npc_get_field_name(bit)); return -EOPNOTSUPP; } @@ -851,6 +882,11 @@ static void npc_update_flow(struct rvu *rvu, struct mcam_entry *entry, npc_update_entry(rvu, NPC_LE, entry, NPC_LT_LE_ESP, 0, ~0ULL, 0, intf); + if (features & BIT_ULL(NPC_LXMB)) { + output->lxmb = is_broadcast_ether_addr(pkt->dmac) ? 2 : 1; + npc_update_entry(rvu, NPC_LXMB, entry, output->lxmb, 0, + output->lxmb, 0, intf); + } #define NPC_WRITE_FLOW(field, member, val_lo, val_hi, mask_lo, mask_hi) \ do { \ if (features & BIT_ULL((field))) { \ @@ -867,6 +903,8 @@ do { \ NPC_WRITE_FLOW(NPC_ETYPE, etype, ntohs(pkt->etype), 0, ntohs(mask->etype), 0); NPC_WRITE_FLOW(NPC_TOS, tos, pkt->tos, 0, mask->tos, 0); + NPC_WRITE_FLOW(NPC_IPFRAG_IPV4, ip_flag, pkt->ip_flag, 0, + mask->ip_flag, 0); NPC_WRITE_FLOW(NPC_SIP_IPV4, ip4src, ntohl(pkt->ip4src), 0, ntohl(mask->ip4src), 0); NPC_WRITE_FLOW(NPC_DIP_IPV4, ip4dst, ntohl(pkt->ip4dst), 0, @@ -887,6 +925,8 @@ do { \ NPC_WRITE_FLOW(NPC_OUTER_VID, vlan_tci, ntohs(pkt->vlan_tci), 0, ntohs(mask->vlan_tci), 0); + NPC_WRITE_FLOW(NPC_IPFRAG_IPV6, next_header, pkt->next_header, 0, + mask->next_header, 0); npc_update_ipv6_flow(rvu, entry, features, pkt, mask, output, intf); npc_update_vlan_features(rvu, entry, features, intf); @@ -991,8 +1031,20 @@ static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf, action.match_id = req->match_id; action.flow_key_alg = req->flow_key_alg; - if (req->op == NIX_RX_ACTION_DEFAULT && pfvf->def_ucast_rule) - action = pfvf->def_ucast_rule->rx_action; + if (req->op == NIX_RX_ACTION_DEFAULT) { + if (pfvf->def_ucast_rule) { + action = pfvf->def_ucast_rule->rx_action; + } else { + /* For profiles which do not extract DMAC, the default + * unicast entry is unused. Hence modify action for the + * requests which use same action as default unicast + * entry + */ + *(u64 *)&action = 0; + action.pf_func = target; + action.op = NIX_RX_ACTIONOP_UCAST; + } + } entry->action = *(u64 *)&action; @@ -1153,6 +1205,7 @@ find_rule: rule->chan_mask = write_req.entry_data.kw_mask[0] & NPC_KEX_CHAN_MASK; rule->chan = write_req.entry_data.kw[0] & NPC_KEX_CHAN_MASK; rule->chan &= rule->chan_mask; + rule->lxmb = dummy.lxmb; if (is_npc_intf_tx(req->intf)) rule->intf = pfvf->nix_tx_intf; else @@ -1215,6 +1268,35 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, if (!is_npc_interface_valid(rvu, req->intf)) return NPC_FLOW_INTF_INVALID; + /* If DMAC is not extracted in MKEX, rules installed by AF + * can rely on L2MB bit set by hardware protocol checker for + * broadcast and multicast addresses. + */ + if (npc_check_field(rvu, blkaddr, NPC_DMAC, req->intf)) + goto process_flow; + + if (is_pffunc_af(req->hdr.pcifunc) && + req->features & BIT_ULL(NPC_DMAC)) { + if (is_unicast_ether_addr(req->packet.dmac)) { + dev_warn(rvu->dev, + "%s: mkex profile does not support ucast flow\n", + __func__); + return NPC_FLOW_NOT_SUPPORTED; + } + + if (!npc_is_field_present(rvu, NPC_LXMB, req->intf)) { + dev_warn(rvu->dev, + "%s: mkex profile does not support bcast/mcast flow", + __func__); + return NPC_FLOW_NOT_SUPPORTED; + } + + /* Modify feature to use LXMB instead of DMAC */ + req->features &= ~BIT_ULL(NPC_DMAC); + req->features |= BIT_ULL(NPC_LXMB); + } + +process_flow: if (from_vf && req->default_rule) return NPC_FLOW_VF_PERM_DENIED; @@ -1558,3 +1640,22 @@ int npc_install_mcam_drop_rule(struct rvu *rvu, int mcam_idx, u16 *counter_idx, return 0; } + +int rvu_mbox_handler_npc_get_field_status(struct rvu *rvu, + struct npc_get_field_status_req *req, + struct npc_get_field_status_rsp *rsp) +{ + int blkaddr; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return NPC_MCAM_INVALID_REQ; + + if (!is_npc_interface_valid(rvu, req->intf)) + return NPC_FLOW_INTF_INVALID; + + if (npc_check_field(rvu, blkaddr, req->field, req->intf)) + rsp->enable = 1; + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 594029007f85..f69102d20c90 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -490,7 +490,7 @@ static bool rvu_npc_exact_alloc_id(struct rvu *rvu, u32 *seq_id) if (idx == table->tot_ids) { mutex_unlock(&table->lock); dev_err(rvu->dev, "%s: No space in id bitmap (%d)\n", - __func__, bitmap_weight(table->id_bmap, table->tot_ids)); + __func__, table->tot_ids); return false; } @@ -1870,12 +1870,11 @@ int rvu_npc_exact_init(struct rvu *rvu) /* Set capability to true */ rvu->hw->cap.npc_exact_match_enabled = true; - table = kmalloc(sizeof(*table), GFP_KERNEL); + table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) return -ENOMEM; dev_dbg(rvu->dev, "%s: Memory allocation for table success\n", __func__); - memset(table, 0, sizeof(*table)); rvu->hw->table = table; /* Read table size, ways and depth */ @@ -1899,24 +1898,24 @@ int rvu_npc_exact_init(struct rvu *rvu) table_size = table->mem_table.depth * table->mem_table.ways; /* Allocate bitmap for 4way 2K table */ - table->mem_table.bmap = devm_kcalloc(rvu->dev, BITS_TO_LONGS(table_size), - sizeof(long), GFP_KERNEL); + table->mem_table.bmap = devm_bitmap_zalloc(rvu->dev, table_size, + GFP_KERNEL); if (!table->mem_table.bmap) return -ENOMEM; dev_dbg(rvu->dev, "%s: Allocated bitmap for 4way 2K entry table\n", __func__); /* Allocate bitmap for 32 entry mcam */ - table->cam_table.bmap = devm_kcalloc(rvu->dev, 1, sizeof(long), GFP_KERNEL); + table->cam_table.bmap = devm_bitmap_zalloc(rvu->dev, 32, GFP_KERNEL); if (!table->cam_table.bmap) return -ENOMEM; dev_dbg(rvu->dev, "%s: Allocated bitmap for 32 entry cam\n", __func__); - table->tot_ids = (table->mem_table.depth * table->mem_table.ways) + table->cam_table.depth; - table->id_bmap = devm_kcalloc(rvu->dev, BITS_TO_LONGS(table->tot_ids), - table->tot_ids, GFP_KERNEL); + table->tot_ids = table_size + table->cam_table.depth; + table->id_bmap = devm_bitmap_zalloc(rvu->dev, table->tot_ids, + GFP_KERNEL); if (!table->id_bmap) return -ENOMEM; @@ -1957,7 +1956,9 @@ int rvu_npc_exact_init(struct rvu *rvu) /* Install SDP drop rule */ drop_mcam_idx = &table->num_drop_rules; - max_lmac_cnt = rvu->cgx_cnt_max * MAX_LMAC_PER_CGX + PF_CGXMAP_BASE; + max_lmac_cnt = rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx + + PF_CGXMAP_BASE; + for (i = PF_CGXMAP_BASE; i < max_lmac_cnt; i++) { if (rvu->pf2cgxlmac_map[i] == 0xFF) continue; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 67aa02bb2b85..5bee3c3a7ce4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -28,6 +28,9 @@ #include "otx2_devlink.h" #include <rvu_trace.h> +/* IPv4 flag more fragment bit */ +#define IPV4_FLAG_MORE 0x20 + /* PCI device IDs */ #define PCI_DEVID_OCTEONTX2_RVU_PF 0xA063 #define PCI_DEVID_OCTEONTX2_RVU_VF 0xA064 diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 777a27047c8e..63ef7c41d18d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -77,22 +77,7 @@ static const struct devlink_param otx2_dl_params[] = { otx2_dl_mcam_count_validate), }; -/* Devlink OPs */ -static int otx2_devlink_info_get(struct devlink *devlink, - struct devlink_info_req *req, - struct netlink_ext_ack *extack) -{ - struct otx2_devlink *otx2_dl = devlink_priv(devlink); - struct otx2_nic *pfvf = otx2_dl->pfvf; - - if (is_otx2_vf(pfvf->pcifunc)) - return devlink_info_driver_name_put(req, "rvu_nicvf"); - - return devlink_info_driver_name_put(req, "rvu_nicpf"); -} - static const struct devlink_ops otx2_devlink_ops = { - .info_get = otx2_devlink_info_get, }; int otx2_register_dl(struct otx2_nic *pfvf) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 0eb74e8c553d..0f8d1a69139f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -1268,6 +1268,39 @@ end: return err; } +static void otx2_get_fec_stats(struct net_device *netdev, + struct ethtool_fec_stats *fec_stats) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + struct cgx_fw_data *rsp; + + otx2_update_lmac_fec_stats(pfvf); + + /* Report MAC FEC stats */ + fec_stats->corrected_blocks.total = pfvf->hw.cgx_fec_corr_blks; + fec_stats->uncorrectable_blocks.total = pfvf->hw.cgx_fec_uncorr_blks; + + rsp = otx2_get_fwdata(pfvf); + if (!IS_ERR(rsp) && rsp->fwdata.phy.misc.has_fec_stats && + !otx2_get_phy_fec_stats(pfvf)) { + /* Fetch fwdata again because it's been recently populated with + * latest PHY FEC stats. + */ + rsp = otx2_get_fwdata(pfvf); + if (!IS_ERR(rsp)) { + struct fec_stats_s *p = &rsp->fwdata.phy.fec_stats; + + if (pfvf->linfo.fec == OTX2_FEC_BASER) { + fec_stats->corrected_blocks.total = p->brfec_corr_blks; + fec_stats->uncorrectable_blocks.total = p->brfec_uncorr_blks; + } else { + fec_stats->corrected_blocks.total = p->rsfec_corr_cws; + fec_stats->uncorrectable_blocks.total = p->rsfec_uncorr_cws; + } + } + } +} + static const struct ethtool_ops otx2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -1298,6 +1331,7 @@ static const struct ethtool_ops otx2_ethtool_ops = { .get_pauseparam = otx2_get_pauseparam, .set_pauseparam = otx2_set_pauseparam, .get_ts_info = otx2_get_ts_info, + .get_fec_stats = otx2_get_fec_stats, .get_fecparam = otx2_get_fecparam, .set_fecparam = otx2_set_fecparam, .get_link_ksettings = otx2_get_link_ksettings, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 709fc0114fbd..684cb8ec9f21 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -164,6 +164,8 @@ EXPORT_SYMBOL(otx2_alloc_mcam_entries); static int otx2_mcam_entry_init(struct otx2_nic *pfvf) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; + struct npc_get_field_status_req *freq; + struct npc_get_field_status_rsp *frsp; struct npc_mcam_alloc_entry_req *req; struct npc_mcam_alloc_entry_rsp *rsp; int vf_vlan_max_flows; @@ -214,8 +216,29 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset + OTX2_MAX_UNICAST_FLOWS; pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT; - pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT; - pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT; + + /* Check if NPC_DMAC field is supported + * by the mkex profile before setting VLAN support flag. + */ + freq = otx2_mbox_alloc_msg_npc_get_field_status(&pfvf->mbox); + if (!freq) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + freq->field = NPC_DMAC; + if (otx2_sync_mbox_msg(&pfvf->mbox)) { + mutex_unlock(&pfvf->mbox.lock); + return -EINVAL; + } + + frsp = (struct npc_get_field_status_rsp *)otx2_mbox_get_rsp + (&pfvf->mbox.mbox, 0, &freq->hdr); + + if (frsp->enable) { + pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT; + pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT; + } pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC; mutex_unlock(&pfvf->mbox.lock); @@ -688,6 +711,11 @@ static int otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp, sizeof(pmask->ip6dst)); req->features |= BIT_ULL(NPC_DIP_IPV6); } + if (ipv6_usr_hdr->l4_proto == IPPROTO_FRAGMENT) { + pkt->next_header = ipv6_usr_hdr->l4_proto; + pmask->next_header = ipv6_usr_mask->l4_proto; + req->features |= BIT_ULL(NPC_IPFRAG_IPV6); + } pkt->etype = cpu_to_be16(ETH_P_IPV6); pmask->etype = cpu_to_be16(0xFFFF); req->features |= BIT_ULL(NPC_ETYPE); @@ -868,10 +896,22 @@ static int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp, req->features |= BIT_ULL(NPC_OUTER_VID); } - /* Not Drop/Direct to queue but use action in default entry */ - if (fsp->m_ext.data[1] && - fsp->h_ext.data[1] == cpu_to_be32(OTX2_DEFAULT_ACTION)) - req->op = NIX_RX_ACTION_DEFAULT; + if (fsp->m_ext.data[1]) { + if (flow_type == IP_USER_FLOW) { + if (be32_to_cpu(fsp->h_ext.data[1]) != IPV4_FLAG_MORE) + return -EINVAL; + + pkt->ip_flag = be32_to_cpu(fsp->h_ext.data[1]); + pmask->ip_flag = be32_to_cpu(fsp->m_ext.data[1]); + req->features |= BIT_ULL(NPC_IPFRAG_IPV4); + } else if (fsp->h_ext.data[1] == + cpu_to_be32(OTX2_DEFAULT_ACTION)) { + /* Not Drop/Direct to queue but use action + * in default entry + */ + req->op = NIX_RX_ACTION_DEFAULT; + } + } } if (fsp->flow_type & FLOW_MAC_EXT && diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 303930499a4c..c1ea60bc2630 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1973,7 +1973,7 @@ static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, #endif #ifdef CONFIG_DCB - if (!skb->vlan_present) + if (!skb_vlan_tag_present(skb)) goto pick_tx; vlan_prio = skb->vlan_tci >> 13; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 6a01ab1a6e6f..044cc211424e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -532,6 +532,31 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, req->features |= BIT_ULL(NPC_IPPROTO_ICMP6); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + NL_SET_ERR_MSG_MOD(extack, "HW doesn't support frag first/later"); + return -EOPNOTSUPP; + } + + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + if (ntohs(flow_spec->etype) == ETH_P_IP) { + flow_spec->ip_flag = IPV4_FLAG_MORE; + flow_mask->ip_flag = 0xff; + req->features |= BIT_ULL(NPC_IPFRAG_IPV4); + } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { + flow_spec->next_header = IPPROTO_FRAGMENT; + flow_mask->next_header = 0xff; + req->features |= BIT_ULL(NPC_IPFRAG_IPV6); + } else { + NL_SET_ERR_MSG_MOD(extack, "flow-type should be either IPv4 and IPv6"); + return -EOPNOTSUPP; + } + } + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 06279cd6da67..2a4c9df4eb79 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -355,11 +355,6 @@ static int prestera_dl_info_get(struct devlink *dl, { struct prestera_switch *sw = devlink_priv(dl); char buf[16]; - int err; - - err = devlink_info_driver_name_put(req, PRESTERA_DRV_NAME); - if (err) - return err; snprintf(buf, sizeof(buf), "%d.%d.%d", sw->dev->fw_rev.maj, @@ -445,23 +440,6 @@ void prestera_devlink_port_unregister(struct prestera_port *port) devlink_port_unregister(&port->dl_port); } -void prestera_devlink_port_set(struct prestera_port *port) -{ - devlink_port_type_eth_set(&port->dl_port, port->dev); -} - -void prestera_devlink_port_clear(struct prestera_port *port) -{ - devlink_port_type_clear(&port->dl_port); -} - -struct devlink_port *prestera_devlink_get_port(struct net_device *dev) -{ - struct prestera_port *port = netdev_priv(dev); - - return &port->dl_port; -} - int prestera_devlink_traps_register(struct prestera_switch *sw) { const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h index b322295bad3a..bf84ad6fd87e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h @@ -15,11 +15,6 @@ void prestera_devlink_unregister(struct prestera_switch *sw); int prestera_devlink_port_register(struct prestera_port *port); void prestera_devlink_port_unregister(struct prestera_port *port); -void prestera_devlink_port_set(struct prestera_port *port); -void prestera_devlink_port_clear(struct prestera_port *port); - -struct devlink_port *prestera_devlink_get_port(struct net_device *dev); - void prestera_devlink_trap_report(struct prestera_port *port, struct sk_buff *skb, u8 cpu_code); int prestera_devlink_traps_register(struct prestera_switch *sw); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 47796e4d900c..9d504142e51a 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -360,7 +360,6 @@ static void prestera_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_mac_ops prestera_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = prestera_mac_select_pcs, .mac_config = prestera_mac_config, .mac_link_down = prestera_mac_link_down, @@ -569,7 +568,6 @@ static const struct net_device_ops prestera_netdev_ops = { .ndo_change_mtu = prestera_port_change_mtu, .ndo_get_stats64 = prestera_port_get_stats64, .ndo_set_mac_address = prestera_port_set_mac_address, - .ndo_get_devlink_port = prestera_devlink_get_port, }; int prestera_port_autoneg_set(struct prestera_port *port, u64 link_modes) @@ -644,6 +642,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) dev->netdev_ops = &prestera_netdev_ops; dev->ethtool_ops = &prestera_ethtool_ops; SET_NETDEV_DEV(dev, sw->dev->dev); + SET_NETDEV_DEVLINK_PORT(dev, &port->dl_port); if (port->caps.transceiver != PRESTERA_PORT_TCVR_SFP) netif_carrier_off(dev); @@ -737,8 +736,6 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) if (err) goto err_register_netdev; - prestera_devlink_port_set(port); - err = prestera_port_sfp_bind(port); if (err) goto err_sfp_bind; @@ -762,7 +759,6 @@ static void prestera_port_destroy(struct prestera_port *port) struct net_device *dev = port->dev; cancel_delayed_work_sync(&port->cached_hw_stats.caching_dw); - prestera_devlink_port_clear(port); unregister_netdev(dev); prestera_port_list_del(port); prestera_devlink_port_unregister(port); @@ -863,17 +859,10 @@ static void prestera_event_handlers_unregister(struct prestera_switch *sw) static int prestera_switch_set_base_mac_addr(struct prestera_switch *sw) { - struct device_node *base_mac_np; - int ret = 0; - - if (sw->np) { - base_mac_np = of_parse_phandle(sw->np, "base-mac-provider", 0); - if (base_mac_np) { - ret = of_get_mac_address(base_mac_np, sw->base_mac); - of_node_put(base_mac_np); - } - } + int ret; + if (sw->np) + ret = of_get_mac_address(sw->np, sw->base_mac); if (!is_valid_ether_addr(sw->base_mac) || ret) { eth_random_addr(sw->base_mac); dev_info(prestera_dev(sw), "using random base mac address\n"); @@ -1377,7 +1366,7 @@ static int prestera_switch_init(struct prestera_switch *sw) { int err; - sw->np = of_find_compatible_node(NULL, NULL, "marvell,prestera"); + sw->np = sw->dev->dev->of_node; err = prestera_hw_switch_init(sw); if (err) { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 59470d99f522..f328d957b2db 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -15,12 +15,13 @@ #define PRESTERA_MSG_MAX_SIZE 1500 #define PRESTERA_SUPP_FW_MAJ_VER 4 -#define PRESTERA_SUPP_FW_MIN_VER 0 +#define PRESTERA_SUPP_FW_MIN_VER 1 #define PRESTERA_PREV_FW_MAJ_VER 4 #define PRESTERA_PREV_FW_MIN_VER 0 #define PRESTERA_FW_PATH_FMT "mrvl/prestera/mvsw_prestera_fw-v%u.%u.img" +#define PRESTERA_FW_ARM64_PATH_FMT "mrvl/prestera/mvsw_prestera_fw_arm64-v%u.%u.img" #define PRESTERA_FW_HDR_MAGIC 0x351D9D06 #define PRESTERA_FW_DL_TIMEOUT_MS 50000 @@ -184,6 +185,15 @@ struct prestera_fw_regs { #define PRESTERA_FW_CMD_DEFAULT_WAIT_MS 30000 #define PRESTERA_FW_READY_WAIT_MS 20000 +#define PRESTERA_DEV_ID_AC3X_98DX_55 0xC804 +#define PRESTERA_DEV_ID_AC3X_98DX_65 0xC80C +#define PRESTERA_DEV_ID_ALDRIN2 0xCC1E +#define PRESTERA_DEV_ID_98DX7312M 0x981F +#define PRESTERA_DEV_ID_98DX3500 0x9820 +#define PRESTERA_DEV_ID_98DX3501 0x9826 +#define PRESTERA_DEV_ID_98DX3510 0x9821 +#define PRESTERA_DEV_ID_98DX3520 0x9822 + struct prestera_fw_evtq { u8 __iomem *addr; size_t len; @@ -201,6 +211,7 @@ struct prestera_fw { const struct firmware *bin; struct workqueue_struct *wq; struct prestera_device dev; + struct pci_dev *pci_dev; u8 __iomem *ldr_regs; u8 __iomem *ldr_ring_buf; u32 ldr_buf_len; @@ -689,6 +700,20 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw) return prestera_fw_rev_check(fw); } +static const char *prestera_fw_path_fmt_get(struct prestera_fw *fw) +{ + switch (fw->pci_dev->device) { + case PRESTERA_DEV_ID_98DX3500: + case PRESTERA_DEV_ID_98DX3501: + case PRESTERA_DEV_ID_98DX3510: + case PRESTERA_DEV_ID_98DX3520: + return PRESTERA_FW_ARM64_PATH_FMT; + + default: + return PRESTERA_FW_PATH_FMT; + } +} + static int prestera_fw_get(struct prestera_fw *fw) { int ver_maj = PRESTERA_SUPP_FW_MAJ_VER; @@ -697,7 +722,7 @@ static int prestera_fw_get(struct prestera_fw *fw) int err; pick_fw_ver: - snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT, + snprintf(fw_path, sizeof(fw_path), prestera_fw_path_fmt_get(fw), ver_maj, ver_min); err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); @@ -774,22 +799,56 @@ out_release: return err; } +static bool prestera_pci_pp_use_bar2(struct pci_dev *pdev) +{ + switch (pdev->device) { + case PRESTERA_DEV_ID_98DX7312M: + case PRESTERA_DEV_ID_98DX3500: + case PRESTERA_DEV_ID_98DX3501: + case PRESTERA_DEV_ID_98DX3510: + case PRESTERA_DEV_ID_98DX3520: + return true; + + default: + return false; + } +} + +static u32 prestera_pci_pp_bar2_offs(struct pci_dev *pdev) +{ + if (pci_resource_len(pdev, 2) == 0x1000000) + return 0x0; + else + return (pci_resource_len(pdev, 2) / 2); +} + +static u32 prestera_pci_fw_bar2_offs(struct pci_dev *pdev) +{ + if (pci_resource_len(pdev, 2) == 0x1000000) + return 0x400000; + else + return 0x0; +} + static int prestera_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { const char *driver_name = dev_driver_string(&pdev->dev); + u8 __iomem *mem_addr, *pp_addr = NULL; struct prestera_fw *fw; int err; err = pcim_enable_device(pdev); - if (err) - return err; + if (err) { + dev_err(&pdev->dev, "pci_enable_device failed\n"); + goto err_pci_enable_device; + } - err = pcim_iomap_regions(pdev, BIT(PRESTERA_PCI_BAR_FW) | - BIT(PRESTERA_PCI_BAR_PP), - pci_name(pdev)); - if (err) - return err; + err = pci_request_regions(pdev, driver_name); + if (err) { + dev_err(&pdev->dev, "pci_request_regions failed\n"); + goto err_pci_request_regions; + } err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30)); if (err) { @@ -797,6 +856,26 @@ static int prestera_pci_probe(struct pci_dev *pdev, goto err_dma_mask; } + mem_addr = pcim_iomap(pdev, 2, 0); + if (!mem_addr) { + dev_err(&pdev->dev, "pci mem ioremap failed\n"); + err = -EIO; + goto err_mem_ioremap; + } + + /* AC5X devices use second half of BAR2 */ + if (prestera_pci_pp_use_bar2(pdev)) { + pp_addr = mem_addr + prestera_pci_pp_bar2_offs(pdev); + mem_addr = mem_addr + prestera_pci_fw_bar2_offs(pdev); + } else { + pp_addr = pcim_iomap(pdev, 4, 0); + if (!pp_addr) { + dev_err(&pdev->dev, "pp regs ioremap failed\n"); + err = -EIO; + goto err_pp_ioremap; + } + } + pci_set_master(pdev); fw = devm_kzalloc(&pdev->dev, sizeof(*fw), GFP_KERNEL); @@ -805,8 +884,9 @@ static int prestera_pci_probe(struct pci_dev *pdev, goto err_pci_dev_alloc; } - fw->dev.ctl_regs = pcim_iomap_table(pdev)[PRESTERA_PCI_BAR_FW]; - fw->dev.pp_regs = pcim_iomap_table(pdev)[PRESTERA_PCI_BAR_PP]; + fw->pci_dev = pdev; + fw->dev.ctl_regs = mem_addr; + fw->dev.pp_regs = pp_addr; fw->dev.dev = &pdev->dev; pci_set_drvdata(pdev, fw); @@ -854,7 +934,12 @@ err_wq_alloc: prestera_fw_uninit(fw); err_prestera_fw_init: err_pci_dev_alloc: +err_pp_ioremap: +err_mem_ioremap: err_dma_mask: + pci_release_regions(pdev); +err_pci_request_regions: +err_pci_enable_device: return err; } @@ -867,12 +952,18 @@ static void prestera_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); destroy_workqueue(fw->wq); prestera_fw_uninit(fw); + pci_release_regions(pdev); } static const struct pci_device_id prestera_pci_devices[] = { - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC804) }, - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC80C) }, - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xCC1E) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_AC3X_98DX_55) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_AC3X_98DX_65) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_ALDRIN2) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX7312M) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3500) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3501) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3510) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3520) }, { } }; MODULE_DEVICE_TABLE(pci, prestera_pci_devices); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index ab33ba1c3023..ff97b140886a 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -3894,19 +3894,19 @@ static void sky2_get_stats(struct net_device *dev, u64 _bytes, _packets; do { - start = u64_stats_fetch_begin_irq(&sky2->rx_stats.syncp); + start = u64_stats_fetch_begin(&sky2->rx_stats.syncp); _bytes = sky2->rx_stats.bytes; _packets = sky2->rx_stats.packets; - } while (u64_stats_fetch_retry_irq(&sky2->rx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&sky2->rx_stats.syncp, start)); stats->rx_packets = _packets; stats->rx_bytes = _bytes; do { - start = u64_stats_fetch_begin_irq(&sky2->tx_stats.syncp); + start = u64_stats_fetch_begin(&sky2->tx_stats.syncp); _bytes = sky2->tx_stats.bytes; _packets = sky2->tx_stats.packets; - } while (u64_stats_fetch_retry_irq(&sky2->tx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&sky2->tx_stats.syncp, start)); stats->tx_packets = _packets; stats->tx_bytes = _bytes; diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile index 45ba0970504a..8e0c61c33ff8 100644 --- a/drivers/net/ethernet/mediatek/Makefile +++ b/drivers/net/ethernet/mediatek/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_ppe.o mtk_ppe_debugfs.o mtk_ppe_offload.o -mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o +mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o mtk_wed_mcu.o mtk_wed_wo.o ifdef CONFIG_DEBUG_FS mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o endif diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 1d36619c5ec9..e3de9a53b2d9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -23,6 +23,7 @@ #include <linux/jhash.h> #include <linux/bitfield.h> #include <net/dsa.h> +#include <net/dst_metadata.h> #include "mtk_eth_soc.h" #include "mtk_wed.h" @@ -54,6 +55,7 @@ static const struct mtk_reg_map mtk_reg_map = { }, .qdma = { .qtx_cfg = 0x1800, + .qtx_sch = 0x1804, .rx_ptr = 0x1900, .rx_cnt_cfg = 0x1904, .qcrx_ptr = 0x1908, @@ -61,6 +63,7 @@ static const struct mtk_reg_map mtk_reg_map = { .rst_idx = 0x1a08, .delay_irq = 0x1a0c, .fc_th = 0x1a10, + .tx_sch_rate = 0x1a14, .int_grp = 0x1a20, .hred = 0x1a44, .ctx_ptr = 0x1b00, @@ -113,6 +116,7 @@ static const struct mtk_reg_map mt7986_reg_map = { }, .qdma = { .qtx_cfg = 0x4400, + .qtx_sch = 0x4404, .rx_ptr = 0x4500, .rx_cnt_cfg = 0x4504, .qcrx_ptr = 0x4508, @@ -130,6 +134,7 @@ static const struct mtk_reg_map mt7986_reg_map = { .fq_tail = 0x4724, .fq_count = 0x4728, .fq_blen = 0x472c, + .tx_sch_rate = 0x4798, }, .gdm1_cnt = 0x1c00, .gdma_to_ppe = 0x3333, @@ -613,6 +618,75 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } +static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx, + int speed) +{ + const struct mtk_soc_data *soc = eth->soc; + u32 ofs, val; + + if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA)) + return; + + val = MTK_QTX_SCH_MIN_RATE_EN | + /* minimum: 10 Mbps */ + FIELD_PREP(MTK_QTX_SCH_MIN_RATE_MAN, 1) | + FIELD_PREP(MTK_QTX_SCH_MIN_RATE_EXP, 4) | + MTK_QTX_SCH_LEAKY_BUCKET_SIZE; + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + val |= MTK_QTX_SCH_LEAKY_BUCKET_EN; + + if (IS_ENABLED(CONFIG_SOC_MT7621)) { + switch (speed) { + case SPEED_10: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 2) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1); + break; + case SPEED_100: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3); + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1); + break; + case SPEED_1000: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 105) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 4) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10); + break; + default: + break; + } + } else { + switch (speed) { + case SPEED_10: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 4) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1); + break; + case SPEED_100: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5); + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1); + break; + case SPEED_1000: + val |= MTK_QTX_SCH_MAX_RATE_EN | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) | + FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10); + break; + default: + break; + } + } + + ofs = MTK_QTX_OFFSET * idx; + mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs); +} + static void mtk_mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, @@ -638,6 +712,8 @@ static void mtk_mac_link_up(struct phylink_config *config, break; } + mtk_set_queue_speed(mac->hw, mac->id, speed); + /* Configure duplex */ if (duplex == DUPLEX_FULL) mcr |= MAC_MCR_FORCE_DPX; @@ -653,7 +729,6 @@ static void mtk_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mtk_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mtk_mac_select_pcs, .mac_pcs_get_state = mtk_mac_pcs_get_state, .mac_config = mtk_mac_config, @@ -865,7 +940,7 @@ static void mtk_get_stats64(struct net_device *dev, } do { - start = u64_stats_fetch_begin_irq(&hw_stats->syncp); + start = u64_stats_fetch_begin(&hw_stats->syncp); storage->rx_packets = hw_stats->rx_packets; storage->tx_packets = hw_stats->tx_packets; storage->rx_bytes = hw_stats->rx_bytes; @@ -877,7 +952,7 @@ static void mtk_get_stats64(struct net_device *dev, storage->rx_crc_errors = hw_stats->rx_fcs_errors; storage->rx_errors = hw_stats->rx_checksum_errors; storage->tx_aborted_errors = hw_stats->tx_skip; - } while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start)); + } while (u64_stats_fetch_retry(&hw_stats->syncp, start)); storage->tx_errors = dev->stats.tx_errors; storage->rx_dropped = dev->stats.rx_dropped; @@ -938,7 +1013,7 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) { const struct mtk_soc_data *soc = eth->soc; dma_addr_t phy_ring_tail; - int cnt = MTK_DMA_SIZE; + int cnt = MTK_QDMA_RING_SIZE; dma_addr_t dma_addr; int i; @@ -1099,7 +1174,8 @@ static void mtk_tx_set_dma_desc_v1(struct net_device *dev, void *txd, WRITE_ONCE(desc->txd1, info->addr); - data = TX_DMA_SWC | TX_DMA_PLEN0(info->size); + data = TX_DMA_SWC | TX_DMA_PLEN0(info->size) | + FIELD_PREP(TX_DMA_PQID, info->qid); if (info->last) data |= TX_DMA_LS0; WRITE_ONCE(desc->txd3, data); @@ -1133,9 +1209,6 @@ static void mtk_tx_set_dma_desc_v2(struct net_device *dev, void *txd, data |= TX_DMA_LS0; WRITE_ONCE(desc->txd3, data); - if (!info->qid && mac->id) - info->qid = MTK_QDMA_GMAC2_QID; - data = (mac->id + 1) << TX_DMA_FPORT_SHIFT_V2; /* forward port */ data |= TX_DMA_SWC_V2 | QID_BITS_V2(info->qid); WRITE_ONCE(desc->txd4, data); @@ -1179,11 +1252,12 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, .gso = gso, .csum = skb->ip_summed == CHECKSUM_PARTIAL, .vlan = skb_vlan_tag_present(skb), - .qid = skb->mark & MTK_QDMA_TX_MASK, + .qid = skb_get_queue_mapping(skb), .vlan_tci = skb_vlan_tag_get(skb), .first = true, .last = !skb_is_nonlinear(skb), }; + struct netdev_queue *txq; struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; const struct mtk_soc_data *soc = eth->soc; @@ -1191,8 +1265,10 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, struct mtk_tx_dma *itxd_pdma, *txd_pdma; struct mtk_tx_buf *itx_buf, *tx_buf; int i, n_desc = 1; + int queue = skb_get_queue_mapping(skb); int k = 0; + txq = netdev_get_tx_queue(dev, queue); itxd = ring->next_free; itxd_pdma = qdma_to_pdma(ring, itxd); if (itxd == ring->last_free) @@ -1241,7 +1317,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info)); txd_info.size = min_t(unsigned int, frag_size, soc->txrx.dma_max_len); - txd_info.qid = skb->mark & MTK_QDMA_TX_MASK; + txd_info.qid = queue; txd_info.last = i == skb_shinfo(skb)->nr_frags - 1 && !(frag_size - txd_info.size); txd_info.addr = skb_frag_dma_map(eth->dma_dev, frag, @@ -1280,7 +1356,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, txd_pdma->txd2 |= TX_DMA_LS1; } - netdev_sent_queue(dev, skb->len); + netdev_tx_sent_queue(txq, skb->len); skb_tx_timestamp(skb); ring->next_free = mtk_qdma_phys_to_virt(ring, txd->txd2); @@ -1292,8 +1368,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, wmb(); if (MTK_HAS_CAPS(soc->caps, MTK_QDMA)) { - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || - !netdev_xmit_more()) + if (netif_xmit_stopped(txq) || !netdev_xmit_more()) mtk_w32(eth, txd->txd2, soc->reg_map->qdma.ctx_ptr); } else { int next_idx; @@ -1362,7 +1437,7 @@ static void mtk_wake_queue(struct mtk_eth *eth) for (i = 0; i < MTK_MAC_COUNT; i++) { if (!eth->netdev[i]) continue; - netif_wake_queue(eth->netdev[i]); + netif_tx_wake_all_queues(eth->netdev[i]); } } @@ -1386,7 +1461,7 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_num = mtk_cal_txd_req(eth, skb); if (unlikely(atomic_read(&ring->free_count) <= tx_num)) { - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); netif_err(eth, tx_queued, dev, "Tx Ring full when queue awake!\n"); spin_unlock(ð->page_lock); @@ -1412,7 +1487,7 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); spin_unlock(ð->page_lock); @@ -1579,10 +1654,12 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); const struct mtk_soc_data *soc = eth->soc; struct mtk_tx_ring *ring = ð->tx_ring; + struct mtk_mac *mac = netdev_priv(dev); struct mtk_tx_dma_desc_info txd_info = { .size = xdpf->len, .first = true, .last = !xdp_frame_has_frags(xdpf), + .qid = mac->id, }; int err, index = 0, n_desc = 1, nr_frags; struct mtk_tx_buf *htx_buf, *tx_buf; @@ -1632,6 +1709,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info)); txd_info.size = skb_frag_size(&sinfo->frags[index]); txd_info.last = index + 1 == nr_frags; + txd_info.qid = mac->id; data = skb_frag_address(&sinfo->frags[index]); index++; @@ -1937,16 +2015,22 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, htons(RX_DMA_VPID(trxd.rxd4)), RX_DMA_VID(trxd.rxd4)); } else if (trxd.rxd2 & RX_DMA_VTAG) { - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)), RX_DMA_VID(trxd.rxd3)); } + } + + /* When using VLAN untagging in combination with DSA, the + * hardware treats the MTK special tag as a VLAN and untags it. + */ + if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) { + unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0); + + if (port < ARRAY_SIZE(eth->dsa_meta) && + eth->dsa_meta[port]) + skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - /* If the device is attached to a dsa switch, the special - * tag inserted in VLAN field by hw switch can * be offloaded - * by RX HW VLAN offload. Clear vlan info. - */ - if (netdev_uses_dsa(netdev)) - __vlan_hwaccel_clear_tag(skb); + __vlan_hwaccel_clear_tag(skb); } skb_record_rx_queue(skb, 0); @@ -1986,8 +2070,46 @@ rx_done: return done; } +struct mtk_poll_state { + struct netdev_queue *txq; + unsigned int total; + unsigned int done; + unsigned int bytes; +}; + +static void +mtk_poll_tx_done(struct mtk_eth *eth, struct mtk_poll_state *state, u8 mac, + struct sk_buff *skb) +{ + struct netdev_queue *txq; + struct net_device *dev; + unsigned int bytes = skb->len; + + state->total++; + eth->tx_packets++; + eth->tx_bytes += bytes; + + dev = eth->netdev[mac]; + if (!dev) + return; + + txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); + if (state->txq == txq) { + state->done++; + state->bytes += bytes; + return; + } + + if (state->txq) + netdev_tx_completed_queue(state->txq, state->done, state->bytes); + + state->txq = txq; + state->done = 1; + state->bytes = bytes; +} + static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, - unsigned int *done, unsigned int *bytes) + struct mtk_poll_state *state) { const struct mtk_reg_map *reg_map = eth->soc->reg_map; struct mtk_tx_ring *ring = ð->tx_ring; @@ -2019,12 +2141,9 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, break; if (tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) { - if (tx_buf->type == MTK_TYPE_SKB) { - struct sk_buff *skb = tx_buf->data; + if (tx_buf->type == MTK_TYPE_SKB) + mtk_poll_tx_done(eth, state, mac, tx_buf->data); - bytes[mac] += skb->len; - done[mac]++; - } budget--; } mtk_tx_unmap(eth, tx_buf, &bq, true); @@ -2043,7 +2162,7 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, } static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, - unsigned int *done, unsigned int *bytes) + struct mtk_poll_state *state) { struct mtk_tx_ring *ring = ð->tx_ring; struct mtk_tx_buf *tx_buf; @@ -2061,12 +2180,8 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, break; if (tx_buf->data != (void *)MTK_DMA_DUMMY_DESC) { - if (tx_buf->type == MTK_TYPE_SKB) { - struct sk_buff *skb = tx_buf->data; - - bytes[0] += skb->len; - done[0]++; - } + if (tx_buf->type == MTK_TYPE_SKB) + mtk_poll_tx_done(eth, state, 0, tx_buf->data); budget--; } mtk_tx_unmap(eth, tx_buf, &bq, true); @@ -2088,26 +2203,15 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) { struct mtk_tx_ring *ring = ð->tx_ring; struct dim_sample dim_sample = {}; - unsigned int done[MTK_MAX_DEVS]; - unsigned int bytes[MTK_MAX_DEVS]; - int total = 0, i; - - memset(done, 0, sizeof(done)); - memset(bytes, 0, sizeof(bytes)); + struct mtk_poll_state state = {}; if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) - budget = mtk_poll_tx_qdma(eth, budget, done, bytes); + budget = mtk_poll_tx_qdma(eth, budget, &state); else - budget = mtk_poll_tx_pdma(eth, budget, done, bytes); + budget = mtk_poll_tx_pdma(eth, budget, &state); - for (i = 0; i < MTK_MAC_COUNT; i++) { - if (!eth->netdev[i] || !done[i]) - continue; - netdev_completed_queue(eth->netdev[i], done[i], bytes[i]); - total += done[i]; - eth->tx_packets += done[i]; - eth->tx_bytes += bytes[i]; - } + if (state.txq) + netdev_tx_completed_queue(state.txq, state.done, state.bytes); dim_update_sample(eth->tx_events, eth->tx_packets, eth->tx_bytes, &dim_sample); @@ -2117,7 +2221,7 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) (atomic_read(&ring->free_count) > ring->thresh)) mtk_wake_queue(eth); - return total; + return state.total; } static void mtk_handle_status_irq(struct mtk_eth *eth) @@ -2202,19 +2306,26 @@ static int mtk_tx_alloc(struct mtk_eth *eth) struct mtk_tx_ring *ring = ð->tx_ring; int i, sz = soc->txrx.txd_size; struct mtk_tx_dma_v2 *txd; + int ring_size; + u32 ofs, val; + + if (MTK_HAS_CAPS(soc->caps, MTK_QDMA)) + ring_size = MTK_QDMA_RING_SIZE; + else + ring_size = MTK_DMA_SIZE; - ring->buf = kcalloc(MTK_DMA_SIZE, sizeof(*ring->buf), + ring->buf = kcalloc(ring_size, sizeof(*ring->buf), GFP_KERNEL); if (!ring->buf) goto no_tx_mem; - ring->dma = dma_alloc_coherent(eth->dma_dev, MTK_DMA_SIZE * sz, + ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz, &ring->phys, GFP_KERNEL); if (!ring->dma) goto no_tx_mem; - for (i = 0; i < MTK_DMA_SIZE; i++) { - int next = (i + 1) % MTK_DMA_SIZE; + for (i = 0; i < ring_size; i++) { + int next = (i + 1) % ring_size; u32 next_ptr = ring->phys + next * sz; txd = ring->dma + i * sz; @@ -2234,22 +2345,22 @@ static int mtk_tx_alloc(struct mtk_eth *eth) * descriptors in ring->dma_pdma. */ if (!MTK_HAS_CAPS(soc->caps, MTK_QDMA)) { - ring->dma_pdma = dma_alloc_coherent(eth->dma_dev, MTK_DMA_SIZE * sz, + ring->dma_pdma = dma_alloc_coherent(eth->dma_dev, ring_size * sz, &ring->phys_pdma, GFP_KERNEL); if (!ring->dma_pdma) goto no_tx_mem; - for (i = 0; i < MTK_DMA_SIZE; i++) { + for (i = 0; i < ring_size; i++) { ring->dma_pdma[i].txd2 = TX_DMA_DESP2_DEF; ring->dma_pdma[i].txd4 = 0; } } - ring->dma_size = MTK_DMA_SIZE; - atomic_set(&ring->free_count, MTK_DMA_SIZE - 2); + ring->dma_size = ring_size; + atomic_set(&ring->free_count, ring_size - 2); ring->next_free = ring->dma; ring->last_free = (void *)txd; - ring->last_free_ptr = (u32)(ring->phys + ((MTK_DMA_SIZE - 1) * sz)); + ring->last_free_ptr = (u32)(ring->phys + ((ring_size - 1) * sz)); ring->thresh = MAX_SKB_FRAGS; /* make sure that all changes to the dma ring are flushed before we @@ -2261,14 +2372,31 @@ static int mtk_tx_alloc(struct mtk_eth *eth) mtk_w32(eth, ring->phys, soc->reg_map->qdma.ctx_ptr); mtk_w32(eth, ring->phys, soc->reg_map->qdma.dtx_ptr); mtk_w32(eth, - ring->phys + ((MTK_DMA_SIZE - 1) * sz), + ring->phys + ((ring_size - 1) * sz), soc->reg_map->qdma.crx_ptr); mtk_w32(eth, ring->last_free_ptr, soc->reg_map->qdma.drx_ptr); - mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, - soc->reg_map->qdma.qtx_cfg); + + for (i = 0, ofs = 0; i < MTK_QDMA_NUM_QUEUES; i++) { + val = (QDMA_RES_THRES << 8) | QDMA_RES_THRES; + mtk_w32(eth, val, soc->reg_map->qdma.qtx_cfg + ofs); + + val = MTK_QTX_SCH_MIN_RATE_EN | + /* minimum: 10 Mbps */ + FIELD_PREP(MTK_QTX_SCH_MIN_RATE_MAN, 1) | + FIELD_PREP(MTK_QTX_SCH_MIN_RATE_EXP, 4) | + MTK_QTX_SCH_LEAKY_BUCKET_SIZE; + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + val |= MTK_QTX_SCH_LEAKY_BUCKET_EN; + mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs); + ofs += MTK_QTX_OFFSET; + } + val = MTK_QDMA_TX_SCH_MAX_WFQ | (MTK_QDMA_TX_SCH_MAX_WFQ << 16); + mtk_w32(eth, val, soc->reg_map->qdma.tx_sch_rate); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + mtk_w32(eth, val, soc->reg_map->qdma.tx_sch_rate + 4); } else { mtk_w32(eth, ring->phys_pdma, MT7628_TX_BASE_PTR0); - mtk_w32(eth, MTK_DMA_SIZE, MT7628_TX_MAX_CNT0); + mtk_w32(eth, ring_size, MT7628_TX_MAX_CNT0); mtk_w32(eth, 0, MT7628_TX_CTX_IDX0); mtk_w32(eth, MT7628_PST_DTX_IDX0, soc->reg_map->pdma.rst_idx); } @@ -2286,7 +2414,7 @@ static void mtk_tx_clean(struct mtk_eth *eth) int i; if (ring->buf) { - for (i = 0; i < MTK_DMA_SIZE; i++) + for (i = 0; i < ring->dma_size; i++) mtk_tx_unmap(eth, &ring->buf[i], NULL, false); kfree(ring->buf); ring->buf = NULL; @@ -2294,14 +2422,14 @@ static void mtk_tx_clean(struct mtk_eth *eth) if (ring->dma) { dma_free_coherent(eth->dma_dev, - MTK_DMA_SIZE * soc->txrx.txd_size, + ring->dma_size * soc->txrx.txd_size, ring->dma, ring->phys); ring->dma = NULL; } if (ring->dma_pdma) { dma_free_coherent(eth->dma_dev, - MTK_DMA_SIZE * soc->txrx.txd_size, + ring->dma_size * soc->txrx.txd_size, ring->dma_pdma, ring->phys_pdma); ring->dma_pdma = NULL; } @@ -2727,15 +2855,30 @@ static netdev_features_t mtk_fix_features(struct net_device *dev, static int mtk_set_features(struct net_device *dev, netdev_features_t features) { - int err = 0; + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + netdev_features_t diff = dev->features ^ features; + int i; - if (!((dev->features ^ features) & NETIF_F_LRO)) + if ((diff & NETIF_F_LRO) && !(features & NETIF_F_LRO)) + mtk_hwlro_netdev_disable(dev); + + /* Set RX VLAN offloading */ + if (!(diff & NETIF_F_HW_VLAN_CTAG_RX)) return 0; - if (!(features & NETIF_F_LRO)) - mtk_hwlro_netdev_disable(dev); + mtk_w32(eth, !!(features & NETIF_F_HW_VLAN_CTAG_RX), + MTK_CDMP_EG_CTRL); - return err; + /* sync features with other MAC */ + for (i = 0; i < MTK_MAC_COUNT; i++) { + if (!eth->netdev[i] || eth->netdev[i] == dev) + continue; + eth->netdev[i]->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + eth->netdev[i]->features |= features & NETIF_F_HW_VLAN_CTAG_RX; + } + + return 0; } /* wait for DMA to finish whatever it is doing before we start using it again */ @@ -2823,7 +2966,7 @@ static void mtk_dma_free(struct mtk_eth *eth) netdev_reset_queue(eth->netdev[i]); if (eth->scratch_ring) { dma_free_coherent(eth->dma_dev, - MTK_DMA_SIZE * soc->txrx.txd_size, + MTK_QDMA_RING_SIZE * soc->txrx.txd_size, eth->scratch_ring, eth->phy_scratch_ring); eth->scratch_ring = NULL; eth->phy_scratch_ring = 0; @@ -2932,7 +3075,7 @@ static int mtk_start_dma(struct mtk_eth *eth) if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) val |= MTK_MUTLI_CNT | MTK_RESV_BUF | MTK_WCOMP_EN | MTK_DMAD_WR_WDONE | - MTK_CHK_DDONE_EN; + MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN; else val |= MTK_RX_BT_32DWORDS; mtk_w32(eth, val, reg_map->qdma.glo_cfg); @@ -2978,11 +3121,85 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config) mtk_w32(eth, 0, MTK_RST_GL); } + +static bool mtk_uses_dsa(struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + return netdev_uses_dsa(dev) && + dev->dsa_ptr->tag_ops->proto == DSA_TAG_PROTO_MTK; +#else + return false; +#endif +} + +static int mtk_device_event(struct notifier_block *n, unsigned long event, void *ptr) +{ + struct mtk_mac *mac = container_of(n, struct mtk_mac, device_notifier); + struct mtk_eth *eth = mac->hw; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ethtool_link_ksettings s; + struct net_device *ldev; + struct list_head *iter; + struct dsa_port *dp; + + if (event != NETDEV_CHANGE) + return NOTIFY_DONE; + + netdev_for_each_lower_dev(dev, ldev, iter) { + if (netdev_priv(ldev) == mac) + goto found; + } + + return NOTIFY_DONE; + +found: + if (!dsa_slave_dev_check(dev)) + return NOTIFY_DONE; + + if (__ethtool_get_link_ksettings(dev, &s)) + return NOTIFY_DONE; + + if (s.base.speed == 0 || s.base.speed == ((__u32)-1)) + return NOTIFY_DONE; + + dp = dsa_port_from_netdev(dev); + if (dp->index >= MTK_QDMA_NUM_QUEUES) + return NOTIFY_DONE; + + mtk_set_queue_speed(eth, dp->index + 3, s.base.speed); + + return NOTIFY_DONE; +} + static int mtk_open(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; - int err; + int i, err; + + if (mtk_uses_dsa(dev) && !eth->prog) { + for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { + struct metadata_dst *md_dst = eth->dsa_meta[i]; + + if (md_dst) + continue; + + md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, + GFP_KERNEL); + if (!md_dst) + return -ENOMEM; + + md_dst->u.port_info.port_id = i; + eth->dsa_meta[i] = md_dst; + } + } else { + /* Hardware special tag parsing needs to be disabled if at least + * one MAC does not use DSA. + */ + u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); + val &= ~MTK_CDMP_STAG_EN; + mtk_w32(eth, val, MTK_CDMP_IG_CTRL); + } err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0); if (err) { @@ -3020,7 +3237,8 @@ static int mtk_open(struct net_device *dev) refcount_inc(ð->dma_refcnt); phylink_start(mac->phylink); - netif_start_queue(dev); + netif_tx_start_all_queues(dev); + return 0; } @@ -3229,6 +3447,30 @@ static void mtk_dim_tx(struct work_struct *work) dim->state = DIM_START_MEASURE; } +static void mtk_set_mcr_max_rx(struct mtk_mac *mac, u32 val) +{ + struct mtk_eth *eth = mac->hw; + u32 mcr_cur, mcr_new; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + return; + + mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); + mcr_new = mcr_cur & ~MAC_MCR_MAX_RX_MASK; + + if (val <= 1518) + mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1518); + else if (val <= 1536) + mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1536); + else if (val <= 1552) + mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1552); + else + mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_2048); + + if (mcr_new != mcr_cur) + mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id)); +} + static int mtk_hw_init(struct mtk_eth *eth) { u32 dma_mask = ETHSYS_DMA_AG_MAP_PDMA | ETHSYS_DMA_AG_MAP_QDMA | @@ -3268,16 +3510,17 @@ static int mtk_hw_init(struct mtk_eth *eth) return 0; } - val = RSTCTRL_FE | RSTCTRL_PPE; if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, 0); - - val |= RSTCTRL_ETH; - if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) - val |= RSTCTRL_PPE1; + val = RSTCTRL_PPE0_V2; + } else { + val = RSTCTRL_PPE0; } - ethsys_reset(eth, val); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) + val |= RSTCTRL_PPE1; + + ethsys_reset(eth, RSTCTRL_ETH | RSTCTRL_FE | val); if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, @@ -3303,14 +3546,26 @@ static int mtk_hw_init(struct mtk_eth *eth) * up with the more appropriate value when mtk_mac_config call is being * invoked. */ - for (i = 0; i < MTK_MAC_COUNT; i++) + for (i = 0; i < MTK_MAC_COUNT; i++) { + struct net_device *dev = eth->netdev[i]; + mtk_w32(eth, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(i)); + if (dev) { + struct mtk_mac *mac = netdev_priv(dev); + + mtk_set_mcr_max_rx(mac, dev->mtu + MTK_RX_ETH_HLEN); + } + } /* Indicates CDM to parse the MTK special tag from CPU * which also is working out for untag packets. */ val = mtk_r32(eth, MTK_CDMQ_IG_CTRL); mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { + val = mtk_r32(eth, MTK_CDMP_IG_CTRL); + mtk_w32(eth, val | MTK_CDMP_STAG_EN, MTK_CDMP_IG_CTRL); + } /* Enable RX VLan Offloading */ mtk_w32(eth, 1, MTK_CDMP_EG_CTRL); @@ -3331,9 +3586,12 @@ static int mtk_hw_init(struct mtk_eth *eth) mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - /* PSE should not drop port8 and port9 packets */ + /* PSE should not drop port8 and port9 packets from WDMA Tx */ mtk_w32(eth, 0x00000300, PSE_DROP_CFG); + /* PSE should drop packets to port 8/9 on WDMA Rx ring full */ + mtk_w32(eth, 0x00000300, PSE_PPE0_DROP); + /* PSE Free Queue Flow Control */ mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2); @@ -3420,7 +3678,6 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu) int length = new_mtu + MTK_RX_ETH_HLEN; struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; - u32 mcr_cur, mcr_new; if (rcu_access_pointer(eth->prog) && length > MTK_PP_MAX_BUF_SIZE) { @@ -3428,23 +3685,7 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } - if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { - mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - mcr_new = mcr_cur & ~MAC_MCR_MAX_RX_MASK; - - if (length <= 1518) - mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1518); - else if (length <= 1536) - mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1536); - else if (length <= 1552) - mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1552); - else - mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_2048); - - if (mcr_new != mcr_cur) - mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id)); - } - + mtk_set_mcr_max_rx(mac, length); dev->mtu = new_mtu; return 0; @@ -3475,11 +3716,8 @@ static void mtk_pending_work(struct work_struct *work) rtnl_lock(); dev_dbg(eth->dev, "[%s][%d] reset\n", __func__, __LINE__); + set_bit(MTK_RESETTING, ð->state); - while (test_and_set_bit_lock(MTK_RESETTING, ð->state)) - cpu_relax(); - - dev_dbg(eth->dev, "[%s][%d] mtk_stop starts\n", __func__, __LINE__); /* stop all devices to make sure that dma is properly shut down */ for (i = 0; i < MTK_MAC_COUNT; i++) { if (!eth->netdev[i]) @@ -3513,7 +3751,7 @@ static void mtk_pending_work(struct work_struct *work) dev_dbg(eth->dev, "[%s][%d] reset done\n", __func__, __LINE__); - clear_bit_unlock(MTK_RESETTING, ð->state); + clear_bit(MTK_RESETTING, ð->state); rtnl_unlock(); } @@ -3528,6 +3766,12 @@ static int mtk_free_dev(struct mtk_eth *eth) free_netdev(eth->netdev[i]); } + for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { + if (!eth->dsa_meta[i]) + break; + metadata_dst_free(eth->dsa_meta[i]); + } + return 0; } @@ -3536,8 +3780,12 @@ static int mtk_unreg_dev(struct mtk_eth *eth) int i; for (i = 0; i < MTK_MAC_COUNT; i++) { + struct mtk_mac *mac; if (!eth->netdev[i]) continue; + mac = netdev_priv(eth->netdev[i]); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + unregister_netdevice_notifier(&mac->device_notifier); unregister_netdev(eth->netdev[i]); } @@ -3688,13 +3936,13 @@ static void mtk_get_ethtool_stats(struct net_device *dev, do { data_dst = data; - start = u64_stats_fetch_begin_irq(&hwstats->syncp); + start = u64_stats_fetch_begin(&hwstats->syncp); for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++) *data_dst++ = *(data_src + mtk_ethtool_stats[i].offset); if (mtk_page_pool_enabled(mac->hw)) mtk_ethtool_pp_stats(mac->hw, data_dst); - } while (u64_stats_fetch_retry_irq(&hwstats->syncp, start)); + } while (u64_stats_fetch_retry(&hwstats->syncp, start)); } static int mtk_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, @@ -3753,6 +4001,23 @@ static int mtk_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } +static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + unsigned int queue = 0; + + if (netdev_uses_dsa(dev)) + queue = skb_get_queue_mapping(skb) + 3; + else + queue = mac->id; + + if (queue >= dev->num_tx_queues) + queue = 0; + + return queue; +} + static const struct ethtool_ops mtk_ethtool_ops = { .get_link_ksettings = mtk_get_link_ksettings, .set_link_ksettings = mtk_set_link_ksettings, @@ -3788,6 +4053,7 @@ static const struct net_device_ops mtk_netdev_ops = { .ndo_setup_tc = mtk_eth_setup_tc, .ndo_bpf = mtk_xdp, .ndo_xdp_xmit = mtk_xdp_xmit, + .ndo_select_queue = mtk_select_queue, }; static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) @@ -3797,6 +4063,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) struct phylink *phylink; struct mtk_mac *mac; int id, err; + int txqs = 1; if (!_id) { dev_err(eth->dev, "missing mac id\n"); @@ -3814,7 +4081,10 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) return -EINVAL; } - eth->netdev[id] = alloc_etherdev(sizeof(*mac)); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + txqs = MTK_QDMA_NUM_QUEUES; + + eth->netdev[id] = alloc_etherdev_mqs(sizeof(*mac), txqs, 1); if (!eth->netdev[id]) { dev_err(eth->dev, "alloc_etherdev failed\n"); return -ENOMEM; @@ -3911,6 +4181,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) else eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH_2K - MTK_RX_ETH_HLEN; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + mac->device_notifier.notifier_call = mtk_device_event; + register_netdevice_notifier(&mac->device_notifier); + } + return 0; free_netdev: @@ -4242,7 +4517,7 @@ static const struct mtk_soc_data mt7621_data = { .hw_features = MTK_HW_FEATURES, .required_clks = MT7621_CLKS_BITMAP, .required_pctl = false, - .offload_version = 2, + .offload_version = 1, .hash_offset = 2, .foe_entry_size = sizeof(struct mtk_foe_entry) - 16, .txrx = { @@ -4281,7 +4556,7 @@ static const struct mtk_soc_data mt7623_data = { .hw_features = MTK_HW_FEATURES, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, - .offload_version = 2, + .offload_version = 1, .hash_offset = 2, .foe_entry_size = sizeof(struct mtk_foe_entry) - 16, .txrx = { @@ -4318,6 +4593,7 @@ static const struct mtk_soc_data mt7986_data = { .hw_features = MTK_HW_FEATURES, .required_clks = MT7986_CLKS_BITMAP, .required_pctl = false, + .offload_version = 2, .hash_offset = 4, .foe_entry_size = sizeof(struct mtk_foe_entry), .txrx = { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index b52f3b0177ef..18a50529ce7b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -22,11 +22,16 @@ #include <linux/bpf_trace.h> #include "mtk_ppe.h" +#define MTK_MAX_DSA_PORTS 7 +#define MTK_DSA_PORT_MASK GENMASK(2, 0) + +#define MTK_QDMA_NUM_QUEUES 16 #define MTK_QDMA_PAGE_SIZE 2048 #define MTK_MAX_RX_LENGTH 1536 #define MTK_MAX_RX_LENGTH_2K 2048 #define MTK_TX_DMA_BUF_LEN 0x3fff #define MTK_TX_DMA_BUF_LEN_V2 0xffff +#define MTK_QDMA_RING_SIZE 2048 #define MTK_DMA_SIZE 512 #define MTK_MAC_COUNT 2 #define MTK_RX_ETH_HLEN (ETH_HLEN + ETH_FCS_LEN) @@ -91,6 +96,9 @@ #define MTK_CDMQ_IG_CTRL 0x1400 #define MTK_CDMQ_STAG_EN BIT(0) +/* CDMQ Exgress Control Register */ +#define MTK_CDMQ_EG_CTRL 0x1404 + /* CDMP Ingress Control Register */ #define MTK_CDMP_IG_CTRL 0x400 #define MTK_CDMP_STAG_EN BIT(0) @@ -120,6 +128,7 @@ #define PSE_FQFC_CFG1 0x100 #define PSE_FQFC_CFG2 0x104 #define PSE_DROP_CFG 0x108 +#define PSE_PPE0_DROP 0x110 /* PSE Input Queue Reservation Register*/ #define PSE_IQ_REV(x) (0x140 + (((x) - 1) << 2)) @@ -202,8 +211,26 @@ #define MTK_RING_MAX_AGG_CNT_H ((MTK_HW_LRO_MAX_AGG_CNT >> 6) & 0x3) /* QDMA TX Queue Configuration Registers */ +#define MTK_QTX_OFFSET 0x10 #define QDMA_RES_THRES 4 +/* QDMA Tx Queue Scheduler Configuration Registers */ +#define MTK_QTX_SCH_TX_SEL BIT(31) +#define MTK_QTX_SCH_TX_SEL_V2 GENMASK(31, 30) + +#define MTK_QTX_SCH_LEAKY_BUCKET_EN BIT(30) +#define MTK_QTX_SCH_LEAKY_BUCKET_SIZE GENMASK(29, 28) +#define MTK_QTX_SCH_MIN_RATE_EN BIT(27) +#define MTK_QTX_SCH_MIN_RATE_MAN GENMASK(26, 20) +#define MTK_QTX_SCH_MIN_RATE_EXP GENMASK(19, 16) +#define MTK_QTX_SCH_MAX_RATE_WEIGHT GENMASK(15, 12) +#define MTK_QTX_SCH_MAX_RATE_EN BIT(11) +#define MTK_QTX_SCH_MAX_RATE_MAN GENMASK(10, 4) +#define MTK_QTX_SCH_MAX_RATE_EXP GENMASK(3, 0) + +/* QDMA TX Scheduler Rate Control Register */ +#define MTK_QDMA_TX_SCH_MAX_WFQ BIT(15) + /* QDMA Global Configuration Register */ #define MTK_RX_2B_OFFSET BIT(31) #define MTK_RX_BT_32DWORDS (3 << 11) @@ -222,6 +249,7 @@ #define MTK_WCOMP_EN BIT(24) #define MTK_RESV_BUF (0x40 << 16) #define MTK_MUTLI_CNT (0x4 << 12) +#define MTK_LEAKY_BUCKET_EN BIT(11) /* QDMA Flow Control Register */ #define FC_THRES_DROP_MODE BIT(20) @@ -250,8 +278,6 @@ #define MTK_STAT_OFFSET 0x40 /* QDMA TX NUM */ -#define MTK_QDMA_TX_NUM 16 -#define MTK_QDMA_TX_MASK (MTK_QDMA_TX_NUM - 1) #define QID_BITS_V2(x) (((x) & 0x3f) << 16) #define MTK_QDMA_GMAC2_QID 8 @@ -281,6 +307,7 @@ #define TX_DMA_PLEN0(x) (((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset) #define TX_DMA_PLEN1(x) ((x) & eth->soc->txrx.dma_max_len) #define TX_DMA_SWC BIT(14) +#define TX_DMA_PQID GENMASK(3, 0) /* PDMA on MT7628 */ #define TX_DMA_DONE BIT(31) @@ -447,18 +474,14 @@ /* ethernet reset control register */ #define ETHSYS_RSTCTRL 0x34 #define RSTCTRL_FE BIT(6) -#define RSTCTRL_PPE BIT(31) -#define RSTCTRL_PPE1 BIT(30) +#define RSTCTRL_PPE0 BIT(31) +#define RSTCTRL_PPE0_V2 BIT(30) +#define RSTCTRL_PPE1 BIT(31) #define RSTCTRL_ETH BIT(23) /* ethernet reset check idle register */ #define ETHSYS_FE_RST_CHK_IDLE_EN 0x28 -/* ethernet reset control register */ -#define ETHSYS_RSTCTRL 0x34 -#define RSTCTRL_FE BIT(6) -#define RSTCTRL_PPE BIT(31) - /* ethernet dma channel agent map */ #define ETHSYS_DMA_AG_MAP 0x408 #define ETHSYS_DMA_AG_MAP_PDMA BIT(0) @@ -466,8 +489,10 @@ #define ETHSYS_DMA_AG_MAP_PPE BIT(2) /* SGMII subsystem config registers */ -/* Register to auto-negotiation restart */ +/* BMCR (low 16) BMSR (high 16) */ #define SGMSYS_PCS_CONTROL_1 0x0 +#define SGMII_BMCR GENMASK(15, 0) +#define SGMII_BMSR GENMASK(31, 16) #define SGMII_AN_RESTART BIT(9) #define SGMII_ISOLATE BIT(10) #define SGMII_AN_ENABLE BIT(12) @@ -477,13 +502,18 @@ #define SGMII_PCS_FAULT BIT(23) #define SGMII_AN_EXPANSION_CLR BIT(30) +#define SGMSYS_PCS_ADVERTISE 0x8 +#define SGMII_ADVERTISE GENMASK(15, 0) +#define SGMII_LPA GENMASK(31, 16) + /* Register to programmable link timer, the unit in 2 * 8ns */ #define SGMSYS_PCS_LINK_TIMER 0x18 -#define SGMII_LINK_TIMER_DEFAULT (0x186a0 & GENMASK(19, 0)) +#define SGMII_LINK_TIMER_MASK GENMASK(19, 0) +#define SGMII_LINK_TIMER_DEFAULT (0x186a0 & SGMII_LINK_TIMER_MASK) /* Register to control remote fault */ #define SGMSYS_SGMII_MODE 0x20 -#define SGMII_IF_MODE_BIT0 BIT(0) +#define SGMII_IF_MODE_SGMII BIT(0) #define SGMII_SPEED_DUPLEX_AN BIT(1) #define SGMII_SPEED_MASK GENMASK(3, 2) #define SGMII_SPEED_10 FIELD_PREP(SGMII_SPEED_MASK, 0) @@ -932,6 +962,7 @@ struct mtk_reg_map { } pdma; struct { u32 qtx_cfg; /* tx queue configuration */ + u32 qtx_sch; /* tx queue scheduler configuration */ u32 rx_ptr; /* rx base pointer */ u32 rx_cnt_cfg; /* rx max count configuration */ u32 qcrx_ptr; /* rx cpu pointer */ @@ -949,6 +980,7 @@ struct mtk_reg_map { u32 fq_tail; /* fq tail pointer */ u32 fq_count; /* fq free page count */ u32 fq_blen; /* fq free page buffer length */ + u32 tx_sch_rate; /* tx scheduler rate control registers */ } qdma; u32 gdm1_cnt; u32 gdma_to_ppe; @@ -1114,6 +1146,8 @@ struct mtk_eth { int ip_align; + struct metadata_dst *dsa_meta[MTK_MAX_DSA_PORTS]; + struct mtk_ppe *ppe[2]; struct rhashtable flow_table; @@ -1140,6 +1174,7 @@ struct mtk_mac { __be32 hwlro_ip[MTK_MAX_LRO_IP_CNT]; int hwlro_ip_cnt; unsigned int syscfg0; + struct notifier_block device_notifier; }; /* the struct describing the SoC. these are declared in the soc_xyz.c files */ diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 784ecb2dc9fb..269208a841c7 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -175,6 +175,8 @@ int mtk_foe_entry_prepare(struct mtk_eth *eth, struct mtk_foe_entry *entry, val = FIELD_PREP(MTK_FOE_IB2_DEST_PORT_V2, pse_port) | FIELD_PREP(MTK_FOE_IB2_PORT_AG_V2, 0xf); } else { + int port_mg = eth->soc->offload_version > 1 ? 0 : 0x3f; + val = FIELD_PREP(MTK_FOE_IB1_STATE, MTK_FOE_STATE_BIND) | FIELD_PREP(MTK_FOE_IB1_PACKET_TYPE, type) | FIELD_PREP(MTK_FOE_IB1_UDP, l4proto == IPPROTO_UDP) | @@ -182,7 +184,7 @@ int mtk_foe_entry_prepare(struct mtk_eth *eth, struct mtk_foe_entry *entry, entry->ib1 = val; val = FIELD_PREP(MTK_FOE_IB2_DEST_PORT, pse_port) | - FIELD_PREP(MTK_FOE_IB2_PORT_MG, 0x3f) | + FIELD_PREP(MTK_FOE_IB2_PORT_MG, port_mg) | FIELD_PREP(MTK_FOE_IB2_PORT_AG, 0x1f); } @@ -397,6 +399,24 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry, return 0; } +int mtk_foe_entry_set_queue(struct mtk_eth *eth, struct mtk_foe_entry *entry, + unsigned int queue) +{ + u32 *ib2 = mtk_foe_entry_ib2(eth, entry); + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { + *ib2 &= ~MTK_FOE_IB2_QID_V2; + *ib2 |= FIELD_PREP(MTK_FOE_IB2_QID_V2, queue); + *ib2 |= MTK_FOE_IB2_PSE_QOS_V2; + } else { + *ib2 &= ~MTK_FOE_IB2_QID; + *ib2 |= FIELD_PREP(MTK_FOE_IB2_QID, queue); + *ib2 |= MTK_FOE_IB2_PSE_QOS; + } + + return 0; +} + static bool mtk_flow_entry_match(struct mtk_eth *eth, struct mtk_flow_entry *entry, struct mtk_foe_entry *data) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index a09c32539bcc..ea64fac1d425 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -68,7 +68,9 @@ enum { #define MTK_FOE_IB2_DSCP GENMASK(31, 24) /* CONFIG_MEDIATEK_NETSYS_V2 */ +#define MTK_FOE_IB2_QID_V2 GENMASK(6, 0) #define MTK_FOE_IB2_PORT_MG_V2 BIT(7) +#define MTK_FOE_IB2_PSE_QOS_V2 BIT(8) #define MTK_FOE_IB2_DEST_PORT_V2 GENMASK(12, 9) #define MTK_FOE_IB2_MULTICAST_V2 BIT(13) #define MTK_FOE_IB2_WDMA_WINFO_V2 BIT(19) @@ -351,6 +353,8 @@ int mtk_foe_entry_set_pppoe(struct mtk_eth *eth, struct mtk_foe_entry *entry, int sid); int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry, int wdma_idx, int txq, int bss, int wcid); +int mtk_foe_entry_set_queue(struct mtk_eth *eth, struct mtk_foe_entry *entry, + unsigned int queue); int mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_flow_entry *entry); void mtk_foe_entry_clear(struct mtk_ppe *ppe, struct mtk_flow_entry *entry); int mtk_foe_entry_idle_time(struct mtk_ppe *ppe, struct mtk_flow_entry *entry); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index 28bbd1df3e30..81afd5ee3fbf 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -188,7 +188,7 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe, int *wed_index) { struct mtk_wdma_info info = {}; - int pse_port, dsa_port; + int pse_port, dsa_port, queue; if (mtk_flow_get_wdma_info(dev, dest_mac, &info) == 0) { mtk_foe_entry_set_wdma(eth, foe, info.wdma_idx, info.queue, @@ -212,8 +212,6 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe, } dsa_port = mtk_flow_get_dsa_port(&dev); - if (dsa_port >= 0) - mtk_foe_entry_set_dsa(eth, foe, dsa_port); if (dev == eth->netdev[0]) pse_port = 1; @@ -222,6 +220,14 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe, else return -EOPNOTSUPP; + if (dsa_port >= 0) { + mtk_foe_entry_set_dsa(eth, foe, dsa_port); + queue = 3 + dsa_port; + } else { + queue = pse_port - 1; + } + mtk_foe_entry_set_queue(eth, foe, queue); + out: mtk_foe_entry_set_pse_port(eth, foe, pse_port); diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 736839c84130..5c286f2c9418 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -19,110 +19,136 @@ static struct mtk_pcs *pcs_to_mtk_pcs(struct phylink_pcs *pcs) return container_of(pcs, struct mtk_pcs, pcs); } -/* For SGMII interface mode */ -static int mtk_pcs_setup_mode_an(struct mtk_pcs *mpcs) +static void mtk_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { - unsigned int val; - - /* Setup the link timer and QPHY power up inside SGMIISYS */ - regmap_write(mpcs->regmap, SGMSYS_PCS_LINK_TIMER, - SGMII_LINK_TIMER_DEFAULT); - - regmap_read(mpcs->regmap, SGMSYS_SGMII_MODE, &val); - val |= SGMII_REMOTE_FAULT_DIS; - regmap_write(mpcs->regmap, SGMSYS_SGMII_MODE, val); - - regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &val); - val |= SGMII_AN_RESTART; - regmap_write(mpcs->regmap, SGMSYS_PCS_CONTROL_1, val); - - regmap_read(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, &val); - val &= ~SGMII_PHYA_PWD; - regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, val); + struct mtk_pcs *mpcs = pcs_to_mtk_pcs(pcs); + unsigned int bm, adv; - return 0; + /* Read the BMSR and LPA */ + regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &bm); + regmap_read(mpcs->regmap, SGMSYS_PCS_ADVERTISE, &adv); + phylink_mii_c22_pcs_decode_state(state, FIELD_GET(SGMII_BMSR, bm), + FIELD_GET(SGMII_LPA, adv)); } -/* For 1000BASE-X and 2500BASE-X interface modes, which operate at a - * fixed speed. - */ -static int mtk_pcs_setup_mode_force(struct mtk_pcs *mpcs, - phy_interface_t interface) +static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - unsigned int val; + struct mtk_pcs *mpcs = pcs_to_mtk_pcs(pcs); + unsigned int rgc3, sgm_mode, bmcr; + int advertise, link_timer; + bool changed, use_an; - regmap_read(mpcs->regmap, mpcs->ana_rgc3, &val); - val &= ~RG_PHY_SPEED_MASK; if (interface == PHY_INTERFACE_MODE_2500BASEX) - val |= RG_PHY_SPEED_3_125G; - regmap_write(mpcs->regmap, mpcs->ana_rgc3, val); + rgc3 = RG_PHY_SPEED_3_125G; + else + rgc3 = 0; + + advertise = phylink_mii_c22_pcs_encode_advertisement(interface, + advertising); + if (advertise < 0) + return advertise; + + link_timer = phylink_get_link_timer_ns(interface); + if (link_timer < 0) + return link_timer; + + /* Clearing IF_MODE_BIT0 switches the PCS to BASE-X mode, and + * we assume that fixes it's speed at bitrate = line rate (in + * other words, 1000Mbps or 2500Mbps). + */ + if (interface == PHY_INTERFACE_MODE_SGMII) { + sgm_mode = SGMII_IF_MODE_SGMII; + if (phylink_autoneg_inband(mode)) { + sgm_mode |= SGMII_REMOTE_FAULT_DIS | + SGMII_SPEED_DUPLEX_AN; + use_an = true; + } else { + use_an = false; + } + } else if (phylink_autoneg_inband(mode)) { + /* 1000base-X or 2500base-X autoneg */ + sgm_mode = SGMII_REMOTE_FAULT_DIS; + use_an = linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + advertising); + } else { + /* 1000base-X or 2500base-X without autoneg */ + sgm_mode = 0; + use_an = false; + } - /* Disable SGMII AN */ - regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &val); - val &= ~SGMII_AN_ENABLE; - regmap_write(mpcs->regmap, SGMSYS_PCS_CONTROL_1, val); + if (use_an) { + /* FIXME: Do we need to set AN_RESTART here? */ + bmcr = SGMII_AN_RESTART | SGMII_AN_ENABLE; + } else { + bmcr = 0; + } - /* Set the speed etc but leave the duplex unchanged */ - regmap_read(mpcs->regmap, SGMSYS_SGMII_MODE, &val); - val &= SGMII_DUPLEX_FULL | ~SGMII_IF_MODE_MASK; - val |= SGMII_SPEED_1000; - regmap_write(mpcs->regmap, SGMSYS_SGMII_MODE, val); + /* Configure the underlying interface speed */ + regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, + RG_PHY_SPEED_3_125G, rgc3); - /* Release PHYA power down state */ - regmap_read(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, &val); - val &= ~SGMII_PHYA_PWD; - regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, val); + /* Update the advertisement, noting whether it has changed */ + regmap_update_bits_check(mpcs->regmap, SGMSYS_PCS_ADVERTISE, + SGMII_ADVERTISE, advertise, &changed); - return 0; -} + /* Setup the link timer and QPHY power up inside SGMIISYS */ + regmap_write(mpcs->regmap, SGMSYS_PCS_LINK_TIMER, link_timer / 2 / 8); -static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, - const unsigned long *advertising, - bool permit_pause_to_mac) -{ - struct mtk_pcs *mpcs = pcs_to_mtk_pcs(pcs); - int err = 0; + /* Update the sgmsys mode register */ + regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE, + SGMII_REMOTE_FAULT_DIS | SGMII_SPEED_DUPLEX_AN | + SGMII_IF_MODE_SGMII, sgm_mode); + + /* Update the BMCR */ + regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1, + SGMII_AN_RESTART | SGMII_AN_ENABLE, bmcr); - /* Setup SGMIISYS with the determined property */ - if (interface != PHY_INTERFACE_MODE_SGMII) - err = mtk_pcs_setup_mode_force(mpcs, interface); - else if (phylink_autoneg_inband(mode)) - err = mtk_pcs_setup_mode_an(mpcs); + /* Release PHYA power down state */ + regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, + SGMII_PHYA_PWD, 0); - return err; + return changed; } static void mtk_pcs_restart_an(struct phylink_pcs *pcs) { struct mtk_pcs *mpcs = pcs_to_mtk_pcs(pcs); - unsigned int val; - regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &val); - val |= SGMII_AN_RESTART; - regmap_write(mpcs->regmap, SGMSYS_PCS_CONTROL_1, val); + regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1, + SGMII_AN_RESTART, SGMII_AN_RESTART); } static void mtk_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex) { struct mtk_pcs *mpcs = pcs_to_mtk_pcs(pcs); - unsigned int val; - - if (!phy_interface_mode_is_8023z(interface)) - return; - - /* SGMII force duplex setting */ - regmap_read(mpcs->regmap, SGMSYS_SGMII_MODE, &val); - val &= ~SGMII_DUPLEX_FULL; - if (duplex == DUPLEX_FULL) - val |= SGMII_DUPLEX_FULL; - - regmap_write(mpcs->regmap, SGMSYS_SGMII_MODE, val); + unsigned int sgm_mode; + + if (!phylink_autoneg_inband(mode)) { + /* Force the speed and duplex setting */ + if (speed == SPEED_10) + sgm_mode = SGMII_SPEED_10; + else if (speed == SPEED_100) + sgm_mode = SGMII_SPEED_100; + else + sgm_mode = SGMII_SPEED_1000; + + if (duplex == DUPLEX_FULL) + sgm_mode |= SGMII_DUPLEX_FULL; + + regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE, + SGMII_DUPLEX_FULL | SGMII_SPEED_MASK, + sgm_mode); + } } static const struct phylink_pcs_ops mtk_pcs_ops = { + .pcs_get_state = mtk_pcs_get_state, .pcs_config = mtk_pcs_config, .pcs_an_restart = mtk_pcs_restart_an, .pcs_link_up = mtk_pcs_link_up, diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 65e01bf4b4d2..a6271449617f 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -9,6 +9,7 @@ #include <linux/skbuff.h> #include <linux/of_platform.h> #include <linux/of_address.h> +#include <linux/of_reserved_mem.h> #include <linux/mfd/syscon.h> #include <linux/debugfs.h> #include <linux/soc/mediatek/mtk_wed.h> @@ -16,12 +17,14 @@ #include "mtk_wed_regs.h" #include "mtk_wed.h" #include "mtk_ppe.h" +#include "mtk_wed_wo.h" #define MTK_PCIE_BASE(n) (0x1a143000 + (n) * 0x2000) #define MTK_WED_PKT_SIZE 1900 #define MTK_WED_BUF_SIZE 2048 #define MTK_WED_BUF_PER_PAGE (PAGE_SIZE / 2048) +#define MTK_WED_RX_RING_SIZE 1536 #define MTK_WED_TX_RING_SIZE 2048 #define MTK_WED_WDMA_RING_SIZE 1024 @@ -30,6 +33,10 @@ #define MTK_WED_PER_GROUP_PKT 128 #define MTK_WED_FBUF_SIZE 128 +#define MTK_WED_MIOD_CNT 16 +#define MTK_WED_FB_CMD_CNT 1024 +#define MTK_WED_RRO_QUE_CNT 8192 +#define MTK_WED_MIOD_ENTRY_CNT 128 static struct mtk_wed_hw *hw_list[2]; static DEFINE_MUTEX(hw_lock); @@ -64,12 +71,81 @@ wdma_set(struct mtk_wed_device *dev, u32 reg, u32 mask) wdma_m32(dev, reg, 0, mask); } +static void +wdma_clr(struct mtk_wed_device *dev, u32 reg, u32 mask) +{ + wdma_m32(dev, reg, mask, 0); +} + +static u32 +wifi_r32(struct mtk_wed_device *dev, u32 reg) +{ + return readl(dev->wlan.base + reg); +} + +static void +wifi_w32(struct mtk_wed_device *dev, u32 reg, u32 val) +{ + writel(val, dev->wlan.base + reg); +} + static u32 mtk_wed_read_reset(struct mtk_wed_device *dev) { return wed_r32(dev, MTK_WED_RESET); } +static u32 +mtk_wdma_read_reset(struct mtk_wed_device *dev) +{ + return wdma_r32(dev, MTK_WDMA_GLO_CFG); +} + +static int +mtk_wdma_rx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_RX_DMA_BUSY; + int i, ret; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_DMA_EN); + ret = readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 10000); + if (ret) + dev_err(dev->hw->dev, "rx reset failed\n"); + + wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX); + wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) { + if (dev->rx_wdma[i].desc) + continue; + + wdma_w32(dev, + MTK_WDMA_RING_RX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); + } + + return ret; +} + +static void +mtk_wdma_tx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_TX_DMA_BUSY; + int i; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN); + if (readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 10000)) + dev_err(dev->hw->dev, "tx reset failed\n"); + + wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_TX); + wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + + for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) + wdma_w32(dev, + MTK_WDMA_RING_TX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); +} + static void mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) { @@ -81,6 +157,55 @@ mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) WARN_ON_ONCE(1); } +static u32 +mtk_wed_wo_read_status(struct mtk_wed_device *dev) +{ + return wed_r32(dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_WO_STATUS); +} + +static void +mtk_wed_wo_reset(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + u8 state = MTK_WED_WO_STATE_DISABLE; + void __iomem *reg; + u32 val; + + mtk_wdma_tx_reset(dev); + mtk_wed_reset(dev, MTK_WED_RESET_WED); + + if (mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_CHANGE_STATE, &state, + sizeof(state), false)) + return; + + if (readx_poll_timeout(mtk_wed_wo_read_status, dev, val, + val == MTK_WED_WOIF_DISABLE_DONE, + 100, MTK_WOCPU_TIMEOUT)) + dev_err(dev->hw->dev, "failed to disable wed-wo\n"); + + reg = ioremap(MTK_WED_WO_CPU_MCUSYS_RESET_ADDR, 4); + + val = readl(reg); + switch (dev->hw->index) { + case 0: + val |= MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + break; + case 1: + val |= MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + break; + default: + break; + } + iounmap(reg); +} + static struct mtk_wed_hw * mtk_wed_assign(struct mtk_wed_device *dev) { @@ -115,7 +240,7 @@ out: } static int -mtk_wed_buffer_alloc(struct mtk_wed_device *dev) +mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev) { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; @@ -132,16 +257,16 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) if (!page_list) return -ENOMEM; - dev->buf_ring.size = ring_size; - dev->buf_ring.pages = page_list; + dev->tx_buf_ring.size = ring_size; + dev->tx_buf_ring.pages = page_list; desc = dma_alloc_coherent(dev->hw->dev, ring_size * sizeof(*desc), &desc_phys, GFP_KERNEL); if (!desc) return -ENOMEM; - dev->buf_ring.desc = desc; - dev->buf_ring.desc_phys = desc_phys; + dev->tx_buf_ring.desc = desc; + dev->tx_buf_ring.desc_phys = desc_phys; for (i = 0, page_idx = 0; i < ring_size; i += MTK_WED_BUF_PER_PAGE) { dma_addr_t page_phys, buf_phys; @@ -202,10 +327,10 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) } static void -mtk_wed_free_buffer(struct mtk_wed_device *dev) +mtk_wed_free_tx_buffer(struct mtk_wed_device *dev) { - struct mtk_wdma_desc *desc = dev->buf_ring.desc; - void **page_list = dev->buf_ring.pages; + struct mtk_wdma_desc *desc = dev->tx_buf_ring.desc; + void **page_list = dev->tx_buf_ring.pages; int page_idx; int i; @@ -215,7 +340,8 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) if (!desc) goto free_pagelist; - for (i = 0, page_idx = 0; i < dev->buf_ring.size; i += MTK_WED_BUF_PER_PAGE) { + for (i = 0, page_idx = 0; i < dev->tx_buf_ring.size; + i += MTK_WED_BUF_PER_PAGE) { void *page = page_list[page_idx++]; dma_addr_t buf_addr; @@ -228,13 +354,59 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) __free_page(page); } - dma_free_coherent(dev->hw->dev, dev->buf_ring.size * sizeof(*desc), - desc, dev->buf_ring.desc_phys); + dma_free_coherent(dev->hw->dev, dev->tx_buf_ring.size * sizeof(*desc), + desc, dev->tx_buf_ring.desc_phys); free_pagelist: kfree(page_list); } +static int +mtk_wed_rx_buffer_alloc(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc; + dma_addr_t desc_phys; + + dev->rx_buf_ring.size = dev->wlan.rx_nbuf; + desc = dma_alloc_coherent(dev->hw->dev, + dev->wlan.rx_nbuf * sizeof(*desc), + &desc_phys, GFP_KERNEL); + if (!desc) + return -ENOMEM; + + dev->rx_buf_ring.desc = desc; + dev->rx_buf_ring.desc_phys = desc_phys; + dev->wlan.init_rx_buf(dev, dev->wlan.rx_npkt); + + return 0; +} + +static void +mtk_wed_free_rx_buffer(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc = dev->rx_buf_ring.desc; + + if (!desc) + return; + + dev->wlan.release_rx_buf(dev); + dma_free_coherent(dev->hw->dev, dev->rx_buf_ring.size * sizeof(*desc), + desc, dev->rx_buf_ring.desc_phys); +} + +static void +mtk_wed_rx_buffer_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RX_BM_RX_DMAD, + FIELD_PREP(MTK_WED_RX_BM_RX_DMAD_SDL0, dev->wlan.rx_size)); + wed_w32(dev, MTK_WED_RX_BM_BASE, dev->rx_buf_ring.desc_phys); + wed_w32(dev, MTK_WED_RX_BM_INIT_PTR, MTK_WED_RX_BM_INIT_SW_TAIL | + FIELD_PREP(MTK_WED_RX_BM_SW_TAIL, dev->wlan.rx_npkt)); + wed_w32(dev, MTK_WED_RX_BM_DYN_ALLOC_TH, + FIELD_PREP(MTK_WED_RX_BM_DYN_ALLOC_TH_H, 0xffff)); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); +} + static void mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) { @@ -246,14 +418,21 @@ mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) } static void +mtk_wed_free_rx_rings(struct mtk_wed_device *dev) +{ + mtk_wed_free_rx_buffer(dev); + mtk_wed_free_ring(dev, &dev->rro.ring); +} + +static void mtk_wed_free_tx_rings(struct mtk_wed_device *dev) { int i; for (i = 0; i < ARRAY_SIZE(dev->tx_ring); i++) mtk_wed_free_ring(dev, &dev->tx_ring[i]); - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - mtk_wed_free_ring(dev, &dev->tx_wdma[i]); + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + mtk_wed_free_ring(dev, &dev->rx_wdma[i]); } static void @@ -290,6 +469,38 @@ mtk_wed_set_512_support(struct mtk_wed_device *dev, bool enable) } } +#define MTK_WFMDA_RX_DMA_EN BIT(2) +static void +mtk_wed_check_wfdma_rx_fill(struct mtk_wed_device *dev, int idx) +{ + u32 val; + int i; + + if (!(dev->rx_ring[idx].flags & MTK_WED_RING_CONFIGURED)) + return; /* queue is not configured by mt76 */ + + for (i = 0; i < 3; i++) { + u32 cur_idx; + + cur_idx = wed_r32(dev, + MTK_WED_WPDMA_RING_RX_DATA(idx) + + MTK_WED_RING_OFS_CPU_IDX); + if (cur_idx == MTK_WED_RX_RING_SIZE - 1) + break; + + usleep_range(100000, 200000); + } + + if (i == 3) { + dev_err(dev->hw->dev, "rx dma enable failed\n"); + return; + } + + val = wifi_r32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base) | + MTK_WFMDA_RX_DMA_EN; + wifi_w32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base, val); +} + static void mtk_wed_dma_disable(struct mtk_wed_device *dev) { @@ -303,59 +514,88 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) MTK_WED_GLO_CFG_TX_DMA_EN | MTK_WED_GLO_CFG_RX_DMA_EN); - wdma_m32(dev, MTK_WDMA_GLO_CFG, + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN | MTK_WDMA_GLO_CFG_RX_INFO1_PRERES | - MTK_WDMA_GLO_CFG_RX_INFO2_PRERES, 0); + MTK_WDMA_GLO_CFG_RX_INFO2_PRERES); if (dev->hw->version == 1) { regmap_write(dev->hw->mirror, dev->hw->index * 4, 0); - wdma_m32(dev, MTK_WDMA_GLO_CFG, - MTK_WDMA_GLO_CFG_RX_INFO3_PRERES, 0); + wdma_clr(dev, MTK_WDMA_GLO_CFG, + MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); - mtk_wed_set_512_support(dev, false); + wed_clr(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN); + wed_clr(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); } + + mtk_wed_set_512_support(dev, false); } static void mtk_wed_stop(struct mtk_wed_device *dev) { - mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); - wed_clr(dev, MTK_WED_CTRL, - MTK_WED_CTRL_WDMA_INT_AGENT_EN | - MTK_WED_CTRL_WPDMA_INT_AGENT_EN | - MTK_WED_CTRL_WED_TX_BM_EN | - MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); + + if (dev->hw->version == 1) + return; + + wed_w32(dev, MTK_WED_EXT_INT_MASK1, 0); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, 0); } static void -mtk_wed_detach(struct mtk_wed_device *dev) +mtk_wed_deinit(struct mtk_wed_device *dev) { - struct mtk_wed_hw *hw = dev->hw; + mtk_wed_stop(dev); + mtk_wed_dma_disable(dev); - mutex_lock(&hw_lock); + wed_clr(dev, MTK_WED_CTRL, + MTK_WED_CTRL_WDMA_INT_AGENT_EN | + MTK_WED_CTRL_WPDMA_INT_AGENT_EN | + MTK_WED_CTRL_WED_TX_BM_EN | + MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); - mtk_wed_stop(dev); + if (dev->hw->version == 1) + return; - wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX); - wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + wed_clr(dev, MTK_WED_CTRL, + MTK_WED_CTRL_RX_ROUTE_QM_EN | + MTK_WED_CTRL_WED_RX_BM_EN | + MTK_WED_CTRL_RX_RRO_QM_EN); +} - mtk_wed_reset(dev, MTK_WED_RESET_WED); +static void +__mtk_wed_detach(struct mtk_wed_device *dev) +{ + struct mtk_wed_hw *hw = dev->hw; + + mtk_wed_deinit(dev); - mtk_wed_free_buffer(dev); + mtk_wdma_rx_reset(dev); + mtk_wed_reset(dev, MTK_WED_RESET_WED); + mtk_wed_free_tx_buffer(dev); mtk_wed_free_tx_rings(dev); + if (mtk_wed_get_rx_capa(dev)) { + if (hw->wed_wo) + mtk_wed_wo_reset(dev); + mtk_wed_free_rx_rings(dev); + if (hw->wed_wo) + mtk_wed_wo_deinit(hw); + } + if (dev->wlan.bus_type == MTK_WED_BUS_PCIE) { struct device_node *wlan_node; @@ -373,6 +613,13 @@ mtk_wed_detach(struct mtk_wed_device *dev) module_put(THIS_MODULE); hw->wed_dev = NULL; +} + +static void +mtk_wed_detach(struct mtk_wed_device *dev) +{ + mutex_lock(&hw_lock); + __mtk_wed_detach(dev); mutex_unlock(&hw_lock); } @@ -431,10 +678,12 @@ mtk_wed_set_wpdma(struct mtk_wed_device *dev) } else { mtk_wed_bus_init(dev); - wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); - wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); + wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_RX_GLO_CFG, dev->wlan.wpdma_rx_glo); + wed_w32(dev, MTK_WED_WPDMA_RX_RING, dev->wlan.wpdma_rx); } } @@ -443,7 +692,7 @@ mtk_wed_hw_init_early(struct mtk_wed_device *dev) { u32 mask, set; - mtk_wed_stop(dev); + mtk_wed_deinit(dev); mtk_wed_reset(dev, MTK_WED_RESET_WED); mtk_wed_set_wpdma(dev); @@ -484,6 +733,132 @@ mtk_wed_hw_init_early(struct mtk_wed_device *dev) } } +static int +mtk_wed_rro_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, + int size) +{ + ring->desc = dma_alloc_coherent(dev->hw->dev, + size * sizeof(*ring->desc), + &ring->desc_phys, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_size = sizeof(*ring->desc); + ring->size = size; + memset(ring->desc, 0, size); + + return 0; +} + +#define MTK_WED_MIOD_COUNT (MTK_WED_MIOD_ENTRY_CNT * MTK_WED_MIOD_CNT) +static int +mtk_wed_rro_alloc(struct mtk_wed_device *dev) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(dev->hw->node, "memory-region-names", + "wo-dlm"); + if (index < 0) + return index; + + np = of_parse_phandle(dev->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + dev->rro.miod_phys = rmem->base; + dev->rro.fdbk_phys = MTK_WED_MIOD_COUNT + dev->rro.miod_phys; + + return mtk_wed_rro_ring_alloc(dev, &dev->rro.ring, + MTK_WED_RRO_QUE_CNT); +} + +static int +mtk_wed_rro_cfg(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + struct { + struct { + __le32 base; + __le32 cnt; + __le32 unit; + } ring[2]; + __le32 wed; + u8 version; + } req = { + .ring[0] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE), + .cnt = cpu_to_le32(MTK_WED_MIOD_CNT), + .unit = cpu_to_le32(MTK_WED_MIOD_ENTRY_CNT), + }, + .ring[1] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE + + MTK_WED_MIOD_COUNT), + .cnt = cpu_to_le32(MTK_WED_FB_CMD_CNT), + .unit = cpu_to_le32(4), + }, + }; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_WED_CFG, + &req, sizeof(req), true); +} + +static void +mtk_wed_rro_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RROQM_MIOD_CFG, + FIELD_PREP(MTK_WED_RROQM_MIOD_MID_DW, 0x70 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_MOD_DW, 0x10 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_ENTRY_DW, + MTK_WED_MIOD_ENTRY_CNT >> 2)); + + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL0, dev->rro.miod_phys); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL1, + FIELD_PREP(MTK_WED_RROQM_MIOD_CNT, MTK_WED_MIOD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL0, dev->rro.fdbk_phys); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL1, + FIELD_PREP(MTK_WED_RROQM_FDBK_CNT, MTK_WED_FB_CMD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL2, 0); + wed_w32(dev, MTK_WED_RROQ_BASE_L, dev->rro.ring.desc_phys); + + wed_set(dev, MTK_WED_RROQM_RST_IDX, + MTK_WED_RROQM_RST_IDX_MIOD | + MTK_WED_RROQM_RST_IDX_FDBK); + + wed_w32(dev, MTK_WED_RROQM_RST_IDX, 0); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL2, MTK_WED_MIOD_CNT - 1); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_RRO_QM_EN); +} + +static void +mtk_wed_route_qm_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RESET, MTK_WED_RESET_RX_ROUTE_QM); + + for (;;) { + usleep_range(100, 200); + if (!(wed_r32(dev, MTK_WED_RESET) & MTK_WED_RESET_RX_ROUTE_QM)) + break; + } + + /* configure RX_ROUTE_QM */ + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_TXDMAD_FPORT); + wed_set(dev, MTK_WED_RTQM_GLO_CFG, + FIELD_PREP(MTK_WED_RTQM_TXDMAD_FPORT, 0x3 + dev->hw->index)); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + /* enable RX_ROUTE_QM */ + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_ROUTE_QM_EN); +} + static void mtk_wed_hw_init(struct mtk_wed_device *dev) { @@ -495,11 +870,11 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_BM_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_BM_CTRL_RSV_GRP_NUM, MTK_WED_TX_RING_SIZE / 256)); - wed_w32(dev, MTK_WED_TX_BM_BASE, dev->buf_ring.desc_phys); + wed_w32(dev, MTK_WED_TX_BM_BASE, dev->tx_buf_ring.desc_phys); wed_w32(dev, MTK_WED_TX_BM_BUF_LEN, MTK_WED_PKT_SIZE); @@ -526,9 +901,9 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_TKID_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_TKID_CTRL_RSV_GRP_NUM, - dev->buf_ring.size / 128)); + dev->tx_buf_ring.size / 128)); wed_w32(dev, MTK_WED_TX_TKID_DYN_THR, FIELD_PREP(MTK_WED_TX_TKID_DYN_THR_LO, 0) | MTK_WED_TX_TKID_DYN_THR_HI); @@ -536,18 +911,28 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) mtk_wed_reset(dev, MTK_WED_RESET_TX_BM); - if (dev->hw->version == 1) + if (dev->hw->version == 1) { wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_TX_BM_EN | MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); - else + } else { wed_clr(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE); + /* rx hw init */ + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, + MTK_WED_WPDMA_RX_D_RST_CRX_IDX | + MTK_WED_WPDMA_RX_D_RST_DRV_IDX); + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, 0); + + mtk_wed_rx_buffer_hw_init(dev); + mtk_wed_rro_hw_init(dev); + mtk_wed_route_qm_hw_init(dev); + } wed_clr(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE); } static void -mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) +mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size, bool tx) { void *head = (void *)ring->desc; int i; @@ -557,49 +942,140 @@ mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) desc = (struct mtk_wdma_desc *)(head + i * ring->desc_size); desc->buf0 = 0; - desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + if (tx) + desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + else + desc->ctrl = cpu_to_le32(MTK_WFDMA_DESC_CTRL_TO_HOST); desc->buf1 = 0; desc->info = 0; } } static u32 -mtk_wed_check_busy(struct mtk_wed_device *dev) +mtk_wed_check_busy(struct mtk_wed_device *dev, u32 reg, u32 mask) { - if (wed_r32(dev, MTK_WED_GLO_CFG) & MTK_WED_GLO_CFG_TX_DMA_BUSY) - return true; - - if (wed_r32(dev, MTK_WED_WPDMA_GLO_CFG) & - MTK_WED_WPDMA_GLO_CFG_TX_DRV_BUSY) - return true; - - if (wed_r32(dev, MTK_WED_CTRL) & MTK_WED_CTRL_WDMA_INT_AGENT_BUSY) - return true; - - if (wed_r32(dev, MTK_WED_WDMA_GLO_CFG) & - MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY) - return true; - - if (wdma_r32(dev, MTK_WDMA_GLO_CFG) & - MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY) - return true; - - if (wed_r32(dev, MTK_WED_CTRL) & - (MTK_WED_CTRL_WED_TX_BM_BUSY | MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY)) - return true; - - return false; + return !!(wed_r32(dev, reg) & mask); } static int -mtk_wed_poll_busy(struct mtk_wed_device *dev) +mtk_wed_poll_busy(struct mtk_wed_device *dev, u32 reg, u32 mask) { int sleep = 15000; int timeout = 100 * sleep; u32 val; return read_poll_timeout(mtk_wed_check_busy, val, !val, sleep, - timeout, false, dev); + timeout, false, dev, reg, mask); +} + +static int +mtk_wed_rx_reset(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + u8 val = MTK_WED_WO_STATE_SER_RESET; + int i, ret; + + ret = mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_CHANGE_STATE, &val, + sizeof(val), true); + if (ret) + return ret; + + wed_clr(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, MTK_WED_WPDMA_RX_D_RX_DRV_EN); + ret = mtk_wed_poll_busy(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_BUSY); + if (ret) { + mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_INT_AGENT); + mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_RX_D_DRV); + } else { + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, + MTK_WED_WPDMA_RX_D_RST_CRX_IDX | + MTK_WED_WPDMA_RX_D_RST_DRV_IDX); + + wed_set(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RST_INIT_COMPLETE | + MTK_WED_WPDMA_RX_D_FSM_RETURN_IDLE); + wed_clr(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RST_INIT_COMPLETE | + MTK_WED_WPDMA_RX_D_FSM_RETURN_IDLE); + + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, 0); + } + + /* reset rro qm */ + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_RRO_QM_EN); + ret = mtk_wed_poll_busy(dev, MTK_WED_CTRL, + MTK_WED_CTRL_RX_RRO_QM_BUSY); + if (ret) { + mtk_wed_reset(dev, MTK_WED_RESET_RX_RRO_QM); + } else { + wed_set(dev, MTK_WED_RROQM_RST_IDX, + MTK_WED_RROQM_RST_IDX_MIOD | + MTK_WED_RROQM_RST_IDX_FDBK); + wed_w32(dev, MTK_WED_RROQM_RST_IDX, 0); + } + + /* reset route qm */ + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_ROUTE_QM_EN); + ret = mtk_wed_poll_busy(dev, MTK_WED_CTRL, + MTK_WED_CTRL_RX_ROUTE_QM_BUSY); + if (ret) + mtk_wed_reset(dev, MTK_WED_RESET_RX_ROUTE_QM); + else + wed_set(dev, MTK_WED_RTQM_GLO_CFG, + MTK_WED_RTQM_Q_RST); + + /* reset tx wdma */ + mtk_wdma_tx_reset(dev); + + /* reset tx wdma drv */ + wed_clr(dev, MTK_WED_WDMA_GLO_CFG, MTK_WED_WDMA_GLO_CFG_TX_DRV_EN); + mtk_wed_poll_busy(dev, MTK_WED_CTRL, + MTK_WED_CTRL_WDMA_INT_AGENT_BUSY); + mtk_wed_reset(dev, MTK_WED_RESET_WDMA_TX_DRV); + + /* reset wed rx dma */ + ret = mtk_wed_poll_busy(dev, MTK_WED_GLO_CFG, + MTK_WED_GLO_CFG_RX_DMA_BUSY); + wed_clr(dev, MTK_WED_GLO_CFG, MTK_WED_GLO_CFG_RX_DMA_EN); + if (ret) { + mtk_wed_reset(dev, MTK_WED_RESET_WED_RX_DMA); + } else { + struct mtk_eth *eth = dev->hw->eth; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + wed_set(dev, MTK_WED_RESET_IDX, + MTK_WED_RESET_IDX_RX_V2); + else + wed_set(dev, MTK_WED_RESET_IDX, MTK_WED_RESET_IDX_RX); + wed_w32(dev, MTK_WED_RESET_IDX, 0); + } + + /* reset rx bm */ + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); + mtk_wed_poll_busy(dev, MTK_WED_CTRL, + MTK_WED_CTRL_WED_RX_BM_BUSY); + mtk_wed_reset(dev, MTK_WED_RESET_RX_BM); + + /* wo change to enable state */ + val = MTK_WED_WO_STATE_ENABLE; + ret = mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_CHANGE_STATE, &val, + sizeof(val), true); + if (ret) + return ret; + + /* wed_rx_ring_reset */ + for (i = 0; i < ARRAY_SIZE(dev->rx_ring); i++) { + if (!dev->rx_ring[i].desc) + continue; + + mtk_wed_ring_reset(&dev->rx_ring[i], MTK_WED_RX_RING_SIZE, + false); + } + mtk_wed_free_rx_buffer(dev); + + return 0; } static void @@ -613,23 +1089,27 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) if (!dev->tx_ring[i].desc) continue; - mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE); + mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE, + true); } - if (mtk_wed_poll_busy(dev)) - busy = mtk_wed_check_busy(dev); - + /* 1. reset WED tx DMA */ + wed_clr(dev, MTK_WED_GLO_CFG, MTK_WED_GLO_CFG_TX_DMA_EN); + busy = mtk_wed_poll_busy(dev, MTK_WED_GLO_CFG, + MTK_WED_GLO_CFG_TX_DMA_BUSY); if (busy) { mtk_wed_reset(dev, MTK_WED_RESET_WED_TX_DMA); } else { - wed_w32(dev, MTK_WED_RESET_IDX, - MTK_WED_RESET_IDX_TX | - MTK_WED_RESET_IDX_RX); + wed_w32(dev, MTK_WED_RESET_IDX, MTK_WED_RESET_IDX_TX); wed_w32(dev, MTK_WED_RESET_IDX, 0); } - wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX); - wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + /* 2. reset WDMA rx DMA */ + busy = !!mtk_wdma_rx_reset(dev); + wed_clr(dev, MTK_WED_WDMA_GLO_CFG, MTK_WED_WDMA_GLO_CFG_RX_DRV_EN); + if (!busy) + busy = mtk_wed_poll_busy(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY); if (busy) { mtk_wed_reset(dev, MTK_WED_RESET_WDMA_INT_AGENT); @@ -646,6 +1126,9 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) MTK_WED_WDMA_GLO_CFG_RST_INIT_COMPLETE); } + /* 3. reset WED WPDMA tx */ + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); + for (i = 0; i < 100; i++) { val = wed_r32(dev, MTK_WED_TX_BM_INTF); if (FIELD_GET(MTK_WED_TX_BM_INTF_TKFIFO_FDEP, val) == 0x40) @@ -653,8 +1136,19 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) } mtk_wed_reset(dev, MTK_WED_RESET_TX_FREE_AGENT); + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_TX_BM_EN); mtk_wed_reset(dev, MTK_WED_RESET_TX_BM); + /* 4. reset WED WPDMA tx */ + busy = mtk_wed_poll_busy(dev, MTK_WED_WPDMA_GLO_CFG, + MTK_WED_WPDMA_GLO_CFG_TX_DRV_BUSY); + wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, + MTK_WED_WPDMA_GLO_CFG_TX_DRV_EN | + MTK_WED_WPDMA_GLO_CFG_RX_DRV_EN); + if (!busy) + busy = mtk_wed_poll_busy(dev, MTK_WED_WPDMA_GLO_CFG, + MTK_WED_WPDMA_GLO_CFG_RX_DRV_BUSY); + if (busy) { mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_INT_AGENT); mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_TX_DRV); @@ -666,11 +1160,21 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_WPDMA_RESET_IDX, 0); } + dev->init_done = false; + if (dev->hw->version == 1) + return; + + if (!busy) { + wed_w32(dev, MTK_WED_RESET_IDX, MTK_WED_RESET_WPDMA_IDX_RX); + wed_w32(dev, MTK_WED_RESET_IDX, 0); + } + + mtk_wed_rx_reset(dev); } static int mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, - int size, u32 desc_size) + int size, u32 desc_size, bool tx) { ring->desc = dma_alloc_coherent(dev->hw->dev, size * desc_size, &ring->desc_phys, GFP_KERNEL); @@ -679,18 +1183,24 @@ mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, ring->desc_size = desc_size; ring->size = size; - mtk_wed_ring_reset(ring, size); + mtk_wed_ring_reset(ring, size, tx); return 0; } static int -mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size) +mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size, + bool reset) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; - struct mtk_wed_ring *wdma = &dev->tx_wdma[idx]; + struct mtk_wed_ring *wdma; + + if (idx >= ARRAY_SIZE(dev->rx_wdma)) + return -EINVAL; - if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size)) + wdma = &dev->rx_wdma[idx]; + if (!reset && mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, + desc_size, true)) return -ENOMEM; wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE, @@ -707,6 +1217,64 @@ mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size) return 0; } +static int +mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size, + bool reset) +{ + u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; + struct mtk_wed_ring *wdma; + + if (idx >= ARRAY_SIZE(dev->tx_wdma)) + return -EINVAL; + + wdma = &dev->tx_wdma[idx]; + if (!reset && mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, + desc_size, true)) + return -ENOMEM; + + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_COUNT, + size); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_DMA_IDX, 0); + + if (reset) + mtk_wed_ring_reset(wdma, MTK_WED_WDMA_RING_SIZE, true); + + if (!idx) { + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_COUNT, + size); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_CPU_IDX, + 0); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_DMA_IDX, + 0); + } + + return 0; +} + +static void +mtk_wed_ppe_check(struct mtk_wed_device *dev, struct sk_buff *skb, + u32 reason, u32 hash) +{ + struct mtk_eth *eth = dev->hw->eth; + struct ethhdr *eh; + + if (!skb) + return; + + if (reason != MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) + return; + + skb_set_mac_header(skb, 0); + eh = eth_hdr(skb); + skb->protocol = eh->h_proto; + mtk_ppe_check_skb(eth->ppe[dev->hw->index], skb, hash); +} + static void mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) { @@ -729,6 +1297,8 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) wed_clr(dev, MTK_WED_WDMA_INT_CTRL, wdma_mask); } else { + wdma_mask |= FIELD_PREP(MTK_WDMA_INT_MASK_TX_DONE, + GENMASK(1, 0)); /* initail tx interrupt trigger */ wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX, MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN | @@ -747,6 +1317,16 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_TRIG, dev->wlan.txfree_tbit)); + wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_RX, + MTK_WED_WPDMA_INT_CTRL_RX0_EN | + MTK_WED_WPDMA_INT_CTRL_RX0_CLR | + MTK_WED_WPDMA_INT_CTRL_RX1_EN | + MTK_WED_WPDMA_INT_CTRL_RX1_CLR | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG, + dev->wlan.rx_tbit[0]) | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG, + dev->wlan.rx_tbit[1])); + wed_w32(dev, MTK_WED_WDMA_INT_CLR, wdma_mask); wed_set(dev, MTK_WED_WDMA_INT_CTRL, FIELD_PREP(MTK_WED_WDMA_INT_CTRL_POLL_SRC_SEL, @@ -784,9 +1364,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { + int i; + wed_set(dev, MTK_WED_WPDMA_CTRL, MTK_WED_WPDMA_CTRL_SDL1_FIXED); + wed_set(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DRV_EN | + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); + wed_set(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); @@ -794,6 +1380,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_TX_TKID_KEEP | MTK_WED_WPDMA_GLO_CFG_TX_DMAD_DW3_PREV); + + wed_set(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN | + FIELD_PREP(MTK_WED_WPDMA_RX_D_RXD_READ_LEN, 0x18) | + FIELD_PREP(MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL, + 0x2)); + + for (i = 0; i < MTK_WED_RX_QUEUES; i++) + mtk_wed_check_wfdma_rx_fill(dev, i); } } @@ -802,9 +1397,12 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) { int i; - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - if (!dev->tx_wdma[i].desc) - mtk_wed_wdma_ring_setup(dev, i, 16); + if (mtk_wed_get_rx_capa(dev) && mtk_wed_rx_buffer_alloc(dev)) + return; + + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + if (!dev->rx_wdma[i].desc) + mtk_wed_wdma_rx_ring_setup(dev, i, 16, false); mtk_wed_hw_init(dev); mtk_wed_configure_irq(dev, irq_mask); @@ -819,9 +1417,22 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) val |= BIT(0) | (BIT(1) * !!dev->hw->index); regmap_write(dev->hw->mirror, dev->hw->index * 4, val); } else { - mtk_wed_set_512_support(dev, true); + /* driver set mid ready and only once */ + wed_w32(dev, MTK_WED_EXT_INT_MASK1, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + + wed_r32(dev, MTK_WED_EXT_INT_MASK1); + wed_r32(dev, MTK_WED_EXT_INT_MASK2); + + if (mtk_wed_rro_cfg(dev)) + return; + } + mtk_wed_set_512_support(dev, dev->wlan.wcid_512); + mtk_wed_dma_enable(dev); dev->running = true; } @@ -853,7 +1464,7 @@ mtk_wed_attach(struct mtk_wed_device *dev) if (!hw) { module_put(THIS_MODULE); ret = -ENODEV; - goto out; + goto unlock; } device = dev->wlan.bus_type == MTK_WED_BUS_PCIE @@ -866,30 +1477,44 @@ mtk_wed_attach(struct mtk_wed_device *dev) dev->dev = hw->dev; dev->irq = hw->irq; dev->wdma_idx = hw->index; + dev->version = hw->version; if (hw->eth->dma_dev == hw->eth->dev && of_dma_is_coherent(hw->eth->dev->of_node)) mtk_eth_set_dma_device(hw->eth, hw->dev); - ret = mtk_wed_buffer_alloc(dev); - if (ret) { - mtk_wed_detach(dev); + ret = mtk_wed_tx_buffer_alloc(dev); + if (ret) goto out; + + if (mtk_wed_get_rx_capa(dev)) { + ret = mtk_wed_rro_alloc(dev); + if (ret) + goto out; } mtk_wed_hw_init_early(dev); - if (hw->hifsys) + if (hw->version == 1) { regmap_update_bits(hw->hifsys, HIFSYS_DMA_AG_MAP, BIT(hw->index), 0); - + } else { + dev->rev_id = wed_r32(dev, MTK_WED_REV_ID); + ret = mtk_wed_wo_init(hw); + } out: + if (ret) { + dev_err(dev->hw->dev, "failed to attach wed device\n"); + __mtk_wed_detach(dev); + } +unlock: mutex_unlock(&hw_lock); return ret; } static int -mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) +mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs, + bool reset) { struct mtk_wed_ring *ring = &dev->tx_ring[idx]; @@ -905,13 +1530,15 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) * WDMA RX. */ - BUG_ON(idx >= ARRAY_SIZE(dev->tx_ring)); + if (WARN_ON(idx >= ARRAY_SIZE(dev->tx_ring))) + return -EINVAL; - if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, - sizeof(*ring->desc))) + if (!reset && mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, + sizeof(*ring->desc), true)) return -ENOMEM; - if (mtk_wed_wdma_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE, + reset)) return -ENOMEM; ring->reg_base = MTK_WED_RING_TX(idx); @@ -955,6 +1582,39 @@ mtk_wed_txfree_ring_setup(struct mtk_wed_device *dev, void __iomem *regs) return 0; } +static int +mtk_wed_rx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs, + bool reset) +{ + struct mtk_wed_ring *ring = &dev->rx_ring[idx]; + + if (WARN_ON(idx >= ARRAY_SIZE(dev->rx_ring))) + return -EINVAL; + + if (!reset && mtk_wed_ring_alloc(dev, ring, MTK_WED_RX_RING_SIZE, + sizeof(*ring->desc), false)) + return -ENOMEM; + + if (mtk_wed_wdma_tx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE, + reset)) + return -ENOMEM; + + ring->reg_base = MTK_WED_RING_RX_DATA(idx); + ring->wpdma = regs; + ring->flags |= MTK_WED_RING_CONFIGURED; + + /* WPDMA -> WED */ + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_BASE, ring->desc_phys); + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_COUNT, MTK_WED_RX_RING_SIZE); + + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_BASE, + ring->desc_phys); + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_COUNT, + MTK_WED_RX_RING_SIZE); + + return 0; +} + static u32 mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) { @@ -1051,7 +1711,9 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, static const struct mtk_wed_ops wed_ops = { .attach = mtk_wed_attach, .tx_ring_setup = mtk_wed_tx_ring_setup, + .rx_ring_setup = mtk_wed_rx_ring_setup, .txfree_ring_setup = mtk_wed_txfree_ring_setup, + .msg_update = mtk_wed_mcu_msg_update, .start = mtk_wed_start, .stop = mtk_wed_stop, .reset_dma = mtk_wed_reset_dma, @@ -1060,6 +1722,7 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, .irq_get = mtk_wed_irq_get, .irq_set_mask = mtk_wed_irq_set_mask, .detach = mtk_wed_detach, + .ppe_check = mtk_wed_ppe_check, }; struct device_node *eth_np = eth->dev->of_node; struct platform_device *pdev; diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h index ae420ca01a48..e012b8a82133 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.h +++ b/drivers/net/ethernet/mediatek/mtk_wed.h @@ -10,6 +10,7 @@ #include <linux/netdevice.h> struct mtk_eth; +struct mtk_wed_wo; struct mtk_wed_hw { struct device_node *node; @@ -22,6 +23,7 @@ struct mtk_wed_hw { struct regmap *mirror; struct dentry *debugfs_dir; struct mtk_wed_device *wed_dev; + struct mtk_wed_wo *wed_wo; u32 debugfs_reg; u32 num_flows; u8 version; @@ -85,6 +87,24 @@ wpdma_tx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) } static inline u32 +wpdma_rx_r32(struct mtk_wed_device *dev, int ring, u32 reg) +{ + if (!dev->rx_ring[ring].wpdma) + return 0; + + return readl(dev->rx_ring[ring].wpdma + reg); +} + +static inline void +wpdma_rx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) +{ + if (!dev->rx_ring[ring].wpdma) + return; + + writel(val, dev->rx_ring[ring].wpdma + reg); +} + +static inline u32 wpdma_txfree_r32(struct mtk_wed_device *dev, u32 reg) { if (!dev->txfree_ring.wpdma) @@ -126,6 +146,7 @@ static inline int mtk_wed_flow_add(int index) static inline void mtk_wed_flow_remove(int index) { } + #endif #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c index f420f187e837..56f663439721 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */ #include <linux/seq_file.h> +#include <linux/soc/mediatek/mtk_wed.h> #include "mtk_wed.h" #include "mtk_wed_regs.h" @@ -18,6 +19,8 @@ enum { DUMP_TYPE_WDMA, DUMP_TYPE_WPDMA_TX, DUMP_TYPE_WPDMA_TXFREE, + DUMP_TYPE_WPDMA_RX, + DUMP_TYPE_WED_RRO, }; #define DUMP_STR(_str) { _str, 0, DUMP_TYPE_STRING } @@ -36,6 +39,9 @@ enum { #define DUMP_WPDMA_TX_RING(_n) DUMP_RING("WPDMA_TX" #_n, 0, DUMP_TYPE_WPDMA_TX, _n) #define DUMP_WPDMA_TXFREE_RING DUMP_RING("WPDMA_RX1", 0, DUMP_TYPE_WPDMA_TXFREE) +#define DUMP_WPDMA_RX_RING(_n) DUMP_RING("WPDMA_RX" #_n, 0, DUMP_TYPE_WPDMA_RX, _n) +#define DUMP_WED_RRO_RING(_base)DUMP_RING("WED_RRO_MIOD", MTK_##_base, DUMP_TYPE_WED_RRO) +#define DUMP_WED_RRO_FDBK(_base)DUMP_RING("WED_RRO_FDBK", MTK_##_base, DUMP_TYPE_WED_RRO) static void print_reg_val(struct seq_file *s, const char *name, u32 val) @@ -57,6 +63,7 @@ dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev, cur > regs ? "\n" : "", cur->name); continue; + case DUMP_TYPE_WED_RRO: case DUMP_TYPE_WED: val = wed_r32(dev, cur->offset); break; @@ -69,6 +76,9 @@ dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev, case DUMP_TYPE_WPDMA_TXFREE: val = wpdma_txfree_r32(dev, cur->offset); break; + case DUMP_TYPE_WPDMA_RX: + val = wpdma_rx_r32(dev, cur->base, cur->offset); + break; } print_reg_val(s, cur->name, val); } @@ -132,6 +142,80 @@ wed_txinfo_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(wed_txinfo); +static int +wed_rxinfo_show(struct seq_file *s, void *data) +{ + static const struct reg_dump regs[] = { + DUMP_STR("WPDMA RX"), + DUMP_WPDMA_RX_RING(0), + DUMP_WPDMA_RX_RING(1), + + DUMP_STR("WPDMA RX"), + DUMP_WED(WED_WPDMA_RX_D_MIB(0)), + DUMP_WED_RING(WED_WPDMA_RING_RX_DATA(0)), + DUMP_WED(WED_WPDMA_RX_D_PROCESSED_MIB(0)), + DUMP_WED(WED_WPDMA_RX_D_MIB(1)), + DUMP_WED_RING(WED_WPDMA_RING_RX_DATA(1)), + DUMP_WED(WED_WPDMA_RX_D_PROCESSED_MIB(1)), + DUMP_WED(WED_WPDMA_RX_D_COHERENT_MIB), + + DUMP_STR("WED RX"), + DUMP_WED_RING(WED_RING_RX_DATA(0)), + DUMP_WED_RING(WED_RING_RX_DATA(1)), + + DUMP_STR("WED RRO"), + DUMP_WED_RRO_RING(WED_RROQM_MIOD_CTRL0), + DUMP_WED(WED_RROQM_MID_MIB), + DUMP_WED(WED_RROQM_MOD_MIB), + DUMP_WED(WED_RROQM_MOD_COHERENT_MIB), + DUMP_WED_RRO_FDBK(WED_RROQM_FDBK_CTRL0), + DUMP_WED(WED_RROQM_FDBK_IND_MIB), + DUMP_WED(WED_RROQM_FDBK_ENQ_MIB), + DUMP_WED(WED_RROQM_FDBK_ANC_MIB), + DUMP_WED(WED_RROQM_FDBK_ANC2H_MIB), + + DUMP_STR("WED Route QM"), + DUMP_WED(WED_RTQM_R2H_MIB(0)), + DUMP_WED(WED_RTQM_R2Q_MIB(0)), + DUMP_WED(WED_RTQM_Q2H_MIB(0)), + DUMP_WED(WED_RTQM_R2H_MIB(1)), + DUMP_WED(WED_RTQM_R2Q_MIB(1)), + DUMP_WED(WED_RTQM_Q2H_MIB(1)), + DUMP_WED(WED_RTQM_Q2N_MIB), + DUMP_WED(WED_RTQM_Q2B_MIB), + DUMP_WED(WED_RTQM_PFDBK_MIB), + + DUMP_STR("WED WDMA TX"), + DUMP_WED(WED_WDMA_TX_MIB), + DUMP_WED_RING(WED_WDMA_RING_TX), + + DUMP_STR("WDMA TX"), + DUMP_WDMA(WDMA_GLO_CFG), + DUMP_WDMA_RING(WDMA_RING_TX(0)), + DUMP_WDMA_RING(WDMA_RING_TX(1)), + + DUMP_STR("WED RX BM"), + DUMP_WED(WED_RX_BM_BASE), + DUMP_WED(WED_RX_BM_RX_DMAD), + DUMP_WED(WED_RX_BM_PTR), + DUMP_WED(WED_RX_BM_TKID_MIB), + DUMP_WED(WED_RX_BM_BLEN), + DUMP_WED(WED_RX_BM_STS), + DUMP_WED(WED_RX_BM_INTF2), + DUMP_WED(WED_RX_BM_INTF), + DUMP_WED(WED_RX_BM_ERR_STS), + }; + struct mtk_wed_hw *hw = s->private; + struct mtk_wed_device *dev = hw->wed_dev; + + if (!dev) + return 0; + + dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(wed_rxinfo); static int mtk_wed_reg_set(void *data, u64 val) @@ -175,4 +259,7 @@ void mtk_wed_hw_add_debugfs(struct mtk_wed_hw *hw) debugfs_create_u32("regidx", 0600, dir, &hw->debugfs_reg); debugfs_create_file_unsafe("regval", 0600, dir, hw, &fops_regval); debugfs_create_file_unsafe("txinfo", 0400, dir, hw, &wed_txinfo_fops); + if (hw->version != 1) + debugfs_create_file_unsafe("rxinfo", 0400, dir, hw, + &wed_rxinfo_fops); } diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c new file mode 100644 index 000000000000..6bad0d262f28 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -0,0 +1,390 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2022 MediaTek Inc. + * + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + * Sujuan Chen <sujuan.chen@mediatek.com> + */ + +#include <linux/firmware.h> +#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> +#include <linux/mfd/syscon.h> +#include <linux/soc/mediatek/mtk_wed.h> +#include <asm/unaligned.h> + +#include "mtk_wed_regs.h" +#include "mtk_wed_wo.h" +#include "mtk_wed.h" + +static u32 wo_r32(struct mtk_wed_wo *wo, u32 reg) +{ + return readl(wo->boot.addr + reg); +} + +static void wo_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +{ + writel(val, wo->boot.addr + reg); +} + +static struct sk_buff * +mtk_wed_mcu_msg_alloc(const void *data, int data_len) +{ + int length = sizeof(struct mtk_wed_mcu_hdr) + data_len; + struct sk_buff *skb; + + skb = alloc_skb(length, GFP_KERNEL); + if (!skb) + return NULL; + + memset(skb->head, 0, length); + skb_reserve(skb, sizeof(struct mtk_wed_mcu_hdr)); + if (data && data_len) + skb_put_data(skb, data, data_len); + + return skb; +} + +static struct sk_buff * +mtk_wed_mcu_get_response(struct mtk_wed_wo *wo, unsigned long expires) +{ + if (!time_is_after_jiffies(expires)) + return NULL; + + wait_event_timeout(wo->mcu.wait, !skb_queue_empty(&wo->mcu.res_q), + expires - jiffies); + return skb_dequeue(&wo->mcu.res_q); +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + skb_queue_tail(&wo->mcu.res_q, skb); + wake_up(&wo->mcu.wait); +} + +static void +mtk_wed_update_rx_stats(struct mtk_wed_device *wed, struct sk_buff *skb) +{ + u32 count = get_unaligned_le32(skb->data); + struct mtk_wed_wo_rx_stats *stats; + int i; + + if (count * sizeof(*stats) > skb->len - sizeof(u32)) + return; + + stats = (struct mtk_wed_wo_rx_stats *)(skb->data + sizeof(u32)); + for (i = 0 ; i < count ; i++) + wed->wlan.update_wo_rx_stats(wed, &stats[i]); +} + +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + skb_pull(skb, sizeof(*hdr)); + + switch (hdr->cmd) { + case MTK_WED_WO_EVT_LOG_DUMP: + dev_notice(wo->hw->dev, "%s\n", skb->data); + break; + case MTK_WED_WO_EVT_PROFILING: { + struct mtk_wed_wo_log_info *info = (void *)skb->data; + u32 count = skb->len / sizeof(*info); + int i; + + for (i = 0 ; i < count ; i++) + dev_notice(wo->hw->dev, + "SN:%u latency: total=%u, rro:%u, mod:%u\n", + le32_to_cpu(info[i].sn), + le32_to_cpu(info[i].total), + le32_to_cpu(info[i].rro), + le32_to_cpu(info[i].mod)); + break; + } + case MTK_WED_WO_EVT_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); + break; + default: + break; + } + + dev_kfree_skb(skb); +} + +static int +mtk_wed_mcu_skb_send_msg(struct mtk_wed_wo *wo, struct sk_buff *skb, + int id, int cmd, u16 *wait_seq, bool wait_resp) +{ + struct mtk_wed_mcu_hdr *hdr; + + /* TODO: make it dynamic based on cmd */ + wo->mcu.timeout = 20 * HZ; + + hdr = (struct mtk_wed_mcu_hdr *)skb_push(skb, sizeof(*hdr)); + hdr->cmd = cmd; + hdr->length = cpu_to_le16(skb->len); + + if (wait_resp && wait_seq) { + u16 seq = ++wo->mcu.seq; + + if (!seq) + seq = ++wo->mcu.seq; + *wait_seq = seq; + + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_NEED_RSP); + hdr->seq = cpu_to_le16(seq); + } + if (id == MTK_WED_MODULE_ID_WO) + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_FROM_TO_WO); + + return mtk_wed_wo_queue_tx_skb(wo, &wo->q_tx, skb); +} + +static int +mtk_wed_mcu_parse_response(struct mtk_wed_wo *wo, struct sk_buff *skb, + int cmd, int seq) +{ + struct mtk_wed_mcu_hdr *hdr; + + if (!skb) { + dev_err(wo->hw->dev, "Message %08x (seq %d) timeout\n", + cmd, seq); + return -ETIMEDOUT; + } + + hdr = (struct mtk_wed_mcu_hdr *)skb->data; + if (le16_to_cpu(hdr->seq) != seq) + return -EAGAIN; + + skb_pull(skb, sizeof(*hdr)); + switch (cmd) { + case MTK_WED_WO_CMD_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); + break; + default: + break; + } + + return 0; +} + +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp) +{ + unsigned long expires; + struct sk_buff *skb; + u16 seq; + int ret; + + skb = mtk_wed_mcu_msg_alloc(data, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&wo->mcu.mutex); + + ret = mtk_wed_mcu_skb_send_msg(wo, skb, id, cmd, &seq, wait_resp); + if (ret || !wait_resp) + goto unlock; + + expires = jiffies + wo->mcu.timeout; + do { + skb = mtk_wed_mcu_get_response(wo, expires); + ret = mtk_wed_mcu_parse_response(wo, skb, cmd, seq); + dev_kfree_skb(skb); + } while (ret == -EAGAIN); + +unlock: + mutex_unlock(&wo->mcu.mutex); + + return ret; +} + +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + + if (dev->hw->version == 1) + return 0; + + if (WARN_ON(!wo)) + return -ENODEV; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, id, data, len, + true); +} + +static int +mtk_wed_get_memory_region(struct mtk_wed_wo *wo, + struct mtk_wed_wo_memory_region *region) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(wo->hw->node, "memory-region-names", + region->name); + if (index < 0) + return index; + + np = of_parse_phandle(wo->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + region->phy_addr = rmem->base; + region->size = rmem->size; + region->addr = devm_ioremap(wo->hw->dev, region->phy_addr, region->size); + + return !region->addr ? -EINVAL : 0; +} + +static int +mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw, + struct mtk_wed_wo_memory_region *region) +{ + const u8 *first_region_ptr, *region_ptr, *trailer_ptr, *ptr = fw->data; + const struct mtk_wed_fw_trailer *trailer; + const struct mtk_wed_fw_region *fw_region; + + trailer_ptr = fw->data + fw->size - sizeof(*trailer); + trailer = (const struct mtk_wed_fw_trailer *)trailer_ptr; + region_ptr = trailer_ptr - trailer->num_region * sizeof(*fw_region); + first_region_ptr = region_ptr; + + while (region_ptr < trailer_ptr) { + u32 length; + + fw_region = (const struct mtk_wed_fw_region *)region_ptr; + length = le32_to_cpu(fw_region->len); + + if (region->phy_addr != le32_to_cpu(fw_region->addr)) + goto next; + + if (region->size < length) + goto next; + + if (first_region_ptr < ptr + length) + goto next; + + if (region->shared && region->consumed) + return 0; + + if (!region->shared || !region->consumed) { + memcpy_toio(region->addr, ptr, length); + region->consumed = true; + return 0; + } +next: + region_ptr += sizeof(*fw_region); + ptr += length; + } + + return -EINVAL; +} + +static int +mtk_wed_mcu_load_firmware(struct mtk_wed_wo *wo) +{ + static struct mtk_wed_wo_memory_region mem_region[] = { + [MTK_WED_WO_REGION_EMI] = { + .name = "wo-emi", + }, + [MTK_WED_WO_REGION_ILM] = { + .name = "wo-ilm", + }, + [MTK_WED_WO_REGION_DATA] = { + .name = "wo-data", + .shared = true, + }, + }; + const struct mtk_wed_fw_trailer *trailer; + const struct firmware *fw; + const char *fw_name; + u32 val, boot_cr; + int ret, i; + + /* load firmware region metadata */ + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_get_memory_region(wo, &mem_region[i]); + if (ret) + return ret; + } + + wo->boot.name = "wo-boot"; + ret = mtk_wed_get_memory_region(wo, &wo->boot); + if (ret) + return ret; + + /* set dummy cr */ + wed_w32(wo->hw->wed_dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL, + wo->hw->index + 1); + + /* load firmware */ + fw_name = wo->hw->index ? MT7986_FIRMWARE_WO1 : MT7986_FIRMWARE_WO0; + ret = request_firmware(&fw, fw_name, wo->hw->dev); + if (ret) + return ret; + + trailer = (void *)(fw->data + fw->size - + sizeof(struct mtk_wed_fw_trailer)); + dev_info(wo->hw->dev, + "MTK WED WO Firmware Version: %.10s, Build Time: %.15s\n", + trailer->fw_ver, trailer->build_date); + dev_info(wo->hw->dev, "MTK WED WO Chip ID %02x Region %d\n", + trailer->chip_id, trailer->num_region); + + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_mcu_run_firmware(wo, fw, &mem_region[i]); + if (ret) + goto out; + } + + /* set the start address */ + boot_cr = wo->hw->index ? MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR + : MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR; + wo_w32(wo, boot_cr, mem_region[MTK_WED_WO_REGION_EMI].phy_addr >> 16); + /* wo firmware reset */ + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR, 0xc00); + + val = wo_r32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR); + val |= wo->hw->index ? MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK + : MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK; + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR, val); +out: + release_firmware(fw); + + return ret; +} + +static u32 +mtk_wed_mcu_read_fw_dl(struct mtk_wed_wo *wo) +{ + return wed_r32(wo->hw->wed_dev, + MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL); +} + +int mtk_wed_mcu_init(struct mtk_wed_wo *wo) +{ + u32 val; + int ret; + + skb_queue_head_init(&wo->mcu.res_q); + init_waitqueue_head(&wo->mcu.wait); + mutex_init(&wo->mcu.mutex); + + ret = mtk_wed_mcu_load_firmware(wo); + if (ret) + return ret; + + return readx_poll_timeout(mtk_wed_mcu_read_fw_dl, wo, val, !val, + 100, MTK_FW_DL_TIMEOUT); +} + +MODULE_FIRMWARE(MT7986_FIRMWARE_WO0); +MODULE_FIRMWARE(MT7986_FIRMWARE_WO1); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h index e270fb336143..0a50bb98c5ea 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h @@ -4,6 +4,7 @@ #ifndef __MTK_WED_REGS_H #define __MTK_WED_REGS_H +#define MTK_WFDMA_DESC_CTRL_TO_HOST BIT(8) #define MTK_WDMA_DESC_CTRL_LEN1 GENMASK(14, 0) #define MTK_WDMA_DESC_CTRL_LEN1_V2 GENMASK(13, 0) #define MTK_WDMA_DESC_CTRL_LAST_SEG1 BIT(15) @@ -19,15 +20,23 @@ struct mtk_wdma_desc { __le32 info; } __packed __aligned(4); +#define MTK_WED_REV_ID 0x004 + #define MTK_WED_RESET 0x008 #define MTK_WED_RESET_TX_BM BIT(0) +#define MTK_WED_RESET_RX_BM BIT(1) #define MTK_WED_RESET_TX_FREE_AGENT BIT(4) #define MTK_WED_RESET_WPDMA_TX_DRV BIT(8) #define MTK_WED_RESET_WPDMA_RX_DRV BIT(9) +#define MTK_WED_RESET_WPDMA_RX_D_DRV BIT(10) #define MTK_WED_RESET_WPDMA_INT_AGENT BIT(11) #define MTK_WED_RESET_WED_TX_DMA BIT(12) +#define MTK_WED_RESET_WED_RX_DMA BIT(13) +#define MTK_WED_RESET_WDMA_TX_DRV BIT(16) #define MTK_WED_RESET_WDMA_RX_DRV BIT(17) #define MTK_WED_RESET_WDMA_INT_AGENT BIT(19) +#define MTK_WED_RESET_RX_RRO_QM BIT(20) +#define MTK_WED_RESET_RX_ROUTE_QM BIT(21) #define MTK_WED_RESET_WED BIT(31) #define MTK_WED_CTRL 0x00c @@ -39,8 +48,12 @@ struct mtk_wdma_desc { #define MTK_WED_CTRL_WED_TX_BM_BUSY BIT(9) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_EN BIT(10) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY BIT(11) -#define MTK_WED_CTRL_RESERVE_EN BIT(12) -#define MTK_WED_CTRL_RESERVE_BUSY BIT(13) +#define MTK_WED_CTRL_WED_RX_BM_EN BIT(12) +#define MTK_WED_CTRL_WED_RX_BM_BUSY BIT(13) +#define MTK_WED_CTRL_RX_RRO_QM_EN BIT(14) +#define MTK_WED_CTRL_RX_RRO_QM_BUSY BIT(15) +#define MTK_WED_CTRL_RX_ROUTE_QM_EN BIT(16) +#define MTK_WED_CTRL_RX_ROUTE_QM_BUSY BIT(17) #define MTK_WED_CTRL_FINAL_DIDX_READ BIT(24) #define MTK_WED_CTRL_ETH_DMAD_FMT BIT(25) #define MTK_WED_CTRL_MIB_READ_CLEAR BIT(28) @@ -62,6 +75,9 @@ struct mtk_wdma_desc { #define MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR BIT(22) #define MTK_WED_EXT_INT_STATUS_TX_DMA_W_RESP_ERR BIT(23) #define MTK_WED_EXT_INT_STATUS_RX_DRV_DMA_RECYCLE BIT(24) +#define MTK_WED_EXT_INT_STATUS_RX_DRV_GET_BM_DMAD_SKIP BIT(25) +#define MTK_WED_EXT_INT_STATUS_WPDMA_RX_D_DRV_ERR BIT(26) +#define MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY BIT(27) #define MTK_WED_EXT_INT_STATUS_ERROR_MASK (MTK_WED_EXT_INT_STATUS_TF_LEN_ERR | \ MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD | \ MTK_WED_EXT_INT_STATUS_TKID_TITO_INVALID | \ @@ -71,6 +87,8 @@ struct mtk_wdma_desc { MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR) #define MTK_WED_EXT_INT_MASK 0x028 +#define MTK_WED_EXT_INT_MASK1 0x02c +#define MTK_WED_EXT_INT_MASK2 0x030 #define MTK_WED_STATUS 0x060 #define MTK_WED_STATUS_TX GENMASK(15, 8) @@ -144,6 +162,8 @@ struct mtk_wdma_desc { #define MTK_WED_RESET_IDX 0x20c #define MTK_WED_RESET_IDX_TX GENMASK(3, 0) #define MTK_WED_RESET_IDX_RX GENMASK(17, 16) +#define MTK_WED_RESET_IDX_RX_V2 GENMASK(7, 6) +#define MTK_WED_RESET_WPDMA_IDX_RX GENMASK(31, 30) #define MTK_WED_TX_MIB(_n) (0x2a0 + (_n) * 4) #define MTK_WED_RX_MIB(_n) (0x2e0 + (_n) * 4) @@ -151,7 +171,9 @@ struct mtk_wdma_desc { #define MTK_WED_RING_TX(_n) (0x300 + (_n) * 0x10) #define MTK_WED_RING_RX(_n) (0x400 + (_n) * 0x10) +#define MTK_WED_RING_RX_DATA(_n) (0x420 + (_n) * 0x10) +#define MTK_WED_SCR0 0x3c0 #define MTK_WED_WPDMA_INT_TRIGGER 0x504 #define MTK_WED_WPDMA_INT_TRIGGER_RX_DONE BIT(1) #define MTK_WED_WPDMA_INT_TRIGGER_TX_DONE GENMASK(5, 4) @@ -212,6 +234,12 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_RX 0x534 +#define MTK_WED_WPDMA_INT_CTRL_RX0_EN BIT(0) +#define MTK_WED_WPDMA_INT_CTRL_RX0_CLR BIT(1) +#define MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG GENMASK(6, 2) +#define MTK_WED_WPDMA_INT_CTRL_RX1_EN BIT(8) +#define MTK_WED_WPDMA_INT_CTRL_RX1_CLR BIT(9) +#define MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_TX_FREE 0x538 #define MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN BIT(0) @@ -241,11 +269,37 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_RING_TX(_n) (0x600 + (_n) * 0x10) #define MTK_WED_WPDMA_RING_RX(_n) (0x700 + (_n) * 0x10) +#define MTK_WED_WPDMA_RING_RX_DATA(_n) (0x730 + (_n) * 0x10) + +#define MTK_WED_WPDMA_RX_D_GLO_CFG 0x75c +#define MTK_WED_WPDMA_RX_D_RX_DRV_EN BIT(0) +#define MTK_WED_WPDMA_RX_D_RX_DRV_BUSY BIT(1) +#define MTK_WED_WPDMA_RX_D_FSM_RETURN_IDLE BIT(3) +#define MTK_WED_WPDMA_RX_D_RST_INIT_COMPLETE BIT(4) +#define MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL GENMASK(11, 7) +#define MTK_WED_WPDMA_RX_D_RXD_READ_LEN GENMASK(31, 24) + +#define MTK_WED_WPDMA_RX_D_RST_IDX 0x760 +#define MTK_WED_WPDMA_RX_D_RST_CRX_IDX GENMASK(17, 16) +#define MTK_WED_WPDMA_RX_D_RST_DRV_IDX GENMASK(25, 24) + +#define MTK_WED_WPDMA_RX_GLO_CFG 0x76c +#define MTK_WED_WPDMA_RX_RING 0x770 + +#define MTK_WED_WPDMA_RX_D_MIB(_n) (0x774 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_PROCESSED_MIB(_n) (0x784 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_COHERENT_MIB 0x78c + +#define MTK_WED_WDMA_RING_TX 0x800 + +#define MTK_WED_WDMA_TX_MIB 0x810 + #define MTK_WED_WDMA_RING_RX(_n) (0x900 + (_n) * 0x10) #define MTK_WED_WDMA_RX_THRES(_n) (0x940 + (_n) * 0x4) #define MTK_WED_WDMA_GLO_CFG 0xa04 #define MTK_WED_WDMA_GLO_CFG_TX_DRV_EN BIT(0) +#define MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK BIT(1) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_EN BIT(2) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY BIT(3) #define MTK_WED_WDMA_GLO_CFG_BT_SIZE GENMASK(5, 4) @@ -290,6 +344,20 @@ struct mtk_wdma_desc { #define MTK_WED_WDMA_RX_RECYCLE_MIB(_n) (0xae8 + (_n) * 4) #define MTK_WED_WDMA_RX_PROCESSED_MIB(_n) (0xaf0 + (_n) * 4) +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_RX_DMAD_SDL0 GENMASK(13, 0) + +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_SW_TAIL GENMASK(15, 0) +#define MTK_WED_RX_BM_INIT_SW_TAIL BIT(16) + +#define MTK_WED_RX_PTR 0xd8c + +#define MTK_WED_RX_BM_DYN_ALLOC_TH 0xdb4 +#define MTK_WED_RX_BM_DYN_ALLOC_TH_H GENMASK(31, 16) +#define MTK_WED_RX_BM_DYN_ALLOC_TH_L GENMASK(15, 0) + #define MTK_WED_RING_OFS_BASE 0x00 #define MTK_WED_RING_OFS_COUNT 0x04 #define MTK_WED_RING_OFS_CPU_IDX 0x08 @@ -300,7 +368,9 @@ struct mtk_wdma_desc { #define MTK_WDMA_GLO_CFG 0x204 #define MTK_WDMA_GLO_CFG_TX_DMA_EN BIT(0) +#define MTK_WDMA_GLO_CFG_TX_DMA_BUSY BIT(1) #define MTK_WDMA_GLO_CFG_RX_DMA_EN BIT(2) +#define MTK_WDMA_GLO_CFG_RX_DMA_BUSY BIT(3) #define MTK_WDMA_GLO_CFG_RX_INFO3_PRERES BIT(26) #define MTK_WDMA_GLO_CFG_RX_INFO2_PRERES BIT(27) #define MTK_WDMA_GLO_CFG_RX_INFO1_PRERES BIT(28) @@ -329,4 +399,70 @@ struct mtk_wdma_desc { /* DMA channel mapping */ #define HIFSYS_DMA_AG_MAP 0x008 +#define MTK_WED_RTQM_GLO_CFG 0xb00 +#define MTK_WED_RTQM_BUSY BIT(1) +#define MTK_WED_RTQM_Q_RST BIT(2) +#define MTK_WED_RTQM_Q_DBG_BYPASS BIT(5) +#define MTK_WED_RTQM_TXDMAD_FPORT GENMASK(23, 20) + +#define MTK_WED_RTQM_R2H_MIB(_n) (0xb70 + (_n) * 0x4) +#define MTK_WED_RTQM_R2Q_MIB(_n) (0xb78 + (_n) * 0x4) +#define MTK_WED_RTQM_Q2N_MIB 0xb80 +#define MTK_WED_RTQM_Q2H_MIB(_n) (0xb84 + (_n) * 0x4) + +#define MTK_WED_RTQM_Q2B_MIB 0xb8c +#define MTK_WED_RTQM_PFDBK_MIB 0xb90 + +#define MTK_WED_RROQM_GLO_CFG 0xc04 +#define MTK_WED_RROQM_RST_IDX 0xc08 +#define MTK_WED_RROQM_RST_IDX_MIOD BIT(0) +#define MTK_WED_RROQM_RST_IDX_FDBK BIT(4) + +#define MTK_WED_RROQM_MIOD_CTRL0 0xc40 +#define MTK_WED_RROQM_MIOD_CTRL1 0xc44 +#define MTK_WED_RROQM_MIOD_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_MIOD_CTRL2 0xc48 +#define MTK_WED_RROQM_MIOD_CTRL3 0xc4c + +#define MTK_WED_RROQM_FDBK_CTRL0 0xc50 +#define MTK_WED_RROQM_FDBK_CTRL1 0xc54 +#define MTK_WED_RROQM_FDBK_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_FDBK_CTRL2 0xc58 + +#define MTK_WED_RROQ_BASE_L 0xc80 +#define MTK_WED_RROQ_BASE_H 0xc84 + +#define MTK_WED_RROQM_MIOD_CFG 0xc8c +#define MTK_WED_RROQM_MIOD_MID_DW GENMASK(5, 0) +#define MTK_WED_RROQM_MIOD_MOD_DW GENMASK(13, 8) +#define MTK_WED_RROQM_MIOD_ENTRY_DW GENMASK(22, 16) + +#define MTK_WED_RROQM_MID_MIB 0xcc0 +#define MTK_WED_RROQM_MOD_MIB 0xcc4 +#define MTK_WED_RROQM_MOD_COHERENT_MIB 0xcc8 +#define MTK_WED_RROQM_FDBK_MIB 0xcd0 +#define MTK_WED_RROQM_FDBK_COHERENT_MIB 0xcd4 +#define MTK_WED_RROQM_FDBK_IND_MIB 0xce0 +#define MTK_WED_RROQM_FDBK_ENQ_MIB 0xce4 +#define MTK_WED_RROQM_FDBK_ANC_MIB 0xce8 +#define MTK_WED_RROQM_FDBK_ANC2H_MIB 0xcec + +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_PTR 0xd8c +#define MTK_WED_RX_BM_PTR_HEAD GENMASK(32, 16) +#define MTK_WED_RX_BM_PTR_TAIL GENMASK(15, 0) + +#define MTK_WED_RX_BM_BLEN 0xd90 +#define MTK_WED_RX_BM_STS 0xd94 +#define MTK_WED_RX_BM_INTF2 0xd98 +#define MTK_WED_RX_BM_INTF 0xd9c +#define MTK_WED_RX_BM_ERR_STS 0xda8 + +#define MTK_WED_WOCPU_VIEW_MIOD_BASE 0x8000 +#define MTK_WED_PCIE_INT_MASK 0x0 + #endif diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c new file mode 100644 index 000000000000..a0a39643caf7 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -0,0 +1,512 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2022 MediaTek Inc. + * + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + * Sujuan Chen <sujuan.chen@mediatek.com> + */ + +#include <linux/kernel.h> +#include <linux/dma-mapping.h> +#include <linux/of_platform.h> +#include <linux/interrupt.h> +#include <linux/of_address.h> +#include <linux/mfd/syscon.h> +#include <linux/of_irq.h> +#include <linux/bitfield.h> + +#include "mtk_wed.h" +#include "mtk_wed_regs.h" +#include "mtk_wed_wo.h" + +static u32 +mtk_wed_mmio_r32(struct mtk_wed_wo *wo, u32 reg) +{ + u32 val; + + if (regmap_read(wo->mmio.regs, reg, &val)) + val = ~0; + + return val; +} + +static void +mtk_wed_mmio_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +{ + regmap_write(wo->mmio.regs, reg, val); +} + +static u32 +mtk_wed_wo_get_isr(struct mtk_wed_wo *wo) +{ + u32 val = mtk_wed_mmio_r32(wo, MTK_WED_WO_CCIF_RCHNUM); + + return val & MTK_WED_WO_CCIF_RCHNUM_MASK; +} + +static void +mtk_wed_wo_set_isr(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_IRQ0_MASK, mask); +} + +static void +mtk_wed_wo_set_ack(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_ACK, mask); +} + +static void +mtk_wed_wo_set_isr_mask(struct mtk_wed_wo *wo, u32 mask, u32 val, bool set) +{ + unsigned long flags; + + spin_lock_irqsave(&wo->mmio.lock, flags); + wo->mmio.irq_mask &= ~mask; + wo->mmio.irq_mask |= val; + if (set) + mtk_wed_wo_set_isr(wo, wo->mmio.irq_mask); + spin_unlock_irqrestore(&wo->mmio.lock, flags); +} + +static void +mtk_wed_wo_irq_enable(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_wo_set_isr_mask(wo, 0, mask, false); + tasklet_schedule(&wo->mmio.irq_tasklet); +} + +static void +mtk_wed_wo_irq_disable(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_wo_set_isr_mask(wo, mask, 0, true); +} + +static void +mtk_wed_wo_kickout(struct mtk_wed_wo *wo) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_BUSY, 1 << MTK_WED_WO_TXCH_NUM); + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_TCHNUM, MTK_WED_WO_TXCH_NUM); +} + +static void +mtk_wed_wo_queue_kick(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + u32 val) +{ + wmb(); + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, val); +} + +static void * +mtk_wed_wo_dequeue(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, u32 *len, + bool flush) +{ + int buf_len = SKB_WITH_OVERHEAD(q->buf_size); + int index = (q->tail + 1) % q->n_desc; + struct mtk_wed_wo_queue_entry *entry; + struct mtk_wed_wo_queue_desc *desc; + void *buf; + + if (!q->queued) + return NULL; + + if (flush) + q->desc[index].ctrl |= cpu_to_le32(MTK_WED_WO_CTL_DMA_DONE); + else if (!(q->desc[index].ctrl & cpu_to_le32(MTK_WED_WO_CTL_DMA_DONE))) + return NULL; + + q->tail = index; + q->queued--; + + desc = &q->desc[index]; + entry = &q->entry[index]; + buf = entry->buf; + if (len) + *len = FIELD_GET(MTK_WED_WO_CTL_SD_LEN0, + le32_to_cpu(READ_ONCE(desc->ctrl))); + if (buf) + dma_unmap_single(wo->hw->dev, entry->addr, buf_len, + DMA_FROM_DEVICE); + entry->buf = NULL; + + return buf; +} + +static int +mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + bool rx) +{ + enum dma_data_direction dir = rx ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + int n_buf = 0; + + spin_lock_bh(&q->lock); + while (q->queued < q->n_desc) { + struct mtk_wed_wo_queue_entry *entry; + dma_addr_t addr; + void *buf; + + buf = page_frag_alloc(&q->cache, q->buf_size, GFP_ATOMIC); + if (!buf) + break; + + addr = dma_map_single(wo->hw->dev, buf, q->buf_size, dir); + if (unlikely(dma_mapping_error(wo->hw->dev, addr))) { + skb_free_frag(buf); + break; + } + + q->head = (q->head + 1) % q->n_desc; + entry = &q->entry[q->head]; + entry->addr = addr; + entry->len = q->buf_size; + q->entry[q->head].buf = buf; + + if (rx) { + struct mtk_wed_wo_queue_desc *desc = &q->desc[q->head]; + u32 ctrl = MTK_WED_WO_CTL_LAST_SEC0 | + FIELD_PREP(MTK_WED_WO_CTL_SD_LEN0, + entry->len); + + WRITE_ONCE(desc->buf0, cpu_to_le32(addr)); + WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + } + q->queued++; + n_buf++; + } + spin_unlock_bh(&q->lock); + + return n_buf; +} + +static void +mtk_wed_wo_rx_complete(struct mtk_wed_wo *wo) +{ + mtk_wed_wo_set_ack(wo, MTK_WED_WO_RXCH_INT_MASK); + mtk_wed_wo_irq_enable(wo, MTK_WED_WO_RXCH_INT_MASK); +} + +static void +mtk_wed_wo_rx_run_queue(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + for (;;) { + struct mtk_wed_mcu_hdr *hdr; + struct sk_buff *skb; + void *data; + u32 len; + + data = mtk_wed_wo_dequeue(wo, q, &len, false); + if (!data) + break; + + skb = build_skb(data, q->buf_size); + if (!skb) { + skb_free_frag(data); + continue; + } + + __skb_put(skb, len); + if (mtk_wed_mcu_check_msg(wo, skb)) { + dev_kfree_skb(skb); + continue; + } + + hdr = (struct mtk_wed_mcu_hdr *)skb->data; + if (hdr->flag & cpu_to_le16(MTK_WED_WARP_CMD_FLAG_RSP)) + mtk_wed_mcu_rx_event(wo, skb); + else + mtk_wed_mcu_rx_unsolicited_event(wo, skb); + } + + if (mtk_wed_wo_queue_refill(wo, q, true)) { + u32 index = (q->head - 1) % q->n_desc; + + mtk_wed_wo_queue_kick(wo, q, index); + } +} + +static irqreturn_t +mtk_wed_wo_irq_handler(int irq, void *data) +{ + struct mtk_wed_wo *wo = data; + + mtk_wed_wo_set_isr(wo, 0); + tasklet_schedule(&wo->mmio.irq_tasklet); + + return IRQ_HANDLED; +} + +static void mtk_wed_wo_irq_tasklet(struct tasklet_struct *t) +{ + struct mtk_wed_wo *wo = from_tasklet(wo, t, mmio.irq_tasklet); + u32 intr, mask; + + /* disable interrupts */ + mtk_wed_wo_set_isr(wo, 0); + + intr = mtk_wed_wo_get_isr(wo); + intr &= wo->mmio.irq_mask; + mask = intr & (MTK_WED_WO_RXCH_INT_MASK | MTK_WED_WO_EXCEPTION_INT_MASK); + mtk_wed_wo_irq_disable(wo, mask); + + if (intr & MTK_WED_WO_RXCH_INT_MASK) { + mtk_wed_wo_rx_run_queue(wo, &wo->q_rx); + mtk_wed_wo_rx_complete(wo); + } +} + +/* mtk wed wo hw queues */ + +static int +mtk_wed_wo_queue_alloc(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + int n_desc, int buf_size, int index, + struct mtk_wed_wo_queue_regs *regs) +{ + spin_lock_init(&q->lock); + q->regs = *regs; + q->n_desc = n_desc; + q->buf_size = buf_size; + + q->desc = dmam_alloc_coherent(wo->hw->dev, n_desc * sizeof(*q->desc), + &q->desc_dma, GFP_KERNEL); + if (!q->desc) + return -ENOMEM; + + q->entry = devm_kzalloc(wo->hw->dev, n_desc * sizeof(*q->entry), + GFP_KERNEL); + if (!q->entry) + return -ENOMEM; + + return 0; +} + +static void +mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, 0); + dma_free_coherent(wo->hw->dev, q->n_desc * sizeof(*q->desc), q->desc, + q->desc_dma); +} + +static void +mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + struct page *page; + int i; + + spin_lock_bh(&q->lock); + for (i = 0; i < q->n_desc; i++) { + struct mtk_wed_wo_queue_entry *entry = &q->entry[i]; + + dma_unmap_single(wo->hw->dev, entry->addr, entry->len, + DMA_TO_DEVICE); + skb_free_frag(entry->buf); + entry->buf = NULL; + } + spin_unlock_bh(&q->lock); + + if (!q->cache.va) + return; + + page = virt_to_page(q->cache.va); + __page_frag_cache_drain(page, q->cache.pagecnt_bias); + memset(&q->cache, 0, sizeof(q->cache)); +} + +static void +mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + struct page *page; + + spin_lock_bh(&q->lock); + for (;;) { + void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); + + if (!buf) + break; + + skb_free_frag(buf); + } + spin_unlock_bh(&q->lock); + + if (!q->cache.va) + return; + + page = virt_to_page(q->cache.va); + __page_frag_cache_drain(page, q->cache.pagecnt_bias); + memset(&q->cache, 0, sizeof(q->cache)); +} + +static void +mtk_wed_wo_queue_reset(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, 0); + mtk_wed_mmio_w32(wo, q->regs.desc_base, q->desc_dma); + mtk_wed_mmio_w32(wo, q->regs.ring_size, q->n_desc); +} + +int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + struct sk_buff *skb) +{ + struct mtk_wed_wo_queue_entry *entry; + struct mtk_wed_wo_queue_desc *desc; + int ret = 0, index; + u32 ctrl; + + spin_lock_bh(&q->lock); + + q->tail = mtk_wed_mmio_r32(wo, q->regs.dma_idx); + index = (q->head + 1) % q->n_desc; + if (q->tail == index) { + ret = -ENOMEM; + goto out; + } + + entry = &q->entry[index]; + if (skb->len > entry->len) { + ret = -ENOMEM; + goto out; + } + + desc = &q->desc[index]; + q->head = index; + + dma_sync_single_for_cpu(wo->hw->dev, entry->addr, skb->len, + DMA_TO_DEVICE); + memcpy(entry->buf, skb->data, skb->len); + dma_sync_single_for_device(wo->hw->dev, entry->addr, skb->len, + DMA_TO_DEVICE); + + ctrl = FIELD_PREP(MTK_WED_WO_CTL_SD_LEN0, skb->len) | + MTK_WED_WO_CTL_LAST_SEC0 | MTK_WED_WO_CTL_DMA_DONE; + WRITE_ONCE(desc->buf0, cpu_to_le32(entry->addr)); + WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + + mtk_wed_wo_queue_kick(wo, q, q->head); + mtk_wed_wo_kickout(wo); +out: + spin_unlock_bh(&q->lock); + + dev_kfree_skb(skb); + + return ret; +} + +static int +mtk_wed_wo_exception_init(struct mtk_wed_wo *wo) +{ + return 0; +} + +static int +mtk_wed_wo_hardware_init(struct mtk_wed_wo *wo) +{ + struct mtk_wed_wo_queue_regs regs; + struct device_node *np; + int ret; + + np = of_parse_phandle(wo->hw->node, "mediatek,wo-ccif", 0); + if (!np) + return -ENODEV; + + wo->mmio.regs = syscon_regmap_lookup_by_phandle(np, NULL); + if (IS_ERR(wo->mmio.regs)) { + ret = PTR_ERR(wo->mmio.regs); + goto error_put; + } + + wo->mmio.irq = irq_of_parse_and_map(np, 0); + wo->mmio.irq_mask = MTK_WED_WO_ALL_INT_MASK; + spin_lock_init(&wo->mmio.lock); + tasklet_setup(&wo->mmio.irq_tasklet, mtk_wed_wo_irq_tasklet); + + ret = devm_request_irq(wo->hw->dev, wo->mmio.irq, + mtk_wed_wo_irq_handler, IRQF_TRIGGER_HIGH, + KBUILD_MODNAME, wo); + if (ret) + goto error; + + regs.desc_base = MTK_WED_WO_CCIF_DUMMY1; + regs.ring_size = MTK_WED_WO_CCIF_DUMMY2; + regs.dma_idx = MTK_WED_WO_CCIF_SHADOW4; + regs.cpu_idx = MTK_WED_WO_CCIF_DUMMY3; + + ret = mtk_wed_wo_queue_alloc(wo, &wo->q_tx, MTK_WED_WO_RING_SIZE, + MTK_WED_WO_CMD_LEN, MTK_WED_WO_TXCH_NUM, + ®s); + if (ret) + goto error; + + mtk_wed_wo_queue_refill(wo, &wo->q_tx, false); + mtk_wed_wo_queue_reset(wo, &wo->q_tx); + + regs.desc_base = MTK_WED_WO_CCIF_DUMMY5; + regs.ring_size = MTK_WED_WO_CCIF_DUMMY6; + regs.dma_idx = MTK_WED_WO_CCIF_SHADOW8; + regs.cpu_idx = MTK_WED_WO_CCIF_DUMMY7; + + ret = mtk_wed_wo_queue_alloc(wo, &wo->q_rx, MTK_WED_WO_RING_SIZE, + MTK_WED_WO_CMD_LEN, MTK_WED_WO_RXCH_NUM, + ®s); + if (ret) + goto error; + + mtk_wed_wo_queue_refill(wo, &wo->q_rx, true); + mtk_wed_wo_queue_reset(wo, &wo->q_rx); + + /* rx queue irqmask */ + mtk_wed_wo_set_isr(wo, wo->mmio.irq_mask); + + return 0; + +error: + devm_free_irq(wo->hw->dev, wo->mmio.irq, wo); +error_put: + of_node_put(np); + return ret; +} + +static void +mtk_wed_wo_hw_deinit(struct mtk_wed_wo *wo) +{ + /* disable interrupts */ + mtk_wed_wo_set_isr(wo, 0); + + tasklet_disable(&wo->mmio.irq_tasklet); + + disable_irq(wo->mmio.irq); + devm_free_irq(wo->hw->dev, wo->mmio.irq, wo); + + mtk_wed_wo_queue_tx_clean(wo, &wo->q_tx); + mtk_wed_wo_queue_rx_clean(wo, &wo->q_rx); + mtk_wed_wo_queue_free(wo, &wo->q_tx); + mtk_wed_wo_queue_free(wo, &wo->q_rx); +} + +int mtk_wed_wo_init(struct mtk_wed_hw *hw) +{ + struct mtk_wed_wo *wo; + int ret; + + wo = devm_kzalloc(hw->dev, sizeof(*wo), GFP_KERNEL); + if (!wo) + return -ENOMEM; + + hw->wed_wo = wo; + wo->hw = hw; + + ret = mtk_wed_wo_hardware_init(wo); + if (ret) + return ret; + + ret = mtk_wed_mcu_init(wo); + if (ret) + return ret; + + return mtk_wed_wo_exception_init(wo); +} + +void mtk_wed_wo_deinit(struct mtk_wed_hw *hw) +{ + struct mtk_wed_wo *wo = hw->wed_wo; + + mtk_wed_wo_hw_deinit(wo); +} diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h new file mode 100644 index 000000000000..c8fb85795864 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -0,0 +1,282 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2022 Lorenzo Bianconi <lorenzo@kernel.org> */ + +#ifndef __MTK_WED_WO_H +#define __MTK_WED_WO_H + +#include <linux/skbuff.h> +#include <linux/netdevice.h> + +struct mtk_wed_hw; + +struct mtk_wed_mcu_hdr { + /* DW0 */ + u8 version; + u8 cmd; + __le16 length; + + /* DW1 */ + __le16 seq; + __le16 flag; + + /* DW2 */ + __le32 status; + + /* DW3 */ + u8 rsv[20]; +}; + +struct mtk_wed_wo_log_info { + __le32 sn; + __le32 total; + __le32 rro; + __le32 mod; +}; + +enum mtk_wed_wo_event { + MTK_WED_WO_EVT_LOG_DUMP = 0x1, + MTK_WED_WO_EVT_PROFILING = 0x2, + MTK_WED_WO_EVT_RXCNT_INFO = 0x3, +}; + +#define MTK_WED_MODULE_ID_WO 1 +#define MTK_FW_DL_TIMEOUT 4000000 /* us */ +#define MTK_WOCPU_TIMEOUT 2000000 /* us */ + +enum { + MTK_WED_WARP_CMD_FLAG_RSP = BIT(0), + MTK_WED_WARP_CMD_FLAG_NEED_RSP = BIT(1), + MTK_WED_WARP_CMD_FLAG_FROM_TO_WO = BIT(2), +}; + +#define MTK_WED_WO_CPU_MCUSYS_RESET_ADDR 0x15194050 +#define MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK 0x20 +#define MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK 0x1 + +enum { + MTK_WED_WO_REGION_EMI, + MTK_WED_WO_REGION_ILM, + MTK_WED_WO_REGION_DATA, + MTK_WED_WO_REGION_BOOT, + __MTK_WED_WO_REGION_MAX, +}; + +enum mtk_wed_wo_state { + MTK_WED_WO_STATE_UNDEFINED, + MTK_WED_WO_STATE_INIT, + MTK_WED_WO_STATE_ENABLE, + MTK_WED_WO_STATE_DISABLE, + MTK_WED_WO_STATE_HALT, + MTK_WED_WO_STATE_GATING, + MTK_WED_WO_STATE_SER_RESET, + MTK_WED_WO_STATE_WF_RESET, +}; + +enum mtk_wed_wo_done_state { + MTK_WED_WOIF_UNDEFINED, + MTK_WED_WOIF_DISABLE_DONE, + MTK_WED_WOIF_TRIGGER_ENABLE, + MTK_WED_WOIF_ENABLE_DONE, + MTK_WED_WOIF_TRIGGER_GATING, + MTK_WED_WOIF_GATING_DONE, + MTK_WED_WOIF_TRIGGER_HALT, + MTK_WED_WOIF_HALT_DONE, +}; + +enum mtk_wed_dummy_cr_idx { + MTK_WED_DUMMY_CR_FWDL, + MTK_WED_DUMMY_CR_WO_STATUS, +}; + +#define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin" +#define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin" + +#define MTK_WO_MCU_CFG_LS_BASE 0 +#define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000) +#define MTK_WO_MCU_CFG_LS_FW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x004) +#define MTK_WO_MCU_CFG_LS_CFG_DBG1_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x00c) +#define MTK_WO_MCU_CFG_LS_CFG_DBG2_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x010) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x014) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_SET_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x018) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x01c) +#define MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x050) +#define MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x060) +#define MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x064) + +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK BIT(5) +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK BIT(0) + +#define MTK_WED_WO_RING_SIZE 256 +#define MTK_WED_WO_CMD_LEN 1504 + +#define MTK_WED_WO_TXCH_NUM 0 +#define MTK_WED_WO_RXCH_NUM 1 +#define MTK_WED_WO_RXCH_WO_EXCEPTION 7 + +#define MTK_WED_WO_TXCH_INT_MASK BIT(0) +#define MTK_WED_WO_RXCH_INT_MASK BIT(1) +#define MTK_WED_WO_EXCEPTION_INT_MASK BIT(7) +#define MTK_WED_WO_ALL_INT_MASK (MTK_WED_WO_RXCH_INT_MASK | \ + MTK_WED_WO_EXCEPTION_INT_MASK) + +#define MTK_WED_WO_CCIF_BUSY 0x004 +#define MTK_WED_WO_CCIF_START 0x008 +#define MTK_WED_WO_CCIF_TCHNUM 0x00c +#define MTK_WED_WO_CCIF_RCHNUM 0x010 +#define MTK_WED_WO_CCIF_RCHNUM_MASK GENMASK(7, 0) + +#define MTK_WED_WO_CCIF_ACK 0x014 +#define MTK_WED_WO_CCIF_IRQ0_MASK 0x018 +#define MTK_WED_WO_CCIF_IRQ1_MASK 0x01c +#define MTK_WED_WO_CCIF_DUMMY1 0x020 +#define MTK_WED_WO_CCIF_DUMMY2 0x024 +#define MTK_WED_WO_CCIF_DUMMY3 0x028 +#define MTK_WED_WO_CCIF_DUMMY4 0x02c +#define MTK_WED_WO_CCIF_SHADOW1 0x030 +#define MTK_WED_WO_CCIF_SHADOW2 0x034 +#define MTK_WED_WO_CCIF_SHADOW3 0x038 +#define MTK_WED_WO_CCIF_SHADOW4 0x03c +#define MTK_WED_WO_CCIF_DUMMY5 0x050 +#define MTK_WED_WO_CCIF_DUMMY6 0x054 +#define MTK_WED_WO_CCIF_DUMMY7 0x058 +#define MTK_WED_WO_CCIF_DUMMY8 0x05c +#define MTK_WED_WO_CCIF_SHADOW5 0x060 +#define MTK_WED_WO_CCIF_SHADOW6 0x064 +#define MTK_WED_WO_CCIF_SHADOW7 0x068 +#define MTK_WED_WO_CCIF_SHADOW8 0x06c + +#define MTK_WED_WO_CTL_SD_LEN1 GENMASK(13, 0) +#define MTK_WED_WO_CTL_LAST_SEC1 BIT(14) +#define MTK_WED_WO_CTL_BURST BIT(15) +#define MTK_WED_WO_CTL_SD_LEN0_SHIFT 16 +#define MTK_WED_WO_CTL_SD_LEN0 GENMASK(29, 16) +#define MTK_WED_WO_CTL_LAST_SEC0 BIT(30) +#define MTK_WED_WO_CTL_DMA_DONE BIT(31) +#define MTK_WED_WO_INFO_WINFO GENMASK(15, 0) + +struct mtk_wed_wo_memory_region { + const char *name; + void __iomem *addr; + phys_addr_t phy_addr; + u32 size; + bool shared:1; + bool consumed:1; +}; + +struct mtk_wed_fw_region { + __le32 decomp_crc; + __le32 decomp_len; + __le32 decomp_blk_sz; + u8 rsv0[4]; + __le32 addr; + __le32 len; + u8 feature_set; + u8 rsv1[15]; +} __packed; + +struct mtk_wed_fw_trailer { + u8 chip_id; + u8 eco_code; + u8 num_region; + u8 format_ver; + u8 format_flag; + u8 rsv[2]; + char fw_ver[10]; + char build_date[15]; + u32 crc; +}; + +struct mtk_wed_wo_queue_regs { + u32 desc_base; + u32 ring_size; + u32 cpu_idx; + u32 dma_idx; +}; + +struct mtk_wed_wo_queue_desc { + __le32 buf0; + __le32 ctrl; + __le32 buf1; + __le32 info; + __le32 reserved[4]; +} __packed __aligned(32); + +struct mtk_wed_wo_queue_entry { + dma_addr_t addr; + void *buf; + u32 len; +}; + +struct mtk_wed_wo_queue { + struct mtk_wed_wo_queue_regs regs; + + struct page_frag_cache cache; + spinlock_t lock; + + struct mtk_wed_wo_queue_desc *desc; + dma_addr_t desc_dma; + + struct mtk_wed_wo_queue_entry *entry; + + u16 head; + u16 tail; + int n_desc; + int queued; + int buf_size; + +}; + +struct mtk_wed_wo { + struct mtk_wed_hw *hw; + struct mtk_wed_wo_memory_region boot; + + struct mtk_wed_wo_queue q_tx; + struct mtk_wed_wo_queue q_rx; + + struct { + struct mutex mutex; + int timeout; + u16 seq; + + struct sk_buff_head res_q; + wait_queue_head_t wait; + } mcu; + + struct { + struct regmap *regs; + + spinlock_t lock; + struct tasklet_struct irq_tasklet; + int irq; + u32 irq_mask; + } mmio; +}; + +static inline int +mtk_wed_mcu_check_msg(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + if (hdr->version) + return -EINVAL; + + if (skb->len < sizeof(*hdr) || skb->len != le16_to_cpu(hdr->length)) + return -EINVAL; + + return 0; +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb); +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb); +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp); +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len); +int mtk_wed_mcu_init(struct mtk_wed_wo *wo); +int mtk_wed_wo_init(struct mtk_wed_hw *hw); +void mtk_wed_wo_deinit(struct mtk_wed_hw *hw); +int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *dev, struct mtk_wed_wo_queue *q, + struct sk_buff *skb); + +#endif /* __MTK_WED_WO_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 024788549c25..98b5ffb4d729 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -111,34 +111,27 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev) } /** - * mlx4_en_phc_adjfreq - adjust the frequency of the hardware clock + * mlx4_en_phc_adjfine - adjust the frequency of the hardware clock * @ptp: ptp clock structure - * @delta: Desired frequency change in parts per billion + * @scaled_ppm: Desired frequency change in scaled parts per million * - * Adjust the frequency of the PHC cycle counter by the indicated delta from - * the base frequency. + * Adjust the frequency of the PHC cycle counter by the indicated scaled_ppm + * from the base frequency. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. **/ -static int mlx4_en_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int mlx4_en_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { - u64 adj; - u32 diff, mult; - int neg_adj = 0; + u32 mult; unsigned long flags; struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev, ptp_clock_info); - if (delta < 0) { - neg_adj = 1; - delta = -delta; - } - mult = mdev->nominal_c_mult; - adj = mult; - adj *= delta; - diff = div_u64(adj, 1000000000ULL); + mult = (u32)adjust_by_scaled_ppm(mdev->nominal_c_mult, scaled_ppm); write_seqlock_irqsave(&mdev->clock_lock, flags); timecounter_read(&mdev->clock); - mdev->cycles.mult = neg_adj ? mult - diff : mult + diff; + mdev->cycles.mult = mult; write_sequnlock_irqrestore(&mdev->clock_lock, flags); return 0; @@ -237,7 +230,7 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 0, - .adjfreq = mlx4_en_phc_adjfreq, + .adjfine = mlx4_en_phc_adjfine, .adjtime = mlx4_en_phc_adjtime, .gettime64 = mlx4_en_phc_gettime, .settime64 = mlx4_en_phc_settime, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index ca4b93a01034..8800d3f1f55c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2337,11 +2337,8 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) { - devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, - priv->port)); + if (priv->registered) unregister_netdev(dev); - } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -3474,6 +3471,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, mdev->profile.prof[priv->port].tx_ppp, mdev->profile.prof[priv->port].tx_pause); + SET_NETDEV_DEVLINK_PORT(dev, + mlx4_get_devlink_port(mdev->dev, priv->port)); err = register_netdev(dev); if (err) { en_err(priv, "Netdev registration failed for port %d\n", port); @@ -3481,8 +3480,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; - devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), - dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 43a4102e9c09..c5758637b7be 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -65,7 +65,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, ring->size = size; ring->size_mask = size - 1; ring->sp_stride = stride; - ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS; + ring->full_size = ring->size - HEADROOM - MLX4_MAX_DESC_TXBBS; tmp = size * sizeof(struct mlx4_en_tx_info); ring->tx_info = kvmalloc_node(tmp, GFP_KERNEL, node); @@ -77,9 +77,11 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n", ring->tx_info, tmp); - ring->bounce_buf = kmalloc_node(MAX_DESC_SIZE, GFP_KERNEL, node); + ring->bounce_buf = kmalloc_node(MLX4_TX_BOUNCE_BUFFER_SIZE, + GFP_KERNEL, node); if (!ring->bounce_buf) { - ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL); + ring->bounce_buf = kmalloc(MLX4_TX_BOUNCE_BUFFER_SIZE, + GFP_KERNEL); if (!ring->bounce_buf) { err = -ENOMEM; goto err_info; @@ -909,11 +911,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) /* Align descriptor to TXBB size */ desc_size = ALIGN(real_size, TXBB_SIZE); nr_txbb = desc_size >> LOG_TXBB_SIZE; - if (unlikely(nr_txbb > MAX_DESC_TXBBS)) { - if (netif_msg_tx_err(priv)) - en_warn(priv, "Oversized header or SG list\n"); - goto tx_drop_count; - } bf_ok = ring->bf_enabled; if (skb_vlan_tag_present(skb)) { @@ -941,6 +938,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) if (likely(index + nr_txbb <= ring->size)) tx_desc = ring->buf + (index << LOG_TXBB_SIZE); else { + if (unlikely(nr_txbb > MLX4_MAX_DESC_TXBBS)) { + if (netif_msg_tx_err(priv)) + en_warn(priv, "Oversized header or SG list\n"); + goto tx_drop_count; + } tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf; bounce = true; bf_ok = false; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d3fc86cd3c1d..3ae246391549 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3043,7 +3043,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) */ if (!IS_ENABLED(CONFIG_MLX4_EN) && dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) - devlink_port_type_eth_set(&info->devlink_port, NULL); + devlink_port_type_eth_set(&info->devlink_port); else if (!IS_ENABLED(CONFIG_MLX4_INFINIBAND) && dev->caps.port_type[port] == MLX4_PORT_TYPE_IB) devlink_port_type_ib_set(&info->devlink_port, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index e132ff4c82f2..3d4226ddba5e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -89,9 +89,19 @@ #define MLX4_EN_FILTER_HASH_SHIFT 4 #define MLX4_EN_FILTER_EXPIRY_QUOTA 60 -/* Typical TSO descriptor with 16 gather entries is 352 bytes... */ -#define MAX_DESC_SIZE 512 -#define MAX_DESC_TXBBS (MAX_DESC_SIZE / TXBB_SIZE) +#define CTRL_SIZE sizeof(struct mlx4_wqe_ctrl_seg) +#define DS_SIZE sizeof(struct mlx4_wqe_data_seg) + +/* Maximal size of the bounce buffer: + * 256 bytes for LSO headers. + * CTRL_SIZE for control desc. + * DS_SIZE if skb->head contains some payload. + * MAX_SKB_FRAGS frags. + */ +#define MLX4_TX_BOUNCE_BUFFER_SIZE \ + ALIGN(256 + CTRL_SIZE + DS_SIZE + MAX_SKB_FRAGS * DS_SIZE, TXBB_SIZE) + +#define MLX4_MAX_DESC_TXBBS (MLX4_TX_BOUNCE_BUFFER_SIZE / TXBB_SIZE) /* * OS related constants and tunables @@ -217,9 +227,7 @@ struct mlx4_en_tx_info { #define MLX4_EN_BIT_DESC_OWN 0x80000000 -#define CTRL_SIZE sizeof(struct mlx4_wqe_ctrl_seg) #define MLX4_EN_MEMTYPE_PAD 0x100 -#define DS_SIZE sizeof(struct mlx4_wqe_data_seg) struct mlx4_en_tx_desc { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index a22c32aabf11..cd4a1ab0ea78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -111,6 +111,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o steering/dr_ste_v2.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o \ + steering/dr_definer.o \ steering/dr_dbg.o lib/smfs.o # # SF device diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index e7a894ba5c3e..d3ca745d107d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -37,7 +37,6 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/random.h> -#include <linux/io-mapping.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/eq.h> #include <linux/debugfs.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 66c6a7017695..ddb197970c22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -46,10 +46,6 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, u32 running_fw, stored_fw; int err; - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; - err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id); if (err) return err; @@ -318,6 +314,10 @@ static const struct devlink_ops mlx5_devlink_ops = { .rate_node_new = mlx5_esw_devlink_rate_node_new, .rate_node_del = mlx5_esw_devlink_rate_node_del, .rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set, + .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, + .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, + .port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get, + .port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set, #endif #ifdef CONFIG_MLX5_SF_MANAGER .port_new = mlx5_devlink_sf_port_new, @@ -840,7 +840,7 @@ static const struct devlink_trap_group mlx5_trap_groups_arr[] = { DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 0), }; -static int mlx5_devlink_traps_register(struct devlink *devlink) +int mlx5_devlink_traps_register(struct devlink *devlink) { struct mlx5_core_dev *core_dev = devlink_priv(devlink); int err; @@ -862,7 +862,7 @@ err_trap_group: return err; } -static void mlx5_devlink_traps_unregister(struct devlink *devlink) +void mlx5_devlink_traps_unregister(struct devlink *devlink) { devl_traps_unregister(devlink, mlx5_traps_arr, ARRAY_SIZE(mlx5_traps_arr)); devl_trap_groups_unregister(devlink, mlx5_trap_groups_arr, @@ -889,17 +889,11 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto max_uc_list_err; - err = mlx5_devlink_traps_register(devlink); - if (err) - goto traps_reg_err; - if (!mlx5_core_is_mp_slave(dev)) devlink_set_features(devlink, DEVLINK_F_RELOAD); return 0; -traps_reg_err: - mlx5_devlink_max_uc_list_param_unregister(devlink); max_uc_list_err: mlx5_devlink_auxdev_params_unregister(devlink); auxdev_reg_err: @@ -910,7 +904,6 @@ auxdev_reg_err: void mlx5_devlink_unregister(struct devlink *devlink) { - mlx5_devlink_traps_unregister(devlink); mlx5_devlink_max_uc_list_param_unregister(devlink); mlx5_devlink_auxdev_params_unregister(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 30bf4882779b..fd033df24856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -30,6 +30,8 @@ void mlx5_devlink_trap_report(struct mlx5_core_dev *dev, int trap_id, struct sk_ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev); int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id, enum devlink_trap_action *action); +int mlx5_devlink_traps_register(struct devlink *devlink); +void mlx5_devlink_traps_unregister(struct devlink *devlink); struct devlink *mlx5_devlink_alloc(struct device *dev); void mlx5_devlink_free(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index c5bb79a4fa57..2732128e7a6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -228,6 +228,17 @@ const char *parse_fs_hdrs(struct trace_seq *p, return ret; } +static const char +*fs_dest_range_field_to_str(enum mlx5_flow_dest_range_field field) +{ + switch (field) { + case MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN: + return "packet len"; + default: + return "unknown dest range field"; + } +} + const char *parse_fs_dst(struct trace_seq *p, const struct mlx5_flow_destination *dst, u32 counter_id) @@ -259,6 +270,11 @@ const char *parse_fs_dst(struct trace_seq *p, case MLX5_FLOW_DESTINATION_TYPE_PORT: trace_seq_printf(p, "port\n"); break; + case MLX5_FLOW_DESTINATION_TYPE_RANGE: + trace_seq_printf(p, "field=%s min=%d max=%d\n", + fs_dest_range_field_to_str(dst->range.field), + dst->range.min, dst->range.max); + break; case MLX5_FLOW_DESTINATION_TYPE_NONE: trace_seq_printf(p, "none\n"); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 26a23047f1f3..2d77fb8a8a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -103,11 +103,11 @@ struct page_pool; * size actually used at runtime, but it's not a problem when calculating static * array sizes. */ -#define MLX5_UMR_MAX_MTT_SPACE \ +#define MLX5_UMR_MAX_FLEX_SPACE \ (ALIGN_DOWN(MLX5_SEND_WQE_MAX_SIZE - sizeof(struct mlx5e_umr_wqe), \ - MLX5_UMR_MTT_ALIGNMENT)) + MLX5_UMR_FLEX_ALIGNMENT)) #define MLX5_MPWRQ_MAX_PAGES_PER_WQE \ - rounddown_pow_of_two(MLX5_UMR_MAX_MTT_SPACE / sizeof(struct mlx5_mtt)) + rounddown_pow_of_two(MLX5_UMR_MAX_FLEX_SPACE / sizeof(struct mlx5_mtt)) #define MLX5E_MAX_RQ_NUM_MTTS \ (ALIGN_DOWN(U16_MAX, 4) * 2) /* Fits into u16 and aligned by WQEBB. */ @@ -160,7 +160,7 @@ struct page_pool; (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm)) #define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\ - ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT) + ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT) #define MLX5E_MAX_KLM_PER_WQE(mdev) \ MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev)) @@ -344,6 +344,7 @@ enum { MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */ MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, /* set when mini_cqe_resp_stride_index cap is used */ MLX5E_RQ_STATE_SHAMPO, /* set when SHAMPO cap is used */ + MLX5E_RQ_STATE_MINI_CQE_ENHANCED, /* set when enhanced mini_cqe_cap is used */ }; struct mlx5e_cq { @@ -370,6 +371,7 @@ struct mlx5e_cq_decomp { u8 mini_arr_idx; u16 left; u16 wqe_counter; + bool last_cqe_title; } ____cacheline_aligned_in_smp; enum mlx5e_dma_map_type { @@ -1243,4 +1245,5 @@ int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_t int mlx5e_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); int mlx5e_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats); #endif +int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey); #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index b69f9d10ccbd..83adaabf59f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -51,13 +51,6 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) return ret; } -void mlx5e_devlink_port_type_eth_set(struct mlx5e_priv *priv) -{ - struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); - - devlink_port_type_eth_set(dl_port, priv->netdev); -} - void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) { struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); @@ -69,13 +62,3 @@ void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) devl_unlock(devlink); } - -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - - if (!netif_device_present(dev)) - return NULL; - - return mlx5e_devlink_get_dl_port(priv); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h index 10b50feb9883..4f238d4fff55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h @@ -9,8 +9,6 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv); void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv); -void mlx5e_devlink_port_type_eth_set(struct mlx5e_priv *priv); -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev); static inline struct devlink_port * mlx5e_devlink_get_dl_port(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index bf2741eb7f9b..379c6dc9a3be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -84,7 +84,8 @@ enum { MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1, #endif #ifdef CONFIG_MLX5_EN_IPSEC - MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1, + MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1, + MLX5E_ACCEL_FS_ESP_FT_LEVEL, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 29dd3a04c154..585bdc8383ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -107,7 +107,7 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, /* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */ max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB; max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe), - MLX5_UMR_MTT_ALIGNMENT) / umr_entry_size; + MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size; max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift; WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU); @@ -146,7 +146,7 @@ u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, u16 umr_wqe_sz; umr_wqe_sz = sizeof(struct mlx5e_umr_wqe) + - ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); + ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT); WARN_ON_ONCE(DIV_ROUND_UP(umr_wqe_sz, MLX5_SEND_WQE_DS) > MLX5_WQE_CTRL_DS_MASK); @@ -607,14 +607,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, params->log_rq_mtu_frames = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; - - mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n", - params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, - params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? - BIT(mlx5e_mpwqe_get_log_rq_size(mdev, params, NULL)) : - BIT(params->log_rq_mtu_frames), - BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)), - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); } void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params) @@ -852,6 +844,10 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { MLX5_SET(cqc, cqc, mini_cqe_res_format, hw_stridx ? MLX5_CQE_FORMAT_CSUM_STRIDX : MLX5_CQE_FORMAT_CSUM); + MLX5_SET(cqc, cqc, cqe_compression_layout, + MLX5_CAP_GEN(mdev, enhanced_cqe_compression) ? + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED : + MLX5_CQE_COMPRESS_LAYOUT_BASIC); MLX5_SET(cqc, cqc, cqe_comp_en, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 034debd140bc..c9be6eb88012 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -154,4 +154,18 @@ int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); int mlx5e_validate_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +static inline void mlx5e_params_print_info(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d %s)\n", + params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, + params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? + BIT(mlx5e_mpwqe_get_log_rq_size(mdev, params, NULL)) : + BIT(params->log_rq_mtu_frames), + BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)), + MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS), + MLX5_CAP_GEN(mdev, enhanced_cqe_compression) ? + "enhanced" : "basic"); +}; + #endif /* __MLX5_EN_PARAMS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index fac7e3ff2674..b08339d986d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -690,7 +690,6 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key); if (err) { - WARN_ON_ONCE(true); netdev_dbg(priv->netdev, "Couldn't find tunnel for tun_id: %d, err: %d\n", tun_id, err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c index 21aab96357b5..a278f52d52b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c @@ -28,4 +28,5 @@ tc_act_parse_accept(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_tc_act mlx5e_tc_act_accept = { .can_offload = tc_act_can_offload_accept, .parse_action = tc_act_parse_accept, + .is_terminating_action = true, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index 3337241cfd84..eba0c8698926 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -11,7 +11,7 @@ static struct mlx5e_tc_act *tc_acts_fdb[NUM_FLOW_ACTIONS] = { [FLOW_ACTION_DROP] = &mlx5e_tc_act_drop, [FLOW_ACTION_TRAP] = &mlx5e_tc_act_trap, [FLOW_ACTION_GOTO] = &mlx5e_tc_act_goto, - [FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_mirred, + [FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_redirect, [FLOW_ACTION_MIRRED] = &mlx5e_tc_act_mirred, [FLOW_ACTION_REDIRECT_INGRESS] = &mlx5e_tc_act_redirect_ingress, [FLOW_ACTION_VLAN_PUSH] = &mlx5e_tc_act_vlan, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index e1570ff056ae..8346557eeaf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -32,6 +32,11 @@ struct mlx5e_tc_act_parse_state { struct mlx5_tc_ct_priv *ct_priv; }; +struct mlx5e_tc_act_branch_ctrl { + enum flow_action_id act_id; + u32 extval; +}; + struct mlx5e_tc_act { bool (*can_offload)(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, @@ -60,6 +65,12 @@ struct mlx5e_tc_act { int (*stats_action)(struct mlx5e_priv *priv, struct flow_offload_action *fl_act); + + bool (*get_branch_ctrl)(const struct flow_action_entry *act, + struct mlx5e_tc_act_branch_ctrl *cond_true, + struct mlx5e_tc_act_branch_ctrl *cond_false); + + bool is_terminating_action; }; struct mlx5e_tc_flow_action { @@ -81,6 +92,7 @@ extern struct mlx5e_tc_act mlx5e_tc_act_vlan_mangle; extern struct mlx5e_tc_act mlx5e_tc_act_mpls_push; extern struct mlx5e_tc_act mlx5e_tc_act_mpls_pop; extern struct mlx5e_tc_act mlx5e_tc_act_mirred; +extern struct mlx5e_tc_act mlx5e_tc_act_redirect; extern struct mlx5e_tc_act mlx5e_tc_act_mirred_nic; extern struct mlx5e_tc_act mlx5e_tc_act_ct; extern struct mlx5e_tc_act mlx5e_tc_act_sample; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c index dd025a95c439..7d16aeabb119 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c @@ -27,4 +27,5 @@ tc_act_parse_drop(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_tc_act mlx5e_tc_act_drop = { .can_offload = tc_act_can_offload_drop, .parse_action = tc_act_parse_drop, + .is_terminating_action = true, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c index 25174f68613e..0923e6db2d0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c @@ -121,4 +121,5 @@ struct mlx5e_tc_act mlx5e_tc_act_goto = { .can_offload = tc_act_can_offload_goto, .parse_action = tc_act_parse_goto, .post_parse = tc_act_post_parse_goto, + .is_terminating_action = true, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index 4ac7de3f6afa..78c427b38048 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -334,4 +334,11 @@ tc_act_parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_tc_act mlx5e_tc_act_mirred = { .can_offload = tc_act_can_offload_mirred, .parse_action = tc_act_parse_mirred, + .is_terminating_action = false, +}; + +struct mlx5e_tc_act mlx5e_tc_act_redirect = { + .can_offload = tc_act_can_offload_mirred, + .parse_action = tc_act_parse_mirred, + .is_terminating_action = true, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c index 90b4c1b34776..7f409692b18f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c @@ -48,4 +48,5 @@ tc_act_parse_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_tc_act mlx5e_tc_act_mirred_nic = { .can_offload = tc_act_can_offload_mirred_nic, .parse_action = tc_act_parse_mirred_nic, + .is_terminating_action = true, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c index c8e5ca65bb6e..512d43148922 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c @@ -3,6 +3,45 @@ #include "act.h" #include "en/tc_priv.h" +#include "fs_core.h" + +static bool police_act_validate_control(enum flow_action_id act_id, + struct netlink_ext_ack *extack) +{ + if (act_id != FLOW_ACTION_PIPE && + act_id != FLOW_ACTION_ACCEPT && + act_id != FLOW_ACTION_JUMP && + act_id != FLOW_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, + "Offload not supported when conform-exceed action is not pipe, ok, jump or drop"); + return false; + } + + return true; +} + +static int police_act_validate(const struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + if (!police_act_validate_control(act->police.exceed.act_id, extack) || + !police_act_validate_control(act->police.notexceed.act_id, extack)) + return -EOPNOTSUPP; + + if (act->police.peakrate_bytes_ps || + act->police.avrate || act->police.overhead) { + NL_SET_ERR_MSG_MOD(extack, + "Offload not supported when peakrate/avrate/overhead is configured"); + return -EOPNOTSUPP; + } + + if (act->police.rate_pkt_ps) { + NL_SET_ERR_MSG_MOD(extack, + "QoS offload not support packets per second"); + return -EOPNOTSUPP; + } + + return 0; +} static bool tc_act_can_offload_police(struct mlx5e_tc_act_parse_state *parse_state, @@ -10,14 +49,10 @@ tc_act_can_offload_police(struct mlx5e_tc_act_parse_state *parse_state, int act_index, struct mlx5_flow_attr *attr) { - if (act->police.notexceed.act_id != FLOW_ACTION_PIPE && - act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) { - NL_SET_ERR_MSG_MOD(parse_state->extack, - "Offload not supported when conform action is not pipe or ok"); - return false; - } - if (mlx5e_policer_validate(parse_state->flow_action, act, - parse_state->extack)) + int err; + + err = police_act_validate(act, parse_state->extack); + if (err) return false; return !!mlx5e_get_flow_meters(parse_state->flow->priv->mdev); @@ -37,6 +72,8 @@ fill_meter_params_from_act(const struct flow_action_entry *act, params->mode = MLX5_RATE_LIMIT_PPS; params->rate = act->police.rate_pkt_ps; params->burst = act->police.burst_pkt; + } else if (act->police.mtu) { + params->mtu = act->police.mtu; } else { return -EOPNOTSUPP; } @@ -50,14 +87,25 @@ tc_act_parse_police(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { + enum mlx5_flow_namespace_type ns = mlx5e_get_flow_namespace(parse_state->flow); + struct mlx5e_flow_meter_params *params = &attr->meter_attr.params; int err; - err = fill_meter_params_from_act(act, &attr->meter_attr.params); + err = fill_meter_params_from_act(act, params); if (err) return err; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO; - attr->exe_aso_type = MLX5_EXE_ASO_FLOW_METER; + if (params->mtu) { + if (!(mlx5_fs_get_capabilities(priv->mdev, ns) & + MLX5_FLOW_STEERING_CAP_MATCH_RANGES)) + return -EOPNOTSUPP; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->flags |= MLX5_ATTR_FLAG_MTU; + } else { + attr->action |= MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO; + attr->exe_aso_type = MLX5_EXE_ASO_FLOW_METER; + } return 0; } @@ -79,7 +127,7 @@ tc_act_police_offload(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; int err = 0; - err = mlx5e_policer_validate(&fl_act->action, act, fl_act->extack); + err = police_act_validate(act, fl_act->extack); if (err) return err; @@ -147,6 +195,19 @@ tc_act_police_stats(struct mlx5e_priv *priv, return 0; } +static bool +tc_act_police_get_branch_ctrl(const struct flow_action_entry *act, + struct mlx5e_tc_act_branch_ctrl *cond_true, + struct mlx5e_tc_act_branch_ctrl *cond_false) +{ + cond_true->act_id = act->police.notexceed.act_id; + cond_true->extval = act->police.notexceed.extval; + + cond_false->act_id = act->police.exceed.act_id; + cond_false->extval = act->police.exceed.extval; + return true; +} + struct mlx5e_tc_act mlx5e_tc_act_police = { .can_offload = tc_act_can_offload_police, .parse_action = tc_act_parse_police, @@ -154,4 +215,5 @@ struct mlx5e_tc_act mlx5e_tc_act_police = { .offload_action = tc_act_police_offload, .destroy_action = tc_act_police_destroy, .stats_action = tc_act_police_stats, + .get_branch_ctrl = tc_act_police_get_branch_ctrl, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c index 53b270f652b9..915ce201aeb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c @@ -3,6 +3,7 @@ #include "act.h" #include "en/tc_priv.h" +#include "eswitch.h" static bool tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state, @@ -10,13 +11,6 @@ tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state, int act_index, struct mlx5_flow_attr *attr) { - struct netlink_ext_ack *extack = parse_state->extack; - - if (parse_state->flow_action->num_entries != 1) { - NL_SET_ERR_MSG_MOD(extack, "action trap is supported as a sole action only"); - return false; - } - return true; } @@ -27,7 +21,7 @@ tc_act_parse_trap(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *attr) { attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; + attr->dest_ft = mlx5_eswitch_get_slow_fdb(priv->mdev->priv.eswitch); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c index be74e1403328..78af8a3175bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c @@ -162,7 +162,6 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev, MLX5_ACCESS_ASO_OPC_MOD_FLOW_METER); aso_ctrl = &aso_wqe->aso_ctrl; - memset(aso_ctrl, 0, sizeof(*aso_ctrl)); aso_ctrl->data_mask_mode = MLX5_ASO_DATA_MASK_MODE_BYTEWISE_64BYTE << 6; aso_ctrl->condition_1_0_operand = MLX5_ASO_ALWAYS_TRUE | MLX5_ASO_ALWAYS_TRUE << 4; @@ -241,7 +240,7 @@ mlx5e_flow_meter_destroy_aso_obj(struct mlx5_core_dev *mdev, u32 obj_id) } static struct mlx5e_flow_meter_handle * -__mlx5e_flow_meter_alloc(struct mlx5e_flow_meters *flow_meters) +__mlx5e_flow_meter_alloc(struct mlx5e_flow_meters *flow_meters, bool alloc_aso) { struct mlx5_core_dev *mdev = flow_meters->mdev; struct mlx5e_flow_meter_aso_obj *meters_obj; @@ -257,16 +256,19 @@ __mlx5e_flow_meter_alloc(struct mlx5e_flow_meters *flow_meters) counter = mlx5_fc_create(mdev, true); if (IS_ERR(counter)) { err = PTR_ERR(counter); - goto err_red_counter; + goto err_drop_counter; } - meter->red_counter = counter; + meter->drop_counter = counter; counter = mlx5_fc_create(mdev, true); if (IS_ERR(counter)) { err = PTR_ERR(counter); - goto err_green_counter; + goto err_act_counter; } - meter->green_counter = counter; + meter->act_counter = counter; + + if (!alloc_aso) + goto no_aso; meters_obj = list_first_entry_or_null(&flow_meters->partial_list, struct mlx5e_flow_meter_aso_obj, @@ -300,11 +302,12 @@ __mlx5e_flow_meter_alloc(struct mlx5e_flow_meters *flow_meters) } bitmap_set(meters_obj->meters_map, pos, 1); - meter->flow_meters = flow_meters; meter->meters_obj = meters_obj; meter->obj_id = meters_obj->base_id + pos / 2; meter->idx = pos % 2; +no_aso: + meter->flow_meters = flow_meters; mlx5_core_dbg(mdev, "flow meter allocated, obj_id=0x%x, index=%d\n", meter->obj_id, meter->idx); @@ -313,10 +316,10 @@ __mlx5e_flow_meter_alloc(struct mlx5e_flow_meters *flow_meters) err_mem: mlx5e_flow_meter_destroy_aso_obj(mdev, id); err_create: - mlx5_fc_destroy(mdev, meter->green_counter); -err_green_counter: - mlx5_fc_destroy(mdev, meter->red_counter); -err_red_counter: + mlx5_fc_destroy(mdev, meter->act_counter); +err_act_counter: + mlx5_fc_destroy(mdev, meter->drop_counter); +err_drop_counter: kfree(meter); return ERR_PTR(err); } @@ -329,8 +332,11 @@ __mlx5e_flow_meter_free(struct mlx5e_flow_meter_handle *meter) struct mlx5e_flow_meter_aso_obj *meters_obj; int n, pos; - mlx5_fc_destroy(mdev, meter->green_counter); - mlx5_fc_destroy(mdev, meter->red_counter); + mlx5_fc_destroy(mdev, meter->act_counter); + mlx5_fc_destroy(mdev, meter->drop_counter); + + if (meter->params.mtu) + goto out_no_aso; meters_obj = meter->meters_obj; pos = (meter->obj_id - meters_obj->base_id) * 2 + meter->idx; @@ -345,6 +351,7 @@ __mlx5e_flow_meter_free(struct mlx5e_flow_meter_handle *meter) list_add(&meters_obj->entry, &flow_meters->partial_list); } +out_no_aso: mlx5_core_dbg(mdev, "flow meter freed, obj_id=0x%x, index=%d\n", meter->obj_id, meter->idx); kfree(meter); @@ -409,12 +416,13 @@ mlx5e_tc_meter_alloc(struct mlx5e_flow_meters *flow_meters, { struct mlx5e_flow_meter_handle *meter; - meter = __mlx5e_flow_meter_alloc(flow_meters); + meter = __mlx5e_flow_meter_alloc(flow_meters, !params->mtu); if (IS_ERR(meter)) return meter; hash_add(flow_meters->hashtbl, &meter->hlist, params->index); meter->params.index = params->index; + meter->params.mtu = params->mtu; meter->refcnt++; return meter; @@ -575,8 +583,8 @@ mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter, u64 bytes1, packets1, lastuse1; u64 bytes2, packets2, lastuse2; - mlx5_fc_query_cached(meter->green_counter, &bytes1, &packets1, &lastuse1); - mlx5_fc_query_cached(meter->red_counter, &bytes2, &packets2, &lastuse2); + mlx5_fc_query_cached(meter->act_counter, &bytes1, &packets1, &lastuse1); + mlx5_fc_query_cached(meter->drop_counter, &bytes2, &packets2, &lastuse2); *bytes = bytes1 + bytes2; *packets = packets1 + packets2; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h index 6de6e8a16327..9b795cd106bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h @@ -20,6 +20,7 @@ struct mlx5e_flow_meter_params { u32 index; u64 rate; u64 burst; + u32 mtu; }; struct mlx5e_flow_meter_handle { @@ -32,8 +33,8 @@ struct mlx5e_flow_meter_handle { struct hlist_node hlist; struct mlx5e_flow_meter_params params; - struct mlx5_fc *green_counter; - struct mlx5_fc *red_counter; + struct mlx5_fc *act_counter; + struct mlx5_fc *drop_counter; }; struct mlx5e_meter_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c index 8b77e822810e..8d7d761482d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c @@ -8,23 +8,56 @@ #define MLX5_PACKET_COLOR_BITS MLX5_REG_MAPPING_MBITS(PACKET_COLOR_TO_REG) #define MLX5_PACKET_COLOR_MASK MLX5_REG_MAPPING_MASK(PACKET_COLOR_TO_REG) -struct mlx5e_post_meter_priv { +struct mlx5e_post_meter_rate_table { + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct mlx5_flow_handle *green_rule; + struct mlx5_flow_attr *green_attr; + struct mlx5_flow_handle *red_rule; + struct mlx5_flow_attr *red_attr; +}; + +struct mlx5e_post_meter_mtu_table { struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; - struct mlx5_flow_handle *fwd_green_rule; - struct mlx5_flow_handle *drop_red_rule; + struct mlx5_flow_handle *rule; + struct mlx5_flow_attr *attr; +}; + +struct mlx5e_post_meter_mtu_tables { + struct mlx5e_post_meter_mtu_table green_table; + struct mlx5e_post_meter_mtu_table red_table; +}; + +struct mlx5e_post_meter_priv { + enum mlx5e_post_meter_type type; + union { + struct mlx5e_post_meter_rate_table rate_steering_table; + struct mlx5e_post_meter_mtu_tables mtu_tables; + }; }; struct mlx5_flow_table * mlx5e_post_meter_get_ft(struct mlx5e_post_meter_priv *post_meter) { - return post_meter->ft; + return post_meter->rate_steering_table.ft; } -static int +struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_true_ft(struct mlx5e_post_meter_priv *post_meter) +{ + return post_meter->mtu_tables.green_table.ft; +} + +struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_false_ft(struct mlx5e_post_meter_priv *post_meter) +{ + return post_meter->mtu_tables.red_table.ft; +} + +static struct mlx5_flow_table * mlx5e_post_meter_table_create(struct mlx5e_priv *priv, - enum mlx5_flow_namespace_type ns_type, - struct mlx5e_post_meter_priv *post_meter) + enum mlx5_flow_namespace_type ns_type) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_namespace *root_ns; @@ -32,7 +65,7 @@ mlx5e_post_meter_table_create(struct mlx5e_priv *priv, root_ns = mlx5_get_flow_namespace(priv->mdev, ns_type); if (!root_ns) { mlx5_core_warn(priv->mdev, "Failed to get namespace for flow meter\n"); - return -EOPNOTSUPP; + return ERR_PTR(-EOPNOTSUPP); } ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED; @@ -40,19 +73,14 @@ mlx5e_post_meter_table_create(struct mlx5e_priv *priv, ft_attr.max_fte = 2; ft_attr.level = 1; - post_meter->ft = mlx5_create_flow_table(root_ns, &ft_attr); - if (IS_ERR(post_meter->ft)) { - mlx5_core_warn(priv->mdev, "Failed to create post_meter table\n"); - return PTR_ERR(post_meter->ft); - } - - return 0; + return mlx5_create_flow_table(root_ns, &ft_attr); } static int -mlx5e_post_meter_fg_create(struct mlx5e_priv *priv, - struct mlx5e_post_meter_priv *post_meter) +mlx5e_post_meter_rate_fg_create(struct mlx5e_priv *priv, + struct mlx5e_post_meter_priv *post_meter) { + struct mlx5e_post_meter_rate_table *table = &post_meter->rate_steering_table; int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); void *misc2, *match_criteria; u32 *flow_group_in; @@ -71,25 +99,58 @@ mlx5e_post_meter_fg_create(struct mlx5e_priv *priv, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); - post_meter->fg = mlx5_create_flow_group(post_meter->ft, flow_group_in); - if (IS_ERR(post_meter->fg)) { + table->fg = mlx5_create_flow_group(table->ft, flow_group_in); + if (IS_ERR(table->fg)) { mlx5_core_warn(priv->mdev, "Failed to create post_meter flow group\n"); - err = PTR_ERR(post_meter->fg); + err = PTR_ERR(table->fg); } kvfree(flow_group_in); return err; } +static struct mlx5_flow_handle * +mlx5e_post_meter_add_rule(struct mlx5e_priv *priv, + struct mlx5e_post_meter_priv *post_meter, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_flow_handle *ret; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DROP) + attr->counter = drop_counter; + else + attr->counter = act_counter; + + attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT; + attr->outer_match_level = MLX5_MATCH_NONE; + attr->chain = 0; + attr->prio = 0; + + ret = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); + + /* We did not create the counter, so we can't delete it. + * Avoid freeing the counter when the attr is deleted in free_branching_attr + */ + attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT; + + return ret; +} + static int -mlx5e_post_meter_rules_create(struct mlx5e_priv *priv, - struct mlx5e_post_meter_priv *post_meter, - struct mlx5e_post_act *post_act, - struct mlx5_fc *green_counter, - struct mlx5_fc *red_counter) -{ - struct mlx5_flow_destination dest[2] = {}; - struct mlx5_flow_act flow_act = {}; +mlx5e_post_meter_rate_rules_create(struct mlx5e_priv *priv, + struct mlx5e_post_meter_priv *post_meter, + struct mlx5e_post_act *post_act, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter, + struct mlx5_flow_attr *green_attr, + struct mlx5_flow_attr *red_attr) +{ + struct mlx5e_post_meter_rate_table *table = &post_meter->rate_steering_table; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; int err; @@ -100,72 +161,242 @@ mlx5e_post_meter_rules_create(struct mlx5e_priv *priv, mlx5e_tc_match_to_reg_match(spec, PACKET_COLOR_TO_REG, MLX5_FLOW_METER_COLOR_RED, MLX5_PACKET_COLOR_MASK); - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; - dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[0].counter_id = mlx5_fc_id(red_counter); - - rule = mlx5_add_flow_rules(post_meter->ft, spec, &flow_act, dest, 1); + red_attr->ft = post_meter->rate_steering_table.ft; + rule = mlx5e_post_meter_add_rule(priv, post_meter, spec, red_attr, + act_counter, drop_counter); if (IS_ERR(rule)) { - mlx5_core_warn(priv->mdev, "Failed to create post_meter flow drop rule\n"); + mlx5_core_warn(priv->mdev, "Failed to create post_meter exceed rule\n"); err = PTR_ERR(rule); goto err_red; } - post_meter->drop_red_rule = rule; + table->red_rule = rule; + table->red_attr = red_attr; mlx5e_tc_match_to_reg_match(spec, PACKET_COLOR_TO_REG, MLX5_FLOW_METER_COLOR_GREEN, MLX5_PACKET_COLOR_MASK); - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest[0].ft = mlx5e_tc_post_act_get_ft(post_act); - dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[1].counter_id = mlx5_fc_id(green_counter); - - rule = mlx5_add_flow_rules(post_meter->ft, spec, &flow_act, dest, 2); + green_attr->ft = post_meter->rate_steering_table.ft; + rule = mlx5e_post_meter_add_rule(priv, post_meter, spec, green_attr, + act_counter, drop_counter); if (IS_ERR(rule)) { - mlx5_core_warn(priv->mdev, "Failed to create post_meter flow fwd rule\n"); + mlx5_core_warn(priv->mdev, "Failed to create post_meter notexceed rule\n"); err = PTR_ERR(rule); goto err_green; } - post_meter->fwd_green_rule = rule; + table->green_rule = rule; + table->green_attr = green_attr; kvfree(spec); return 0; err_green: - mlx5_del_flow_rules(post_meter->drop_red_rule); + mlx5_del_flow_rules(table->red_rule); err_red: kvfree(spec); return err; } static void -mlx5e_post_meter_rules_destroy(struct mlx5e_post_meter_priv *post_meter) +mlx5e_post_meter_rate_rules_destroy(struct mlx5_eswitch *esw, + struct mlx5e_post_meter_priv *post_meter) { - mlx5_del_flow_rules(post_meter->drop_red_rule); - mlx5_del_flow_rules(post_meter->fwd_green_rule); + struct mlx5e_post_meter_rate_table *rate_table = &post_meter->rate_steering_table; + + mlx5_eswitch_del_offloaded_rule(esw, rate_table->red_rule, rate_table->red_attr); + mlx5_eswitch_del_offloaded_rule(esw, rate_table->green_rule, rate_table->green_attr); } static void -mlx5e_post_meter_fg_destroy(struct mlx5e_post_meter_priv *post_meter) +mlx5e_post_meter_rate_fg_destroy(struct mlx5e_post_meter_priv *post_meter) { - mlx5_destroy_flow_group(post_meter->fg); + mlx5_destroy_flow_group(post_meter->rate_steering_table.fg); } static void -mlx5e_post_meter_table_destroy(struct mlx5e_post_meter_priv *post_meter) +mlx5e_post_meter_rate_table_destroy(struct mlx5e_post_meter_priv *post_meter) +{ + mlx5_destroy_flow_table(post_meter->rate_steering_table.ft); +} + +static void +mlx5e_post_meter_mtu_rules_destroy(struct mlx5e_post_meter_priv *post_meter) +{ + struct mlx5e_post_meter_mtu_tables *mtu_tables = &post_meter->mtu_tables; + + mlx5_del_flow_rules(mtu_tables->green_table.rule); + mlx5_del_flow_rules(mtu_tables->red_table.rule); +} + +static void +mlx5e_post_meter_mtu_fg_destroy(struct mlx5e_post_meter_priv *post_meter) +{ + struct mlx5e_post_meter_mtu_tables *mtu_tables = &post_meter->mtu_tables; + + mlx5_destroy_flow_group(mtu_tables->green_table.fg); + mlx5_destroy_flow_group(mtu_tables->red_table.fg); +} + +static void +mlx5e_post_meter_mtu_table_destroy(struct mlx5e_post_meter_priv *post_meter) +{ + struct mlx5e_post_meter_mtu_tables *mtu_tables = &post_meter->mtu_tables; + + mlx5_destroy_flow_table(mtu_tables->green_table.ft); + mlx5_destroy_flow_table(mtu_tables->red_table.ft); +} + +static int +mlx5e_post_meter_rate_create(struct mlx5e_priv *priv, + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter, + struct mlx5e_post_meter_priv *post_meter, + struct mlx5_flow_attr *green_attr, + struct mlx5_flow_attr *red_attr) +{ + struct mlx5_flow_table *ft; + int err; + + post_meter->type = MLX5E_POST_METER_RATE; + + ft = mlx5e_post_meter_table_create(priv, ns_type); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + mlx5_core_warn(priv->mdev, "Failed to create post_meter table\n"); + goto err_ft; + } + + post_meter->rate_steering_table.ft = ft; + + err = mlx5e_post_meter_rate_fg_create(priv, post_meter); + if (err) + goto err_fg; + + err = mlx5e_post_meter_rate_rules_create(priv, post_meter, post_act, + act_counter, drop_counter, + green_attr, red_attr); + if (err) + goto err_rules; + + return 0; + +err_rules: + mlx5e_post_meter_rate_fg_destroy(post_meter); +err_fg: + mlx5e_post_meter_rate_table_destroy(post_meter); +err_ft: + return err; +} + +static int +mlx5e_post_meter_create_mtu_table(struct mlx5e_priv *priv, + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_meter_mtu_table *table) { - mlx5_destroy_flow_table(post_meter->ft); + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *flow_group_in; + int err; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + table->ft = mlx5e_post_meter_table_create(priv, ns_type); + if (IS_ERR(table->ft)) { + err = PTR_ERR(table->ft); + goto err_ft; + } + + /* create miss group */ + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); + fg = mlx5_create_flow_group(table->ft, flow_group_in); + if (IS_ERR(fg)) { + err = PTR_ERR(fg); + goto err_miss_grp; + } + table->fg = fg; + + kvfree(flow_group_in); + return 0; + +err_miss_grp: + mlx5_destroy_flow_table(table->ft); +err_ft: + kvfree(flow_group_in); + return err; +} + +static int +mlx5e_post_meter_mtu_create(struct mlx5e_priv *priv, + enum mlx5_flow_namespace_type ns_type, + struct mlx5e_post_act *post_act, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter, + struct mlx5e_post_meter_priv *post_meter, + struct mlx5_flow_attr *green_attr, + struct mlx5_flow_attr *red_attr) +{ + struct mlx5e_post_meter_mtu_tables *mtu_tables = &post_meter->mtu_tables; + static struct mlx5_flow_spec zero_spec = {}; + struct mlx5_flow_handle *rule; + int err; + + post_meter->type = MLX5E_POST_METER_MTU; + + err = mlx5e_post_meter_create_mtu_table(priv, ns_type, &mtu_tables->green_table); + if (err) + goto err_green_ft; + + green_attr->ft = mtu_tables->green_table.ft; + rule = mlx5e_post_meter_add_rule(priv, post_meter, &zero_spec, green_attr, + act_counter, drop_counter); + if (IS_ERR(rule)) { + mlx5_core_warn(priv->mdev, "Failed to create post_meter conform rule\n"); + err = PTR_ERR(rule); + goto err_green_rule; + } + mtu_tables->green_table.rule = rule; + mtu_tables->green_table.attr = green_attr; + + err = mlx5e_post_meter_create_mtu_table(priv, ns_type, &mtu_tables->red_table); + if (err) + goto err_red_ft; + + red_attr->ft = mtu_tables->red_table.ft; + rule = mlx5e_post_meter_add_rule(priv, post_meter, &zero_spec, red_attr, + act_counter, drop_counter); + if (IS_ERR(rule)) { + mlx5_core_warn(priv->mdev, "Failed to create post_meter exceed rule\n"); + err = PTR_ERR(rule); + goto err_red_rule; + } + mtu_tables->red_table.rule = rule; + mtu_tables->red_table.attr = red_attr; + + return 0; + +err_red_rule: + mlx5_destroy_flow_table(mtu_tables->red_table.ft); +err_red_ft: + mlx5_del_flow_rules(mtu_tables->green_table.rule); +err_green_rule: + mlx5_destroy_flow_table(mtu_tables->green_table.ft); +err_green_ft: + return err; } struct mlx5e_post_meter_priv * mlx5e_post_meter_init(struct mlx5e_priv *priv, enum mlx5_flow_namespace_type ns_type, struct mlx5e_post_act *post_act, - struct mlx5_fc *green_counter, - struct mlx5_fc *red_counter) + enum mlx5e_post_meter_type type, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter, + struct mlx5_flow_attr *branch_true, + struct mlx5_flow_attr *branch_false) { struct mlx5e_post_meter_priv *post_meter; int err; @@ -174,36 +405,55 @@ mlx5e_post_meter_init(struct mlx5e_priv *priv, if (!post_meter) return ERR_PTR(-ENOMEM); - err = mlx5e_post_meter_table_create(priv, ns_type, post_meter); - if (err) - goto err_ft; - - err = mlx5e_post_meter_fg_create(priv, post_meter); - if (err) - goto err_fg; + switch (type) { + case MLX5E_POST_METER_MTU: + err = mlx5e_post_meter_mtu_create(priv, ns_type, post_act, + act_counter, drop_counter, post_meter, + branch_true, branch_false); + break; + case MLX5E_POST_METER_RATE: + err = mlx5e_post_meter_rate_create(priv, ns_type, post_act, + act_counter, drop_counter, post_meter, + branch_true, branch_false); + break; + default: + err = -EOPNOTSUPP; + } - err = mlx5e_post_meter_rules_create(priv, post_meter, post_act, green_counter, - red_counter); if (err) - goto err_rules; + goto err; return post_meter; -err_rules: - mlx5e_post_meter_fg_destroy(post_meter); -err_fg: - mlx5e_post_meter_table_destroy(post_meter); -err_ft: +err: kfree(post_meter); return ERR_PTR(err); } +static void +mlx5e_post_meter_rate_destroy(struct mlx5_eswitch *esw, struct mlx5e_post_meter_priv *post_meter) +{ + mlx5e_post_meter_rate_rules_destroy(esw, post_meter); + mlx5e_post_meter_rate_fg_destroy(post_meter); + mlx5e_post_meter_rate_table_destroy(post_meter); +} + +static void +mlx5e_post_meter_mtu_destroy(struct mlx5e_post_meter_priv *post_meter) +{ + mlx5e_post_meter_mtu_rules_destroy(post_meter); + mlx5e_post_meter_mtu_fg_destroy(post_meter); + mlx5e_post_meter_mtu_table_destroy(post_meter); +} + void -mlx5e_post_meter_cleanup(struct mlx5e_post_meter_priv *post_meter) +mlx5e_post_meter_cleanup(struct mlx5_eswitch *esw, struct mlx5e_post_meter_priv *post_meter) { - mlx5e_post_meter_rules_destroy(post_meter); - mlx5e_post_meter_fg_destroy(post_meter); - mlx5e_post_meter_table_destroy(post_meter); + if (post_meter->type == MLX5E_POST_METER_RATE) + mlx5e_post_meter_rate_destroy(esw, post_meter); + else + mlx5e_post_meter_mtu_destroy(post_meter); + kfree(post_meter); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.h index 34d0e4b9fc7a..e013b77186b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.h @@ -14,16 +14,49 @@ struct mlx5e_post_meter_priv; +enum mlx5e_post_meter_type { + MLX5E_POST_METER_RATE = 0, + MLX5E_POST_METER_MTU +}; + +#if IS_ENABLED(CONFIG_MLX5_CLS_ACT) + struct mlx5_flow_table * mlx5e_post_meter_get_ft(struct mlx5e_post_meter_priv *post_meter); +struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_true_ft(struct mlx5e_post_meter_priv *post_meter); + +struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_false_ft(struct mlx5e_post_meter_priv *post_meter); + struct mlx5e_post_meter_priv * mlx5e_post_meter_init(struct mlx5e_priv *priv, enum mlx5_flow_namespace_type ns_type, struct mlx5e_post_act *post_act, - struct mlx5_fc *green_counter, - struct mlx5_fc *red_counter); + enum mlx5e_post_meter_type type, + struct mlx5_fc *act_counter, + struct mlx5_fc *drop_counter, + struct mlx5_flow_attr *branch_true, + struct mlx5_flow_attr *branch_false); + void -mlx5e_post_meter_cleanup(struct mlx5e_post_meter_priv *post_meter); +mlx5e_post_meter_cleanup(struct mlx5_eswitch *esw, struct mlx5e_post_meter_priv *post_meter); + +#else /* CONFIG_MLX5_CLS_ACT */ + +static inline struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_true_ft(struct mlx5e_post_meter_priv *post_meter) +{ + return NULL; +} + +static inline struct mlx5_flow_table * +mlx5e_post_meter_get_mtu_false_ft(struct mlx5e_post_meter_priv *post_meter) +{ + return NULL; +} + +#endif #endif /* __MLX5_EN_POST_METER_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 864ce0c393e6..a69849e0deed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1774,35 +1774,42 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) /* We translate the tc filter with CT action to the following HW model: * - * +---------------------+ - * + ft prio (tc chain) + - * + original match + - * +---------------------+ - * | set chain miss mapping - * | set fte_id - * | set tunnel_id - * | do decap - * v - * +---------------------+ - * + pre_ct/pre_ct_nat + if matches +-------------------------+ - * + zone+nat match +---------------->+ post_act (see below) + - * +---------------------+ set zone +-------------------------+ - * | set zone - * v - * +--------------------+ - * + CT (nat or no nat) + - * + tuple + zone match + - * +--------------------+ - * | set mark - * | set labels_id - * | set established - * | set zone_restore - * | do nat (if needed) - * v - * +--------------+ - * + post_act + original filter actions - * + fte_id match +------------------------> - * +--------------+ + * +---------------------+ + * + ft prio (tc chain) + + * + original match + + * +---------------------+ + * | set chain miss mapping + * | set fte_id + * | set tunnel_id + * | do decap + * | + * +-------------+ + * | Chain 0 | + * | optimization| + * | v + * | +---------------------+ + * | + pre_ct/pre_ct_nat + if matches +----------------------+ + * | + zone+nat match +---------------->+ post_act (see below) + + * | +---------------------+ set zone +----------------------+ + * | | + * +-------------+ set zone + * | + * v + * +--------------------+ + * + CT (nat or no nat) + + * + tuple + zone match + + * +--------------------+ + * | set mark + * | set labels_id + * | set established + * | set zone_restore + * | do nat (if needed) + * v + * +--------------+ + * + post_act + original filter actions + * + fte_id match +------------------------> + * +--------------+ + * */ static struct mlx5_flow_handle * __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, @@ -1818,6 +1825,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_flow *ct_flow; int chain_mapping = 0, err; struct mlx5_ct_ft *ft; + u16 zone; ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL); if (!ct_flow) { @@ -1884,6 +1892,25 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } } + /* Change original rule point to ct table + * Chain 0 sets the zone and jumps to ct table + * Other chains jump to pre_ct table to align with act_ct cached logic + */ + pre_ct_attr->dest_chain = 0; + if (!attr->chain) { + zone = ft->zone & MLX5_CT_ZONE_MASK; + err = mlx5e_tc_match_to_reg_set(priv->mdev, pre_mod_acts, ct_priv->ns_type, + ZONE_TO_REG, zone); + if (err) { + ct_dbg("Failed to set zone register mapping"); + goto err_mapping; + } + + pre_ct_attr->dest_ft = nat ? ct_priv->ct_nat : ct_priv->ct; + } else { + pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft; + } + mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, pre_mod_acts->num_actions, pre_mod_acts->actions); @@ -1893,10 +1920,6 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, goto err_mapping; } pre_ct_attr->modify_hdr = mod_hdr; - - /* Change original rule point to ct table */ - pre_ct_attr->dest_chain = 0; - pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft; ct_flow->pre_ct_rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); if (IS_ERR(ct_flow->pre_ct_rule)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 2e42d7c5451e..2b7fd1c0e643 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -211,8 +211,4 @@ struct mlx5e_flow_meters *mlx5e_get_flow_meters(struct mlx5_core_dev *dev); void *mlx5e_get_match_headers_value(u32 flags, struct mlx5_flow_spec *spec); void *mlx5e_get_match_headers_criteria(u32 flags, struct mlx5_flow_spec *spec); -int mlx5e_policer_validate(const struct flow_action *action, - const struct flow_action_entry *act, - struct netlink_ext_ack *extack); - #endif /* __MLX5_EN_TC_PRIV_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index a715601865d3..bb9023957f74 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -45,55 +45,9 @@ static struct mlx5e_ipsec_sa_entry *to_ipsec_sa_entry(struct xfrm_state *x) return (struct mlx5e_ipsec_sa_entry *)x->xso.offload_handle; } -struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *ipsec, - unsigned int handle) +static struct mlx5e_ipsec_pol_entry *to_ipsec_pol_entry(struct xfrm_policy *x) { - struct mlx5e_ipsec_sa_entry *sa_entry; - struct xfrm_state *ret = NULL; - - rcu_read_lock(); - hash_for_each_possible_rcu(ipsec->sadb_rx, sa_entry, hlist, handle) - if (sa_entry->handle == handle) { - ret = sa_entry->x; - xfrm_state_hold(ret); - break; - } - rcu_read_unlock(); - - return ret; -} - -static int mlx5e_ipsec_sadb_rx_add(struct mlx5e_ipsec_sa_entry *sa_entry) -{ - unsigned int handle = sa_entry->ipsec_obj_id; - struct mlx5e_ipsec *ipsec = sa_entry->ipsec; - struct mlx5e_ipsec_sa_entry *_sa_entry; - unsigned long flags; - - rcu_read_lock(); - hash_for_each_possible_rcu(ipsec->sadb_rx, _sa_entry, hlist, handle) - if (_sa_entry->handle == handle) { - rcu_read_unlock(); - return -EEXIST; - } - rcu_read_unlock(); - - spin_lock_irqsave(&ipsec->sadb_rx_lock, flags); - sa_entry->handle = handle; - hash_add_rcu(ipsec->sadb_rx, &sa_entry->hlist, sa_entry->handle); - spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags); - - return 0; -} - -static void mlx5e_ipsec_sadb_rx_del(struct mlx5e_ipsec_sa_entry *sa_entry) -{ - struct mlx5e_ipsec *ipsec = sa_entry->ipsec; - unsigned long flags; - - spin_lock_irqsave(&ipsec->sadb_rx_lock, flags); - hash_del_rcu(&sa_entry->hlist); - spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags); + return (struct mlx5e_ipsec_pol_entry *)x->xdo.offload_handle; } static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) @@ -129,9 +83,33 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) return false; } -static void -mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, - struct mlx5_accel_esp_xfrm_attrs *attrs) +static void mlx5e_ipsec_init_limits(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_accel_esp_xfrm_attrs *attrs) +{ + struct xfrm_state *x = sa_entry->x; + + attrs->hard_packet_limit = x->lft.hard_packet_limit; + if (x->lft.soft_packet_limit == XFRM_INF) + return; + + /* Hardware decrements hard_packet_limit counter through + * the operation. While fires an event when soft_packet_limit + * is reached. It emans that we need substitute the numbers + * in order to properly count soft limit. + * + * As an example: + * XFRM user sets soft limit is 2 and hard limit is 9 and + * expects to see soft event after 2 packets and hard event + * after 9 packets. In our case, the hard limit will be set + * to 9 and soft limit is comparator to 7 so user gets the + * soft event after 2 packeta + */ + attrs->soft_packet_limit = + x->lft.hard_packet_limit - x->lft.soft_packet_limit; +} + +void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_accel_esp_xfrm_attrs *attrs) { struct xfrm_state *x = sa_entry->x; struct aes_gcm_keymat *aes_gcm = &attrs->aes_gcm; @@ -157,33 +135,31 @@ mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, memcpy(&aes_gcm->salt, x->aead->alg_key + key_len, sizeof(aes_gcm->salt)); + attrs->authsize = crypto_aead_authsize(aead) / 4; /* in dwords */ + /* iv len */ aes_gcm->icv_len = x->aead->alg_icv_len; /* esn */ if (sa_entry->esn_state.trigger) { - attrs->flags |= MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED; + attrs->esn_trigger = true; attrs->esn = sa_entry->esn_state.esn; - if (sa_entry->esn_state.overlap) - attrs->flags |= MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP; + attrs->esn_overlap = sa_entry->esn_state.overlap; + attrs->replay_window = x->replay_esn->replay_window; } - /* action */ - attrs->action = (x->xso.dir == XFRM_DEV_OFFLOAD_OUT) ? - MLX5_ACCEL_ESP_ACTION_ENCRYPT : - MLX5_ACCEL_ESP_ACTION_DECRYPT; - /* flags */ - attrs->flags |= (x->props.mode == XFRM_MODE_TRANSPORT) ? - MLX5_ACCEL_ESP_FLAGS_TRANSPORT : - MLX5_ACCEL_ESP_FLAGS_TUNNEL; - + attrs->dir = x->xso.dir; /* spi */ attrs->spi = be32_to_cpu(x->id.spi); /* source , destination ips */ memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr)); memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr)); - attrs->is_ipv6 = (x->props.family != AF_INET); + attrs->family = x->props.family; + attrs->type = x->xso.type; + attrs->reqid = x->props.reqid; + + mlx5e_ipsec_init_limits(sa_entry, attrs); } static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x) @@ -215,11 +191,6 @@ static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x) netdev_info(netdev, "Only IPv4/6 xfrm states may be offloaded\n"); return -EINVAL; } - if (x->props.mode != XFRM_MODE_TRANSPORT && - x->props.mode != XFRM_MODE_TUNNEL) { - dev_info(&netdev->dev, "Only transport and tunnel xfrm states may be offloaded\n"); - return -EINVAL; - } if (x->id.proto != IPPROTO_ESP) { netdev_info(netdev, "Only ESP xfrm state may be offloaded\n"); return -EINVAL; @@ -253,6 +224,67 @@ static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x) netdev_info(netdev, "Cannot offload xfrm states with geniv other than seqiv\n"); return -EINVAL; } + switch (x->xso.type) { + case XFRM_DEV_OFFLOAD_CRYPTO: + if (!(mlx5_ipsec_device_caps(priv->mdev) & + MLX5_IPSEC_CAP_CRYPTO)) { + netdev_info(netdev, "Crypto offload is not supported\n"); + return -EINVAL; + } + + if (x->props.mode != XFRM_MODE_TRANSPORT && + x->props.mode != XFRM_MODE_TUNNEL) { + netdev_info(netdev, "Only transport and tunnel xfrm states may be offloaded\n"); + return -EINVAL; + } + break; + case XFRM_DEV_OFFLOAD_PACKET: + if (!(mlx5_ipsec_device_caps(priv->mdev) & + MLX5_IPSEC_CAP_PACKET_OFFLOAD)) { + netdev_info(netdev, "Packet offload is not supported\n"); + return -EINVAL; + } + + if (x->props.mode != XFRM_MODE_TRANSPORT) { + netdev_info(netdev, "Only transport xfrm states may be offloaded in packet mode\n"); + return -EINVAL; + } + + if (x->replay_esn && x->replay_esn->replay_window != 32 && + x->replay_esn->replay_window != 64 && + x->replay_esn->replay_window != 128 && + x->replay_esn->replay_window != 256) { + netdev_info(netdev, + "Unsupported replay window size %u\n", + x->replay_esn->replay_window); + return -EINVAL; + } + + if (!x->props.reqid) { + netdev_info(netdev, "Cannot offload without reqid\n"); + return -EINVAL; + } + + if (x->lft.hard_byte_limit != XFRM_INF || + x->lft.soft_byte_limit != XFRM_INF) { + netdev_info(netdev, + "Device doesn't support limits in bytes\n"); + return -EINVAL; + } + + if (x->lft.soft_packet_limit >= x->lft.hard_packet_limit && + x->lft.hard_packet_limit != XFRM_INF) { + /* XFRM stack doesn't prevent such configuration :(. */ + netdev_info(netdev, + "Hard packet limit must be greater than soft one\n"); + return -EINVAL; + } + break; + default: + netdev_info(netdev, "Unsupported xfrm offload type %d\n", + x->xso.type); + return -EINVAL; + } return 0; } @@ -270,6 +302,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = NULL; struct net_device *netdev = x->xso.real_dev; + struct mlx5e_ipsec *ipsec; struct mlx5e_priv *priv; int err; @@ -277,6 +310,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) if (!priv->ipsec) return -EOPNOTSUPP; + ipsec = priv->ipsec; err = mlx5e_xfrm_validate_state(x); if (err) return err; @@ -288,7 +322,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) } sa_entry->x = x; - sa_entry->ipsec = priv->ipsec; + sa_entry->ipsec = ipsec; /* check esn */ mlx5e_ipsec_update_esn_state(sa_entry); @@ -299,25 +333,29 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) if (err) goto err_xfrm; - err = mlx5e_accel_ipsec_fs_add_rule(priv, sa_entry); + err = mlx5e_accel_ipsec_fs_add_rule(sa_entry); if (err) goto err_hw_ctx; - if (x->xso.dir == XFRM_DEV_OFFLOAD_IN) { - err = mlx5e_ipsec_sadb_rx_add(sa_entry); - if (err) - goto err_add_rule; - } else { + /* We use *_bh() variant because xfrm_timer_handler(), which runs + * in softirq context, can reach our state delete logic and we need + * xa_erase_bh() there. + */ + err = xa_insert_bh(&ipsec->sadb, sa_entry->ipsec_obj_id, sa_entry, + GFP_KERNEL); + if (err) + goto err_add_rule; + + if (x->xso.dir == XFRM_DEV_OFFLOAD_OUT) sa_entry->set_iv_op = (x->props.flags & XFRM_STATE_ESN) ? mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv; - } INIT_WORK(&sa_entry->modify_work.work, _update_xfrm_state); x->xso.offload_handle = (unsigned long)sa_entry; - goto out; + return 0; err_add_rule: - mlx5e_accel_ipsec_fs_del_rule(priv, sa_entry); + mlx5e_accel_ipsec_fs_del_rule(sa_entry); err_hw_ctx: mlx5_ipsec_free_sa_ctx(sa_entry); err_xfrm: @@ -329,59 +367,69 @@ out: static void mlx5e_xfrm_del_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5e_ipsec_sa_entry *old; - if (x->xso.dir == XFRM_DEV_OFFLOAD_IN) - mlx5e_ipsec_sadb_rx_del(sa_entry); + old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id); + WARN_ON(old != sa_entry); } static void mlx5e_xfrm_free_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); - struct mlx5e_priv *priv = netdev_priv(x->xso.dev); cancel_work_sync(&sa_entry->modify_work.work); - mlx5e_accel_ipsec_fs_del_rule(priv, sa_entry); + mlx5e_accel_ipsec_fs_del_rule(sa_entry); mlx5_ipsec_free_sa_ctx(sa_entry); kfree(sa_entry); } -int mlx5e_ipsec_init(struct mlx5e_priv *priv) +void mlx5e_ipsec_init(struct mlx5e_priv *priv) { struct mlx5e_ipsec *ipsec; - int ret; + int ret = -ENOMEM; if (!mlx5_ipsec_device_caps(priv->mdev)) { netdev_dbg(priv->netdev, "Not an IPSec offload device\n"); - return 0; + return; } ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL); if (!ipsec) - return -ENOMEM; + return; - hash_init(ipsec->sadb_rx); - spin_lock_init(&ipsec->sadb_rx_lock); + xa_init_flags(&ipsec->sadb, XA_FLAGS_ALLOC); ipsec->mdev = priv->mdev; ipsec->wq = alloc_ordered_workqueue("mlx5e_ipsec: %s", 0, priv->netdev->name); - if (!ipsec->wq) { - ret = -ENOMEM; + if (!ipsec->wq) goto err_wq; + + if (mlx5_ipsec_device_caps(priv->mdev) & + MLX5_IPSEC_CAP_PACKET_OFFLOAD) { + ret = mlx5e_ipsec_aso_init(ipsec); + if (ret) + goto err_aso; } ret = mlx5e_accel_ipsec_fs_init(ipsec); if (ret) goto err_fs_init; + ipsec->fs = priv->fs; priv->ipsec = ipsec; netdev_dbg(priv->netdev, "IPSec attached to netdevice\n"); - return 0; + return; err_fs_init: + if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + mlx5e_ipsec_aso_cleanup(ipsec); +err_aso: destroy_workqueue(ipsec->wq); err_wq: kfree(ipsec); - return (ret != -EOPNOTSUPP) ? ret : 0; + mlx5_core_err(priv->mdev, "IPSec initialization failed, %d\n", ret); + return; } void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) @@ -392,6 +440,8 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) return; mlx5e_accel_ipsec_fs_cleanup(ipsec); + if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + mlx5e_ipsec_aso_cleanup(ipsec); destroy_workqueue(ipsec->wq); kfree(ipsec); priv->ipsec = NULL; @@ -427,6 +477,122 @@ static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x) queue_work(sa_entry->ipsec->wq, &modify_work->work); } +static void mlx5e_xfrm_update_curlft(struct xfrm_state *x) +{ + struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); + int err; + + lockdep_assert_held(&x->lock); + + if (sa_entry->attrs.soft_packet_limit == XFRM_INF) + /* Limits are not configured, as soft limit + * must be lowever than hard limit. + */ + return; + + err = mlx5e_ipsec_aso_query(sa_entry, NULL); + if (err) + return; + + mlx5e_ipsec_aso_update_curlft(sa_entry, &x->curlft.packets); +} + +static int mlx5e_xfrm_validate_policy(struct xfrm_policy *x) +{ + struct net_device *netdev = x->xdo.real_dev; + + if (x->type != XFRM_POLICY_TYPE_MAIN) { + netdev_info(netdev, "Cannot offload non-main policy types\n"); + return -EINVAL; + } + + /* Please pay attention that we support only one template */ + if (x->xfrm_nr > 1) { + netdev_info(netdev, "Cannot offload more than one template\n"); + return -EINVAL; + } + + if (x->xdo.dir != XFRM_DEV_OFFLOAD_IN && + x->xdo.dir != XFRM_DEV_OFFLOAD_OUT) { + netdev_info(netdev, "Cannot offload forward policy\n"); + return -EINVAL; + } + + if (!x->xfrm_vec[0].reqid) { + netdev_info(netdev, "Cannot offload policy without reqid\n"); + return -EINVAL; + } + + if (x->xdo.type != XFRM_DEV_OFFLOAD_PACKET) { + netdev_info(netdev, "Unsupported xfrm offload type\n"); + return -EINVAL; + } + + return 0; +} + +static void +mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry, + struct mlx5_accel_pol_xfrm_attrs *attrs) +{ + struct xfrm_policy *x = pol_entry->x; + struct xfrm_selector *sel; + + sel = &x->selector; + memset(attrs, 0, sizeof(*attrs)); + + memcpy(&attrs->saddr, sel->saddr.a6, sizeof(attrs->saddr)); + memcpy(&attrs->daddr, sel->daddr.a6, sizeof(attrs->daddr)); + attrs->family = sel->family; + attrs->dir = x->xdo.dir; + attrs->action = x->action; + attrs->type = XFRM_DEV_OFFLOAD_PACKET; + attrs->reqid = x->xfrm_vec[0].reqid; +} + +static int mlx5e_xfrm_add_policy(struct xfrm_policy *x) +{ + struct net_device *netdev = x->xdo.real_dev; + struct mlx5e_ipsec_pol_entry *pol_entry; + struct mlx5e_priv *priv; + int err; + + priv = netdev_priv(netdev); + if (!priv->ipsec) + return -EOPNOTSUPP; + + err = mlx5e_xfrm_validate_policy(x); + if (err) + return err; + + pol_entry = kzalloc(sizeof(*pol_entry), GFP_KERNEL); + if (!pol_entry) + return -ENOMEM; + + pol_entry->x = x; + pol_entry->ipsec = priv->ipsec; + + mlx5e_ipsec_build_accel_pol_attrs(pol_entry, &pol_entry->attrs); + err = mlx5e_accel_ipsec_fs_add_pol(pol_entry); + if (err) + goto err_fs; + + x->xdo.offload_handle = (unsigned long)pol_entry; + return 0; + +err_fs: + kfree(pol_entry); + return err; +} + +static void mlx5e_xfrm_free_policy(struct xfrm_policy *x) +{ + struct mlx5e_ipsec_pol_entry *pol_entry = to_ipsec_pol_entry(x); + + mlx5e_accel_ipsec_fs_del_pol(pol_entry); + kfree(pol_entry); +} + static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_add = mlx5e_xfrm_add_state, .xdo_dev_state_delete = mlx5e_xfrm_del_state, @@ -435,6 +601,18 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, }; +static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { + .xdo_dev_state_add = mlx5e_xfrm_add_state, + .xdo_dev_state_delete = mlx5e_xfrm_del_state, + .xdo_dev_state_free = mlx5e_xfrm_free_state, + .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, + .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, + + .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, + .xdo_dev_policy_add = mlx5e_xfrm_add_policy, + .xdo_dev_policy_free = mlx5e_xfrm_free_policy, +}; + void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -444,7 +622,12 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) return; mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n"); - netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; + + if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops; + else + netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; + netdev->features |= NETIF_F_HW_ESP; netdev->hw_enc_features |= NETIF_F_HW_ESP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 16bcceec16c4..a92e19c4c499 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -34,27 +34,14 @@ #ifndef __MLX5E_IPSEC_H__ #define __MLX5E_IPSEC_H__ -#ifdef CONFIG_MLX5_EN_IPSEC - #include <linux/mlx5/device.h> #include <net/xfrm.h> #include <linux/idr.h> +#include "lib/aso.h" #define MLX5E_IPSEC_SADB_RX_BITS 10 #define MLX5E_IPSEC_ESN_SCOPE_MID 0x80000000L -enum mlx5_accel_esp_flags { - MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ - MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, - MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED = 1UL << 1, - MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2, -}; - -enum mlx5_accel_esp_action { - MLX5_ACCEL_ESP_ACTION_DECRYPT, - MLX5_ACCEL_ESP_ACTION_ENCRYPT, -}; - struct aes_gcm_keymat { u64 seq_iv; @@ -66,7 +53,6 @@ struct aes_gcm_keymat { }; struct mlx5_accel_esp_xfrm_attrs { - enum mlx5_accel_esp_action action; u32 esn; u32 spi; u32 flags; @@ -82,16 +68,37 @@ struct mlx5_accel_esp_xfrm_attrs { __be32 a6[4]; } daddr; - u8 is_ipv6; + u8 dir : 2; + u8 esn_overlap : 1; + u8 esn_trigger : 1; + u8 type : 2; + u8 family; + u32 replay_window; + u32 authsize; + u32 reqid; + u64 hard_packet_limit; + u64 soft_packet_limit; }; enum mlx5_ipsec_cap { MLX5_IPSEC_CAP_CRYPTO = 1 << 0, MLX5_IPSEC_CAP_ESN = 1 << 1, + MLX5_IPSEC_CAP_PACKET_OFFLOAD = 1 << 2, }; struct mlx5e_priv; +struct mlx5e_ipsec_hw_stats { + u64 ipsec_rx_pkts; + u64 ipsec_rx_bytes; + u64 ipsec_rx_drop_pkts; + u64 ipsec_rx_drop_bytes; + u64 ipsec_tx_pkts; + u64 ipsec_tx_bytes; + u64 ipsec_tx_drop_pkts; + u64 ipsec_tx_drop_bytes; +}; + struct mlx5e_ipsec_sw_stats { atomic64_t ipsec_rx_drop_sp_alloc; atomic64_t ipsec_rx_drop_sadb_miss; @@ -102,17 +109,38 @@ struct mlx5e_ipsec_sw_stats { atomic64_t ipsec_tx_drop_trailer; }; -struct mlx5e_accel_fs_esp; +struct mlx5e_ipsec_rx; struct mlx5e_ipsec_tx; +struct mlx5e_ipsec_work { + struct work_struct work; + struct mlx5e_ipsec *ipsec; + u32 id; +}; + +struct mlx5e_ipsec_aso { + u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)]; + dma_addr_t dma_addr; + struct mlx5_aso *aso; + /* IPsec ASO caches data on every query call, + * so in nested calls, we can use this boolean to save + * recursive calls to mlx5e_ipsec_aso_query() + */ + u8 use_cache : 1; +}; + struct mlx5e_ipsec { struct mlx5_core_dev *mdev; - DECLARE_HASHTABLE(sadb_rx, MLX5E_IPSEC_SADB_RX_BITS); - spinlock_t sadb_rx_lock; /* Protects sadb_rx */ + struct xarray sadb; struct mlx5e_ipsec_sw_stats sw_stats; + struct mlx5e_ipsec_hw_stats hw_stats; struct workqueue_struct *wq; - struct mlx5e_accel_fs_esp *rx_fs; - struct mlx5e_ipsec_tx *tx_fs; + struct mlx5e_flow_steering *fs; + struct mlx5e_ipsec_rx *rx_ipv4; + struct mlx5e_ipsec_rx *rx_ipv6; + struct mlx5e_ipsec_tx *tx; + struct mlx5e_ipsec_aso *aso; + struct notifier_block nb; }; struct mlx5e_ipsec_esn_state { @@ -123,7 +151,8 @@ struct mlx5e_ipsec_esn_state { struct mlx5e_ipsec_rule { struct mlx5_flow_handle *rule; - struct mlx5_modify_hdr *set_modify_hdr; + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; }; struct mlx5e_ipsec_modify_state_work { @@ -132,9 +161,7 @@ struct mlx5e_ipsec_modify_state_work { }; struct mlx5e_ipsec_sa_entry { - struct hlist_node hlist; /* Item in SADB_RX hashtable */ struct mlx5e_ipsec_esn_state esn_state; - unsigned int handle; /* Handle in SADB_RX */ struct xfrm_state *x; struct mlx5e_ipsec *ipsec; struct mlx5_accel_esp_xfrm_attrs attrs; @@ -146,19 +173,43 @@ struct mlx5e_ipsec_sa_entry { struct mlx5e_ipsec_modify_state_work modify_work; }; -int mlx5e_ipsec_init(struct mlx5e_priv *priv); +struct mlx5_accel_pol_xfrm_attrs { + union { + __be32 a4; + __be32 a6[4]; + } saddr; + + union { + __be32 a4; + __be32 a6[4]; + } daddr; + + u8 family; + u8 action; + u8 type : 2; + u8 dir : 2; + u32 reqid; +}; + +struct mlx5e_ipsec_pol_entry { + struct xfrm_policy *x; + struct mlx5e_ipsec *ipsec; + struct mlx5e_ipsec_rule ipsec_rule; + struct mlx5_accel_pol_xfrm_attrs attrs; +}; + +#ifdef CONFIG_MLX5_EN_IPSEC + +void mlx5e_ipsec_init(struct mlx5e_priv *priv); void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv); void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv); -struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *dev, - unsigned int handle); - void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec); int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec); -int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry); -void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry); +int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry); +void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry); +int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry); +void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry); int mlx5_ipsec_create_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry); void mlx5_ipsec_free_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry); @@ -168,15 +219,33 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); void mlx5_accel_esp_modify_xfrm(struct mlx5e_ipsec_sa_entry *sa_entry, const struct mlx5_accel_esp_xfrm_attrs *attrs); +int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec); +void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec); + +int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_wqe_aso_ctrl_seg *data); +void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry, + u64 *packets); + +void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, + void *ipsec_stats); + +void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_accel_esp_xfrm_attrs *attrs); static inline struct mlx5_core_dev * mlx5e_ipsec_sa2dev(struct mlx5e_ipsec_sa_entry *sa_entry) { return sa_entry->ipsec->mdev; } + +static inline struct mlx5_core_dev * +mlx5e_ipsec_pol2dev(struct mlx5e_ipsec_pol_entry *pol_entry) +{ + return pol_entry->ipsec->mdev; +} #else -static inline int mlx5e_ipsec_init(struct mlx5e_priv *priv) +static inline void mlx5e_ipsec_init(struct mlx5e_priv *priv) { - return 0; } static inline void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index b859e4a4c744..9f19f4b59a70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -9,53 +9,67 @@ #define NUM_IPSEC_FTE BIT(15) -enum accel_fs_esp_type { - ACCEL_FS_ESP4, - ACCEL_FS_ESP6, - ACCEL_FS_ESP_NUM_TYPES, +struct mlx5e_ipsec_fc { + struct mlx5_fc *cnt; + struct mlx5_fc *drop; }; -struct mlx5e_ipsec_rx_err { - struct mlx5_flow_table *ft; - struct mlx5_flow_handle *rule; - struct mlx5_modify_hdr *copy_modify_hdr; +struct mlx5e_ipsec_ft { + struct mutex mutex; /* Protect changes to this struct */ + struct mlx5_flow_table *pol; + struct mlx5_flow_table *sa; + struct mlx5_flow_table *status; + u32 refcnt; }; -struct mlx5e_accel_fs_esp_prot { - struct mlx5_flow_table *ft; - struct mlx5_flow_group *miss_group; - struct mlx5_flow_handle *miss_rule; - struct mlx5_flow_destination default_dest; - struct mlx5e_ipsec_rx_err rx_err; - u32 refcnt; - struct mutex prot_mutex; /* protect ESP4/ESP6 protocol */ +struct mlx5e_ipsec_miss { + struct mlx5_flow_group *group; + struct mlx5_flow_handle *rule; }; -struct mlx5e_accel_fs_esp { - struct mlx5e_accel_fs_esp_prot fs_prot[ACCEL_FS_ESP_NUM_TYPES]; +struct mlx5e_ipsec_rx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; + struct mlx5e_ipsec_rule status; + struct mlx5e_ipsec_fc *fc; }; struct mlx5e_ipsec_tx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; struct mlx5_flow_namespace *ns; - struct mlx5_flow_table *ft; - struct mutex mutex; /* Protect IPsec TX steering */ - u32 refcnt; + struct mlx5e_ipsec_fc *fc; }; /* IPsec RX flow steering */ -static enum mlx5_traffic_types fs_esp2tt(enum accel_fs_esp_type i) +static enum mlx5_traffic_types family2tt(u32 family) { - if (i == ACCEL_FS_ESP4) + if (family == AF_INET) return MLX5_TT_IPV4_IPSEC_ESP; return MLX5_TT_IPV6_IPSEC_ESP; } -static int rx_err_add_rule(struct mlx5e_priv *priv, - struct mlx5e_accel_fs_esp_prot *fs_prot, - struct mlx5e_ipsec_rx_err *rx_err) +static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns, + int level, int prio, + int max_num_groups) +{ + struct mlx5_flow_table_attr ft_attr = {}; + + ft_attr.autogroup.num_reserved_entries = 1; + ft_attr.autogroup.max_num_groups = max_num_groups; + ft_attr.max_fte = NUM_IPSEC_FTE; + ft_attr.level = level; + ft_attr.prio = prio; + + return mlx5_create_auto_grouped_flow_table(ns, &ft_attr); +} + +static int ipsec_status_rule(struct mlx5_core_dev *mdev, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) { u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; - struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_flow_act flow_act = {}; struct mlx5_modify_hdr *modify_hdr; struct mlx5_flow_handle *fte; @@ -79,26 +93,26 @@ static int rx_err_add_rule(struct mlx5e_priv *priv, if (IS_ERR(modify_hdr)) { err = PTR_ERR(modify_hdr); - netdev_err(priv->netdev, - "fail to alloc ipsec copy modify_header_id err=%d\n", err); + mlx5_core_err(mdev, + "fail to alloc ipsec copy modify_header_id err=%d\n", err); goto out_spec; } /* create fte */ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, - &fs_prot->default_dest, 1); + fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); if (IS_ERR(fte)) { err = PTR_ERR(fte); - netdev_err(priv->netdev, "fail to add ipsec rx err copy rule err=%d\n", err); + mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err); goto out; } kvfree(spec); - rx_err->rule = fte; - rx_err->copy_modify_hdr = modify_hdr; + rx->status.rule = fte; + rx->status.modify_hdr = modify_hdr; return 0; out: @@ -108,13 +122,12 @@ out_spec: return err; } -static int rx_fs_create(struct mlx5e_priv *priv, - struct mlx5e_accel_fs_esp_prot *fs_prot) +static int ipsec_miss_create(struct mlx5_core_dev *mdev, + struct mlx5_flow_table *ft, + struct mlx5e_ipsec_miss *miss, + struct mlx5_flow_destination *dest) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table *ft = fs_prot->ft; - struct mlx5_flow_group *miss_group; - struct mlx5_flow_handle *miss_rule; MLX5_DECLARE_FLOW_ACT(flow_act); struct mlx5_flow_spec *spec; u32 *flow_group_in; @@ -130,450 +143,888 @@ static int rx_fs_create(struct mlx5e_priv *priv, /* Create miss_group */ MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); - miss_group = mlx5_create_flow_group(ft, flow_group_in); - if (IS_ERR(miss_group)) { - err = PTR_ERR(miss_group); - netdev_err(priv->netdev, "fail to create ipsec rx miss_group err=%d\n", err); + miss->group = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(miss->group)) { + err = PTR_ERR(miss->group); + mlx5_core_err(mdev, "fail to create IPsec miss_group err=%d\n", + err); goto out; } - fs_prot->miss_group = miss_group; /* Create miss rule */ - miss_rule = mlx5_add_flow_rules(ft, spec, &flow_act, &fs_prot->default_dest, 1); - if (IS_ERR(miss_rule)) { - mlx5_destroy_flow_group(fs_prot->miss_group); - err = PTR_ERR(miss_rule); - netdev_err(priv->netdev, "fail to create ipsec rx miss_rule err=%d\n", err); + miss->rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(miss->rule)) { + mlx5_destroy_flow_group(miss->group); + err = PTR_ERR(miss->rule); + mlx5_core_err(mdev, "fail to create IPsec miss_rule err=%d\n", + err); goto out; } - fs_prot->miss_rule = miss_rule; out: kvfree(flow_group_in); kvfree(spec); return err; } -static void rx_destroy(struct mlx5e_priv *priv, enum accel_fs_esp_type type) +static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_rx *rx) { - struct mlx5e_accel_fs_esp_prot *fs_prot; - struct mlx5e_accel_fs_esp *accel_esp; - - accel_esp = priv->ipsec->rx_fs; - - /* The netdev unreg already happened, so all offloaded rule are already removed */ - fs_prot = &accel_esp->fs_prot[type]; + mlx5_del_flow_rules(rx->pol.rule); + mlx5_destroy_flow_group(rx->pol.group); + mlx5_destroy_flow_table(rx->ft.pol); - mlx5_del_flow_rules(fs_prot->miss_rule); - mlx5_destroy_flow_group(fs_prot->miss_group); - mlx5_destroy_flow_table(fs_prot->ft); + mlx5_del_flow_rules(rx->sa.rule); + mlx5_destroy_flow_group(rx->sa.group); + mlx5_destroy_flow_table(rx->ft.sa); - mlx5_del_flow_rules(fs_prot->rx_err.rule); - mlx5_modify_header_dealloc(priv->mdev, fs_prot->rx_err.copy_modify_hdr); - mlx5_destroy_flow_table(fs_prot->rx_err.ft); + mlx5_del_flow_rules(rx->status.rule); + mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + mlx5_destroy_flow_table(rx->ft.status); } -static int rx_create(struct mlx5e_priv *priv, enum accel_fs_esp_type type) +static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, u32 family) { - struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(priv->fs, false); - struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(priv->fs, false); - struct mlx5_flow_table_attr ft_attr = {}; - struct mlx5e_accel_fs_esp_prot *fs_prot; - struct mlx5e_accel_fs_esp *accel_esp; + struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(ipsec->fs, false); + struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false); + struct mlx5_flow_destination dest[2]; struct mlx5_flow_table *ft; int err; - accel_esp = priv->ipsec->rx_fs; - fs_prot = &accel_esp->fs_prot[type]; - fs_prot->default_dest = - mlx5_ttc_get_default_dest(ttc, fs_esp2tt(type)); - - ft_attr.max_fte = 1; - ft_attr.autogroup.max_num_groups = 1; - ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL; - ft_attr.prio = MLX5E_NIC_PRIO; - ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); + ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL, + MLX5E_NIC_PRIO, 1); if (IS_ERR(ft)) return PTR_ERR(ft); - fs_prot->rx_err.ft = ft; - err = rx_err_add_rule(priv, fs_prot, &fs_prot->rx_err); + rx->ft.status = ft; + + dest[0] = mlx5_ttc_get_default_dest(ttc, family2tt(family)); + dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); + err = ipsec_status_rule(mdev, rx, dest); if (err) goto err_add; /* Create FT */ - ft_attr.max_fte = NUM_IPSEC_FTE; - ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_LEVEL; - ft_attr.prio = MLX5E_NIC_PRIO; - ft_attr.autogroup.num_reserved_entries = 1; - ft_attr.autogroup.max_num_groups = 1; - ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); + ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_ESP_FT_LEVEL, MLX5E_NIC_PRIO, + 2); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto err_fs_ft; } - fs_prot->ft = ft; + rx->ft.sa = ft; - err = rx_fs_create(priv, fs_prot); + err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, dest); if (err) goto err_fs; + ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_POL_FT_LEVEL, MLX5E_NIC_PRIO, + 2); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + goto err_pol_ft; + } + rx->ft.pol = ft; + memset(dest, 0x00, 2 * sizeof(*dest)); + dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest[0].ft = rx->ft.sa; + err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol, dest); + if (err) + goto err_pol_miss; + return 0; +err_pol_miss: + mlx5_destroy_flow_table(rx->ft.pol); +err_pol_ft: + mlx5_del_flow_rules(rx->sa.rule); + mlx5_destroy_flow_group(rx->sa.group); err_fs: - mlx5_destroy_flow_table(fs_prot->ft); + mlx5_destroy_flow_table(rx->ft.sa); err_fs_ft: - mlx5_del_flow_rules(fs_prot->rx_err.rule); - mlx5_modify_header_dealloc(priv->mdev, fs_prot->rx_err.copy_modify_hdr); + mlx5_del_flow_rules(rx->status.rule); + mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); err_add: - mlx5_destroy_flow_table(fs_prot->rx_err.ft); + mlx5_destroy_flow_table(rx->ft.status); return err; } -static int rx_ft_get(struct mlx5e_priv *priv, enum accel_fs_esp_type type) +static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev, + struct mlx5e_ipsec *ipsec, u32 family) { - struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(priv->fs, false); - struct mlx5e_accel_fs_esp_prot *fs_prot; + struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false); struct mlx5_flow_destination dest = {}; - struct mlx5e_accel_fs_esp *accel_esp; + struct mlx5e_ipsec_rx *rx; int err = 0; - accel_esp = priv->ipsec->rx_fs; - fs_prot = &accel_esp->fs_prot[type]; - mutex_lock(&fs_prot->prot_mutex); - if (fs_prot->refcnt) + if (family == AF_INET) + rx = ipsec->rx_ipv4; + else + rx = ipsec->rx_ipv6; + + mutex_lock(&rx->ft.mutex); + if (rx->ft.refcnt) goto skip; /* create FT */ - err = rx_create(priv, type); + err = rx_create(mdev, ipsec, rx, family); if (err) goto out; /* connect */ dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest.ft = fs_prot->ft; - mlx5_ttc_fwd_dest(ttc, fs_esp2tt(type), &dest); + dest.ft = rx->ft.pol; + mlx5_ttc_fwd_dest(ttc, family2tt(family), &dest); skip: - fs_prot->refcnt++; + rx->ft.refcnt++; out: - mutex_unlock(&fs_prot->prot_mutex); - return err; + mutex_unlock(&rx->ft.mutex); + if (err) + return ERR_PTR(err); + return rx; } -static void rx_ft_put(struct mlx5e_priv *priv, enum accel_fs_esp_type type) +static void rx_ft_put(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, + u32 family) { - struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(priv->fs, false); - struct mlx5e_accel_fs_esp_prot *fs_prot; - struct mlx5e_accel_fs_esp *accel_esp; + struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false); + struct mlx5e_ipsec_rx *rx; + + if (family == AF_INET) + rx = ipsec->rx_ipv4; + else + rx = ipsec->rx_ipv6; - accel_esp = priv->ipsec->rx_fs; - fs_prot = &accel_esp->fs_prot[type]; - mutex_lock(&fs_prot->prot_mutex); - fs_prot->refcnt--; - if (fs_prot->refcnt) + mutex_lock(&rx->ft.mutex); + rx->ft.refcnt--; + if (rx->ft.refcnt) goto out; /* disconnect */ - mlx5_ttc_fwd_default_dest(ttc, fs_esp2tt(type)); + mlx5_ttc_fwd_default_dest(ttc, family2tt(family)); /* remove FT */ - rx_destroy(priv, type); + rx_destroy(mdev, rx); out: - mutex_unlock(&fs_prot->prot_mutex); + mutex_unlock(&rx->ft.mutex); } /* IPsec TX flow steering */ -static int tx_create(struct mlx5e_priv *priv) +static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx) { - struct mlx5_flow_table_attr ft_attr = {}; - struct mlx5e_ipsec *ipsec = priv->ipsec; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_table *ft; int err; - ft_attr.max_fte = NUM_IPSEC_FTE; - ft_attr.autogroup.max_num_groups = 1; - ft = mlx5_create_auto_grouped_flow_table(ipsec->tx_fs->ns, &ft_attr); + ft = ipsec_ft_create(tx->ns, 1, 0, 4); + if (IS_ERR(ft)) + return PTR_ERR(ft); + + tx->ft.sa = ft; + + ft = ipsec_ft_create(tx->ns, 0, 0, 2); if (IS_ERR(ft)) { err = PTR_ERR(ft); - netdev_err(priv->netdev, "fail to create ipsec tx ft err=%d\n", err); - return err; + goto err_pol_ft; } - ipsec->tx_fs->ft = ft; + tx->ft.pol = ft; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = tx->ft.sa; + err = ipsec_miss_create(mdev, tx->ft.pol, &tx->pol, &dest); + if (err) + goto err_pol_miss; return 0; + +err_pol_miss: + mlx5_destroy_flow_table(tx->ft.pol); +err_pol_ft: + mlx5_destroy_flow_table(tx->ft.sa); + return err; } -static int tx_ft_get(struct mlx5e_priv *priv) +static struct mlx5e_ipsec_tx *tx_ft_get(struct mlx5_core_dev *mdev, + struct mlx5e_ipsec *ipsec) { - struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs; + struct mlx5e_ipsec_tx *tx = ipsec->tx; int err = 0; - mutex_lock(&tx_fs->mutex); - if (tx_fs->refcnt) + mutex_lock(&tx->ft.mutex); + if (tx->ft.refcnt) goto skip; - err = tx_create(priv); + err = tx_create(mdev, tx); if (err) goto out; skip: - tx_fs->refcnt++; + tx->ft.refcnt++; out: - mutex_unlock(&tx_fs->mutex); - return err; + mutex_unlock(&tx->ft.mutex); + if (err) + return ERR_PTR(err); + return tx; } -static void tx_ft_put(struct mlx5e_priv *priv) +static void tx_ft_put(struct mlx5e_ipsec *ipsec) { - struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs; + struct mlx5e_ipsec_tx *tx = ipsec->tx; - mutex_lock(&tx_fs->mutex); - tx_fs->refcnt--; - if (tx_fs->refcnt) + mutex_lock(&tx->ft.mutex); + tx->ft.refcnt--; + if (tx->ft.refcnt) goto out; - mlx5_destroy_flow_table(tx_fs->ft); + mlx5_del_flow_rules(tx->pol.rule); + mlx5_destroy_flow_group(tx->pol.group); + mlx5_destroy_flow_table(tx->ft.pol); + mlx5_destroy_flow_table(tx->ft.sa); out: - mutex_unlock(&tx_fs->mutex); + mutex_unlock(&tx->ft.mutex); } -static void setup_fte_common(struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 ipsec_obj_id, - struct mlx5_flow_spec *spec, - struct mlx5_flow_act *flow_act) +static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr, + __be32 *daddr) { - u8 ip_version = attrs->is_ipv6 ? 6 : 4; - - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS; + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; - /* ip_version */ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ip_version); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, 4); + + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), saddr, 4); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), daddr, 4); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); +} - /* Non fragmented */ - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.frag); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.frag, 0); +static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr, + __be32 *daddr) +{ + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, 6); + + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), saddr, 16); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), daddr, 16); + memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), 0xff, 16); + memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16); +} + +static void setup_fte_esp(struct mlx5_flow_spec *spec) +{ /* ESP header */ + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP); +} +static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi) +{ /* SPI number */ + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi); +} + +static void setup_fte_no_frags(struct mlx5_flow_spec *spec) +{ + /* Non fragmented */ + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.frag); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.frag, 0); +} + +static void setup_fte_reg_a(struct mlx5_flow_spec *spec) +{ + /* Add IPsec indicator in metadata_reg_a */ + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; + + MLX5_SET(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC); MLX5_SET(fte_match_param, spec->match_value, - misc_parameters.outer_esp_spi, attrs->spi); - - if (ip_version == 4) { - memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, - outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), - &attrs->saddr.a4, 4); - memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, - outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - &attrs->daddr.a4, 4); - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4); - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); - } else { - memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, - outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), - &attrs->saddr.a6, 16); - memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, - outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &attrs->daddr.a6, 16); - memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), - 0xff, 16); - memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - 0xff, 16); - } + misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC); +} - flow_act->crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC; - flow_act->crypto.obj_id = ipsec_obj_id; - flow_act->flags |= FLOW_ACT_NO_APPEND; +static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid) +{ + /* Pass policy check before choosing this SA */ + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; + + MLX5_SET(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_c_0, reqid); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_0, reqid); } -static int rx_add_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry) +static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir, + struct mlx5_flow_act *flow_act) { u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; - struct mlx5e_ipsec_rule *ipsec_rule = &sa_entry->ipsec_rule; + enum mlx5_flow_namespace_type ns_type; + struct mlx5_modify_hdr *modify_hdr; + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + switch (dir) { + case XFRM_DEV_OFFLOAD_IN: + MLX5_SET(set_action_in, action, field, + MLX5_ACTION_IN_FIELD_METADATA_REG_B); + ns_type = MLX5_FLOW_NAMESPACE_KERNEL; + break; + case XFRM_DEV_OFFLOAD_OUT: + MLX5_SET(set_action_in, action, field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_0); + ns_type = MLX5_FLOW_NAMESPACE_EGRESS; + break; + default: + return -EINVAL; + } + + MLX5_SET(set_action_in, action, data, val); + MLX5_SET(set_action_in, action, offset, 0); + MLX5_SET(set_action_in, action, length, 32); + + modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action); + if (IS_ERR(modify_hdr)) { + mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n", + PTR_ERR(modify_hdr)); + return PTR_ERR(modify_hdr); + } + + flow_act->modify_hdr = modify_hdr; + flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + return 0; +} + +static int setup_pkt_reformat(struct mlx5_core_dev *mdev, + struct mlx5_accel_esp_xfrm_attrs *attrs, + struct mlx5_flow_act *flow_act) +{ + enum mlx5_flow_namespace_type ns_type = MLX5_FLOW_NAMESPACE_EGRESS; + struct mlx5_pkt_reformat_params reformat_params = {}; + struct mlx5_pkt_reformat *pkt_reformat; + u8 reformatbf[16] = {}; + __be32 spi; + + if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { + reformat_params.type = MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT; + ns_type = MLX5_FLOW_NAMESPACE_KERNEL; + goto cmd; + } + + if (attrs->family == AF_INET) + reformat_params.type = + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4; + else + reformat_params.type = + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6; + + /* convert to network format */ + spi = htonl(attrs->spi); + memcpy(reformatbf, &spi, 4); + + reformat_params.param_0 = attrs->authsize; + reformat_params.size = sizeof(reformatbf); + reformat_params.data = &reformatbf; + +cmd: + pkt_reformat = + mlx5_packet_reformat_alloc(mdev, &reformat_params, ns_type); + if (IS_ERR(pkt_reformat)) + return PTR_ERR(pkt_reformat); + + flow_act->pkt_reformat = pkt_reformat; + flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + return 0; +} + +static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) +{ struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; - u32 ipsec_obj_id = sa_entry->ipsec_obj_id; - struct mlx5_modify_hdr *modify_hdr = NULL; - struct mlx5e_accel_fs_esp_prot *fs_prot; + struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry); + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; struct mlx5_flow_destination dest = {}; - struct mlx5e_accel_fs_esp *accel_esp; struct mlx5_flow_act flow_act = {}; struct mlx5_flow_handle *rule; - enum accel_fs_esp_type type; struct mlx5_flow_spec *spec; - int err = 0; + struct mlx5e_ipsec_rx *rx; + int err; - accel_esp = priv->ipsec->rx_fs; - type = attrs->is_ipv6 ? ACCEL_FS_ESP6 : ACCEL_FS_ESP4; - fs_prot = &accel_esp->fs_prot[type]; - - err = rx_ft_get(priv, type); - if (err) - return err; + rx = rx_ft_get(mdev, ipsec, attrs->family); + if (IS_ERR(rx)) + return PTR_ERR(rx); spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { err = -ENOMEM; - goto out_err; + goto err_alloc; } - setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act); + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - /* Set bit[31] ipsec marker */ - /* Set bit[23-0] ipsec_obj_id */ - MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); - MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31))); - MLX5_SET(set_action_in, action, offset, 0); - MLX5_SET(set_action_in, action, length, 32); + setup_fte_spi(spec, attrs->spi); + setup_fte_esp(spec); + setup_fte_no_frags(spec); - modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL, - 1, action); - if (IS_ERR(modify_hdr)) { - err = PTR_ERR(modify_hdr); - netdev_err(priv->netdev, - "fail to alloc ipsec set modify_header_id err=%d\n", err); - modify_hdr = NULL; - goto out_err; + err = setup_modify_header(mdev, sa_entry->ipsec_obj_id | BIT(31), + XFRM_DEV_OFFLOAD_IN, &flow_act); + if (err) + goto err_mod_header; + + switch (attrs->type) { + case XFRM_DEV_OFFLOAD_PACKET: + err = setup_pkt_reformat(mdev, attrs, &flow_act); + if (err) + goto err_pkt_reformat; + break; + default: + break; } - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT | - MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC; + flow_act.crypto.obj_id = sa_entry->ipsec_obj_id; + flow_act.flags |= FLOW_ACT_NO_APPEND; + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - flow_act.modify_hdr = modify_hdr; - dest.ft = fs_prot->rx_err.ft; - rule = mlx5_add_flow_rules(fs_prot->ft, spec, &flow_act, &dest, 1); + dest.ft = rx->ft.status; + rule = mlx5_add_flow_rules(rx->ft.sa, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); - netdev_err(priv->netdev, "fail to add ipsec rule attrs->action=0x%x, err=%d\n", - attrs->action, err); - goto out_err; + mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err); + goto err_add_flow; } + kvfree(spec); - ipsec_rule->rule = rule; - ipsec_rule->set_modify_hdr = modify_hdr; - goto out; - -out_err: - if (modify_hdr) - mlx5_modify_header_dealloc(priv->mdev, modify_hdr); - rx_ft_put(priv, type); + sa_entry->ipsec_rule.rule = rule; + sa_entry->ipsec_rule.modify_hdr = flow_act.modify_hdr; + sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat; + return 0; -out: +err_add_flow: + if (flow_act.pkt_reformat) + mlx5_packet_reformat_dealloc(mdev, flow_act.pkt_reformat); +err_pkt_reformat: + mlx5_modify_header_dealloc(mdev, flow_act.modify_hdr); +err_mod_header: kvfree(spec); +err_alloc: + rx_ft_put(mdev, ipsec, attrs->family); return err; } -static int tx_add_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry) +static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) { + struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; + struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry); + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; + struct mlx5e_ipsec_tx *tx; int err = 0; - err = tx_ft_get(priv); - if (err) - return err; + tx = tx_ft_get(mdev, ipsec); + if (IS_ERR(tx)) + return PTR_ERR(tx); spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { err = -ENOMEM; - goto out; + goto err_alloc; } - setup_fte_common(&sa_entry->attrs, sa_entry->ipsec_obj_id, spec, - &flow_act); + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); + + setup_fte_no_frags(spec); + + switch (attrs->type) { + case XFRM_DEV_OFFLOAD_CRYPTO: + setup_fte_spi(spec, attrs->spi); + setup_fte_esp(spec); + setup_fte_reg_a(spec); + break; + case XFRM_DEV_OFFLOAD_PACKET: + setup_fte_reg_c0(spec, attrs->reqid); + err = setup_pkt_reformat(mdev, attrs, &flow_act); + if (err) + goto err_pkt_reformat; + break; + default: + break; + } - /* Add IPsec indicator in metadata_reg_a */ - spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; - MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a, - MLX5_ETH_WQE_FT_META_IPSEC); - MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a, - MLX5_ETH_WQE_FT_META_IPSEC); - - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW | - MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT; - rule = mlx5_add_flow_rules(priv->ipsec->tx_fs->ft, spec, &flow_act, NULL, 0); + flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC; + flow_act.crypto.obj_id = sa_entry->ipsec_obj_id; + flow_act.flags |= FLOW_ACT_NO_APPEND; + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW | + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(tx->fc->cnt); + rule = mlx5_add_flow_rules(tx->ft.sa, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); - netdev_err(priv->netdev, "fail to add ipsec rule attrs->action=0x%x, err=%d\n", - sa_entry->attrs.action, err); - goto out; + mlx5_core_err(mdev, "fail to add TX ipsec rule err=%d\n", err); + goto err_add_flow; } + kvfree(spec); sa_entry->ipsec_rule.rule = rule; + sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat; + return 0; -out: +err_add_flow: + if (flow_act.pkt_reformat) + mlx5_packet_reformat_dealloc(mdev, flow_act.pkt_reformat); +err_pkt_reformat: kvfree(spec); +err_alloc: + tx_ft_put(ipsec); + return err; +} + +static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) +{ + struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs; + struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry); + struct mlx5_flow_destination dest[2] = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + struct mlx5e_ipsec_tx *tx; + int err, dstn = 0; + + tx = tx_ft_get(mdev, pol_entry->ipsec); + if (IS_ERR(tx)) + return PTR_ERR(tx); + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + err = -ENOMEM; + goto err_alloc; + } + + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); + + setup_fte_no_frags(spec); + + err = setup_modify_header(mdev, attrs->reqid, XFRM_DEV_OFFLOAD_OUT, + &flow_act); if (err) - tx_ft_put(priv); + goto err_mod_header; + + switch (attrs->action) { + case XFRM_POLICY_ALLOW: + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + break; + case XFRM_POLICY_BLOCK: + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[dstn].counter_id = mlx5_fc_id(tx->fc->drop); + dstn++; + break; + default: + WARN_ON(true); + err = -EINVAL; + goto err_action; + } + + flow_act.flags |= FLOW_ACT_NO_APPEND; + dest[dstn].ft = tx->ft.sa; + dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dstn++; + rule = mlx5_add_flow_rules(tx->ft.pol, spec, &flow_act, dest, dstn); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, "fail to add TX ipsec rule err=%d\n", err); + goto err_action; + } + + kvfree(spec); + pol_entry->ipsec_rule.rule = rule; + pol_entry->ipsec_rule.modify_hdr = flow_act.modify_hdr; + return 0; + +err_action: + mlx5_modify_header_dealloc(mdev, flow_act.modify_hdr); +err_mod_header: + kvfree(spec); +err_alloc: + tx_ft_put(pol_entry->ipsec); return err; } -int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry) +static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) { - if (sa_entry->attrs.action == MLX5_ACCEL_ESP_ACTION_ENCRYPT) - return tx_add_rule(priv, sa_entry); + struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs; + struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry); + struct mlx5_flow_destination dest[2]; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + struct mlx5e_ipsec_rx *rx; + int err, dstn = 0; + + rx = rx_ft_get(mdev, pol_entry->ipsec, attrs->family); + if (IS_ERR(rx)) + return PTR_ERR(rx); + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + err = -ENOMEM; + goto err_alloc; + } - return rx_add_rule(priv, sa_entry); + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); + + setup_fte_no_frags(spec); + + switch (attrs->action) { + case XFRM_POLICY_ALLOW: + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + break; + case XFRM_POLICY_BLOCK: + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[dstn].counter_id = mlx5_fc_id(rx->fc->drop); + dstn++; + break; + default: + WARN_ON(true); + err = -EINVAL; + goto err_action; + } + + flow_act.flags |= FLOW_ACT_NO_APPEND; + dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest[dstn].ft = rx->ft.sa; + dstn++; + rule = mlx5_add_flow_rules(rx->ft.pol, spec, &flow_act, dest, dstn); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, "Fail to add RX IPsec policy rule err=%d\n", err); + goto err_action; + } + + kvfree(spec); + pol_entry->ipsec_rule.rule = rule; + return 0; + +err_action: + kvfree(spec); +err_alloc: + rx_ft_put(mdev, pol_entry->ipsec, attrs->family); + return err; } -void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv, - struct mlx5e_ipsec_sa_entry *sa_entry) +static void ipsec_fs_destroy_counters(struct mlx5e_ipsec *ipsec) +{ + struct mlx5e_ipsec_rx *rx_ipv4 = ipsec->rx_ipv4; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5e_ipsec_tx *tx = ipsec->tx; + + mlx5_fc_destroy(mdev, tx->fc->drop); + mlx5_fc_destroy(mdev, tx->fc->cnt); + kfree(tx->fc); + mlx5_fc_destroy(mdev, rx_ipv4->fc->drop); + mlx5_fc_destroy(mdev, rx_ipv4->fc->cnt); + kfree(rx_ipv4->fc); +} + +static int ipsec_fs_init_counters(struct mlx5e_ipsec *ipsec) +{ + struct mlx5e_ipsec_rx *rx_ipv4 = ipsec->rx_ipv4; + struct mlx5e_ipsec_rx *rx_ipv6 = ipsec->rx_ipv6; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5e_ipsec_tx *tx = ipsec->tx; + struct mlx5e_ipsec_fc *fc; + struct mlx5_fc *counter; + int err; + + fc = kzalloc(sizeof(*rx_ipv4->fc), GFP_KERNEL); + if (!fc) + return -ENOMEM; + + /* Both IPv4 and IPv6 point to same flow counters struct. */ + rx_ipv4->fc = fc; + rx_ipv6->fc = fc; + counter = mlx5_fc_create(mdev, false); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_rx_cnt; + } + + fc->cnt = counter; + counter = mlx5_fc_create(mdev, false); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_rx_drop; + } + + fc->drop = counter; + fc = kzalloc(sizeof(*tx->fc), GFP_KERNEL); + if (!fc) { + err = -ENOMEM; + goto err_tx_fc; + } + + tx->fc = fc; + counter = mlx5_fc_create(mdev, false); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_tx_cnt; + } + + fc->cnt = counter; + counter = mlx5_fc_create(mdev, false); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_tx_drop; + } + + fc->drop = counter; + return 0; + +err_tx_drop: + mlx5_fc_destroy(mdev, tx->fc->cnt); +err_tx_cnt: + kfree(tx->fc); +err_tx_fc: + mlx5_fc_destroy(mdev, rx_ipv4->fc->drop); +err_rx_drop: + mlx5_fc_destroy(mdev, rx_ipv4->fc->cnt); +err_rx_cnt: + kfree(rx_ipv4->fc); + return err; +} + +void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_ipsec *ipsec = priv->ipsec; + struct mlx5e_ipsec_hw_stats *stats; + struct mlx5e_ipsec_fc *fc; + + stats = (struct mlx5e_ipsec_hw_stats *)ipsec_stats; + + stats->ipsec_rx_pkts = 0; + stats->ipsec_rx_bytes = 0; + stats->ipsec_rx_drop_pkts = 0; + stats->ipsec_rx_drop_bytes = 0; + stats->ipsec_tx_pkts = 0; + stats->ipsec_tx_bytes = 0; + stats->ipsec_tx_drop_pkts = 0; + stats->ipsec_tx_drop_bytes = 0; + + fc = ipsec->rx_ipv4->fc; + mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_rx_pkts, &stats->ipsec_rx_bytes); + mlx5_fc_query(mdev, fc->drop, &stats->ipsec_rx_drop_pkts, + &stats->ipsec_rx_drop_bytes); + + fc = ipsec->tx->fc; + mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_tx_pkts, &stats->ipsec_tx_bytes); + mlx5_fc_query(mdev, fc->drop, &stats->ipsec_tx_drop_pkts, + &stats->ipsec_tx_drop_bytes); +} + +int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) +{ + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) + return tx_add_rule(sa_entry); + + return rx_add_rule(sa_entry); +} + +void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) { struct mlx5e_ipsec_rule *ipsec_rule = &sa_entry->ipsec_rule; struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry); mlx5_del_flow_rules(ipsec_rule->rule); - if (sa_entry->attrs.action == MLX5_ACCEL_ESP_ACTION_ENCRYPT) { - tx_ft_put(priv); + if (ipsec_rule->pkt_reformat) + mlx5_packet_reformat_dealloc(mdev, ipsec_rule->pkt_reformat); + + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) { + tx_ft_put(sa_entry->ipsec); return; } - mlx5_modify_header_dealloc(mdev, ipsec_rule->set_modify_hdr); - rx_ft_put(priv, - sa_entry->attrs.is_ipv6 ? ACCEL_FS_ESP6 : ACCEL_FS_ESP4); + mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + rx_ft_put(mdev, sa_entry->ipsec, sa_entry->attrs.family); } -void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) +int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry) { - struct mlx5e_accel_fs_esp_prot *fs_prot; - struct mlx5e_accel_fs_esp *accel_esp; - enum accel_fs_esp_type i; + if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) + return tx_add_policy(pol_entry); - if (!ipsec->rx_fs) - return; + return rx_add_policy(pol_entry); +} + +void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry) +{ + struct mlx5e_ipsec_rule *ipsec_rule = &pol_entry->ipsec_rule; + struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry); - mutex_destroy(&ipsec->tx_fs->mutex); - WARN_ON(ipsec->tx_fs->refcnt); - kfree(ipsec->tx_fs); + mlx5_del_flow_rules(ipsec_rule->rule); - accel_esp = ipsec->rx_fs; - for (i = 0; i < ACCEL_FS_ESP_NUM_TYPES; i++) { - fs_prot = &accel_esp->fs_prot[i]; - mutex_destroy(&fs_prot->prot_mutex); - WARN_ON(fs_prot->refcnt); + if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) { + rx_ft_put(mdev, pol_entry->ipsec, pol_entry->attrs.family); + return; } - kfree(ipsec->rx_fs); + + mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + tx_ft_put(pol_entry->ipsec); +} + +void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) +{ + if (!ipsec->tx) + return; + + ipsec_fs_destroy_counters(ipsec); + mutex_destroy(&ipsec->tx->ft.mutex); + WARN_ON(ipsec->tx->ft.refcnt); + kfree(ipsec->tx); + + mutex_destroy(&ipsec->rx_ipv4->ft.mutex); + WARN_ON(ipsec->rx_ipv4->ft.refcnt); + kfree(ipsec->rx_ipv4); + + mutex_destroy(&ipsec->rx_ipv6->ft.mutex); + WARN_ON(ipsec->rx_ipv6->ft.refcnt); + kfree(ipsec->rx_ipv6); } int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec) { - struct mlx5e_accel_fs_esp_prot *fs_prot; - struct mlx5e_accel_fs_esp *accel_esp; struct mlx5_flow_namespace *ns; - enum accel_fs_esp_type i; int err = -ENOMEM; ns = mlx5_get_flow_namespace(ipsec->mdev, @@ -581,26 +1032,34 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec) if (!ns) return -EOPNOTSUPP; - ipsec->tx_fs = kzalloc(sizeof(*ipsec->tx_fs), GFP_KERNEL); - if (!ipsec->tx_fs) + ipsec->tx = kzalloc(sizeof(*ipsec->tx), GFP_KERNEL); + if (!ipsec->tx) return -ENOMEM; - ipsec->rx_fs = kzalloc(sizeof(*ipsec->rx_fs), GFP_KERNEL); - if (!ipsec->rx_fs) - goto err_rx; + ipsec->rx_ipv4 = kzalloc(sizeof(*ipsec->rx_ipv4), GFP_KERNEL); + if (!ipsec->rx_ipv4) + goto err_rx_ipv4; - mutex_init(&ipsec->tx_fs->mutex); - ipsec->tx_fs->ns = ns; + ipsec->rx_ipv6 = kzalloc(sizeof(*ipsec->rx_ipv6), GFP_KERNEL); + if (!ipsec->rx_ipv6) + goto err_rx_ipv6; - accel_esp = ipsec->rx_fs; - for (i = 0; i < ACCEL_FS_ESP_NUM_TYPES; i++) { - fs_prot = &accel_esp->fs_prot[i]; - mutex_init(&fs_prot->prot_mutex); - } + err = ipsec_fs_init_counters(ipsec); + if (err) + goto err_counters; + + mutex_init(&ipsec->tx->ft.mutex); + mutex_init(&ipsec->rx_ipv4->ft.mutex); + mutex_init(&ipsec->rx_ipv6->ft.mutex); + ipsec->tx->ns = ns; return 0; -err_rx: - kfree(ipsec->tx_fs); +err_counters: + kfree(ipsec->rx_ipv6); +err_rx_ipv6: + kfree(ipsec->rx_ipv4); +err_rx_ipv4: + kfree(ipsec->tx); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 792724ce7336..8e3614218fc4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -2,9 +2,14 @@ /* Copyright (c) 2017, Mellanox Technologies inc. All rights reserved. */ #include "mlx5_core.h" +#include "en.h" #include "ipsec.h" #include "lib/mlx5.h" +enum { + MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, +}; + u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) { u32 caps = 0; @@ -31,6 +36,12 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp)) caps |= MLX5_IPSEC_CAP_CRYPTO; + if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && + MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_del_esp_trasport) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap)) + caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD; + if (!caps) return 0; @@ -46,6 +57,52 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) } EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps); +static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, + struct mlx5_accel_esp_xfrm_attrs *attrs) +{ + void *aso_ctx; + + aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso); + if (attrs->esn_trigger) { + MLX5_SET(ipsec_aso, aso_ctx, esn_event_arm, 1); + + if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { + MLX5_SET(ipsec_aso, aso_ctx, window_sz, + attrs->replay_window / 64); + MLX5_SET(ipsec_aso, aso_ctx, mode, + MLX5_IPSEC_ASO_REPLAY_PROTECTION); + } + } + + /* ASO context */ + MLX5_SET(ipsec_obj, obj, ipsec_aso_access_pd, pdn); + MLX5_SET(ipsec_obj, obj, full_offload, 1); + MLX5_SET(ipsec_aso, aso_ctx, valid, 1); + /* MLX5_IPSEC_ASO_REG_C_4_5 is type C register that is used + * in flow steering to perform matching against. Please be + * aware that this register was chosen arbitrary and can't + * be used in other places as long as IPsec packet offload + * active. + */ + MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5); + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN); + + if (attrs->hard_packet_limit != XFRM_INF) { + MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, + lower_32_bits(attrs->hard_packet_limit)); + MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1); + MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1); + } + + if (attrs->soft_packet_limit != XFRM_INF) { + MLX5_SET(ipsec_aso, aso_ctx, remove_flow_soft_lft, + lower_32_bits(attrs->soft_packet_limit)); + + MLX5_SET(ipsec_aso, aso_ctx, soft_lft_arm, 1); + } +} + static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) { struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; @@ -54,6 +111,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; u32 in[MLX5_ST_SZ_DW(create_ipsec_obj_in)] = {}; void *obj, *salt_p, *salt_iv_p; + struct mlx5e_hw_objs *res; int err; obj = MLX5_ADDR_OF(create_ipsec_obj_in, in, ipsec_object); @@ -66,11 +124,10 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) salt_iv_p = MLX5_ADDR_OF(ipsec_obj, obj, implicit_iv); memcpy(salt_iv_p, &aes_gcm->seq_iv, sizeof(aes_gcm->seq_iv)); /* esn */ - if (attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED) { + if (attrs->esn_trigger) { MLX5_SET(ipsec_obj, obj, esn_en, 1); MLX5_SET(ipsec_obj, obj, esn_msb, attrs->esn); - if (attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP) - MLX5_SET(ipsec_obj, obj, esn_overlap, 1); + MLX5_SET(ipsec_obj, obj, esn_overlap, attrs->esn_overlap); } MLX5_SET(ipsec_obj, obj, dekn, sa_entry->enc_key_id); @@ -81,6 +138,10 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_GENERAL_OBJECT_TYPES_IPSEC); + res = &mdev->mlx5e_res.hw_objs; + if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) + mlx5e_ipsec_packet_setup(obj, res->pdn, attrs); + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (!err) sa_entry->ipsec_obj_id = @@ -152,7 +213,7 @@ static int mlx5_modify_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry, void *obj; int err; - if (!(attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED)) + if (!attrs->esn_trigger) return 0; general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types); @@ -183,8 +244,7 @@ static int mlx5_modify_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry, MLX5_MODIFY_IPSEC_BITMASK_ESN_OVERLAP | MLX5_MODIFY_IPSEC_BITMASK_ESN_MSB); MLX5_SET(ipsec_obj, obj, esn_msb, attrs->esn); - if (attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP) - MLX5_SET(ipsec_obj, obj, esn_overlap, 1); + MLX5_SET(ipsec_obj, obj, esn_overlap, attrs->esn_overlap); /* general object fields set */ MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_MODIFY_GENERAL_OBJECT); @@ -203,3 +263,234 @@ void mlx5_accel_esp_modify_xfrm(struct mlx5e_ipsec_sa_entry *sa_entry, memcpy(&sa_entry->attrs, attrs, sizeof(sa_entry->attrs)); } + +static void +mlx5e_ipsec_aso_update_esn(struct mlx5e_ipsec_sa_entry *sa_entry, + const struct mlx5_accel_esp_xfrm_attrs *attrs) +{ + struct mlx5_wqe_aso_ctrl_seg data = {}; + + data.data_mask_mode = MLX5_ASO_DATA_MASK_MODE_BITWISE_64BIT << 6; + data.condition_1_0_operand = MLX5_ASO_ALWAYS_TRUE | MLX5_ASO_ALWAYS_TRUE + << 4; + data.data_offset_condition_operand = MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET; + data.bitwise_data = cpu_to_be64(BIT_ULL(54)); + data.data_mask = data.bitwise_data; + + mlx5e_ipsec_aso_query(sa_entry, &data); +} + +static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry, + u32 mode_param) +{ + struct mlx5_accel_esp_xfrm_attrs attrs = {}; + + if (mode_param < MLX5E_IPSEC_ESN_SCOPE_MID) { + sa_entry->esn_state.esn++; + sa_entry->esn_state.overlap = 0; + } else { + sa_entry->esn_state.overlap = 1; + } + + mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &attrs); + mlx5_accel_esp_modify_xfrm(sa_entry, &attrs); + mlx5e_ipsec_aso_update_esn(sa_entry, &attrs); +} + +static void mlx5e_ipsec_handle_event(struct work_struct *_work) +{ + struct mlx5e_ipsec_work *work = + container_of(_work, struct mlx5e_ipsec_work, work); + struct mlx5_accel_esp_xfrm_attrs *attrs; + struct mlx5e_ipsec_sa_entry *sa_entry; + struct mlx5e_ipsec_aso *aso; + struct mlx5e_ipsec *ipsec; + int ret; + + sa_entry = xa_load(&work->ipsec->sadb, work->id); + if (!sa_entry) + goto out; + + ipsec = sa_entry->ipsec; + aso = ipsec->aso; + attrs = &sa_entry->attrs; + + spin_lock(&sa_entry->x->lock); + ret = mlx5e_ipsec_aso_query(sa_entry, NULL); + if (ret) + goto unlock; + + aso->use_cache = true; + if (attrs->esn_trigger && + !MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) { + u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter); + + mlx5e_ipsec_update_esn_state(sa_entry, mode_param); + } + + if (attrs->soft_packet_limit != XFRM_INF) + if (!MLX5_GET(ipsec_aso, aso->ctx, soft_lft_arm) || + !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) || + !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable)) + xfrm_state_check_expire(sa_entry->x); + aso->use_cache = false; + +unlock: + spin_unlock(&sa_entry->x->lock); +out: + kfree(work); +} + +static int mlx5e_ipsec_event(struct notifier_block *nb, unsigned long event, + void *data) +{ + struct mlx5e_ipsec *ipsec = container_of(nb, struct mlx5e_ipsec, nb); + struct mlx5_eqe_obj_change *object; + struct mlx5e_ipsec_work *work; + struct mlx5_eqe *eqe = data; + u16 type; + + if (event != MLX5_EVENT_TYPE_OBJECT_CHANGE) + return NOTIFY_DONE; + + object = &eqe->data.obj_change; + type = be16_to_cpu(object->obj_type); + + if (type != MLX5_GENERAL_OBJECT_TYPES_IPSEC) + return NOTIFY_DONE; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return NOTIFY_DONE; + + INIT_WORK(&work->work, mlx5e_ipsec_handle_event); + work->ipsec = ipsec; + work->id = be32_to_cpu(object->obj_id); + + queue_work(ipsec->wq, &work->work); + return NOTIFY_OK; +} + +int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec) +{ + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5e_ipsec_aso *aso; + struct mlx5e_hw_objs *res; + struct device *pdev; + int err; + + aso = kzalloc(sizeof(*ipsec->aso), GFP_KERNEL); + if (!aso) + return -ENOMEM; + + res = &mdev->mlx5e_res.hw_objs; + + pdev = mlx5_core_dma_dev(mdev); + aso->dma_addr = dma_map_single(pdev, aso->ctx, sizeof(aso->ctx), + DMA_BIDIRECTIONAL); + err = dma_mapping_error(pdev, aso->dma_addr); + if (err) + goto err_dma; + + aso->aso = mlx5_aso_create(mdev, res->pdn); + if (IS_ERR(aso->aso)) { + err = PTR_ERR(aso->aso); + goto err_aso_create; + } + + ipsec->nb.notifier_call = mlx5e_ipsec_event; + mlx5_notifier_register(mdev, &ipsec->nb); + + ipsec->aso = aso; + return 0; + +err_aso_create: + dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), + DMA_BIDIRECTIONAL); +err_dma: + kfree(aso); + return err; +} + +void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec) +{ + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5e_ipsec_aso *aso; + struct device *pdev; + + aso = ipsec->aso; + pdev = mlx5_core_dma_dev(mdev); + + mlx5_notifier_unregister(mdev, &ipsec->nb); + mlx5_aso_destroy(aso->aso); + dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), + DMA_BIDIRECTIONAL); + kfree(aso); +} + +static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl, + struct mlx5_wqe_aso_ctrl_seg *data) +{ + if (!data) + return; + + ctrl->data_mask_mode = data->data_mask_mode; + ctrl->condition_1_0_operand = data->condition_1_0_operand; + ctrl->condition_1_0_offset = data->condition_1_0_offset; + ctrl->data_offset_condition_operand = data->data_offset_condition_operand; + ctrl->condition_0_data = data->condition_0_data; + ctrl->condition_0_mask = data->condition_0_mask; + ctrl->condition_1_data = data->condition_1_data; + ctrl->condition_1_mask = data->condition_1_mask; + ctrl->bitwise_data = data->bitwise_data; + ctrl->data_mask = data->data_mask; +} + +int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_wqe_aso_ctrl_seg *data) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5e_ipsec_aso *aso = ipsec->aso; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_wqe_aso_ctrl_seg *ctrl; + struct mlx5e_hw_objs *res; + struct mlx5_aso_wqe *wqe; + u8 ds_cnt; + + lockdep_assert_held(&sa_entry->x->lock); + if (aso->use_cache) + return 0; + + res = &mdev->mlx5e_res.hw_objs; + + memset(aso->ctx, 0, sizeof(aso->ctx)); + wqe = mlx5_aso_get_wqe(aso->aso); + ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS); + mlx5_aso_build_wqe(aso->aso, ds_cnt, wqe, sa_entry->ipsec_obj_id, + MLX5_ACCESS_ASO_OPC_MOD_IPSEC); + + ctrl = &wqe->aso_ctrl; + ctrl->va_l = + cpu_to_be32(lower_32_bits(aso->dma_addr) | ASO_CTRL_READ_EN); + ctrl->va_h = cpu_to_be32(upper_32_bits(aso->dma_addr)); + ctrl->l_key = cpu_to_be32(res->mkey); + mlx5e_ipsec_aso_copy(ctrl, data); + + mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl); + return mlx5_aso_poll_cq(aso->aso, false); +} + +void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry, + u64 *packets) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5e_ipsec_aso *aso = ipsec->aso; + u64 hard_cnt; + + hard_cnt = MLX5_GET(ipsec_aso, aso->ctx, remove_flow_pkt_cnt); + /* HW decresases the limit till it reaches zero to fire an avent. + * We need to fix the calculations, so the returned count is a total + * number of passed packets and not how much left. + */ + *packets = sa_entry->attrs.hard_packet_limit - hard_cnt; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 6859f1c1a831..eab5bc718771 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -312,27 +312,31 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct mlx5_cqe64 *cqe) { u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata); - struct mlx5e_priv *priv; + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_ipsec *ipsec = priv->ipsec; + struct mlx5e_ipsec_sa_entry *sa_entry; struct xfrm_offload *xo; - struct xfrm_state *xs; struct sec_path *sp; u32 sa_handle; sa_handle = MLX5_IPSEC_METADATA_HANDLE(ipsec_meta_data); - priv = netdev_priv(netdev); sp = secpath_set(skb); if (unlikely(!sp)) { - atomic64_inc(&priv->ipsec->sw_stats.ipsec_rx_drop_sp_alloc); + atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sp_alloc); return; } - xs = mlx5e_ipsec_sadb_rx_lookup(priv->ipsec, sa_handle); - if (unlikely(!xs)) { - atomic64_inc(&priv->ipsec->sw_stats.ipsec_rx_drop_sadb_miss); + rcu_read_lock(); + sa_entry = xa_load(&ipsec->sadb, sa_handle); + if (unlikely(!sa_entry)) { + rcu_read_unlock(); + atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss); return; } + xfrm_state_hold(sa_entry->x); + rcu_read_unlock(); - sp->xvec[sp->len++] = xs; + sp->xvec[sp->len++] = sa_entry->x; sp->olen++; xo = xfrm_offload(skb); @@ -349,6 +353,6 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, xo->status = CRYPTO_INVALID_PACKET_SYNTAX; break; default: - atomic64_inc(&priv->ipsec->sw_stats.ipsec_rx_drop_syndrome); + atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c index 9de84821dafb..e0e36a09721c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c @@ -37,6 +37,17 @@ #include "en.h" #include "ipsec.h" +static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_pkts) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_pkts) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_pkts) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_drop_pkts) }, + { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_drop_bytes) }, +}; + static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sp_alloc) }, { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sadb_miss) }, @@ -50,8 +61,48 @@ static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = { #define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \ atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset)) +#define NUM_IPSEC_HW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_hw_stats_desc) #define NUM_IPSEC_SW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_sw_stats_desc) +static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_hw) +{ + if (!priv->ipsec) + return 0; + + return NUM_IPSEC_HW_COUNTERS; +} + +static inline MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw) {} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_hw) +{ + unsigned int i; + + if (!priv->ipsec) + return idx; + + for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + mlx5e_ipsec_hw_stats_desc[i].format); + + return idx; +} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw) +{ + int i; + + if (!priv->ipsec) + return idx; + + mlx5e_accel_ipsec_fs_read_stats(priv, &priv->ipsec->hw_stats); + for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) + data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->hw_stats, + mlx5e_ipsec_hw_stats_desc, i); + + return idx; +} + static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_sw) { return priv->ipsec ? NUM_IPSEC_SW_COUNTERS : 0; @@ -81,4 +132,5 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw) return idx; } +MLX5E_DEFINE_STATS_GRP(ipsec_hw, 0); MLX5E_DEFINE_STATS_GRP(ipsec_sw, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 2e0335246967..78072bf93f3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -125,10 +125,8 @@ mlx5e_get_ktls_tx_priv_ctx(struct tls_context *tls_ctx) /* struct for callback API management */ struct mlx5e_async_ctx { struct mlx5_async_work context; - struct mlx5_async_ctx async_ctx; - struct work_struct work; + struct mlx5_async_ctx *async_ctx; struct mlx5e_ktls_offload_context_tx *priv_tx; - struct completion complete; int err; union { u32 out_create[MLX5_ST_SZ_DW(create_tis_out)]; @@ -136,34 +134,33 @@ struct mlx5e_async_ctx { }; }; -static struct mlx5e_async_ctx *mlx5e_bulk_async_init(struct mlx5_core_dev *mdev, int n) +struct mlx5e_bulk_async_ctx { + struct mlx5_async_ctx async_ctx; + DECLARE_FLEX_ARRAY(struct mlx5e_async_ctx, arr); +}; + +static struct mlx5e_bulk_async_ctx *mlx5e_bulk_async_init(struct mlx5_core_dev *mdev, int n) { - struct mlx5e_async_ctx *bulk_async; + struct mlx5e_bulk_async_ctx *bulk_async; + int sz; int i; - bulk_async = kvcalloc(n, sizeof(struct mlx5e_async_ctx), GFP_KERNEL); + sz = struct_size(bulk_async, arr, n); + bulk_async = kvzalloc(sz, GFP_KERNEL); if (!bulk_async) return NULL; - for (i = 0; i < n; i++) { - struct mlx5e_async_ctx *async = &bulk_async[i]; + mlx5_cmd_init_async_ctx(mdev, &bulk_async->async_ctx); - mlx5_cmd_init_async_ctx(mdev, &async->async_ctx); - init_completion(&async->complete); - } + for (i = 0; i < n; i++) + bulk_async->arr[i].async_ctx = &bulk_async->async_ctx; return bulk_async; } -static void mlx5e_bulk_async_cleanup(struct mlx5e_async_ctx *bulk_async, int n) +static void mlx5e_bulk_async_cleanup(struct mlx5e_bulk_async_ctx *bulk_async) { - int i; - - for (i = 0; i < n; i++) { - struct mlx5e_async_ctx *async = &bulk_async[i]; - - mlx5_cmd_cleanup_async_ctx(&async->async_ctx); - } + mlx5_cmd_cleanup_async_ctx(&bulk_async->async_ctx); kvfree(bulk_async); } @@ -176,12 +173,10 @@ static void create_tis_callback(int status, struct mlx5_async_work *context) if (status) { async->err = status; priv_tx->create_err = 1; - goto out; + return; } priv_tx->tisn = MLX5_GET(create_tis_out, async->out_create, tisn); -out: - complete(&async->complete); } static void destroy_tis_callback(int status, struct mlx5_async_work *context) @@ -190,7 +185,6 @@ static void destroy_tis_callback(int status, struct mlx5_async_work *context) container_of(context, struct mlx5e_async_ctx, context); struct mlx5e_ktls_offload_context_tx *priv_tx = async->priv_tx; - complete(&async->complete); kfree(priv_tx); } @@ -214,7 +208,7 @@ mlx5e_tls_priv_tx_init(struct mlx5_core_dev *mdev, struct mlx5e_tls_sw_stats *sw goto err_out; } else { async->priv_tx = priv_tx; - err = mlx5e_ktls_create_tis_cb(mdev, &async->async_ctx, + err = mlx5e_ktls_create_tis_cb(mdev, async->async_ctx, async->out_create, sizeof(async->out_create), create_tis_callback, &async->context); if (err) @@ -232,13 +226,12 @@ static void mlx5e_tls_priv_tx_cleanup(struct mlx5e_ktls_offload_context_tx *priv struct mlx5e_async_ctx *async) { if (priv_tx->create_err) { - complete(&async->complete); kfree(priv_tx); return; } async->priv_tx = priv_tx; mlx5e_ktls_destroy_tis_cb(priv_tx->mdev, priv_tx->tisn, - &async->async_ctx, + async->async_ctx, async->out_destroy, sizeof(async->out_destroy), destroy_tis_callback, &async->context); } @@ -247,7 +240,7 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev, struct list_head *list, int size) { struct mlx5e_ktls_offload_context_tx *obj, *n; - struct mlx5e_async_ctx *bulk_async; + struct mlx5e_bulk_async_ctx *bulk_async; int i; bulk_async = mlx5e_bulk_async_init(mdev, size); @@ -256,16 +249,11 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev, i = 0; list_for_each_entry_safe(obj, n, list, list_node) { - mlx5e_tls_priv_tx_cleanup(obj, &bulk_async[i]); + mlx5e_tls_priv_tx_cleanup(obj, &bulk_async->arr[i]); i++; } - for (i = 0; i < size; i++) { - struct mlx5e_async_ctx *async = &bulk_async[i]; - - wait_for_completion(&async->complete); - } - mlx5e_bulk_async_cleanup(bulk_async, size); + mlx5e_bulk_async_cleanup(bulk_async); } /* Recycling pool API */ @@ -291,7 +279,7 @@ static void create_work(struct work_struct *work) struct mlx5e_tls_tx_pool *pool = container_of(work, struct mlx5e_tls_tx_pool, create_work); struct mlx5e_ktls_offload_context_tx *obj; - struct mlx5e_async_ctx *bulk_async; + struct mlx5e_bulk_async_ctx *bulk_async; LIST_HEAD(local_list); int i, j, err = 0; @@ -300,7 +288,7 @@ static void create_work(struct work_struct *work) return; for (i = 0; i < MLX5E_TLS_TX_POOL_BULK; i++) { - obj = mlx5e_tls_priv_tx_init(pool->mdev, pool->sw_stats, &bulk_async[i]); + obj = mlx5e_tls_priv_tx_init(pool->mdev, pool->sw_stats, &bulk_async->arr[i]); if (IS_ERR(obj)) { err = PTR_ERR(obj); break; @@ -309,14 +297,13 @@ static void create_work(struct work_struct *work) } for (j = 0; j < i; j++) { - struct mlx5e_async_ctx *async = &bulk_async[j]; + struct mlx5e_async_ctx *async = &bulk_async->arr[j]; - wait_for_completion(&async->complete); if (!err && async->err) err = async->err; } atomic64_add(i, &pool->sw_stats->tx_tls_pool_alloc); - mlx5e_bulk_async_cleanup(bulk_async, MLX5E_TLS_TX_POOL_BULK); + mlx5e_bulk_async_cleanup(bulk_async); if (err) goto err_out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index f900709639f6..9369a580743e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -186,7 +186,7 @@ static int mlx5e_macsec_aso_reg_mr(struct mlx5_core_dev *mdev, struct mlx5e_macs return err; } - dma_device = &mdev->pdev->dev; + dma_device = mlx5_core_dma_dev(mdev); dma_addr = dma_map_single(dma_device, umr->ctx, sizeof(umr->ctx), DMA_BIDIRECTIONAL); err = dma_mapping_error(dma_device, dma_addr); if (err) { @@ -1299,12 +1299,12 @@ static void macsec_aso_build_wqe_ctrl_seg(struct mlx5e_macsec_aso *macsec_aso, struct mlx5_wqe_aso_ctrl_seg *aso_ctrl, struct mlx5_aso_ctrl_param *param) { + struct mlx5e_macsec_umr *umr = macsec_aso->umr; + memset(aso_ctrl, 0, sizeof(*aso_ctrl)); - if (macsec_aso->umr->dma_addr) { - aso_ctrl->va_l = cpu_to_be32(macsec_aso->umr->dma_addr | ASO_CTRL_READ_EN); - aso_ctrl->va_h = cpu_to_be32((u64)macsec_aso->umr->dma_addr >> 32); - aso_ctrl->l_key = cpu_to_be32(macsec_aso->umr->mkey); - } + aso_ctrl->va_l = cpu_to_be32(umr->dma_addr | ASO_CTRL_READ_EN); + aso_ctrl->va_h = cpu_to_be32((u64)umr->dma_addr >> 32); + aso_ctrl->l_key = cpu_to_be32(umr->mkey); if (!param) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 0ae1865086ff..bed0c2d043e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -57,7 +57,6 @@ struct mlx5e_arfs_tables { struct arfs_table arfs_tables[ARFS_NUM_TYPES]; /* Protect aRFS rules list */ spinlock_t arfs_lock; - struct list_head rules; int last_filter_id; struct workqueue_struct *wq; }; @@ -376,7 +375,6 @@ int mlx5e_arfs_create_tables(struct mlx5e_flow_steering *fs, return -ENOMEM; spin_lock_init(&arfs->arfs_lock); - INIT_LIST_HEAD(&arfs->rules); arfs->wq = create_singlethread_workqueue("mlx5e_arfs"); if (!arfs->wq) goto err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 1728e197558d..7708acc9b2ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2445,4 +2445,5 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_eth_mac_stats = mlx5e_get_eth_mac_stats, .get_eth_ctrl_stats = mlx5e_get_eth_ctrl_stats, .get_rmon_stats = mlx5e_get_rmon_stats, + .get_link_ext_stats = mlx5e_get_link_ext_stats }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5e41dfdf79c8..8d36e2de53a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -208,7 +208,7 @@ static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_ u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode); u32 sz; - sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); + sz = ALIGN(entries * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT); return sz / MLX5_OCTWORD; } @@ -1206,6 +1206,13 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index)) __set_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state); + /* For enhanced CQE compression packet processing. decompress + * session according to the enhanced layout. + */ + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) && + MLX5_CAP_GEN(mdev, enhanced_cqe_compression)) + __set_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state); + return 0; err_destroy_rq: @@ -1896,6 +1903,7 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); cqe->op_own = 0xf1; + cqe->validity_iteration_count = 0xff; } cq->mdev = mdev; @@ -3062,7 +3070,10 @@ int mlx5e_open_locked(struct net_device *netdev) if (err) goto err_clear_state_opened_flag; - priv->profile->update_rx(priv); + err = priv->profile->update_rx(priv); + if (err) + goto err_close_channels; + mlx5e_selq_apply(&priv->selq); mlx5e_activate_priv_channels(priv); mlx5e_apply_traps(priv, true); @@ -3072,6 +3083,8 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_queue_update_stats(priv); return 0; +err_close_channels: + mlx5e_close_channels(&priv->channels); err_clear_state_opened_flag: clear_bit(MLX5E_STATE_OPENED, &priv->state); mlx5e_selq_cancel(&priv->selq); @@ -4898,7 +4911,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, #endif - .ndo_get_devlink_port = mlx5e_get_devlink_port, }; static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) @@ -5226,10 +5238,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, } priv->fs = fs; - err = mlx5e_ipsec_init(priv); - if (err) - mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); - err = mlx5e_ktls_init(priv); if (err) mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); @@ -5242,7 +5250,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { mlx5e_health_destroy_reporters(priv); mlx5e_ktls_cleanup(priv); - mlx5e_ipsec_cleanup(priv); mlx5e_fs_cleanup(priv->fs); } @@ -5371,6 +5378,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) int err; mlx5e_fs_init_l2_addr(priv->fs, netdev); + mlx5e_ipsec_init(priv); err = mlx5e_macsec_init(priv); if (err) @@ -5434,6 +5442,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5_lag_remove_netdev(mdev, priv->netdev); mlx5_vxlan_reset_to_default(mdev->vxlan); mlx5e_macsec_cleanup(priv); + mlx5e_ipsec_cleanup(priv); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) @@ -5940,16 +5949,16 @@ static int mlx5e_probe(struct auxiliary_device *adev, goto err_profile_cleanup; } + SET_NETDEV_DEVLINK_PORT(netdev, mlx5e_devlink_get_dl_port(priv)); err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); goto err_resume; } - mlx5e_devlink_port_type_eth_set(priv); - mlx5e_dcbnl_init_app(priv); mlx5_uplink_netdev_set(mdev, netdev); + mlx5e_params_print_info(mdev, &priv->channels.params); return 0; err_resume: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 794cd8dfe9c9..75b9e1528fd2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -85,18 +85,25 @@ static const struct counter_desc sw_rep_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) }, }; -struct vport_stats { - u64 vport_rx_packets; - u64 vport_tx_packets; - u64 vport_rx_bytes; - u64 vport_tx_bytes; -}; - static const struct counter_desc vport_rep_stats_desc[] = { - { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_packets) }, - { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_bytes) }, - { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_packets) }, - { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, vport_rx_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, vport_rx_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, vport_tx_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, vport_tx_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + rx_vport_rdma_unicast_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, rx_vport_rdma_unicast_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + tx_vport_rdma_unicast_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, tx_vport_rdma_unicast_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + rx_vport_rdma_multicast_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + rx_vport_rdma_multicast_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + tx_vport_rdma_multicast_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + tx_vport_rdma_multicast_bytes) }, }; #define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc) @@ -161,33 +168,80 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep) int i; for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport, + data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats, vport_rep_stats_desc, i); return idx; } static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) { + struct mlx5e_rep_stats *rep_stats = &priv->stats.rep_stats; + int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out); struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - struct rtnl_link_stats64 *vport_stats; - struct ifla_vf_stats vf_stats; + u32 *out; int err; - err = mlx5_eswitch_get_vport_stats(esw, rep->vport, &vf_stats); + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return; + + err = mlx5_core_query_vport_counter(esw->dev, 1, rep->vport - 1, 0, out); if (err) { netdev_warn(priv->netdev, "vport %d error %d reading stats\n", rep->vport, err); return; } - vport_stats = &priv->stats.vf_vport; + #define MLX5_GET_CTR(p, x) \ + MLX5_GET64(query_vport_counter_out, p, x) /* flip tx/rx as we are reporting the counters for the switch vport */ - vport_stats->rx_packets = vf_stats.tx_packets; - vport_stats->rx_bytes = vf_stats.tx_bytes; - vport_stats->tx_packets = vf_stats.rx_packets; - vport_stats->tx_bytes = vf_stats.rx_bytes; + rep_stats->vport_rx_packets = + MLX5_GET_CTR(out, transmitted_ib_unicast.packets) + + MLX5_GET_CTR(out, transmitted_eth_unicast.packets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.packets) + + MLX5_GET_CTR(out, transmitted_eth_multicast.packets) + + MLX5_GET_CTR(out, transmitted_eth_broadcast.packets); + + rep_stats->vport_tx_packets = + MLX5_GET_CTR(out, received_ib_unicast.packets) + + MLX5_GET_CTR(out, received_eth_unicast.packets) + + MLX5_GET_CTR(out, received_ib_multicast.packets) + + MLX5_GET_CTR(out, received_eth_multicast.packets) + + MLX5_GET_CTR(out, received_eth_broadcast.packets); + + rep_stats->vport_rx_bytes = + MLX5_GET_CTR(out, transmitted_ib_unicast.octets) + + MLX5_GET_CTR(out, transmitted_eth_unicast.octets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.octets) + + MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); + + rep_stats->vport_tx_bytes = + MLX5_GET_CTR(out, received_ib_unicast.octets) + + MLX5_GET_CTR(out, received_eth_unicast.octets) + + MLX5_GET_CTR(out, received_ib_multicast.octets) + + MLX5_GET_CTR(out, received_eth_multicast.octets) + + MLX5_GET_CTR(out, received_eth_broadcast.octets); + + rep_stats->rx_vport_rdma_unicast_packets = + MLX5_GET_CTR(out, transmitted_ib_unicast.packets); + rep_stats->tx_vport_rdma_unicast_packets = + MLX5_GET_CTR(out, received_ib_unicast.packets); + rep_stats->rx_vport_rdma_unicast_bytes = + MLX5_GET_CTR(out, transmitted_ib_unicast.octets); + rep_stats->tx_vport_rdma_unicast_bytes = + MLX5_GET_CTR(out, received_ib_unicast.octets); + rep_stats->rx_vport_rdma_multicast_packets = + MLX5_GET_CTR(out, transmitted_ib_multicast.packets); + rep_stats->tx_vport_rdma_multicast_packets = + MLX5_GET_CTR(out, received_ib_multicast.packets); + rep_stats->rx_vport_rdma_multicast_bytes = + MLX5_GET_CTR(out, transmitted_ib_multicast.octets); + rep_stats->tx_vport_rdma_multicast_bytes = + MLX5_GET_CTR(out, received_ib_multicast.octets); + + kvfree(out); } static void mlx5e_rep_get_strings(struct net_device *dev, @@ -607,15 +661,6 @@ static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) return mlx5e_change_mtu(netdev, new_mtu, NULL); } -static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *netdev) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_core_dev *dev = priv->mdev; - - return mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); -} - static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -644,7 +689,6 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_setup_tc = mlx5e_rep_setup_tc, - .ndo_get_devlink_port = mlx5e_rep_get_devlink_port, .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, @@ -761,7 +805,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - int err; priv->fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); @@ -770,10 +813,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, return -ENOMEM; } - err = mlx5e_ipsec_init(priv); - if (err) - mlx5_core_err(mdev, "Uplink rep IPsec initialization failed, %d\n", err); - mlx5e_vxlan_set_netdev_info(priv); mlx5e_build_rep_params(netdev); mlx5e_timestamp_init(priv); @@ -783,7 +822,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { mlx5e_fs_cleanup(priv->fs); - mlx5e_ipsec_cleanup(priv); } static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv) @@ -1122,6 +1160,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; + mlx5e_ipsec_init(priv); + netdev->min_mtu = ETH_MIN_MTU; mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1); netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu); @@ -1168,6 +1208,8 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) mlx5e_rep_tc_disable(priv); mlx5_lag_remove_netdev(mdev, priv->netdev); mlx5_vxlan_reset_to_default(mdev->vxlan); + + mlx5e_ipsec_cleanup(priv); } static MLX5E_DEFINE_STATS_GRP(sw_rep, 0); @@ -1253,37 +1295,20 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev)); struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); - struct devlink_port *dl_port; - int err; rpriv->netdev = priv->netdev; - - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); - if (err) - return err; - - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_eth_set(dl_port, rpriv->netdev); - - return 0; + return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, + rpriv); } static void mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) { struct net_device *netdev = rpriv->netdev; - struct devlink_port *dl_port; - struct mlx5_core_dev *dev; struct mlx5e_priv *priv; priv = netdev_priv(netdev); - dev = priv->mdev; - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_clear(dl_port); mlx5e_netdev_attach_nic_profile(priv); } @@ -1326,6 +1351,11 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto err_cleanup_profile; } + dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, + rpriv->rep->vport); + if (dl_port) + SET_NETDEV_DEVLINK_PORT(netdev, dl_port); + err = register_netdev(netdev); if (err) { netdev_warn(netdev, @@ -1334,9 +1364,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto err_detach_netdev; } - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_eth_set(dl_port, netdev); return 0; err_detach_netdev: @@ -1382,8 +1409,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5_core_dev *dev = priv->mdev; - struct devlink_port *dl_port; void *ppriv = priv->ppriv; if (rep->vport == MLX5_VPORT_UPLINK) { @@ -1391,9 +1416,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) goto free_ppriv; } - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_clear(dl_port); unregister_netdev(netdev); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index a61a43fc8d5c..c8820ab22169 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -89,6 +89,25 @@ static inline void mlx5e_read_cqe_slot(struct mlx5_cqwq *wq, memcpy(data, mlx5_cqwq_get_wqe(wq, ci), sizeof(struct mlx5_cqe64)); } +static void mlx5e_read_enhanced_title_slot(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe) +{ + struct mlx5e_cq_decomp *cqd = &rq->cqd; + struct mlx5_cqe64 *title = &cqd->title; + + memcpy(title, cqe, sizeof(struct mlx5_cqe64)); + + if (likely(test_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state))) + return; + + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + cqd->wqe_counter = mpwrq_get_cqe_stride_index(title) + + mpwrq_get_cqe_consumed_strides(title); + else + cqd->wqe_counter = + mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, be16_to_cpu(title->wqe_counter) + 1); +} + static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq, struct mlx5_cqwq *wq, u32 cqcc) @@ -175,6 +194,38 @@ static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq, cqd->title.rss_hash_result = 0; } +static u32 mlx5e_decompress_enhanced_cqe(struct mlx5e_rq *rq, + struct mlx5_cqwq *wq, + struct mlx5_cqe64 *cqe, + int budget_rem) +{ + struct mlx5e_cq_decomp *cqd = &rq->cqd; + u32 cqcc, left; + u32 i; + + left = get_cqe_enhanced_num_mini_cqes(cqe); + /* Here we avoid breaking the cqe compression session in the middle + * in case budget is not sufficient to handle all of it. In this case + * we return work_done == budget_rem to give 'busy' napi indication. + */ + if (unlikely(left > budget_rem)) + return budget_rem; + + cqcc = wq->cc; + cqd->mini_arr_idx = 0; + memcpy(cqd->mini_arr, cqe, sizeof(struct mlx5_cqe64)); + for (i = 0; i < left; i++, cqd->mini_arr_idx++, cqcc++) { + mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, &cqd->title); + } + wq->cc = cqcc; + rq->stats->cqe_compress_pkts += left; + + return left; +} + static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, struct mlx5_cqwq *wq, int update_owner_only, @@ -220,7 +271,7 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, rq, &cqd->title); cqd->mini_arr_idx++; - return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; + return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem); } static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, struct page *page) @@ -542,8 +593,8 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, int headroom, i; headroom = rq->buff.headroom; - new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); - entries = ALIGN(klm_entries, MLX5_UMR_KLM_ALIGNMENT); + new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1)); + entries = ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT); wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries); pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs); umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); @@ -552,7 +603,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, for (i = 0; i < entries; i++, index++) { dma_info = &shampo->info[index]; if (i >= klm_entries || (index < shampo->pi && shampo->pi - index < - MLX5_UMR_KLM_ALIGNMENT)) + MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT)) goto update_klm; header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; @@ -617,8 +668,8 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) if (!klm_entries) return 0; - klm_entries += (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); - index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_ALIGNMENT); + klm_entries += (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1)); + index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT); entries_before = shampo->hd_per_wq - index; if (unlikely(entries_before < klm_entries)) @@ -676,6 +727,17 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) }; } + /* Pad if needed, in case the value set to ucseg->xlt_octowords + * in mlx5e_build_umr_wqe() needed alignment. + */ + if (rq->mpwqe.pages_per_wqe & (MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT - 1)) { + int pad = ALIGN(rq->mpwqe.pages_per_wqe, MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT) - + rq->mpwqe.pages_per_wqe; + + memset(&umr_wqe->inline_mtts[rq->mpwqe.pages_per_wqe], 0, + sizeof(*umr_wqe->inline_mtts) * pad); + } + bitmap_zero(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe); wi->consumed_strides = 0; @@ -2211,45 +2273,102 @@ mpwrq_cqe_out: mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); } -int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) +static int mlx5e_rx_cq_process_enhanced_cqe_comp(struct mlx5e_rq *rq, + struct mlx5_cqwq *cqwq, + int budget_rem) { - struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); - struct mlx5_cqwq *cqwq = &cq->wq; - struct mlx5_cqe64 *cqe; + struct mlx5_cqe64 *cqe, *title_cqe = NULL; + struct mlx5e_cq_decomp *cqd = &rq->cqd; int work_done = 0; - if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) - return 0; + cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq); + if (!cqe) + return work_done; - if (rq->cqd.left) { - work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget); - if (work_done >= budget) - goto out; + if (cqd->last_cqe_title && + (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED)) { + rq->stats->cqe_compress_blks++; + cqd->last_cqe_title = false; } - cqe = mlx5_cqwq_get_cqe(cqwq); - if (!cqe) { - if (unlikely(work_done)) - goto out; - return 0; + do { + if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { + if (title_cqe) { + mlx5e_read_enhanced_title_slot(rq, title_cqe); + title_cqe = NULL; + rq->stats->cqe_compress_blks++; + } + work_done += + mlx5e_decompress_enhanced_cqe(rq, cqwq, cqe, + budget_rem - work_done); + continue; + } + title_cqe = cqe; + mlx5_cqwq_pop(cqwq); + + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, cqe); + work_done++; + } while (work_done < budget_rem && + (cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq))); + + /* last cqe might be title on next poll bulk */ + if (title_cqe) { + mlx5e_read_enhanced_title_slot(rq, title_cqe); + cqd->last_cqe_title = true; } - do { + return work_done; +} + +static int mlx5e_rx_cq_process_basic_cqe_comp(struct mlx5e_rq *rq, + struct mlx5_cqwq *cqwq, + int budget_rem) +{ + struct mlx5_cqe64 *cqe; + int work_done = 0; + + if (rq->cqd.left) + work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget_rem); + + while (work_done < budget_rem && (cqe = mlx5_cqwq_get_cqe(cqwq))) { if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { work_done += mlx5e_decompress_cqes_start(rq, cqwq, - budget - work_done); + budget_rem - work_done); continue; } mlx5_cqwq_pop(cqwq); - INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, rq, cqe); - } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); + work_done++; + } + + return work_done; +} + +int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) +{ + struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); + struct mlx5_cqwq *cqwq = &cq->wq; + int work_done; + + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) + return 0; + + if (test_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state)) + work_done = mlx5e_rx_cq_process_enhanced_cqe_comp(rq, cqwq, + budget); + else + work_done = mlx5e_rx_cq_process_basic_cqe_comp(rq, cqwq, + budget); + + if (work_done == 0) + return 0; -out: if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state) && rq->hw_gro_data->skb) mlx5e_shampo_flush_skb(rq, NULL, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 03c1841970f1..6687b8136e44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1241,6 +1241,23 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy) mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0); } +void mlx5e_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + u32 out[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; + int sz = MLX5_ST_SZ_BYTES(ppcnt_reg); + + MLX5_SET(ppcnt_reg, in, local_port, 1); + MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP); + mlx5_core_access_reg(priv->mdev, in, sz, out, + MLX5_ST_SZ_BYTES(ppcnt_reg), MLX5_REG_PPCNT, 0, 0); + + stats->link_down_events = MLX5_GET(ppcnt_reg, out, + counter_set.phys_layer_cntrs.link_down_events); +} + static int fec_num_lanes(struct mlx5_core_dev *dev) { u32 out[MLX5_ST_SZ_DW(pmlp_reg)] = {}; @@ -2463,6 +2480,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = { &MLX5E_STATS_GRP(per_prio), &MLX5E_STATS_GRP(pme), #ifdef CONFIG_MLX5_EN_IPSEC + &MLX5E_STATS_GRP(ipsec_hw), &MLX5E_STATS_GRP(ipsec_sw), #endif &MLX5E_STATS_GRP(tls), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 9f781085be47..375752d6546d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -126,6 +126,8 @@ void mlx5e_stats_eth_ctrl_get(struct mlx5e_priv *priv, void mlx5e_stats_rmon_get(struct mlx5e_priv *priv, struct ethtool_rmon_stats *rmon, const struct ethtool_rmon_hist_range **ranges); +void mlx5e_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats); /* Concrete NIC Stats */ @@ -461,6 +463,21 @@ struct mlx5e_ptp_cq_stats { u64 resync_event; }; +struct mlx5e_rep_stats { + u64 vport_rx_packets; + u64 vport_tx_packets; + u64 vport_rx_bytes; + u64 vport_tx_bytes; + u64 rx_vport_rdma_unicast_packets; + u64 tx_vport_rdma_unicast_packets; + u64 rx_vport_rdma_unicast_bytes; + u64 tx_vport_rdma_unicast_bytes; + u64 rx_vport_rdma_multicast_packets; + u64 tx_vport_rdma_multicast_packets; + u64 rx_vport_rdma_multicast_bytes; + u64 tx_vport_rdma_multicast_bytes; +}; + struct mlx5e_stats { struct mlx5e_sw_stats sw; struct mlx5e_qcounter_stats qcnt; @@ -469,6 +486,7 @@ struct mlx5e_stats { struct mlx5e_pport_stats pport; struct rtnl_link_stats64 vf_vport; struct mlx5e_pcie_stats pcie; + struct mlx5e_rep_stats rep_stats; }; extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[]; @@ -488,6 +506,7 @@ extern MLX5E_DECLARE_STATS_GRP(per_prio); extern MLX5E_DECLARE_STATS_GRP(pme); extern MLX5E_DECLARE_STATS_GRP(channels); extern MLX5E_DECLARE_STATS_GRP(per_port_buff_congest); +extern MLX5E_DECLARE_STATS_GRP(ipsec_hw); extern MLX5E_DECLARE_STATS_GRP(ipsec_sw); extern MLX5E_DECLARE_STATS_GRP(ptp); extern MLX5E_DECLARE_STATS_GRP(macsec_hw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index bd9936af4582..9af2aa2922f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -132,6 +132,15 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [PACKET_COLOR_TO_REG] = packet_color_to_reg, }; +struct mlx5e_tc_jump_state { + u32 jump_count; + bool jump_target; + struct mlx5_flow_attr *jumping_attr; + + enum flow_action_id last_id; + u32 last_index; +}; + struct mlx5e_tc_table *mlx5e_tc_table_alloc(void) { struct mlx5e_tc_table *tc; @@ -160,6 +169,7 @@ static struct lock_class_key tc_ht_lock_key; static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); static void free_flow_post_acts(struct mlx5e_tc_flow *flow); +static void mlx5_free_flow_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr); void mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, @@ -392,8 +402,9 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, static bool is_flow_meter_action(struct mlx5_flow_attr *attr) { - return ((attr->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) && - (attr->exe_aso_type == MLX5_EXE_ASO_FLOW_METER)); + return (((attr->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) && + (attr->exe_aso_type == MLX5_EXE_ASO_FLOW_METER)) || + attr->flags & MLX5_ATTR_FLAG_MTU); } static int @@ -404,6 +415,7 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, struct mlx5e_post_meter_priv *post_meter; enum mlx5_flow_namespace_type ns_type; struct mlx5e_flow_meter_handle *meter; + enum mlx5e_post_meter_type type; meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params); if (IS_ERR(meter)) { @@ -412,8 +424,11 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, } ns_type = mlx5e_tc_meter_get_namespace(meter->flow_meters); - post_meter = mlx5e_post_meter_init(priv, ns_type, post_act, meter->green_counter, - meter->red_counter); + type = meter->params.mtu ? MLX5E_POST_METER_MTU : MLX5E_POST_METER_RATE; + post_meter = mlx5e_post_meter_init(priv, ns_type, post_act, + type, + meter->act_counter, meter->drop_counter, + attr->branch_true, attr->branch_false); if (IS_ERR(post_meter)) { mlx5_core_err(priv->mdev, "Failed to init post meter\n"); goto err_meter_init; @@ -432,9 +447,9 @@ err_meter_init: } static void -mlx5e_tc_del_flow_meter(struct mlx5_flow_attr *attr) +mlx5e_tc_del_flow_meter(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) { - mlx5e_post_meter_cleanup(attr->meter_attr.post_meter); + mlx5e_post_meter_cleanup(esw, attr->meter_attr.post_meter); mlx5e_tc_meter_put(attr->meter_attr.meter); } @@ -495,7 +510,7 @@ mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv, mlx5_eswitch_del_offloaded_rule(esw, rule, attr); if (attr->meter_attr.meter) - mlx5e_tc_del_flow_meter(attr); + mlx5e_tc_del_flow_meter(esw, attr); } int @@ -606,6 +621,12 @@ int mlx5e_get_flow_namespace(struct mlx5e_tc_flow *flow) MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; } +static struct mlx5_core_dev * +get_flow_counter_dev(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? flow->attr->esw_attr->counter_dev : flow->priv->mdev; +} + static struct mod_hdr_tbl * get_mod_hdr_table(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { @@ -1060,12 +1081,9 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, hash_hairpin_info(peer_id, match_prio)); mutex_unlock(&tc->hairpin_tbl_lock); - params.log_data_size = 16; - params.log_data_size = min_t(u8, params.log_data_size, - MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); - params.log_data_size = max_t(u8, params.log_data_size, - MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz)); - + params.log_data_size = clamp_t(u8, 16, + MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), + MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); params.log_num_packets = params.log_data_size - MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(priv->mdev); params.log_num_packets = min_t(u8, params.log_num_packets, @@ -1722,6 +1740,90 @@ clean_encap_dests(struct mlx5e_priv *priv, } static int +verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) +{ + if (!(actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule must have at least one forward/drop action"); + return -EOPNOTSUPP; + } + + if (!(~actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); + return -EOPNOTSUPP; + } + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int +post_process_attr(struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + bool is_post_act_attr, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; + bool vf_tun; + int err = 0; + + err = verify_attr_actions(attr->action, extack); + if (err) + goto err_out; + + err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); + if (err) + goto err_out; + + if (mlx5e_is_eswitch_flow(flow)) { + err = mlx5_eswitch_add_vlan_action(esw, attr); + if (err) + goto err_out; + } + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + if (vf_tun || is_post_act_attr) { + err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr); + if (err) + goto err_out; + } else { + err = mlx5e_attach_mod_hdr(flow->priv, flow, attr->parse_attr); + if (err) + goto err_out; + } + } + + if (attr->branch_true && + attr->branch_true->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_true); + if (err) + goto err_out; + } + + if (attr->branch_false && + attr->branch_false->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_false); + if (err) + goto err_out; + } + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + err = alloc_flow_attr_counter(get_flow_counter_dev(flow), attr); + if (err) + goto err_out; + } + +err_out: + return err; +} + +static int mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -1731,7 +1833,6 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; u32 max_prio, max_chain; - bool vf_tun; int err = 0; parse_attr = attr->parse_attr; @@ -1821,32 +1922,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - err = set_encap_dests(priv, flow, attr, extack, &vf_tun); + err = post_process_attr(flow, attr, false, extack); if (err) goto err_out; - err = mlx5_eswitch_add_vlan_action(esw, attr); - if (err) - goto err_out; - - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - if (vf_tun) { - err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); - if (err) - goto err_out; - } else { - err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - if (err) - goto err_out; - } - } - - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - err = alloc_flow_attr_counter(esw_attr->counter_dev, attr); - if (err) - goto err_out; - } - /* we get here if one of the following takes place: * (1) there's no error * (2) there's an encap action and we don't have valid neigh @@ -1882,6 +1961,16 @@ static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow) return !!geneve_tlv_opt_0_data; } +static void free_branch_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) +{ + if (!attr) + return; + + mlx5_free_flow_attr(flow, attr); + kvfree(attr->parse_attr); + kfree(attr); +} + static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { @@ -1937,6 +2026,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_detach_decap(priv, flow); free_flow_post_acts(flow); + free_branch_attr(flow, attr->branch_true); + free_branch_attr(flow, attr->branch_false); if (flow->attr->lag.count) mlx5_lag_del_mpesw_rule(esw->dev); @@ -3510,36 +3601,6 @@ actions_match_supported(struct mlx5e_priv *priv, ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; ct_flow = flow_flag_test(flow, CT) && !ct_clear; - if (!(actions & - (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG_MOD(extack, "Rule must have at least one forward/drop action"); - return false; - } - - if (!(~actions & - (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); - return false; - } - - if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && - actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { - NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); - return false; - } - - if (!(~actions & - (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); - return false; - } - - if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && - actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { - NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); - return false; - } - if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, ct_flow, ct_clear, extack)) @@ -3639,15 +3700,12 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr, attr2->esw_attr->split_count = 0; } + attr2->branch_true = NULL; + attr2->branch_false = NULL; + attr2->jumping_attr = NULL; return attr2; } -static struct mlx5_core_dev * -get_flow_counter_dev(struct mlx5e_tc_flow *flow) -{ - return mlx5e_is_eswitch_flow(flow) ? flow->attr->esw_attr->counter_dev : flow->priv->mdev; -} - struct mlx5_flow_attr * mlx5e_tc_get_encap_attr(struct mlx5e_tc_flow *flow) { @@ -3683,28 +3741,15 @@ mlx5e_tc_unoffload_flow_post_acts(struct mlx5e_tc_flow *flow) static void free_flow_post_acts(struct mlx5e_tc_flow *flow) { - struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); - struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *tmp; - bool vf_tun; list_for_each_entry_safe(attr, tmp, &flow->attrs, list) { if (list_is_last(&attr->list, &flow->attrs)) break; - if (attr->post_act_handle) - mlx5e_tc_post_act_del(post_act, attr->post_act_handle); - - clean_encap_dests(flow->priv, flow, attr, &vf_tun); - - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) - mlx5_fc_destroy(counter_dev, attr->counter); - - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); - if (attr->modify_hdr) - mlx5_modify_header_dealloc(flow->priv->mdev, attr->modify_hdr); - } + mlx5_free_flow_attr(flow, attr); + free_branch_attr(flow, attr->branch_true); + free_branch_attr(flow, attr->branch_false); list_del(&attr->list); kvfree(attr->parse_attr); @@ -3757,7 +3802,6 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *next_attr = NULL; struct mlx5e_post_act_handle *handle; - bool vf_tun; int err; /* This is going in reverse order as needed. @@ -3767,7 +3811,9 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (!next_attr) { /* Set counter action on last post act rule. */ attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; - } else { + } + + if (next_attr && !(attr->flags & MLX5_ATTR_FLAG_TERMINATING)) { err = mlx5e_tc_act_set_next_post_act(flow, attr, next_attr); if (err) goto out_free; @@ -3779,26 +3825,14 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (list_is_last(&attr->list, &flow->attrs)) break; - err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); + err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); if (err) goto out_free; - err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); + err = post_process_attr(flow, attr, true, extack); if (err) goto out_free; - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr); - if (err) - goto out_free; - } - - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - err = alloc_flow_attr_counter(get_flow_counter_dev(flow), attr); - if (err) - goto out_free; - } - handle = mlx5e_tc_post_act_add(post_act, attr); if (IS_ERR(handle)) { err = PTR_ERR(handle); @@ -3806,6 +3840,13 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) } attr->post_act_handle = handle; + + if (attr->jumping_attr) { + err = mlx5e_tc_act_set_next_post_act(flow, attr->jumping_attr, attr); + if (err) + goto out_free; + } + next_attr = attr; } @@ -3825,12 +3866,145 @@ out_free: } static int +alloc_branch_attr(struct mlx5e_tc_flow *flow, + struct mlx5e_tc_act_branch_ctrl *cond, + struct mlx5_flow_attr **cond_attr, + u32 *jump_count, + struct netlink_ext_ack *extack) +{ + struct mlx5_flow_attr *attr; + int err = 0; + + *cond_attr = mlx5e_clone_flow_attr_for_post_act(flow->attr, + mlx5e_get_flow_namespace(flow)); + if (!(*cond_attr)) + return -ENOMEM; + + attr = *cond_attr; + + switch (cond->act_id) { + case FLOW_ACTION_DROP: + attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP; + break; + case FLOW_ACTION_ACCEPT: + case FLOW_ACTION_PIPE: + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + break; + case FLOW_ACTION_JUMP: + if (*jump_count) { + NL_SET_ERR_MSG_MOD(extack, "Cannot offload flows with nested jumps"); + err = -EOPNOTSUPP; + goto out_err; + } + *jump_count = cond->extval; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + break; + default: + err = -EOPNOTSUPP; + goto out_err; + } + + return err; +out_err: + kfree(*cond_attr); + *cond_attr = NULL; + return err; +} + +static void +dec_jump_count(struct flow_action_entry *act, struct mlx5e_tc_act *tc_act, + struct mlx5_flow_attr *attr, struct mlx5e_priv *priv, + struct mlx5e_tc_jump_state *jump_state) +{ + if (!jump_state->jump_count) + return; + + /* Single tc action can instantiate multiple offload actions (e.g. pedit) + * Jump only over a tc action + */ + if (act->id == jump_state->last_id && act->hw_index == jump_state->last_index) + return; + + jump_state->last_id = act->id; + jump_state->last_index = act->hw_index; + + /* nothing to do for intermediate actions */ + if (--jump_state->jump_count > 1) + return; + + if (jump_state->jump_count == 1) { /* last action in the jump action list */ + + /* create a new attribute after this action */ + jump_state->jump_target = true; + + if (tc_act->is_terminating_action) { /* the branch ends here */ + attr->flags |= MLX5_ATTR_FLAG_TERMINATING; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + } else { /* the branch continues executing the rest of the actions */ + struct mlx5e_post_act *post_act; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + post_act = get_post_action(priv); + attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act); + } + } else if (jump_state->jump_count == 0) { /* first attr after the jump action list */ + /* This is the post action for the jumping attribute (either red or green) + * Use the stored jumping_attr to set the post act id on the jumping attribute + */ + attr->jumping_attr = jump_state->jumping_attr; + } +} + +static int +parse_branch_ctrl(struct flow_action_entry *act, struct mlx5e_tc_act *tc_act, + struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, + struct mlx5e_tc_jump_state *jump_state, + struct netlink_ext_ack *extack) +{ + struct mlx5e_tc_act_branch_ctrl cond_true, cond_false; + u32 jump_count = jump_state->jump_count; + int err; + + if (!tc_act->get_branch_ctrl) + return 0; + + tc_act->get_branch_ctrl(act, &cond_true, &cond_false); + + err = alloc_branch_attr(flow, &cond_true, + &attr->branch_true, &jump_count, extack); + if (err) + goto out_err; + + if (jump_count) + jump_state->jumping_attr = attr->branch_true; + + err = alloc_branch_attr(flow, &cond_false, + &attr->branch_false, &jump_count, extack); + if (err) + goto err_branch_false; + + if (jump_count && !jump_state->jumping_attr) + jump_state->jumping_attr = attr->branch_false; + + jump_state->jump_count = jump_count; + return 0; + +err_branch_false: + free_branch_attr(flow, attr->branch_true); +out_err: + return err; +} + +static int parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, struct flow_action *flow_action) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow_action flow_action_reorder; struct mlx5e_tc_flow *flow = parse_state->flow; + struct mlx5e_tc_jump_state jump_state = {}; struct mlx5_flow_attr *attr = flow->attr; enum mlx5_flow_namespace_type ns_type; struct mlx5e_priv *priv = flow->priv; @@ -3850,6 +4024,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, list_add(&attr->list, &flow->attrs); flow_action_for_each(i, _act, &flow_action_reorder) { + jump_state.jump_target = false; act = *_act; tc_act = mlx5e_tc_act_get(act->id, ns_type); if (!tc_act) { @@ -3867,12 +4042,19 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, if (err) goto out_free; + dec_jump_count(act, tc_act, attr, priv, &jump_state); + + err = parse_branch_ctrl(act, tc_act, flow, attr, &jump_state, extack); + if (err) + goto out_free; + parse_state->actions |= attr->action; /* Split attr for multi table act if not the last act. */ - if (tc_act->is_multi_table_act && + if (jump_state.jump_target || + (tc_act->is_multi_table_act && tc_act->is_multi_table_act(priv, act, attr) && - i < flow_action_reorder.num_entries - 1) { + i < flow_action_reorder.num_entries - 1)) { err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); if (err) goto out_free; @@ -3954,6 +4136,10 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, if (err) return err; + err = verify_attr_actions(attr->action, extack); + if (err) + return err; + if (!actions_match_supported(priv, flow_action, parse_state->actions, parse_attr, flow, extack)) return -EOPNOTSUPP; @@ -4191,6 +4377,30 @@ mlx5_alloc_flow_attr(enum mlx5_flow_namespace_type type) return attr; } +static void +mlx5_free_flow_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) +{ + struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + bool vf_tun; + + if (!attr) + return; + + if (attr->post_act_handle) + mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle); + + clean_encap_dests(flow->priv, flow, attr, &vf_tun); + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) + mlx5_fc_destroy(counter_dev, attr->counter); + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); + if (attr->modify_hdr) + mlx5_modify_header_dealloc(flow->priv->mdev, attr->modify_hdr); + } +} + static int mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, struct flow_cls_offload *f, unsigned long flow_flags, @@ -4733,10 +4943,17 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, return err; } -int mlx5e_policer_validate(const struct flow_action *action, - const struct flow_action_entry *act, - struct netlink_ext_ack *extack) +static int +tc_matchall_police_validate(const struct flow_action *action, + const struct flow_action_entry *act, + struct netlink_ext_ack *extack) { + if (act->police.notexceed.act_id != FLOW_ACTION_CONTINUE) { + NL_SET_ERR_MSG_MOD(extack, + "Offload not supported when conform action is not continue"); + return -EOPNOTSUPP; + } + if (act->police.exceed.act_id != FLOW_ACTION_DROP) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when exceed action is not drop"); @@ -4787,13 +5004,7 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, flow_action_for_each(i, act, flow_action) { switch (act->id) { case FLOW_ACTION_POLICE: - if (act->police.notexceed.act_id != FLOW_ACTION_CONTINUE) { - NL_SET_ERR_MSG_MOD(extack, - "Offload not supported when conform action is not continue"); - return -EOPNOTSUPP; - } - - err = mlx5e_policer_validate(flow_action, act, extack); + err = tc_matchall_police_validate(flow_action, act, extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 48241317a535..50af70ef22f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -95,10 +95,13 @@ struct mlx5_flow_attr { */ bool count; } lag; + struct mlx5_flow_attr *branch_true; + struct mlx5_flow_attr *branch_false; + struct mlx5_flow_attr *jumping_attr; /* keep this union last */ union { - struct mlx5_esw_flow_attr esw_attr[0]; - struct mlx5_nic_flow_attr nic_attr[0]; + DECLARE_FLEX_ARRAY(struct mlx5_esw_flow_attr, esw_attr); + DECLARE_FLEX_ARRAY(struct mlx5_nic_flow_attr, nic_attr); }; }; @@ -110,6 +113,8 @@ enum { MLX5_ATTR_FLAG_SAMPLE = BIT(4), MLX5_ATTR_FLAG_ACCEPT = BIT(5), MLX5_ATTR_FLAG_CT = BIT(6), + MLX5_ATTR_FLAG_TERMINATING = BIT(7), + MLX5_ATTR_FLAG_MTU = BIT(8), }; /* Returns true if any of the flags that require skipping further TC/NF processing are set. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index a0242dc15741..8f7580fec193 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -19,6 +19,7 @@ #include "diag/fw_tracer.h" #include "mlx5_irq.h" #include "devlink.h" +#include "en_accel/ipsec.h" enum { MLX5_EQE_OWNER_INIT_VAL = 0x1, @@ -578,6 +579,10 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4]) if (MLX5_CAP_MACSEC(dev, log_max_macsec_offload)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE); + if (mlx5_ipsec_device_caps(dev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + async_event_mask |= + (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE); + mask[0] = async_event_mask; if (MLX5_CAP_GEN(dev, event_cap)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 4fbff7bcc155..b176648d1343 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1722,7 +1722,7 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid); if (!entry) { esw_debug(br_offloads->esw->dev, - "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + "FDB update entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", fdb_info->addr, fdb_info->vid, vport_num); return; } @@ -1775,9 +1775,9 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_o bridge = port->bridge; entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid); if (!entry) { - esw_warn(esw->dev, - "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", - fdb_info->addr, fdb_info->vid, vport_num); + esw_debug(esw->dev, + "FDB remove entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + fdb_info->addr, fdb_info->vid, vport_num); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c index 2db13c71e88c..3d0bbcca1cb9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c @@ -12,10 +12,11 @@ enum vnic_diag_counter { MLX5_VNIC_DIAG_CQ_OVERRUN, MLX5_VNIC_DIAG_INVALID_COMMAND, MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND, + MLX5_VNIC_DIAG_RX_STEERING_DISCARD, }; static int mlx5_esw_query_vnic_diag(struct mlx5_vport *vport, enum vnic_diag_counter counter, - u32 *val) + u64 *val) { u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {}; @@ -57,6 +58,10 @@ static int mlx5_esw_query_vnic_diag(struct mlx5_vport *vport, enum vnic_diag_cou case MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND: *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, quota_exceeded_command); break; + case MLX5_VNIC_DIAG_RX_STEERING_DISCARD: + *val = MLX5_GET64(vnic_diagnostic_statistics, vnic_diag_out, + nic_receive_steering_discard); + break; } return 0; @@ -65,14 +70,14 @@ static int mlx5_esw_query_vnic_diag(struct mlx5_vport *vport, enum vnic_diag_cou static int __show_vnic_diag(struct seq_file *file, struct mlx5_vport *vport, enum vnic_diag_counter type) { - u32 val = 0; + u64 val = 0; int ret; ret = mlx5_esw_query_vnic_diag(vport, type, &val); if (ret) return ret; - seq_printf(file, "%d\n", val); + seq_printf(file, "%llu\n", val); return 0; } @@ -112,6 +117,11 @@ static int quota_exceeded_command_show(struct seq_file *file, void *priv) return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND); } +static int rx_steering_discard_show(struct seq_file *file, void *priv) +{ + return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_RX_STEERING_DISCARD); +} + DEFINE_SHOW_ATTRIBUTE(total_q_under_processor_handle); DEFINE_SHOW_ATTRIBUTE(send_queue_priority_update_flow); DEFINE_SHOW_ATTRIBUTE(comp_eq_overrun); @@ -119,6 +129,7 @@ DEFINE_SHOW_ATTRIBUTE(async_eq_overrun); DEFINE_SHOW_ATTRIBUTE(cq_overrun); DEFINE_SHOW_ATTRIBUTE(invalid_command); DEFINE_SHOW_ATTRIBUTE(quota_exceeded_command); +DEFINE_SHOW_ATTRIBUTE(rx_steering_discard); void mlx5_esw_vport_debugfs_destroy(struct mlx5_eswitch *esw, u16 vport_num) { @@ -179,4 +190,9 @@ void mlx5_esw_vport_debugfs_create(struct mlx5_eswitch *esw, u16 vport_num, bool if (MLX5_CAP_GEN(esw->dev, quota_exceeded_count)) debugfs_create_file("quota_exceeded_command", 0444, vnic_diag, vport, "a_exceeded_command_fops); + + if (MLX5_CAP_GEN(esw->dev, nic_receive_steering_discard)) + debugfs_create_file("rx_steering_discard", 0444, vnic_diag, vport, + &rx_steering_discard_fops); + } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 9bc7be95db54..084a910bb4e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -91,7 +91,7 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ if (err) goto reg_err; - err = devl_rate_leaf_create(dl_port, vport); + err = devl_rate_leaf_create(dl_port, vport, NULL); if (err) goto rate_err; @@ -160,7 +160,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (err) return err; - err = devl_rate_leaf_create(dl_port, vport); + err = devl_rate_leaf_create(dl_port, vport, NULL); if (err) goto rate_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 374e3fbdc2cf..527e4bffda8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -772,6 +772,41 @@ static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw, esw_vport_destroy_offloads_acl_tables(esw, vport); } +static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + void *query_ctx; + void *hca_caps; + int err; + + if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) + return 0; + + query_ctx = kzalloc(query_out_sz, GFP_KERNEL); + if (!query_ctx) + return -ENOMEM; + + err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx, + MLX5_CAP_GENERAL); + if (err) + goto out_free; + + hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); + vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce); + + memset(query_ctx, 0, query_out_sz); + err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx, + MLX5_CAP_GENERAL_2); + if (err) + goto out_free; + + hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); + vport->info.mig_enabled = MLX5_GET(cmd_hca_cap_2, hca_caps, migratable); +out_free: + kfree(query_ctx); + return err; +} + static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { u16 vport_num = vport->vport; @@ -785,6 +820,10 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) if (mlx5_esw_is_manager_vport(esw, vport_num)) return 0; + err = mlx5_esw_vport_caps_get(esw, vport); + if (err) + goto err_caps; + mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, vport_num, 1, @@ -804,6 +843,10 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) vport->info.qos, flags); return 0; + +err_caps: + esw_vport_cleanup_acl(esw, vport); + return err; } /* Don't cleanup vport->info, it's needed to restore vport configuration */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 3029bc1c0dd0..5a85a5d32be7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -153,6 +153,8 @@ struct mlx5_vport_info { u8 qos; u8 spoofchk: 1; u8 trusted: 1; + u8 roce_enabled: 1; + u8 mig_enabled: 1; }; /* Vport context events */ @@ -508,7 +510,14 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); - +int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled, + struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, + struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled, + struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, + struct netlink_ext_ack *extack); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, @@ -744,6 +753,11 @@ static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw) return 0; } +static inline struct mlx5_flow_table * +mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw) +{ + return esw->fdb_table.offloads.slow_fdb; +} #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8c6c9bcb3dc3..e455b215c708 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -50,6 +50,7 @@ #include "en/mapping.h" #include "devlink.h" #include "lag/lag.h" +#include "en/tc/post_meter.h" #define mlx5_esw_for_each_rep(esw, i, rep) \ xa_for_each(&((esw)->offloads.vport_reps), i, rep) @@ -202,6 +203,21 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw, } static int +esw_setup_mtu_dest(struct mlx5_flow_destination *dest, + struct mlx5e_meter_attr *meter, + int i) +{ + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_RANGE; + dest[i].range.field = MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN; + dest[i].range.min = 0; + dest[i].range.max = meter->params.mtu; + dest[i].range.hit_ft = mlx5e_post_meter_get_mtu_true_ft(meter->post_meter); + dest[i].range.miss_ft = mlx5e_post_meter_get_mtu_false_ft(meter->post_meter); + + return 0; +} + +static int esw_setup_sampler_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, u32 sampler_id, @@ -248,7 +264,7 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_ac if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level)) flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest[i].ft = esw->fdb_table.offloads.slow_fdb; + dest[i].ft = mlx5_eswitch_get_slow_fdb(esw); } static int @@ -479,16 +495,21 @@ esw_setup_dests(struct mlx5_flow_destination *dest, esw_src_port_rewrite_supported(esw)) attr->flags |= MLX5_ATTR_FLAG_SRC_REWRITE; - if (attr->flags & MLX5_ATTR_FLAG_SAMPLE && - !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) { - esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i); - (*i)++; - } else if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) { + if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) { esw_setup_slow_path_dest(dest, flow_act, esw, *i); (*i)++; + goto out; + } + + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) { + esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i); + (*i)++; } else if (attr->flags & MLX5_ATTR_FLAG_ACCEPT) { esw_setup_accept_dest(dest, flow_act, chains, *i); (*i)++; + } else if (attr->flags & MLX5_ATTR_FLAG_MTU) { + err = esw_setup_mtu_dest(dest, &attr->meter_attr, *i); + (*i)++; } else if (esw_is_indir_table(esw, attr)) { err = esw_setup_indir_table(dest, flow_act, esw, attr, spec, true, i); } else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) { @@ -506,6 +527,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest, } } +out: return err; } @@ -637,6 +659,11 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, goto err_esw_get; } + if (!i) { + kfree(dest); + dest = NULL; + } + if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, esw_attr, &flow_act, dest, i); @@ -1046,7 +1073,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, if (rep->vport == MLX5_VPORT_UPLINK) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; - flow_rule = mlx5_add_flow_rules(on_esw->fdb_table.offloads.slow_fdb, + flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) esw_warn(on_esw->dev, "FDB: Failed to add send to vport rule err %ld\n", @@ -1095,7 +1122,7 @@ mlx5_eswitch_add_send_to_vport_meta_rule(struct mlx5_eswitch *esw, u16 vport_num mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num)); dest.vport.num = vport_num; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) esw_warn(esw->dev, "FDB: Failed to add send to vport meta rule vport %d, err %ld\n", @@ -1248,7 +1275,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, spec, MLX5_VPORT_PF); - flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); @@ -1260,7 +1287,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, if (mlx5_ecpf_vport_exists(esw->dev)) { vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); - flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); @@ -1274,7 +1301,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, peer_dev->priv.eswitch, spec, vport->vport); - flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); @@ -1363,7 +1390,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dest.vport.num = esw->manager_vport; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); @@ -1378,7 +1405,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16); dmac_v[0] = 0x01; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); @@ -1927,7 +1954,7 @@ send_vport_err: fdb_chains_err: mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); tc_miss_table_err: - mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); + mlx5_destroy_flow_table(mlx5_eswitch_get_slow_fdb(esw)); slow_fdb_err: /* Holds true only as long as DMFS is the default */ mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS); @@ -1938,7 +1965,7 @@ ns_err: static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) { - if (!esw->fdb_table.offloads.slow_fdb) + if (!mlx5_eswitch_get_slow_fdb(esw)) return; esw_debug(esw->dev, "Destroy offloads FDB Tables\n"); @@ -1954,7 +1981,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_chains_destroy(esw, esw_chains(esw)); mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); - mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); + mlx5_destroy_flow_table(mlx5_eswitch_get_slow_fdb(esw)); /* Holds true only as long as DMFS is the default */ mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, MLX5_FLOW_STEERING_MODE_DMFS); @@ -3886,7 +3913,7 @@ static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, if (!query_ctx) return -ENOMEM; - err = mlx5_vport_get_other_func_cap(esw->dev, vport_num, query_ctx); + err = mlx5_vport_get_other_func_general_cap(esw->dev, vport_num, query_ctx); if (err) goto out_free; @@ -4019,3 +4046,212 @@ int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, return mlx5_eswitch_set_vport_mac(esw, vport_num, hw_addr); } + +static struct mlx5_vport * +mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *esw) +{ + u16 vport_num; + + if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) + return ERR_PTR(-EOPNOTSUPP); + + vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index); + if (!is_port_function_supported(esw, vport_num)) + return ERR_PTR(-EOPNOTSUPP); + + return mlx5_eswitch_get_vport(esw, vport_num); +} + +int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + int err = -EOPNOTSUPP; + + esw = mlx5_devlink_eswitch_get(port->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + if (!MLX5_CAP_GEN(esw->dev, migration)) { + NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration"); + return err; + } + + vport = mlx5_devlink_port_fn_get_vport(port, esw); + if (IS_ERR(vport)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid port"); + return PTR_ERR(vport); + } + + mutex_lock(&esw->state_lock); + if (vport->enabled) { + *is_enabled = vport->info.mig_enabled; + err = 0; + } + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, + struct netlink_ext_ack *extack) +{ + int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + void *query_ctx; + void *hca_caps; + int err = -EOPNOTSUPP; + + esw = mlx5_devlink_eswitch_get(port->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + if (!MLX5_CAP_GEN(esw->dev, migration)) { + NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration"); + return err; + } + + vport = mlx5_devlink_port_fn_get_vport(port, esw); + if (IS_ERR(vport)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid port"); + return PTR_ERR(vport); + } + + mutex_lock(&esw->state_lock); + if (!vport->enabled) { + NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled"); + goto out; + } + + if (vport->info.mig_enabled == enable) { + err = 0; + goto out; + } + + query_ctx = kzalloc(query_out_sz, GFP_KERNEL); + if (!query_ctx) { + err = -ENOMEM; + goto out; + } + + err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx, + MLX5_CAP_GENERAL_2); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed getting HCA caps"); + goto out_free; + } + + hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); + memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), + MLX5_UN_SZ_BYTES(hca_cap_union)); + MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1); + + err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport, + MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting HCA migratable cap"); + goto out_free; + } + + vport->info.mig_enabled = enable; + +out_free: + kfree(query_ctx); +out: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + int err = -EOPNOTSUPP; + + esw = mlx5_devlink_eswitch_get(port->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + vport = mlx5_devlink_port_fn_get_vport(port, esw); + if (IS_ERR(vport)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid port"); + return PTR_ERR(vport); + } + + mutex_lock(&esw->state_lock); + if (vport->enabled) { + *is_enabled = vport->info.roce_enabled; + err = 0; + } + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, + struct netlink_ext_ack *extack) +{ + int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + int err = -EOPNOTSUPP; + void *query_ctx; + void *hca_caps; + u16 vport_num; + + esw = mlx5_devlink_eswitch_get(port->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + vport = mlx5_devlink_port_fn_get_vport(port, esw); + if (IS_ERR(vport)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid port"); + return PTR_ERR(vport); + } + vport_num = vport->vport; + + mutex_lock(&esw->state_lock); + if (!vport->enabled) { + NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled"); + goto out; + } + + if (vport->info.roce_enabled == enable) { + err = 0; + goto out; + } + + query_ctx = kzalloc(query_out_sz, GFP_KERNEL); + if (!query_ctx) { + err = -ENOMEM; + goto out; + } + + err = mlx5_vport_get_other_func_cap(esw->dev, vport_num, query_ctx, + MLX5_CAP_GENERAL); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed getting HCA caps"); + goto out_free; + } + + hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); + memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), + MLX5_UN_SZ_BYTES(hca_cap_union)); + MLX5_SET(cmd_hca_cap, hca_caps, roce, enable); + + err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num, + MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting HCA roce cap"); + goto out_free; + } + + vport->info.roce_enabled = enable; + +out_free: + kfree(query_ctx); +out: + mutex_unlock(&esw->state_lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index edd910258314..3a9a6bb9158d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -210,6 +210,18 @@ static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, return (port_mask & port_value) == MLX5_VPORT_UPLINK; } +static bool +mlx5_eswitch_is_push_vlan_no_cap(struct mlx5_eswitch *esw, + struct mlx5_flow_act *flow_act) +{ + if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH && + !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) & + MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX)) + return true; + + return false; +} + bool mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, @@ -225,10 +237,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, (!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port)) return false; - /* push vlan on RX */ - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH && - !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) & - MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX)) + if (mlx5_eswitch_is_push_vlan_no_cap(esw, flow_act)) return true; /* hairpin */ @@ -252,19 +261,31 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, struct mlx5_flow_act term_tbl_act = {}; struct mlx5_flow_handle *rule = NULL; bool term_table_created = false; + bool is_push_vlan_on_rx; int num_vport_dests = 0; int i, curr_dest; + is_push_vlan_on_rx = mlx5_eswitch_is_push_vlan_no_cap(esw, flow_act); mlx5_eswitch_termtbl_actions_move(flow_act, &term_tbl_act); term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; for (i = 0; i < num_dest; i++) { struct mlx5_termtbl_handle *tt; + bool hairpin = false; /* only vport destinations can be terminated */ if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) continue; + if (attr->dests[num_vport_dests].rep && + attr->dests[num_vport_dests].rep->vport == MLX5_VPORT_UPLINK) + hairpin = true; + + if (!is_push_vlan_on_rx && !hairpin) { + num_vport_dests++; + continue; + } + if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) { term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat; @@ -312,6 +333,9 @@ revert_changes: for (curr_dest = 0; curr_dest < num_vport_dests; curr_dest++) { struct mlx5_termtbl_handle *tt = attr->dests[curr_dest].termtbl; + if (!tt) + continue; + attr->dests[curr_dest].termtbl = NULL; /* search for the destination associated with the diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d53749248fa0..5a85d8c1e797 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -111,8 +111,8 @@ #define ETHTOOL_PRIO_NUM_LEVELS 1 #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) -/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}} */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 7 +/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy */ +#define KERNEL_NIC_PRIO_NUM_LEVELS 8 #define KERNEL_NIC_NUM_PRIOS 1 /* One more level for tc */ #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1) @@ -133,7 +133,7 @@ #define LAG_MIN_LEVEL (OFFLOADS_MIN_LEVEL + KERNEL_RX_MACSEC_MIN_LEVEL + 1) #define KERNEL_TX_IPSEC_NUM_PRIOS 1 -#define KERNEL_TX_IPSEC_NUM_LEVELS 1 +#define KERNEL_TX_IPSEC_NUM_LEVELS 2 #define KERNEL_TX_IPSEC_MIN_LEVEL (KERNEL_TX_IPSEC_NUM_LEVELS) #define KERNEL_TX_MACSEC_NUM_PRIOS 1 @@ -448,7 +448,8 @@ static bool is_fwd_dest_type(enum mlx5_flow_destination_type type) type == MLX5_FLOW_DESTINATION_TYPE_UPLINK || type == MLX5_FLOW_DESTINATION_TYPE_VPORT || type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER || - type == MLX5_FLOW_DESTINATION_TYPE_TIR; + type == MLX5_FLOW_DESTINATION_TYPE_TIR || + type == MLX5_FLOW_DESTINATION_TYPE_RANGE; } static bool check_valid_spec(const struct mlx5_flow_spec *spec) @@ -1578,7 +1579,13 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM && d1->ft_num == d2->ft_num) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER && - d1->sampler_id == d2->sampler_id)) + d1->sampler_id == d2->sampler_id) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_RANGE && + d1->range.field == d2->range.field && + d1->range.hit_ft == d2->range.hit_ft && + d1->range.miss_ft == d2->range.miss_ft && + d1->range.min == d2->range.min && + d1->range.max == d2->range.max)) return true; } @@ -1962,6 +1969,9 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->fg && ft->autogroup.active) return ERR_PTR(-EINVAL); + if (dest && dest_num <= 0) + return ERR_PTR(-EINVAL); + for (i = 0; i < dest_num; i++) { if (!dest_is_valid(&dest[i], flow_act, ft)) return ERR_PTR(-EINVAL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 3af50fd04d28..f137a0611b77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -123,6 +123,7 @@ enum mlx5_flow_steering_mode { enum mlx5_flow_steering_capabilty { MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0, MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1, + MLX5_FLOW_STEERING_CAP_MATCH_RANGES = 1UL << 2, }; struct mlx5_flow_steering { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 4e3a75496dd9..7c5c500fd215 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -561,12 +561,17 @@ static int mlx5i_open(struct net_device *netdev) if (err) goto err_remove_fs_underlay_qp; - epriv->profile->update_rx(epriv); + err = epriv->profile->update_rx(epriv); + if (err) + goto err_close_channels; + mlx5e_activate_priv_channels(epriv); mutex_unlock(&epriv->state_lock); return 0; +err_close_channels: + mlx5e_close_channels(&epriv->channels); err_remove_fs_underlay_qp: mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn); err_reset_qp: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 0227a521d301..4d9c9e49645c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -221,12 +221,16 @@ static int mlx5i_pkey_open(struct net_device *netdev) mlx5_core_warn(mdev, "opening child channels failed, %d\n", err); goto err_clear_state_opened_flag; } - epriv->profile->update_rx(epriv); + err = epriv->profile->update_rx(epriv); + if (err) + goto err_close_channels; mlx5e_activate_priv_channels(epriv); mutex_unlock(&epriv->state_lock); return 0; +err_close_channels: + mlx5e_close_channels(&epriv->channels); err_clear_state_opened_flag: mlx5e_destroy_tis(mdev, epriv->tisn[0][0]); err_remove_rx_uderlay_qp: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 0259a149a64c..d9fcb9ed726f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -118,13 +118,41 @@ struct mlx5_fib_event_work { }; }; +static struct net_device* +mlx5_lag_get_next_fib_dev(struct mlx5_lag *ldev, + struct fib_info *fi, + struct net_device *current_dev) +{ + struct net_device *fib_dev; + int i, ldev_idx, nhs; + + nhs = fib_info_num_path(fi); + i = 0; + if (current_dev) { + for (; i < nhs; i++) { + fib_dev = fib_info_nh(fi, i)->fib_nh_dev; + if (fib_dev == current_dev) { + i++; + break; + } + } + } + for (; i < nhs; i++) { + fib_dev = fib_info_nh(fi, i)->fib_nh_dev; + ldev_idx = mlx5_lag_dev_get_netdev_idx(ldev, fib_dev); + if (ldev_idx >= 0) + return ldev->pf[ldev_idx].netdev; + } + + return NULL; +} + static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, struct fib_entry_notifier_info *fen_info) { + struct net_device *nh_dev0, *nh_dev1; struct fib_info *fi = fen_info->fi; struct lag_mp *mp = &ldev->lag_mp; - struct fib_nh *fib_nh0, *fib_nh1; - unsigned int nhs; /* Handle delete event */ if (event == FIB_EVENT_ENTRY_DEL) { @@ -140,16 +168,25 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, fi->fib_priority >= mp->fib.priority) return; + nh_dev0 = mlx5_lag_get_next_fib_dev(ldev, fi, NULL); + nh_dev1 = mlx5_lag_get_next_fib_dev(ldev, fi, nh_dev0); + /* Handle add/replace event */ - nhs = fib_info_num_path(fi); - if (nhs == 1) { - if (__mlx5_lag_is_active(ldev)) { - struct fib_nh *nh = fib_info_nh(fi, 0); - struct net_device *nh_dev = nh->fib_nh_dev; - int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev); + if (!nh_dev0) { + if (mp->fib.dst == fen_info->dst && mp->fib.dst_len == fen_info->dst_len) + mp->fib.mfi = NULL; + return; + } - if (i < 0) - return; + if (nh_dev0 == nh_dev1) { + mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, + "Multipath offload doesn't support routes with multiple nexthops of the same device"); + return; + } + + if (!nh_dev1) { + if (__mlx5_lag_is_active(ldev)) { + int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev0); i++; mlx5_lag_set_port_affinity(ldev, i); @@ -159,21 +196,6 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, return; } - if (nhs != 2) - return; - - /* Verify next hops are ports of the same hca */ - fib_nh0 = fib_info_nh(fi, 0); - fib_nh1 = fib_info_nh(fi, 1); - if (!(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev && - fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev) && - !(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev && - fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev)) { - mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, - "Multipath offload require two ports of the same HCA\n"); - return; - } - /* First time we see multipath route */ if (!mp->fib.mfi && !__mlx5_lag_is_active(ldev)) { struct lag_tracker tracker; @@ -268,7 +290,6 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, struct mlx5_fib_event_work *fib_work; struct fib_entry_notifier_info *fen_info; struct fib_nh_notifier_info *fnh_info; - struct net_device *fib_dev; struct fib_info *fi; if (info->family != AF_INET) @@ -285,11 +306,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, fi = fen_info->fi; if (fi->nh) return NOTIFY_DONE; - fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; - if (fib_dev != ldev->pf[MLX5_LAG_P1].netdev && - fib_dev != ldev->pf[MLX5_LAG_P2].netdev) { - return NOTIFY_DONE; - } + fib_work = mlx5_lag_init_fib_work(ldev, event); if (!fib_work) return NOTIFY_DONE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index c971ff04dd04..5a80fb7dbbca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -334,9 +334,6 @@ err_cq: void mlx5_aso_destroy(struct mlx5_aso *aso) { - if (IS_ERR_OR_NULL(aso)) - return; - mlx5_aso_destroy_sq(aso); mlx5_aso_destroy_cq(&aso->cq); kfree(aso); @@ -356,12 +353,15 @@ void mlx5_aso_build_wqe(struct mlx5_aso *aso, u8 ds_cnt, cseg->general_id = cpu_to_be32(obj_id); } -void *mlx5_aso_get_wqe(struct mlx5_aso *aso) +struct mlx5_aso_wqe *mlx5_aso_get_wqe(struct mlx5_aso *aso) { + struct mlx5_aso_wqe *wqe; u16 pi; pi = mlx5_wq_cyc_ctr2ix(&aso->wq, aso->pc); - return mlx5_wq_cyc_get_wqe(&aso->wq, pi); + wqe = mlx5_wq_cyc_get_wqe(&aso->wq, pi); + memset(wqe, 0, sizeof(*wqe)); + return wqe; } void mlx5_aso_post_wqe(struct mlx5_aso *aso, bool with_data, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h index 2d40dcf9d42e..afb078bbb8ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h @@ -15,6 +15,7 @@ #define MLX5_WQE_CTRL_WQE_OPC_MOD_SHIFT 24 #define MLX5_MACSEC_ASO_DS_CNT (DIV_ROUND_UP(sizeof(struct mlx5_aso_wqe), MLX5_SEND_WQE_DS)) +#define ASO_CTRL_READ_EN BIT(0) struct mlx5_wqe_aso_ctrl_seg { __be32 va_h; __be32 va_l; /* include read_enable */ @@ -71,13 +72,14 @@ enum { }; enum { + MLX5_ACCESS_ASO_OPC_MOD_IPSEC = 0x0, MLX5_ACCESS_ASO_OPC_MOD_FLOW_METER = 0x2, MLX5_ACCESS_ASO_OPC_MOD_MACSEC = 0x5, }; struct mlx5_aso; -void *mlx5_aso_get_wqe(struct mlx5_aso *aso); +struct mlx5_aso_wqe *mlx5_aso_get_wqe(struct mlx5_aso *aso); void mlx5_aso_build_wqe(struct mlx5_aso *aso, u8 ds_cnt, struct mlx5_aso_wqe *aso_wqe, u32 obj_id, u32 opc_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index d3a9ae80fd30..69cfe60c558a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -339,35 +339,25 @@ static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) return mlx5_set_mtutc(mdev, in, sizeof(in)); } -static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); struct mlx5_timer *timer = &clock->timer; struct mlx5_core_dev *mdev; unsigned long flags; - int neg_adj = 0; - u32 diff; - u64 adj; + u32 mult; int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_adjfreq_real_time(mdev, delta); + err = mlx5_ptp_adjfreq_real_time(mdev, scaled_ppm_to_ppb(scaled_ppm)); if (err) return err; - if (delta < 0) { - neg_adj = 1; - delta = -delta; - } - - adj = timer->nominal_c_mult; - adj *= delta; - diff = div_u64(adj, 1000000000ULL); + mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm); write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); - timer->cycles.mult = neg_adj ? timer->nominal_c_mult - diff : - timer->nominal_c_mult + diff; + timer->cycles.mult = mult; mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); @@ -697,7 +687,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 0, - .adjfreq = mlx5_ptp_adjfreq, + .adjfine = mlx5_ptp_adjfine, .adjtime = mlx5_ptp_adjtime, .gettimex64 = mlx5_ptp_gettimex, .settime64 = mlx5_ptp_settime, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e58775a7d955..7f5db13e3550 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -37,7 +37,6 @@ #include <linux/pci.h> #include <linux/dma-mapping.h> #include <linux/slab.h> -#include <linux/io-mapping.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/mlx5/driver.h> @@ -1306,8 +1305,15 @@ static int mlx5_load(struct mlx5_core_dev *dev) mlx5_sf_dev_table_create(dev); + err = mlx5_devlink_traps_register(priv_to_devlink(dev)); + if (err) + goto err_traps_reg; + return 0; +err_traps_reg: + mlx5_sf_dev_table_destroy(dev); + mlx5_sriov_detach(dev); err_sriov: mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); @@ -1336,6 +1342,7 @@ err_irq_table: static void mlx5_unload(struct mlx5_core_dev *dev) { + mlx5_devlink_traps_unregister(priv_to_devlink(dev)); mlx5_sf_dev_table_destroy(dev); mlx5_sriov_detach(dev); mlx5_eswitch_disable(dev->priv.eswitch); @@ -1580,14 +1587,22 @@ err: return -ENOMEM; } +static int vhca_id_show(struct seq_file *file, void *priv) +{ + struct mlx5_core_dev *dev = file->private; + + seq_printf(file, "0x%x\n", MLX5_CAP_GEN(dev, vhca_id)); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(vhca_id); + int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; int err; memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); - INIT_LIST_HEAD(&priv->ctx_list); - spin_lock_init(&priv->ctx_lock); lockdep_register_key(&dev->lock_key); mutex_init(&dev->intf_state_mutex); lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key); @@ -1604,6 +1619,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device), mlx5_debugfs_root); + debugfs_create_file("vhca_id", 0400, priv->dbg.dbg_root, dev, &vhca_id_fops); INIT_LIST_HEAD(&priv->traps); err = mlx5_tout_init(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index a806e3de7b7c..029305a8b80a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -324,7 +324,10 @@ void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev); int mlx5_load_one(struct mlx5_core_dev *dev, bool recovery); int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery); -int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out); +int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 function_id, + u16 opmod); +#define mlx5_vport_get_other_func_general_cap(dev, fid, out) \ + mlx5_vport_get_other_func_cap(dev, fid, out, MLX5_CAP_GENERAL) void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work); static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 662f1d55e30e..6bde18bcd42f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -4,6 +4,7 @@ #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include "mlx5_core.h" #include "mlx5_irq.h" #include "pci_irq.h" @@ -101,7 +102,7 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, goto out; } - ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap); + ret = mlx5_vport_get_other_func_general_cap(dev, function_id, query_cap); if (ret) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index b1dfad274a39..ee104cf04392 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -44,6 +44,7 @@ static const char * const action_type_to_str[] = { [DR_ACTION_TYP_INSERT_HDR] = "DR_ACTION_TYP_INSERT_HDR", [DR_ACTION_TYP_REMOVE_HDR] = "DR_ACTION_TYP_REMOVE_HDR", [DR_ACTION_TYP_ASO_FLOW_METER] = "DR_ACTION_TYP_ASO_FLOW_METER", + [DR_ACTION_TYP_RANGE] = "DR_ACTION_TYP_RANGE", [DR_ACTION_TYP_MAX] = "DR_ACTION_UNKNOWN", }; @@ -61,6 +62,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, @@ -79,6 +81,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, @@ -94,6 +97,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, @@ -103,6 +107,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, @@ -116,6 +121,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, @@ -129,6 +135,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, @@ -141,6 +148,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, @@ -159,6 +167,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ASO, }, [DR_ACTION_STATE_TERM] = { @@ -169,6 +178,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -183,6 +193,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_ASO_FLOW_METER] = DR_ACTION_STATE_ASO, @@ -190,6 +201,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_ASO_FLOW_METER] = DR_ACTION_STATE_ASO, @@ -197,6 +209,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -207,6 +220,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] }, [DR_ACTION_STATE_POP_VLAN] = { [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, @@ -220,6 +234,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, @@ -231,6 +246,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -250,6 +266,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ASO, [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_TERM] = { [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, @@ -259,6 +276,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, @@ -276,6 +294,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, @@ -291,6 +310,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, @@ -299,6 +319,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, @@ -311,6 +332,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_POP_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, @@ -324,6 +346,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, @@ -337,6 +360,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, @@ -354,6 +378,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_ASO] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ASO, }, @@ -365,6 +390,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, @@ -380,6 +406,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, @@ -388,6 +415,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, @@ -396,6 +424,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -407,6 +436,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] }, [DR_ACTION_STATE_POP_VLAN] = { [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_POP_VLAN, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_POP_VLAN, @@ -421,6 +451,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_PUSH_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_PUSH_VLAN, @@ -433,6 +464,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, @@ -452,6 +484,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_PUSH_VLAN, [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_RANGE] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ASO, }, @@ -634,6 +667,83 @@ static void dr_action_print_sequence(struct mlx5dr_domain *dmn, actions[i]->action_type); } +static int dr_action_get_dest_fw_tbl_addr(struct mlx5dr_matcher *matcher, + struct mlx5dr_action_dest_tbl *dest_tbl, + bool is_rx_rule, + u64 *final_icm_addr) +{ + struct mlx5dr_cmd_query_flow_table_details output; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + int ret; + + if (!dest_tbl->fw_tbl.rx_icm_addr) { + ret = mlx5dr_cmd_query_flow_table(dmn->mdev, + dest_tbl->fw_tbl.type, + dest_tbl->fw_tbl.id, + &output); + if (ret) { + mlx5dr_err(dmn, + "Failed mlx5_cmd_query_flow_table ret: %d\n", + ret); + return ret; + } + + dest_tbl->fw_tbl.tx_icm_addr = output.sw_owner_icm_root_1; + dest_tbl->fw_tbl.rx_icm_addr = output.sw_owner_icm_root_0; + } + + *final_icm_addr = is_rx_rule ? dest_tbl->fw_tbl.rx_icm_addr : + dest_tbl->fw_tbl.tx_icm_addr; + return 0; +} + +static int dr_action_get_dest_sw_tbl_addr(struct mlx5dr_matcher *matcher, + struct mlx5dr_action_dest_tbl *dest_tbl, + bool is_rx_rule, + u64 *final_icm_addr) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_icm_chunk *chunk; + + if (dest_tbl->tbl->dmn != dmn) { + mlx5dr_err(dmn, + "Destination table belongs to a different domain\n"); + return -EINVAL; + } + + if (dest_tbl->tbl->level <= matcher->tbl->level) { + mlx5_core_dbg_once(dmn->mdev, + "Connecting table to a lower/same level destination table\n"); + mlx5dr_dbg(dmn, + "Connecting table at level %d to a destination table at level %d\n", + matcher->tbl->level, + dest_tbl->tbl->level); + } + + chunk = is_rx_rule ? dest_tbl->tbl->rx.s_anchor->chunk : + dest_tbl->tbl->tx.s_anchor->chunk; + + *final_icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(chunk); + return 0; +} + +static int dr_action_get_dest_tbl_addr(struct mlx5dr_matcher *matcher, + struct mlx5dr_action_dest_tbl *dest_tbl, + bool is_rx_rule, + u64 *final_icm_addr) +{ + if (dest_tbl->is_fw_tbl) + return dr_action_get_dest_fw_tbl_addr(matcher, + dest_tbl, + is_rx_rule, + final_icm_addr); + + return dr_action_get_dest_sw_tbl_addr(matcher, + dest_tbl, + is_rx_rule, + final_icm_addr); +} + #define WITH_VLAN_NUM_HW_ACTIONS 6 int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, @@ -661,8 +771,6 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->type); for (i = 0; i < num_actions; i++) { - struct mlx5dr_action_dest_tbl *dest_tbl; - struct mlx5dr_icm_chunk *chunk; struct mlx5dr_action *action; int max_actions_type = 1; u32 action_type; @@ -676,50 +784,27 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, break; case DR_ACTION_TYP_FT: dest_action = action; - dest_tbl = action->dest_tbl; - if (!dest_tbl->is_fw_tbl) { - if (dest_tbl->tbl->dmn != dmn) { - mlx5dr_err(dmn, - "Destination table belongs to a different domain\n"); - return -EINVAL; - } - if (dest_tbl->tbl->level <= matcher->tbl->level) { - mlx5_core_dbg_once(dmn->mdev, - "Connecting table to a lower/same level destination table\n"); - mlx5dr_dbg(dmn, - "Connecting table at level %d to a destination table at level %d\n", - matcher->tbl->level, - dest_tbl->tbl->level); - } - chunk = rx_rule ? dest_tbl->tbl->rx.s_anchor->chunk : - dest_tbl->tbl->tx.s_anchor->chunk; - attr.final_icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(chunk); - } else { - struct mlx5dr_cmd_query_flow_table_details output; - int ret; - - /* get the relevant addresses */ - if (!action->dest_tbl->fw_tbl.rx_icm_addr) { - ret = mlx5dr_cmd_query_flow_table(dmn->mdev, - dest_tbl->fw_tbl.type, - dest_tbl->fw_tbl.id, - &output); - if (!ret) { - dest_tbl->fw_tbl.tx_icm_addr = - output.sw_owner_icm_root_1; - dest_tbl->fw_tbl.rx_icm_addr = - output.sw_owner_icm_root_0; - } else { - mlx5dr_err(dmn, - "Failed mlx5_cmd_query_flow_table ret: %d\n", - ret); - return ret; - } - } - attr.final_icm_addr = rx_rule ? - dest_tbl->fw_tbl.rx_icm_addr : - dest_tbl->fw_tbl.tx_icm_addr; - } + ret = dr_action_get_dest_tbl_addr(matcher, action->dest_tbl, + rx_rule, &attr.final_icm_addr); + if (ret) + return ret; + break; + case DR_ACTION_TYP_RANGE: + ret = dr_action_get_dest_tbl_addr(matcher, + action->range->hit_tbl_action->dest_tbl, + rx_rule, &attr.final_icm_addr); + if (ret) + return ret; + + ret = dr_action_get_dest_tbl_addr(matcher, + action->range->miss_tbl_action->dest_tbl, + rx_rule, &attr.range.miss_icm_addr); + if (ret) + return ret; + + attr.range.definer_id = action->range->definer_id; + attr.range.min = action->range->min; + attr.range.max = action->range->max; break; case DR_ACTION_TYP_QP: mlx5dr_info(dmn, "Domain doesn't support QP\n"); @@ -866,6 +951,7 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = { [DR_ACTION_TYP_REMOVE_HDR] = sizeof(struct mlx5dr_action_reformat), [DR_ACTION_TYP_SAMPLER] = sizeof(struct mlx5dr_action_sampler), [DR_ACTION_TYP_ASO_FLOW_METER] = sizeof(struct mlx5dr_action_aso_flow_meter), + [DR_ACTION_TYP_RANGE] = sizeof(struct mlx5dr_action_range), }; static struct mlx5dr_action * @@ -933,6 +1019,123 @@ dec_ref: return NULL; } +static void dr_action_range_definer_fill(u16 *format_id, + u8 *dw_selectors, + u8 *byte_selectors, + u8 *match_mask) +{ + int i; + + *format_id = MLX5_IFC_DEFINER_FORMAT_ID_SELECT; + + dw_selectors[0] = MLX5_IFC_DEFINER_FORMAT_OFFSET_OUTER_ETH_PKT_LEN / 4; + + for (i = 1; i < MLX5_IFC_DEFINER_DW_SELECTORS_NUM; i++) + dw_selectors[i] = MLX5_IFC_DEFINER_FORMAT_OFFSET_UNUSED; + + for (i = 0; i < MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM; i++) + byte_selectors[i] = MLX5_IFC_DEFINER_FORMAT_OFFSET_UNUSED; + + MLX5_SET(match_definer_match_mask, match_mask, + match_dw_0, 0xffffUL << 16); +} + +static int dr_action_create_range_definer(struct mlx5dr_action *action) +{ + u8 match_mask[MLX5_FLD_SZ_BYTES(match_definer, match_mask)] = {}; + u8 byte_selectors[MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM] = {}; + u8 dw_selectors[MLX5_IFC_DEFINER_DW_SELECTORS_NUM] = {}; + struct mlx5dr_domain *dmn = action->range->dmn; + u32 definer_id; + u16 format_id; + int ret; + + dr_action_range_definer_fill(&format_id, + dw_selectors, + byte_selectors, + match_mask); + + ret = mlx5dr_definer_get(dmn, format_id, + dw_selectors, byte_selectors, + match_mask, &definer_id); + if (ret) + return ret; + + action->range->definer_id = definer_id; + return 0; +} + +static void dr_action_destroy_range_definer(struct mlx5dr_action *action) +{ + mlx5dr_definer_put(action->range->dmn, action->range->definer_id); +} + +struct mlx5dr_action * +mlx5dr_action_create_dest_match_range(struct mlx5dr_domain *dmn, + u32 field, + struct mlx5_flow_table *hit_ft, + struct mlx5_flow_table *miss_ft, + u32 min, + u32 max) +{ + struct mlx5dr_action *action; + int ret; + + if (!mlx5dr_supp_match_ranges(dmn->mdev)) { + mlx5dr_dbg(dmn, "SELECT definer support is needed for match range\n"); + return NULL; + } + + if (field != MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN || + min > 0xffff || max > 0xffff) { + mlx5dr_err(dmn, "Invalid match range parameters\n"); + return NULL; + } + + action = dr_action_create_generic(DR_ACTION_TYP_RANGE); + if (!action) + return NULL; + + action->range->hit_tbl_action = + mlx5dr_is_fw_table(hit_ft) ? + mlx5dr_action_create_dest_flow_fw_table(dmn, hit_ft) : + mlx5dr_action_create_dest_table(hit_ft->fs_dr_table.dr_table); + + if (!action->range->hit_tbl_action) + goto free_action; + + action->range->miss_tbl_action = + mlx5dr_is_fw_table(miss_ft) ? + mlx5dr_action_create_dest_flow_fw_table(dmn, miss_ft) : + mlx5dr_action_create_dest_table(miss_ft->fs_dr_table.dr_table); + + if (!action->range->miss_tbl_action) + goto free_hit_tbl_action; + + action->range->min = min; + action->range->max = max; + action->range->dmn = dmn; + + ret = dr_action_create_range_definer(action); + if (ret) + goto free_miss_tbl_action; + + /* No need to increase refcount on domain for this action, + * the hit/miss table actions will do it internally. + */ + + return action; + +free_miss_tbl_action: + mlx5dr_action_destroy(action->range->miss_tbl_action); +free_hit_tbl_action: + mlx5dr_action_destroy(action->range->hit_tbl_action); +free_action: + kfree(action); + + return NULL; +} + struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, @@ -1980,6 +2183,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) case DR_ACTION_TYP_ASO_FLOW_METER: refcount_dec(&action->aso->dmn->refcount); break; + case DR_ACTION_TYP_RANGE: + dr_action_destroy_range_definer(action); + mlx5dr_action_destroy(action->range->miss_tbl_action); + mlx5dr_action_destroy(action->range->hit_tbl_action); + break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c index 7df11a019df9..fe228d948b47 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c @@ -15,8 +15,6 @@ int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, buddy->max_order = max_order; INIT_LIST_HEAD(&buddy->list_node); - INIT_LIST_HEAD(&buddy->used_list); - INIT_LIST_HEAD(&buddy->hot_list); buddy->bitmap = kcalloc(buddy->max_order + 1, sizeof(*buddy->bitmap), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 16d65fe4f654..07b6a6dcb92f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -271,6 +271,13 @@ int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {}; + /* Skip SYNC in case the device is internal error state. + * Besides a device error, this also happens when we're + * in fast teardown + */ + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + return 0; + MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING); return mlx5_cmd_exec_in(mdev, sync_steering, in); @@ -557,6 +564,83 @@ void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, mlx5_cmd_exec_in(mdev, dealloc_packet_reformat_context, in); } +static void dr_cmd_set_definer_format(void *ptr, u16 format_id, + u8 *dw_selectors, + u8 *byte_selectors) +{ + if (format_id != MLX5_IFC_DEFINER_FORMAT_ID_SELECT) + return; + + MLX5_SET(match_definer, ptr, format_select_dw0, dw_selectors[0]); + MLX5_SET(match_definer, ptr, format_select_dw1, dw_selectors[1]); + MLX5_SET(match_definer, ptr, format_select_dw2, dw_selectors[2]); + MLX5_SET(match_definer, ptr, format_select_dw3, dw_selectors[3]); + MLX5_SET(match_definer, ptr, format_select_dw4, dw_selectors[4]); + MLX5_SET(match_definer, ptr, format_select_dw5, dw_selectors[5]); + MLX5_SET(match_definer, ptr, format_select_dw6, dw_selectors[6]); + MLX5_SET(match_definer, ptr, format_select_dw7, dw_selectors[7]); + MLX5_SET(match_definer, ptr, format_select_dw8, dw_selectors[8]); + + MLX5_SET(match_definer, ptr, format_select_byte0, byte_selectors[0]); + MLX5_SET(match_definer, ptr, format_select_byte1, byte_selectors[1]); + MLX5_SET(match_definer, ptr, format_select_byte2, byte_selectors[2]); + MLX5_SET(match_definer, ptr, format_select_byte3, byte_selectors[3]); + MLX5_SET(match_definer, ptr, format_select_byte4, byte_selectors[4]); + MLX5_SET(match_definer, ptr, format_select_byte5, byte_selectors[5]); + MLX5_SET(match_definer, ptr, format_select_byte6, byte_selectors[6]); + MLX5_SET(match_definer, ptr, format_select_byte7, byte_selectors[7]); +} + +int mlx5dr_cmd_create_definer(struct mlx5_core_dev *mdev, + u16 format_id, + u8 *dw_selectors, + u8 *byte_selectors, + u8 *match_mask, + u32 *definer_id) +{ + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(create_match_definer_in)] = {}; + void *ptr; + int err; + + ptr = MLX5_ADDR_OF(create_match_definer_in, in, + general_obj_in_cmd_hdr); + MLX5_SET(general_obj_in_cmd_hdr, ptr, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, ptr, obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + + ptr = MLX5_ADDR_OF(create_match_definer_in, in, obj_context); + MLX5_SET(match_definer, ptr, format_id, format_id); + + dr_cmd_set_definer_format(ptr, format_id, + dw_selectors, byte_selectors); + + ptr = MLX5_ADDR_OF(match_definer, ptr, match_mask); + memcpy(ptr, match_mask, MLX5_FLD_SZ_BYTES(match_definer, match_mask)); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *definer_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + return 0; +} + +void +mlx5dr_cmd_destroy_definer(struct mlx5_core_dev *mdev, u32 definer_id) +{ + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_MATCH_DEFINER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, definer_id); + + mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num, u16 index, struct mlx5dr_cmd_gid_attr *attr) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c index 7adcf0eec13b..db81d881d38e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c @@ -49,7 +49,8 @@ enum dr_dump_rec_type { DR_DUMP_REC_TYPE_ACTION_POP_VLAN = 3413, DR_DUMP_REC_TYPE_ACTION_SAMPLER = 3415, DR_DUMP_REC_TYPE_ACTION_INSERT_HDR = 3420, - DR_DUMP_REC_TYPE_ACTION_REMOVE_HDR = 3421 + DR_DUMP_REC_TYPE_ACTION_REMOVE_HDR = 3421, + DR_DUMP_REC_TYPE_ACTION_MATCH_RANGE = 3425, }; void mlx5dr_dbg_tbl_add(struct mlx5dr_table *tbl) @@ -107,6 +108,8 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, { struct mlx5dr_action *action = action_mem->action; const u64 action_id = DR_DBG_PTR_TO_ID(action); + u64 hit_tbl_ptr, miss_tbl_ptr; + u32 hit_tbl_id, miss_tbl_id; switch (action->action_type) { case DR_ACTION_TYP_DROP: @@ -198,6 +201,30 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, action->sampler->rx_icm_addr, action->sampler->tx_icm_addr); break; + case DR_ACTION_TYP_RANGE: + if (action->range->hit_tbl_action->dest_tbl->is_fw_tbl) { + hit_tbl_id = action->range->hit_tbl_action->dest_tbl->fw_tbl.id; + hit_tbl_ptr = 0; + } else { + hit_tbl_id = action->range->hit_tbl_action->dest_tbl->tbl->table_id; + hit_tbl_ptr = + DR_DBG_PTR_TO_ID(action->range->hit_tbl_action->dest_tbl->tbl); + } + + if (action->range->miss_tbl_action->dest_tbl->is_fw_tbl) { + miss_tbl_id = action->range->miss_tbl_action->dest_tbl->fw_tbl.id; + miss_tbl_ptr = 0; + } else { + miss_tbl_id = action->range->miss_tbl_action->dest_tbl->tbl->table_id; + miss_tbl_ptr = + DR_DBG_PTR_TO_ID(action->range->miss_tbl_action->dest_tbl->tbl); + } + + seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%llx,0x%x,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_MATCH_RANGE, action_id, rule_id, + hit_tbl_id, hit_tbl_ptr, miss_tbl_id, miss_tbl_ptr, + action->range->definer_id); + break; default: return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_definer.c new file mode 100644 index 000000000000..d5ea97751945 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_definer.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "dr_types.h" +#include "dr_ste.h" + +struct dr_definer_object { + u32 id; + u16 format_id; + u8 dw_selectors[MLX5_IFC_DEFINER_DW_SELECTORS_NUM]; + u8 byte_selectors[MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM]; + u8 match_mask[DR_STE_SIZE_MATCH_TAG]; + refcount_t refcount; +}; + +static bool dr_definer_compare(struct dr_definer_object *definer, + u16 format_id, u8 *dw_selectors, + u8 *byte_selectors, u8 *match_mask) +{ + int i; + + if (definer->format_id != format_id) + return false; + + for (i = 0; i < MLX5_IFC_DEFINER_DW_SELECTORS_NUM; i++) + if (definer->dw_selectors[i] != dw_selectors[i]) + return false; + + for (i = 0; i < MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM; i++) + if (definer->byte_selectors[i] != byte_selectors[i]) + return false; + + if (memcmp(definer->match_mask, match_mask, DR_STE_SIZE_MATCH_TAG)) + return false; + + return true; +} + +static struct dr_definer_object * +dr_definer_find_obj(struct mlx5dr_domain *dmn, u16 format_id, + u8 *dw_selectors, u8 *byte_selectors, u8 *match_mask) +{ + struct dr_definer_object *definer_obj; + unsigned long id; + + xa_for_each(&dmn->definers_xa, id, definer_obj) { + if (dr_definer_compare(definer_obj, format_id, + dw_selectors, byte_selectors, + match_mask)) + return definer_obj; + } + + return NULL; +} + +static struct dr_definer_object * +dr_definer_create_obj(struct mlx5dr_domain *dmn, u16 format_id, + u8 *dw_selectors, u8 *byte_selectors, u8 *match_mask) +{ + struct dr_definer_object *definer_obj; + int ret = 0; + + definer_obj = kzalloc(sizeof(*definer_obj), GFP_KERNEL); + if (!definer_obj) + return NULL; + + ret = mlx5dr_cmd_create_definer(dmn->mdev, + format_id, + dw_selectors, + byte_selectors, + match_mask, + &definer_obj->id); + if (ret) + goto err_free_definer_obj; + + /* Definer ID can have 32 bits, but STE format + * supports only definers with 8 bit IDs. + */ + if (definer_obj->id > 0xff) { + mlx5dr_err(dmn, "Unsupported definer ID (%d)\n", definer_obj->id); + goto err_destroy_definer; + } + + definer_obj->format_id = format_id; + memcpy(definer_obj->dw_selectors, dw_selectors, sizeof(definer_obj->dw_selectors)); + memcpy(definer_obj->byte_selectors, byte_selectors, sizeof(definer_obj->byte_selectors)); + memcpy(definer_obj->match_mask, match_mask, sizeof(definer_obj->match_mask)); + + refcount_set(&definer_obj->refcount, 1); + + ret = xa_insert(&dmn->definers_xa, definer_obj->id, definer_obj, GFP_KERNEL); + if (ret) { + mlx5dr_dbg(dmn, "Couldn't insert new definer into xarray (%d)\n", ret); + goto err_destroy_definer; + } + + return definer_obj; + +err_destroy_definer: + mlx5dr_cmd_destroy_definer(dmn->mdev, definer_obj->id); +err_free_definer_obj: + kfree(definer_obj); + + return NULL; +} + +static void dr_definer_destroy_obj(struct mlx5dr_domain *dmn, + struct dr_definer_object *definer_obj) +{ + mlx5dr_cmd_destroy_definer(dmn->mdev, definer_obj->id); + xa_erase(&dmn->definers_xa, definer_obj->id); + kfree(definer_obj); +} + +int mlx5dr_definer_get(struct mlx5dr_domain *dmn, u16 format_id, + u8 *dw_selectors, u8 *byte_selectors, + u8 *match_mask, u32 *definer_id) +{ + struct dr_definer_object *definer_obj; + int ret = 0; + + definer_obj = dr_definer_find_obj(dmn, format_id, dw_selectors, + byte_selectors, match_mask); + if (!definer_obj) { + definer_obj = dr_definer_create_obj(dmn, format_id, + dw_selectors, byte_selectors, + match_mask); + if (!definer_obj) + return -ENOMEM; + } else { + refcount_inc(&definer_obj->refcount); + } + + *definer_id = definer_obj->id; + + return ret; +} + +void mlx5dr_definer_put(struct mlx5dr_domain *dmn, u32 definer_id) +{ + struct dr_definer_object *definer_obj; + + definer_obj = xa_load(&dmn->definers_xa, definer_id); + if (!definer_obj) { + mlx5dr_err(dmn, "Definer ID %d not found\n", definer_id); + return; + } + + if (refcount_dec_and_test(&definer_obj->refcount)) + dr_definer_destroy_obj(dmn, definer_obj); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index fc6ae49b5ecc..5b8bb2ca31e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -56,6 +56,70 @@ int mlx5dr_domain_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, return 0; } +static int dr_domain_init_mem_resources(struct mlx5dr_domain *dmn) +{ + int ret; + + dmn->chunks_kmem_cache = kmem_cache_create("mlx5_dr_chunks", + sizeof(struct mlx5dr_icm_chunk), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!dmn->chunks_kmem_cache) { + mlx5dr_err(dmn, "Couldn't create chunks kmem_cache\n"); + return -ENOMEM; + } + + dmn->htbls_kmem_cache = kmem_cache_create("mlx5_dr_htbls", + sizeof(struct mlx5dr_ste_htbl), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!dmn->htbls_kmem_cache) { + mlx5dr_err(dmn, "Couldn't create hash tables kmem_cache\n"); + ret = -ENOMEM; + goto free_chunks_kmem_cache; + } + + dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE); + if (!dmn->ste_icm_pool) { + mlx5dr_err(dmn, "Couldn't get icm memory\n"); + ret = -ENOMEM; + goto free_htbls_kmem_cache; + } + + dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION); + if (!dmn->action_icm_pool) { + mlx5dr_err(dmn, "Couldn't get action icm memory\n"); + ret = -ENOMEM; + goto free_ste_icm_pool; + } + + ret = mlx5dr_send_info_pool_create(dmn); + if (ret) { + mlx5dr_err(dmn, "Couldn't create send info pool\n"); + goto free_action_icm_pool; + } + + return 0; + +free_action_icm_pool: + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); +free_ste_icm_pool: + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); +free_htbls_kmem_cache: + kmem_cache_destroy(dmn->htbls_kmem_cache); +free_chunks_kmem_cache: + kmem_cache_destroy(dmn->chunks_kmem_cache); + + return ret; +} + +static void dr_domain_uninit_mem_resources(struct mlx5dr_domain *dmn) +{ + mlx5dr_send_info_pool_destroy(dmn); + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); + kmem_cache_destroy(dmn->htbls_kmem_cache); + kmem_cache_destroy(dmn->chunks_kmem_cache); +} + static int dr_domain_init_resources(struct mlx5dr_domain *dmn) { int ret; @@ -79,32 +143,22 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn) goto clean_pd; } - dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE); - if (!dmn->ste_icm_pool) { - mlx5dr_err(dmn, "Couldn't get icm memory\n"); - ret = -ENOMEM; + ret = dr_domain_init_mem_resources(dmn); + if (ret) { + mlx5dr_err(dmn, "Couldn't create domain memory resources\n"); goto clean_uar; } - dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION); - if (!dmn->action_icm_pool) { - mlx5dr_err(dmn, "Couldn't get action icm memory\n"); - ret = -ENOMEM; - goto free_ste_icm_pool; - } - ret = mlx5dr_send_ring_alloc(dmn); if (ret) { mlx5dr_err(dmn, "Couldn't create send-ring\n"); - goto free_action_icm_pool; + goto clean_mem_resources; } return 0; -free_action_icm_pool: - mlx5dr_icm_pool_destroy(dmn->action_icm_pool); -free_ste_icm_pool: - mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); +clean_mem_resources: + dr_domain_uninit_mem_resources(dmn); clean_uar: mlx5_put_uars_page(dmn->mdev, dmn->uar); clean_pd: @@ -116,8 +170,7 @@ clean_pd: static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn) { mlx5dr_send_ring_free(dmn, dmn->send_ring); - mlx5dr_icm_pool_destroy(dmn->action_icm_pool); - mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); + dr_domain_uninit_mem_resources(dmn); mlx5_put_uars_page(dmn->mdev, dmn->uar); mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); } @@ -372,10 +425,11 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) refcount_set(&dmn->refcount, 1); mutex_init(&dmn->info.rx.mutex); mutex_init(&dmn->info.tx.mutex); + xa_init(&dmn->definers_xa); if (dr_domain_caps_init(mdev, dmn)) { mlx5dr_err(dmn, "Failed init domain, no caps\n"); - goto free_domain; + goto def_xa_destroy; } dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K; @@ -400,7 +454,8 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) uninit_caps: dr_domain_caps_uninit(dmn); -free_domain: +def_xa_destroy: + xa_destroy(&dmn->definers_xa); kfree(dmn); return NULL; } @@ -440,6 +495,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) dr_domain_uninit_csum_recalc_fts(dmn); dr_domain_uninit_resources(dmn); dr_domain_caps_uninit(dmn); + xa_destroy(&dmn->definers_xa); mutex_destroy(&dmn->info.tx.mutex); mutex_destroy(&dmn->info.rx.mutex); kfree(dmn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 4ca67fa24cc6..3eb6719bc8eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -4,14 +4,30 @@ #include "dr_types.h" #define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 +#define DR_ICM_POOL_HOT_MEMORY_FRACTION 4 + +struct mlx5dr_icm_hot_chunk { + struct mlx5dr_icm_buddy_mem *buddy_mem; + unsigned int seg; + enum mlx5dr_icm_chunk_size size; +}; struct mlx5dr_icm_pool { enum mlx5dr_icm_type icm_type; enum mlx5dr_icm_chunk_size max_log_chunk_sz; struct mlx5dr_domain *dmn; + struct kmem_cache *chunks_kmem_cache; + /* memory management */ struct mutex mutex; /* protect the ICM pool and ICM buddy */ struct list_head buddy_mem_list; + + /* Hardware may be accessing this memory but at some future, + * undetermined time, it might cease to do so. + * sync_ste command sets them free. + */ + struct mlx5dr_icm_hot_chunk *hot_chunks_arr; + u32 hot_chunks_num; u64 hot_memory_size; }; @@ -177,46 +193,20 @@ static int dr_icm_buddy_get_ste_size(struct mlx5dr_icm_buddy_mem *buddy) static void dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk, int offset) { + int num_of_entries = mlx5dr_icm_pool_get_chunk_num_of_entries(chunk); struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; + int ste_size = dr_icm_buddy_get_ste_size(buddy); int index = offset / DR_STE_SIZE; chunk->ste_arr = &buddy->ste_arr[index]; chunk->miss_list = &buddy->miss_list[index]; - chunk->hw_ste_arr = buddy->hw_ste_arr + - index * dr_icm_buddy_get_ste_size(buddy); -} + chunk->hw_ste_arr = buddy->hw_ste_arr + index * ste_size; -static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) -{ - int num_of_entries = mlx5dr_icm_pool_get_chunk_num_of_entries(chunk); - struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; - - memset(chunk->hw_ste_arr, 0, - num_of_entries * dr_icm_buddy_get_ste_size(buddy)); + memset(chunk->hw_ste_arr, 0, num_of_entries * ste_size); memset(chunk->ste_arr, 0, num_of_entries * sizeof(chunk->ste_arr[0])); } -static enum mlx5dr_icm_type -get_chunk_icm_type(struct mlx5dr_icm_chunk *chunk) -{ - return chunk->buddy_mem->pool->icm_type; -} - -static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk, - struct mlx5dr_icm_buddy_mem *buddy) -{ - enum mlx5dr_icm_type icm_type = get_chunk_icm_type(chunk); - - buddy->used_memory -= mlx5dr_icm_pool_get_chunk_byte_size(chunk); - list_del(&chunk->chunk_list); - - if (icm_type == DR_ICM_TYPE_STE) - dr_icm_chunk_ste_cleanup(chunk); - - kvfree(chunk); -} - static int dr_icm_buddy_init_ste_cache(struct mlx5dr_icm_buddy_mem *buddy) { int num_of_entries = @@ -296,14 +286,6 @@ free_mr: static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy) { - struct mlx5dr_icm_chunk *chunk, *next; - - list_for_each_entry_safe(chunk, next, &buddy->hot_list, chunk_list) - dr_icm_chunk_destroy(chunk, buddy); - - list_for_each_entry_safe(chunk, next, &buddy->used_list, chunk_list) - dr_icm_chunk_destroy(chunk, buddy); - dr_icm_pool_mr_destroy(buddy->icm_mr); mlx5dr_buddy_cleanup(buddy); @@ -314,53 +296,62 @@ static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy) kvfree(buddy); } -static struct mlx5dr_icm_chunk * -dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, - enum mlx5dr_icm_chunk_size chunk_size, - struct mlx5dr_icm_buddy_mem *buddy_mem_pool, - unsigned int seg) +static void +dr_icm_chunk_init(struct mlx5dr_icm_chunk *chunk, + struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + struct mlx5dr_icm_buddy_mem *buddy_mem_pool, + unsigned int seg) { - struct mlx5dr_icm_chunk *chunk; int offset; - chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); - if (!chunk) - return NULL; - - offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; - chunk->seg = seg; chunk->size = chunk_size; chunk->buddy_mem = buddy_mem_pool; - if (pool->icm_type == DR_ICM_TYPE_STE) + if (pool->icm_type == DR_ICM_TYPE_STE) { + offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; dr_icm_chunk_ste_init(chunk, offset); + } buddy_mem_pool->used_memory += mlx5dr_icm_pool_get_chunk_byte_size(chunk); - INIT_LIST_HEAD(&chunk->chunk_list); - - /* chunk now is part of the used_list */ - list_add_tail(&chunk->chunk_list, &buddy_mem_pool->used_list); - - return chunk; } static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool) { int allow_hot_size; - /* sync when hot memory reaches half of the pool size */ + /* sync when hot memory reaches a certain fraction of the pool size */ allow_hot_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, - pool->icm_type) / 2; + pool->icm_type) / + DR_ICM_POOL_HOT_MEMORY_FRACTION; return pool->hot_memory_size > allow_hot_size; } +static void dr_icm_pool_clear_hot_chunks_arr(struct mlx5dr_icm_pool *pool) +{ + struct mlx5dr_icm_hot_chunk *hot_chunk; + u32 i, num_entries; + + for (i = 0; i < pool->hot_chunks_num; i++) { + hot_chunk = &pool->hot_chunks_arr[i]; + num_entries = mlx5dr_icm_pool_chunk_size_to_entries(hot_chunk->size); + mlx5dr_buddy_free_mem(hot_chunk->buddy_mem, + hot_chunk->seg, ilog2(num_entries)); + hot_chunk->buddy_mem->used_memory -= + mlx5dr_icm_pool_chunk_size_to_byte(hot_chunk->size, + pool->icm_type); + } + + pool->hot_chunks_num = 0; + pool->hot_memory_size = 0; +} + static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool) { struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; - u32 num_entries; int err; err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); @@ -369,16 +360,9 @@ static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool) return err; } - list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) { - struct mlx5dr_icm_chunk *chunk, *tmp_chunk; - - list_for_each_entry_safe(chunk, tmp_chunk, &buddy->hot_list, chunk_list) { - num_entries = mlx5dr_icm_pool_get_chunk_num_of_entries(chunk); - mlx5dr_buddy_free_mem(buddy, chunk->seg, ilog2(num_entries)); - pool->hot_memory_size -= mlx5dr_icm_pool_get_chunk_byte_size(chunk); - dr_icm_chunk_destroy(chunk, buddy); - } + dr_icm_pool_clear_hot_chunks_arr(pool); + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) { if (!buddy->used_memory && pool->icm_type == DR_ICM_TYPE_STE) dr_icm_buddy_destroy(buddy); } @@ -452,10 +436,12 @@ mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, if (ret) goto out; - chunk = dr_icm_chunk_create(pool, chunk_size, buddy, seg); + chunk = kmem_cache_alloc(pool->chunks_kmem_cache, GFP_KERNEL); if (!chunk) goto out_err; + dr_icm_chunk_init(chunk, pool, chunk_size, buddy, seg); + goto out; out_err: @@ -469,12 +455,23 @@ void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) { struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; struct mlx5dr_icm_pool *pool = buddy->pool; + struct mlx5dr_icm_hot_chunk *hot_chunk; + struct kmem_cache *chunks_cache; + + chunks_cache = pool->chunks_kmem_cache; - /* move the memory to the waiting list AKA "hot" */ + /* move the chunk to the waiting chunks array, AKA "hot" memory */ mutex_lock(&pool->mutex); - list_move_tail(&chunk->chunk_list, &buddy->hot_list); + pool->hot_memory_size += mlx5dr_icm_pool_get_chunk_byte_size(chunk); + hot_chunk = &pool->hot_chunks_arr[pool->hot_chunks_num++]; + hot_chunk->buddy_mem = chunk->buddy_mem; + hot_chunk->seg = chunk->seg; + hot_chunk->size = chunk->size; + + kmem_cache_free(chunks_cache, chunk); + /* Check if we have chunks that are waiting for sync-ste */ if (dr_icm_pool_is_sync_required(pool)) dr_icm_pool_sync_all_buddy_pools(pool); @@ -482,9 +479,20 @@ void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) mutex_unlock(&pool->mutex); } +struct mlx5dr_ste_htbl *mlx5dr_icm_pool_alloc_htbl(struct mlx5dr_icm_pool *pool) +{ + return kmem_cache_alloc(pool->dmn->htbls_kmem_cache, GFP_KERNEL); +} + +void mlx5dr_icm_pool_free_htbl(struct mlx5dr_icm_pool *pool, struct mlx5dr_ste_htbl *htbl) +{ + kmem_cache_free(pool->dmn->htbls_kmem_cache, htbl); +} + struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, enum mlx5dr_icm_type icm_type) { + u32 num_of_chunks, entry_size, max_hot_size; enum mlx5dr_icm_chunk_size max_log_chunk_sz; struct mlx5dr_icm_pool *pool; @@ -500,21 +508,43 @@ struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, pool->dmn = dmn; pool->icm_type = icm_type; pool->max_log_chunk_sz = max_log_chunk_sz; + pool->chunks_kmem_cache = dmn->chunks_kmem_cache; INIT_LIST_HEAD(&pool->buddy_mem_list); mutex_init(&pool->mutex); + entry_size = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type); + + max_hot_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type) / + DR_ICM_POOL_HOT_MEMORY_FRACTION; + + num_of_chunks = DIV_ROUND_UP(max_hot_size, entry_size) + 1; + + pool->hot_chunks_arr = kvcalloc(num_of_chunks, + sizeof(struct mlx5dr_icm_hot_chunk), + GFP_KERNEL); + if (!pool->hot_chunks_arr) + goto free_pool; + return pool; + +free_pool: + kvfree(pool); + return NULL; } void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool) { struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; + dr_icm_pool_clear_hot_chunks_arr(pool); + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) dr_icm_buddy_destroy(buddy); + kvfree(pool->hot_chunks_arr); mutex_destroy(&pool->mutex); kvfree(pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 91ff19f67695..74cbe53ee9db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -3,13 +3,16 @@ #include "dr_types.h" -#define DR_RULE_MAX_STE_CHAIN (DR_RULE_MAX_STES + DR_ACTION_MAX_STES) +#define DR_RULE_MAX_STES_OPTIMIZED 5 +#define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES) -static int dr_rule_append_to_miss_list(struct mlx5dr_ste_ctx *ste_ctx, +static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn, + enum mlx5dr_domain_nic_type nic_type, struct mlx5dr_ste *new_last_ste, struct list_head *miss_list, struct list_head *send_list) { + struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; struct mlx5dr_ste_send_info *ste_info_last; struct mlx5dr_ste *last_ste; @@ -17,7 +20,7 @@ static int dr_rule_append_to_miss_list(struct mlx5dr_ste_ctx *ste_ctx, last_ste = list_last_entry(miss_list, struct mlx5dr_ste, miss_list_node); WARN_ON(!last_ste); - ste_info_last = kzalloc(sizeof(*ste_info_last), GFP_KERNEL); + ste_info_last = mlx5dr_send_info_alloc(dmn, nic_type); if (!ste_info_last) return -ENOMEM; @@ -32,16 +35,28 @@ static int dr_rule_append_to_miss_list(struct mlx5dr_ste_ctx *ste_ctx, return 0; } +static void dr_rule_set_last_ste_miss_addr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 *hw_ste) +{ + struct mlx5dr_ste_ctx *ste_ctx = matcher->tbl->dmn->ste_ctx; + u64 icm_addr; + + if (mlx5dr_ste_is_miss_addr_set(ste_ctx, hw_ste)) + return; + + icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(nic_matcher->e_anchor->chunk); + mlx5dr_ste_set_miss_addr(ste_ctx, hw_ste, icm_addr); +} + static struct mlx5dr_ste * dr_rule_create_collision_htbl(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, u8 *hw_ste) { struct mlx5dr_domain *dmn = matcher->tbl->dmn; - struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; struct mlx5dr_ste_htbl *new_htbl; struct mlx5dr_ste *ste; - u64 icm_addr; /* Create new table for miss entry */ new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, @@ -55,8 +70,7 @@ dr_rule_create_collision_htbl(struct mlx5dr_matcher *matcher, /* One and only entry, never grows */ ste = new_htbl->chunk->ste_arr; - icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(nic_matcher->e_anchor->chunk); - mlx5dr_ste_set_miss_addr(ste_ctx, hw_ste, icm_addr); + dr_rule_set_last_ste_miss_addr(matcher, nic_matcher, hw_ste); mlx5dr_htbl_get(new_htbl); return ste; @@ -120,7 +134,7 @@ dr_rule_handle_one_ste_in_update_list(struct mlx5dr_ste_send_info *ste_info, goto out; out: - kfree(ste_info); + mlx5dr_send_info_free(ste_info); return ret; } @@ -191,8 +205,8 @@ dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher, new_ste->htbl->chunk->miss_list = mlx5dr_ste_get_miss_list(col_ste); /* Update the previous from the list */ - ret = dr_rule_append_to_miss_list(dmn->ste_ctx, new_ste, - mlx5dr_ste_get_miss_list(col_ste), + ret = dr_rule_append_to_miss_list(dmn, nic_matcher->nic_tbl->nic_dmn->type, + new_ste, mlx5dr_ste_get_miss_list(col_ste), update_list); if (ret) { mlx5dr_dbg(dmn, "Failed update dup entry\n"); @@ -238,7 +252,6 @@ dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher, bool use_update_list = false; u8 hw_ste[DR_STE_SIZE] = {}; struct mlx5dr_ste *new_ste; - u64 icm_addr; int new_idx; u8 sb_idx; @@ -247,9 +260,8 @@ dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher, mlx5dr_ste_set_bit_mask(hw_ste, nic_matcher->ste_builder[sb_idx].bit_mask); /* Copy STE control and tag */ - icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(nic_matcher->e_anchor->chunk); memcpy(hw_ste, mlx5dr_ste_get_hw_ste(cur_ste), DR_STE_SIZE_REDUCED); - mlx5dr_ste_set_miss_addr(dmn->ste_ctx, hw_ste, icm_addr); + dr_rule_set_last_ste_miss_addr(matcher, nic_matcher, hw_ste); new_idx = mlx5dr_ste_calc_hash_index(hw_ste, new_htbl); new_ste = &new_htbl->chunk->ste_arr[new_idx]; @@ -278,7 +290,8 @@ dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher, new_htbl->ctrl.num_of_valid_entries++; if (use_update_list) { - ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + ste_info = mlx5dr_send_info_alloc(dmn, + nic_matcher->nic_tbl->nic_dmn->type); if (!ste_info) goto err_exit; @@ -357,6 +370,15 @@ static int dr_rule_rehash_copy_htbl(struct mlx5dr_matcher *matcher, update_list); if (err) goto clean_copy; + + /* In order to decrease the number of allocated ste_send_info + * structs, send the current table row now. + */ + err = dr_rule_send_update_list(update_list, matcher->tbl->dmn, false); + if (err) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed updating table to HW\n"); + goto clean_copy; + } } clean_copy: @@ -387,7 +409,8 @@ dr_rule_rehash_htbl(struct mlx5dr_rule *rule, nic_matcher = nic_rule->nic_matcher; nic_dmn = nic_matcher->nic_tbl->nic_dmn; - ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + ste_info = mlx5dr_send_info_alloc(dmn, + nic_matcher->nic_tbl->nic_dmn->type); if (!ste_info) return NULL; @@ -473,13 +496,13 @@ free_ste_list: list_for_each_entry_safe(del_ste_info, tmp_ste_info, &rehash_table_send_list, send_list) { list_del(&del_ste_info->send_list); - kfree(del_ste_info); + mlx5dr_send_info_free(del_ste_info); } free_new_htbl: mlx5dr_ste_htbl_free(new_htbl); free_ste_info: - kfree(ste_info); + mlx5dr_send_info_free(ste_info); mlx5dr_info(dmn, "Failed creating rehash table\n"); return NULL; } @@ -512,11 +535,11 @@ dr_rule_handle_collision(struct mlx5dr_matcher *matcher, struct list_head *send_list) { struct mlx5dr_domain *dmn = matcher->tbl->dmn; - struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx; struct mlx5dr_ste_send_info *ste_info; struct mlx5dr_ste *new_ste; - ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + ste_info = mlx5dr_send_info_alloc(dmn, + nic_matcher->nic_tbl->nic_dmn->type); if (!ste_info) return NULL; @@ -524,8 +547,8 @@ dr_rule_handle_collision(struct mlx5dr_matcher *matcher, if (!new_ste) goto free_send_info; - if (dr_rule_append_to_miss_list(ste_ctx, new_ste, - miss_list, send_list)) { + if (dr_rule_append_to_miss_list(dmn, nic_matcher->nic_tbl->nic_dmn->type, + new_ste, miss_list, send_list)) { mlx5dr_dbg(dmn, "Failed to update prev miss_list\n"); goto err_exit; } @@ -541,7 +564,7 @@ dr_rule_handle_collision(struct mlx5dr_matcher *matcher, err_exit: mlx5dr_ste_free(new_ste, matcher, nic_matcher); free_send_info: - kfree(ste_info); + mlx5dr_send_info_free(ste_info); return NULL; } @@ -721,8 +744,8 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, list_add_tail(&action_ste->miss_list_node, mlx5dr_ste_get_miss_list(action_ste)); - ste_info_arr[k] = kzalloc(sizeof(*ste_info_arr[k]), - GFP_KERNEL); + ste_info_arr[k] = mlx5dr_send_info_alloc(dmn, + nic_matcher->nic_tbl->nic_dmn->type); if (!ste_info_arr[k]) goto err_exit; @@ -759,7 +782,6 @@ static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher, { struct mlx5dr_domain *dmn = matcher->tbl->dmn; struct mlx5dr_ste_send_info *ste_info; - u64 icm_addr; /* Take ref on table, only on first time this ste is used */ mlx5dr_htbl_get(cur_htbl); @@ -767,12 +789,12 @@ static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher, /* new entry -> new branch */ list_add_tail(&ste->miss_list_node, miss_list); - icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(nic_matcher->e_anchor->chunk); - mlx5dr_ste_set_miss_addr(dmn->ste_ctx, hw_ste, icm_addr); + dr_rule_set_last_ste_miss_addr(matcher, nic_matcher, hw_ste); ste->ste_chain_location = ste_location; - ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + ste_info = mlx5dr_send_info_alloc(dmn, + nic_matcher->nic_tbl->nic_dmn->type); if (!ste_info) goto clean_ste_setting; @@ -793,7 +815,7 @@ static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher, return 0; clean_ste_info: - kfree(ste_info); + mlx5dr_send_info_free(ste_info); clean_ste_setting: list_del_init(&ste->miss_list_node); mlx5dr_htbl_put(cur_htbl); @@ -1089,6 +1111,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, size_t num_actions, struct mlx5dr_action *actions[]) { + u8 hw_ste_arr_optimized[DR_RULE_MAX_STE_CHAIN_OPTIMIZED * DR_STE_SIZE] = {}; struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info; struct mlx5dr_matcher *matcher = rule->matcher; struct mlx5dr_domain *dmn = matcher->tbl->dmn; @@ -1098,6 +1121,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, struct mlx5dr_ste_htbl *cur_htbl; struct mlx5dr_ste *ste = NULL; LIST_HEAD(send_ste_list); + bool hw_ste_arr_is_opt; u8 *hw_ste_arr = NULL; u32 new_hw_ste_arr_sz; int ret, i; @@ -1109,9 +1133,23 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, rule->flow_source)) return 0; - hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL); - if (!hw_ste_arr) - return -ENOMEM; + ret = mlx5dr_matcher_select_builders(matcher, + nic_matcher, + dr_rule_get_ipv(¶m->outer), + dr_rule_get_ipv(¶m->inner)); + if (ret) + return ret; + + hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED; + if (likely(hw_ste_arr_is_opt)) { + hw_ste_arr = hw_ste_arr_optimized; + } else { + hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) * + DR_STE_SIZE, GFP_KERNEL); + + if (!hw_ste_arr) + return -ENOMEM; + } mlx5dr_domain_nic_lock(nic_dmn); @@ -1119,13 +1157,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, if (ret) goto free_hw_ste; - ret = mlx5dr_matcher_select_builders(matcher, - nic_matcher, - dr_rule_get_ipv(¶m->outer), - dr_rule_get_ipv(¶m->inner)); - if (ret) - goto remove_from_nic_tbl; - /* Set the tag values inside the ste array */ ret = mlx5dr_ste_build_ste_arr(matcher, nic_matcher, param, hw_ste_arr); if (ret) @@ -1187,7 +1218,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - kfree(hw_ste_arr); + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); return 0; @@ -1196,7 +1228,7 @@ free_rule: /* Clean all ste_info's */ list_for_each_entry_safe(ste_info, tmp_ste_info, &send_ste_list, send_list) { list_del(&ste_info->send_list); - kfree(ste_info); + mlx5dr_send_info_free(ste_info); } remove_from_nic_tbl: @@ -1205,7 +1237,10 @@ remove_from_nic_tbl: free_hw_ste: mlx5dr_domain_nic_unlock(nic_dmn); - kfree(hw_ste_arr); + + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); + return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index ef19a66f5233..a4476cb4c3b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -7,6 +7,7 @@ #define QUEUE_SIZE 128 #define SIGNAL_PER_DIV_QUEUE 16 #define TH_NUMS_TO_DRAIN 2 +#define DR_SEND_INFO_POOL_SIZE 1000 enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 }; @@ -49,6 +50,136 @@ struct dr_qp_init_attr { u8 isolate_vl_tc:1; }; +struct mlx5dr_send_info_pool_obj { + struct mlx5dr_ste_send_info ste_send_info; + struct mlx5dr_send_info_pool *pool; + struct list_head list_node; +}; + +struct mlx5dr_send_info_pool { + struct list_head free_list; +}; + +static int dr_send_info_pool_fill(struct mlx5dr_send_info_pool *pool) +{ + struct mlx5dr_send_info_pool_obj *pool_obj, *tmp_pool_obj; + int i; + + for (i = 0; i < DR_SEND_INFO_POOL_SIZE; i++) { + pool_obj = kzalloc(sizeof(*pool_obj), GFP_KERNEL); + if (!pool_obj) + goto clean_pool; + + pool_obj->pool = pool; + list_add_tail(&pool_obj->list_node, &pool->free_list); + } + + return 0; + +clean_pool: + list_for_each_entry_safe(pool_obj, tmp_pool_obj, &pool->free_list, list_node) { + list_del(&pool_obj->list_node); + kfree(pool_obj); + } + + return -ENOMEM; +} + +static void dr_send_info_pool_destroy(struct mlx5dr_send_info_pool *pool) +{ + struct mlx5dr_send_info_pool_obj *pool_obj, *tmp_pool_obj; + + list_for_each_entry_safe(pool_obj, tmp_pool_obj, &pool->free_list, list_node) { + list_del(&pool_obj->list_node); + kfree(pool_obj); + } + + kfree(pool); +} + +void mlx5dr_send_info_pool_destroy(struct mlx5dr_domain *dmn) +{ + dr_send_info_pool_destroy(dmn->send_info_pool_tx); + dr_send_info_pool_destroy(dmn->send_info_pool_rx); +} + +static struct mlx5dr_send_info_pool *dr_send_info_pool_create(void) +{ + struct mlx5dr_send_info_pool *pool; + int ret; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + INIT_LIST_HEAD(&pool->free_list); + + ret = dr_send_info_pool_fill(pool); + if (ret) { + kfree(pool); + return NULL; + } + + return pool; +} + +int mlx5dr_send_info_pool_create(struct mlx5dr_domain *dmn) +{ + dmn->send_info_pool_rx = dr_send_info_pool_create(); + if (!dmn->send_info_pool_rx) + return -ENOMEM; + + dmn->send_info_pool_tx = dr_send_info_pool_create(); + if (!dmn->send_info_pool_tx) { + dr_send_info_pool_destroy(dmn->send_info_pool_rx); + return -ENOMEM; + } + + return 0; +} + +struct mlx5dr_ste_send_info +*mlx5dr_send_info_alloc(struct mlx5dr_domain *dmn, + enum mlx5dr_domain_nic_type nic_type) +{ + struct mlx5dr_send_info_pool_obj *pool_obj; + struct mlx5dr_send_info_pool *pool; + int ret; + + pool = nic_type == DR_DOMAIN_NIC_TYPE_RX ? dmn->send_info_pool_rx : + dmn->send_info_pool_tx; + + if (unlikely(list_empty(&pool->free_list))) { + ret = dr_send_info_pool_fill(pool); + if (ret) + return NULL; + } + + pool_obj = list_first_entry_or_null(&pool->free_list, + struct mlx5dr_send_info_pool_obj, + list_node); + + if (likely(pool_obj)) { + list_del_init(&pool_obj->list_node); + } else { + WARN_ONCE(!pool_obj, "Failed getting ste send info obj from pool"); + return NULL; + } + + return &pool_obj->ste_send_info; +} + +void mlx5dr_send_info_free(struct mlx5dr_ste_send_info *ste_send_info) +{ + struct mlx5dr_send_info_pool_obj *pool_obj; + + pool_obj = container_of(ste_send_info, + struct mlx5dr_send_info_pool_obj, + ste_send_info); + + list_add(&pool_obj->list_node, &pool_obj->pool->free_list); +} + static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64) { unsigned int idx; @@ -78,8 +209,15 @@ static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq) int err; cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq); - if (!cqe64) + if (!cqe64) { + if (unlikely(dr_cq->mdev->state == + MLX5_DEVICE_STATE_INTERNAL_ERROR)) { + mlx5_core_dbg_once(dr_cq->mdev, + "Polling CQ while device is shutting down\n"); + return CQ_POLL_ERR; + } return CQ_EMPTY; + } mlx5_cqwq_pop(&dr_cq->wq); err = dr_parse_cqe(dr_cq, cqe64); @@ -833,6 +971,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cq->mcq.vector = 0; cq->mcq.uar = uar; + cq->mdev = mdev; return cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 09ebd3088857..1e15f605df6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -90,6 +90,16 @@ static void dr_ste_set_always_miss(struct dr_hw_ste_format *hw_ste) hw_ste->mask[0] = 0; } +bool mlx5dr_ste_is_miss_addr_set(struct mlx5dr_ste_ctx *ste_ctx, + u8 *hw_ste_p) +{ + if (!ste_ctx->is_miss_addr_set) + return false; + + /* check if miss address is already set for this type of STE */ + return ste_ctx->is_miss_addr_set(hw_ste_p); +} + void mlx5dr_ste_set_miss_addr(struct mlx5dr_ste_ctx *ste_ctx, u8 *hw_ste_p, u64 miss_addr) { @@ -491,7 +501,7 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, u32 num_entries; int i; - htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); + htbl = mlx5dr_icm_pool_alloc_htbl(pool); if (!htbl) return NULL; @@ -503,6 +513,9 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, htbl->lu_type = lu_type; htbl->byte_mask = byte_mask; htbl->refcount = 0; + htbl->pointing_ste = NULL; + htbl->ctrl.num_of_valid_entries = 0; + htbl->ctrl.num_of_collisions = 0; num_entries = mlx5dr_icm_pool_get_chunk_num_of_entries(chunk); for (i = 0; i < num_entries; i++) { @@ -517,17 +530,20 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, return htbl; out_free_htbl: - kfree(htbl); + mlx5dr_icm_pool_free_htbl(pool, htbl); return NULL; } int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl) { + struct mlx5dr_icm_pool *pool = htbl->chunk->buddy_mem->pool; + if (htbl->refcount) return -EBUSY; mlx5dr_icm_free_chunk(htbl->chunk); - kfree(htbl); + mlx5dr_icm_pool_free_htbl(pool, htbl); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index 17513baff9b0..7075142bcfb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -151,6 +151,7 @@ struct mlx5dr_ste_ctx { bool is_rx, u16 gvmi); void (*set_next_lu_type)(u8 *hw_ste_p, u16 lu_type); u16 (*get_next_lu_type)(u8 *hw_ste_p); + bool (*is_miss_addr_set)(u8 *hw_ste_p); void (*set_miss_addr)(u8 *hw_ste_p, u64 miss_addr); u64 (*get_miss_addr)(u8 *hw_ste_p); void (*set_hit_addr)(u8 *hw_ste_p, u64 icm_addr, u32 ht_size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index ee677a5c76be..084145f18084 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -13,6 +13,7 @@ enum dr_ste_v1_entry_format { DR_STE_V1_TYPE_BWC_BYTE = 0x0, DR_STE_V1_TYPE_BWC_DW = 0x1, DR_STE_V1_TYPE_MATCH = 0x2, + DR_STE_V1_TYPE_MATCH_RANGES = 0x7, }; /* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */ @@ -267,6 +268,16 @@ static void dr_ste_v1_set_entry_type(u8 *hw_ste_p, u8 entry_type) MLX5_SET(ste_match_bwc_v1, hw_ste_p, entry_format, entry_type); } +bool dr_ste_v1_is_miss_addr_set(u8 *hw_ste_p) +{ + u8 entry_type = MLX5_GET(ste_match_bwc_v1, hw_ste_p, entry_format); + + /* unlike MATCH STE, for MATCH_RANGES STE both hit and miss addresses + * are part of the action, so they both set as part of STE init + */ + return entry_type == DR_STE_V1_TYPE_MATCH_RANGES; +} + void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) { u64 index = miss_addr >> 6; @@ -520,6 +531,27 @@ static void dr_ste_v1_set_aso_flow_meter(u8 *d_action, init_color); } +static void dr_ste_v1_set_match_range_pkt_len(u8 *hw_ste_p, u32 definer_id, + u32 min, u32 max) +{ + MLX5_SET(ste_match_ranges_v1, hw_ste_p, match_definer_ctx_idx, definer_id); + + /* When the STE will be sent, its mask and tags will be swapped in + * dr_ste_v1_prepare_for_postsend(). This, however, is match range STE + * which doesn't have mask, and shouldn't have mask/tag swapped. + * We're using the common utilities functions to send this STE, so need + * to allow for this swapping - place the values in the corresponding + * locations to allow flipping them when writing to ICM. + * + * min/max_value_2 corresponds to match_dw_0 in its definer. + * To allow mask/tag swapping, writing the min/max_2 to min/max_0. + * + * Pkt len is 2 bytes that are stored in the higher section of the DW. + */ + MLX5_SET(ste_match_ranges_v1, hw_ste_p, min_value_0, min << 16); + MLX5_SET(ste_match_ranges_v1, hw_ste_p, max_value_0, max << 16); +} + static void dr_ste_v1_arr_init_next_match(u8 **last_ste, u32 *added_stes, u16 gvmi) @@ -535,6 +567,14 @@ static void dr_ste_v1_arr_init_next_match(u8 **last_ste, memset(action, 0, MLX5_FLD_SZ_BYTES(ste_mask_and_match_v1, action)); } +static void dr_ste_v1_arr_init_next_match_range(u8 **last_ste, + u32 *added_stes, + u16 gvmi) +{ + dr_ste_v1_arr_init_next_match(last_ste, added_stes, gvmi); + dr_ste_v1_set_entry_type(*last_ste, DR_STE_V1_TYPE_MATCH_RANGES); +} + void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, @@ -670,6 +710,20 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action += DR_STE_ACTION_DOUBLE_SZ; } + if (action_type_set[DR_ACTION_TYP_RANGE]) { + /* match ranges requires a new STE of its own type */ + dr_ste_v1_arr_init_next_match_range(&last_ste, added_stes, attr->gvmi); + dr_ste_v1_set_miss_addr(last_ste, attr->range.miss_icm_addr); + + /* we do not support setting any action on the match ranges STE */ + action_sz = 0; + + dr_ste_v1_set_match_range_pkt_len(last_ste, + attr->range.definer_id, + attr->range.min, + attr->range.max); + } + dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } @@ -858,6 +912,20 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action += DR_STE_ACTION_DOUBLE_SZ; } + if (action_type_set[DR_ACTION_TYP_RANGE]) { + /* match ranges requires a new STE of its own type */ + dr_ste_v1_arr_init_next_match_range(&last_ste, added_stes, attr->gvmi); + dr_ste_v1_set_miss_addr(last_ste, attr->range.miss_icm_addr); + + /* we do not support setting any action on the match ranges STE */ + action_sz = 0; + + dr_ste_v1_set_match_range_pkt_len(last_ste, + attr->range.definer_id, + attr->range.min, + attr->range.max); + } + dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } @@ -2144,6 +2212,7 @@ static struct mlx5dr_ste_ctx ste_ctx_v1 = { .ste_init = &dr_ste_v1_init, .set_next_lu_type = &dr_ste_v1_set_next_lu_type, .get_next_lu_type = &dr_ste_v1_get_next_lu_type, + .is_miss_addr_set = &dr_ste_v1_is_miss_addr_set, .set_miss_addr = &dr_ste_v1_set_miss_addr, .get_miss_addr = &dr_ste_v1_get_miss_addr, .set_hit_addr = &dr_ste_v1_set_hit_addr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h index 8a1d49790c6e..b5c0f0f8392f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h @@ -7,6 +7,7 @@ #include "dr_types.h" #include "dr_ste.h" +bool dr_ste_v1_is_miss_addr_set(u8 *hw_ste_p); void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr); u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p); void dr_ste_v1_set_byte_mask(u8 *hw_ste_p, u16 byte_mask); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c index c60fddd125d2..cf1a3c9a1cf4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c @@ -202,6 +202,7 @@ static struct mlx5dr_ste_ctx ste_ctx_v2 = { .ste_init = &dr_ste_v1_init, .set_next_lu_type = &dr_ste_v1_set_next_lu_type, .get_next_lu_type = &dr_ste_v1_get_next_lu_type, + .is_miss_addr_set = &dr_ste_v1_is_miss_addr_set, .set_miss_addr = &dr_ste_v1_set_miss_addr, .get_miss_addr = &dr_ste_v1_get_miss_addr, .set_hit_addr = &dr_ste_v1_set_hit_addr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c index f68461b13391..69294a66fd7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -295,7 +295,7 @@ int mlx5dr_table_destroy(struct mlx5dr_table *tbl) mlx5dr_dbg_tbl_del(tbl); ret = dr_table_destroy_sw_owned_tbl(tbl); if (ret) - return ret; + mlx5dr_err(tbl->dmn, "Failed to destroy sw owned table\n"); dr_table_uninit(tbl); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 1777a1e508e7..2b769dcbd453 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -81,6 +81,7 @@ mlx5dr_icm_next_higher_chunk(enum mlx5dr_icm_chunk_size chunk) enum { DR_STE_SIZE = 64, DR_STE_SIZE_CTRL = 32, + DR_STE_SIZE_MATCH_TAG = 32, DR_STE_SIZE_TAG = 16, DR_STE_SIZE_MASK = 16, DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK, @@ -128,6 +129,7 @@ enum mlx5dr_action_type { DR_ACTION_TYP_REMOVE_HDR, DR_ACTION_TYP_SAMPLER, DR_ACTION_TYP_ASO_FLOW_METER, + DR_ACTION_TYP_RANGE, DR_ACTION_TYP_MAX, }; @@ -146,6 +148,8 @@ struct mlx5dr_cmd_caps; struct mlx5dr_rule_rx_tx; struct mlx5dr_matcher_rx_tx; struct mlx5dr_ste_ctx; +struct mlx5dr_send_info_pool; +struct mlx5dr_icm_hot_chunk; struct mlx5dr_ste { /* refcount: indicates the num of rules that using this ste */ @@ -235,6 +239,7 @@ static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl) /* STE utils */ u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl); +bool mlx5dr_ste_is_miss_addr_set(struct mlx5dr_ste_ctx *ste_ctx, u8 *hw_ste_p); void mlx5dr_ste_set_miss_addr(struct mlx5dr_ste_ctx *ste_ctx, u8 *hw_ste, u64 miss_addr); void mlx5dr_ste_set_hit_addr(struct mlx5dr_ste_ctx *ste_ctx, @@ -279,6 +284,13 @@ struct mlx5dr_ste_actions_attr { u8 dest_reg_id; u8 init_color; } aso_flow_meter; + + struct { + u64 miss_icm_addr; + u32 definer_id; + u32 min; + u32 max; + } range; }; void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, @@ -912,12 +924,17 @@ struct mlx5dr_domain { refcount_t refcount; struct mlx5dr_icm_pool *ste_icm_pool; struct mlx5dr_icm_pool *action_icm_pool; + struct mlx5dr_send_info_pool *send_info_pool_rx; + struct mlx5dr_send_info_pool *send_info_pool_tx; + struct kmem_cache *chunks_kmem_cache; + struct kmem_cache *htbls_kmem_cache; struct mlx5dr_send_ring *send_ring; struct mlx5dr_domain_info info; struct xarray csum_fts_xa; struct mlx5dr_ste_ctx *ste_ctx; struct list_head dbg_tbl_list; struct mlx5dr_dbg_dump_info dump_info; + struct xarray definers_xa; }; struct mlx5dr_table_rx_tx { @@ -1020,6 +1037,15 @@ struct mlx5dr_action_dest_tbl { }; }; +struct mlx5dr_action_range { + struct mlx5dr_domain *dmn; + struct mlx5dr_action *hit_tbl_action; + struct mlx5dr_action *miss_tbl_action; + u32 definer_id; + u32 min; + u32 max; +}; + struct mlx5dr_action_ctr { u32 ctr_id; u32 offset; @@ -1066,6 +1092,7 @@ struct mlx5dr_action { struct mlx5dr_action_push_vlan *push_vlan; struct mlx5dr_action_flow_tag *flow_tag; struct mlx5dr_action_aso_flow_meter *aso; + struct mlx5dr_action_range *range; }; }; @@ -1105,7 +1132,6 @@ int mlx5dr_rule_get_reverse_rule_members(struct mlx5dr_ste **ste_arr, struct mlx5dr_icm_chunk { struct mlx5dr_icm_buddy_mem *buddy_mem; - struct list_head chunk_list; /* indicates the index of this chunk in the whole memory, * used for deleting the chunk from the buddy @@ -1158,6 +1184,9 @@ u32 mlx5dr_icm_pool_get_chunk_num_of_entries(struct mlx5dr_icm_chunk *chunk); u32 mlx5dr_icm_pool_get_chunk_byte_size(struct mlx5dr_icm_chunk *chunk); u8 *mlx5dr_ste_get_hw_ste(struct mlx5dr_ste *ste); +struct mlx5dr_ste_htbl *mlx5dr_icm_pool_alloc_htbl(struct mlx5dr_icm_pool *pool); +void mlx5dr_icm_pool_free_htbl(struct mlx5dr_icm_pool *pool, struct mlx5dr_ste_htbl *htbl); + static inline int mlx5dr_icm_pool_dm_type_to_entry_size(enum mlx5dr_icm_type icm_type) { @@ -1287,6 +1316,14 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, u32 *reformat_id); void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, u32 reformat_id); +int mlx5dr_cmd_create_definer(struct mlx5_core_dev *mdev, + u16 format_id, + u8 *dw_selectors, + u8 *byte_selectors, + u8 *match_mask, + u32 *definer_id); +void mlx5dr_cmd_destroy_definer(struct mlx5_core_dev *mdev, + u32 definer_id); struct mlx5dr_cmd_gid_attr { u8 gid[16]; @@ -1404,6 +1441,12 @@ int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, struct mlx5dr_action *action); +int mlx5dr_send_info_pool_create(struct mlx5dr_domain *dmn); +void mlx5dr_send_info_pool_destroy(struct mlx5dr_domain *dmn); +struct mlx5dr_ste_send_info *mlx5dr_send_info_alloc(struct mlx5dr_domain *dmn, + enum mlx5dr_domain_nic_type nic_type); +void mlx5dr_send_info_free(struct mlx5dr_ste_send_info *ste_send_info); + struct mlx5dr_cmd_ft_info { u32 id; u16 vport; @@ -1469,4 +1512,18 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, u32 flow_source); void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id, u32 group_id); + +static inline bool mlx5dr_is_fw_table(struct mlx5_flow_table *ft) +{ + return !ft->fs_dr_table.dr_table; +} + +static inline bool mlx5dr_supp_match_ranges(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_GEN(dev, steering_format_version) >= + MLX5_STEERING_FORMAT_CONNECTX_6DX) && + (MLX5_CAP_GEN_64(dev, match_definer_format_supported) & + (1ULL << MLX5_IFC_DEFINER_FORMAT_ID_SELECT)); +} + #endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 13b6d4721e17..984653756779 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -7,10 +7,11 @@ #include "fs_cmd.h" #include "mlx5dr.h" #include "fs_dr.h" +#include "dr_types.h" -static bool mlx5_dr_is_fw_table(u32 flags) +static bool dr_is_fw_term_table(struct mlx5_flow_table *ft) { - if (flags & MLX5_FLOW_TABLE_TERMINATION) + if (ft->flags & MLX5_FLOW_TABLE_TERMINATION) return true; return false; @@ -69,7 +70,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, u32 flags; int err; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, ft_attr, next_ft); @@ -109,7 +110,7 @@ static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5dr_action *action = ft->fs_dr_table.miss_action; int err; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table); @@ -134,7 +135,7 @@ static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct mlx5_flow_table *next_ft) { - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft); return set_miss_action(ns, ft, next_ft); @@ -153,7 +154,7 @@ static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns, match_criteria_enable); struct mlx5dr_match_parameters mask; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, fg); @@ -178,7 +179,7 @@ static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct mlx5_flow_group *fg) { - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg); return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher); @@ -209,11 +210,22 @@ static struct mlx5dr_action *create_ft_action(struct mlx5dr_domain *domain, { struct mlx5_flow_table *dest_ft = dst->dest_attr.ft; - if (mlx5_dr_is_fw_table(dest_ft->flags)) + if (mlx5dr_is_fw_table(dest_ft)) return mlx5dr_action_create_dest_flow_fw_table(domain, dest_ft); return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table); } +static struct mlx5dr_action *create_range_action(struct mlx5dr_domain *domain, + struct mlx5_flow_rule *dst) +{ + return mlx5dr_action_create_dest_match_range(domain, + dst->dest_attr.range.field, + dst->dest_attr.range.hit_ft, + dst->dest_attr.range.miss_ft, + dst->dest_attr.range.min, + dst->dest_attr.range.max); +} + static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domain, struct mlx5_fs_vlan *vlan) { @@ -260,7 +272,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, int err = 0; int i; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte); actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions), @@ -467,6 +479,15 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, fs_dr_actions[fs_dr_num_actions++] = tmp_action; term_actions[num_term_actions++].dest = tmp_action; break; + case MLX5_FLOW_DESTINATION_TYPE_RANGE: + tmp_action = create_range_action(domain, dst); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_actions[num_term_actions++].dest = tmp_action; + break; default: err = -EOPNOTSUPP; goto free_actions; @@ -702,7 +723,7 @@ static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, int err; int i; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte); err = mlx5dr_rule_destroy(rule->dr_rule); @@ -727,7 +748,7 @@ static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns, struct fs_fte fte_tmp = {}; int ret; - if (mlx5_dr_is_fw_table(ft->flags)) + if (dr_is_fw_term_table(ft)) return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, modify_mask, fte); /* Backup current dr rule details */ @@ -780,11 +801,19 @@ static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns) static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns, enum fs_flow_table_type ft_type) { + u32 steering_caps = 0; + if (ft_type != FS_FT_FDB || MLX5_CAP_GEN(ns->dev, steering_format_version) == MLX5_STEERING_FORMAT_CONNECTX_5) return 0; - return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX; + steering_caps |= MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX; + steering_caps |= MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX; + + if (mlx5dr_supp_match_ranges(ns->dev)) + steering_caps |= MLX5_FLOW_STEERING_CAP_MATCH_RANGES; + + return steering_caps; } bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h index 34c2bd17a8b4..790a17d6207f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h @@ -165,6 +165,41 @@ struct mlx5_ifc_ste_mask_and_match_v1_bits { u8 action[0x60]; }; +struct mlx5_ifc_ste_match_ranges_v1_bits { + u8 entry_format[0x8]; + u8 counter_id[0x18]; + + u8 miss_address_63_48[0x10]; + u8 match_definer_ctx_idx[0x8]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 reserved_at_5a[0x1]; + u8 match_polarity[0x1]; + u8 reparse[0x1]; + u8 reserved_at_5d[0x3]; + + u8 next_table_base_63_48[0x10]; + u8 hash_definer_ctx_idx[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 hash_type[0x2]; + u8 hash_after_actions[0x1]; + u8 reserved_at_9e[0x2]; + + u8 action[0x60]; + + u8 max_value_0[0x20]; + u8 min_value_0[0x20]; + u8 max_value_1[0x20]; + u8 min_value_1[0x20]; + u8 max_value_2[0x20]; + u8 min_value_2[0x20]; + u8 max_value_3[0x20]; + u8 min_value_3[0x20]; +}; + struct mlx5_ifc_ste_eth_l2_src_v1_bits { u8 reserved_at_0[0x1]; u8 sx_sniffer[0x1]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 226a0d7bb06d..9afd268a2573 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -140,8 +140,21 @@ mlx5dr_action_create_aso(struct mlx5dr_domain *dmn, u8 init_color, u8 meter_id); +struct mlx5dr_action * +mlx5dr_action_create_dest_match_range(struct mlx5dr_domain *dmn, + u32 field, + struct mlx5_flow_table *hit_ft, + struct mlx5_flow_table *miss_ft, + u32 min, + u32 max); + int mlx5dr_action_destroy(struct mlx5dr_action *action); +int mlx5dr_definer_get(struct mlx5dr_domain *dmn, u16 format_id, + u8 *dw_selectors, u8 *byte_selectors, + u8 *match_mask, u32 *definer_id); +void mlx5dr_definer_put(struct mlx5dr_domain *dmn, u32 definer_id); + static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { @@ -164,16 +177,9 @@ struct mlx5dr_icm_buddy_mem { struct mlx5dr_icm_mr *icm_mr; struct mlx5dr_icm_pool *pool; - /* This is the list of used chunks. HW may be accessing this memory */ - struct list_head used_list; + /* Amount of memory in used chunks - HW may be accessing this memory */ u64 used_memory; - /* Hardware may be accessing this memory but at some future, - * undetermined time, it might cease to do so. - * sync_ste command sets them free. - */ - struct list_head hot_list; - /* Memory optimisation */ struct mlx5dr_ste *ste_arr; struct list_head *miss_list; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 8455e79bc44a..1513112ecec8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -31,7 +31,6 @@ */ #include <linux/kernel.h> -#include <linux/io-mapping.h> #include <linux/mlx5/driver.h> #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index d5c317325030..ba7e3df22413 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -1160,14 +1160,40 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); -int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out) +int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out, + u16 opmod) { - u16 opmod = (MLX5_CAP_GENERAL << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01); u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)] = {}; + opmod = (opmod << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01); MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); MLX5_SET(query_hca_cap_in, in, op_mod, opmod); MLX5_SET(query_hca_cap_in, in, function_id, function_id); MLX5_SET(query_hca_cap_in, in, other_function, true); return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out); } +EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap); + +int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, + u16 function_id, u16 opmod) +{ + int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + void *set_hca_cap; + void *set_ctx; + int ret; + + set_ctx = kzalloc(set_sz, GFP_KERNEL); + if (!set_ctx) + return -ENOMEM; + + MLX5_SET(set_hca_cap_in, set_ctx, opcode, MLX5_CMD_OP_SET_HCA_CAP); + MLX5_SET(set_hca_cap_in, set_ctx, op_mod, opmod << 1); + set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); + memcpy(set_hca_cap, hca_cap, MLX5_ST_SZ_BYTES(cmd_hca_cap)); + MLX5_SET(set_hca_cap_in, set_ctx, function_id, function_id); + MLX5_SET(set_hca_cap_in, set_ctx, other_function, true); + ret = mlx5_cmd_exec_in(dev, set_hca_cap, set_ctx); + + kfree(set_ctx); + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 4d629e5ddbc7..e4ef1d24a3ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -243,6 +243,23 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq) return cqe; } +static inline +struct mlx5_cqe64 *mlx5_cqwq_get_cqe_enahnced_comp(struct mlx5_cqwq *wq) +{ + u8 sw_validity_iteration_count = mlx5_cqwq_get_wrap_cnt(wq) & 0xff; + u32 ci = mlx5_cqwq_get_ci(wq); + struct mlx5_cqe64 *cqe; + + cqe = mlx5_cqwq_get_wqe(wq, ci); + if (cqe->validity_iteration_count != sw_validity_iteration_count) + return NULL; + + /* ensure cqe content is read after cqe ownership bit/validity byte */ + dma_rmb(); + + return cqe; +} + static inline u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) { return (u32)wq->fbc.sz_m1 + 1; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e2a985ec2c76..a0a06e2eff82 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1459,11 +1459,6 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, char buf[32]; int err; - err = devlink_info_driver_name_put(req, - mlxsw_core->bus_info->device_kind); - if (err) - return err; - mlxsw_reg_mgir_pack(mgir_pl); err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgir), mgir_pl); if (err) @@ -3172,29 +3167,17 @@ void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core) } EXPORT_SYMBOL(mlxsw_core_cpu_port_fini); -void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv, struct net_device *dev) -{ - struct mlxsw_core_port *mlxsw_core_port = - &mlxsw_core->ports[local_port]; - struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; - - mlxsw_core_port->port_driver_priv = port_driver_priv; - devlink_port_type_eth_set(devlink_port, dev); -} -EXPORT_SYMBOL(mlxsw_core_port_eth_set); - -void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv) +void mlxsw_core_port_netdev_link(struct mlxsw_core *mlxsw_core, u16 local_port, + void *port_driver_priv, struct net_device *dev) { struct mlxsw_core_port *mlxsw_core_port = &mlxsw_core->ports[local_port]; struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; mlxsw_core_port->port_driver_priv = port_driver_priv; - devlink_port_type_clear(devlink_port); + SET_NETDEV_DEVLINK_PORT(dev, devlink_port); } -EXPORT_SYMBOL(mlxsw_core_port_clear); +EXPORT_SYMBOL(mlxsw_core_port_netdev_link); struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index ca0c3d2bee6b..e0a6fcbbcb19 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -264,10 +264,9 @@ int mlxsw_core_cpu_port_init(struct mlxsw_core *mlxsw_core, const unsigned char *switch_id, unsigned char switch_id_len); void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core); -void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv, struct net_device *dev); -void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv); +void mlxsw_core_port_netdev_link(struct mlxsw_core *mlxsw_core, u16 local_port, + void *port_driver_priv, + struct net_device *dev); struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u16 local_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index f5f5f8dc3d19..2c586c2308ae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -632,9 +632,9 @@ static const struct mlxsw_bus mlxsw_i2c_bus = { .cmd_exec = mlxsw_i2c_cmd_exec, }; -static int mlxsw_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int mlxsw_i2c_probe(struct i2c_client *client) { + const struct i2c_device_id *id = i2c_client_get_device_id(client); const struct i2c_adapter_quirks *quirks = client->adapter->quirks; struct mlxsw_i2c *mlxsw_i2c; u8 status; @@ -751,7 +751,7 @@ static void mlxsw_i2c_remove(struct i2c_client *client) int mlxsw_i2c_driver_register(struct i2c_driver *i2c_driver) { - i2c_driver->probe = mlxsw_i2c_probe; + i2c_driver->probe_new = mlxsw_i2c_probe; i2c_driver->remove = mlxsw_i2c_remove; return i2c_add_driver(i2c_driver); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 55b3c42bb007..6b56eadd736e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -81,20 +81,9 @@ static int mlxsw_m_port_stop(struct net_device *dev) return 0; } -static struct devlink_port * -mlxsw_m_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); - struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; - - return mlxsw_core_port_devlink_port_get(mlxsw_m->core, - mlxsw_m_port->local_port); -} - static const struct net_device_ops mlxsw_m_port_netdev_ops = { .ndo_open = mlxsw_m_port_open, .ndo_stop = mlxsw_m_port_stop, - .ndo_get_devlink_port = mlxsw_m_port_get_devlink_port, }; static void mlxsw_m_module_get_drvinfo(struct net_device *dev, @@ -265,6 +254,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u16 local_port, u8 slot_index, SET_NETDEV_DEV(dev, mlxsw_m->bus_info->dev); dev_net_set(dev, mlxsw_core_net(mlxsw_m->core)); mlxsw_m_port = netdev_priv(dev); + mlxsw_core_port_netdev_link(mlxsw_m->core, local_port, + mlxsw_m_port, dev); mlxsw_m_port->dev = dev; mlxsw_m_port->mlxsw_m = mlxsw_m; mlxsw_m_port->local_port = local_port; @@ -298,9 +289,6 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u16 local_port, u8 slot_index, goto err_register_netdev; } - mlxsw_core_port_eth_set(mlxsw_m->core, mlxsw_m_port->local_port, - mlxsw_m_port, dev); - return 0; err_register_netdev: @@ -316,7 +304,6 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u16 local_port) { struct mlxsw_m_port *mlxsw_m_port = mlxsw_m->ports[local_port]; - mlxsw_core_port_clear(mlxsw_m->core, local_port, mlxsw_m); unregister_netdev(mlxsw_m_port->dev); /* This calls ndo_stop */ mlxsw_m->ports[local_port] = NULL; free_netdev(mlxsw_m_port->dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0777bed5bb1a..f2d6f8654e04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2046,6 +2046,39 @@ static inline void mlxsw_reg_spvmlr_pack(char *payload, u16 local_port, } } +/* SPFSR - Switch Port FDB Security Register + * ----------------------------------------- + * Configures the security mode per port. + */ +#define MLXSW_REG_SPFSR_ID 0x2023 +#define MLXSW_REG_SPFSR_LEN 0x08 + +MLXSW_REG_DEFINE(spfsr, MLXSW_REG_SPFSR_ID, MLXSW_REG_SPFSR_LEN); + +/* reg_spfsr_local_port + * Local port. + * Access: Index + * + * Note: not supported for CPU port. + */ +MLXSW_ITEM32_LP(reg, spfsr, 0x00, 16, 0x00, 12); + +/* reg_spfsr_security + * Security checks. + * 0: disabled (default) + * 1: enabled + * Access: RW + */ +MLXSW_ITEM32(reg, spfsr, security, 0x04, 31, 1); + +static inline void mlxsw_reg_spfsr_pack(char *payload, u16 local_port, + bool security) +{ + MLXSW_REG_ZERO(spfsr, payload); + mlxsw_reg_spfsr_local_port_set(payload, local_port); + mlxsw_reg_spfsr_security_set(payload, security); +} + /* SPVC - Switch Port VLAN Classification Register * ----------------------------------------------- * Configures the port to identify packets as untagged / single tagged / @@ -4620,6 +4653,7 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4); #define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2 BIT(10) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4 BIT(12) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_8 BIT(15) +#define MLXSW_REG_PTYS_EXT_ETH_SPEED_800GAUI_8 BIT(19) /* reg_ptys_ext_eth_proto_cap * Extended Ethernet port supported speeds and protocols. @@ -6315,6 +6349,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_BUFFER_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EAPOL, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 @@ -12760,6 +12795,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(svpe), MLXSW_REG(sfmr), MLXSW_REG(spvmlr), + MLXSW_REG(spfsr), MLXSW_REG(spvc), MLXSW_REG(spevet), MLXSW_REG(smpe), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5bcf5bceff71..f5b2d965d476 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -466,6 +466,24 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, return err; } +int mlxsw_sp_port_security_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char spfsr_pl[MLXSW_REG_SPFSR_LEN]; + int err; + + if (mlxsw_sp_port->security == enable) + return 0; + + mlxsw_reg_spfsr_pack(spfsr_pl, mlxsw_sp_port->local_port, enable); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spfsr), spfsr_pl); + if (err) + return err; + + mlxsw_sp_port->security = enable; + return 0; +} + int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type) { switch (ethtype) { @@ -827,12 +845,12 @@ mlxsw_sp_port_get_sw_stats64(const struct net_device *dev, for_each_possible_cpu(i) { p = per_cpu_ptr(mlxsw_sp_port->pcpu_stats, i); do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); rx_packets = p->rx_packets; rx_bytes = p->rx_bytes; tx_packets = p->tx_packets; tx_bytes = p->tx_bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -1259,16 +1277,6 @@ static int mlxsw_sp_set_features(struct net_device *dev, return 0; } -static struct devlink_port * -mlxsw_sp_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - - return mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - mlxsw_sp_port->local_port); -} - static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, struct ifreq *ifr) { @@ -1342,7 +1350,6 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid, .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_set_features = mlxsw_sp_set_features, - .ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port, .ndo_eth_ioctl = mlxsw_sp_port_ioctl, }; @@ -1651,6 +1658,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, SET_NETDEV_DEV(dev, mlxsw_sp->bus_info->dev); dev_net_set(dev, mlxsw_sp_net(mlxsw_sp)); mlxsw_sp_port = netdev_priv(dev); + mlxsw_core_port_netdev_link(mlxsw_sp->core, local_port, + mlxsw_sp_port, dev); mlxsw_sp_port->dev = dev; mlxsw_sp_port->mlxsw_sp = mlxsw_sp; mlxsw_sp_port->local_port = local_port; @@ -1839,8 +1848,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, goto err_register_netdev; } - mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port, - mlxsw_sp_port, dev); mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0); return 0; @@ -1897,7 +1904,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u16 local_port) cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw); cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw); - mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ mlxsw_sp_port_ptp_clear(mlxsw_sp_port); mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true); @@ -4754,6 +4760,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol"); return -EOPNOTSUPP; } + if (is_vlan_dev(upper_dev) && mlxsw_sp_port->security) { + NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are not supported on a locked port"); + return -EOPNOTSUPP; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index c8ff2a6d7e90..bbc73324451d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -321,7 +321,8 @@ struct mlxsw_sp_port { struct mlxsw_sp *mlxsw_sp; u16 local_port; u8 lagged:1, - split:1; + split:1, + security:1; u16 pvid; u16 lag_id; struct { @@ -687,6 +688,8 @@ int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable); int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, bool learn_enable); +int mlxsw_sp_port_security_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool enable); int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type); int mlxsw_sp_port_egress_ethtype_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 ethtype); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index dcd79d7e2af4..472830d07ac1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1672,6 +1672,19 @@ mlxsw_sp2_mask_ethtool_400gaui_8[] = { #define MLXSW_SP2_MASK_ETHTOOL_400GAUI_8_LEN \ ARRAY_SIZE(mlxsw_sp2_mask_ethtool_400gaui_8) +static const enum ethtool_link_mode_bit_indices +mlxsw_sp2_mask_ethtool_800gaui_8[] = { + ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT, + ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT, + ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT, + ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT, + ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT, + ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT, +}; + +#define MLXSW_SP2_MASK_ETHTOOL_800GAUI_8_LEN \ + ARRAY_SIZE(mlxsw_sp2_mask_ethtool_800gaui_8) + #define MLXSW_SP_PORT_MASK_WIDTH_1X BIT(0) #define MLXSW_SP_PORT_MASK_WIDTH_2X BIT(1) #define MLXSW_SP_PORT_MASK_WIDTH_4X BIT(2) @@ -1820,6 +1833,14 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .speed = SPEED_400000, .width = 8, }, + { + .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_800GAUI_8, + .mask_ethtool = mlxsw_sp2_mask_ethtool_800gaui_8, + .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_800GAUI_8_LEN, + .mask_sup_width = MLXSW_SP_PORT_MASK_WIDTH_8X, + .speed = SPEED_800000, + .width = 8, + }, }; #define MLXSW_SP2_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp2_port_link_mode) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index a2ee695a3f17..3340b4a694c3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -363,93 +363,7 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = { }; static struct mlxsw_sp_ipip_parms -mlxsw_sp1_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) -{ - struct mlxsw_sp_ipip_parms parms = {0}; - - WARN_ON_ONCE(1); - return parms; -} - -static int -mlxsw_sp1_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, - struct mlxsw_sp_ipip_entry *ipip_entry, - bool force, char *ratr_pl) -{ - WARN_ON_ONCE(1); - return -EINVAL; -} - -static int -mlxsw_sp1_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - u32 tunnel_index) -{ - WARN_ON_ONCE(1); - return -EINVAL; -} - -static bool mlxsw_sp1_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev) -{ - return false; -} - -static struct mlxsw_sp_rif_ipip_lb_config -mlxsw_sp1_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev) -{ - struct mlxsw_sp_rif_ipip_lb_config config = {0}; - - WARN_ON_ONCE(1); - return config; -} - -static int -mlxsw_sp1_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - struct netlink_ext_ack *extack) -{ - WARN_ON_ONCE(1); - return -EINVAL; -} - -static int -mlxsw_sp1_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry) -{ - WARN_ON_ONCE(1); - return -EINVAL; -} - -static void -mlxsw_sp1_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_ipip_entry *ipip_entry) -{ - WARN_ON_ONCE(1); -} - -static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = { - .dev_type = ARPHRD_IP6GRE, - .ul_proto = MLXSW_SP_L3_PROTO_IPV6, - .inc_parsing_depth = true, - .parms_init = mlxsw_sp1_ipip_netdev_parms_init_gre6, - .nexthop_update = mlxsw_sp1_ipip_nexthop_update_gre6, - .decap_config = mlxsw_sp1_ipip_decap_config_gre6, - .can_offload = mlxsw_sp1_ipip_can_offload_gre6, - .ol_loopback_config = mlxsw_sp1_ipip_ol_loopback_config_gre6, - .ol_netdev_change = mlxsw_sp1_ipip_ol_netdev_change_gre6, - .rem_ip_addr_set = mlxsw_sp1_ipip_rem_addr_set_gre6, - .rem_ip_addr_unset = mlxsw_sp1_ipip_rem_addr_unset_gre6, -}; - -const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = { - [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, - [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops, -}; - -static struct mlxsw_sp_ipip_parms -mlxsw_sp2_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) +mlxsw_sp_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) { struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); @@ -464,9 +378,9 @@ mlxsw_sp2_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) } static int -mlxsw_sp2_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, - struct mlxsw_sp_ipip_entry *ipip_entry, - bool force, char *ratr_pl) +mlxsw_sp_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry, + bool force, char *ratr_pl) { u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); enum mlxsw_reg_ratr_op op; @@ -482,9 +396,9 @@ mlxsw_sp2_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, } static int -mlxsw_sp2_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - u32 tunnel_index) +mlxsw_sp_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) { u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb); @@ -519,8 +433,8 @@ mlxsw_sp2_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl); } -static bool mlxsw_sp2_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev) +static bool mlxsw_sp_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) { struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev); bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; @@ -534,8 +448,8 @@ static bool mlxsw_sp2_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, } static struct mlxsw_sp_rif_ipip_lb_config -mlxsw_sp2_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, - const struct net_device *ol_dev) +mlxsw_sp_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) { struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; @@ -553,20 +467,20 @@ mlxsw_sp2_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, } static int -mlxsw_sp2_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - struct netlink_ext_ack *extack) +mlxsw_sp_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) { struct mlxsw_sp_ipip_parms new_parms; - new_parms = mlxsw_sp2_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); + new_parms = mlxsw_sp_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, &new_parms, extack); } static int -mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) { return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, &ipip_entry->parms.daddr.addr6, @@ -574,24 +488,44 @@ mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, } static void -mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) { mlxsw_sp_ipv6_addr_put(mlxsw_sp, &ipip_entry->parms.daddr.addr6); } +static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = { + .dev_type = ARPHRD_IP6GRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV6, + .inc_parsing_depth = true, + .double_rif_entry = true, + .parms_init = mlxsw_sp_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp_ipip_decap_config_gre6, + .can_offload = mlxsw_sp_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp_ipip_rem_addr_unset_gre6, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = { + [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, + [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops, +}; + static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { .dev_type = ARPHRD_IP6GRE, .ul_proto = MLXSW_SP_L3_PROTO_IPV6, .inc_parsing_depth = true, - .parms_init = mlxsw_sp2_ipip_netdev_parms_init_gre6, - .nexthop_update = mlxsw_sp2_ipip_nexthop_update_gre6, - .decap_config = mlxsw_sp2_ipip_decap_config_gre6, - .can_offload = mlxsw_sp2_ipip_can_offload_gre6, - .ol_loopback_config = mlxsw_sp2_ipip_ol_loopback_config_gre6, - .ol_netdev_change = mlxsw_sp2_ipip_ol_netdev_change_gre6, - .rem_ip_addr_set = mlxsw_sp2_ipip_rem_addr_set_gre6, - .rem_ip_addr_unset = mlxsw_sp2_ipip_rem_addr_unset_gre6, + .parms_init = mlxsw_sp_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp_ipip_decap_config_gre6, + .can_offload = mlxsw_sp_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp_ipip_rem_addr_unset_gre6, }; const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index 8cc259dcc8d0..a35f009da561 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -49,6 +49,7 @@ struct mlxsw_sp_ipip_ops { int dev_type; enum mlxsw_sp_l3proto ul_proto; /* Underlay. */ bool inc_parsing_depth; + bool double_rif_entry; struct mlxsw_sp_ipip_parms (*parms_init)(const struct net_device *ol_dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 7b01b9c20722..cbb6c75a6620 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -189,29 +189,17 @@ mlxsw_sp1_ptp_phc_settime(struct mlxsw_sp1_ptp_clock *clock, u64 nsec) static int mlxsw_sp1_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct mlxsw_sp1_ptp_clock *clock = mlxsw_sp1_ptp_clock(ptp); - int neg_adj = 0; - u32 diff; - u64 adj; s32 ppb; ppb = scaled_ppm_to_ppb(scaled_ppm); - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - - adj = clock->nominal_c_mult; - adj *= ppb; - diff = div_u64(adj, NSEC_PER_SEC); - spin_lock_bh(&clock->lock); timecounter_read(&clock->tc); - clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : - clock->nominal_c_mult + diff; + clock->cycles.mult = adjust_by_scaled_ppm(clock->nominal_c_mult, + scaled_ppm); spin_unlock_bh(&clock->lock); - return mlxsw_sp_ptp_phc_adjfreq(&clock->common, neg_adj ? -ppb : ppb); + return mlxsw_sp_ptp_phc_adjfreq(&clock->common, ppb); } static int mlxsw_sp1_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 48f1fa62a4fd..c22c3ac4e2a1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -18,6 +18,7 @@ #include <linux/jhash.h> #include <linux/net_namespace.h> #include <linux/mutex.h> +#include <linux/genalloc.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> @@ -59,6 +60,7 @@ struct mlxsw_sp_rif { int mtu; u16 rif_index; u8 mac_profile_id; + u8 rif_entries; u16 vr_id; const struct mlxsw_sp_rif_ops *ops; struct mlxsw_sp *mlxsw_sp; @@ -77,6 +79,7 @@ struct mlxsw_sp_rif_params { }; u16 vid; bool lag; + bool double_entry; }; struct mlxsw_sp_rif_subport { @@ -1068,6 +1071,7 @@ mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp, lb_params = (struct mlxsw_sp_rif_params_ipip_lb) { .common.dev = ol_dev, .common.lag = false, + .common.double_entry = ipip_ops->double_rif_entry, .lb_config = ipip_ops->ol_loopback_config(mlxsw_sp, ol_dev), }; @@ -7826,18 +7830,26 @@ mlxsw_sp_dev_rif_type(const struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fid_type_rif_type(mlxsw_sp, type); } -static int mlxsw_sp_rif_index_alloc(struct mlxsw_sp *mlxsw_sp, u16 *p_rif_index) +static int mlxsw_sp_rif_index_alloc(struct mlxsw_sp *mlxsw_sp, u16 *p_rif_index, + u8 rif_entries) { - int i; + *p_rif_index = gen_pool_alloc(mlxsw_sp->router->rifs_table, + rif_entries); + if (*p_rif_index == 0) + return -ENOBUFS; + *p_rif_index -= MLXSW_SP_ROUTER_GENALLOC_OFFSET; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { - if (!mlxsw_sp->router->rifs[i]) { - *p_rif_index = i; - return 0; - } - } + /* RIF indexes must be aligned to the allocation size. */ + WARN_ON_ONCE(*p_rif_index % rif_entries); - return -ENOBUFS; + return 0; +} + +static void mlxsw_sp_rif_index_free(struct mlxsw_sp *mlxsw_sp, u16 rif_index, + u8 rif_entries) +{ + gen_pool_free(mlxsw_sp->router->rifs_table, + MLXSW_SP_ROUTER_GENALLOC_OFFSET + rif_index, rif_entries); } static struct mlxsw_sp_rif *mlxsw_sp_rif_alloc(size_t rif_size, u16 rif_index, @@ -8081,6 +8093,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_rif_params *params, struct netlink_ext_ack *extack) { + u8 rif_entries = params->double_entry ? 2 : 1; u32 tb_id = l3mdev_fib_table(params->dev); const struct mlxsw_sp_rif_ops *ops; struct mlxsw_sp_fid *fid = NULL; @@ -8098,7 +8111,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, return ERR_CAST(vr); vr->rif_count++; - err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); + err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index, rif_entries); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces"); goto err_rif_index_alloc; @@ -8113,6 +8126,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router->rifs[rif_index] = rif; rif->mlxsw_sp = mlxsw_sp; rif->ops = ops; + rif->rif_entries = rif_entries; if (ops->fid_get) { fid = ops->fid_get(rif, extack); @@ -8146,7 +8160,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_counters_alloc(rif); } - atomic_inc(&mlxsw_sp->router->rifs_count); + atomic_add(rif_entries, &mlxsw_sp->router->rifs_count); return rif; err_stats_enable: @@ -8162,6 +8176,7 @@ err_fid_get: dev_put(rif->dev); kfree(rif); err_rif_alloc: + mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); err_rif_index_alloc: vr->rif_count--; mlxsw_sp_vr_put(mlxsw_sp, vr); @@ -8173,10 +8188,12 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) const struct mlxsw_sp_rif_ops *ops = rif->ops; struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; struct mlxsw_sp_fid *fid = rif->fid; + u8 rif_entries = rif->rif_entries; + u16 rif_index = rif->rif_index; struct mlxsw_sp_vr *vr; int i; - atomic_dec(&mlxsw_sp->router->rifs_count); + atomic_sub(rif_entries, &mlxsw_sp->router->rifs_count); mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr = &mlxsw_sp->router->vrs[rif->vr_id]; @@ -8198,6 +8215,7 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp->router->rifs[rif->rif_index] = NULL; dev_put(rif->dev); kfree(rif); + mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); vr->rif_count--; mlxsw_sp_vr_put(mlxsw_sp, vr); } @@ -9771,42 +9789,51 @@ mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, struct netlink_ext_ack *extack) { struct mlxsw_sp_rif *ul_rif; + u8 rif_entries = 1; u16 rif_index; int err; - err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); + err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index, rif_entries); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces"); return ERR_PTR(err); } ul_rif = mlxsw_sp_rif_alloc(sizeof(*ul_rif), rif_index, vr->id, NULL); - if (!ul_rif) - return ERR_PTR(-ENOMEM); + if (!ul_rif) { + err = -ENOMEM; + goto err_rif_alloc; + } mlxsw_sp->router->rifs[rif_index] = ul_rif; ul_rif->mlxsw_sp = mlxsw_sp; + ul_rif->rif_entries = rif_entries; err = mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, true); if (err) goto ul_rif_op_err; - atomic_inc(&mlxsw_sp->router->rifs_count); + atomic_add(rif_entries, &mlxsw_sp->router->rifs_count); return ul_rif; ul_rif_op_err: mlxsw_sp->router->rifs[rif_index] = NULL; kfree(ul_rif); +err_rif_alloc: + mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); return ERR_PTR(err); } static void mlxsw_sp_ul_rif_destroy(struct mlxsw_sp_rif *ul_rif) { struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp; + u8 rif_entries = ul_rif->rif_entries; + u16 rif_index = ul_rif->rif_index; - atomic_dec(&mlxsw_sp->router->rifs_count); + atomic_sub(rif_entries, &mlxsw_sp->router->rifs_count); mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, false); mlxsw_sp->router->rifs[ul_rif->rif_index] = NULL; kfree(ul_rif); + mlxsw_sp_rif_index_free(mlxsw_sp, rif_index, rif_entries); } static struct mlxsw_sp_rif * @@ -9940,11 +9967,43 @@ static const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[] = { [MLXSW_SP_RIF_TYPE_IPIP_LB] = &mlxsw_sp2_rif_ipip_lb_ops, }; +static int mlxsw_sp_rifs_table_init(struct mlxsw_sp *mlxsw_sp) +{ + struct gen_pool *rifs_table; + int err; + + rifs_table = gen_pool_create(0, -1); + if (!rifs_table) + return -ENOMEM; + + gen_pool_set_algo(rifs_table, gen_pool_first_fit_order_align, + NULL); + + err = gen_pool_add(rifs_table, MLXSW_SP_ROUTER_GENALLOC_OFFSET, + MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS), -1); + if (err) + goto err_gen_pool_add; + + mlxsw_sp->router->rifs_table = rifs_table; + + return 0; + +err_gen_pool_add: + gen_pool_destroy(rifs_table); + return err; +} + +static void mlxsw_sp_rifs_table_fini(struct mlxsw_sp *mlxsw_sp) +{ + gen_pool_destroy(mlxsw_sp->router->rifs_table); +} + static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) { u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); struct mlxsw_core *core = mlxsw_sp->core; + int err; if (!MLXSW_CORE_RES_VALID(core, MAX_RIF_MAC_PROFILES)) return -EIO; @@ -9957,6 +10016,10 @@ static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp->router->rifs) return -ENOMEM; + err = mlxsw_sp_rifs_table_init(mlxsw_sp); + if (err) + goto err_rifs_table_init; + idr_init(&mlxsw_sp->router->rif_mac_profiles_idr); atomic_set(&mlxsw_sp->router->rif_mac_profiles_count, 0); atomic_set(&mlxsw_sp->router->rifs_count, 0); @@ -9970,6 +10033,10 @@ static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) mlxsw_sp); return 0; + +err_rifs_table_init: + kfree(mlxsw_sp->router->rifs); + return err; } static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) @@ -9986,6 +10053,7 @@ static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) MLXSW_SP_RESOURCE_RIF_MAC_PROFILES); WARN_ON(!idr_is_empty(&mlxsw_sp->router->rif_mac_profiles_idr)); idr_destroy(&mlxsw_sp->router->rif_mac_profiles_idr); + mlxsw_sp_rifs_table_fini(mlxsw_sp); kfree(mlxsw_sp->router->rifs); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index c5dfb972b433..37d6e4c80e6a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -15,8 +15,12 @@ struct mlxsw_sp_router_nve_decap { u8 valid:1; }; +/* gen_pool_alloc() returns 0 when allocation fails, so use an offset */ +#define MLXSW_SP_ROUTER_GENALLOC_OFFSET 0x100 + struct mlxsw_sp_router { struct mlxsw_sp *mlxsw_sp; + struct gen_pool *rifs_table; struct mlxsw_sp_rif **rifs; struct idr rif_mac_profiles_idr; atomic_t rif_mac_profiles_count; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 1290b2d3eae6..d88e62bc759f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -782,10 +782,25 @@ err_port_bridge_vlan_learning_set: static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, - struct switchdev_brport_flags flags) + const struct net_device *orig_dev, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { - if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD)) + if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_PORT_LOCKED | BR_PORT_MAB)) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported bridge port flag"); return -EINVAL; + } + + if ((flags.mask & BR_PORT_LOCKED) && is_vlan_dev(orig_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Locked flag cannot be set on a VLAN upper"); + return -EINVAL; + } + + if ((flags.mask & BR_PORT_LOCKED) && vlan_uses_dev(orig_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Locked flag cannot be set on a bridge port that has VLAN uppers"); + return -EINVAL; + } return 0; } @@ -819,6 +834,13 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, return err; } + if (flags.mask & BR_PORT_LOCKED) { + err = mlxsw_sp_port_security_set(mlxsw_sp_port, + flags.val & BR_PORT_LOCKED); + if (err) + return err; + } + if (bridge_port->bridge_device->multicast_enabled) goto out; @@ -1186,7 +1208,9 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, const void *ctx, break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port, - attr->u.brport_flags); + attr->orig_dev, + attr->u.brport_flags, + extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, @@ -2783,6 +2807,7 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, bridge_device->ops->port_leave(bridge_device, bridge_port, mlxsw_sp_port); + mlxsw_sp_port_security_set(mlxsw_sp_port, false); mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port); } @@ -2888,13 +2913,14 @@ static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev, static void mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, - struct net_device *dev, bool offloaded) + struct net_device *dev, bool offloaded, bool locked) { struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; info.offloaded = offloaded; + info.locked = locked; call_switchdev_notifiers(type, dev, &info.info, NULL); } @@ -2941,6 +2967,12 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0; evid = mlxsw_sp_port_vlan->vid; + if (adding && mlxsw_sp_port->security) { + mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, mac, + vid, bridge_port->dev, false, true); + return; + } + do_fdb_op: err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, evid, adding, true); @@ -2952,7 +2984,8 @@ do_fdb_op: if (!do_notification) return; type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding, + false); return; @@ -3004,6 +3037,12 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0; lag_vid = mlxsw_sp_port_vlan->vid; + if (adding && mlxsw_sp_port->security) { + mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, mac, + vid, bridge_port->dev, false, true); + return; + } + do_fdb_op: err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid, adding, true); @@ -3015,7 +3054,8 @@ do_fdb_op: if (!do_notification) return; type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding, + false); return; @@ -3122,7 +3162,7 @@ static void mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp, type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding, false); mlxsw_sp_fid_put(fid); @@ -3264,7 +3304,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp, &vxlan_fdb_info.info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, vxlan_fdb_info.eth_addr, - fdb_info->vid, dev, true); + fdb_info->vid, dev, true, false); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: err = mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, @@ -3359,7 +3399,7 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work) break; mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, fdb_info->addr, - fdb_info->vid, dev, true); + fdb_info->vid, dev, true, false); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; @@ -3443,7 +3483,8 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp, call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, &vxlan_fdb_info->info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, - vxlan_fdb_info->eth_addr, vid, dev, true); + vxlan_fdb_info->eth_addr, vid, dev, true, + false); mlxsw_sp_fid_put(fid); @@ -3495,7 +3536,8 @@ mlxsw_sp_switchdev_vxlan_fdb_del(struct mlxsw_sp *mlxsw_sp, false, false); vid = bridge_device->ops->fid_vid(bridge_device, fid); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, - vxlan_fdb_info->eth_addr, vid, dev, false); + vxlan_fdb_info->eth_addr, vid, dev, false, + false); mlxsw_sp_fid_put(fid); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index f4bfdb6dab9c..899c954e0e5f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -510,6 +510,9 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(20, 10240, 4096), }, + { + .policer = MLXSW_SP_TRAP_POLICER(21, 128, 128), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -628,6 +631,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING, .priority = 4, }, + { + .group = DEVLINK_TRAP_GROUP_GENERIC(EAPOL, 21), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EAPOL, + .priority = 5, + }, }; static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { @@ -1160,6 +1168,23 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { MLXSW_SP_RXL_DISCARD(ROUTER3, L3_DISCARDS), }, }, + { + .trap = MLXSW_SP_TRAP_CONTROL(EAPOL, EAPOL, TRAP), + .listeners_arr = { + MLXSW_SP_RXL_NO_MARK(EAPOL, EAPOL, TRAP_TO_CPU, true), + }, + }, + { + .trap = MLXSW_SP_TRAP_DROP(LOCKED_PORT, L2_DROPS), + .listeners_arr = { + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, FDB_MISS, + TRAP_EXCEPTION_TO_CPU, false, + SP_L2_DISCARDS, DISCARD, SP_L2_DISCARDS), + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, FDB_MISMATCH, + TRAP_EXCEPTION_TO_CPU, false, + SP_L2_DISCARDS, DISCARD, SP_L2_DISCARDS), + }, + }, }; static struct mlxsw_sp_trap_policer_item * diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 8da169663bda..83477c8e6971 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -25,6 +25,8 @@ enum { MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33, MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, MLXSW_TRAP_ID_PKT_SAMPLE = 0x38, + MLXSW_TRAP_ID_FDB_MISS = 0x3A, + MLXSW_TRAP_ID_FDB_MISMATCH = 0x3B, MLXSW_TRAP_ID_FID_MISS = 0x3D, MLXSW_TRAP_ID_DECAP_ECN0 = 0x40, MLXSW_TRAP_ID_MTUERROR = 0x52, diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index ed7a35c3ceac..24c994baad13 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -57,5 +57,6 @@ config LAN743X source "drivers/net/ethernet/microchip/lan966x/Kconfig" source "drivers/net/ethernet/microchip/sparx5/Kconfig" +source "drivers/net/ethernet/microchip/vcap/Kconfig" endif # NET_VENDOR_MICROCHIP diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile index 9faa41436198..bbd349264e6f 100644 --- a/drivers/net/ethernet/microchip/Makefile +++ b/drivers/net/ethernet/microchip/Makefile @@ -11,3 +11,4 @@ lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o obj-$(CONFIG_LAN966X_SWITCH) += lan966x/ obj-$(CONFIG_SPARX5_SWITCH) += sparx5/ +obj-$(CONFIG_VCAP) += vcap/ diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index c739d60ee17d..2db5949b4c7e 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1190,14 +1190,12 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, } #endif /* CONFIG_PM */ -static void lan743x_common_regs(struct net_device *dev, - struct ethtool_regs *regs, void *p) - +static void lan743x_common_regs(struct net_device *dev, void *p) { struct lan743x_adapter *adapter = netdev_priv(dev); u32 *rb = p; - memset(p, 0, (MAX_LAN743X_ETH_REGS * sizeof(u32))); + memset(p, 0, (MAX_LAN743X_ETH_COMMON_REGS * sizeof(u32))); rb[ETH_PRIV_FLAGS] = adapter->flags; rb[ETH_ID_REV] = lan743x_csr_read(adapter, ID_REV); @@ -1220,17 +1218,164 @@ static void lan743x_common_regs(struct net_device *dev, rb[ETH_WK_SRC] = lan743x_csr_read(adapter, MAC_WK_SRC); } +static void lan743x_sgmii_regs(struct net_device *dev, void *p) +{ + struct lan743x_adapter *adp = netdev_priv(dev); + u32 *rb = p; + u16 idx; + int val; + struct { + u8 id; + u8 dev; + u16 addr; + } regs[] = { + { ETH_SR_VSMMD_DEV_ID1, MDIO_MMD_VEND1, 0x0002}, + { ETH_SR_VSMMD_DEV_ID2, MDIO_MMD_VEND1, 0x0003}, + { ETH_SR_VSMMD_PCS_ID1, MDIO_MMD_VEND1, 0x0004}, + { ETH_SR_VSMMD_PCS_ID2, MDIO_MMD_VEND1, 0x0005}, + { ETH_SR_VSMMD_STS, MDIO_MMD_VEND1, 0x0008}, + { ETH_SR_VSMMD_CTRL, MDIO_MMD_VEND1, 0x0009}, + { ETH_SR_MII_CTRL, MDIO_MMD_VEND2, 0x0000}, + { ETH_SR_MII_STS, MDIO_MMD_VEND2, 0x0001}, + { ETH_SR_MII_DEV_ID1, MDIO_MMD_VEND2, 0x0002}, + { ETH_SR_MII_DEV_ID2, MDIO_MMD_VEND2, 0x0003}, + { ETH_SR_MII_AN_ADV, MDIO_MMD_VEND2, 0x0004}, + { ETH_SR_MII_LP_BABL, MDIO_MMD_VEND2, 0x0005}, + { ETH_SR_MII_EXPN, MDIO_MMD_VEND2, 0x0006}, + { ETH_SR_MII_EXT_STS, MDIO_MMD_VEND2, 0x000F}, + { ETH_SR_MII_TIME_SYNC_ABL, MDIO_MMD_VEND2, 0x0708}, + { ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_LWR, MDIO_MMD_VEND2, 0x0709}, + { ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_UPR, MDIO_MMD_VEND2, 0x070A}, + { ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_LWR, MDIO_MMD_VEND2, 0x070B}, + { ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_UPR, MDIO_MMD_VEND2, 0x070C}, + { ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_LWR, MDIO_MMD_VEND2, 0x070D}, + { ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_UPR, MDIO_MMD_VEND2, 0x070E}, + { ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_LWR, MDIO_MMD_VEND2, 0x070F}, + { ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_UPR, MDIO_MMD_VEND2, 0x0710}, + { ETH_VR_MII_DIG_CTRL1, MDIO_MMD_VEND2, 0x8000}, + { ETH_VR_MII_AN_CTRL, MDIO_MMD_VEND2, 0x8001}, + { ETH_VR_MII_AN_INTR_STS, MDIO_MMD_VEND2, 0x8002}, + { ETH_VR_MII_TC, MDIO_MMD_VEND2, 0x8003}, + { ETH_VR_MII_DBG_CTRL, MDIO_MMD_VEND2, 0x8005}, + { ETH_VR_MII_EEE_MCTRL0, MDIO_MMD_VEND2, 0x8006}, + { ETH_VR_MII_EEE_TXTIMER, MDIO_MMD_VEND2, 0x8008}, + { ETH_VR_MII_EEE_RXTIMER, MDIO_MMD_VEND2, 0x8009}, + { ETH_VR_MII_LINK_TIMER_CTRL, MDIO_MMD_VEND2, 0x800A}, + { ETH_VR_MII_EEE_MCTRL1, MDIO_MMD_VEND2, 0x800B}, + { ETH_VR_MII_DIG_STS, MDIO_MMD_VEND2, 0x8010}, + { ETH_VR_MII_ICG_ERRCNT1, MDIO_MMD_VEND2, 0x8011}, + { ETH_VR_MII_GPIO, MDIO_MMD_VEND2, 0x8015}, + { ETH_VR_MII_EEE_LPI_STATUS, MDIO_MMD_VEND2, 0x8016}, + { ETH_VR_MII_EEE_WKERR, MDIO_MMD_VEND2, 0x8017}, + { ETH_VR_MII_MISC_STS, MDIO_MMD_VEND2, 0x8018}, + { ETH_VR_MII_RX_LSTS, MDIO_MMD_VEND2, 0x8020}, + { ETH_VR_MII_GEN2_GEN4_TX_BSTCTRL0, MDIO_MMD_VEND2, 0x8038}, + { ETH_VR_MII_GEN2_GEN4_TX_LVLCTRL0, MDIO_MMD_VEND2, 0x803A}, + { ETH_VR_MII_GEN2_GEN4_TXGENCTRL0, MDIO_MMD_VEND2, 0x803C}, + { ETH_VR_MII_GEN2_GEN4_TXGENCTRL1, MDIO_MMD_VEND2, 0x803D}, + { ETH_VR_MII_GEN4_TXGENCTRL2, MDIO_MMD_VEND2, 0x803E}, + { ETH_VR_MII_GEN2_GEN4_TX_STS, MDIO_MMD_VEND2, 0x8048}, + { ETH_VR_MII_GEN2_GEN4_RXGENCTRL0, MDIO_MMD_VEND2, 0x8058}, + { ETH_VR_MII_GEN2_GEN4_RXGENCTRL1, MDIO_MMD_VEND2, 0x8059}, + { ETH_VR_MII_GEN4_RXEQ_CTRL, MDIO_MMD_VEND2, 0x805B}, + { ETH_VR_MII_GEN4_RXLOS_CTRL0, MDIO_MMD_VEND2, 0x805D}, + { ETH_VR_MII_GEN2_GEN4_MPLL_CTRL0, MDIO_MMD_VEND2, 0x8078}, + { ETH_VR_MII_GEN2_GEN4_MPLL_CTRL1, MDIO_MMD_VEND2, 0x8079}, + { ETH_VR_MII_GEN2_GEN4_MPLL_STS, MDIO_MMD_VEND2, 0x8088}, + { ETH_VR_MII_GEN2_GEN4_LVL_CTRL, MDIO_MMD_VEND2, 0x8090}, + { ETH_VR_MII_GEN4_MISC_CTRL2, MDIO_MMD_VEND2, 0x8093}, + { ETH_VR_MII_GEN2_GEN4_MISC_CTRL0, MDIO_MMD_VEND2, 0x8099}, + { ETH_VR_MII_GEN2_GEN4_MISC_CTRL1, MDIO_MMD_VEND2, 0x809A}, + { ETH_VR_MII_SNPS_CR_CTRL, MDIO_MMD_VEND2, 0x80A0}, + { ETH_VR_MII_SNPS_CR_ADDR, MDIO_MMD_VEND2, 0x80A1}, + { ETH_VR_MII_SNPS_CR_DATA, MDIO_MMD_VEND2, 0x80A2}, + { ETH_VR_MII_DIG_CTRL2, MDIO_MMD_VEND2, 0x80E1}, + { ETH_VR_MII_DIG_ERRCNT, MDIO_MMD_VEND2, 0x80E2}, + }; + + for (idx = 0; idx < ARRAY_SIZE(regs); idx++) { + val = lan743x_sgmii_read(adp, regs[idx].dev, regs[idx].addr); + if (val < 0) + rb[regs[idx].id] = 0xFFFF; + else + rb[regs[idx].id] = val; + } +} + static int lan743x_get_regs_len(struct net_device *dev) { - return MAX_LAN743X_ETH_REGS * sizeof(u32); + struct lan743x_adapter *adapter = netdev_priv(dev); + u32 num_regs = MAX_LAN743X_ETH_COMMON_REGS; + + if (adapter->is_sgmii_en) + num_regs += MAX_LAN743X_ETH_SGMII_REGS; + + return num_regs * sizeof(u32); } static void lan743x_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) { + struct lan743x_adapter *adapter = netdev_priv(dev); + int regs_len; + + regs_len = lan743x_get_regs_len(dev); + memset(p, 0, regs_len); + regs->version = LAN743X_ETH_REG_VERSION; + regs->len = regs_len; + + lan743x_common_regs(dev, p); + p = (u32 *)p + MAX_LAN743X_ETH_COMMON_REGS; - lan743x_common_regs(dev, regs, p); + if (adapter->is_sgmii_en) { + lan743x_sgmii_regs(dev, p); + p = (u32 *)p + MAX_LAN743X_ETH_SGMII_REGS; + } +} + +static void lan743x_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct lan743x_adapter *adapter = netdev_priv(dev); + struct lan743x_phy *phy = &adapter->phy; + + if (phy->fc_request_control & FLOW_CTRL_TX) + pause->tx_pause = 1; + if (phy->fc_request_control & FLOW_CTRL_RX) + pause->rx_pause = 1; + pause->autoneg = phy->fc_autoneg; +} + +static int lan743x_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct lan743x_adapter *adapter = netdev_priv(dev); + struct phy_device *phydev = dev->phydev; + struct lan743x_phy *phy = &adapter->phy; + + if (!phydev) + return -ENODEV; + + if (!phy_validate_pause(phydev, pause)) + return -EINVAL; + + phy->fc_request_control = 0; + if (pause->rx_pause) + phy->fc_request_control |= FLOW_CTRL_RX; + + if (pause->tx_pause) + phy->fc_request_control |= FLOW_CTRL_TX; + + phy->fc_autoneg = pause->autoneg; + + if (pause->autoneg == AUTONEG_DISABLE) + lan743x_mac_flow_ctrl_set_enables(adapter, pause->tx_pause, + pause->rx_pause); + else + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); + + return 0; } const struct ethtool_ops lan743x_ethtool_ops = { @@ -1259,6 +1404,8 @@ const struct ethtool_ops lan743x_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_regs_len = lan743x_get_regs_len, .get_regs = lan743x_get_regs, + .get_pauseparam = lan743x_get_pauseparam, + .set_pauseparam = lan743x_set_pauseparam, #ifdef CONFIG_PM .get_wol = lan743x_ethtool_get_wol, .set_wol = lan743x_ethtool_set_wol, diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.h b/drivers/net/ethernet/microchip/lan743x_ethtool.h index 7f5996a52488..267d5035b8ad 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.h +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.h @@ -29,7 +29,76 @@ enum { ETH_WK_SRC, /* Add new registers above */ - MAX_LAN743X_ETH_REGS + MAX_LAN743X_ETH_COMMON_REGS +}; + +enum { + /* SGMII Register */ + ETH_SR_VSMMD_DEV_ID1, + ETH_SR_VSMMD_DEV_ID2, + ETH_SR_VSMMD_PCS_ID1, + ETH_SR_VSMMD_PCS_ID2, + ETH_SR_VSMMD_STS, + ETH_SR_VSMMD_CTRL, + ETH_SR_MII_CTRL, + ETH_SR_MII_STS, + ETH_SR_MII_DEV_ID1, + ETH_SR_MII_DEV_ID2, + ETH_SR_MII_AN_ADV, + ETH_SR_MII_LP_BABL, + ETH_SR_MII_EXPN, + ETH_SR_MII_EXT_STS, + ETH_SR_MII_TIME_SYNC_ABL, + ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_LWR, + ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_UPR, + ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_LWR, + ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_UPR, + ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_LWR, + ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_UPR, + ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_LWR, + ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_UPR, + ETH_VR_MII_DIG_CTRL1, + ETH_VR_MII_AN_CTRL, + ETH_VR_MII_AN_INTR_STS, + ETH_VR_MII_TC, + ETH_VR_MII_DBG_CTRL, + ETH_VR_MII_EEE_MCTRL0, + ETH_VR_MII_EEE_TXTIMER, + ETH_VR_MII_EEE_RXTIMER, + ETH_VR_MII_LINK_TIMER_CTRL, + ETH_VR_MII_EEE_MCTRL1, + ETH_VR_MII_DIG_STS, + ETH_VR_MII_ICG_ERRCNT1, + ETH_VR_MII_GPIO, + ETH_VR_MII_EEE_LPI_STATUS, + ETH_VR_MII_EEE_WKERR, + ETH_VR_MII_MISC_STS, + ETH_VR_MII_RX_LSTS, + ETH_VR_MII_GEN2_GEN4_TX_BSTCTRL0, + ETH_VR_MII_GEN2_GEN4_TX_LVLCTRL0, + ETH_VR_MII_GEN2_GEN4_TXGENCTRL0, + ETH_VR_MII_GEN2_GEN4_TXGENCTRL1, + ETH_VR_MII_GEN4_TXGENCTRL2, + ETH_VR_MII_GEN2_GEN4_TX_STS, + ETH_VR_MII_GEN2_GEN4_RXGENCTRL0, + ETH_VR_MII_GEN2_GEN4_RXGENCTRL1, + ETH_VR_MII_GEN4_RXEQ_CTRL, + ETH_VR_MII_GEN4_RXLOS_CTRL0, + ETH_VR_MII_GEN2_GEN4_MPLL_CTRL0, + ETH_VR_MII_GEN2_GEN4_MPLL_CTRL1, + ETH_VR_MII_GEN2_GEN4_MPLL_STS, + ETH_VR_MII_GEN2_GEN4_LVL_CTRL, + ETH_VR_MII_GEN4_MISC_CTRL2, + ETH_VR_MII_GEN2_GEN4_MISC_CTRL0, + ETH_VR_MII_GEN2_GEN4_MISC_CTRL1, + ETH_VR_MII_SNPS_CR_CTRL, + ETH_VR_MII_SNPS_CR_ADDR, + ETH_VR_MII_SNPS_CR_DATA, + ETH_VR_MII_DIG_CTRL2, + ETH_VR_MII_DIG_ERRCNT, + + /* Add new registers above */ + MAX_LAN743X_ETH_SGMII_REGS }; extern const struct ethtool_ops lan743x_ethtool_ops; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 50eeecba1f18..534840f9a7ca 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -939,7 +939,7 @@ static int lan743x_sgmii_wait_till_not_busy(struct lan743x_adapter *adapter) return ret; } -static int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr) +int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr) { u32 mmd_access; int ret; @@ -1326,8 +1326,8 @@ static void lan743x_mac_close(struct lan743x_adapter *adapter) 1, 1000, 20000, 100); } -static void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, - bool tx_enable, bool rx_enable) +void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, + bool tx_enable, bool rx_enable) { u32 flow_setting = 0; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 67877d3b6dd9..8438c3dbcf36 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1159,5 +1159,8 @@ u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset); void lan743x_csr_write(struct lan743x_adapter *adapter, int offset, u32 data); int lan743x_hs_syslock_acquire(struct lan743x_adapter *adapter, u16 timeout); void lan743x_hs_syslock_release(struct lan743x_adapter *adapter); +void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, + bool tx_enable, bool rx_enable); +int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr); #endif /* _LAN743X_H */ diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index da3ea905adbb..39e1066ecd5f 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -339,59 +339,18 @@ static int lan743x_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) struct lan743x_adapter *adapter = container_of(ptp, struct lan743x_adapter, ptp); u32 lan743x_rate_adj = 0; - bool positive = true; - u64 u64_delta = 0; + u64 u64_delta; if ((scaled_ppm < (-LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM)) || scaled_ppm > LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM) { return -EINVAL; } - if (scaled_ppm > 0) { - u64_delta = (u64)scaled_ppm; - positive = true; - } else { - u64_delta = (u64)(-scaled_ppm); - positive = false; - } - u64_delta = (u64_delta << 19); - lan743x_rate_adj = div_u64(u64_delta, 1000000); - - if (positive) - lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_; - - lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ, - lan743x_rate_adj); - - return 0; -} - -static int lan743x_ptpci_adjfreq(struct ptp_clock_info *ptpci, s32 delta_ppb) -{ - struct lan743x_ptp *ptp = - container_of(ptpci, struct lan743x_ptp, ptp_clock_info); - struct lan743x_adapter *adapter = - container_of(ptp, struct lan743x_adapter, ptp); - u32 lan743x_rate_adj = 0; - bool positive = true; - u32 u32_delta = 0; - u64 u64_delta = 0; - if ((delta_ppb < (-LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB)) || - delta_ppb > LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB) { - return -EINVAL; - } - if (delta_ppb > 0) { - u32_delta = (u32)delta_ppb; - positive = true; - } else { - u32_delta = (u32)(-delta_ppb); - positive = false; - } - u64_delta = (((u64)u32_delta) << 35); - lan743x_rate_adj = div_u64(u64_delta, 1000000000); - - if (positive) - lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_; + /* diff_by_scaled_ppm returns true if the difference is negative */ + if (diff_by_scaled_ppm(1ULL << 35, scaled_ppm, &u64_delta)) + lan743x_rate_adj = (u32)u64_delta; + else + lan743x_rate_adj = (u32)u64_delta | PTP_CLOCK_RATE_ADJ_DIR_; lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ, lan743x_rate_adj); @@ -1583,7 +1542,6 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter) ptp->ptp_clock_info.pps = LAN743X_PTP_N_PPS; ptp->ptp_clock_info.pin_config = ptp->pin_config; ptp->ptp_clock_info.adjfine = lan743x_ptpci_adjfine; - ptp->ptp_clock_info.adjfreq = lan743x_ptpci_adjfreq; ptp->ptp_clock_info.adjtime = lan743x_ptpci_adjtime; ptp->ptp_clock_info.gettime64 = lan743x_ptpci_gettime64; ptp->ptp_clock_info.getcrosststamp = NULL; diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig index 49e1464a4313..8bcd60f17d6d 100644 --- a/drivers/net/ethernet/microchip/lan966x/Kconfig +++ b/drivers/net/ethernet/microchip/lan966x/Kconfig @@ -7,5 +7,7 @@ config LAN966X_SWITCH depends on BRIDGE || BRIDGE=n select PHYLINK select PACKING + select PAGE_POOL + select VCAP help This driver supports the Lan966x network switch device. diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 962f7c5f9e7d..56afd694f3c7 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -11,4 +11,9 @@ lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_ptp.o lan966x_fdma.o lan966x_lag.o \ lan966x_tc.o lan966x_mqprio.o lan966x_taprio.o \ lan966x_tbf.o lan966x_cbs.o lan966x_ets.o \ - lan966x_tc_matchall.o lan966x_police.o lan966x_mirror.o + lan966x_tc_matchall.o lan966x_police.o lan966x_mirror.o \ + lan966x_xdp.o lan966x_vcap_impl.o lan966x_vcap_ag_api.o \ + lan966x_tc_flower.o lan966x_goto.o + +# Provide include files +ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index e6948939ccc2..5314c064ceae 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0+ +#include <linux/bpf.h> +#include <linux/filter.h> + #include "lan966x_main.h" static int lan966x_fdma_channel_active(struct lan966x *lan966x) @@ -10,50 +13,39 @@ static int lan966x_fdma_channel_active(struct lan966x *lan966x) static struct page *lan966x_fdma_rx_alloc_page(struct lan966x_rx *rx, struct lan966x_db *db) { - struct lan966x *lan966x = rx->lan966x; - dma_addr_t dma_addr; struct page *page; - page = dev_alloc_pages(rx->page_order); + page = page_pool_dev_alloc_pages(rx->page_pool); if (unlikely(!page)) return NULL; - dma_addr = dma_map_page(lan966x->dev, page, 0, - PAGE_SIZE << rx->page_order, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(lan966x->dev, dma_addr))) - goto free_page; - - db->dataptr = dma_addr; + db->dataptr = page_pool_get_dma_addr(page) + XDP_PACKET_HEADROOM; return page; - -free_page: - __free_pages(page, rx->page_order); - return NULL; } static void lan966x_fdma_rx_free_pages(struct lan966x_rx *rx) { - struct lan966x *lan966x = rx->lan966x; - struct lan966x_rx_dcb *dcb; - struct lan966x_db *db; int i, j; for (i = 0; i < FDMA_DCB_MAX; ++i) { - dcb = &rx->dcbs[i]; - - for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j) { - db = &dcb->db[j]; - dma_unmap_single(lan966x->dev, - (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, - DMA_FROM_DEVICE); - __free_pages(rx->page[i][j], rx->page_order); - } + for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j) + page_pool_put_full_page(rx->page_pool, + rx->page[i][j], false); } } +static void lan966x_fdma_rx_free_page(struct lan966x_rx *rx) +{ + struct page *page; + + page = rx->page[rx->dcb_index][rx->db_index]; + if (unlikely(!page)) + return; + + page_pool_recycle_direct(rx->page_pool, page); +} + static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx, struct lan966x_rx_dcb *dcb, u64 nextptr) @@ -73,6 +65,41 @@ static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx, rx->last_entry = dcb; } +static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx) +{ + struct lan966x *lan966x = rx->lan966x; + struct page_pool_params pp_params = { + .order = rx->page_order, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = FDMA_DCB_MAX, + .nid = NUMA_NO_NODE, + .dev = lan966x->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = XDP_PACKET_HEADROOM, + .max_len = rx->max_mtu - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + }; + + if (lan966x_xdp_present(lan966x)) + pp_params.dma_dir = DMA_BIDIRECTIONAL; + + rx->page_pool = page_pool_create(&pp_params); + + for (int i = 0; i < lan966x->num_phys_ports; ++i) { + struct lan966x_port *port; + + if (!lan966x->ports[i]) + continue; + + port = lan966x->ports[i]; + xdp_rxq_info_unreg_mem_model(&port->xdp_rxq); + xdp_rxq_info_reg_mem_model(&port->xdp_rxq, MEM_TYPE_PAGE_POOL, + rx->page_pool); + } + + return PTR_ERR_OR_ZERO(rx->page_pool); +} + static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) { struct lan966x *lan966x = rx->lan966x; @@ -82,6 +109,9 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) int i, j; int size; + if (lan966x_fdma_rx_alloc_page_pool(rx)) + return PTR_ERR(rx->page_pool); + /* calculate how many pages are needed to allocate the dcbs */ size = sizeof(struct lan966x_rx_dcb) * FDMA_DCB_MAX; size = ALIGN(size, PAGE_SIZE); @@ -116,6 +146,12 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) return 0; } +static void lan966x_fdma_rx_advance_dcb(struct lan966x_rx *rx) +{ + rx->dcb_index++; + rx->dcb_index &= FDMA_DCB_MAX - 1; +} + static void lan966x_fdma_rx_free(struct lan966x_rx *rx) { struct lan966x *lan966x = rx->lan966x; @@ -355,11 +391,14 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight) { struct lan966x_tx *tx = &lan966x->tx; struct lan966x_tx_dcb_buf *dcb_buf; + struct xdp_frame_bulk bq; struct lan966x_db *db; unsigned long flags; bool clear = false; int i; + xdp_frame_bulk_init(&bq); + spin_lock_irqsave(&lan966x->tx_lock, flags); for (i = 0; i < FDMA_DCB_MAX; ++i) { dcb_buf = &tx->dcbs_buf[i]; @@ -372,19 +411,35 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight) continue; dcb_buf->dev->stats.tx_packets++; - dcb_buf->dev->stats.tx_bytes += dcb_buf->skb->len; + dcb_buf->dev->stats.tx_bytes += dcb_buf->len; dcb_buf->used = false; - dma_unmap_single(lan966x->dev, - dcb_buf->dma_addr, - dcb_buf->skb->len, - DMA_TO_DEVICE); - if (!dcb_buf->ptp) - dev_kfree_skb_any(dcb_buf->skb); + if (dcb_buf->use_skb) { + dma_unmap_single(lan966x->dev, + dcb_buf->dma_addr, + dcb_buf->len, + DMA_TO_DEVICE); + + if (!dcb_buf->ptp) + napi_consume_skb(dcb_buf->data.skb, weight); + } else { + if (dcb_buf->xdp_ndo) + dma_unmap_single(lan966x->dev, + dcb_buf->dma_addr, + dcb_buf->len, + DMA_TO_DEVICE); + + if (dcb_buf->xdp_ndo) + xdp_return_frame_bulk(dcb_buf->data.xdpf, &bq); + else + xdp_return_frame_rx_napi(dcb_buf->data.xdpf); + } clear = true; } + xdp_flush_frame_bulk(&bq); + if (clear) lan966x_fdma_wakeup_netdev(lan966x); @@ -403,40 +458,61 @@ static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx) return true; } -static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) +static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port) { struct lan966x *lan966x = rx->lan966x; - u64 src_port, timestamp; + struct lan966x_port *port; struct lan966x_db *db; - struct sk_buff *skb; struct page *page; - /* Get the received frame and unmap it */ db = &rx->dcbs[rx->dcb_index].db[rx->db_index]; page = rx->page[rx->dcb_index][rx->db_index]; + if (unlikely(!page)) + return FDMA_ERROR; - dma_sync_single_for_cpu(lan966x->dev, (dma_addr_t)db->dataptr, + dma_sync_single_for_cpu(lan966x->dev, + (dma_addr_t)db->dataptr + XDP_PACKET_HEADROOM, FDMA_DCB_STATUS_BLOCKL(db->status), DMA_FROM_DEVICE); + lan966x_ifh_get_src_port(page_address(page) + XDP_PACKET_HEADROOM, + src_port); + if (WARN_ON(*src_port >= lan966x->num_phys_ports)) + return FDMA_ERROR; + + port = lan966x->ports[*src_port]; + if (!lan966x_xdp_port_present(port)) + return FDMA_PASS; + + return lan966x_xdp_run(port, page, FDMA_DCB_STATUS_BLOCKL(db->status)); +} + +static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx, + u64 src_port) +{ + struct lan966x *lan966x = rx->lan966x; + struct lan966x_db *db; + struct sk_buff *skb; + struct page *page; + u64 timestamp; + + /* Get the received frame and unmap it */ + db = &rx->dcbs[rx->dcb_index].db[rx->db_index]; + page = rx->page[rx->dcb_index][rx->db_index]; + skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order); if (unlikely(!skb)) - goto unmap_page; + goto free_page; + + skb_mark_for_recycle(skb); + skb_reserve(skb, XDP_PACKET_HEADROOM); skb_put(skb, FDMA_DCB_STATUS_BLOCKL(db->status)); - lan966x_ifh_get_src_port(skb->data, &src_port); lan966x_ifh_get_timestamp(skb->data, ×tamp); - if (WARN_ON(src_port >= lan966x->num_phys_ports)) - goto free_skb; - - dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - skb->dev = lan966x->ports[src_port]->dev; - skb_pull(skb, IFH_LEN * sizeof(u32)); + skb_pull(skb, IFH_LEN_BYTES); if (likely(!(skb->dev->features & NETIF_F_RXFCS))) skb_trim(skb, skb->len - ETH_FCS_LEN); @@ -457,13 +533,8 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) return skb; -free_skb: - kfree_skb(skb); -unmap_page: - dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - __free_pages(page, rx->page_order); +free_page: + page_pool_recycle_direct(rx->page_pool, page); return NULL; } @@ -475,9 +546,11 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight) int dcb_reload = rx->dcb_index; struct lan966x_rx_dcb *old_dcb; struct lan966x_db *db; + bool redirect = false; struct sk_buff *skb; struct page *page; int counter = 0; + u64 src_port; u64 nextptr; lan966x_fdma_tx_clear_buf(lan966x, weight); @@ -487,19 +560,36 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight) if (!lan966x_fdma_rx_more_frames(rx)) break; - skb = lan966x_fdma_rx_get_frame(rx); + counter++; - rx->page[rx->dcb_index][rx->db_index] = NULL; - rx->dcb_index++; - rx->dcb_index &= FDMA_DCB_MAX - 1; + switch (lan966x_fdma_rx_check_frame(rx, &src_port)) { + case FDMA_PASS: + break; + case FDMA_ERROR: + lan966x_fdma_rx_free_page(rx); + lan966x_fdma_rx_advance_dcb(rx); + goto allocate_new; + case FDMA_REDIRECT: + redirect = true; + fallthrough; + case FDMA_TX: + lan966x_fdma_rx_advance_dcb(rx); + continue; + case FDMA_DROP: + lan966x_fdma_rx_free_page(rx); + lan966x_fdma_rx_advance_dcb(rx); + continue; + } + skb = lan966x_fdma_rx_get_frame(rx, src_port); + lan966x_fdma_rx_advance_dcb(rx); if (!skb) - break; + goto allocate_new; napi_gro_receive(&lan966x->napi, skb); - counter++; } +allocate_new: /* Allocate new pages and map them */ while (dcb_reload != rx->dcb_index) { db = &rx->dcbs[dcb_reload].db[rx->db_index]; @@ -521,6 +611,9 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight) if (counter < weight && napi_complete_done(napi, counter)) lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA); + if (redirect) + xdp_do_flush(); + return counter; } @@ -565,14 +658,139 @@ static int lan966x_fdma_get_next_dcb(struct lan966x_tx *tx) return -1; } +static void lan966x_fdma_tx_setup_dcb(struct lan966x_tx *tx, + int next_to_use, int len, + dma_addr_t dma_addr) +{ + struct lan966x_tx_dcb *next_dcb; + struct lan966x_db *next_db; + + next_dcb = &tx->dcbs[next_to_use]; + next_dcb->nextptr = FDMA_DCB_INVALID_DATA; + + next_db = &next_dcb->db[0]; + next_db->dataptr = dma_addr; + next_db->status = FDMA_DCB_STATUS_SOF | + FDMA_DCB_STATUS_EOF | + FDMA_DCB_STATUS_INTR | + FDMA_DCB_STATUS_BLOCKO(0) | + FDMA_DCB_STATUS_BLOCKL(len); +} + +static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use) +{ + struct lan966x *lan966x = tx->lan966x; + struct lan966x_tx_dcb *dcb; + + if (likely(lan966x->tx.activated)) { + /* Connect current dcb to the next db */ + dcb = &tx->dcbs[tx->last_in_use]; + dcb->nextptr = tx->dma + (next_to_use * + sizeof(struct lan966x_tx_dcb)); + + lan966x_fdma_tx_reload(tx); + } else { + /* Because it is first time, then just activate */ + lan966x->tx.activated = true; + lan966x_fdma_tx_activate(tx); + } + + /* Move to next dcb because this last in use */ + tx->last_in_use = next_to_use; +} + +int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, + struct xdp_frame *xdpf, + struct page *page, + bool dma_map) +{ + struct lan966x *lan966x = port->lan966x; + struct lan966x_tx_dcb_buf *next_dcb_buf; + struct lan966x_tx *tx = &lan966x->tx; + dma_addr_t dma_addr; + int next_to_use; + __be32 *ifh; + int ret = 0; + + spin_lock(&lan966x->tx_lock); + + /* Get next index */ + next_to_use = lan966x_fdma_get_next_dcb(tx); + if (next_to_use < 0) { + netif_stop_queue(port->dev); + ret = NETDEV_TX_BUSY; + goto out; + } + + /* Generate new IFH */ + if (dma_map) { + if (xdpf->headroom < IFH_LEN_BYTES) { + ret = NETDEV_TX_OK; + goto out; + } + + ifh = xdpf->data - IFH_LEN_BYTES; + memset(ifh, 0x0, sizeof(__be32) * IFH_LEN); + lan966x_ifh_set_bypass(ifh, 1); + lan966x_ifh_set_port(ifh, BIT_ULL(port->chip_port)); + + dma_addr = dma_map_single(lan966x->dev, + xdpf->data - IFH_LEN_BYTES, + xdpf->len + IFH_LEN_BYTES, + DMA_TO_DEVICE); + if (dma_mapping_error(lan966x->dev, dma_addr)) { + ret = NETDEV_TX_OK; + goto out; + } + + /* Setup next dcb */ + lan966x_fdma_tx_setup_dcb(tx, next_to_use, + xdpf->len + IFH_LEN_BYTES, + dma_addr); + } else { + ifh = page_address(page) + XDP_PACKET_HEADROOM; + memset(ifh, 0x0, sizeof(__be32) * IFH_LEN); + lan966x_ifh_set_bypass(ifh, 1); + lan966x_ifh_set_port(ifh, BIT_ULL(port->chip_port)); + + dma_addr = page_pool_get_dma_addr(page); + dma_sync_single_for_device(lan966x->dev, + dma_addr + XDP_PACKET_HEADROOM, + xdpf->len + IFH_LEN_BYTES, + DMA_TO_DEVICE); + + /* Setup next dcb */ + lan966x_fdma_tx_setup_dcb(tx, next_to_use, + xdpf->len + IFH_LEN_BYTES, + dma_addr + XDP_PACKET_HEADROOM); + } + + /* Fill up the buffer */ + next_dcb_buf = &tx->dcbs_buf[next_to_use]; + next_dcb_buf->use_skb = false; + next_dcb_buf->data.xdpf = xdpf; + next_dcb_buf->xdp_ndo = dma_map; + next_dcb_buf->len = xdpf->len + IFH_LEN_BYTES; + next_dcb_buf->dma_addr = dma_addr; + next_dcb_buf->used = true; + next_dcb_buf->ptp = false; + next_dcb_buf->dev = port->dev; + + /* Start the transmission */ + lan966x_fdma_tx_start(tx, next_to_use); + +out: + spin_unlock(&lan966x->tx_lock); + + return ret; +} + int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) { struct lan966x_port *port = netdev_priv(dev); struct lan966x *lan966x = port->lan966x; struct lan966x_tx_dcb_buf *next_dcb_buf; - struct lan966x_tx_dcb *next_dcb, *dcb; struct lan966x_tx *tx = &lan966x->tx; - struct lan966x_db *next_db; int needed_headroom; int needed_tailroom; dma_addr_t dma_addr; @@ -592,7 +810,7 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) } /* skb processing */ - needed_headroom = max_t(int, IFH_LEN * sizeof(u32) - skb_headroom(skb), 0); + needed_headroom = max_t(int, IFH_LEN_BYTES - skb_headroom(skb), 0); needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0); if (needed_headroom || needed_tailroom || skb_header_cloned(skb)) { err = pskb_expand_head(skb, needed_headroom, needed_tailroom, @@ -605,8 +823,8 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) } skb_tx_timestamp(skb); - skb_push(skb, IFH_LEN * sizeof(u32)); - memcpy(skb->data, ifh, IFH_LEN * sizeof(u32)); + skb_push(skb, IFH_LEN_BYTES); + memcpy(skb->data, ifh, IFH_LEN_BYTES); skb_put(skb, 4); dma_addr = dma_map_single(lan966x->dev, skb->data, skb->len, @@ -618,20 +836,14 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) } /* Setup next dcb */ - next_dcb = &tx->dcbs[next_to_use]; - next_dcb->nextptr = FDMA_DCB_INVALID_DATA; - - next_db = &next_dcb->db[0]; - next_db->dataptr = dma_addr; - next_db->status = FDMA_DCB_STATUS_SOF | - FDMA_DCB_STATUS_EOF | - FDMA_DCB_STATUS_INTR | - FDMA_DCB_STATUS_BLOCKO(0) | - FDMA_DCB_STATUS_BLOCKL(skb->len); + lan966x_fdma_tx_setup_dcb(tx, next_to_use, skb->len, dma_addr); /* Fill up the buffer */ next_dcb_buf = &tx->dcbs_buf[next_to_use]; - next_dcb_buf->skb = skb; + next_dcb_buf->use_skb = true; + next_dcb_buf->data.skb = skb; + next_dcb_buf->xdp_ndo = false; + next_dcb_buf->len = skb->len; next_dcb_buf->dma_addr = dma_addr; next_dcb_buf->used = true; next_dcb_buf->ptp = false; @@ -641,21 +853,8 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) next_dcb_buf->ptp = true; - if (likely(lan966x->tx.activated)) { - /* Connect current dcb to the next db */ - dcb = &tx->dcbs[tx->last_in_use]; - dcb->nextptr = tx->dma + (next_to_use * - sizeof(struct lan966x_tx_dcb)); - - lan966x_fdma_tx_reload(tx); - } else { - /* Because it is first time, then just activate */ - lan966x->tx.activated = true; - lan966x_fdma_tx_activate(tx); - } - - /* Move to next dcb because this last in use */ - tx->last_in_use = next_to_use; + /* Start the transmission */ + lan966x_fdma_tx_start(tx, next_to_use); return NETDEV_TX_OK; @@ -696,6 +895,7 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x) static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) { + struct page_pool *page_pool; dma_addr_t rx_dma; void *rx_dcbs; u32 size; @@ -704,6 +904,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) /* Store these for later to free them */ rx_dma = lan966x->rx.dma; rx_dcbs = lan966x->rx.dcbs; + page_pool = lan966x->rx.page_pool; napi_synchronize(&lan966x->napi); napi_disable(&lan966x->napi); @@ -712,6 +913,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) lan966x_fdma_rx_disable(&lan966x->rx); lan966x_fdma_rx_free_pages(&lan966x->rx); lan966x->rx.page_order = round_up(new_mtu, PAGE_SIZE) / PAGE_SIZE - 1; + lan966x->rx.max_mtu = new_mtu; err = lan966x_fdma_rx_alloc(&lan966x->rx); if (err) goto restore; @@ -721,11 +923,14 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) size = ALIGN(size, PAGE_SIZE); dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma); + page_pool_destroy(page_pool); + lan966x_fdma_wakeup_netdev(lan966x); napi_enable(&lan966x->napi); return err; restore: + lan966x->rx.page_pool = page_pool; lan966x->rx.dma = rx_dma; lan966x->rx.dcbs = rx_dcbs; lan966x_fdma_rx_start(&lan966x->rx); @@ -733,21 +938,20 @@ restore: return err; } -int lan966x_fdma_change_mtu(struct lan966x *lan966x) +static int lan966x_fdma_get_max_frame(struct lan966x *lan966x) +{ + return lan966x_fdma_get_max_mtu(lan966x) + + IFH_LEN_BYTES + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + VLAN_HLEN * 2 + + XDP_PACKET_HEADROOM; +} + +static int __lan966x_fdma_reload(struct lan966x *lan966x, int max_mtu) { - int max_mtu; int err; u32 val; - max_mtu = lan966x_fdma_get_max_mtu(lan966x); - max_mtu += IFH_LEN * sizeof(u32); - max_mtu += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - max_mtu += VLAN_HLEN * 2; - - if (round_up(max_mtu, PAGE_SIZE) / PAGE_SIZE - 1 == - lan966x->rx.page_order) - return 0; - /* Disable the CPU port */ lan_rmw(QSYS_SW_PORT_MODE_PORT_ENA_SET(0), QSYS_SW_PORT_MODE_PORT_ENA, @@ -773,6 +977,25 @@ int lan966x_fdma_change_mtu(struct lan966x *lan966x) return err; } +int lan966x_fdma_change_mtu(struct lan966x *lan966x) +{ + int max_mtu; + + max_mtu = lan966x_fdma_get_max_frame(lan966x); + if (max_mtu == lan966x->rx.max_mtu) + return 0; + + return __lan966x_fdma_reload(lan966x, max_mtu); +} + +int lan966x_fdma_reload_page_pool(struct lan966x *lan966x) +{ + int max_mtu; + + max_mtu = lan966x_fdma_get_max_frame(lan966x); + return __lan966x_fdma_reload(lan966x, max_mtu); +} + void lan966x_fdma_netdev_init(struct lan966x *lan966x, struct net_device *dev) { if (lan966x->fdma_ndev) @@ -800,6 +1023,7 @@ int lan966x_fdma_init(struct lan966x *lan966x) lan966x->rx.lan966x = lan966x; lan966x->rx.channel_id = FDMA_XTR_CHANNEL; + lan966x->rx.max_mtu = lan966x_fdma_get_max_frame(lan966x); lan966x->tx.lan966x = lan966x; lan966x->tx.channel_id = FDMA_INJ_CHANNEL; lan966x->tx.last_in_use = -1; @@ -832,5 +1056,6 @@ void lan966x_fdma_deinit(struct lan966x *lan966x) lan966x_fdma_rx_free_pages(&lan966x->rx); lan966x_fdma_rx_free(&lan966x->rx); + page_pool_destroy(lan966x->rx.page_pool); lan966x_fdma_tx_free(&lan966x->tx); } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c b/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c new file mode 100644 index 000000000000..bf0cfe24a8fc --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "lan966x_main.h" +#include "vcap_api_client.h" + +int lan966x_goto_port_add(struct lan966x_port *port, + struct flow_action_entry *act, + unsigned long goto_id, + struct netlink_ext_ack *extack) +{ + struct lan966x *lan966x = port->lan966x; + int err; + + err = vcap_enable_lookups(lan966x->vcap_ctrl, port->dev, + act->chain_index, goto_id, + true); + if (err == -EFAULT) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported goto chain"); + return -EOPNOTSUPP; + } + + if (err == -EADDRINUSE) { + NL_SET_ERR_MSG_MOD(extack, "VCAP already enabled"); + return -EOPNOTSUPP; + } + + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Could not enable VCAP lookups"); + return err; + } + + port->tc.goto_id = goto_id; + + return 0; +} + +int lan966x_goto_port_del(struct lan966x_port *port, + unsigned long goto_id, + struct netlink_ext_ack *extack) +{ + struct lan966x *lan966x = port->lan966x; + int err; + + err = vcap_enable_lookups(lan966x->vcap_ctrl, port->dev, 0, + goto_id, false); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Could not disable VCAP lookups"); + return err; + } + + port->tc.goto_id = 0; + + return 0; +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h index ca3314789d18..f3b1e0d31826 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h @@ -8,6 +8,7 @@ */ #define IFH_LEN 7 +#define IFH_LEN_BYTES (IFH_LEN * sizeof(u32)) /* Timestamp for frame */ #define IFH_POS_TIMESTAMP 192 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 20ee5b28f70a..cadde20505ba 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -47,6 +47,9 @@ static const struct lan966x_main_io_resource lan966x_main_iomap[] = { { TARGET_PTP, 0xc000, 1 }, /* 0xe200c000 */ { TARGET_CHIP_TOP, 0x10000, 1 }, /* 0xe2010000 */ { TARGET_REW, 0x14000, 1 }, /* 0xe2014000 */ + { TARGET_VCAP, 0x18000, 1 }, /* 0xe2018000 */ + { TARGET_VCAP + 1, 0x20000, 1 }, /* 0xe2020000 */ + { TARGET_VCAP + 2, 0x24000, 1 }, /* 0xe2024000 */ { TARGET_SYS, 0x28000, 1 }, /* 0xe2028000 */ { TARGET_DEV, 0x34000, 1 }, /* 0xe2034000 */ { TARGET_DEV + 1, 0x38000, 1 }, /* 0xe2038000 */ @@ -302,13 +305,13 @@ err: return NETDEV_TX_BUSY; } -static void lan966x_ifh_set_bypass(void *ifh, u64 bypass) +void lan966x_ifh_set_bypass(void *ifh, u64 bypass) { packing(ifh, &bypass, IFH_POS_BYPASS + IFH_WID_BYPASS - 1, IFH_POS_BYPASS, IFH_LEN * 4, PACK, 0); } -static void lan966x_ifh_set_port(void *ifh, u64 bypass) +void lan966x_ifh_set_port(void *ifh, u64 bypass) { packing(ifh, &bypass, IFH_POS_DSTS + IFH_WID_DSTS - 1, IFH_POS_DSTS, IFH_LEN * 4, PACK, 0); @@ -440,11 +443,22 @@ static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct lan966x_port *port = netdev_priv(dev); + int err; + + if (cmd == SIOCSHWTSTAMP) { + err = lan966x_ptp_setup_traps(port, ifr); + if (err) + return err; + } if (!phy_has_hwtstamp(dev->phydev) && port->lan966x->ptp) { switch (cmd) { case SIOCSHWTSTAMP: - return lan966x_ptp_hwtstamp_set(port, ifr); + err = lan966x_ptp_hwtstamp_set(port, ifr); + if (err) + lan966x_ptp_del_traps(port); + + return err; case SIOCGHWTSTAMP: return lan966x_ptp_hwtstamp_get(port, ifr); } @@ -453,7 +467,11 @@ static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr, if (!dev->phydev) return -ENODEV; - return phy_mii_ioctl(dev->phydev, ifr, cmd); + err = phy_mii_ioctl(dev->phydev, ifr, cmd); + if (err && cmd == SIOCSHWTSTAMP) + lan966x_ptp_del_traps(port); + + return err; } static const struct net_device_ops lan966x_port_netdev_ops = { @@ -468,6 +486,8 @@ static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_get_port_parent_id = lan966x_port_get_parent_id, .ndo_eth_ioctl = lan966x_port_ioctl, .ndo_setup_tc = lan966x_tc_setup, + .ndo_bpf = lan966x_xdp, + .ndo_xdp_xmit = lan966x_xdp_xmit, }; bool lan966x_netdevice_check(const struct net_device *dev) @@ -694,6 +714,7 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) if (port->dev) unregister_netdev(port->dev); + lan966x_xdp_port_deinit(port); if (lan966x->fdma && lan966x->fdma_ndev == port->dev) lan966x_fdma_netdev_deinit(lan966x, port->dev); @@ -760,7 +781,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC; - dev->needed_headroom = IFH_LEN * sizeof(u32); + dev->needed_headroom = IFH_LEN_BYTES; eth_hw_addr_gen(dev, lan966x->base_mac, p + 1); @@ -1136,6 +1157,9 @@ static int lan966x_probe(struct platform_device *pdev) lan966x->ports[p]->serdes = serdes; lan966x_port_init(lan966x->ports[p]); + err = lan966x_xdp_port_init(lan966x->ports[p]); + if (err) + goto cleanup_ports; } lan966x_mdb_init(lan966x); @@ -1151,8 +1175,15 @@ static int lan966x_probe(struct platform_device *pdev) if (err) goto cleanup_ptp; + err = lan966x_vcap_init(lan966x); + if (err) + goto cleanup_fdma; + return 0; +cleanup_fdma: + lan966x_fdma_deinit(lan966x); + cleanup_ptp: lan966x_ptp_deinit(lan966x); @@ -1176,6 +1207,7 @@ static int lan966x_remove(struct platform_device *pdev) struct lan966x *lan966x = platform_get_drvdata(pdev); lan966x_taprio_deinit(lan966x); + lan966x_vcap_deinit(lan966x); lan966x_fdma_deinit(lan966x); lan966x_cleanup_ports(lan966x); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 4ec33999e4df..3491f1961835 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -9,6 +9,7 @@ #include <linux/phy.h> #include <linux/phylink.h> #include <linux/ptp_clock_kernel.h> +#include <net/page_pool.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/switchdev.h> @@ -87,6 +88,10 @@ #define SE_IDX_QUEUE 0 /* 0-79 : Queue scheduler elements */ #define SE_IDX_PORT 80 /* 80-89 : Port schedular elements */ +#define LAN966X_VCAP_CID_IS2_L0 VCAP_CID_INGRESS_STAGE2_L0 /* IS2 lookup 0 */ +#define LAN966X_VCAP_CID_IS2_L1 VCAP_CID_INGRESS_STAGE2_L1 /* IS2 lookup 1 */ +#define LAN966X_VCAP_CID_IS2_MAX (VCAP_CID_INGRESS_STAGE2_L2 - 1) /* IS2 Max */ + /* MAC table entry types. * ENTRYTYPE_NORMAL is subject to aging. * ENTRYTYPE_LOCKED is not subject to aging. @@ -100,6 +105,29 @@ enum macaccess_entry_type { ENTRYTYPE_MACV6, }; +/* FDMA return action codes for checking if the frame is valid + * FDMA_PASS, frame is valid and can be used + * FDMA_ERROR, something went wrong, stop getting more frames + * FDMA_DROP, frame is dropped, but continue to get more frames + * FDMA_TX, frame is given to TX, but continue to get more frames + * FDMA_REDIRECT, frame is given to TX, but continue to get more frames + */ +enum lan966x_fdma_action { + FDMA_PASS = 0, + FDMA_ERROR, + FDMA_DROP, + FDMA_TX, + FDMA_REDIRECT, +}; + +/* Controls how PORT_MASK is applied */ +enum LAN966X_PORT_MASK_MODE { + LAN966X_PMM_NO_ACTION, + LAN966X_PMM_REPLACE, + LAN966X_PMM_FORWARDING, + LAN966X_PMM_REDIRECT, +}; + struct lan966x_port; struct lan966x_db { @@ -150,15 +178,28 @@ struct lan966x_rx { */ u8 page_order; + /* Represents the max size frame that it can receive to the CPU. This + * includes the IFH + VLAN tags + frame + skb_shared_info + */ + u32 max_mtu; + u8 channel_id; + + struct page_pool *page_pool; }; struct lan966x_tx_dcb_buf { - struct net_device *dev; - struct sk_buff *skb; dma_addr_t dma_addr; - bool used; - bool ptp; + struct net_device *dev; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + } data; + u32 len; + u32 used : 1; + u32 ptp : 1; + u32 use_skb : 1; + u32 xdp_ndo : 1; }; struct lan966x_tx { @@ -271,6 +312,9 @@ struct lan966x { struct lan966x_port *mirror_monitor; u32 mirror_mask[2]; u32 mirror_count; + + /* vcap */ + struct vcap_control *vcap_ctrl; }; struct lan966x_port_config { @@ -288,6 +332,7 @@ struct lan966x_port_tc { unsigned long police_id; unsigned long ingress_mirror_id; unsigned long egress_mirror_id; + unsigned long goto_id; struct flow_stats police_stat; struct flow_stats mirror_stat; }; @@ -320,6 +365,9 @@ struct lan966x_port { enum netdev_lag_hash hash_type; struct lan966x_port_tc tc; + + struct bpf_prog *xdp_prog; + struct xdp_rxq_info xdp_rxq; }; extern const struct phylink_mac_ops lan966x_phylink_mac_ops; @@ -337,6 +385,8 @@ bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, struct sk_buff *skb); void lan966x_ifh_get_src_port(void *ifh, u64 *src_port); void lan966x_ifh_get_timestamp(void *ifh, u64 *timestamp); +void lan966x_ifh_set_bypass(void *ifh, u64 bypass); +void lan966x_ifh_set_port(void *ifh, u64 bypass); void lan966x_stats_get(struct net_device *dev, struct rtnl_link_stats64 *stats); @@ -435,14 +485,21 @@ irqreturn_t lan966x_ptp_irq_handler(int irq, void *args); irqreturn_t lan966x_ptp_ext_irq_handler(int irq, void *args); u32 lan966x_ptp_get_period_ps(void); int lan966x_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); +int lan966x_ptp_setup_traps(struct lan966x_port *port, struct ifreq *ifr); +int lan966x_ptp_del_traps(struct lan966x_port *port); int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev); +int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, + struct xdp_frame *frame, + struct page *page, + bool dma_map); int lan966x_fdma_change_mtu(struct lan966x *lan966x); void lan966x_fdma_netdev_init(struct lan966x *lan966x, struct net_device *dev); void lan966x_fdma_netdev_deinit(struct lan966x *lan966x, struct net_device *dev); int lan966x_fdma_init(struct lan966x *lan966x); void lan966x_fdma_deinit(struct lan966x *lan966x); irqreturn_t lan966x_fdma_irq_handler(int irq, void *args); +int lan966x_fdma_reload_page_pool(struct lan966x *lan966x); int lan966x_lag_port_join(struct lan966x_port *port, struct net_device *brport_dev, @@ -527,6 +584,36 @@ void lan966x_mirror_port_stats(struct lan966x_port *port, struct flow_stats *stats, bool ingress); +int lan966x_xdp_port_init(struct lan966x_port *port); +void lan966x_xdp_port_deinit(struct lan966x_port *port); +int lan966x_xdp(struct net_device *dev, struct netdev_bpf *xdp); +int lan966x_xdp_run(struct lan966x_port *port, + struct page *page, + u32 data_len); +int lan966x_xdp_xmit(struct net_device *dev, + int n, + struct xdp_frame **frames, + u32 flags); +bool lan966x_xdp_present(struct lan966x *lan966x); +static inline bool lan966x_xdp_port_present(struct lan966x_port *port) +{ + return !!port->xdp_prog; +} + +int lan966x_vcap_init(struct lan966x *lan966x); +void lan966x_vcap_deinit(struct lan966x *lan966x); + +int lan966x_tc_flower(struct lan966x_port *port, + struct flow_cls_offload *f); + +int lan966x_goto_port_add(struct lan966x_port *port, + struct flow_action_entry *act, + unsigned long goto_id, + struct netlink_ext_ack *extack); +int lan966x_goto_port_del(struct lan966x_port *port, + unsigned long goto_id, + struct netlink_ext_ack *extack); + static inline void __iomem *lan_addr(void __iomem *base[], int id, int tinst, int tcnt, int gbase, int ginst, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index e4ac59480514..c5f9803e6e63 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -5,7 +5,6 @@ #include <linux/device.h> #include <linux/netdevice.h> #include <linux/phy/phy.h> -#include <linux/sfp.h> #include "lan966x_main.h" @@ -125,7 +124,6 @@ static void lan966x_pcs_aneg_restart(struct phylink_pcs *pcs) } const struct phylink_mac_ops lan966x_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = lan966x_phylink_mac_select, .mac_config = lan966x_phylink_mac_config, .mac_prepare = lan966x_phylink_mac_prepare, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index e5a2bbe064f8..f9ebfaafbebc 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -3,6 +3,8 @@ #include <linux/ptp_classify.h> #include "lan966x_main.h" +#include "vcap_api.h" +#include "vcap_api_client.h" #define LAN966X_MAX_PTP_ID 512 @@ -18,6 +20,17 @@ #define TOD_ACC_PIN 0x7 +/* This represents the base rule ID for the PTP rules that are added in the + * VCAP to trap frames to CPU. This number needs to be bigger than the maximum + * number of entries that can exist in the VCAP. + */ +#define LAN966X_VCAP_PTP_RULE_ID 1000000 +#define LAN966X_VCAP_L2_PTP_TRAP (LAN966X_VCAP_PTP_RULE_ID + 0) +#define LAN966X_VCAP_IPV4_EV_PTP_TRAP (LAN966X_VCAP_PTP_RULE_ID + 1) +#define LAN966X_VCAP_IPV4_GEN_PTP_TRAP (LAN966X_VCAP_PTP_RULE_ID + 2) +#define LAN966X_VCAP_IPV6_EV_PTP_TRAP (LAN966X_VCAP_PTP_RULE_ID + 3) +#define LAN966X_VCAP_IPV6_GEN_PTP_TRAP (LAN966X_VCAP_PTP_RULE_ID + 4) + enum { PTP_PIN_ACTION_IDLE = 0, PTP_PIN_ACTION_LOAD, @@ -35,19 +48,226 @@ static u64 lan966x_ptp_get_nominal_value(void) return 0x304d4873ecade305; } +static int lan966x_ptp_add_trap(struct lan966x_port *port, + int (*add_ptp_key)(struct vcap_rule *vrule, + struct lan966x_port*), + u32 rule_id, + u16 proto) +{ + struct lan966x *lan966x = port->lan966x; + struct vcap_rule *vrule; + int err; + + vrule = vcap_get_rule(lan966x->vcap_ctrl, rule_id); + if (vrule) { + u32 value, mask; + + /* Just modify the ingress port mask and exit */ + vcap_rule_get_key_u32(vrule, VCAP_KF_IF_IGR_PORT_MASK, + &value, &mask); + mask &= ~BIT(port->chip_port); + vcap_rule_mod_key_u32(vrule, VCAP_KF_IF_IGR_PORT_MASK, + value, mask); + + err = vcap_mod_rule(vrule); + goto free_rule; + } + + vrule = vcap_alloc_rule(lan966x->vcap_ctrl, port->dev, + LAN966X_VCAP_CID_IS2_L0, + VCAP_USER_PTP, 0, rule_id); + if (IS_ERR(vrule)) + return PTR_ERR(vrule); + + err = add_ptp_key(vrule, port); + if (err) + goto free_rule; + + err = vcap_set_rule_set_actionset(vrule, VCAP_AFS_BASE_TYPE); + err |= vcap_rule_add_action_bit(vrule, VCAP_AF_CPU_COPY_ENA, VCAP_BIT_1); + err |= vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE, LAN966X_PMM_REPLACE); + err |= vcap_val_rule(vrule, proto); + if (err) + goto free_rule; + + err = vcap_add_rule(vrule); + +free_rule: + /* Free the local copy of the rule */ + vcap_free_rule(vrule); + return err; +} + +static int lan966x_ptp_del_trap(struct lan966x_port *port, + u32 rule_id) +{ + struct lan966x *lan966x = port->lan966x; + struct vcap_rule *vrule; + u32 value, mask; + int err; + + vrule = vcap_get_rule(lan966x->vcap_ctrl, rule_id); + if (!vrule) + return -EEXIST; + + vcap_rule_get_key_u32(vrule, VCAP_KF_IF_IGR_PORT_MASK, &value, &mask); + mask |= BIT(port->chip_port); + + /* No other port requires this trap, so it is safe to remove it */ + if (mask == GENMASK(lan966x->num_phys_ports, 0)) { + err = vcap_del_rule(lan966x->vcap_ctrl, port->dev, rule_id); + goto free_rule; + } + + vcap_rule_mod_key_u32(vrule, VCAP_KF_IF_IGR_PORT_MASK, value, mask); + err = vcap_mod_rule(vrule); + +free_rule: + vcap_free_rule(vrule); + return err; +} + +static int lan966x_ptp_add_l2_key(struct vcap_rule *vrule, + struct lan966x_port *port) +{ + return vcap_rule_add_key_u32(vrule, VCAP_KF_ETYPE, ETH_P_1588, ~0); +} + +static int lan966x_ptp_add_ip_event_key(struct vcap_rule *vrule, + struct lan966x_port *port) +{ + return vcap_rule_add_key_u32(vrule, VCAP_KF_L4_DPORT, PTP_EV_PORT, ~0) || + vcap_rule_add_key_bit(vrule, VCAP_KF_TCP_IS, VCAP_BIT_0); +} + +static int lan966x_ptp_add_ip_general_key(struct vcap_rule *vrule, + struct lan966x_port *port) +{ + return vcap_rule_add_key_u32(vrule, VCAP_KF_L4_DPORT, PTP_GEN_PORT, ~0) || + vcap_rule_add_key_bit(vrule, VCAP_KF_TCP_IS, VCAP_BIT_0); +} + +static int lan966x_ptp_add_l2_rule(struct lan966x_port *port) +{ + return lan966x_ptp_add_trap(port, lan966x_ptp_add_l2_key, + LAN966X_VCAP_L2_PTP_TRAP, ETH_P_ALL); +} + +static int lan966x_ptp_add_ipv4_rules(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_add_trap(port, lan966x_ptp_add_ip_event_key, + LAN966X_VCAP_IPV4_EV_PTP_TRAP, ETH_P_IP); + if (err) + return err; + + err = lan966x_ptp_add_trap(port, lan966x_ptp_add_ip_general_key, + LAN966X_VCAP_IPV4_GEN_PTP_TRAP, ETH_P_IP); + if (err) + lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV4_EV_PTP_TRAP); + + return err; +} + +static int lan966x_ptp_add_ipv6_rules(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_add_trap(port, lan966x_ptp_add_ip_event_key, + LAN966X_VCAP_IPV6_EV_PTP_TRAP, ETH_P_IPV6); + if (err) + return err; + + err = lan966x_ptp_add_trap(port, lan966x_ptp_add_ip_general_key, + LAN966X_VCAP_IPV6_GEN_PTP_TRAP, ETH_P_IPV6); + if (err) + lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV6_EV_PTP_TRAP); + + return err; +} + +static int lan966x_ptp_del_l2_rule(struct lan966x_port *port) +{ + return lan966x_ptp_del_trap(port, LAN966X_VCAP_L2_PTP_TRAP); +} + +static int lan966x_ptp_del_ipv4_rules(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV4_EV_PTP_TRAP); + err |= lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV4_GEN_PTP_TRAP); + + return err; +} + +static int lan966x_ptp_del_ipv6_rules(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV6_EV_PTP_TRAP); + err |= lan966x_ptp_del_trap(port, LAN966X_VCAP_IPV6_GEN_PTP_TRAP); + + return err; +} + +static int lan966x_ptp_add_traps(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_add_l2_rule(port); + if (err) + goto err_l2; + + err = lan966x_ptp_add_ipv4_rules(port); + if (err) + goto err_ipv4; + + err = lan966x_ptp_add_ipv6_rules(port); + if (err) + goto err_ipv6; + + return err; + +err_ipv6: + lan966x_ptp_del_ipv4_rules(port); +err_ipv4: + lan966x_ptp_del_l2_rule(port); +err_l2: + return err; +} + +int lan966x_ptp_del_traps(struct lan966x_port *port) +{ + int err; + + err = lan966x_ptp_del_l2_rule(port); + err |= lan966x_ptp_del_ipv4_rules(port); + err |= lan966x_ptp_del_ipv6_rules(port); + + return err; +} + +int lan966x_ptp_setup_traps(struct lan966x_port *port, struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.rx_filter == HWTSTAMP_FILTER_NONE) + return lan966x_ptp_del_traps(port); + else + return lan966x_ptp_add_traps(port); +} + int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) { struct lan966x *lan966x = port->lan966x; struct hwtstamp_config cfg; struct lan966x_phc *phc; - /* For now don't allow to run ptp on ports that are part of a bridge, - * because in case of transparent clock the HW will still forward the - * frames, so there would be duplicate frames - */ - if (lan966x->bridge_mask & BIT(port->chip_port)) - return -EINVAL; - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h index fb5087fef22e..9767b5a1c958 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h @@ -25,6 +25,7 @@ enum lan966x_target { TARGET_QSYS = 46, TARGET_REW = 47, TARGET_SYS = 52, + TARGET_VCAP = 61, NUM_TARGETS = 66 }; @@ -315,6 +316,69 @@ enum lan966x_target { #define ANA_DROP_CFG_DROP_MC_SMAC_ENA_GET(x)\ FIELD_GET(ANA_DROP_CFG_DROP_MC_SMAC_ENA, x) +/* ANA:PORT:VCAP_S2_CFG */ +#define ANA_VCAP_S2_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 28, 0, 1, 4) + +#define ANA_VCAP_S2_CFG_ISDX_ENA GENMASK(20, 19) +#define ANA_VCAP_S2_CFG_ISDX_ENA_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_ISDX_ENA, x) +#define ANA_VCAP_S2_CFG_ISDX_ENA_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_ISDX_ENA, x) + +#define ANA_VCAP_S2_CFG_UDP_PAYLOAD_ENA GENMASK(18, 17) +#define ANA_VCAP_S2_CFG_UDP_PAYLOAD_ENA_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_UDP_PAYLOAD_ENA, x) +#define ANA_VCAP_S2_CFG_UDP_PAYLOAD_ENA_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_UDP_PAYLOAD_ENA, x) + +#define ANA_VCAP_S2_CFG_ETYPE_PAYLOAD_ENA GENMASK(16, 15) +#define ANA_VCAP_S2_CFG_ETYPE_PAYLOAD_ENA_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_ETYPE_PAYLOAD_ENA, x) +#define ANA_VCAP_S2_CFG_ETYPE_PAYLOAD_ENA_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_ETYPE_PAYLOAD_ENA, x) + +#define ANA_VCAP_S2_CFG_ENA BIT(14) +#define ANA_VCAP_S2_CFG_ENA_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_ENA, x) +#define ANA_VCAP_S2_CFG_ENA_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_ENA, x) + +#define ANA_VCAP_S2_CFG_SNAP_DIS GENMASK(13, 12) +#define ANA_VCAP_S2_CFG_SNAP_DIS_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_SNAP_DIS, x) +#define ANA_VCAP_S2_CFG_SNAP_DIS_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_SNAP_DIS, x) + +#define ANA_VCAP_S2_CFG_ARP_DIS GENMASK(11, 10) +#define ANA_VCAP_S2_CFG_ARP_DIS_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_ARP_DIS, x) +#define ANA_VCAP_S2_CFG_ARP_DIS_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_ARP_DIS, x) + +#define ANA_VCAP_S2_CFG_IP_TCPUDP_DIS GENMASK(9, 8) +#define ANA_VCAP_S2_CFG_IP_TCPUDP_DIS_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_IP_TCPUDP_DIS, x) +#define ANA_VCAP_S2_CFG_IP_TCPUDP_DIS_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_IP_TCPUDP_DIS, x) + +#define ANA_VCAP_S2_CFG_IP_OTHER_DIS GENMASK(7, 6) +#define ANA_VCAP_S2_CFG_IP_OTHER_DIS_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_IP_OTHER_DIS, x) +#define ANA_VCAP_S2_CFG_IP_OTHER_DIS_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_IP_OTHER_DIS, x) + +#define ANA_VCAP_S2_CFG_IP6_CFG GENMASK(5, 2) +#define ANA_VCAP_S2_CFG_IP6_CFG_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_IP6_CFG, x) +#define ANA_VCAP_S2_CFG_IP6_CFG_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_IP6_CFG, x) + +#define ANA_VCAP_S2_CFG_OAM_DIS GENMASK(1, 0) +#define ANA_VCAP_S2_CFG_OAM_DIS_SET(x)\ + FIELD_PREP(ANA_VCAP_S2_CFG_OAM_DIS, x) +#define ANA_VCAP_S2_CFG_OAM_DIS_GET(x)\ + FIELD_GET(ANA_VCAP_S2_CFG_OAM_DIS, x) + /* ANA:PORT:CPU_FWD_CFG */ #define ANA_CPU_FWD_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 96, 0, 1, 4) @@ -1506,4 +1570,136 @@ enum lan966x_target { #define SYS_RAM_INIT_RAM_INIT_GET(x)\ FIELD_GET(SYS_RAM_INIT_RAM_INIT, x) +/* VCAP:VCAP_CORE_CFG:VCAP_UPDATE_CTRL */ +#define VCAP_UPDATE_CTRL(t) __REG(TARGET_VCAP, t, 3, 0, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_UPDATE_CTRL_UPDATE_CMD GENMASK(24, 22) +#define VCAP_UPDATE_CTRL_UPDATE_CMD_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_CMD, x) +#define VCAP_UPDATE_CTRL_UPDATE_CMD_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_CMD, x) + +#define VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS BIT(21) +#define VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS, x) +#define VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS, x) + +#define VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS BIT(20) +#define VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS, x) +#define VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS, x) + +#define VCAP_UPDATE_CTRL_UPDATE_CNT_DIS BIT(19) +#define VCAP_UPDATE_CTRL_UPDATE_CNT_DIS_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_CNT_DIS, x) +#define VCAP_UPDATE_CTRL_UPDATE_CNT_DIS_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_CNT_DIS, x) + +#define VCAP_UPDATE_CTRL_UPDATE_ADDR GENMASK(18, 3) +#define VCAP_UPDATE_CTRL_UPDATE_ADDR_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_ADDR, x) +#define VCAP_UPDATE_CTRL_UPDATE_ADDR_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_ADDR, x) + +#define VCAP_UPDATE_CTRL_UPDATE_SHOT BIT(2) +#define VCAP_UPDATE_CTRL_UPDATE_SHOT_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_UPDATE_SHOT, x) +#define VCAP_UPDATE_CTRL_UPDATE_SHOT_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_UPDATE_SHOT, x) + +#define VCAP_UPDATE_CTRL_CLEAR_CACHE BIT(1) +#define VCAP_UPDATE_CTRL_CLEAR_CACHE_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_CLEAR_CACHE, x) +#define VCAP_UPDATE_CTRL_CLEAR_CACHE_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_CLEAR_CACHE, x) + +#define VCAP_UPDATE_CTRL_MV_TRAFFIC_IGN BIT(0) +#define VCAP_UPDATE_CTRL_MV_TRAFFIC_IGN_SET(x)\ + FIELD_PREP(VCAP_UPDATE_CTRL_MV_TRAFFIC_IGN, x) +#define VCAP_UPDATE_CTRL_MV_TRAFFIC_IGN_GET(x)\ + FIELD_GET(VCAP_UPDATE_CTRL_MV_TRAFFIC_IGN, x) + +/* VCAP:VCAP_CORE_CFG:VCAP_MV_CFG */ +#define VCAP_MV_CFG(t) __REG(TARGET_VCAP, t, 3, 0, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_MV_CFG_MV_NUM_POS GENMASK(31, 16) +#define VCAP_MV_CFG_MV_NUM_POS_SET(x)\ + FIELD_PREP(VCAP_MV_CFG_MV_NUM_POS, x) +#define VCAP_MV_CFG_MV_NUM_POS_GET(x)\ + FIELD_GET(VCAP_MV_CFG_MV_NUM_POS, x) + +#define VCAP_MV_CFG_MV_SIZE GENMASK(15, 0) +#define VCAP_MV_CFG_MV_SIZE_SET(x)\ + FIELD_PREP(VCAP_MV_CFG_MV_SIZE, x) +#define VCAP_MV_CFG_MV_SIZE_GET(x)\ + FIELD_GET(VCAP_MV_CFG_MV_SIZE, x) + +/* VCAP:VCAP_CORE_CACHE:VCAP_ENTRY_DAT */ +#define VCAP_ENTRY_DAT(t, r) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 0, r, 64, 4) + +/* VCAP:VCAP_CORE_CACHE:VCAP_MASK_DAT */ +#define VCAP_MASK_DAT(t, r) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 256, r, 64, 4) + +/* VCAP:VCAP_CORE_CACHE:VCAP_ACTION_DAT */ +#define VCAP_ACTION_DAT(t, r) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 512, r, 64, 4) + +/* VCAP:VCAP_CORE_CACHE:VCAP_CNT_DAT */ +#define VCAP_CNT_DAT(t, r) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 768, r, 32, 4) + +/* VCAP:VCAP_CORE_CACHE:VCAP_CNT_FW_DAT */ +#define VCAP_CNT_FW_DAT(t) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 896, 0, 1, 4) + +/* VCAP:VCAP_CORE_CACHE:VCAP_TG_DAT */ +#define VCAP_TG_DAT(t) __REG(TARGET_VCAP, t, 3, 8, 0, 1, 904, 900, 0, 1, 4) + +/* VCAP:VCAP_CORE_MAP:VCAP_CORE_IDX */ +#define VCAP_CORE_IDX(t) __REG(TARGET_VCAP, t, 3, 912, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_CORE_IDX_CORE_IDX GENMASK(3, 0) +#define VCAP_CORE_IDX_CORE_IDX_SET(x)\ + FIELD_PREP(VCAP_CORE_IDX_CORE_IDX, x) +#define VCAP_CORE_IDX_CORE_IDX_GET(x)\ + FIELD_GET(VCAP_CORE_IDX_CORE_IDX, x) + +/* VCAP:VCAP_CORE_MAP:VCAP_CORE_MAP */ +#define VCAP_CORE_MAP(t) __REG(TARGET_VCAP, t, 3, 912, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_CORE_MAP_CORE_MAP GENMASK(2, 0) +#define VCAP_CORE_MAP_CORE_MAP_SET(x)\ + FIELD_PREP(VCAP_CORE_MAP_CORE_MAP, x) +#define VCAP_CORE_MAP_CORE_MAP_GET(x)\ + FIELD_GET(VCAP_CORE_MAP_CORE_MAP, x) + +/* VCAP:VCAP_CONST:VCAP_VER */ +#define VCAP_VER(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 0, 0, 1, 4) + +/* VCAP:VCAP_CONST:ENTRY_WIDTH */ +#define VCAP_ENTRY_WIDTH(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 4, 0, 1, 4) + +/* VCAP:VCAP_CONST:ENTRY_CNT */ +#define VCAP_ENTRY_CNT(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 8, 0, 1, 4) + +/* VCAP:VCAP_CONST:ENTRY_SWCNT */ +#define VCAP_ENTRY_SWCNT(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 12, 0, 1, 4) + +/* VCAP:VCAP_CONST:ENTRY_TG_WIDTH */ +#define VCAP_ENTRY_TG_WIDTH(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 16, 0, 1, 4) + +/* VCAP:VCAP_CONST:ACTION_DEF_CNT */ +#define VCAP_ACTION_DEF_CNT(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 20, 0, 1, 4) + +/* VCAP:VCAP_CONST:ACTION_WIDTH */ +#define VCAP_ACTION_WIDTH(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 24, 0, 1, 4) + +/* VCAP:VCAP_CONST:CNT_WIDTH */ +#define VCAP_CNT_WIDTH(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 28, 0, 1, 4) + +/* VCAP:VCAP_CONST:CORE_CNT */ +#define VCAP_CORE_CNT(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 32, 0, 1, 4) + +/* VCAP:VCAP_CONST:IF_CNT */ +#define VCAP_IF_CNT(t) __REG(TARGET_VCAP, t, 3, 924, 0, 1, 40, 36, 0, 1, 4) + #endif /* _LAN966X_REGS_H_ */ diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c index 651d5493ae55..01072121c999 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c @@ -69,6 +69,8 @@ static int lan966x_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSMATCHALL: return lan966x_tc_matchall(port, type_data, ingress); + case TC_SETUP_CLSFLOWER: + return lan966x_tc_flower(port, type_data); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c new file mode 100644 index 000000000000..ba3fa917d6b7 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "lan966x_main.h" +#include "vcap_api.h" +#include "vcap_api_client.h" + +struct lan966x_tc_flower_parse_usage { + struct flow_cls_offload *f; + struct flow_rule *frule; + struct vcap_rule *vrule; + unsigned int used_keys; + u16 l3_proto; +}; + +static int lan966x_tc_flower_handler_ethaddr_usage(struct lan966x_tc_flower_parse_usage *st) +{ + enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; + enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; + struct flow_match_eth_addrs match; + struct vcap_u48_key smac, dmac; + int err = 0; + + flow_rule_match_eth_addrs(st->frule, &match); + + if (!is_zero_ether_addr(match.mask->src)) { + vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); + vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + if (err) + goto out; + } + + if (!is_zero_ether_addr(match.mask->dst)) { + vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); + vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->f->common.extack, "eth_addr parse error"); + return err; +} + +static int +(*lan966x_tc_flower_handlers_usage[])(struct lan966x_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = lan966x_tc_flower_handler_ethaddr_usage, +}; + +static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, + struct vcap_admin *admin, + struct vcap_rule *vrule, + u16 *l3_proto) +{ + struct lan966x_tc_flower_parse_usage state = { + .f = f, + .vrule = vrule, + .l3_proto = ETH_P_ALL, + }; + int err = 0; + + state.frule = flow_cls_offload_flow_rule(f); + for (int i = 0; i < ARRAY_SIZE(lan966x_tc_flower_handlers_usage); ++i) { + if (!flow_rule_match_key(state.frule, i) || + !lan966x_tc_flower_handlers_usage[i]) + continue; + + err = lan966x_tc_flower_handlers_usage[i](&state); + if (err) + return err; + } + + if (l3_proto) + *l3_proto = state.l3_proto; + + return err; +} + +static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(fco); + struct flow_action_entry *actent, *last_actent = NULL; + struct flow_action *act = &rule->action; + u64 action_mask = 0; + int idx; + + if (!flow_action_has_entries(act)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, "No actions"); + return -EINVAL; + } + + if (!flow_action_basic_hw_stats_check(act, fco->common.extack)) + return -EOPNOTSUPP; + + flow_action_for_each(idx, actent, act) { + if (action_mask & BIT(actent->id)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "More actions of the same type"); + return -EINVAL; + } + action_mask |= BIT(actent->id); + last_actent = actent; /* Save last action for later check */ + } + + /* Check that last action is a goto */ + if (last_actent->id != FLOW_ACTION_GOTO) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Last action must be 'goto'"); + return -EINVAL; + } + + /* Check if the goto chain is in the next lookup */ + if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, + last_actent->chain_index)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Invalid goto chain"); + return -EINVAL; + } + + /* Catch unsupported combinations of actions */ + if (action_mask & BIT(FLOW_ACTION_TRAP) && + action_mask & BIT(FLOW_ACTION_ACCEPT)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Cannot combine pass and trap action"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int lan966x_tc_flower_add(struct lan966x_port *port, + struct flow_cls_offload *f, + struct vcap_admin *admin) +{ + struct flow_action_entry *act; + u16 l3_proto = ETH_P_ALL; + struct flow_rule *frule; + struct vcap_rule *vrule; + int err, idx; + + err = lan966x_tc_flower_action_check(port->lan966x->vcap_ctrl, f, + admin); + if (err) + return err; + + vrule = vcap_alloc_rule(port->lan966x->vcap_ctrl, port->dev, + f->common.chain_index, VCAP_USER_TC, + f->common.prio, 0); + if (IS_ERR(vrule)) + return PTR_ERR(vrule); + + vrule->cookie = f->cookie; + err = lan966x_tc_flower_use_dissectors(f, admin, vrule, &l3_proto); + if (err) + goto out; + + frule = flow_cls_offload_flow_rule(f); + + flow_action_for_each(idx, act, &frule->action) { + switch (act->id) { + case FLOW_ACTION_TRAP: + err = vcap_rule_add_action_bit(vrule, + VCAP_AF_CPU_COPY_ENA, + VCAP_BIT_1); + err |= vcap_rule_add_action_u32(vrule, + VCAP_AF_CPU_QUEUE_NUM, + 0); + err |= vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE, + LAN966X_PMM_REPLACE); + err |= vcap_set_rule_set_actionset(vrule, + VCAP_AFS_BASE_TYPE); + if (err) + goto out; + + break; + case FLOW_ACTION_GOTO: + break; + default: + NL_SET_ERR_MSG_MOD(f->common.extack, + "Unsupported TC action"); + err = -EOPNOTSUPP; + goto out; + } + } + + err = vcap_val_rule(vrule, l3_proto); + if (err) { + vcap_set_tc_exterr(f, vrule); + goto out; + } + + err = vcap_add_rule(vrule); + if (err) + NL_SET_ERR_MSG_MOD(f->common.extack, + "Could not add the filter"); +out: + vcap_free_rule(vrule); + return err; +} + +static int lan966x_tc_flower_del(struct lan966x_port *port, + struct flow_cls_offload *f, + struct vcap_admin *admin) +{ + struct vcap_control *vctrl; + int err = -ENOENT, rule_id; + + vctrl = port->lan966x->vcap_ctrl; + while (true) { + rule_id = vcap_lookup_rule_by_cookie(vctrl, f->cookie); + if (rule_id <= 0) + break; + + err = vcap_del_rule(vctrl, port->dev, rule_id); + if (err) { + NL_SET_ERR_MSG_MOD(f->common.extack, + "Cannot delete rule"); + break; + } + } + + return err; +} + +int lan966x_tc_flower(struct lan966x_port *port, + struct flow_cls_offload *f) +{ + struct vcap_admin *admin; + + admin = vcap_find_admin(port->lan966x->vcap_ctrl, + f->common.chain_index); + if (!admin) { + NL_SET_ERR_MSG_MOD(f->common.extack, "Invalid chain"); + return -EINVAL; + } + + switch (f->command) { + case FLOW_CLS_REPLACE: + return lan966x_tc_flower_add(port, f, admin); + case FLOW_CLS_DESTROY: + return lan966x_tc_flower_del(port, f, admin); + default: + return -EOPNOTSUPP; + } + + return 0; +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c index 7368433b9277..a539abaad9b6 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c @@ -23,6 +23,9 @@ static int lan966x_tc_matchall_add(struct lan966x_port *port, case FLOW_ACTION_MIRRED: return lan966x_mirror_port_add(port, act, f->cookie, ingress, f->common.extack); + case FLOW_ACTION_GOTO: + return lan966x_goto_port_add(port, act, f->cookie, + f->common.extack); default: NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported action"); @@ -43,6 +46,9 @@ static int lan966x_tc_matchall_del(struct lan966x_port *port, f->cookie == port->tc.egress_mirror_id) { return lan966x_mirror_port_del(port, ingress, f->common.extack); + } else if (f->cookie == port->tc.goto_id) { + return lan966x_goto_port_del(port, f->cookie, + f->common.extack); } else { NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported action"); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.c new file mode 100644 index 000000000000..928e711960e6 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.c @@ -0,0 +1,1608 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +#include <linux/types.h> +#include <linux/kernel.h> + +#include "lan966x_vcap_ag_api.h" + +/* keyfields */ +static const struct vcap_field is2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 91, + .width = 48, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 139, + .width = 16, + }, + [VCAP_KF_L2_FRM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 155, + .width = 4, + }, + [VCAP_KF_L2_PAYLOAD0] = { + .type = VCAP_FIELD_U32, + .offset = 159, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD1] = { + .type = VCAP_FIELD_U32, + .offset = 175, + .width = 8, + }, + [VCAP_KF_L2_PAYLOAD2] = { + .type = VCAP_FIELD_U32, + .offset = 183, + .width = 3, + }, +}; + +static const struct vcap_field is2_mac_llc_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 91, + .width = 48, + }, + [VCAP_KF_L2_LLC] = { + .type = VCAP_FIELD_U48, + .offset = 139, + .width = 40, + }, +}; + +static const struct vcap_field is2_mac_snap_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 91, + .width = 48, + }, + [VCAP_KF_L2_SNAP] = { + .type = VCAP_FIELD_U48, + .offset = 139, + .width = 40, + }, +}; + +static const struct vcap_field is2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 131, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 163, + .width = 1, + }, +}; + +static const struct vcap_field is2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 43, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT] = { + .type = VCAP_FIELD_BIT, + .offset = 44, + .width = 1, + }, + [VCAP_KF_L3_FRAG_OFS_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 45, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 47, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 48, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 120, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 121, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 122, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 138, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 154, + .width = 8, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 162, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 163, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 164, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 165, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 166, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 167, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 169, + .width = 1, + }, + [VCAP_KF_L4_1588_DOM] = { + .type = VCAP_FIELD_U32, + .offset = 170, + .width = 8, + }, + [VCAP_KF_L4_1588_VER] = { + .type = VCAP_FIELD_U32, + .offset = 178, + .width = 4, + }, +}; + +static const struct vcap_field is2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 43, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT] = { + .type = VCAP_FIELD_BIT, + .offset = 44, + .width = 1, + }, + [VCAP_KF_L3_FRAG_OFS_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 45, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 47, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 48, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 120, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 121, + .width = 8, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U56, + .offset = 129, + .width = 56, + }, +}; + +static const struct vcap_field is2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 43, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 44, + .width = 128, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 172, + .width = 8, + }, +}; + +static const struct vcap_field is2_oam_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 3, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 91, + .width = 48, + }, + [VCAP_KF_OAM_MEL_FLAGS] = { + .type = VCAP_FIELD_U32, + .offset = 139, + .width = 7, + }, + [VCAP_KF_OAM_VER] = { + .type = VCAP_FIELD_U32, + .offset = 146, + .width = 5, + }, + [VCAP_KF_OAM_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 151, + .width = 8, + }, + [VCAP_KF_OAM_FLAGS] = { + .type = VCAP_FIELD_U32, + .offset = 159, + .width = 8, + }, + [VCAP_KF_OAM_MEPID] = { + .type = VCAP_FIELD_U32, + .offset = 167, + .width = 16, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 183, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 184, + .width = 1, + }, + [VCAP_KF_OAM_DETECTED] = { + .type = VCAP_FIELD_BIT, + .offset = 185, + .width = 1, + }, +}; + +static const struct vcap_field is2_ip6_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 11, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 21, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 37, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 38, + .width = 3, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 41, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 50, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 178, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 306, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 307, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 308, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 324, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 340, + .width = 8, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 348, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 349, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 350, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 351, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 352, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 353, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 354, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 355, + .width = 1, + }, + [VCAP_KF_L4_1588_DOM] = { + .type = VCAP_FIELD_U32, + .offset = 356, + .width = 8, + }, + [VCAP_KF_L4_1588_VER] = { + .type = VCAP_FIELD_U32, + .offset = 364, + .width = 4, + }, +}; + +static const struct vcap_field is2_ip6_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 11, + .width = 9, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_KF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 21, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 22, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 24, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 12, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 37, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 38, + .width = 3, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 41, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 50, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 178, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 306, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 307, + .width = 8, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U56, + .offset = 315, + .width = 56, + }, +}; + +static const struct vcap_field is2_smac_sip4_keyfield[] = { + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 4, + .width = 48, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 52, + .width = 32, + }, +}; + +static const struct vcap_field is2_smac_sip6_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 4, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 8, + .width = 48, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 56, + .width = 128, + }, +}; + +/* keyfield_set */ +static const struct vcap_set is2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_MAC_LLC] = { + .type_id = 1, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_MAC_SNAP] = { + .type_id = 2, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 3, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 4, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 5, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 6, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_OAM] = { + .type_id = 7, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_KFS_IP6_TCP_UDP] = { + .type_id = 0, + .sw_per_item = 4, + .sw_cnt = 1, + }, + [VCAP_KFS_IP6_OTHER] = { + .type_id = 1, + .sw_per_item = 4, + .sw_cnt = 1, + }, + [VCAP_KFS_SMAC_SIP4] = { + .type_id = -1, + .sw_per_item = 1, + .sw_cnt = 4, + }, + [VCAP_KFS_SMAC_SIP6] = { + .type_id = 8, + .sw_per_item = 2, + .sw_cnt = 2, + }, +}; + +/* keyfield_set map */ +static const struct vcap_field *is2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = is2_mac_etype_keyfield, + [VCAP_KFS_MAC_LLC] = is2_mac_llc_keyfield, + [VCAP_KFS_MAC_SNAP] = is2_mac_snap_keyfield, + [VCAP_KFS_ARP] = is2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = is2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = is2_ip4_other_keyfield, + [VCAP_KFS_IP6_STD] = is2_ip6_std_keyfield, + [VCAP_KFS_OAM] = is2_oam_keyfield, + [VCAP_KFS_IP6_TCP_UDP] = is2_ip6_tcp_udp_keyfield, + [VCAP_KFS_IP6_OTHER] = is2_ip6_other_keyfield, + [VCAP_KFS_SMAC_SIP4] = is2_smac_sip4_keyfield, + [VCAP_KFS_SMAC_SIP6] = is2_smac_sip6_keyfield, +}; + +/* keyfield_set map sizes */ +static int is2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(is2_mac_etype_keyfield), + [VCAP_KFS_MAC_LLC] = ARRAY_SIZE(is2_mac_llc_keyfield), + [VCAP_KFS_MAC_SNAP] = ARRAY_SIZE(is2_mac_snap_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(is2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(is2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(is2_ip4_other_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(is2_ip6_std_keyfield), + [VCAP_KFS_OAM] = ARRAY_SIZE(is2_oam_keyfield), + [VCAP_KFS_IP6_TCP_UDP] = ARRAY_SIZE(is2_ip6_tcp_udp_keyfield), + [VCAP_KFS_IP6_OTHER] = ARRAY_SIZE(is2_ip6_other_keyfield), + [VCAP_KFS_SMAC_SIP4] = ARRAY_SIZE(is2_smac_sip4_keyfield), + [VCAP_KFS_SMAC_SIP6] = ARRAY_SIZE(is2_smac_sip6_keyfield), +}; + +/* actionfields */ +static const struct vcap_field is2_base_type_actionfield[] = { + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 3, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 2, + }, + [VCAP_AF_MIRROR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 7, + .width = 1, + }, + [VCAP_AF_LRN_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 8, + .width = 1, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 9, + }, + [VCAP_AF_POLICE_VCAP_ONLY] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 8, + }, + [VCAP_AF_REW_OP] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 16, + }, + [VCAP_AF_ISDX_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 44, + .width = 1, + }, + [VCAP_AF_ACL_ID] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 6, + }, +}; + +static const struct vcap_field is2_smac_sip_actionfield[] = { + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 3, + }, + [VCAP_AF_FWD_KILL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_AF_HOST_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 5, + .width = 1, + }, +}; + +/* actionfield_set */ +static const struct vcap_set is2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 2, + .sw_cnt = 2, + }, + [VCAP_AFS_SMAC_SIP] = { + .type_id = -1, + .sw_per_item = 1, + .sw_cnt = 4, + }, +}; + +/* actionfield_set map */ +static const struct vcap_field *is2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = is2_base_type_actionfield, + [VCAP_AFS_SMAC_SIP] = is2_smac_sip_actionfield, +}; + +/* actionfield_set map size */ +static int is2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(is2_base_type_actionfield), + [VCAP_AFS_SMAC_SIP] = ARRAY_SIZE(is2_smac_sip_actionfield), +}; + +/* Type Groups */ +static const struct vcap_typegroup is2_x4_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 96, + .width = 1, + .value = 0, + }, + { + .offset = 192, + .width = 2, + .value = 0, + }, + { + .offset = 288, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x2_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 96, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x1_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 1, + .value = 1, + }, + {} +}; + +static const struct vcap_typegroup *is2_keyfield_set_typegroups[] = { + [4] = is2_x4_keyfield_set_typegroups, + [2] = is2_x2_keyfield_set_typegroups, + [1] = is2_x1_keyfield_set_typegroups, + [5] = NULL, +}; + +static const struct vcap_typegroup is2_x2_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 31, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x1_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 1, + .value = 1, + }, + {} +}; + +static const struct vcap_typegroup *is2_actionfield_set_typegroups[] = { + [2] = is2_x2_actionfield_set_typegroups, + [1] = is2_x1_actionfield_set_typegroups, + [5] = NULL, +}; + +/* Keyfieldset names */ +static const char * const vcap_keyfield_set_names[] = { + [VCAP_KFS_NO_VALUE] = "(None)", + [VCAP_KFS_ARP] = "VCAP_KFS_ARP", + [VCAP_KFS_IP4_OTHER] = "VCAP_KFS_IP4_OTHER", + [VCAP_KFS_IP4_TCP_UDP] = "VCAP_KFS_IP4_TCP_UDP", + [VCAP_KFS_IP6_OTHER] = "VCAP_KFS_IP6_OTHER", + [VCAP_KFS_IP6_STD] = "VCAP_KFS_IP6_STD", + [VCAP_KFS_IP6_TCP_UDP] = "VCAP_KFS_IP6_TCP_UDP", + [VCAP_KFS_MAC_ETYPE] = "VCAP_KFS_MAC_ETYPE", + [VCAP_KFS_MAC_LLC] = "VCAP_KFS_MAC_LLC", + [VCAP_KFS_MAC_SNAP] = "VCAP_KFS_MAC_SNAP", + [VCAP_KFS_OAM] = "VCAP_KFS_OAM", + [VCAP_KFS_SMAC_SIP4] = "VCAP_KFS_SMAC_SIP4", + [VCAP_KFS_SMAC_SIP6] = "VCAP_KFS_SMAC_SIP6", +}; + +/* Actionfieldset names */ +static const char * const vcap_actionfield_set_names[] = { + [VCAP_AFS_NO_VALUE] = "(None)", + [VCAP_AFS_BASE_TYPE] = "VCAP_AFS_BASE_TYPE", + [VCAP_AFS_SMAC_SIP] = "VCAP_AFS_SMAC_SIP", +}; + +/* Keyfield names */ +static const char * const vcap_keyfield_names[] = { + [VCAP_KF_NO_VALUE] = "(None)", + [VCAP_KF_8021Q_DEI_CLS] = "8021Q_DEI_CLS", + [VCAP_KF_8021Q_PCP_CLS] = "8021Q_PCP_CLS", + [VCAP_KF_8021Q_VID_CLS] = "8021Q_VID_CLS", + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = "8021Q_VLAN_TAGGED_IS", + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = "ARP_ADDR_SPACE_OK_IS", + [VCAP_KF_ARP_LEN_OK_IS] = "ARP_LEN_OK_IS", + [VCAP_KF_ARP_OPCODE] = "ARP_OPCODE", + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = "ARP_OPCODE_UNKNOWN_IS", + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = "ARP_PROTO_SPACE_OK_IS", + [VCAP_KF_ARP_SENDER_MATCH_IS] = "ARP_SENDER_MATCH_IS", + [VCAP_KF_ARP_TGT_MATCH_IS] = "ARP_TGT_MATCH_IS", + [VCAP_KF_ETYPE] = "ETYPE", + [VCAP_KF_HOST_MATCH] = "HOST_MATCH", + [VCAP_KF_IF_IGR_PORT] = "IF_IGR_PORT", + [VCAP_KF_IF_IGR_PORT_MASK] = "IF_IGR_PORT_MASK", + [VCAP_KF_IP4_IS] = "IP4_IS", + [VCAP_KF_ISDX_GT0_IS] = "ISDX_GT0_IS", + [VCAP_KF_L2_BC_IS] = "L2_BC_IS", + [VCAP_KF_L2_DMAC] = "L2_DMAC", + [VCAP_KF_L2_FRM_TYPE] = "L2_FRM_TYPE", + [VCAP_KF_L2_LLC] = "L2_LLC", + [VCAP_KF_L2_MC_IS] = "L2_MC_IS", + [VCAP_KF_L2_PAYLOAD0] = "L2_PAYLOAD0", + [VCAP_KF_L2_PAYLOAD1] = "L2_PAYLOAD1", + [VCAP_KF_L2_PAYLOAD2] = "L2_PAYLOAD2", + [VCAP_KF_L2_SMAC] = "L2_SMAC", + [VCAP_KF_L2_SNAP] = "L2_SNAP", + [VCAP_KF_L3_DIP_EQ_SIP_IS] = "L3_DIP_EQ_SIP_IS", + [VCAP_KF_L3_FRAGMENT] = "L3_FRAGMENT", + [VCAP_KF_L3_FRAG_OFS_GT0] = "L3_FRAG_OFS_GT0", + [VCAP_KF_L3_IP4_DIP] = "L3_IP4_DIP", + [VCAP_KF_L3_IP4_SIP] = "L3_IP4_SIP", + [VCAP_KF_L3_IP6_DIP] = "L3_IP6_DIP", + [VCAP_KF_L3_IP6_SIP] = "L3_IP6_SIP", + [VCAP_KF_L3_IP_PROTO] = "L3_IP_PROTO", + [VCAP_KF_L3_OPTIONS_IS] = "L3_OPTIONS_IS", + [VCAP_KF_L3_PAYLOAD] = "L3_PAYLOAD", + [VCAP_KF_L3_TOS] = "L3_TOS", + [VCAP_KF_L3_TTL_GT0] = "L3_TTL_GT0", + [VCAP_KF_L4_1588_DOM] = "L4_1588_DOM", + [VCAP_KF_L4_1588_VER] = "L4_1588_VER", + [VCAP_KF_L4_ACK] = "L4_ACK", + [VCAP_KF_L4_DPORT] = "L4_DPORT", + [VCAP_KF_L4_FIN] = "L4_FIN", + [VCAP_KF_L4_PSH] = "L4_PSH", + [VCAP_KF_L4_RNG] = "L4_RNG", + [VCAP_KF_L4_RST] = "L4_RST", + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = "L4_SEQUENCE_EQ0_IS", + [VCAP_KF_L4_SPORT] = "L4_SPORT", + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = "L4_SPORT_EQ_DPORT_IS", + [VCAP_KF_L4_SYN] = "L4_SYN", + [VCAP_KF_L4_URG] = "L4_URG", + [VCAP_KF_LOOKUP_FIRST_IS] = "LOOKUP_FIRST_IS", + [VCAP_KF_LOOKUP_PAG] = "LOOKUP_PAG", + [VCAP_KF_OAM_CCM_CNTS_EQ0] = "OAM_CCM_CNTS_EQ0", + [VCAP_KF_OAM_DETECTED] = "OAM_DETECTED", + [VCAP_KF_OAM_FLAGS] = "OAM_FLAGS", + [VCAP_KF_OAM_MEL_FLAGS] = "OAM_MEL_FLAGS", + [VCAP_KF_OAM_MEPID] = "OAM_MEPID", + [VCAP_KF_OAM_OPCODE] = "OAM_OPCODE", + [VCAP_KF_OAM_VER] = "OAM_VER", + [VCAP_KF_OAM_Y1731_IS] = "OAM_Y1731_IS", + [VCAP_KF_TCP_IS] = "TCP_IS", + [VCAP_KF_TYPE] = "TYPE", +}; + +/* Actionfield names */ +static const char * const vcap_actionfield_names[] = { + [VCAP_AF_NO_VALUE] = "(None)", + [VCAP_AF_ACL_ID] = "ACL_ID", + [VCAP_AF_CPU_COPY_ENA] = "CPU_COPY_ENA", + [VCAP_AF_CPU_QUEUE_NUM] = "CPU_QUEUE_NUM", + [VCAP_AF_FWD_KILL_ENA] = "FWD_KILL_ENA", + [VCAP_AF_HIT_ME_ONCE] = "HIT_ME_ONCE", + [VCAP_AF_HOST_MATCH] = "HOST_MATCH", + [VCAP_AF_ISDX_ENA] = "ISDX_ENA", + [VCAP_AF_LRN_DIS] = "LRN_DIS", + [VCAP_AF_MASK_MODE] = "MASK_MODE", + [VCAP_AF_MIRROR_ENA] = "MIRROR_ENA", + [VCAP_AF_POLICE_ENA] = "POLICE_ENA", + [VCAP_AF_POLICE_IDX] = "POLICE_IDX", + [VCAP_AF_POLICE_VCAP_ONLY] = "POLICE_VCAP_ONLY", + [VCAP_AF_PORT_MASK] = "PORT_MASK", + [VCAP_AF_REW_OP] = "REW_OP", +}; + +/* VCAPs */ +const struct vcap_info lan966x_vcaps[] = { + [VCAP_TYPE_IS2] = { + .name = "is2", + .rows = 64, + .sw_count = 4, + .sw_width = 96, + .sticky_width = 32, + .act_width = 31, + .default_cnt = 11, + .require_cnt_dis = 1, + .version = 1, + .keyfield_set = is2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is2_keyfield_set), + .actionfield_set = is2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is2_actionfield_set), + .keyfield_set_map = is2_keyfield_set_map, + .keyfield_set_map_size = is2_keyfield_set_map_size, + .actionfield_set_map = is2_actionfield_set_map, + .actionfield_set_map_size = is2_actionfield_set_map_size, + .keyfield_set_typegroups = is2_keyfield_set_typegroups, + .actionfield_set_typegroups = is2_actionfield_set_typegroups, + }, +}; + +const struct vcap_statistics lan966x_vcap_stats = { + .name = "lan966x", + .count = 1, + .keyfield_set_names = vcap_keyfield_set_names, + .actionfield_set_names = vcap_actionfield_set_names, + .keyfield_names = vcap_keyfield_names, + .actionfield_names = vcap_actionfield_names, +}; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.h b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.h new file mode 100644 index 000000000000..0d8bbee73b2a --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_ag_api.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ + +#ifndef __LAN966X_VCAP_AG_API_H__ +#define __LAN966X_VCAP_AG_API_H__ + +#include "vcap_api.h" + +extern const struct vcap_info lan966x_vcaps[]; +extern const struct vcap_statistics lan966x_vcap_stats; + +#endif /* __LAN966X_VCAP_AG_API_H__ */ diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c new file mode 100644 index 000000000000..d8dc9fbb81e1 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "lan966x_main.h" +#include "lan966x_vcap_ag_api.h" +#include "vcap_api.h" +#include "vcap_api_client.h" + +#define STREAMSIZE (64 * 4) + +#define LAN966X_IS2_LOOKUPS 2 + +enum vcap_is2_port_sel_ipv6 { + VCAP_IS2_PS_IPV6_TCPUDP_OTHER, + VCAP_IS2_PS_IPV6_STD, + VCAP_IS2_PS_IPV6_IP4_TCPUDP_IP4_OTHER, + VCAP_IS2_PS_IPV6_MAC_ETYPE, +}; + +static struct lan966x_vcap_inst { + enum vcap_type vtype; /* type of vcap */ + int tgt_inst; /* hardware instance number */ + int lookups; /* number of lookups in this vcap type */ + int first_cid; /* first chain id in this vcap */ + int last_cid; /* last chain id in this vcap */ + int count; /* number of available addresses */ +} lan966x_vcap_inst_cfg[] = { + { + .vtype = VCAP_TYPE_IS2, /* IS2-0 */ + .tgt_inst = 2, + .lookups = LAN966X_IS2_LOOKUPS, + .first_cid = LAN966X_VCAP_CID_IS2_L0, + .last_cid = LAN966X_VCAP_CID_IS2_MAX, + .count = 256, + }, +}; + +struct lan966x_vcap_cmd_cb { + struct lan966x *lan966x; + u32 instance; +}; + +static u32 lan966x_vcap_read_update_ctrl(const struct lan966x_vcap_cmd_cb *cb) +{ + return lan_rd(cb->lan966x, VCAP_UPDATE_CTRL(cb->instance)); +} + +static void lan966x_vcap_wait_update(struct lan966x *lan966x, int instance) +{ + const struct lan966x_vcap_cmd_cb cb = { .lan966x = lan966x, + .instance = instance }; + u32 val; + + readx_poll_timeout(lan966x_vcap_read_update_ctrl, &cb, val, + (val & VCAP_UPDATE_CTRL_UPDATE_SHOT) == 0, 10, + 100000); +} + +static void __lan966x_vcap_range_init(struct lan966x *lan966x, + struct vcap_admin *admin, + u32 addr, + u32 count) +{ + lan_wr(VCAP_MV_CFG_MV_NUM_POS_SET(0) | + VCAP_MV_CFG_MV_SIZE_SET(count - 1), + lan966x, VCAP_MV_CFG(admin->tgt_inst)); + + lan_wr(VCAP_UPDATE_CTRL_UPDATE_CMD_SET(VCAP_CMD_INITIALIZE) | + VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_UPDATE_CTRL_CLEAR_CACHE_SET(true) | + VCAP_UPDATE_CTRL_UPDATE_SHOT_SET(1), + lan966x, VCAP_UPDATE_CTRL(admin->tgt_inst)); + + lan966x_vcap_wait_update(lan966x, admin->tgt_inst); +} + +static int lan966x_vcap_cid_to_lookup(int cid) +{ + if (cid >= LAN966X_VCAP_CID_IS2_L1 && + cid < LAN966X_VCAP_CID_IS2_MAX) + return 1; + + return 0; +} + +static int +lan966x_vcap_is2_get_port_keysets(struct net_device *dev, int lookup, + struct vcap_keyset_list *keysetlist, + u16 l3_proto) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + bool found = false; + u32 val; + + /* Check if the port keyset selection is enabled */ + val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port)); + if (!ANA_VCAP_S2_CFG_ENA_GET(val)) + return -ENOENT; + + /* Collect all keysets for the port in a list */ + if (l3_proto == ETH_P_ALL) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_SNAP) { + if (ANA_VCAP_S2_CFG_SNAP_DIS_GET(val) & (BIT(0) << lookup)) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_LLC); + else + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_SNAP); + + found = true; + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_CFM) { + if (ANA_VCAP_S2_CFG_OAM_DIS_GET(val) & (BIT(0) << lookup)) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + else + vcap_keyset_list_add(keysetlist, VCAP_KFS_OAM); + + found = true; + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_ARP) { + if (ANA_VCAP_S2_CFG_ARP_DIS_GET(val) & (BIT(0) << lookup)) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + else + vcap_keyset_list_add(keysetlist, VCAP_KFS_ARP); + + found = true; + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IP) { + if (ANA_VCAP_S2_CFG_IP_OTHER_DIS_GET(val) & (BIT(0) << lookup)) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + else + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + + if (ANA_VCAP_S2_CFG_IP_TCPUDP_DIS_GET(val) & (BIT(0) << lookup)) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + else + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + + found = true; + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IPV6) { + switch (ANA_VCAP_S2_CFG_IP6_CFG_GET(val) & (0x3 << lookup)) { + case VCAP_IS2_PS_IPV6_TCPUDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_OTHER); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_TCP_UDP); + break; + case VCAP_IS2_PS_IPV6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_IS2_PS_IPV6_IP4_TCPUDP_IP4_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + break; + case VCAP_IS2_PS_IPV6_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + } + + found = true; + } + + if (!found) + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + + return 0; +} + +static enum vcap_keyfield_set +lan966x_vcap_validate_keyset(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_rule *rule, + struct vcap_keyset_list *kslist, + u16 l3_proto) +{ + struct vcap_keyset_list keysetlist = {}; + enum vcap_keyfield_set keysets[10] = {}; + int lookup; + int err; + + if (!kslist || kslist->cnt == 0) + return VCAP_KFS_NO_VALUE; + + lookup = lan966x_vcap_cid_to_lookup(rule->vcap_chain_id); + keysetlist.max = ARRAY_SIZE(keysets); + keysetlist.keysets = keysets; + err = lan966x_vcap_is2_get_port_keysets(dev, lookup, &keysetlist, + l3_proto); + if (err) + return VCAP_KFS_NO_VALUE; + + /* Check if there is a match and return the match */ + for (int i = 0; i < kslist->cnt; ++i) + for (int j = 0; j < keysetlist.cnt; ++j) + if (kslist->keysets[i] == keysets[j]) + return kslist->keysets[i]; + + return VCAP_KFS_NO_VALUE; +} + +static bool lan966x_vcap_is_first_chain(struct vcap_rule *rule) +{ + return (rule->vcap_chain_id >= LAN966X_VCAP_CID_IS2_L0 && + rule->vcap_chain_id < LAN966X_VCAP_CID_IS2_L1); +} + +static void lan966x_vcap_add_default_fields(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + struct lan966x_port *port = netdev_priv(dev); + u32 value, mask; + + if (vcap_rule_get_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK, + &value, &mask)) + vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK, 0, + ~BIT(port->chip_port)); + + if (lan966x_vcap_is_first_chain(rule)) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_0); +} + +static void lan966x_vcap_cache_erase(struct vcap_admin *admin) +{ + memset(admin->cache.keystream, 0, STREAMSIZE); + memset(admin->cache.maskstream, 0, STREAMSIZE); + memset(admin->cache.actionstream, 0, STREAMSIZE); + memset(&admin->cache.counter, 0, sizeof(admin->cache.counter)); +} + +static void lan966x_vcap_cache_write(struct net_device *dev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + u32 *keystr, *mskstr, *actstr; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + switch (sel) { + case VCAP_SEL_ENTRY: + for (int i = 0; i < count; ++i) { + lan_wr(keystr[i] & mskstr[i], lan966x, + VCAP_ENTRY_DAT(admin->tgt_inst, i)); + lan_wr(~mskstr[i], lan966x, + VCAP_MASK_DAT(admin->tgt_inst, i)); + } + break; + case VCAP_SEL_ACTION: + for (int i = 0; i < count; ++i) + lan_wr(actstr[i], lan966x, + VCAP_ACTION_DAT(admin->tgt_inst, i)); + break; + case VCAP_SEL_COUNTER: + admin->cache.sticky = admin->cache.counter > 0; + lan_wr(admin->cache.counter, lan966x, + VCAP_CNT_DAT(admin->tgt_inst, 0)); + break; + default: + break; + } +} + +static void lan966x_vcap_cache_read(struct net_device *dev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + int instance = admin->tgt_inst; + u32 *keystr, *mskstr, *actstr; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + if (sel & VCAP_SEL_ENTRY) { + for (int i = 0; i < count; ++i) { + keystr[i] = + lan_rd(lan966x, VCAP_ENTRY_DAT(instance, i)); + mskstr[i] = + ~lan_rd(lan966x, VCAP_MASK_DAT(instance, i)); + } + } + + if (sel & VCAP_SEL_ACTION) + for (int i = 0; i < count; ++i) + actstr[i] = + lan_rd(lan966x, VCAP_ACTION_DAT(instance, i)); + + if (sel & VCAP_SEL_COUNTER) { + admin->cache.counter = + lan_rd(lan966x, VCAP_CNT_DAT(instance, 0)); + admin->cache.sticky = admin->cache.counter > 0; + } +} + +static void lan966x_vcap_range_init(struct net_device *dev, + struct vcap_admin *admin, + u32 addr, + u32 count) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + + __lan966x_vcap_range_init(lan966x, admin, addr, count); +} + +static void lan966x_vcap_update(struct net_device *dev, + struct vcap_admin *admin, + enum vcap_command cmd, + enum vcap_selection sel, + u32 addr) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + bool clear; + + clear = (cmd == VCAP_CMD_INITIALIZE); + + lan_wr(VCAP_MV_CFG_MV_NUM_POS_SET(0) | + VCAP_MV_CFG_MV_SIZE_SET(0), + lan966x, VCAP_MV_CFG(admin->tgt_inst)); + + lan_wr(VCAP_UPDATE_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS_SET((VCAP_SEL_ENTRY & sel) == 0) | + VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS_SET((VCAP_SEL_ACTION & sel) == 0) | + VCAP_UPDATE_CTRL_UPDATE_CNT_DIS_SET((VCAP_SEL_COUNTER & sel) == 0) | + VCAP_UPDATE_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_UPDATE_CTRL_CLEAR_CACHE_SET(clear) | + VCAP_UPDATE_CTRL_UPDATE_SHOT, + lan966x, VCAP_UPDATE_CTRL(admin->tgt_inst)); + + lan966x_vcap_wait_update(lan966x, admin->tgt_inst); +} + +static void lan966x_vcap_move(struct net_device *dev, + struct vcap_admin *admin, + u32 addr, int offset, int count) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + enum vcap_command cmd; + u16 mv_num_pos; + u16 mv_size; + + mv_size = count - 1; + if (offset > 0) { + mv_num_pos = offset - 1; + cmd = VCAP_CMD_MOVE_DOWN; + } else { + mv_num_pos = -offset - 1; + cmd = VCAP_CMD_MOVE_UP; + } + + lan_wr(VCAP_MV_CFG_MV_NUM_POS_SET(mv_num_pos) | + VCAP_MV_CFG_MV_SIZE_SET(mv_size), + lan966x, VCAP_MV_CFG(admin->tgt_inst)); + + lan_wr(VCAP_UPDATE_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_UPDATE_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_UPDATE_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_UPDATE_CTRL_CLEAR_CACHE_SET(false) | + VCAP_UPDATE_CTRL_UPDATE_SHOT, + lan966x, VCAP_UPDATE_CTRL(admin->tgt_inst)); + + lan966x_vcap_wait_update(lan966x, admin->tgt_inst); +} + +static int lan966x_vcap_port_info(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + return 0; +} + +static int lan966x_vcap_enable(struct net_device *dev, + struct vcap_admin *admin, + bool enable) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + + lan_rmw(ANA_VCAP_S2_CFG_ENA_SET(enable), + ANA_VCAP_S2_CFG_ENA, + lan966x, ANA_VCAP_S2_CFG(port->chip_port)); + + return 0; +} + +static struct vcap_operations lan966x_vcap_ops = { + .validate_keyset = lan966x_vcap_validate_keyset, + .add_default_fields = lan966x_vcap_add_default_fields, + .cache_erase = lan966x_vcap_cache_erase, + .cache_write = lan966x_vcap_cache_write, + .cache_read = lan966x_vcap_cache_read, + .init = lan966x_vcap_range_init, + .update = lan966x_vcap_update, + .move = lan966x_vcap_move, + .port_info = lan966x_vcap_port_info, + .enable = lan966x_vcap_enable, +}; + +static void lan966x_vcap_admin_free(struct vcap_admin *admin) +{ + if (!admin) + return; + + kfree(admin->cache.keystream); + kfree(admin->cache.maskstream); + kfree(admin->cache.actionstream); + mutex_destroy(&admin->lock); + kfree(admin); +} + +static struct vcap_admin * +lan966x_vcap_admin_alloc(struct lan966x *lan966x, struct vcap_control *ctrl, + const struct lan966x_vcap_inst *cfg) +{ + struct vcap_admin *admin; + + admin = kzalloc(sizeof(*admin), GFP_KERNEL); + if (!admin) + return ERR_PTR(-ENOMEM); + + mutex_init(&admin->lock); + INIT_LIST_HEAD(&admin->list); + INIT_LIST_HEAD(&admin->rules); + INIT_LIST_HEAD(&admin->enabled); + + admin->vtype = cfg->vtype; + admin->vinst = 0; + admin->w32be = true; + admin->tgt_inst = cfg->tgt_inst; + + admin->lookups = cfg->lookups; + admin->lookups_per_instance = cfg->lookups; + + admin->first_cid = cfg->first_cid; + admin->last_cid = cfg->last_cid; + + admin->cache.keystream = kzalloc(STREAMSIZE, GFP_KERNEL); + admin->cache.maskstream = kzalloc(STREAMSIZE, GFP_KERNEL); + admin->cache.actionstream = kzalloc(STREAMSIZE, GFP_KERNEL); + if (!admin->cache.keystream || + !admin->cache.maskstream || + !admin->cache.actionstream) { + lan966x_vcap_admin_free(admin); + return ERR_PTR(-ENOMEM); + } + + return admin; +} + +static void lan966x_vcap_block_init(struct lan966x *lan966x, + struct vcap_admin *admin, + struct lan966x_vcap_inst *cfg) +{ + admin->first_valid_addr = 0; + admin->last_used_addr = cfg->count; + admin->last_valid_addr = cfg->count - 1; + + lan_wr(VCAP_CORE_IDX_CORE_IDX_SET(0), + lan966x, VCAP_CORE_IDX(admin->tgt_inst)); + lan_wr(VCAP_CORE_MAP_CORE_MAP_SET(1), + lan966x, VCAP_CORE_MAP(admin->tgt_inst)); + + __lan966x_vcap_range_init(lan966x, admin, admin->first_valid_addr, + admin->last_valid_addr - + admin->first_valid_addr); +} + +static void lan966x_vcap_port_key_deselection(struct lan966x *lan966x, + struct vcap_admin *admin) +{ + for (int p = 0; p < lan966x->num_phys_ports; ++p) + lan_wr(0, lan966x, ANA_VCAP_S2_CFG(p)); +} + +int lan966x_vcap_init(struct lan966x *lan966x) +{ + struct lan966x_vcap_inst *cfg; + struct vcap_control *ctrl; + struct vcap_admin *admin; + + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + ctrl->vcaps = lan966x_vcaps; + ctrl->stats = &lan966x_vcap_stats; + ctrl->ops = &lan966x_vcap_ops; + + INIT_LIST_HEAD(&ctrl->list); + for (int i = 0; i < ARRAY_SIZE(lan966x_vcap_inst_cfg); ++i) { + cfg = &lan966x_vcap_inst_cfg[i]; + + admin = lan966x_vcap_admin_alloc(lan966x, ctrl, cfg); + if (IS_ERR(admin)) + return PTR_ERR(admin); + + lan966x_vcap_block_init(lan966x, admin, cfg); + lan966x_vcap_port_key_deselection(lan966x, admin); + + list_add_tail(&admin->list, &ctrl->list); + } + + lan966x->vcap_ctrl = ctrl; + + return 0; +} + +void lan966x_vcap_deinit(struct lan966x *lan966x) +{ + struct vcap_admin *admin, *admin_next; + struct vcap_control *ctrl; + + ctrl = lan966x->vcap_ctrl; + if (!ctrl) + return; + + list_for_each_entry_safe(admin, admin_next, &ctrl->list, list) { + lan966x_vcap_port_key_deselection(lan966x, admin); + vcap_del_rules(ctrl, admin); + list_del(&admin->list); + lan966x_vcap_admin_free(admin); + } + + kfree(ctrl); +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c new file mode 100644 index 000000000000..2e6f486ec67d --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/filter.h> + +#include "lan966x_main.h" + +static int lan966x_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + struct bpf_prog *old_prog; + bool old_xdp, new_xdp; + int err; + + if (!lan966x->fdma) { + NL_SET_ERR_MSG_MOD(xdp->extack, + "Allow to set xdp only when using fdma"); + return -EOPNOTSUPP; + } + + old_xdp = lan966x_xdp_present(lan966x); + old_prog = xchg(&port->xdp_prog, xdp->prog); + new_xdp = lan966x_xdp_present(lan966x); + + if (old_xdp == new_xdp) + goto out; + + err = lan966x_fdma_reload_page_pool(lan966x); + if (err) { + xchg(&port->xdp_prog, old_prog); + return err; + } + +out: + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +int lan966x_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return lan966x_xdp_setup(dev, xdp); + default: + return -EINVAL; + } +} + +int lan966x_xdp_xmit(struct net_device *dev, + int n, + struct xdp_frame **frames, + u32 flags) +{ + struct lan966x_port *port = netdev_priv(dev); + int nxmit = 0; + + for (int i = 0; i < n; ++i) { + struct xdp_frame *xdpf = frames[i]; + int err; + + err = lan966x_fdma_xmit_xdpf(port, xdpf, NULL, true); + if (err) + break; + + nxmit++; + } + + return nxmit; +} + +int lan966x_xdp_run(struct lan966x_port *port, struct page *page, u32 data_len) +{ + struct bpf_prog *xdp_prog = port->xdp_prog; + struct lan966x *lan966x = port->lan966x; + struct xdp_frame *xdpf; + struct xdp_buff xdp; + u32 act; + + xdp_init_buff(&xdp, PAGE_SIZE << lan966x->rx.page_order, + &port->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), + IFH_LEN_BYTES + XDP_PACKET_HEADROOM, + data_len - IFH_LEN_BYTES, false); + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + return FDMA_PASS; + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(&xdp); + if (!xdpf) + return FDMA_DROP; + + return lan966x_fdma_xmit_xdpf(port, xdpf, page, false) ? + FDMA_DROP : FDMA_TX; + case XDP_REDIRECT: + if (xdp_do_redirect(port->dev, &xdp, xdp_prog)) + return FDMA_DROP; + + return FDMA_REDIRECT; + default: + bpf_warn_invalid_xdp_action(port->dev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(port->dev, xdp_prog, act); + fallthrough; + case XDP_DROP: + return FDMA_DROP; + } +} + +bool lan966x_xdp_present(struct lan966x *lan966x) +{ + for (int p = 0; p < lan966x->num_phys_ports; ++p) { + if (!lan966x->ports[p]) + continue; + + if (lan966x_xdp_port_present(lan966x->ports[p])) + return true; + } + + return false; +} + +int lan966x_xdp_port_init(struct lan966x_port *port) +{ + struct lan966x *lan966x = port->lan966x; + + return xdp_rxq_info_reg(&port->xdp_rxq, port->dev, 0, + lan966x->napi.napi_id); +} + +void lan966x_xdp_port_deinit(struct lan966x_port *port) +{ + if (xdp_rxq_info_is_reg(&port->xdp_rxq)) + xdp_rxq_info_unreg(&port->xdp_rxq); +} diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index cc5e48e1bb4c..f58c506bda22 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -9,5 +9,17 @@ config SPARX5_SWITCH select PHYLINK select PHY_SPARX5_SERDES select RESET_CONTROLLER + select VCAP help This driver supports the Sparx5 network switch device. + +config SPARX5_DCB + bool "Data Center Bridging (DCB) support" + depends on SPARX5_SWITCH && DCB + default y + help + Say Y here if you want to use Data Center Bridging (DCB) in the + driver. This can be used to assign priority to traffic, based on + DSCP and PCP. + + If unsure, set to Y. diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index d1c6ad966747..d0ed7090aa54 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -5,7 +5,14 @@ obj-$(CONFIG_SPARX5_SWITCH) += sparx5-switch.o -sparx5-switch-objs := sparx5_main.o sparx5_packet.o \ +sparx5-switch-y := sparx5_main.o sparx5_packet.o \ sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \ sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o \ - sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o + sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o \ + sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o sparx5_tc_matchall.o + +sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o +sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o + +# Provide include files +ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c b/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c new file mode 100644 index 000000000000..74abb946b2a3 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include <net/dcbnl.h> + +#include "sparx5_port.h" + +enum sparx5_dcb_apptrust_values { + SPARX5_DCB_APPTRUST_EMPTY, + SPARX5_DCB_APPTRUST_DSCP, + SPARX5_DCB_APPTRUST_PCP, + SPARX5_DCB_APPTRUST_DSCP_PCP, + __SPARX5_DCB_APPTRUST_MAX +}; + +static const struct sparx5_dcb_apptrust { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1]; + int nselectors; +} *sparx5_port_apptrust[SPX5_PORTS]; + +static const char *sparx5_dcb_apptrust_names[__SPARX5_DCB_APPTRUST_MAX] = { + [SPARX5_DCB_APPTRUST_EMPTY] = "empty", + [SPARX5_DCB_APPTRUST_DSCP] = "dscp", + [SPARX5_DCB_APPTRUST_PCP] = "pcp", + [SPARX5_DCB_APPTRUST_DSCP_PCP] = "dscp pcp" +}; + +/* Sparx5 supported apptrust policies */ +static const struct sparx5_dcb_apptrust + sparx5_dcb_apptrust_policies[__SPARX5_DCB_APPTRUST_MAX] = { + /* Empty *must* be first */ + [SPARX5_DCB_APPTRUST_EMPTY] = { { 0 }, 0 }, + [SPARX5_DCB_APPTRUST_DSCP] = { { IEEE_8021QAZ_APP_SEL_DSCP }, 1 }, + [SPARX5_DCB_APPTRUST_PCP] = { { DCB_APP_SEL_PCP }, 1 }, + [SPARX5_DCB_APPTRUST_DSCP_PCP] = { { IEEE_8021QAZ_APP_SEL_DSCP, + DCB_APP_SEL_PCP }, 2 }, +}; + +/* Validate app entry. + * + * Check for valid selectors and valid protocol and priority ranges. + */ +static int sparx5_dcb_app_validate(struct net_device *dev, + const struct dcb_app *app) +{ + int err = 0; + + switch (app->selector) { + /* Default priority checks */ + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + if (app->protocol != 0) + err = -EINVAL; + else if (app->priority >= SPX5_PRIOS) + err = -ERANGE; + break; + /* Dscp checks */ + case IEEE_8021QAZ_APP_SEL_DSCP: + if (app->protocol >= SPARX5_PORT_QOS_DSCP_COUNT) + err = -EINVAL; + else if (app->priority >= SPX5_PRIOS) + err = -ERANGE; + break; + /* Pcp checks */ + case DCB_APP_SEL_PCP: + if (app->protocol >= SPARX5_PORT_QOS_PCP_DEI_COUNT) + err = -EINVAL; + else if (app->priority >= SPX5_PRIOS) + err = -ERANGE; + break; + default: + err = -EINVAL; + break; + } + + if (err) + netdev_err(dev, "Invalid entry: %d:%d\n", app->protocol, + app->priority); + + return err; +} + +/* Validate apptrust configuration. + * + * Return index of supported apptrust configuration if valid, otherwise return + * error. + */ +static int sparx5_dcb_apptrust_validate(struct net_device *dev, u8 *selectors, + int nselectors, int *err) +{ + bool match = false; + int i, ii; + + for (i = 0; i < ARRAY_SIZE(sparx5_dcb_apptrust_policies); i++) { + if (sparx5_dcb_apptrust_policies[i].nselectors != nselectors) + continue; + match = true; + for (ii = 0; ii < nselectors; ii++) { + if (sparx5_dcb_apptrust_policies[i].selectors[ii] != + *(selectors + ii)) { + match = false; + break; + } + } + if (match) + break; + } + + /* Requested trust configuration is not supported */ + if (!match) { + netdev_err(dev, "Valid apptrust configurations are:\n"); + for (i = 0; i < ARRAY_SIZE(sparx5_dcb_apptrust_names); i++) + pr_info("order: %s\n", sparx5_dcb_apptrust_names[i]); + *err = -EOPNOTSUPP; + } + + return i; +} + +static bool sparx5_dcb_apptrust_contains(int portno, u8 selector) +{ + const struct sparx5_dcb_apptrust *conf = sparx5_port_apptrust[portno]; + int i; + + for (i = 0; i < conf->nselectors; i++) + if (conf->selectors[i] == selector) + return true; + + return false; +} + +static int sparx5_dcb_app_update(struct net_device *dev) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5_port_qos_dscp_map *dscp_map; + struct sparx5_port_qos_pcp_map *pcp_map; + struct sparx5_port_qos qos = {0}; + struct dcb_app app_itr = {0}; + int portno = port->portno; + int i; + + dscp_map = &qos.dscp.map; + pcp_map = &qos.pcp.map; + + /* Get default prio. */ + qos.default_prio = dcb_ieee_getapp_default_prio_mask(dev); + if (qos.default_prio) + qos.default_prio = fls(qos.default_prio) - 1; + + /* Get dscp ingress mapping */ + for (i = 0; i < ARRAY_SIZE(dscp_map->map); i++) { + app_itr.selector = IEEE_8021QAZ_APP_SEL_DSCP; + app_itr.protocol = i; + dscp_map->map[i] = dcb_getapp(dev, &app_itr); + } + + /* Get pcp ingress mapping */ + for (i = 0; i < ARRAY_SIZE(pcp_map->map); i++) { + app_itr.selector = DCB_APP_SEL_PCP; + app_itr.protocol = i; + pcp_map->map[i] = dcb_getapp(dev, &app_itr); + } + + /* Enable use of pcp for queue classification ? */ + if (sparx5_dcb_apptrust_contains(portno, DCB_APP_SEL_PCP)) { + qos.pcp.qos_enable = true; + qos.pcp.dp_enable = qos.pcp.qos_enable; + } + + /* Enable use of dscp for queue classification ? */ + if (sparx5_dcb_apptrust_contains(portno, IEEE_8021QAZ_APP_SEL_DSCP)) { + qos.dscp.qos_enable = true; + qos.dscp.dp_enable = qos.dscp.qos_enable; + } + + return sparx5_port_qos_set(port, &qos); +} + +/* Set or delete dscp app entry. + * + * Dscp mapping is global for all ports, so set and delete app entries are + * replicated for each port. + */ +static int sparx5_dcb_ieee_dscp_setdel_app(struct net_device *dev, + struct dcb_app *app, bool del) +{ + struct sparx5_port *port = netdev_priv(dev); + struct dcb_app apps[SPX5_PORTS]; + struct sparx5_port *port_itr; + int err, i; + + for (i = 0; i < SPX5_PORTS; i++) { + port_itr = port->sparx5->ports[i]; + if (!port_itr) + continue; + memcpy(&apps[i], app, sizeof(struct dcb_app)); + if (del) + err = dcb_ieee_delapp(port_itr->ndev, &apps[i]); + else + err = dcb_ieee_setapp(port_itr->ndev, &apps[i]); + if (err) + return err; + } + + return 0; +} + +static int sparx5_dcb_ieee_setapp(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app app_itr; + int err = 0; + u8 prio; + + err = sparx5_dcb_app_validate(dev, app); + if (err) + goto out; + + /* Delete current mapping, if it exists */ + prio = dcb_getapp(dev, app); + if (prio) { + app_itr = *app; + app_itr.priority = prio; + dcb_ieee_delapp(dev, &app_itr); + } + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = sparx5_dcb_ieee_dscp_setdel_app(dev, app, false); + else + err = dcb_ieee_setapp(dev, app); + + if (err) + goto out; + + sparx5_dcb_app_update(dev); + +out: + return err; +} + +static int sparx5_dcb_ieee_delapp(struct net_device *dev, struct dcb_app *app) +{ + int err; + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = sparx5_dcb_ieee_dscp_setdel_app(dev, app, true); + else + err = dcb_ieee_delapp(dev, app); + + if (err < 0) + return err; + + return sparx5_dcb_app_update(dev); +} + +static int sparx5_dcb_setapptrust(struct net_device *dev, u8 *selectors, + int nselectors) +{ + struct sparx5_port *port = netdev_priv(dev); + int err = 0, idx; + + idx = sparx5_dcb_apptrust_validate(dev, selectors, nselectors, &err); + if (err < 0) + return err; + + sparx5_port_apptrust[port->portno] = &sparx5_dcb_apptrust_policies[idx]; + + return sparx5_dcb_app_update(dev); +} + +static int sparx5_dcb_getapptrust(struct net_device *dev, u8 *selectors, + int *nselectors) +{ + struct sparx5_port *port = netdev_priv(dev); + const struct sparx5_dcb_apptrust *trust; + + trust = sparx5_port_apptrust[port->portno]; + + memcpy(selectors, trust->selectors, trust->nselectors); + *nselectors = trust->nselectors; + + return 0; +} + +const struct dcbnl_rtnl_ops sparx5_dcbnl_ops = { + .ieee_setapp = sparx5_dcb_ieee_setapp, + .ieee_delapp = sparx5_dcb_ieee_delapp, + .dcbnl_setapptrust = sparx5_dcb_setapptrust, + .dcbnl_getapptrust = sparx5_dcb_getapptrust, +}; + +int sparx5_dcb_init(struct sparx5 *sparx5) +{ + struct sparx5_port *port; + int i; + + for (i = 0; i < SPX5_PORTS; i++) { + port = sparx5->ports[i]; + if (!port) + continue; + port->ndev->dcbnl_ops = &sparx5_dcbnl_ops; + /* Initialize [dscp, pcp] default trust */ + sparx5_port_apptrust[port->portno] = + &sparx5_dcb_apptrust_policies + [SPARX5_DCB_APPTRUST_DSCP_PCP]; + } + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index b6bbb3c9bd7a..d25f4f09faa0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -675,6 +675,14 @@ static int sparx5_start(struct sparx5 *sparx5) sparx5_board_init(sparx5); err = sparx5_register_notifier_blocks(sparx5); + if (err) + return err; + + err = sparx5_vcap_init(sparx5); + if (err) { + sparx5_unregister_notifier_blocks(sparx5); + return err; + } /* Start Frame DMA with fallback to register based INJ/XTR */ err = -ENXIO; @@ -755,6 +763,8 @@ static int mchp_sparx5_probe(struct platform_device *pdev) /* Default values, some from DT */ sparx5->coreclock = SPX5_CORE_CLOCK_DEFAULT; + sparx5->debugfs_root = debugfs_create_dir("sparx5", NULL); + ports = of_get_child_by_name(np, "ethernet-ports"); if (!ports) { dev_err(sparx5->dev, "no ethernet-ports child node found\n"); @@ -900,6 +910,7 @@ static int mchp_sparx5_remove(struct platform_device *pdev) { struct sparx5 *sparx5 = platform_get_drvdata(pdev); + debugfs_remove_recursive(sparx5->debugfs_root); if (sparx5->xtr_irq) { disable_irq(sparx5->xtr_irq); sparx5->xtr_irq = -ENXIO; @@ -911,6 +922,7 @@ static int mchp_sparx5_remove(struct platform_device *pdev) sparx5_ptp_deinit(sparx5); sparx5_fdma_stop(sparx5); sparx5_cleanup_ports(sparx5); + sparx5_vcap_destroy(sparx5); /* Unregister netdevs */ sparx5_unregister_notifier_blocks(sparx5); destroy_workqueue(sparx5->mact_queue); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 7a83222caa73..4a574cdcb584 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -17,6 +17,7 @@ #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include <linux/hrtimer.h> +#include <linux/debugfs.h> #include "sparx5_main_regs.h" @@ -288,8 +289,12 @@ struct sparx5 { struct mutex ptp_lock; /* lock for ptp interface state */ u16 ptp_skbs; int ptp_irq; + /* VCAP */ + struct vcap_control *vcap_ctrl; /* PGID allocation map */ u8 pgid_map[PGID_TABLE_SIZE]; + /* Common root for debugfs */ + struct dentry *debugfs_root; }; /* sparx5_switchdev.c */ @@ -357,6 +362,16 @@ int sparx5_config_dsm_calendar(struct sparx5 *sparx5); void sparx5_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats); int sparx_stats_init(struct sparx5 *sparx5); +/* sparx5_dcb.c */ +#ifdef CONFIG_SPARX5_DCB +int sparx5_dcb_init(struct sparx5 *sparx5); +#else +static inline int sparx5_dcb_init(struct sparx5 *sparx5) +{ + return 0; +} +#endif + /* sparx5_netdev.c */ void sparx5_set_port_ifh_timestamp(void *ifh_hdr, u64 timestamp); void sparx5_set_port_ifh_rew_op(void *ifh_hdr, u32 rew_op); @@ -382,6 +397,10 @@ void sparx5_ptp_txtstamp_release(struct sparx5_port *port, struct sk_buff *skb); irqreturn_t sparx5_ptp_irq_handler(int irq, void *args); +/* sparx5_vcap_impl.c */ +int sparx5_vcap_init(struct sparx5 *sparx5); +void sparx5_vcap_destroy(struct sparx5 *sparx5); + /* sparx5_pgid.c */ enum sparx5_pgid_type { SPX5_PGID_FREE, @@ -418,6 +437,7 @@ static inline bool sparx5_is_baser(phy_interface_t interface) extern const struct phylink_mac_ops sparx5_phylink_mac_ops; extern const struct phylink_pcs_ops sparx5_phylink_pcs_ops; extern const struct ethtool_ops sparx5_ethtool_ops; +extern const struct dcbnl_rtnl_ops sparx5_dcbnl_ops; /* Calculate raw offset */ static inline __pure int spx5_offset(int id, int tinst, int tcnt, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index fa2eb70f487a..6c93dd6b01b0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -4,8 +4,8 @@ * Copyright (c) 2021 Microchip Technology Inc. */ -/* This file is autogenerated by cml-utils 2022-02-26 14:15:01 +0100. - * Commit ID: 98bdd3d171cc2a1afd30d241d41a4281d471a48c (dirty) +/* This file is autogenerated by cml-utils 2022-09-28 11:17:02 +0200. + * Commit ID: 385c8a11d71a9f6a60368d3a3cb648fa257b479a */ #ifndef _SPARX5_MAIN_REGS_H_ @@ -171,6 +171,162 @@ enum sparx5_target { /* ANA_AC:STAT_CNT_CFG_PORT:STAT_LSB_CNT */ #define ANA_AC_PORT_STAT_LSB_CNT(g, r) __REG(TARGET_ANA_AC, 0, 1, 843776, g, 70, 64, 20, r, 4, 4) +/* ANA_ACL:COMMON:VCAP_S2_CFG */ +#define ANA_ACL_VCAP_S2_CFG(r) __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 0, r, 70, 4) + +#define ANA_ACL_VCAP_S2_CFG_SEC_ROUTE_HANDLING_ENA BIT(28) +#define ANA_ACL_VCAP_S2_CFG_SEC_ROUTE_HANDLING_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_ROUTE_HANDLING_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_ROUTE_HANDLING_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_ROUTE_HANDLING_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_OAM_ENA GENMASK(27, 26) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_OAM_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_OAM_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_OAM_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_OAM_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_OTHER_ENA GENMASK(25, 24) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_OTHER_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_OTHER_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_OTHER_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_OTHER_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_VID_ENA GENMASK(23, 22) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_VID_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_VID_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_VID_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_VID_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_STD_ENA GENMASK(21, 20) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_STD_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_STD_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_STD_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_STD_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_ENA GENMASK(19, 18) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP6_TCPUDP_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP_7TUPLE_ENA GENMASK(17, 16) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP_7TUPLE_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP_7TUPLE_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP_7TUPLE_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP_7TUPLE_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_VID_ENA GENMASK(15, 14) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_VID_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_VID_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_VID_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_VID_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_TCPUDP_ENA GENMASK(13, 12) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_TCPUDP_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_TCPUDP_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_TCPUDP_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_TCPUDP_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_OTHER_ENA GENMASK(11, 10) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_OTHER_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_OTHER_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_OTHER_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_IP4_OTHER_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_ARP_ENA GENMASK(9, 8) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_ARP_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_ARP_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_ARP_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_ARP_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_SNAP_ENA GENMASK(7, 6) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_SNAP_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_SNAP_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_SNAP_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_SNAP_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_LLC_ENA GENMASK(5, 4) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_LLC_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_LLC_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_LLC_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_TYPE_MAC_LLC_ENA, x) + +#define ANA_ACL_VCAP_S2_CFG_SEC_ENA GENMASK(3, 0) +#define ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_CFG_SEC_ENA, x) +#define ANA_ACL_VCAP_S2_CFG_SEC_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_CFG_SEC_ENA, x) + +/* ANA_ACL:COMMON:SWAP_IP_CTRL */ +#define ANA_ACL_SWAP_IP_CTRL __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 412, 0, 1, 4) + +#define ANA_ACL_SWAP_IP_CTRL_DMAC_REPL_OFFSET_VAL GENMASK(23, 18) +#define ANA_ACL_SWAP_IP_CTRL_DMAC_REPL_OFFSET_VAL_SET(x)\ + FIELD_PREP(ANA_ACL_SWAP_IP_CTRL_DMAC_REPL_OFFSET_VAL, x) +#define ANA_ACL_SWAP_IP_CTRL_DMAC_REPL_OFFSET_VAL_GET(x)\ + FIELD_GET(ANA_ACL_SWAP_IP_CTRL_DMAC_REPL_OFFSET_VAL, x) + +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_VAL GENMASK(17, 10) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_VAL_SET(x)\ + FIELD_PREP(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_VAL, x) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_VAL_GET(x)\ + FIELD_GET(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_VAL, x) + +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_VAL GENMASK(9, 2) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_VAL_SET(x)\ + FIELD_PREP(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_VAL, x) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_VAL_GET(x)\ + FIELD_GET(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_VAL, x) + +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_ENA BIT(1) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_ENA, x) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_ENA_GET(x)\ + FIELD_GET(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP6_HOPC_ENA, x) + +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_ENA BIT(0) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_ENA, x) +#define ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_ENA_GET(x)\ + FIELD_GET(ANA_ACL_SWAP_IP_CTRL_IP_SWAP_IP4_TTL_ENA, x) + +/* ANA_ACL:COMMON:VCAP_S2_RLEG_STAT */ +#define ANA_ACL_VCAP_S2_RLEG_STAT(r) __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 424, r, 4, 4) + +#define ANA_ACL_VCAP_S2_RLEG_STAT_IRLEG_STAT_MASK GENMASK(12, 6) +#define ANA_ACL_VCAP_S2_RLEG_STAT_IRLEG_STAT_MASK_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_RLEG_STAT_IRLEG_STAT_MASK, x) +#define ANA_ACL_VCAP_S2_RLEG_STAT_IRLEG_STAT_MASK_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_RLEG_STAT_IRLEG_STAT_MASK, x) + +#define ANA_ACL_VCAP_S2_RLEG_STAT_ERLEG_STAT_MASK GENMASK(5, 0) +#define ANA_ACL_VCAP_S2_RLEG_STAT_ERLEG_STAT_MASK_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_RLEG_STAT_ERLEG_STAT_MASK, x) +#define ANA_ACL_VCAP_S2_RLEG_STAT_ERLEG_STAT_MASK_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_RLEG_STAT_ERLEG_STAT_MASK, x) + +/* ANA_ACL:COMMON:VCAP_S2_FRAGMENT_CFG */ +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 440, 0, 1, 4) + +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_L4_MIN_LEN GENMASK(9, 5) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_L4_MIN_LEN_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_FRAGMENT_CFG_L4_MIN_LEN, x) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_L4_MIN_LEN_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_FRAGMENT_CFG_L4_MIN_LEN, x) + +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_DIS BIT(4) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_DIS_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_DIS, x) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_DIS_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_DIS, x) + +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES GENMASK(3, 0) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES, x) +#define ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_FRAGMENT_CFG_FRAGMENT_OFFSET_THRES, x) + /* ANA_ACL:COMMON:OWN_UPSID */ #define ANA_ACL_OWN_UPSID(r) __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 580, r, 3, 4) @@ -180,6 +336,174 @@ enum sparx5_target { #define ANA_ACL_OWN_UPSID_OWN_UPSID_GET(x)\ FIELD_GET(ANA_ACL_OWN_UPSID_OWN_UPSID, x) +/* ANA_ACL:KEY_SEL:VCAP_S2_KEY_SEL */ +#define ANA_ACL_VCAP_S2_KEY_SEL(g, r) __REG(TARGET_ANA_ACL, 0, 1, 34200, g, 134, 16, 0, r, 4, 4) + +#define ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA BIT(13) +#define ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_IGR_PORT_MASK_SEL BIT(12) +#define ANA_ACL_VCAP_S2_KEY_SEL_IGR_PORT_MASK_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_IGR_PORT_MASK_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_IGR_PORT_MASK_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_IGR_PORT_MASK_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL GENMASK(11, 10) +#define ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL GENMASK(9, 8) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL GENMASK(7, 6) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL GENMASK(5, 3) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL GENMASK(2, 1) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL, x) + +#define ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL BIT(0) +#define ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_SET(x)\ + FIELD_PREP(ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL, x) +#define ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_GET(x)\ + FIELD_GET(ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL, x) + +/* ANA_ACL:CNT_A:CNT_A */ +#define ANA_ACL_CNT_A(g) __REG(TARGET_ANA_ACL, 0, 1, 0, g, 4096, 4, 0, 0, 1, 4) + +/* ANA_ACL:CNT_B:CNT_B */ +#define ANA_ACL_CNT_B(g) __REG(TARGET_ANA_ACL, 0, 1, 16384, g, 4096, 4, 0, 0, 1, 4) + +/* ANA_ACL:STICKY:SEC_LOOKUP_STICKY */ +#define ANA_ACL_SEC_LOOKUP_STICKY(r) __REG(TARGET_ANA_ACL, 0, 1, 36408, 0, 1, 16, 0, r, 4, 4) + +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY BIT(17) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY BIT(16) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY BIT(15) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY BIT(14) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY BIT(13) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY BIT(12) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY BIT(11) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY BIT(10) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY BIT(9) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY BIT(8) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY BIT(7) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY BIT(6) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY BIT(5) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY BIT(4) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY BIT(3) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY BIT(2) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY BIT(1) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY, x) + +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY BIT(0) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_SET(x)\ + FIELD_PREP(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY, x) +#define ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_GET(x)\ + FIELD_GET(ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY, x) + /* ANA_AC_POL:POL_ALL_CFG:POL_UPD_INT_CFG */ #define ANA_AC_POL_POL_UPD_INT_CFG __REG(TARGET_ANA_AC_POL, 0, 1, 75968, 0, 1, 1160, 1148, 0, 1, 4) @@ -426,6 +750,96 @@ enum sparx5_target { #define ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT_GET(x)\ FIELD_GET(ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT, x) +/* ANA_CL:PORT:PCP_DEI_MAP_CFG */ +#define ANA_CL_PCP_DEI_MAP_CFG(g, r) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 108, r, 16, 4) + +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL GENMASK(4, 3) +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL_SET(x)\ + FIELD_PREP(ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL, x) +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL_GET(x)\ + FIELD_GET(ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL, x) + +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL GENMASK(2, 0) +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL_SET(x)\ + FIELD_PREP(ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL, x) +#define ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL_GET(x)\ + FIELD_GET(ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL, x) + +/* ANA_CL:PORT:QOS_CFG */ +#define ANA_CL_QOS_CFG(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 172, 0, 1, 4) + +#define ANA_CL_QOS_CFG_DEFAULT_COSID_ENA BIT(17) +#define ANA_CL_QOS_CFG_DEFAULT_COSID_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DEFAULT_COSID_ENA, x) +#define ANA_CL_QOS_CFG_DEFAULT_COSID_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DEFAULT_COSID_ENA, x) + +#define ANA_CL_QOS_CFG_DEFAULT_COSID_VAL GENMASK(16, 14) +#define ANA_CL_QOS_CFG_DEFAULT_COSID_VAL_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DEFAULT_COSID_VAL, x) +#define ANA_CL_QOS_CFG_DEFAULT_COSID_VAL_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DEFAULT_COSID_VAL, x) + +#define ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL GENMASK(13, 12) +#define ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL, x) +#define ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL, x) + +#define ANA_CL_QOS_CFG_DSCP_TRANSLATE_ENA BIT(11) +#define ANA_CL_QOS_CFG_DSCP_TRANSLATE_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DSCP_TRANSLATE_ENA, x) +#define ANA_CL_QOS_CFG_DSCP_TRANSLATE_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DSCP_TRANSLATE_ENA, x) + +#define ANA_CL_QOS_CFG_DSCP_KEEP_ENA BIT(10) +#define ANA_CL_QOS_CFG_DSCP_KEEP_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DSCP_KEEP_ENA, x) +#define ANA_CL_QOS_CFG_DSCP_KEEP_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DSCP_KEEP_ENA, x) + +#define ANA_CL_QOS_CFG_KEEP_ENA BIT(9) +#define ANA_CL_QOS_CFG_KEEP_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_KEEP_ENA, x) +#define ANA_CL_QOS_CFG_KEEP_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_KEEP_ENA, x) + +#define ANA_CL_QOS_CFG_PCP_DEI_DP_ENA BIT(8) +#define ANA_CL_QOS_CFG_PCP_DEI_DP_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_PCP_DEI_DP_ENA, x) +#define ANA_CL_QOS_CFG_PCP_DEI_DP_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_PCP_DEI_DP_ENA, x) + +#define ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA BIT(7) +#define ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA, x) +#define ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA, x) + +#define ANA_CL_QOS_CFG_DSCP_DP_ENA BIT(6) +#define ANA_CL_QOS_CFG_DSCP_DP_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DSCP_DP_ENA, x) +#define ANA_CL_QOS_CFG_DSCP_DP_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DSCP_DP_ENA, x) + +#define ANA_CL_QOS_CFG_DSCP_QOS_ENA BIT(5) +#define ANA_CL_QOS_CFG_DSCP_QOS_ENA_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DSCP_QOS_ENA, x) +#define ANA_CL_QOS_CFG_DSCP_QOS_ENA_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DSCP_QOS_ENA, x) + +#define ANA_CL_QOS_CFG_DEFAULT_DP_VAL GENMASK(4, 3) +#define ANA_CL_QOS_CFG_DEFAULT_DP_VAL_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DEFAULT_DP_VAL, x) +#define ANA_CL_QOS_CFG_DEFAULT_DP_VAL_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DEFAULT_DP_VAL, x) + +#define ANA_CL_QOS_CFG_DEFAULT_QOS_VAL GENMASK(2, 0) +#define ANA_CL_QOS_CFG_DEFAULT_QOS_VAL_SET(x)\ + FIELD_PREP(ANA_CL_QOS_CFG_DEFAULT_QOS_VAL, x) +#define ANA_CL_QOS_CFG_DEFAULT_QOS_VAL_GET(x)\ + FIELD_GET(ANA_CL_QOS_CFG_DEFAULT_QOS_VAL, x) + /* ANA_CL:PORT:CAPTURE_BPDU_CFG */ #define ANA_CL_CAPTURE_BPDU_CFG(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 196, 0, 1, 4) @@ -438,6 +852,39 @@ enum sparx5_target { #define ANA_CL_OWN_UPSID_OWN_UPSID_GET(x)\ FIELD_GET(ANA_CL_OWN_UPSID_OWN_UPSID, x) +/* ANA_CL:COMMON:DSCP_CFG */ +#define ANA_CL_DSCP_CFG(r) __REG(TARGET_ANA_CL, 0, 1, 166912, 0, 1, 756, 256, r, 64, 4) + +#define ANA_CL_DSCP_CFG_DSCP_TRANSLATE_VAL GENMASK(12, 7) +#define ANA_CL_DSCP_CFG_DSCP_TRANSLATE_VAL_SET(x)\ + FIELD_PREP(ANA_CL_DSCP_CFG_DSCP_TRANSLATE_VAL, x) +#define ANA_CL_DSCP_CFG_DSCP_TRANSLATE_VAL_GET(x)\ + FIELD_GET(ANA_CL_DSCP_CFG_DSCP_TRANSLATE_VAL, x) + +#define ANA_CL_DSCP_CFG_DSCP_QOS_VAL GENMASK(6, 4) +#define ANA_CL_DSCP_CFG_DSCP_QOS_VAL_SET(x)\ + FIELD_PREP(ANA_CL_DSCP_CFG_DSCP_QOS_VAL, x) +#define ANA_CL_DSCP_CFG_DSCP_QOS_VAL_GET(x)\ + FIELD_GET(ANA_CL_DSCP_CFG_DSCP_QOS_VAL, x) + +#define ANA_CL_DSCP_CFG_DSCP_DP_VAL GENMASK(3, 2) +#define ANA_CL_DSCP_CFG_DSCP_DP_VAL_SET(x)\ + FIELD_PREP(ANA_CL_DSCP_CFG_DSCP_DP_VAL, x) +#define ANA_CL_DSCP_CFG_DSCP_DP_VAL_GET(x)\ + FIELD_GET(ANA_CL_DSCP_CFG_DSCP_DP_VAL, x) + +#define ANA_CL_DSCP_CFG_DSCP_REWR_ENA BIT(1) +#define ANA_CL_DSCP_CFG_DSCP_REWR_ENA_SET(x)\ + FIELD_PREP(ANA_CL_DSCP_CFG_DSCP_REWR_ENA, x) +#define ANA_CL_DSCP_CFG_DSCP_REWR_ENA_GET(x)\ + FIELD_GET(ANA_CL_DSCP_CFG_DSCP_REWR_ENA, x) + +#define ANA_CL_DSCP_CFG_DSCP_TRUST_ENA BIT(0) +#define ANA_CL_DSCP_CFG_DSCP_TRUST_ENA_SET(x)\ + FIELD_PREP(ANA_CL_DSCP_CFG_DSCP_TRUST_ENA, x) +#define ANA_CL_DSCP_CFG_DSCP_TRUST_ENA_GET(x)\ + FIELD_GET(ANA_CL_DSCP_CFG_DSCP_TRUST_ENA, x) + /* ANA_L2:COMMON:AUTO_LRN_CFG */ #define ANA_L2_AUTO_LRN_CFG __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 24, 0, 1, 4) @@ -5039,6 +5486,138 @@ enum sparx5_target { #define REW_RAM_INIT_RAM_CFG_HOOK_GET(x)\ FIELD_GET(REW_RAM_INIT_RAM_CFG_HOOK, x) +/* VCAP_SUPER:VCAP_CORE_CFG:VCAP_UPDATE_CTRL */ +#define VCAP_SUPER_CTRL __REG(TARGET_VCAP_SUPER, 0, 1, 0, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_SUPER_CTRL_UPDATE_CMD GENMASK(24, 22) +#define VCAP_SUPER_CTRL_UPDATE_CMD_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_CMD, x) +#define VCAP_SUPER_CTRL_UPDATE_CMD_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_CMD, x) + +#define VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS BIT(21) +#define VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS, x) +#define VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS, x) + +#define VCAP_SUPER_CTRL_UPDATE_ACTION_DIS BIT(20) +#define VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_ACTION_DIS, x) +#define VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_ACTION_DIS, x) + +#define VCAP_SUPER_CTRL_UPDATE_CNT_DIS BIT(19) +#define VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_CNT_DIS, x) +#define VCAP_SUPER_CTRL_UPDATE_CNT_DIS_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_CNT_DIS, x) + +#define VCAP_SUPER_CTRL_UPDATE_ADDR GENMASK(18, 3) +#define VCAP_SUPER_CTRL_UPDATE_ADDR_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_ADDR, x) +#define VCAP_SUPER_CTRL_UPDATE_ADDR_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_ADDR, x) + +#define VCAP_SUPER_CTRL_UPDATE_SHOT BIT(2) +#define VCAP_SUPER_CTRL_UPDATE_SHOT_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_UPDATE_SHOT, x) +#define VCAP_SUPER_CTRL_UPDATE_SHOT_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_UPDATE_SHOT, x) + +#define VCAP_SUPER_CTRL_CLEAR_CACHE BIT(1) +#define VCAP_SUPER_CTRL_CLEAR_CACHE_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_CLEAR_CACHE, x) +#define VCAP_SUPER_CTRL_CLEAR_CACHE_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_CLEAR_CACHE, x) + +#define VCAP_SUPER_CTRL_MV_TRAFFIC_IGN BIT(0) +#define VCAP_SUPER_CTRL_MV_TRAFFIC_IGN_SET(x)\ + FIELD_PREP(VCAP_SUPER_CTRL_MV_TRAFFIC_IGN, x) +#define VCAP_SUPER_CTRL_MV_TRAFFIC_IGN_GET(x)\ + FIELD_GET(VCAP_SUPER_CTRL_MV_TRAFFIC_IGN, x) + +/* VCAP_SUPER:VCAP_CORE_CFG:VCAP_MV_CFG */ +#define VCAP_SUPER_CFG __REG(TARGET_VCAP_SUPER, 0, 1, 0, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_SUPER_CFG_MV_NUM_POS GENMASK(31, 16) +#define VCAP_SUPER_CFG_MV_NUM_POS_SET(x)\ + FIELD_PREP(VCAP_SUPER_CFG_MV_NUM_POS, x) +#define VCAP_SUPER_CFG_MV_NUM_POS_GET(x)\ + FIELD_GET(VCAP_SUPER_CFG_MV_NUM_POS, x) + +#define VCAP_SUPER_CFG_MV_SIZE GENMASK(15, 0) +#define VCAP_SUPER_CFG_MV_SIZE_SET(x)\ + FIELD_PREP(VCAP_SUPER_CFG_MV_SIZE, x) +#define VCAP_SUPER_CFG_MV_SIZE_GET(x)\ + FIELD_GET(VCAP_SUPER_CFG_MV_SIZE, x) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_ENTRY_DAT */ +#define VCAP_SUPER_VCAP_ENTRY_DAT(r) __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 0, r, 64, 4) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_MASK_DAT */ +#define VCAP_SUPER_VCAP_MASK_DAT(r) __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 256, r, 64, 4) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_ACTION_DAT */ +#define VCAP_SUPER_VCAP_ACTION_DAT(r) __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 512, r, 64, 4) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_CNT_DAT */ +#define VCAP_SUPER_VCAP_CNT_DAT(r) __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 768, r, 32, 4) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_CNT_FW_DAT */ +#define VCAP_SUPER_VCAP_CNT_FW_DAT __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 896, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CORE_CACHE:VCAP_TG_DAT */ +#define VCAP_SUPER_VCAP_TG_DAT __REG(TARGET_VCAP_SUPER, 0, 1, 8, 0, 1, 904, 900, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CORE_MAP:VCAP_CORE_IDX */ +#define VCAP_SUPER_IDX __REG(TARGET_VCAP_SUPER, 0, 1, 912, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_SUPER_IDX_CORE_IDX GENMASK(3, 0) +#define VCAP_SUPER_IDX_CORE_IDX_SET(x)\ + FIELD_PREP(VCAP_SUPER_IDX_CORE_IDX, x) +#define VCAP_SUPER_IDX_CORE_IDX_GET(x)\ + FIELD_GET(VCAP_SUPER_IDX_CORE_IDX, x) + +/* VCAP_SUPER:VCAP_CORE_MAP:VCAP_CORE_MAP */ +#define VCAP_SUPER_MAP __REG(TARGET_VCAP_SUPER, 0, 1, 912, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_SUPER_MAP_CORE_MAP GENMASK(2, 0) +#define VCAP_SUPER_MAP_CORE_MAP_SET(x)\ + FIELD_PREP(VCAP_SUPER_MAP_CORE_MAP, x) +#define VCAP_SUPER_MAP_CORE_MAP_GET(x)\ + FIELD_GET(VCAP_SUPER_MAP_CORE_MAP, x) + +/* VCAP_SUPER:VCAP_CONST:VCAP_VER */ +#define VCAP_SUPER_VCAP_VER __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 0, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ENTRY_WIDTH */ +#define VCAP_SUPER_ENTRY_WIDTH __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 4, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ENTRY_CNT */ +#define VCAP_SUPER_ENTRY_CNT __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 8, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ENTRY_SWCNT */ +#define VCAP_SUPER_ENTRY_SWCNT __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 12, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ENTRY_TG_WIDTH */ +#define VCAP_SUPER_ENTRY_TG_WIDTH __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 16, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ACTION_DEF_CNT */ +#define VCAP_SUPER_ACTION_DEF_CNT __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 20, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:ACTION_WIDTH */ +#define VCAP_SUPER_ACTION_WIDTH __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 24, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:CNT_WIDTH */ +#define VCAP_SUPER_CNT_WIDTH __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 28, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:CORE_CNT */ +#define VCAP_SUPER_CORE_CNT __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 32, 0, 1, 4) + +/* VCAP_SUPER:VCAP_CONST:IF_CNT */ +#define VCAP_SUPER_IF_CNT __REG(TARGET_VCAP_SUPER, 0, 1, 924, 0, 1, 40, 36, 0, 1, 4) + /* VCAP_SUPER:RAM_CTRL:RAM_INIT */ #define VCAP_SUPER_RAM_INIT __REG(TARGET_VCAP_SUPER, 0, 1, 1120, 0, 1, 4, 0, 0, 1, 4) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 830da0e5ff27..bb97d27a1da4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -138,7 +138,6 @@ const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { }; const struct phylink_mac_ops sparx5_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = sparx5_phylink_mac_select_pcs, .mac_config = sparx5_phylink_mac_config, .mac_link_down = sparx5_phylink_mac_link_down, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 32709d21ab2f..107b9cd931c0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -6,6 +6,7 @@ #include <linux/module.h> #include <linux/phy/phy.h> +#include <net/dcbnl.h> #include "sparx5_main_regs.h" #include "sparx5_main.h" @@ -1144,3 +1145,101 @@ void sparx5_port_enable(struct sparx5_port *port, bool enable) sparx5, QFWD_SWITCH_PORT_MODE(port->portno)); } + +int sparx5_port_qos_set(struct sparx5_port *port, + struct sparx5_port_qos *qos) +{ + sparx5_port_qos_dscp_set(port, &qos->dscp); + sparx5_port_qos_pcp_set(port, &qos->pcp); + sparx5_port_qos_default_set(port, qos); + + return 0; +} + +int sparx5_port_qos_pcp_set(const struct sparx5_port *port, + struct sparx5_port_qos_pcp *qos) +{ + struct sparx5 *sparx5 = port->sparx5; + u8 *pcp_itr = qos->map.map; + u8 pcp, dp; + int i; + + /* Enable/disable pcp and dp for qos classification. */ + spx5_rmw(ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA_SET(qos->qos_enable) | + ANA_CL_QOS_CFG_PCP_DEI_DP_ENA_SET(qos->dp_enable), + ANA_CL_QOS_CFG_PCP_DEI_QOS_ENA | ANA_CL_QOS_CFG_PCP_DEI_DP_ENA, + sparx5, ANA_CL_QOS_CFG(port->portno)); + + /* Map each pcp and dei value to priority and dp */ + for (i = 0; i < ARRAY_SIZE(qos->map.map); i++) { + pcp = *(pcp_itr + i); + dp = (i < SPARX5_PORT_QOS_PCP_COUNT) ? 0 : 1; + spx5_rmw(ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL_SET(pcp) | + ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL_SET(dp), + ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_QOS_VAL | + ANA_CL_PCP_DEI_MAP_CFG_PCP_DEI_DP_VAL, sparx5, + ANA_CL_PCP_DEI_MAP_CFG(port->portno, i)); + } + + return 0; +} + +int sparx5_port_qos_dscp_set(const struct sparx5_port *port, + struct sparx5_port_qos_dscp *qos) +{ + struct sparx5 *sparx5 = port->sparx5; + u8 *dscp = qos->map.map; + int i; + + /* Enable/disable dscp and dp for qos classification. + * Disable rewrite of dscp values for now. + */ + spx5_rmw(ANA_CL_QOS_CFG_DSCP_QOS_ENA_SET(qos->qos_enable) | + ANA_CL_QOS_CFG_DSCP_DP_ENA_SET(qos->dp_enable) | + ANA_CL_QOS_CFG_DSCP_KEEP_ENA_SET(1), + ANA_CL_QOS_CFG_DSCP_QOS_ENA | ANA_CL_QOS_CFG_DSCP_DP_ENA | + ANA_CL_QOS_CFG_DSCP_KEEP_ENA, sparx5, + ANA_CL_QOS_CFG(port->portno)); + + /* Map each dscp value to priority and dp */ + for (i = 0; i < ARRAY_SIZE(qos->map.map); i++) { + spx5_rmw(ANA_CL_DSCP_CFG_DSCP_QOS_VAL_SET(*(dscp + i)) | + ANA_CL_DSCP_CFG_DSCP_DP_VAL_SET(0), + ANA_CL_DSCP_CFG_DSCP_QOS_VAL | + ANA_CL_DSCP_CFG_DSCP_DP_VAL, sparx5, + ANA_CL_DSCP_CFG(i)); + } + + /* Set per-dscp trust */ + for (i = 0; i < ARRAY_SIZE(qos->map.map); i++) { + if (qos->qos_enable) { + spx5_rmw(ANA_CL_DSCP_CFG_DSCP_TRUST_ENA_SET(1), + ANA_CL_DSCP_CFG_DSCP_TRUST_ENA, sparx5, + ANA_CL_DSCP_CFG(i)); + } + } + + return 0; +} + +int sparx5_port_qos_default_set(const struct sparx5_port *port, + const struct sparx5_port_qos *qos) +{ + struct sparx5 *sparx5 = port->sparx5; + + /* Set default prio and dp level */ + spx5_rmw(ANA_CL_QOS_CFG_DEFAULT_QOS_VAL_SET(qos->default_prio) | + ANA_CL_QOS_CFG_DEFAULT_DP_VAL_SET(0), + ANA_CL_QOS_CFG_DEFAULT_QOS_VAL | + ANA_CL_QOS_CFG_DEFAULT_DP_VAL, + sparx5, ANA_CL_QOS_CFG(port->portno)); + + /* Set default pcp and dei for untagged frames */ + spx5_rmw(ANA_CL_VLAN_CTRL_PORT_PCP_SET(0) | + ANA_CL_VLAN_CTRL_PORT_DEI_SET(0), + ANA_CL_VLAN_CTRL_PORT_PCP | + ANA_CL_VLAN_CTRL_PORT_DEI, + sparx5, ANA_CL_VLAN_CTRL(port->portno)); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h index 2f8043eac71b..fbafe22e25cc 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h @@ -91,4 +91,46 @@ int sparx5_get_port_status(struct sparx5 *sparx5, void sparx5_port_enable(struct sparx5_port *port, bool enable); int sparx5_port_fwd_urg(struct sparx5 *sparx5, u32 speed); +#define SPARX5_PORT_QOS_PCP_COUNT 8 +#define SPARX5_PORT_QOS_DEI_COUNT 8 +#define SPARX5_PORT_QOS_PCP_DEI_COUNT \ + (SPARX5_PORT_QOS_PCP_COUNT + SPARX5_PORT_QOS_DEI_COUNT) +struct sparx5_port_qos_pcp_map { + u8 map[SPARX5_PORT_QOS_PCP_DEI_COUNT]; +}; + +#define SPARX5_PORT_QOS_DSCP_COUNT 64 +struct sparx5_port_qos_dscp_map { + u8 map[SPARX5_PORT_QOS_DSCP_COUNT]; +}; + +struct sparx5_port_qos_pcp { + struct sparx5_port_qos_pcp_map map; + bool qos_enable; + bool dp_enable; +}; + +struct sparx5_port_qos_dscp { + struct sparx5_port_qos_dscp_map map; + bool qos_enable; + bool dp_enable; +}; + +struct sparx5_port_qos { + struct sparx5_port_qos_pcp pcp; + struct sparx5_port_qos_dscp dscp; + u8 default_prio; +}; + +int sparx5_port_qos_set(struct sparx5_port *port, struct sparx5_port_qos *qos); + +int sparx5_port_qos_pcp_set(const struct sparx5_port *port, + struct sparx5_port_qos_pcp *qos); + +int sparx5_port_qos_dscp_set(const struct sparx5_port *port, + struct sparx5_port_qos_dscp *qos); + +int sparx5_port_qos_default_set(const struct sparx5_port *port, + const struct sparx5_port_qos *qos); + #endif /* __SPARX5_PORT_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c index 1e79d0ef0cb8..379e540e5e6a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c @@ -389,6 +389,10 @@ int sparx5_qos_init(struct sparx5 *sparx5) if (ret < 0) return ret; + ret = sparx5_dcb_init(sparx5); + if (ret < 0) + return ret; + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index dc2c3756e3a2..205246b5af82 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -10,6 +10,55 @@ #include "sparx5_main.h" #include "sparx5_qos.h" +/* tc block handling */ +static LIST_HEAD(sparx5_block_cb_list); + +static int sparx5_tc_block_cb(enum tc_setup_type type, + void *type_data, + void *cb_priv, bool ingress) +{ + struct net_device *ndev = cb_priv; + + switch (type) { + case TC_SETUP_CLSMATCHALL: + return sparx5_tc_matchall(ndev, type_data, ingress); + case TC_SETUP_CLSFLOWER: + return sparx5_tc_flower(ndev, type_data, ingress); + default: + return -EOPNOTSUPP; + } +} + +static int sparx5_tc_block_cb_ingress(enum tc_setup_type type, + void *type_data, + void *cb_priv) +{ + return sparx5_tc_block_cb(type, type_data, cb_priv, true); +} + +static int sparx5_tc_block_cb_egress(enum tc_setup_type type, + void *type_data, + void *cb_priv) +{ + return sparx5_tc_block_cb(type, type_data, cb_priv, false); +} + +static int sparx5_tc_setup_block(struct net_device *ndev, + struct flow_block_offload *fbo) +{ + flow_setup_cb_t *cb; + + if (fbo->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + cb = sparx5_tc_block_cb_ingress; + else if (fbo->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + cb = sparx5_tc_block_cb_egress; + else + return -EOPNOTSUPP; + + return flow_block_cb_setup_simple(fbo, &sparx5_block_cb_list, + cb, ndev, ndev, false); +} + static void sparx5_tc_get_layer_and_idx(u32 parent, u32 portno, u32 *layer, u32 *idx) { @@ -108,6 +157,8 @@ int sparx5_port_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data) { switch (type) { + case TC_SETUP_BLOCK: + return sparx5_tc_setup_block(ndev, type_data); case TC_SETUP_QDISC_MQPRIO: return sparx5_tc_setup_qdisc_mqprio(ndev, type_data); case TC_SETUP_QDISC_TBF: diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h index 5b55e11b77e1..adab88e6b21f 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h @@ -7,9 +7,28 @@ #ifndef __SPARX5_TC_H__ #define __SPARX5_TC_H__ +#include <net/flow_offload.h> +#include <net/pkt_cls.h> #include <linux/netdevice.h> +/* Controls how PORT_MASK is applied */ +enum SPX5_PORT_MASK_MODE { + SPX5_PMM_OR_DSTMASK, + SPX5_PMM_AND_VLANMASK, + SPX5_PMM_REPLACE_PGID, + SPX5_PMM_REPLACE_ALL, + SPX5_PMM_REDIR_PGID, + SPX5_PMM_OR_PGID_MASK, +}; + int sparx5_port_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data); +int sparx5_tc_matchall(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress); + +int sparx5_tc_flower(struct net_device *ndev, struct flow_cls_offload *fco, + bool ingress); + #endif /* __SPARX5_TC_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c new file mode 100644 index 000000000000..1ed304a816cc --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -0,0 +1,1016 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP API + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include <net/tcp.h> + +#include "sparx5_tc.h" +#include "vcap_api.h" +#include "vcap_api_client.h" +#include "sparx5_main.h" +#include "sparx5_vcap_impl.h" + +#define SPX5_MAX_RULE_SIZE 13 /* allows X1, X2, X4, X6 and X12 rules */ + +/* Collect keysets and type ids for multiple rules per size */ +struct sparx5_wildcard_rule { + bool selected; + u8 value; + u8 mask; + enum vcap_keyfield_set keyset; +}; + +struct sparx5_multiple_rules { + struct sparx5_wildcard_rule rule[SPX5_MAX_RULE_SIZE]; +}; + +struct sparx5_tc_flower_parse_usage { + struct flow_cls_offload *fco; + struct flow_rule *frule; + struct vcap_rule *vrule; + u16 l3_proto; + u8 l4_proto; + unsigned int used_keys; +}; + +struct sparx5_tc_rule_pkt_cnt { + u64 cookie; + u32 pkts; +}; + +/* These protocols have dedicated keysets in IS2 and a TC dissector + * ETH_P_ARP does not have a TC dissector + */ +static u16 sparx5_tc_known_etypes[] = { + ETH_P_ALL, + ETH_P_ARP, + ETH_P_IP, + ETH_P_IPV6, +}; + +enum sparx5_is2_arp_opcode { + SPX5_IS2_ARP_REQUEST, + SPX5_IS2_ARP_REPLY, + SPX5_IS2_RARP_REQUEST, + SPX5_IS2_RARP_REPLY, +}; + +enum tc_arp_opcode { + TC_ARP_OP_RESERVED, + TC_ARP_OP_REQUEST, + TC_ARP_OP_REPLY, +}; + +static bool sparx5_tc_is_known_etype(u16 etype) +{ + int idx; + + /* For now this only knows about IS2 traffic classification */ + for (idx = 0; idx < ARRAY_SIZE(sparx5_tc_known_etypes); ++idx) + if (sparx5_tc_known_etypes[idx] == etype) + return true; + + return false; +} + +static int sparx5_tc_flower_handler_ethaddr_usage(struct sparx5_tc_flower_parse_usage *st) +{ + enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; + enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; + struct flow_match_eth_addrs match; + struct vcap_u48_key smac, dmac; + int err = 0; + + flow_rule_match_eth_addrs(st->frule, &match); + + if (!is_zero_ether_addr(match.mask->src)) { + vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); + vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + if (err) + goto out; + } + + if (!is_zero_ether_addr(match.mask->dst)) { + vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); + vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "eth_addr parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_ipv4_usage(struct sparx5_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IP) { + struct flow_match_ipv4_addrs mt; + + flow_rule_match_ipv4_addrs(st->frule, &mt); + if (mt.mask->src) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_SIP, + be32_to_cpu(mt.key->src), + be32_to_cpu(mt.mask->src)); + if (err) + goto out; + } + if (mt.mask->dst) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_DIP, + be32_to_cpu(mt.key->dst), + be32_to_cpu(mt.mask->dst)); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_ipv6_usage(struct sparx5_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IPV6) { + struct flow_match_ipv6_addrs mt; + struct vcap_u128_key sip; + struct vcap_u128_key dip; + + flow_rule_match_ipv6_addrs(st->frule, &mt); + /* Check if address masks are non-zero */ + if (!ipv6_addr_any(&mt.mask->src)) { + vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); + vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_SIP, &sip); + if (err) + goto out; + } + if (!ipv6_addr_any(&mt.mask->dst)) { + vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); + vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_DIP, &dip); + if (err) + goto out; + } + } + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_control_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_control mt; + u32 value, mask; + int err = 0; + + flow_rule_match_control(st->frule, &mt); + + if (mt.mask->flags) { + if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { + value = 1; /* initial fragment */ + mask = 0x3; + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_FRAGMENT_TYPE, + value, mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_portnum_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_ports mt; + u16 value, mask; + int err = 0; + + flow_rule_match_ports(st->frule, &mt); + + if (mt.mask->src) { + value = be16_to_cpu(mt.key->src); + mask = be16_to_cpu(mt.mask->src); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, + mask); + if (err) + goto out; + } + + if (mt.mask->dst) { + value = be16_to_cpu(mt.key->dst); + mask = be16_to_cpu(mt.mask->dst); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, + mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_basic mt; + int err = 0; + + flow_rule_match_basic(st->frule, &mt); + + if (mt.mask->n_proto) { + st->l3_proto = be16_to_cpu(mt.key->n_proto); + if (!sparx5_tc_is_known_etype(st->l3_proto)) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE, + st->l3_proto, ~0); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IP) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IPV6) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_0); + if (err) + goto out; + } + } + + if (mt.mask->ip_proto) { + st->l4_proto = mt.key->ip_proto; + if (st->l4_proto == IPPROTO_TCP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l4_proto == IPPROTO_UDP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_0); + if (err) + goto out; + } else { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP_PROTO, + st->l4_proto, ~0); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_vlan_usage(struct sparx5_tc_flower_parse_usage *st) +{ + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; + struct flow_match_vlan mt; + int err; + + flow_rule_match_vlan(st->frule, &mt); + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + + return 0; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_tcp_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_tcp mt; + u16 tcp_flags_mask; + u16 tcp_flags_key; + enum vcap_bit val; + int err = 0; + + flow_rule_match_tcp(st->frule, &mt); + tcp_flags_key = be16_to_cpu(mt.key->flags); + tcp_flags_mask = be16_to_cpu(mt.mask->flags); + + if (tcp_flags_mask & TCPHDR_FIN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_FIN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_SYN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_SYN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_RST) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_RST) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_PSH) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_PSH) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_ACK) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_ACK) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_URG) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_URG) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_arp_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_arp mt; + u16 value, mask; + u32 ipval, ipmsk; + int err; + + flow_rule_match_arp(st->frule, &mt); + + if (mt.mask->op) { + mask = 0x3; + if (st->l3_proto == ETH_P_ARP) { + value = mt.key->op == TC_ARP_OP_REQUEST ? + SPX5_IS2_ARP_REQUEST : + SPX5_IS2_ARP_REPLY; + } else { /* RARP */ + value = mt.key->op == TC_ARP_OP_REQUEST ? + SPX5_IS2_RARP_REQUEST : + SPX5_IS2_RARP_REPLY; + } + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ARP_OPCODE, + value, mask); + if (err) + goto out; + } + + /* The IS2 ARP keyset does not support ARP hardware addresses */ + if (!is_zero_ether_addr(mt.mask->sha) || + !is_zero_ether_addr(mt.mask->tha)) { + err = -EINVAL; + goto out; + } + + if (mt.mask->sip) { + ipval = be32_to_cpu((__force __be32)mt.key->sip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->sip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_SIP, + ipval, ipmsk); + if (err) + goto out; + } + + if (mt.mask->tip) { + ipval = be32_to_cpu((__force __be32)mt.key->tip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->tip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_DIP, + ipval, ipmsk); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); + + return 0; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "arp parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_ip_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_ip mt; + int err = 0; + + flow_rule_match_ip(st->frule, &mt); + + if (mt.mask->tos) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, + mt.key->tos, + mt.mask->tos); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); + return err; +} + +static int (*sparx5_tc_flower_usage_handlers[])(struct sparx5_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = sparx5_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = sparx5_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = sparx5_tc_flower_handler_ipv6_usage, + [FLOW_DISSECTOR_KEY_CONTROL] = sparx5_tc_flower_handler_control_usage, + [FLOW_DISSECTOR_KEY_PORTS] = sparx5_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_BASIC] = sparx5_tc_flower_handler_basic_usage, + [FLOW_DISSECTOR_KEY_VLAN] = sparx5_tc_flower_handler_vlan_usage, + [FLOW_DISSECTOR_KEY_TCP] = sparx5_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_ARP] = sparx5_tc_flower_handler_arp_usage, + [FLOW_DISSECTOR_KEY_IP] = sparx5_tc_flower_handler_ip_usage, +}; + +static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, + struct vcap_admin *admin, + struct vcap_rule *vrule, + u16 *l3_proto) +{ + struct sparx5_tc_flower_parse_usage state = { + .fco = fco, + .vrule = vrule, + .l3_proto = ETH_P_ALL, + }; + int idx, err = 0; + + state.frule = flow_cls_offload_flow_rule(fco); + for (idx = 0; idx < ARRAY_SIZE(sparx5_tc_flower_usage_handlers); ++idx) { + if (!flow_rule_match_key(state.frule, idx)) + continue; + if (!sparx5_tc_flower_usage_handlers[idx]) + continue; + err = sparx5_tc_flower_usage_handlers[idx](&state); + if (err) + return err; + } + + if (state.frule->match.dissector->used_keys ^ state.used_keys) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Unsupported match item"); + return -ENOENT; + } + + if (l3_proto) + *l3_proto = state.l3_proto; + return err; +} + +static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(fco); + struct flow_action_entry *actent, *last_actent = NULL; + struct flow_action *act = &rule->action; + u64 action_mask = 0; + int idx; + + if (!flow_action_has_entries(act)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, "No actions"); + return -EINVAL; + } + + if (!flow_action_basic_hw_stats_check(act, fco->common.extack)) + return -EOPNOTSUPP; + + flow_action_for_each(idx, actent, act) { + if (action_mask & BIT(actent->id)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "More actions of the same type"); + return -EINVAL; + } + action_mask |= BIT(actent->id); + last_actent = actent; /* Save last action for later check */ + } + + /* Check that last action is a goto */ + if (last_actent->id != FLOW_ACTION_GOTO) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Last action must be 'goto'"); + return -EINVAL; + } + + /* Check if the goto chain is in the next lookup */ + if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, + last_actent->chain_index)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Invalid goto chain"); + return -EINVAL; + } + + /* Catch unsupported combinations of actions */ + if (action_mask & BIT(FLOW_ACTION_TRAP) && + action_mask & BIT(FLOW_ACTION_ACCEPT)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Cannot combine pass and trap action"); + return -EOPNOTSUPP; + } + + return 0; +} + +/* Add a rule counter action - only IS2 is considered for now */ +static int sparx5_tc_add_rule_counter(struct vcap_admin *admin, + struct vcap_rule *vrule) +{ + int err; + + err = vcap_rule_mod_action_u32(vrule, VCAP_AF_CNT_ID, vrule->id); + if (err) + return err; + + vcap_rule_set_counter_id(vrule, vrule->id); + return err; +} + +/* Collect all port keysets and apply the first of them, possibly wildcarded */ +static int sparx5_tc_select_protocol_keyset(struct net_device *ndev, + struct vcap_rule *vrule, + struct vcap_admin *admin, + u16 l3_proto, + struct sparx5_multiple_rules *multi) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct vcap_keyset_list portkeysetlist = {}; + enum vcap_keyfield_set portkeysets[10] = {}; + struct vcap_keyset_list matches = {}; + enum vcap_keyfield_set keysets[10]; + int idx, jdx, err = 0, count = 0; + struct sparx5_wildcard_rule *mru; + const struct vcap_set *kinfo; + struct vcap_control *vctrl; + + vctrl = port->sparx5->vcap_ctrl; + + /* Find the keysets that the rule can use */ + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + if (vcap_rule_find_keysets(vrule, &matches) == 0) + return -EINVAL; + + /* Find the keysets that the port configuration supports */ + portkeysetlist.max = ARRAY_SIZE(portkeysets); + portkeysetlist.keysets = portkeysets; + err = sparx5_vcap_get_port_keyset(ndev, + admin, vrule->vcap_chain_id, + l3_proto, + &portkeysetlist); + if (err) + return err; + + /* Find the intersection of the two sets of keyset */ + for (idx = 0; idx < portkeysetlist.cnt; ++idx) { + kinfo = vcap_keyfieldset(vctrl, admin->vtype, + portkeysetlist.keysets[idx]); + if (!kinfo) + continue; + + /* Find a port keyset that matches the required keys + * If there are multiple keysets then compose a type id mask + */ + for (jdx = 0; jdx < matches.cnt; ++jdx) { + if (portkeysetlist.keysets[idx] != matches.keysets[jdx]) + continue; + + mru = &multi->rule[kinfo->sw_per_item]; + if (!mru->selected) { + mru->selected = true; + mru->keyset = portkeysetlist.keysets[idx]; + mru->value = kinfo->type_id; + } + mru->value &= kinfo->type_id; + mru->mask |= kinfo->type_id; + ++count; + } + } + if (count == 0) + return -EPROTO; + + if (l3_proto == ETH_P_ALL && count < portkeysetlist.cnt) + return -ENOENT; + + for (idx = 0; idx < SPX5_MAX_RULE_SIZE; ++idx) { + mru = &multi->rule[idx]; + if (!mru->selected) + continue; + + /* Align the mask to the combined value */ + mru->mask ^= mru->value; + } + + /* Set the chosen keyset on the rule and set a wildcarded type if there + * are more than one keyset + */ + for (idx = 0; idx < SPX5_MAX_RULE_SIZE; ++idx) { + mru = &multi->rule[idx]; + if (!mru->selected) + continue; + + vcap_set_rule_set_keyset(vrule, mru->keyset); + if (count > 1) + /* Some keysets do not have a type field */ + vcap_rule_mod_key_u32(vrule, VCAP_KF_TYPE, + mru->value, + ~mru->mask); + mru->selected = false; /* mark as done */ + break; /* Stop here and add more rules later */ + } + return err; +} + +static int sparx5_tc_add_rule_copy(struct vcap_control *vctrl, + struct flow_cls_offload *fco, + struct vcap_rule *erule, + struct vcap_admin *admin, + struct sparx5_wildcard_rule *rule) +{ + enum vcap_key_field keylist[] = { + VCAP_KF_IF_IGR_PORT_MASK, + VCAP_KF_IF_IGR_PORT_MASK_SEL, + VCAP_KF_IF_IGR_PORT_MASK_RNG, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_TYPE, + }; + struct vcap_rule *vrule; + int err; + + /* Add an extra rule with a special user and the new keyset */ + erule->user = VCAP_USER_TC_EXTRA; + vrule = vcap_copy_rule(erule); + if (IS_ERR(vrule)) + return PTR_ERR(vrule); + + /* Link the new rule to the existing rule with the cookie */ + vrule->cookie = erule->cookie; + vcap_filter_rule_keys(vrule, keylist, ARRAY_SIZE(keylist), true); + err = vcap_set_rule_set_keyset(vrule, rule->keyset); + if (err) { + pr_err("%s:%d: could not set keyset %s in rule: %u\n", + __func__, __LINE__, + vcap_keyset_name(vctrl, rule->keyset), + vrule->id); + goto out; + } + + /* Some keysets do not have a type field, so ignore return value */ + vcap_rule_mod_key_u32(vrule, VCAP_KF_TYPE, rule->value, ~rule->mask); + + err = vcap_set_rule_set_actionset(vrule, erule->actionset); + if (err) + goto out; + + err = sparx5_tc_add_rule_counter(admin, vrule); + if (err) + goto out; + + err = vcap_val_rule(vrule, ETH_P_ALL); + if (err) { + pr_err("%s:%d: could not validate rule: %u\n", + __func__, __LINE__, vrule->id); + vcap_set_tc_exterr(fco, vrule); + goto out; + } + err = vcap_add_rule(vrule); + if (err) { + pr_err("%s:%d: could not add rule: %u\n", + __func__, __LINE__, vrule->id); + goto out; + } +out: + vcap_free_rule(vrule); + return err; +} + +static int sparx5_tc_add_remaining_rules(struct vcap_control *vctrl, + struct flow_cls_offload *fco, + struct vcap_rule *erule, + struct vcap_admin *admin, + struct sparx5_multiple_rules *multi) +{ + int idx, err = 0; + + for (idx = 0; idx < SPX5_MAX_RULE_SIZE; ++idx) { + if (!multi->rule[idx].selected) + continue; + + err = sparx5_tc_add_rule_copy(vctrl, fco, erule, admin, + &multi->rule[idx]); + if (err) + break; + } + return err; +} + +static int sparx5_tc_flower_replace(struct net_device *ndev, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5_multiple_rules multi = {}; + struct flow_action_entry *act; + struct vcap_control *vctrl; + struct flow_rule *frule; + struct vcap_rule *vrule; + u16 l3_proto; + int err, idx; + + vctrl = port->sparx5->vcap_ctrl; + + err = sparx5_tc_flower_action_check(vctrl, fco, admin); + if (err) + return err; + + vrule = vcap_alloc_rule(vctrl, ndev, fco->common.chain_index, VCAP_USER_TC, + fco->common.prio, 0); + if (IS_ERR(vrule)) + return PTR_ERR(vrule); + + vrule->cookie = fco->cookie; + + l3_proto = ETH_P_ALL; + err = sparx5_tc_use_dissectors(fco, admin, vrule, &l3_proto); + if (err) + goto out; + + err = sparx5_tc_add_rule_counter(admin, vrule); + if (err) + goto out; + + frule = flow_cls_offload_flow_rule(fco); + flow_action_for_each(idx, act, &frule->action) { + switch (act->id) { + case FLOW_ACTION_TRAP: + err = vcap_rule_add_action_bit(vrule, + VCAP_AF_CPU_COPY_ENA, + VCAP_BIT_1); + if (err) + goto out; + err = vcap_rule_add_action_u32(vrule, + VCAP_AF_CPU_QUEUE_NUM, 0); + if (err) + goto out; + err = vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE, + SPX5_PMM_REPLACE_ALL); + if (err) + goto out; + /* For now the actionset is hardcoded */ + err = vcap_set_rule_set_actionset(vrule, + VCAP_AFS_BASE_TYPE); + if (err) + goto out; + break; + case FLOW_ACTION_ACCEPT: + /* For now the actionset is hardcoded */ + err = vcap_set_rule_set_actionset(vrule, + VCAP_AFS_BASE_TYPE); + if (err) + goto out; + break; + case FLOW_ACTION_GOTO: + /* Links between VCAPs will be added later */ + break; + default: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Unsupported TC action"); + err = -EOPNOTSUPP; + goto out; + } + } + + err = sparx5_tc_select_protocol_keyset(ndev, vrule, admin, l3_proto, + &multi); + if (err) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "No matching port keyset for filter protocol and keys"); + goto out; + } + + /* provide the l3 protocol to guide the keyset selection */ + err = vcap_val_rule(vrule, l3_proto); + if (err) { + vcap_set_tc_exterr(fco, vrule); + goto out; + } + err = vcap_add_rule(vrule); + if (err) + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Could not add the filter"); + + if (l3_proto == ETH_P_ALL) + err = sparx5_tc_add_remaining_rules(vctrl, fco, vrule, admin, + &multi); + +out: + vcap_free_rule(vrule); + return err; +} + +static int sparx5_tc_flower_destroy(struct net_device *ndev, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct vcap_control *vctrl; + int err = -ENOENT, rule_id; + + vctrl = port->sparx5->vcap_ctrl; + while (true) { + rule_id = vcap_lookup_rule_by_cookie(vctrl, fco->cookie); + if (rule_id <= 0) + break; + err = vcap_del_rule(vctrl, ndev, rule_id); + if (err) { + pr_err("%s:%d: could not delete rule %d\n", + __func__, __LINE__, rule_id); + break; + } + } + return err; +} + +/* Collect packet counts from all rules with the same cookie */ +static int sparx5_tc_rule_counter_cb(void *arg, struct vcap_rule *rule) +{ + struct sparx5_tc_rule_pkt_cnt *rinfo = arg; + struct vcap_counter counter; + int err = 0; + + if (rule->cookie == rinfo->cookie) { + err = vcap_rule_get_counter(rule, &counter); + if (err) + return err; + rinfo->pkts += counter.value; + /* Reset the rule counter */ + counter.value = 0; + vcap_rule_set_counter(rule, &counter); + } + return err; +} + +static int sparx5_tc_flower_stats(struct net_device *ndev, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5_tc_rule_pkt_cnt rinfo = {}; + struct vcap_control *vctrl; + ulong lastused = 0; + u64 drops = 0; + u32 pkts = 0; + int err; + + rinfo.cookie = fco->cookie; + vctrl = port->sparx5->vcap_ctrl; + err = vcap_rule_iter(vctrl, sparx5_tc_rule_counter_cb, &rinfo); + if (err) + return err; + pkts = rinfo.pkts; + flow_stats_update(&fco->stats, 0x0, pkts, drops, lastused, + FLOW_ACTION_HW_STATS_IMMEDIATE); + return err; +} + +int sparx5_tc_flower(struct net_device *ndev, struct flow_cls_offload *fco, + bool ingress) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct vcap_control *vctrl; + struct vcap_admin *admin; + int err = -EINVAL; + + /* Get vcap instance from the chain id */ + vctrl = port->sparx5->vcap_ctrl; + admin = vcap_find_admin(vctrl, fco->common.chain_index); + if (!admin) { + NL_SET_ERR_MSG_MOD(fco->common.extack, "Invalid chain"); + return err; + } + + switch (fco->command) { + case FLOW_CLS_REPLACE: + return sparx5_tc_flower_replace(ndev, fco, admin); + case FLOW_CLS_DESTROY: + return sparx5_tc_flower_destroy(ndev, fco, admin); + case FLOW_CLS_STATS: + return sparx5_tc_flower_stats(ndev, fco, admin); + default: + return -EOPNOTSUPP; + } +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c new file mode 100644 index 000000000000..30dd61e5d150 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP API + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_tc.h" +#include "vcap_api.h" +#include "vcap_api_client.h" +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_vcap_impl.h" + +static int sparx5_tc_matchall_replace(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct flow_action_entry *action; + struct sparx5 *sparx5; + int err; + + if (!flow_offload_has_one_action(&tmo->rule->action)) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Only one action per filter is supported"); + return -EOPNOTSUPP; + } + action = &tmo->rule->action.entries[0]; + + sparx5 = port->sparx5; + switch (action->id) { + case FLOW_ACTION_GOTO: + err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, + action->chain_index, tmo->cookie, + true); + if (err == -EFAULT) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Unsupported goto chain"); + return -EOPNOTSUPP; + } + if (err == -EADDRINUSE) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "VCAP already enabled"); + return -EOPNOTSUPP; + } + if (err) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Could not enable VCAP lookups"); + return err; + } + break; + default: + NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action"); + return -EOPNOTSUPP; + } + return 0; +} + +static int sparx5_tc_matchall_destroy(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5; + int err; + + sparx5 = port->sparx5; + if (!tmo->rule && tmo->cookie) { + err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, 0, + tmo->cookie, false); + if (err) + return err; + return 0; + } + NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action"); + return -EOPNOTSUPP; +} + +int sparx5_tc_matchall(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + if (!tc_cls_can_offload_and_chain0(ndev, &tmo->common)) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Only chain zero is supported"); + return -EOPNOTSUPP; + } + + switch (tmo->command) { + case TC_CLSMATCHALL_REPLACE: + return sparx5_tc_matchall_replace(ndev, tmo, ingress); + case TC_CLSMATCHALL_DESTROY: + return sparx5_tc_matchall_destroy(ndev, tmo, ingress); + default: + return -EOPNOTSUPP; + } +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c new file mode 100644 index 000000000000..1bd987c664e8 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c @@ -0,0 +1,1351 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +/* This file is autogenerated by cml-utils 2022-10-13 10:04:41 +0200. + * Commit ID: fd7cafd175899f0672c73afb3a30fc872500ae86 + */ + +#include <linux/types.h> +#include <linux/kernel.h> + +#include "vcap_api.h" +#include "sparx5_vcap_ag_api.h" + +/* keyfields */ +static const struct vcap_field is2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 90, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 138, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 186, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 187, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 203, + .width = 64, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 267, + .width = 16, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 283, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 284, + .width = 1, + }, +}; + +static const struct vcap_field is2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 86, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 134, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 135, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 136, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 137, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 138, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 139, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 140, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 142, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 174, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 206, + .width = 1, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 207, + .width = 16, + }, +}; + +static const struct vcap_field is2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 136, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 169, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 170, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 186, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 202, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 220, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 221, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 222, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 223, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 224, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 225, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 226, + .width = 64, + }, +}; + +static const struct vcap_field is2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 136, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 169, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 177, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 193, + .width = 96, + }, +}; + +static const struct vcap_field is2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 91, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 220, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 228, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U48, + .offset = 244, + .width = 40, + }, +}; + +static const struct vcap_field is2_ip_7tuple_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 18, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 112, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 113, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 116, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 119, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 120, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 121, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 169, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 217, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 219, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 227, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 355, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 483, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 484, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 485, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 486, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 502, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 518, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 534, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 535, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 536, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 537, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 538, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 539, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 540, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 541, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 542, + .width = 64, + }, +}; + +/* keyfield_set */ +static const struct vcap_set is2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 4, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 5, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 6, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = 1, + .sw_per_item = 12, + .sw_cnt = 1, + }, +}; + +/* keyfield_set map */ +static const struct vcap_field *is2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = is2_mac_etype_keyfield, + [VCAP_KFS_ARP] = is2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = is2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = is2_ip4_other_keyfield, + [VCAP_KFS_IP6_STD] = is2_ip6_std_keyfield, + [VCAP_KFS_IP_7TUPLE] = is2_ip_7tuple_keyfield, +}; + +/* keyfield_set map sizes */ +static int is2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(is2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(is2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(is2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(is2_ip4_other_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(is2_ip6_std_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(is2_ip_7tuple_keyfield), +}; + +/* actionfields */ +static const struct vcap_field is2_base_type_actionfield[] = { + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 5, + }, + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 7, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 8, + .width = 1, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 3, + }, + [VCAP_AF_LRN_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_AF_RT_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 16, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 6, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 30, + .width = 68, + }, + [VCAP_AF_MIRROR_PROBE] = { + .type = VCAP_FIELD_U32, + .offset = 111, + .width = 2, + }, + [VCAP_AF_MATCH_ID] = { + .type = VCAP_FIELD_U32, + .offset = 159, + .width = 16, + }, + [VCAP_AF_MATCH_ID_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 175, + .width = 16, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 191, + .width = 12, + }, +}; + +/* actionfield_set */ +static const struct vcap_set is2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + +/* actionfield_set map */ +static const struct vcap_field *is2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = is2_base_type_actionfield, +}; + +/* actionfield_set map size */ +static int is2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(is2_base_type_actionfield), +}; + +/* Type Groups */ +static const struct vcap_typegroup is2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is2_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is2_keyfield_set_typegroups[] = { + [12] = is2_x12_keyfield_set_typegroups, + [6] = is2_x6_keyfield_set_typegroups, + [3] = is2_x3_keyfield_set_typegroups, + [1] = is2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup is2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 110, + .width = 1, + .value = 0, + }, + { + .offset = 220, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is2_actionfield_set_typegroups[] = { + [3] = is2_x3_actionfield_set_typegroups, + [1] = is2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +/* Keyfieldset names */ +static const char * const vcap_keyfield_set_names[] = { + [VCAP_KFS_NO_VALUE] = "(None)", + [VCAP_KFS_ARP] = "VCAP_KFS_ARP", + [VCAP_KFS_IP4_OTHER] = "VCAP_KFS_IP4_OTHER", + [VCAP_KFS_IP4_TCP_UDP] = "VCAP_KFS_IP4_TCP_UDP", + [VCAP_KFS_IP6_STD] = "VCAP_KFS_IP6_STD", + [VCAP_KFS_IP_7TUPLE] = "VCAP_KFS_IP_7TUPLE", + [VCAP_KFS_MAC_ETYPE] = "VCAP_KFS_MAC_ETYPE", +}; + +/* Actionfieldset names */ +static const char * const vcap_actionfield_set_names[] = { + [VCAP_AFS_NO_VALUE] = "(None)", + [VCAP_AFS_BASE_TYPE] = "VCAP_AFS_BASE_TYPE", +}; + +/* Keyfield names */ +static const char * const vcap_keyfield_names[] = { + [VCAP_KF_NO_VALUE] = "(None)", + [VCAP_KF_8021Q_DEI_CLS] = "8021Q_DEI_CLS", + [VCAP_KF_8021Q_PCP_CLS] = "8021Q_PCP_CLS", + [VCAP_KF_8021Q_VID_CLS] = "8021Q_VID_CLS", + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = "8021Q_VLAN_TAGGED_IS", + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = "ARP_ADDR_SPACE_OK_IS", + [VCAP_KF_ARP_LEN_OK_IS] = "ARP_LEN_OK_IS", + [VCAP_KF_ARP_OPCODE] = "ARP_OPCODE", + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = "ARP_OPCODE_UNKNOWN_IS", + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = "ARP_PROTO_SPACE_OK_IS", + [VCAP_KF_ARP_SENDER_MATCH_IS] = "ARP_SENDER_MATCH_IS", + [VCAP_KF_ARP_TGT_MATCH_IS] = "ARP_TGT_MATCH_IS", + [VCAP_KF_ETYPE] = "ETYPE", + [VCAP_KF_ETYPE_LEN_IS] = "ETYPE_LEN_IS", + [VCAP_KF_IF_IGR_PORT_MASK] = "IF_IGR_PORT_MASK", + [VCAP_KF_IF_IGR_PORT_MASK_L3] = "IF_IGR_PORT_MASK_L3", + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = "IF_IGR_PORT_MASK_RNG", + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = "IF_IGR_PORT_MASK_SEL", + [VCAP_KF_IP4_IS] = "IP4_IS", + [VCAP_KF_ISDX_CLS] = "ISDX_CLS", + [VCAP_KF_ISDX_GT0_IS] = "ISDX_GT0_IS", + [VCAP_KF_L2_BC_IS] = "L2_BC_IS", + [VCAP_KF_L2_DMAC] = "L2_DMAC", + [VCAP_KF_L2_FWD_IS] = "L2_FWD_IS", + [VCAP_KF_L2_MC_IS] = "L2_MC_IS", + [VCAP_KF_L2_PAYLOAD_ETYPE] = "L2_PAYLOAD_ETYPE", + [VCAP_KF_L2_SMAC] = "L2_SMAC", + [VCAP_KF_L3_DIP_EQ_SIP_IS] = "L3_DIP_EQ_SIP_IS", + [VCAP_KF_L3_DST_IS] = "L3_DST_IS", + [VCAP_KF_L3_FRAGMENT_TYPE] = "L3_FRAGMENT_TYPE", + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = "L3_FRAG_INVLD_L4_LEN", + [VCAP_KF_L3_IP4_DIP] = "L3_IP4_DIP", + [VCAP_KF_L3_IP4_SIP] = "L3_IP4_SIP", + [VCAP_KF_L3_IP6_DIP] = "L3_IP6_DIP", + [VCAP_KF_L3_IP6_SIP] = "L3_IP6_SIP", + [VCAP_KF_L3_IP_PROTO] = "L3_IP_PROTO", + [VCAP_KF_L3_OPTIONS_IS] = "L3_OPTIONS_IS", + [VCAP_KF_L3_PAYLOAD] = "L3_PAYLOAD", + [VCAP_KF_L3_RT_IS] = "L3_RT_IS", + [VCAP_KF_L3_TOS] = "L3_TOS", + [VCAP_KF_L3_TTL_GT0] = "L3_TTL_GT0", + [VCAP_KF_L4_ACK] = "L4_ACK", + [VCAP_KF_L4_DPORT] = "L4_DPORT", + [VCAP_KF_L4_FIN] = "L4_FIN", + [VCAP_KF_L4_PAYLOAD] = "L4_PAYLOAD", + [VCAP_KF_L4_PSH] = "L4_PSH", + [VCAP_KF_L4_RNG] = "L4_RNG", + [VCAP_KF_L4_RST] = "L4_RST", + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = "L4_SEQUENCE_EQ0_IS", + [VCAP_KF_L4_SPORT] = "L4_SPORT", + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = "L4_SPORT_EQ_DPORT_IS", + [VCAP_KF_L4_SYN] = "L4_SYN", + [VCAP_KF_L4_URG] = "L4_URG", + [VCAP_KF_LOOKUP_FIRST_IS] = "LOOKUP_FIRST_IS", + [VCAP_KF_LOOKUP_PAG] = "LOOKUP_PAG", + [VCAP_KF_OAM_CCM_CNTS_EQ0] = "OAM_CCM_CNTS_EQ0", + [VCAP_KF_OAM_Y1731_IS] = "OAM_Y1731_IS", + [VCAP_KF_TCP_IS] = "TCP_IS", + [VCAP_KF_TCP_UDP_IS] = "TCP_UDP_IS", + [VCAP_KF_TYPE] = "TYPE", +}; + +/* Actionfield names */ +static const char * const vcap_actionfield_names[] = { + [VCAP_AF_NO_VALUE] = "(None)", + [VCAP_AF_CNT_ID] = "CNT_ID", + [VCAP_AF_CPU_COPY_ENA] = "CPU_COPY_ENA", + [VCAP_AF_CPU_QUEUE_NUM] = "CPU_QUEUE_NUM", + [VCAP_AF_HIT_ME_ONCE] = "HIT_ME_ONCE", + [VCAP_AF_IGNORE_PIPELINE_CTRL] = "IGNORE_PIPELINE_CTRL", + [VCAP_AF_INTR_ENA] = "INTR_ENA", + [VCAP_AF_LRN_DIS] = "LRN_DIS", + [VCAP_AF_MASK_MODE] = "MASK_MODE", + [VCAP_AF_MATCH_ID] = "MATCH_ID", + [VCAP_AF_MATCH_ID_MASK] = "MATCH_ID_MASK", + [VCAP_AF_MIRROR_PROBE] = "MIRROR_PROBE", + [VCAP_AF_PIPELINE_FORCE_ENA] = "PIPELINE_FORCE_ENA", + [VCAP_AF_PIPELINE_PT] = "PIPELINE_PT", + [VCAP_AF_POLICE_ENA] = "POLICE_ENA", + [VCAP_AF_POLICE_IDX] = "POLICE_IDX", + [VCAP_AF_PORT_MASK] = "PORT_MASK", + [VCAP_AF_RT_DIS] = "RT_DIS", +}; + +/* VCAPs */ +const struct vcap_info sparx5_vcaps[] = { + [VCAP_TYPE_IS2] = { + .name = "is2", + .rows = 256, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 110, + .default_cnt = 73, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = is2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is2_keyfield_set), + .actionfield_set = is2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is2_actionfield_set), + .keyfield_set_map = is2_keyfield_set_map, + .keyfield_set_map_size = is2_keyfield_set_map_size, + .actionfield_set_map = is2_actionfield_set_map, + .actionfield_set_map_size = is2_actionfield_set_map_size, + .keyfield_set_typegroups = is2_keyfield_set_typegroups, + .actionfield_set_typegroups = is2_actionfield_set_typegroups, + }, +}; + +const struct vcap_statistics sparx5_vcap_stats = { + .name = "sparx5", + .count = 1, + .keyfield_set_names = vcap_keyfield_set_names, + .actionfield_set_names = vcap_actionfield_set_names, + .keyfield_names = vcap_keyfield_names, + .actionfield_names = vcap_actionfield_names, +}; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h new file mode 100644 index 000000000000..7d106f1276fe --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +/* This file is autogenerated by cml-utils 2022-10-13 10:04:41 +0200. + * Commit ID: fd7cafd175899f0672c73afb3a30fc872500ae86 + */ + +#ifndef __SPARX5_VCAP_AG_API_H__ +#define __SPARX5_VCAP_AG_API_H__ + +/* VCAPs */ +extern const struct vcap_info sparx5_vcaps[]; +extern const struct vcap_statistics sparx5_vcap_stats; + +#endif /* __SPARX5_VCAP_AG_API_H__ */ + diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c new file mode 100644 index 000000000000..b91e05ffe2f4 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver VCAP debugFS implementation + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include <linux/types.h> +#include <linux/list.h> + +#include "sparx5_vcap_debugfs.h" +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_vcap_impl.h" +#include "sparx5_vcap_ag_api.h" + +static void sparx5_vcap_port_keys(struct sparx5 *sparx5, + struct vcap_admin *admin, + struct sparx5_port *port, + struct vcap_output_print *out) +{ + int lookup; + u32 value; + + out->prf(out->dst, " port[%02d] (%s): ", port->portno, + netdev_name(port->ndev)); + for (lookup = 0; lookup < admin->lookups; ++lookup) { + out->prf(out->dst, "\n Lookup %d: ", lookup); + + /* Get lookup state */ + value = spx5_rd(sparx5, ANA_ACL_VCAP_S2_CFG(port->portno)); + out->prf(out->dst, "\n state: "); + if (ANA_ACL_VCAP_S2_CFG_SEC_ENA_GET(value)) + out->prf(out->dst, "on"); + else + out->prf(out->dst, "off"); + + /* Get key selection state */ + value = spx5_rd(sparx5, + ANA_ACL_VCAP_S2_KEY_SEL(port->portno, lookup)); + + out->prf(out->dst, "\n noneth: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_NONETH_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_NONETH_CUSTOM_1: + out->prf(out->dst, "custom1"); + break; + case VCAP_IS2_PS_NONETH_CUSTOM_2: + out->prf(out->dst, "custom2"); + break; + case VCAP_IS2_PS_NONETH_NO_LOOKUP: + out->prf(out->dst, "none"); + break; + } + out->prf(out->dst, "\n ipv4_mc: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_MC_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER: + out->prf(out->dst, "ip4_tcp_udp ip4_other"); + break; + case VCAP_IS2_PS_IPV4_MC_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + case VCAP_IS2_PS_IPV4_MC_IP4_VID: + out->prf(out->dst, "ip4_vid"); + break; + } + out->prf(out->dst, "\n ipv4_uc: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_UC_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER: + out->prf(out->dst, "ip4_tcp_udp ip4_other"); + break; + case VCAP_IS2_PS_IPV4_UC_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + } + out->prf(out->dst, "\n ipv6_mc: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_MC_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_IPV6_MC_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_VID: + out->prf(out->dst, "ip6_vid"); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_STD: + out->prf(out->dst, "ip6_std"); + break; + case VCAP_IS2_PS_IPV6_MC_IP4_TCP_UDP_OTHER: + out->prf(out->dst, "ip4_tcp_udp ipv4_other"); + break; + } + out->prf(out->dst, "\n ipv6_uc: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_UC_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_IPV6_UC_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + case VCAP_IS2_PS_IPV6_UC_IP6_STD: + out->prf(out->dst, "ip6_std"); + break; + case VCAP_IS2_PS_IPV6_UC_IP4_TCP_UDP_OTHER: + out->prf(out->dst, "ip4_tcp_udp ip4_other"); + break; + } + out->prf(out->dst, "\n arp: "); + switch (ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_ARP_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_IS2_PS_ARP_ARP: + out->prf(out->dst, "arp"); + break; + } + } + out->prf(out->dst, "\n"); +} + +static void sparx5_vcap_port_stickies(struct sparx5 *sparx5, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + int lookup; + u32 value; + + out->prf(out->dst, " Sticky bits: "); + for (lookup = 0; lookup < admin->lookups; ++lookup) { + out->prf(out->dst, "\n Lookup %d: ", lookup); + /* Get lookup sticky bits */ + value = spx5_rd(sparx5, ANA_ACL_SEC_LOOKUP_STICKY(lookup)); + + if (ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_CLM_STICKY_GET(value)) + out->prf(out->dst, " sel_clm"); + if (ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_IRLEG_STICKY_GET(value)) + out->prf(out->dst, " sel_irleg"); + if (ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_ERLEG_STICKY_GET(value)) + out->prf(out->dst, " sel_erleg"); + if (ANA_ACL_SEC_LOOKUP_STICKY_KEY_SEL_PORT_STICKY_GET(value)) + out->prf(out->dst, " sel_port"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM2_STICKY_GET(value)) + out->prf(out->dst, " custom2"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_CUSTOM1_STICKY_GET(value)) + out->prf(out->dst, " custom1"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_OAM_STICKY_GET(value)) + out->prf(out->dst, " oam"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_GET(value)) + out->prf(out->dst, " ip6_vid"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_GET(value)) + out->prf(out->dst, " ip6_std"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_TCPUDP_STICKY_GET(value)) + out->prf(out->dst, " ip6_tcpudp"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_GET(value)) + out->prf(out->dst, " ip_7tuple"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_GET(value)) + out->prf(out->dst, " ip4_vid"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_GET(value)) + out->prf(out->dst, " ip4_tcpudp"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_GET(value)) + out->prf(out->dst, " ip4_other"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_GET(value)) + out->prf(out->dst, " arp"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_SNAP_STICKY_GET(value)) + out->prf(out->dst, " mac_snap"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_LLC_STICKY_GET(value)) + out->prf(out->dst, " mac_llc"); + if (ANA_ACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_GET(value)) + out->prf(out->dst, " mac_etype"); + /* Clear stickies */ + spx5_wr(value, sparx5, ANA_ACL_SEC_LOOKUP_STICKY(lookup)); + } + out->prf(out->dst, "\n"); +} + +/* Provide port information via a callback interface */ +int sparx5_port_info(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + const struct vcap_info *vcap; + struct vcap_control *vctrl; + + vctrl = sparx5->vcap_ctrl; + vcap = &vctrl->vcaps[admin->vtype]; + out->prf(out->dst, "%s:\n", vcap->name); + sparx5_vcap_port_keys(sparx5, admin, port, out); + sparx5_vcap_port_stickies(sparx5, admin, out); + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.h new file mode 100644 index 000000000000..f9ede03441f2 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Microchip Sparx5 Switch driver VCAP implementation + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#ifndef __SPARX5_VCAP_DEBUGFS_H__ +#define __SPARX5_VCAP_DEBUGFS_H__ + +#include <linux/netdevice.h> + +#include <vcap_api.h> +#include <vcap_api_client.h> + +#if defined(CONFIG_DEBUG_FS) + +/* Provide port information via a callback interface */ +int sparx5_port_info(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out); + +#else + +static inline int sparx5_port_info(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + return 0; +} + +#endif + +#endif /* __SPARX5_VCAP_DEBUGFS_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c new file mode 100644 index 000000000000..a0c126ba9a87 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -0,0 +1,723 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver VCAP implementation + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + * + * The Sparx5 Chip Register Model can be browsed at this location: + * https://github.com/microchip-ung/sparx-5_reginfo + */ + +#include "vcap_api_debugfs.h" +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_vcap_impl.h" +#include "sparx5_vcap_ag_api.h" +#include "sparx5_vcap_debugfs.h" + +#define SUPER_VCAP_BLK_SIZE 3072 /* addresses per Super VCAP block */ +#define STREAMSIZE (64 * 4) /* bytes in the VCAP cache area */ + +#define SPARX5_IS2_LOOKUPS 4 +#define VCAP_IS2_KEYSEL(_ena, _noneth, _v4_mc, _v4_uc, _v6_mc, _v6_uc, _arp) \ + (ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_SET(_ena) | \ + ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_SET(_noneth) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_SET(_v4_mc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_SET(_v4_uc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_SET(_v6_mc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_SET(_v6_uc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_SET(_arp)) + +static struct sparx5_vcap_inst { + enum vcap_type vtype; /* type of vcap */ + int vinst; /* instance number within the same type */ + int lookups; /* number of lookups in this vcap type */ + int lookups_per_instance; /* number of lookups in this instance */ + int first_cid; /* first chain id in this vcap */ + int last_cid; /* last chain id in this vcap */ + int count; /* number of available addresses, not in super vcap */ + int map_id; /* id in the super vcap block mapping (if applicable) */ + int blockno; /* starting block in super vcap (if applicable) */ + int blocks; /* number of blocks in super vcap (if applicable) */ +} sparx5_vcap_inst_cfg[] = { + { + .vtype = VCAP_TYPE_IS2, /* IS2-0 */ + .vinst = 0, + .map_id = 4, + .lookups = SPARX5_IS2_LOOKUPS, + .lookups_per_instance = SPARX5_IS2_LOOKUPS / 2, + .first_cid = SPARX5_VCAP_CID_IS2_L0, + .last_cid = SPARX5_VCAP_CID_IS2_L2 - 1, + .blockno = 0, /* Maps block 0-1 */ + .blocks = 2, + }, + { + .vtype = VCAP_TYPE_IS2, /* IS2-1 */ + .vinst = 1, + .map_id = 5, + .lookups = SPARX5_IS2_LOOKUPS, + .lookups_per_instance = SPARX5_IS2_LOOKUPS / 2, + .first_cid = SPARX5_VCAP_CID_IS2_L2, + .last_cid = SPARX5_VCAP_CID_IS2_MAX, + .blockno = 2, /* Maps block 2-3 */ + .blocks = 2, + }, +}; + +/* Await the super VCAP completion of the current operation */ +static void sparx5_vcap_wait_super_update(struct sparx5 *sparx5) +{ + u32 value; + + read_poll_timeout(spx5_rd, value, + !VCAP_SUPER_CTRL_UPDATE_SHOT_GET(value), 500, 10000, + false, sparx5, VCAP_SUPER_CTRL); +} + +/* Initializing a VCAP address range: only IS2 for now */ +static void _sparx5_vcap_range_init(struct sparx5 *sparx5, + struct vcap_admin *admin, + u32 addr, u32 count) +{ + u32 size = count - 1; + + spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(0) | + VCAP_SUPER_CFG_MV_SIZE_SET(size), + sparx5, VCAP_SUPER_CFG); + spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(VCAP_CMD_INITIALIZE) | + VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_SUPER_CTRL_CLEAR_CACHE_SET(true) | + VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_SUPER_CTRL); + sparx5_vcap_wait_super_update(sparx5); +} + +/* Initializing VCAP rule data area */ +static void sparx5_vcap_block_init(struct sparx5 *sparx5, + struct vcap_admin *admin) +{ + _sparx5_vcap_range_init(sparx5, admin, admin->first_valid_addr, + admin->last_valid_addr - + admin->first_valid_addr); +} + +/* Get the keyset name from the sparx5 VCAP model */ +static const char *sparx5_vcap_keyset_name(struct net_device *ndev, + enum vcap_keyfield_set keyset) +{ + struct sparx5_port *port = netdev_priv(ndev); + + return vcap_keyset_name(port->sparx5->vcap_ctrl, keyset); +} + +/* Check if this is the first lookup of IS2 */ +static bool sparx5_vcap_is2_is_first_chain(struct vcap_rule *rule) +{ + return (rule->vcap_chain_id >= SPARX5_VCAP_CID_IS2_L0 && + rule->vcap_chain_id < SPARX5_VCAP_CID_IS2_L1) || + ((rule->vcap_chain_id >= SPARX5_VCAP_CID_IS2_L2 && + rule->vcap_chain_id < SPARX5_VCAP_CID_IS2_L3)); +} + +/* Set the narrow range ingress port mask on a rule */ +static void sparx5_vcap_add_range_port_mask(struct vcap_rule *rule, + struct net_device *ndev) +{ + struct sparx5_port *port = netdev_priv(ndev); + u32 port_mask; + u32 range; + + range = port->portno / BITS_PER_TYPE(u32); + /* Port bit set to match-any */ + port_mask = ~BIT(port->portno % BITS_PER_TYPE(u32)); + vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK_SEL, 0, 0xf); + vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK_RNG, range, 0xf); + vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK, 0, port_mask); +} + +/* Set the wide range ingress port mask on a rule */ +static void sparx5_vcap_add_wide_port_mask(struct vcap_rule *rule, + struct net_device *ndev) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct vcap_u72_key port_mask; + u32 range; + + /* Port bit set to match-any */ + memset(port_mask.value, 0, sizeof(port_mask.value)); + memset(port_mask.mask, 0xff, sizeof(port_mask.mask)); + range = port->portno / BITS_PER_BYTE; + port_mask.mask[range] = ~BIT(port->portno % BITS_PER_BYTE); + vcap_rule_add_key_u72(rule, VCAP_KF_IF_IGR_PORT_MASK, &port_mask); +} + +/* Convert chain id to vcap lookup id */ +static int sparx5_vcap_cid_to_lookup(int cid) +{ + int lookup = 0; + + /* For now only handle IS2 */ + if (cid >= SPARX5_VCAP_CID_IS2_L1 && cid < SPARX5_VCAP_CID_IS2_L2) + lookup = 1; + else if (cid >= SPARX5_VCAP_CID_IS2_L2 && cid < SPARX5_VCAP_CID_IS2_L3) + lookup = 2; + else if (cid >= SPARX5_VCAP_CID_IS2_L3 && cid < SPARX5_VCAP_CID_IS2_MAX) + lookup = 3; + + return lookup; +} + +/* Return the list of keysets for the vcap port configuration */ +static int sparx5_vcap_is2_get_port_keysets(struct net_device *ndev, + int lookup, + struct vcap_keyset_list *keysetlist, + u16 l3_proto) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + u32 value; + + /* Check if the port keyset selection is enabled */ + value = spx5_rd(sparx5, ANA_ACL_VCAP_S2_KEY_SEL(portno, lookup)); + if (!ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_GET(value)) + return -ENOENT; + + /* Collect all keysets for the port in a list */ + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_ARP) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_ARP_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_ARP_ARP: + vcap_keyset_list_add(keysetlist, VCAP_KFS_ARP); + break; + } + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IP) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_UC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV4_UC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + } + + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_MC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV4_MC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + } + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IPV6) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_UC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV6_UC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_IS2_PS_IPV6_UC_IP6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_IS2_PS_IPV6_UC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + } + + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_MC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV6_MC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_IS2_PS_IPV6_MC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_VID: + /* Not used */ + break; + } + } + + if (l3_proto != ETH_P_ARP && l3_proto != ETH_P_IP && + l3_proto != ETH_P_IPV6) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_NONETH_MAC_ETYPE: + /* IS2 non-classified frames generate MAC_ETYPE */ + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + } + } + return 0; +} + +/* Get the port keyset for the vcap lookup */ +int sparx5_vcap_get_port_keyset(struct net_device *ndev, + struct vcap_admin *admin, + int cid, + u16 l3_proto, + struct vcap_keyset_list *kslist) +{ + int lookup; + + lookup = sparx5_vcap_cid_to_lookup(cid); + return sparx5_vcap_is2_get_port_keysets(ndev, lookup, kslist, l3_proto); +} + +/* API callback used for validating a field keyset (check the port keysets) */ +static enum vcap_keyfield_set +sparx5_vcap_validate_keyset(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule, + struct vcap_keyset_list *kslist, + u16 l3_proto) +{ + struct vcap_keyset_list keysetlist = {}; + enum vcap_keyfield_set keysets[10] = {}; + int idx, jdx, lookup; + + if (!kslist || kslist->cnt == 0) + return VCAP_KFS_NO_VALUE; + + /* Get a list of currently configured keysets in the lookups */ + lookup = sparx5_vcap_cid_to_lookup(rule->vcap_chain_id); + keysetlist.max = ARRAY_SIZE(keysets); + keysetlist.keysets = keysets; + sparx5_vcap_is2_get_port_keysets(ndev, lookup, &keysetlist, l3_proto); + + /* Check if there is a match and return the match */ + for (idx = 0; idx < kslist->cnt; ++idx) + for (jdx = 0; jdx < keysetlist.cnt; ++jdx) + if (kslist->keysets[idx] == keysets[jdx]) + return kslist->keysets[idx]; + + pr_err("%s:%d: %s not supported in port key selection\n", + __func__, __LINE__, + sparx5_vcap_keyset_name(ndev, kslist->keysets[0])); + + return -ENOENT; +} + +/* API callback used for adding default fields to a rule */ +static void sparx5_vcap_add_default_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + const struct vcap_field *field; + + field = vcap_lookup_keyfield(rule, VCAP_KF_IF_IGR_PORT_MASK); + if (field && field->width == SPX5_PORTS) + sparx5_vcap_add_wide_port_mask(rule, ndev); + else if (field && field->width == BITS_PER_TYPE(u32)) + sparx5_vcap_add_range_port_mask(rule, ndev); + else + pr_err("%s:%d: %s: could not add an ingress port mask for: %s\n", + __func__, __LINE__, netdev_name(ndev), + sparx5_vcap_keyset_name(ndev, rule->keyset)); + /* add the lookup bit */ + if (sparx5_vcap_is2_is_first_chain(rule)) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_0); +} + +/* API callback used for erasing the vcap cache area (not the register area) */ +static void sparx5_vcap_cache_erase(struct vcap_admin *admin) +{ + memset(admin->cache.keystream, 0, STREAMSIZE); + memset(admin->cache.maskstream, 0, STREAMSIZE); + memset(admin->cache.actionstream, 0, STREAMSIZE); + memset(&admin->cache.counter, 0, sizeof(admin->cache.counter)); +} + +/* API callback used for writing to the VCAP cache */ +static void sparx5_vcap_cache_write(struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + switch (sel) { + case VCAP_SEL_ENTRY: + for (idx = 0; idx < count; ++idx) { + /* Avoid 'match-off' by setting value & mask */ + spx5_wr(keystr[idx] & mskstr[idx], sparx5, + VCAP_SUPER_VCAP_ENTRY_DAT(idx)); + spx5_wr(~mskstr[idx], sparx5, + VCAP_SUPER_VCAP_MASK_DAT(idx)); + } + break; + case VCAP_SEL_ACTION: + for (idx = 0; idx < count; ++idx) + spx5_wr(actstr[idx], sparx5, + VCAP_SUPER_VCAP_ACTION_DAT(idx)); + break; + case VCAP_SEL_ALL: + pr_err("%s:%d: cannot write all streams at once\n", + __func__, __LINE__); + break; + default: + break; + } + if (sel & VCAP_SEL_COUNTER) { + start = start & 0xfff; /* counter limit */ + if (admin->vinst == 0) + spx5_wr(admin->cache.counter, sparx5, + ANA_ACL_CNT_A(start)); + else + spx5_wr(admin->cache.counter, sparx5, + ANA_ACL_CNT_B(start)); + spx5_wr(admin->cache.sticky, sparx5, + VCAP_SUPER_VCAP_CNT_DAT(0)); + } +} + +/* API callback used for reading from the VCAP into the VCAP cache */ +static void sparx5_vcap_cache_read(struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + if (sel & VCAP_SEL_ENTRY) { + for (idx = 0; idx < count; ++idx) { + keystr[idx] = spx5_rd(sparx5, + VCAP_SUPER_VCAP_ENTRY_DAT(idx)); + mskstr[idx] = ~spx5_rd(sparx5, + VCAP_SUPER_VCAP_MASK_DAT(idx)); + } + } + if (sel & VCAP_SEL_ACTION) { + for (idx = 0; idx < count; ++idx) + actstr[idx] = spx5_rd(sparx5, + VCAP_SUPER_VCAP_ACTION_DAT(idx)); + } + if (sel & VCAP_SEL_COUNTER) { + start = start & 0xfff; /* counter limit */ + if (admin->vinst == 0) + admin->cache.counter = + spx5_rd(sparx5, ANA_ACL_CNT_A(start)); + else + admin->cache.counter = + spx5_rd(sparx5, ANA_ACL_CNT_B(start)); + admin->cache.sticky = + spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); + } +} + +/* API callback used for initializing a VCAP address range */ +static void sparx5_vcap_range_init(struct net_device *ndev, + struct vcap_admin *admin, u32 addr, + u32 count) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + + _sparx5_vcap_range_init(sparx5, admin, addr, count); +} + +/* API callback used for updating the VCAP cache */ +static void sparx5_vcap_update(struct net_device *ndev, + struct vcap_admin *admin, enum vcap_command cmd, + enum vcap_selection sel, u32 addr) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + bool clear; + + clear = (cmd == VCAP_CMD_INITIALIZE); + spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(0) | + VCAP_SUPER_CFG_MV_SIZE_SET(0), sparx5, VCAP_SUPER_CFG); + spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET((VCAP_SEL_ENTRY & sel) == 0) | + VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET((VCAP_SEL_ACTION & sel) == 0) | + VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET((VCAP_SEL_COUNTER & sel) == 0) | + VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_SUPER_CTRL_CLEAR_CACHE_SET(clear) | + VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_SUPER_CTRL); + sparx5_vcap_wait_super_update(sparx5); +} + +/* API callback used for moving a block of rules in the VCAP */ +static void sparx5_vcap_move(struct net_device *ndev, struct vcap_admin *admin, + u32 addr, int offset, int count) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + enum vcap_command cmd; + u16 mv_num_pos; + u16 mv_size; + + mv_size = count - 1; + if (offset > 0) { + mv_num_pos = offset - 1; + cmd = VCAP_CMD_MOVE_DOWN; + } else { + mv_num_pos = -offset - 1; + cmd = VCAP_CMD_MOVE_UP; + } + spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(mv_num_pos) | + VCAP_SUPER_CFG_MV_SIZE_SET(mv_size), + sparx5, VCAP_SUPER_CFG); + spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_SUPER_CTRL_CLEAR_CACHE_SET(false) | + VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_SUPER_CTRL); + sparx5_vcap_wait_super_update(sparx5); +} + +/* Enable all lookups in the VCAP instance */ +static int sparx5_vcap_enable(struct net_device *ndev, + struct vcap_admin *admin, + bool enable) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5; + int portno; + + sparx5 = port->sparx5; + portno = port->portno; + + /* For now we only consider IS2 */ + if (enable) + spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); + else + spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0), sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); + return 0; +} + +/* API callback operations: only IS2 is supported for now */ +static struct vcap_operations sparx5_vcap_ops = { + .validate_keyset = sparx5_vcap_validate_keyset, + .add_default_fields = sparx5_vcap_add_default_fields, + .cache_erase = sparx5_vcap_cache_erase, + .cache_write = sparx5_vcap_cache_write, + .cache_read = sparx5_vcap_cache_read, + .init = sparx5_vcap_range_init, + .update = sparx5_vcap_update, + .move = sparx5_vcap_move, + .port_info = sparx5_port_info, + .enable = sparx5_vcap_enable, +}; + +/* Enable lookups per port and set the keyset generation: only IS2 for now */ +static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, + struct vcap_admin *admin) +{ + int portno, lookup; + u32 keysel; + + /* all traffic types generate the MAC_ETYPE keyset for now in all + * lookups on all ports + */ + keysel = VCAP_IS2_KEYSEL(true, VCAP_IS2_PS_NONETH_MAC_ETYPE, + VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV6_MC_IP_7TUPLE, + VCAP_IS2_PS_IPV6_UC_IP_7TUPLE, + VCAP_IS2_PS_ARP_ARP); + for (lookup = 0; lookup < admin->lookups; ++lookup) { + for (portno = 0; portno < SPX5_PORTS; ++portno) { + spx5_wr(keysel, sparx5, + ANA_ACL_VCAP_S2_KEY_SEL(portno, lookup)); + } + } +} + +/* Disable lookups per port and set the keyset generation: only IS2 for now */ +static void sparx5_vcap_port_key_deselection(struct sparx5 *sparx5, + struct vcap_admin *admin) +{ + int portno; + + for (portno = 0; portno < SPX5_PORTS; ++portno) + spx5_rmw(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0), + ANA_ACL_VCAP_S2_CFG_SEC_ENA, + sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); +} + +static void sparx5_vcap_admin_free(struct vcap_admin *admin) +{ + if (!admin) + return; + mutex_destroy(&admin->lock); + kfree(admin->cache.keystream); + kfree(admin->cache.maskstream); + kfree(admin->cache.actionstream); + kfree(admin); +} + +/* Allocate a vcap instance with a rule list and a cache area */ +static struct vcap_admin * +sparx5_vcap_admin_alloc(struct sparx5 *sparx5, struct vcap_control *ctrl, + const struct sparx5_vcap_inst *cfg) +{ + struct vcap_admin *admin; + + admin = kzalloc(sizeof(*admin), GFP_KERNEL); + if (!admin) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&admin->list); + INIT_LIST_HEAD(&admin->rules); + INIT_LIST_HEAD(&admin->enabled); + mutex_init(&admin->lock); + admin->vtype = cfg->vtype; + admin->vinst = cfg->vinst; + admin->lookups = cfg->lookups; + admin->lookups_per_instance = cfg->lookups_per_instance; + admin->first_cid = cfg->first_cid; + admin->last_cid = cfg->last_cid; + admin->cache.keystream = + kzalloc(STREAMSIZE, GFP_KERNEL); + admin->cache.maskstream = + kzalloc(STREAMSIZE, GFP_KERNEL); + admin->cache.actionstream = + kzalloc(STREAMSIZE, GFP_KERNEL); + if (!admin->cache.keystream || !admin->cache.maskstream || + !admin->cache.actionstream) { + sparx5_vcap_admin_free(admin); + return ERR_PTR(-ENOMEM); + } + return admin; +} + +/* Do block allocations and provide addresses for VCAP instances */ +static void sparx5_vcap_block_alloc(struct sparx5 *sparx5, + struct vcap_admin *admin, + const struct sparx5_vcap_inst *cfg) +{ + int idx; + + /* Super VCAP block mapping and address configuration. Block 0 + * is assigned addresses 0 through 3071, block 1 is assigned + * addresses 3072 though 6143, and so on. + */ + for (idx = cfg->blockno; idx < cfg->blockno + cfg->blocks; ++idx) { + spx5_wr(VCAP_SUPER_IDX_CORE_IDX_SET(idx), sparx5, + VCAP_SUPER_IDX); + spx5_wr(VCAP_SUPER_MAP_CORE_MAP_SET(cfg->map_id), sparx5, + VCAP_SUPER_MAP); + } + admin->first_valid_addr = cfg->blockno * SUPER_VCAP_BLK_SIZE; + admin->last_used_addr = admin->first_valid_addr + + cfg->blocks * SUPER_VCAP_BLK_SIZE; + admin->last_valid_addr = admin->last_used_addr - 1; +} + +/* Allocate a vcap control and vcap instances and configure the system */ +int sparx5_vcap_init(struct sparx5 *sparx5) +{ + const struct sparx5_vcap_inst *cfg; + struct vcap_control *ctrl; + struct vcap_admin *admin; + struct dentry *dir; + int err = 0, idx; + + /* Create a VCAP control instance that owns the platform specific VCAP + * model with VCAP instances and information about keysets, keys, + * actionsets and actions + * - Create administrative state for each available VCAP + * - Lists of rules + * - Address information + * - Initialize VCAP blocks + * - Configure port keysets + */ + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + sparx5->vcap_ctrl = ctrl; + /* select the sparx5 VCAP model */ + ctrl->vcaps = sparx5_vcaps; + ctrl->stats = &sparx5_vcap_stats; + /* Setup callbacks to allow the API to use the VCAP HW */ + ctrl->ops = &sparx5_vcap_ops; + + INIT_LIST_HEAD(&ctrl->list); + for (idx = 0; idx < ARRAY_SIZE(sparx5_vcap_inst_cfg); ++idx) { + cfg = &sparx5_vcap_inst_cfg[idx]; + admin = sparx5_vcap_admin_alloc(sparx5, ctrl, cfg); + if (IS_ERR(admin)) { + err = PTR_ERR(admin); + pr_err("%s:%d: vcap allocation failed: %d\n", + __func__, __LINE__, err); + return err; + } + sparx5_vcap_block_alloc(sparx5, admin, cfg); + sparx5_vcap_block_init(sparx5, admin); + if (cfg->vinst == 0) + sparx5_vcap_port_key_selection(sparx5, admin); + list_add_tail(&admin->list, &ctrl->list); + } + dir = vcap_debugfs(sparx5->dev, sparx5->debugfs_root, ctrl); + for (idx = 0; idx < SPX5_PORTS; ++idx) + if (sparx5->ports[idx]) + vcap_port_debugfs(sparx5->dev, dir, ctrl, + sparx5->ports[idx]->ndev); + + return err; +} + +void sparx5_vcap_destroy(struct sparx5 *sparx5) +{ + struct vcap_control *ctrl = sparx5->vcap_ctrl; + struct vcap_admin *admin, *admin_next; + + if (!ctrl) + return; + + list_for_each_entry_safe(admin, admin_next, &ctrl->list, list) { + sparx5_vcap_port_key_deselection(sparx5, admin); + vcap_del_rules(ctrl, admin); + list_del(&admin->list); + sparx5_vcap_admin_free(admin); + } + kfree(ctrl); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h new file mode 100644 index 000000000000..0a0f2412c980 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Microchip Sparx5 Switch driver VCAP implementation + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + * + * The Sparx5 Chip Register Model can be browsed at this location: + * https://github.com/microchip-ung/sparx-5_reginfo + */ + +#ifndef __SPARX5_VCAP_IMPL_H__ +#define __SPARX5_VCAP_IMPL_H__ + +#include <linux/types.h> +#include <linux/list.h> + +#include "vcap_api.h" +#include "vcap_api_client.h" + +#define SPARX5_VCAP_CID_IS2_L0 VCAP_CID_INGRESS_STAGE2_L0 /* IS2 lookup 0 */ +#define SPARX5_VCAP_CID_IS2_L1 VCAP_CID_INGRESS_STAGE2_L1 /* IS2 lookup 1 */ +#define SPARX5_VCAP_CID_IS2_L2 VCAP_CID_INGRESS_STAGE2_L2 /* IS2 lookup 2 */ +#define SPARX5_VCAP_CID_IS2_L3 VCAP_CID_INGRESS_STAGE2_L3 /* IS2 lookup 3 */ +#define SPARX5_VCAP_CID_IS2_MAX \ + (VCAP_CID_INGRESS_STAGE2_L3 + VCAP_CID_LOOKUP_SIZE - 1) /* IS2 Max */ + +/* IS2 port keyset selection control */ + +/* IS2 non-ethernet traffic type keyset generation */ +enum vcap_is2_port_sel_noneth { + VCAP_IS2_PS_NONETH_MAC_ETYPE, + VCAP_IS2_PS_NONETH_CUSTOM_1, + VCAP_IS2_PS_NONETH_CUSTOM_2, + VCAP_IS2_PS_NONETH_NO_LOOKUP +}; + +/* IS2 IPv4 unicast traffic type keyset generation */ +enum vcap_is2_port_sel_ipv4_uc { + VCAP_IS2_PS_IPV4_UC_MAC_ETYPE, + VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV4_UC_IP_7TUPLE, +}; + +/* IS2 IPv4 multicast traffic type keyset generation */ +enum vcap_is2_port_sel_ipv4_mc { + VCAP_IS2_PS_IPV4_MC_MAC_ETYPE, + VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV4_MC_IP_7TUPLE, + VCAP_IS2_PS_IPV4_MC_IP4_VID, +}; + +/* IS2 IPv6 unicast traffic type keyset generation */ +enum vcap_is2_port_sel_ipv6_uc { + VCAP_IS2_PS_IPV6_UC_MAC_ETYPE, + VCAP_IS2_PS_IPV6_UC_IP_7TUPLE, + VCAP_IS2_PS_IPV6_UC_IP6_STD, + VCAP_IS2_PS_IPV6_UC_IP4_TCP_UDP_OTHER, +}; + +/* IS2 IPv6 multicast traffic type keyset generation */ +enum vcap_is2_port_sel_ipv6_mc { + VCAP_IS2_PS_IPV6_MC_MAC_ETYPE, + VCAP_IS2_PS_IPV6_MC_IP_7TUPLE, + VCAP_IS2_PS_IPV6_MC_IP6_VID, + VCAP_IS2_PS_IPV6_MC_IP6_STD, + VCAP_IS2_PS_IPV6_MC_IP4_TCP_UDP_OTHER, +}; + +/* IS2 ARP traffic type keyset generation */ +enum vcap_is2_port_sel_arp { + VCAP_IS2_PS_ARP_MAC_ETYPE, + VCAP_IS2_PS_ARP_ARP, +}; + +/* Get the port keyset for the vcap lookup */ +int sparx5_vcap_get_port_keyset(struct net_device *ndev, + struct vcap_admin *admin, + int cid, + u16 l3_proto, + struct vcap_keyset_list *kslist); + +#endif /* __SPARX5_VCAP_IMPL_H__ */ diff --git a/drivers/net/ethernet/microchip/vcap/Kconfig b/drivers/net/ethernet/microchip/vcap/Kconfig new file mode 100644 index 000000000000..97f43fd4473f --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/Kconfig @@ -0,0 +1,53 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Microchip VCAP API configuration +# + +if NET_VENDOR_MICROCHIP + +config VCAP + bool "VCAP (Versatile Content-Aware Processor) library" + help + Provides the basic VCAP functionality for multiple Microchip switchcores + + A VCAP is essentially a TCAM with rules consisting of + + - Programmable key fields + - Programmable action fields + - A counter (which may be only one bit wide) + + Besides this each VCAP has: + + - A number of lookups + - A keyset configuration per port per lookup + + The VCAP implementation provides switchcore independent handling of rules + and supports: + + - Creating and deleting rules + - Updating and getting rules + + The platform specific configuration as well as the platform specific model + of the VCAP instances are attached to the VCAP API and a client can then + access rules via the API in a platform independent way, with the + limitations that each VCAP has in terms of its supported keys and actions. + + Different switchcores will have different VCAP instances with different + characteristics. Look in the datasheet for the VCAP specifications for the + specific switchcore. + +config VCAP_KUNIT_TEST + bool "KUnit test for VCAP library" if !KUNIT_ALL_TESTS + depends on KUNIT + depends on KUNIT=y && VCAP=y && y + select DEBUG_FS + default KUNIT_ALL_TESTS + help + This builds unit tests for the VCAP library. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + +endif # NET_VENDOR_MICROCHIP diff --git a/drivers/net/ethernet/microchip/vcap/Makefile b/drivers/net/ethernet/microchip/vcap/Makefile new file mode 100644 index 000000000000..0adb8f5a8735 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the Microchip VCAP API +# + +obj-$(CONFIG_VCAP) += vcap.o +obj-$(CONFIG_VCAP_KUNIT_TEST) += vcap_model_kunit.o +vcap-$(CONFIG_DEBUG_FS) += vcap_api_debugfs.o + +vcap-y += vcap_api.o diff --git a/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h new file mode 100644 index 000000000000..84de2aee4169 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h @@ -0,0 +1,735 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +/* This file is autogenerated by cml-utils 2022-10-13 10:04:41 +0200. + * Commit ID: fd7cafd175899f0672c73afb3a30fc872500ae86 + */ + +#ifndef __VCAP_AG_API__ +#define __VCAP_AG_API__ + +enum vcap_type { + VCAP_TYPE_ES2, + VCAP_TYPE_IS0, + VCAP_TYPE_IS2, + VCAP_TYPE_MAX +}; + +/* Keyfieldset names with origin information */ +enum vcap_keyfield_set { + VCAP_KFS_NO_VALUE, /* initial value */ + VCAP_KFS_ARP, /* sparx5 is2 X6, sparx5 es2 X6 */ + VCAP_KFS_ETAG, /* sparx5 is0 X2 */ + VCAP_KFS_IP4_OTHER, /* sparx5 is2 X6, sparx5 es2 X6 */ + VCAP_KFS_IP4_TCP_UDP, /* sparx5 is2 X6, sparx5 es2 X6 */ + VCAP_KFS_IP4_VID, /* sparx5 es2 X3 */ + VCAP_KFS_IP6_STD, /* sparx5 is2 X6 */ + VCAP_KFS_IP6_VID, /* sparx5 is2 X6, sparx5 es2 X6 */ + VCAP_KFS_IP_7TUPLE, /* sparx5 is2 X12, sparx5 es2 X12 */ + VCAP_KFS_LL_FULL, /* sparx5 is0 X6 */ + VCAP_KFS_MAC_ETYPE, /* sparx5 is2 X6, sparx5 es2 X6 */ + VCAP_KFS_MLL, /* sparx5 is0 X3 */ + VCAP_KFS_NORMAL, /* sparx5 is0 X6 */ + VCAP_KFS_NORMAL_5TUPLE_IP4, /* sparx5 is0 X6 */ + VCAP_KFS_NORMAL_7TUPLE, /* sparx5 is0 X12 */ + VCAP_KFS_PURE_5TUPLE_IP4, /* sparx5 is0 X3 */ + VCAP_KFS_TRI_VID, /* sparx5 is0 X2 */ + VCAP_KFS_MAC_LLC, /* lan966x is2 X2 */ + VCAP_KFS_MAC_SNAP, /* lan966x is2 X2 */ + VCAP_KFS_OAM, /* lan966x is2 X2 */ + VCAP_KFS_IP6_TCP_UDP, /* lan966x is2 X4 */ + VCAP_KFS_IP6_OTHER, /* lan966x is2 X4 */ + VCAP_KFS_SMAC_SIP4, /* lan966x is2 X1 */ + VCAP_KFS_SMAC_SIP6, /* lan966x is2 X2 */ +}; + +/* List of keyfields with description + * + * Keys ending in _IS are booleans derived from frame data + * Keys ending in _CLS are classified frame data + * + * VCAP_KF_8021BR_ECID_BASE: W12, sparx5: is0 + * Used by 802.1BR Bridge Port Extension in an E-Tag + * VCAP_KF_8021BR_ECID_EXT: W8, sparx5: is0 + * Used by 802.1BR Bridge Port Extension in an E-Tag + * VCAP_KF_8021BR_E_TAGGED: W1, sparx5: is0 + * Set for frames containing an E-TAG (802.1BR Ethertype 893f) + * VCAP_KF_8021BR_GRP: W2, sparx5: is0 + * E-Tag group bits in 802.1BR Bridge Port Extension + * VCAP_KF_8021BR_IGR_ECID_BASE: W12, sparx5: is0 + * Used by 802.1BR Bridge Port Extension in an E-Tag + * VCAP_KF_8021BR_IGR_ECID_EXT: W8, sparx5: is0 + * Used by 802.1BR Bridge Port Extension in an E-Tag + * VCAP_KF_8021Q_DEI0: W1, sparx5: is0 + * First DEI in multiple vlan tags (outer tag or default port tag) + * VCAP_KF_8021Q_DEI1: W1, sparx5: is0 + * Second DEI in multiple vlan tags (inner tag) + * VCAP_KF_8021Q_DEI2: W1, sparx5: is0 + * Third DEI in multiple vlan tags (not always available) + * VCAP_KF_8021Q_DEI_CLS: W1, sparx5: is2/es2, lan966x: is2 + * Classified DEI + * VCAP_KF_8021Q_PCP0: W3, sparx5: is0 + * First PCP in multiple vlan tags (outer tag or default port tag) + * VCAP_KF_8021Q_PCP1: W3, sparx5: is0 + * Second PCP in multiple vlan tags (inner tag) + * VCAP_KF_8021Q_PCP2: W3, sparx5: is0 + * Third PCP in multiple vlan tags (not always available) + * VCAP_KF_8021Q_PCP_CLS: W3, sparx5: is2/es2, lan966x: is2 + * Classified PCP + * VCAP_KF_8021Q_TPID0: W3, sparx5: is0 + * First TPIC in multiple vlan tags (outer tag or default port tag) + * VCAP_KF_8021Q_TPID1: W3, sparx5: is0 + * Second TPID in multiple vlan tags (inner tag) + * VCAP_KF_8021Q_TPID2: W3, sparx5: is0 + * Third TPID in multiple vlan tags (not always available) + * VCAP_KF_8021Q_VID0: W12, sparx5: is0 + * First VID in multiple vlan tags (outer tag or default port tag) + * VCAP_KF_8021Q_VID1: W12, sparx5: is0 + * Second VID in multiple vlan tags (inner tag) + * VCAP_KF_8021Q_VID2: W12, sparx5: is0 + * Third VID in multiple vlan tags (not always available) + * VCAP_KF_8021Q_VID_CLS: W13, sparx5: is2/es2, lan966x is2 W12 + * Classified VID + * VCAP_KF_8021Q_VLAN_TAGGED_IS: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5: Set if frame was received with a VLAN tag, LAN966x: Set if frame has + * one or more Q-tags. Independent of port VLAN awareness + * VCAP_KF_8021Q_VLAN_TAGS: W3, sparx5: is0 + * Number of VLAN tags in frame: 0: Untagged, 1: Single tagged, 3: Double + * tagged, 7: Triple tagged + * VCAP_KF_ACL_GRP_ID: W8, sparx5: es2 + * Used in interface map table + * VCAP_KF_ARP_ADDR_SPACE_OK_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if hardware address is Ethernet + * VCAP_KF_ARP_LEN_OK_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if hardware address length = 6 (Ethernet) and IP address length = 4 (IP). + * VCAP_KF_ARP_OPCODE: W2, sparx5: is2/es2, lan966x: i2 + * ARP opcode + * VCAP_KF_ARP_OPCODE_UNKNOWN_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if not one of the codes defined in VCAP_KF_ARP_OPCODE + * VCAP_KF_ARP_PROTO_SPACE_OK_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if protocol address space is 0x0800 + * VCAP_KF_ARP_SENDER_MATCH_IS: W1, sparx5: is2/es2, lan966x: is2 + * Sender Hardware Address = SMAC (ARP) + * VCAP_KF_ARP_TGT_MATCH_IS: W1, sparx5: is2/es2, lan966x: is2 + * Target Hardware Address = SMAC (RARP) + * VCAP_KF_COSID_CLS: W3, sparx5: es2 + * Class of service + * VCAP_KF_DST_ENTRY: W1, sparx5: is0 + * Selects whether the frame’s destination or source information is used for + * fields L2_SMAC and L3_IP4_SIP + * VCAP_KF_ES0_ISDX_KEY_ENA: W1, sparx5: es2 + * The value taken from the IFH .FWD.ES0_ISDX_KEY_ENA + * VCAP_KF_ETYPE: W16, sparx5: is0/is2/es2, lan966x: is2 + * Ethernet type + * VCAP_KF_ETYPE_LEN_IS: W1, sparx5: is0/is2/es2 + * Set if frame has EtherType >= 0x600 + * VCAP_KF_ETYPE_MPLS: W2, sparx5: is0 + * Type of MPLS Ethertype (or not) + * VCAP_KF_IF_EGR_PORT_MASK: W32, sparx5: es2 + * Egress port mask, one bit per port + * VCAP_KF_IF_EGR_PORT_MASK_RNG: W3, sparx5: es2 + * Select which 32 port group is available in IF_EGR_PORT (or virtual ports or + * CPU queue) + * VCAP_KF_IF_IGR_PORT: sparx5 is0 W7, sparx5 es2 W9 + * Sparx5: Logical ingress port number retrieved from + * ANA_CL::PORT_ID_CFG.LPORT_NUM or ERLEG, LAN966x: ingress port nunmber + * VCAP_KF_IF_IGR_PORT_MASK: sparx5 is0 W65, sparx5 is2 W32, sparx5 is2 W65, + * lan966x is2 W9 + * Ingress port mask, one bit per port/erleg + * VCAP_KF_IF_IGR_PORT_MASK_L3: W1, sparx5: is2 + * If set, IF_IGR_PORT_MASK, IF_IGR_PORT_MASK_RNG, and IF_IGR_PORT_MASK_SEL are + * used to specify L3 interfaces + * VCAP_KF_IF_IGR_PORT_MASK_RNG: W4, sparx5: is2 + * Range selector for IF_IGR_PORT_MASK. Specifies which group of 32 ports are + * available in IF_IGR_PORT_MASK + * VCAP_KF_IF_IGR_PORT_MASK_SEL: W2, sparx5: is0/is2 + * Mode selector for IF_IGR_PORT_MASK, applicable when IF_IGR_PORT_MASK_L3 == 0. + * Mapping: 0: DEFAULT 1: LOOPBACK 2: MASQUERADE 3: CPU_VD + * VCAP_KF_IF_IGR_PORT_SEL: W1, sparx5: es2 + * Selector for IF_IGR_PORT: physical port number or ERLEG + * VCAP_KF_IP4_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if frame has EtherType = 0x800 and IP version = 4 + * VCAP_KF_IP_MC_IS: W1, sparx5: is0 + * Set if frame is IPv4 frame and frame’s destination MAC address is an IPv4 + * multicast address (0x01005E0 /25). Set if frame is IPv6 frame and frame’s + * destination MAC address is an IPv6 multicast address (0x3333/16). + * VCAP_KF_IP_PAYLOAD_5TUPLE: W32, sparx5: is0 + * Payload bytes after IP header + * VCAP_KF_IP_SNAP_IS: W1, sparx5: is0 + * Set if frame is IPv4, IPv6, or SNAP frame + * VCAP_KF_ISDX_CLS: W12, sparx5: is2/es2 + * Classified ISDX + * VCAP_KF_ISDX_GT0_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if classified ISDX > 0 + * VCAP_KF_L2_BC_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if frame’s destination MAC address is the broadcast address + * (FF-FF-FF-FF-FF-FF). + * VCAP_KF_L2_DMAC: W48, sparx5: is0/is2/es2, lan966x: is2 + * Destination MAC address + * VCAP_KF_L2_FWD_IS: W1, sparx5: is2 + * Set if the frame is allowed to be forwarded to front ports + * VCAP_KF_L2_MC_IS: W1, sparx5: is0/is2/es2, lan9966x is2 + * Set if frame’s destination MAC address is a multicast address (bit 40 = 1). + * VCAP_KF_L2_PAYLOAD_ETYPE: W64, sparx5: is2/es2 + * Byte 0-7 of L2 payload after Type/Len field and overloading for OAM + * VCAP_KF_L2_SMAC: W48, sparx5: is0/is2/es2, lan966x is2 + * Source MAC address + * VCAP_KF_L3_DIP_EQ_SIP_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if Src IP matches Dst IP address + * VCAP_KF_L3_DMAC_DIP_MATCH: W1, sparx5: is2 + * Match found in DIP security lookup in ANA_L3 + * VCAP_KF_L3_DPL_CLS: W1, sparx5: es2 + * The frames drop precedence level + * VCAP_KF_L3_DSCP: W6, sparx5: is0 + * Frame’s DSCP value + * VCAP_KF_L3_DST_IS: W1, sparx5: is2 + * Set if lookup is done for egress router leg + * VCAP_KF_L3_FRAGMENT_TYPE: W2, sparx5: is0/is2/es2 + * L3 Fragmentation type (none, initial, suspicious, valid follow up) + * VCAP_KF_L3_FRAG_INVLD_L4_LEN: W1, sparx5: is0/is2 + * Set if frame's L4 length is less than ANA_CL:COMMON:CLM_FRAGMENT_CFG.L4_MIN_L + * EN + * VCAP_KF_L3_IP4_DIP: W32, sparx5: is0/is2/es2, lan966x: is2 + * Destination IPv4 Address + * VCAP_KF_L3_IP4_SIP: W32, sparx5: is0/is2/es2, lan966x: is2 + * Source IPv4 Address + * VCAP_KF_L3_IP6_DIP: W128, sparx5: is0/is2/es2, lan966x: is2 + * Sparx5: Full IPv6 DIP, LAN966x: Either Full IPv6 DIP or a subset depending on + * frame type + * VCAP_KF_L3_IP6_SIP: W128, sparx5: is0/is2/es2, lan966x: is2 + * Sparx5: Full IPv6 SIP, LAN966x: Either Full IPv6 SIP or a subset depending on + * frame type + * VCAP_KF_L3_IP_PROTO: W8, sparx5: is0/is2/es2, lan966x: is2 + * IPv4 frames: IP protocol. IPv6 frames: Next header, same as for IPV4 + * VCAP_KF_L3_OPTIONS_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if IPv4 frame contains options (IP len > 5) + * VCAP_KF_L3_PAYLOAD: sparx5 is2 W96, sparx5 is2 W40, sparx5 es2 W96, + * lan966x is2 W56 + * Sparx5: Payload bytes after IP header. IPv4: IPv4 options are not parsed so + * payload is always taken 20 bytes after the start of the IPv4 header, LAN966x: + * Bytes 0-6 after IP header + * VCAP_KF_L3_RT_IS: W1, sparx5: is2/es2 + * Set if frame has hit a router leg + * VCAP_KF_L3_SMAC_SIP_MATCH: W1, sparx5: is2 + * Match found in SIP security lookup in ANA_L3 + * VCAP_KF_L3_TOS: W8, sparx5: is2/es2, lan966x: is2 + * Sparx5: Frame's IPv4/IPv6 DSCP and ECN fields, LAN966x: IP TOS field + * VCAP_KF_L3_TTL_GT0: W1, sparx5: is2/es2, lan966x: is2 + * Set if IPv4 TTL / IPv6 hop limit is greater than 0 + * VCAP_KF_L4_ACK: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5 and LAN966x: TCP flag ACK, LAN966x only: PTP over UDP: flagField bit 2 + * (unicastFlag) + * VCAP_KF_L4_DPORT: W16, sparx5: is2/es2, lan966x: is2 + * Sparx5: TCP/UDP destination port. Overloading for IP_7TUPLE: Non-TCP/UDP IP + * frames: L4_DPORT = L3_IP_PROTO, LAN966x: TCP/UDP destination port + * VCAP_KF_L4_FIN: W1, sparx5: is2/es2 + * TCP flag FIN, LAN966x: TCP flag FIN, and for PTP over UDP: messageType bit 1 + * VCAP_KF_L4_PAYLOAD: W64, sparx5: is2/es2 + * Payload bytes after TCP/UDP header Overloading for IP_7TUPLE: Non TCP/UDP + * frames: Payload bytes 0–7 after IP header. IPv4 options are not parsed so + * payload is always taken 20 bytes after the start of the IPv4 header for non + * TCP/UDP IPv4 frames + * VCAP_KF_L4_PSH: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5: TCP flag PSH, LAN966x: TCP: TCP flag PSH. PTP over UDP: flagField bit + * 1 (twoStepFlag) + * VCAP_KF_L4_RNG: sparx5 is0 W8, sparx5 is2 W16, sparx5 es2 W16, lan966x: is2 + * Range checker bitmask (one for each range checker). Input into range checkers + * is taken from classified results (VID, DSCP) and frame (SPORT, DPORT, ETYPE, + * outer VID, inner VID) + * VCAP_KF_L4_RST: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5: TCP flag RST , LAN966x: TCP: TCP flag RST. PTP over UDP: messageType + * bit 3 + * VCAP_KF_L4_SEQUENCE_EQ0_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if TCP sequence number is 0, LAN966x: Overlayed with PTP over UDP: + * messageType bit 0 + * VCAP_KF_L4_SPORT: W16, sparx5: is0/is2/es2, lan966x: is2 + * TCP/UDP source port + * VCAP_KF_L4_SPORT_EQ_DPORT_IS: W1, sparx5: is2/es2, lan966x: is2 + * Set if UDP or TCP source port equals UDP or TCP destination port + * VCAP_KF_L4_SYN: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5: TCP flag SYN, LAN966x: TCP: TCP flag SYN. PTP over UDP: messageType + * bit 2 + * VCAP_KF_L4_URG: W1, sparx5: is2/es2, lan966x: is2 + * Sparx5: TCP flag URG, LAN966x: TCP: TCP flag URG. PTP over UDP: flagField bit + * 7 (reserved) + * VCAP_KF_LOOKUP_FIRST_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Selects between entries relevant for first and second lookup. Set for first + * lookup, cleared for second lookup. + * VCAP_KF_LOOKUP_GEN_IDX: W12, sparx5: is0 + * Generic index - for chaining CLM instances + * VCAP_KF_LOOKUP_GEN_IDX_SEL: W2, sparx5: is0 + * Select the mode of the Generic Index + * VCAP_KF_LOOKUP_PAG: W8, sparx5: is2, lan966x: is2 + * Classified Policy Association Group: chains rules from IS1/CLM to IS2 + * VCAP_KF_OAM_CCM_CNTS_EQ0: W1, sparx5: is2/es2, lan966x: is2 + * Dual-ended loss measurement counters in CCM frames are all zero + * VCAP_KF_OAM_MEL_FLAGS: W7, sparx5: is0, lan966x: is2 + * Encoding of MD level/MEG level (MEL) + * VCAP_KF_OAM_Y1731_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if frame’s EtherType = 0x8902 + * VCAP_KF_PROT_ACTIVE: W1, sparx5: es2 + * Protection is active + * VCAP_KF_TCP_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if frame is IPv4 TCP frame (IP protocol = 6) or IPv6 TCP frames (Next + * header = 6) + * VCAP_KF_TCP_UDP_IS: W1, sparx5: is0/is2/es2, lan966x: is2 + * Set if frame is IPv4/IPv6 TCP or UDP frame (IP protocol/next header equals 6 + * or 17) + * VCAP_KF_TYPE: sparx5 is0 W2, sparx5 is0 W1, sparx5 is2 W4, sparx5 is2 W2, + * sparx5 es2 W3, lan966x: is2 + * Keyset type id - set by the API + * VCAP_KF_HOST_MATCH: W1, lan966x: is2 + * The action from the SMAC_SIP4 or SMAC_SIP6 lookups. Used for IP source + * guarding. + * VCAP_KF_L2_FRM_TYPE: W4, lan966x: is2 + * Frame subtype for specific EtherTypes (MRP, DLR) + * VCAP_KF_L2_PAYLOAD0: W16, lan966x: is2 + * Payload bytes 0-1 after the frame’s EtherType + * VCAP_KF_L2_PAYLOAD1: W8, lan966x: is2 + * Payload byte 4 after the frame’s EtherType. This is specifically for PTP + * frames. + * VCAP_KF_L2_PAYLOAD2: W3, lan966x: is2 + * Bits 7, 2, and 1 from payload byte 6 after the frame’s EtherType. This is + * specifically for PTP frames. + * VCAP_KF_L2_LLC: W40, lan966x: is2 + * LLC header and data after up to two VLAN tags and the type/length field + * VCAP_KF_L3_FRAGMENT: W1, lan966x: is2 + * Set if IPv4 frame is fragmented + * VCAP_KF_L3_FRAG_OFS_GT0: W1, lan966x: is2 + * Set if IPv4 frame is fragmented and it is not the first fragment + * VCAP_KF_L2_SNAP: W40, lan966x: is2 + * SNAP header after LLC header (AA-AA-03) + * VCAP_KF_L4_1588_DOM: W8, lan966x: is2 + * PTP over UDP: domainNumber + * VCAP_KF_L4_1588_VER: W4, lan966x: is2 + * PTP over UDP: version + * VCAP_KF_OAM_MEPID: W16, lan966x: is2 + * CCM frame’s OAM MEP ID + * VCAP_KF_OAM_OPCODE: W8, lan966x: is2 + * Frame’s OAM opcode + * VCAP_KF_OAM_VER: W5, lan966x: is2 + * Frame’s OAM version + * VCAP_KF_OAM_FLAGS: W8, lan966x: is2 + * Frame’s OAM flags + * VCAP_KF_OAM_DETECTED: W1, lan966x: is2 + * This is missing in the datasheet, but present in the OAM keyset in XML + */ + +/* Keyfield names */ +enum vcap_key_field { + VCAP_KF_NO_VALUE, /* initial value */ + VCAP_KF_8021BR_ECID_BASE, + VCAP_KF_8021BR_ECID_EXT, + VCAP_KF_8021BR_E_TAGGED, + VCAP_KF_8021BR_GRP, + VCAP_KF_8021BR_IGR_ECID_BASE, + VCAP_KF_8021BR_IGR_ECID_EXT, + VCAP_KF_8021Q_DEI0, + VCAP_KF_8021Q_DEI1, + VCAP_KF_8021Q_DEI2, + VCAP_KF_8021Q_DEI_CLS, + VCAP_KF_8021Q_PCP0, + VCAP_KF_8021Q_PCP1, + VCAP_KF_8021Q_PCP2, + VCAP_KF_8021Q_PCP_CLS, + VCAP_KF_8021Q_TPID0, + VCAP_KF_8021Q_TPID1, + VCAP_KF_8021Q_TPID2, + VCAP_KF_8021Q_VID0, + VCAP_KF_8021Q_VID1, + VCAP_KF_8021Q_VID2, + VCAP_KF_8021Q_VID_CLS, + VCAP_KF_8021Q_VLAN_TAGGED_IS, + VCAP_KF_8021Q_VLAN_TAGS, + VCAP_KF_ACL_GRP_ID, + VCAP_KF_ARP_ADDR_SPACE_OK_IS, + VCAP_KF_ARP_LEN_OK_IS, + VCAP_KF_ARP_OPCODE, + VCAP_KF_ARP_OPCODE_UNKNOWN_IS, + VCAP_KF_ARP_PROTO_SPACE_OK_IS, + VCAP_KF_ARP_SENDER_MATCH_IS, + VCAP_KF_ARP_TGT_MATCH_IS, + VCAP_KF_COSID_CLS, + VCAP_KF_DST_ENTRY, + VCAP_KF_ES0_ISDX_KEY_ENA, + VCAP_KF_ETYPE, + VCAP_KF_ETYPE_LEN_IS, + VCAP_KF_ETYPE_MPLS, + VCAP_KF_IF_EGR_PORT_MASK, + VCAP_KF_IF_EGR_PORT_MASK_RNG, + VCAP_KF_IF_IGR_PORT, + VCAP_KF_IF_IGR_PORT_MASK, + VCAP_KF_IF_IGR_PORT_MASK_L3, + VCAP_KF_IF_IGR_PORT_MASK_RNG, + VCAP_KF_IF_IGR_PORT_MASK_SEL, + VCAP_KF_IF_IGR_PORT_SEL, + VCAP_KF_IP4_IS, + VCAP_KF_IP_MC_IS, + VCAP_KF_IP_PAYLOAD_5TUPLE, + VCAP_KF_IP_SNAP_IS, + VCAP_KF_ISDX_CLS, + VCAP_KF_ISDX_GT0_IS, + VCAP_KF_L2_BC_IS, + VCAP_KF_L2_DMAC, + VCAP_KF_L2_FWD_IS, + VCAP_KF_L2_MC_IS, + VCAP_KF_L2_PAYLOAD_ETYPE, + VCAP_KF_L2_SMAC, + VCAP_KF_L3_DIP_EQ_SIP_IS, + VCAP_KF_L3_DMAC_DIP_MATCH, + VCAP_KF_L3_DPL_CLS, + VCAP_KF_L3_DSCP, + VCAP_KF_L3_DST_IS, + VCAP_KF_L3_FRAGMENT_TYPE, + VCAP_KF_L3_FRAG_INVLD_L4_LEN, + VCAP_KF_L3_IP4_DIP, + VCAP_KF_L3_IP4_SIP, + VCAP_KF_L3_IP6_DIP, + VCAP_KF_L3_IP6_SIP, + VCAP_KF_L3_IP_PROTO, + VCAP_KF_L3_OPTIONS_IS, + VCAP_KF_L3_PAYLOAD, + VCAP_KF_L3_RT_IS, + VCAP_KF_L3_SMAC_SIP_MATCH, + VCAP_KF_L3_TOS, + VCAP_KF_L3_TTL_GT0, + VCAP_KF_L4_ACK, + VCAP_KF_L4_DPORT, + VCAP_KF_L4_FIN, + VCAP_KF_L4_PAYLOAD, + VCAP_KF_L4_PSH, + VCAP_KF_L4_RNG, + VCAP_KF_L4_RST, + VCAP_KF_L4_SEQUENCE_EQ0_IS, + VCAP_KF_L4_SPORT, + VCAP_KF_L4_SPORT_EQ_DPORT_IS, + VCAP_KF_L4_SYN, + VCAP_KF_L4_URG, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_LOOKUP_GEN_IDX, + VCAP_KF_LOOKUP_GEN_IDX_SEL, + VCAP_KF_LOOKUP_PAG, + VCAP_KF_MIRROR_ENA, + VCAP_KF_OAM_CCM_CNTS_EQ0, + VCAP_KF_OAM_MEL_FLAGS, + VCAP_KF_OAM_Y1731_IS, + VCAP_KF_PROT_ACTIVE, + VCAP_KF_TCP_IS, + VCAP_KF_TCP_UDP_IS, + VCAP_KF_TYPE, + VCAP_KF_HOST_MATCH, + VCAP_KF_L2_FRM_TYPE, + VCAP_KF_L2_PAYLOAD0, + VCAP_KF_L2_PAYLOAD1, + VCAP_KF_L2_PAYLOAD2, + VCAP_KF_L2_LLC, + VCAP_KF_L3_FRAGMENT, + VCAP_KF_L3_FRAG_OFS_GT0, + VCAP_KF_L2_SNAP, + VCAP_KF_L4_1588_DOM, + VCAP_KF_L4_1588_VER, + VCAP_KF_OAM_MEPID, + VCAP_KF_OAM_OPCODE, + VCAP_KF_OAM_VER, + VCAP_KF_OAM_FLAGS, + VCAP_KF_OAM_DETECTED, +}; + +/* Actionset names with origin information */ +enum vcap_actionfield_set { + VCAP_AFS_NO_VALUE, /* initial value */ + VCAP_AFS_BASE_TYPE, /* sparx5 is2 X3, sparx5 es2 X3, lan966x is2 X2 */ + VCAP_AFS_CLASSIFICATION, /* sparx5 is0 X2 */ + VCAP_AFS_CLASS_REDUCED, /* sparx5 is0 X1 */ + VCAP_AFS_FULL, /* sparx5 is0 X3 */ + VCAP_AFS_MLBS, /* sparx5 is0 X2 */ + VCAP_AFS_MLBS_REDUCED, /* sparx5 is0 X1 */ + VCAP_AFS_SMAC_SIP, /* lan966x is2 x1 */ +}; + +/* List of actionfields with description + * + * VCAP_AF_CLS_VID_SEL: W3, sparx5: is0 + * Controls the classified VID: 0: VID_NONE: No action. 1: VID_ADD: New VID = + * old VID + VID_VAL. 2: VID_REPLACE: New VID = VID_VAL. 3: VID_FIRST_TAG: New + * VID = VID from frame's first tag (outer tag) if available, otherwise VID_VAL. + * 4: VID_SECOND_TAG: New VID = VID from frame's second tag (middle tag) if + * available, otherwise VID_VAL. 5: VID_THIRD_TAG: New VID = VID from frame's + * third tag (inner tag) if available, otherwise VID_VAL. + * VCAP_AF_CNT_ID: sparx5 is2 W12, sparx5 es2 W11 + * Counter ID, used per lookup to index the 4K frame counters (ANA_ACL:CNT_TBL). + * Multiple VCAP IS2 entries can use the same counter. + * VCAP_AF_COPY_PORT_NUM: W7, sparx5: es2 + * QSYS port number when FWD_MODE is redirect or copy + * VCAP_AF_COPY_QUEUE_NUM: W16, sparx5: es2 + * QSYS queue number when FWD_MODE is redirect or copy + * VCAP_AF_CPU_COPY_ENA: W1, sparx5: is2/es2, lan966x: is2 + * Setting this bit to 1 causes all frames that hit this action to be copied to + * the CPU extraction queue specified in CPU_QUEUE_NUM. + * VCAP_AF_CPU_QUEUE_NUM: W3, sparx5: is2/es2, lan966x: is2 + * CPU queue number. Used when CPU_COPY_ENA is set. + * VCAP_AF_DEI_ENA: W1, sparx5: is0 + * If set, use DEI_VAL as classified DEI value. Otherwise, DEI from basic + * classification is used + * VCAP_AF_DEI_VAL: W1, sparx5: is0 + * See DEI_ENA + * VCAP_AF_DP_ENA: W1, sparx5: is0 + * If set, use DP_VAL as classified drop precedence level. Otherwise, drop + * precedence level from basic classification is used. + * VCAP_AF_DP_VAL: W2, sparx5: is0 + * See DP_ENA. + * VCAP_AF_DSCP_ENA: W1, sparx5: is0 + * If set, use DSCP_VAL as classified DSCP value. Otherwise, DSCP value from + * basic classification is used. + * VCAP_AF_DSCP_VAL: W6, sparx5: is0 + * See DSCP_ENA. + * VCAP_AF_ES2_REW_CMD: W3, sparx5: es2 + * Command forwarded to REW: 0: No action. 1: SWAP MAC addresses. 2: Do L2CP + * DMAC translation when entering or leaving a tunnel. + * VCAP_AF_FWD_MODE: W2, sparx5: es2 + * Forward selector: 0: Forward. 1: Discard. 2: Redirect. 3: Copy. + * VCAP_AF_HIT_ME_ONCE: W1, sparx5: is2/es2, lan966x: is2 + * Setting this bit to 1 causes the first frame that hits this action where the + * HIT_CNT counter is zero to be copied to the CPU extraction queue specified in + * CPU_QUEUE_NUM. The HIT_CNT counter is then incremented and any frames that + * hit this action later are not copied to the CPU. To re-enable the HIT_ME_ONCE + * functionality, the HIT_CNT counter must be cleared. + * VCAP_AF_IGNORE_PIPELINE_CTRL: W1, sparx5: is2/es2 + * Ignore ingress pipeline control. This enforces the use of the VCAP IS2 action + * even when the pipeline control has terminated the frame before VCAP IS2. + * VCAP_AF_INTR_ENA: W1, sparx5: is2/es2 + * If set, an interrupt is triggered when this rule is hit + * VCAP_AF_ISDX_ADD_REPLACE_SEL: W1, sparx5: is0 + * Controls the classified ISDX. 0: New ISDX = old ISDX + ISDX_VAL. 1: New ISDX + * = ISDX_VAL. + * VCAP_AF_ISDX_VAL: W12, sparx5: is0 + * See isdx_add_replace_sel + * VCAP_AF_LRN_DIS: W1, sparx5: is2, lan966x: is2 + * Setting this bit to 1 disables learning of frames hitting this action. + * VCAP_AF_MAP_IDX: W9, sparx5: is0 + * Index for QoS mapping table lookup + * VCAP_AF_MAP_KEY: W3, sparx5: is0 + * Key type for QoS mapping table lookup. 0: DEI0, PCP0 (outer tag). 1: DEI1, + * PCP1 (middle tag). 2: DEI2, PCP2 (inner tag). 3: MPLS TC. 4: PCP0 (outer + * tag). 5: E-DEI, E-PCP (E-TAG). 6: DSCP if available, otherwise none. 7: DSCP + * if available, otherwise DEI0, PCP0 (outer tag) if available using MAP_IDX+8, + * otherwise none + * VCAP_AF_MAP_LOOKUP_SEL: W2, sparx5: is0 + * Selects which of the two QoS Mapping Table lookups that MAP_KEY and MAP_IDX + * are applied to. 0: No changes to the QoS Mapping Table lookup. 1: Update key + * type and index for QoS Mapping Table lookup #0. 2: Update key type and index + * for QoS Mapping Table lookup #1. 3: Reserved. + * VCAP_AF_MASK_MODE: W3, sparx5: is0/is2, lan966x is2 W2 + * Controls the PORT_MASK use. Sparx5: 0: OR_DSTMASK, 1: AND_VLANMASK, 2: + * REPLACE_PGID, 3: REPLACE_ALL, 4: REDIR_PGID, 5: OR_PGID_MASK, 6: VSTAX, 7: + * Not applicable. LAN966X: 0: No action, 1: Permit/deny (AND), 2: Policy + * forwarding (DMAC lookup), 3: Redirect. The CPU port is untouched by + * MASK_MODE. + * VCAP_AF_MATCH_ID: W16, sparx5: is0/is2 + * Logical ID for the entry. The MATCH_ID is extracted together with the frame + * if the frame is forwarded to the CPU (CPU_COPY_ENA). The result is placed in + * IFH.CL_RSLT. + * VCAP_AF_MATCH_ID_MASK: W16, sparx5: is0/is2 + * Mask used by MATCH_ID. + * VCAP_AF_MIRROR_PROBE: W2, sparx5: is2 + * Mirroring performed according to configuration of a mirror probe. 0: No + * mirroring. 1: Mirror probe 0. 2: Mirror probe 1. 3: Mirror probe 2 + * VCAP_AF_MIRROR_PROBE_ID: W2, sparx5: es2 + * Signals a mirror probe to be placed in the IFH. Only possible when FWD_MODE + * is copy. 0: No mirroring. 1–3: Use mirror probe 0-2. + * VCAP_AF_NXT_IDX: W12, sparx5: is0 + * Index used as part of key (field G_IDX) in the next lookup. + * VCAP_AF_NXT_IDX_CTRL: W3, sparx5: is0 + * Controls the generation of the G_IDX used in the VCAP CLM next lookup + * VCAP_AF_PAG_OVERRIDE_MASK: W8, sparx5: is0 + * Bits set in this mask will override PAG_VAL from port profile. ï€ New PAG = + * (PAG (input) AND ~PAG_OVERRIDE_MASK) OR (PAG_VAL AND PAG_OVERRIDE_MASK) + * VCAP_AF_PAG_VAL: W8, sparx5: is0 + * See PAG_OVERRIDE_MASK. + * VCAP_AF_PCP_ENA: W1, sparx5: is0 + * If set, use PCP_VAL as classified PCP value. Otherwise, PCP from basic + * classification is used. + * VCAP_AF_PCP_VAL: W3, sparx5: is0 + * See PCP_ENA. + * VCAP_AF_PIPELINE_FORCE_ENA: sparx5 is0 W2, sparx5 is2 W1 + * If set, use PIPELINE_PT unconditionally and set PIPELINE_ACT = NONE if + * PIPELINE_PT == NONE. Overrules previous settings of pipeline point. + * VCAP_AF_PIPELINE_PT: W5, sparx5: is0/is2 + * Pipeline point used if PIPELINE_FORCE_ENA is set + * VCAP_AF_POLICE_ENA: W1, sparx5: is2/es2, lan966x: is2 + * Setting this bit to 1 causes frames that hit this action to be policed by the + * ACL policer specified in POLICE_IDX. Only applies to the first lookup. + * VCAP_AF_POLICE_IDX: W6, sparx5: is2/es2, lan966x: is2 W9 + * Selects VCAP policer used when policing frames (POLICE_ENA) + * VCAP_AF_POLICE_REMARK: W1, sparx5: es2 + * If set, frames exceeding policer rates are marked as yellow but not + * discarded. + * VCAP_AF_PORT_MASK: sparx5 is0 W65, sparx5 is2 W68, lan966x is2 W8 + * Port mask applied to the forwarding decision based on MASK_MODE. + * VCAP_AF_QOS_ENA: W1, sparx5: is0 + * If set, use QOS_VAL as classified QoS class. Otherwise, QoS class from basic + * classification is used. + * VCAP_AF_QOS_VAL: W3, sparx5: is0 + * See QOS_ENA. + * VCAP_AF_RT_DIS: W1, sparx5: is2 + * If set, routing is disallowed. Only applies when IS_INNER_ACL is 0. See also + * IGR_ACL_ENA, EGR_ACL_ENA, and RLEG_STAT_IDX. + * VCAP_AF_TYPE: W1, sparx5: is0 + * Actionset type id - Set by the API + * VCAP_AF_VID_VAL: W13, sparx5: is0 + * New VID Value + * VCAP_AF_MIRROR_ENA: W1, lan966x: is2 + * Setting this bit to 1 causes frames to be mirrored to the mirror target + * port (ANA::MIRRPORPORTS). + * VCAP_AF_POLICE_VCAP_ONLY: W1, lan966x: is2 + * Disable policing from QoS, and port policers. Only the VCAP policer + * selected by POLICE_IDX is active. Only applies to the second lookup. + * VCAP_AF_REW_OP: W16, lan966x: is2 + * Rewriter operation command. + * VCAP_AF_ISDX_ENA: W1, lan966x: is2 + * Setting this bit to 1 causes the classified ISDX to be set to the value of + * POLICE_IDX[8:0]. + * VCAP_AF_ACL_ID: W6, lan966x: is2 + * Logical ID for the entry. This ID is extracted together with the frame in + * the CPU extraction header. Only applicable to actions with CPU_COPY_ENA or + * HIT_ME_ONCE set. + * VCAP_AF_FWD_KILL_ENA: W1, lan966x: is2 + * Setting this bit to 1 denies forwarding of the frame forwarding to any + * front port. The frame can still be copied to the CPU by other actions. + * VCAP_AF_HOST_MATCH: W1, lan966x: is2 + * Used for IP source guarding. If set, it signals that the host is a valid + * (for instance a valid combination of source MAC address and source IP + * address). HOST_MATCH is input to the IS2 keys. + */ + +/* Actionfield names */ +enum vcap_action_field { + VCAP_AF_NO_VALUE, /* initial value */ + VCAP_AF_ACL_MAC, + VCAP_AF_ACL_RT_MODE, + VCAP_AF_CLS_VID_SEL, + VCAP_AF_CNT_ID, + VCAP_AF_COPY_PORT_NUM, + VCAP_AF_COPY_QUEUE_NUM, + VCAP_AF_COSID_ENA, + VCAP_AF_COSID_VAL, + VCAP_AF_CPU_COPY_ENA, + VCAP_AF_CPU_DIS, + VCAP_AF_CPU_ENA, + VCAP_AF_CPU_Q, + VCAP_AF_CPU_QUEUE_NUM, + VCAP_AF_CUSTOM_ACE_ENA, + VCAP_AF_CUSTOM_ACE_OFFSET, + VCAP_AF_DEI_ENA, + VCAP_AF_DEI_VAL, + VCAP_AF_DLB_OFFSET, + VCAP_AF_DMAC_OFFSET_ENA, + VCAP_AF_DP_ENA, + VCAP_AF_DP_VAL, + VCAP_AF_DSCP_ENA, + VCAP_AF_DSCP_VAL, + VCAP_AF_EGR_ACL_ENA, + VCAP_AF_ES2_REW_CMD, + VCAP_AF_FWD_DIS, + VCAP_AF_FWD_MODE, + VCAP_AF_FWD_TYPE, + VCAP_AF_GVID_ADD_REPLACE_SEL, + VCAP_AF_HIT_ME_ONCE, + VCAP_AF_IGNORE_PIPELINE_CTRL, + VCAP_AF_IGR_ACL_ENA, + VCAP_AF_INJ_MASQ_ENA, + VCAP_AF_INJ_MASQ_LPORT, + VCAP_AF_INJ_MASQ_PORT, + VCAP_AF_INTR_ENA, + VCAP_AF_ISDX_ADD_REPLACE_SEL, + VCAP_AF_ISDX_VAL, + VCAP_AF_IS_INNER_ACL, + VCAP_AF_L3_MAC_UPDATE_DIS, + VCAP_AF_LOG_MSG_INTERVAL, + VCAP_AF_LPM_AFFIX_ENA, + VCAP_AF_LPM_AFFIX_VAL, + VCAP_AF_LPORT_ENA, + VCAP_AF_LRN_DIS, + VCAP_AF_MAP_IDX, + VCAP_AF_MAP_KEY, + VCAP_AF_MAP_LOOKUP_SEL, + VCAP_AF_MASK_MODE, + VCAP_AF_MATCH_ID, + VCAP_AF_MATCH_ID_MASK, + VCAP_AF_MIP_SEL, + VCAP_AF_MIRROR_PROBE, + VCAP_AF_MIRROR_PROBE_ID, + VCAP_AF_MPLS_IP_CTRL_ENA, + VCAP_AF_MPLS_MEP_ENA, + VCAP_AF_MPLS_MIP_ENA, + VCAP_AF_MPLS_OAM_FLAVOR, + VCAP_AF_MPLS_OAM_TYPE, + VCAP_AF_NUM_VLD_LABELS, + VCAP_AF_NXT_IDX, + VCAP_AF_NXT_IDX_CTRL, + VCAP_AF_NXT_KEY_TYPE, + VCAP_AF_NXT_NORMALIZE, + VCAP_AF_NXT_NORM_W16_OFFSET, + VCAP_AF_NXT_NORM_W32_OFFSET, + VCAP_AF_NXT_OFFSET_FROM_TYPE, + VCAP_AF_NXT_TYPE_AFTER_OFFSET, + VCAP_AF_OAM_IP_BFD_ENA, + VCAP_AF_OAM_TWAMP_ENA, + VCAP_AF_OAM_Y1731_SEL, + VCAP_AF_PAG_OVERRIDE_MASK, + VCAP_AF_PAG_VAL, + VCAP_AF_PCP_ENA, + VCAP_AF_PCP_VAL, + VCAP_AF_PIPELINE_ACT_SEL, + VCAP_AF_PIPELINE_FORCE_ENA, + VCAP_AF_PIPELINE_PT, + VCAP_AF_PIPELINE_PT_REDUCED, + VCAP_AF_POLICE_ENA, + VCAP_AF_POLICE_IDX, + VCAP_AF_POLICE_REMARK, + VCAP_AF_PORT_MASK, + VCAP_AF_PTP_MASTER_SEL, + VCAP_AF_QOS_ENA, + VCAP_AF_QOS_VAL, + VCAP_AF_REW_CMD, + VCAP_AF_RLEG_DMAC_CHK_DIS, + VCAP_AF_RLEG_STAT_IDX, + VCAP_AF_RSDX_ENA, + VCAP_AF_RSDX_VAL, + VCAP_AF_RSVD_LBL_VAL, + VCAP_AF_RT_DIS, + VCAP_AF_RT_SEL, + VCAP_AF_S2_KEY_SEL_ENA, + VCAP_AF_S2_KEY_SEL_IDX, + VCAP_AF_SAM_SEQ_ENA, + VCAP_AF_SIP_IDX, + VCAP_AF_SWAP_MAC_ENA, + VCAP_AF_TCP_UDP_DPORT, + VCAP_AF_TCP_UDP_ENA, + VCAP_AF_TCP_UDP_SPORT, + VCAP_AF_TC_ENA, + VCAP_AF_TC_LABEL, + VCAP_AF_TPID_SEL, + VCAP_AF_TTL_DECR_DIS, + VCAP_AF_TTL_ENA, + VCAP_AF_TTL_LABEL, + VCAP_AF_TTL_UPDATE_ENA, + VCAP_AF_TYPE, + VCAP_AF_VID_VAL, + VCAP_AF_VLAN_POP_CNT, + VCAP_AF_VLAN_POP_CNT_ENA, + VCAP_AF_VLAN_PUSH_CNT, + VCAP_AF_VLAN_PUSH_CNT_ENA, + VCAP_AF_VLAN_WAS_TAGGED, + VCAP_AF_MIRROR_ENA, + VCAP_AF_POLICE_VCAP_ONLY, + VCAP_AF_REW_OP, + VCAP_AF_ISDX_ENA, + VCAP_AF_ACL_ID, + VCAP_AF_FWD_KILL_ENA, + VCAP_AF_HOST_MATCH, +}; + +#endif /* __VCAP_AG_API__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c new file mode 100644 index 000000000000..664aae3e2acd --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -0,0 +1,2883 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP API + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include <linux/types.h> + +#include "vcap_api_private.h" + +static int keyfield_size_table[] = { + [VCAP_FIELD_BIT] = sizeof(struct vcap_u1_key), + [VCAP_FIELD_U32] = sizeof(struct vcap_u32_key), + [VCAP_FIELD_U48] = sizeof(struct vcap_u48_key), + [VCAP_FIELD_U56] = sizeof(struct vcap_u56_key), + [VCAP_FIELD_U64] = sizeof(struct vcap_u64_key), + [VCAP_FIELD_U72] = sizeof(struct vcap_u72_key), + [VCAP_FIELD_U112] = sizeof(struct vcap_u112_key), + [VCAP_FIELD_U128] = sizeof(struct vcap_u128_key), +}; + +static int actionfield_size_table[] = { + [VCAP_FIELD_BIT] = sizeof(struct vcap_u1_action), + [VCAP_FIELD_U32] = sizeof(struct vcap_u32_action), + [VCAP_FIELD_U48] = sizeof(struct vcap_u48_action), + [VCAP_FIELD_U56] = sizeof(struct vcap_u56_action), + [VCAP_FIELD_U64] = sizeof(struct vcap_u64_action), + [VCAP_FIELD_U72] = sizeof(struct vcap_u72_action), + [VCAP_FIELD_U112] = sizeof(struct vcap_u112_action), + [VCAP_FIELD_U128] = sizeof(struct vcap_u128_action), +}; + +/* Moving a rule in the VCAP address space */ +struct vcap_rule_move { + int addr; /* address to move */ + int offset; /* change in address */ + int count; /* blocksize of addresses to move */ +}; + +/* Stores the filter cookie that enabled the port */ +struct vcap_enabled_port { + struct list_head list; /* for insertion in enabled ports list */ + struct net_device *ndev; /* the enabled port */ + unsigned long cookie; /* filter that enabled the port */ +}; + +void vcap_iter_set(struct vcap_stream_iter *itr, int sw_width, + const struct vcap_typegroup *tg, u32 offset) +{ + memset(itr, 0, sizeof(*itr)); + itr->offset = offset; + itr->sw_width = sw_width; + itr->regs_per_sw = DIV_ROUND_UP(sw_width, 32); + itr->tg = tg; +} + +static void vcap_iter_skip_tg(struct vcap_stream_iter *itr) +{ + /* Compensate the field offset for preceding typegroups. + * A typegroup table ends with an all-zero terminator. + */ + while (itr->tg->width && itr->offset >= itr->tg->offset) { + itr->offset += itr->tg->width; + itr->tg++; /* next typegroup */ + } +} + +void vcap_iter_update(struct vcap_stream_iter *itr) +{ + int sw_idx, sw_bitpos; + + /* Calculate the subword index and bitposition for current bit */ + sw_idx = itr->offset / itr->sw_width; + sw_bitpos = itr->offset % itr->sw_width; + /* Calculate the register index and bitposition for current bit */ + itr->reg_idx = (sw_idx * itr->regs_per_sw) + (sw_bitpos / 32); + itr->reg_bitpos = sw_bitpos % 32; +} + +void vcap_iter_init(struct vcap_stream_iter *itr, int sw_width, + const struct vcap_typegroup *tg, u32 offset) +{ + vcap_iter_set(itr, sw_width, tg, offset); + vcap_iter_skip_tg(itr); + vcap_iter_update(itr); +} + +void vcap_iter_next(struct vcap_stream_iter *itr) +{ + itr->offset++; + vcap_iter_skip_tg(itr); + vcap_iter_update(itr); +} + +static void vcap_set_bit(u32 *stream, struct vcap_stream_iter *itr, bool value) +{ + u32 mask = BIT(itr->reg_bitpos); + u32 *p = &stream[itr->reg_idx]; + + if (value) + *p |= mask; + else + *p &= ~mask; +} + +static void vcap_encode_bit(u32 *stream, struct vcap_stream_iter *itr, bool val) +{ + /* When intersected by a type group field, stream the type group bits + * before continuing with the value bit + */ + while (itr->tg->width && + itr->offset >= itr->tg->offset && + itr->offset < itr->tg->offset + itr->tg->width) { + int tg_bitpos = itr->tg->offset - itr->offset; + + vcap_set_bit(stream, itr, (itr->tg->value >> tg_bitpos) & 0x1); + itr->offset++; + vcap_iter_update(itr); + } + vcap_set_bit(stream, itr, val); +} + +static void vcap_encode_field(u32 *stream, struct vcap_stream_iter *itr, + int width, const u8 *value) +{ + int idx; + + /* Loop over the field value bits and add the value bits one by one to + * the output stream. + */ + for (idx = 0; idx < width; idx++) { + u8 bidx = idx & GENMASK(2, 0); + + /* Encode one field value bit */ + vcap_encode_bit(stream, itr, (value[idx / 8] >> bidx) & 0x1); + vcap_iter_next(itr); + } +} + +static void vcap_encode_typegroups(u32 *stream, int sw_width, + const struct vcap_typegroup *tg, + bool mask) +{ + struct vcap_stream_iter iter; + int idx; + + /* Mask bits must be set to zeros (inverted later when writing to the + * mask cache register), so that the mask typegroup bits consist of + * match-1 or match-0, or both + */ + vcap_iter_set(&iter, sw_width, tg, 0); + while (iter.tg->width) { + /* Set position to current typegroup bit */ + iter.offset = iter.tg->offset; + vcap_iter_update(&iter); + for (idx = 0; idx < iter.tg->width; idx++) { + /* Iterate over current typegroup bits. Mask typegroup + * bits are always set + */ + if (mask) + vcap_set_bit(stream, &iter, 0x1); + else + vcap_set_bit(stream, &iter, + (iter.tg->value >> idx) & 0x1); + iter.offset++; + vcap_iter_update(&iter); + } + iter.tg++; /* next typegroup */ + } +} + +static bool vcap_bitarray_zero(int width, u8 *value) +{ + int bytes = DIV_ROUND_UP(width, BITS_PER_BYTE); + u8 total = 0, bmask = 0xff; + int rwidth = width; + int idx; + + for (idx = 0; idx < bytes; ++idx, rwidth -= BITS_PER_BYTE) { + if (rwidth && rwidth < BITS_PER_BYTE) + bmask = (1 << rwidth) - 1; + total += value[idx] & bmask; + } + return total == 0; +} + +static bool vcap_get_bit(u32 *stream, struct vcap_stream_iter *itr) +{ + u32 mask = BIT(itr->reg_bitpos); + u32 *p = &stream[itr->reg_idx]; + + return !!(*p & mask); +} + +static void vcap_decode_field(u32 *stream, struct vcap_stream_iter *itr, + int width, u8 *value) +{ + int idx; + + /* Loop over the field value bits and get the field bits and + * set them in the output value byte array + */ + for (idx = 0; idx < width; idx++) { + u8 bidx = idx & 0x7; + + /* Decode one field value bit */ + if (vcap_get_bit(stream, itr)) + *value |= 1 << bidx; + vcap_iter_next(itr); + if (bidx == 7) + value++; + } +} + +/* Verify that the type id in the stream matches the type id of the keyset */ +static bool vcap_verify_keystream_keyset(struct vcap_control *vctrl, + enum vcap_type vt, + u32 *keystream, + u32 *mskstream, + enum vcap_keyfield_set keyset) +{ + const struct vcap_info *vcap = &vctrl->vcaps[vt]; + const struct vcap_field *typefld; + const struct vcap_typegroup *tgt; + const struct vcap_field *fields; + struct vcap_stream_iter iter; + const struct vcap_set *info; + u32 value = 0; + u32 mask = 0; + + if (vcap_keyfield_count(vctrl, vt, keyset) == 0) + return false; + + info = vcap_keyfieldset(vctrl, vt, keyset); + /* Check that the keyset is valid */ + if (!info) + return false; + + /* a type_id of value -1 means that there is no type field */ + if (info->type_id == (u8)-1) + return true; + + /* Get a valid typegroup for the specific keyset */ + tgt = vcap_keyfield_typegroup(vctrl, vt, keyset); + if (!tgt) + return false; + + fields = vcap_keyfields(vctrl, vt, keyset); + if (!fields) + return false; + + typefld = &fields[VCAP_KF_TYPE]; + vcap_iter_init(&iter, vcap->sw_width, tgt, typefld->offset); + vcap_decode_field(mskstream, &iter, typefld->width, (u8 *)&mask); + /* no type info if there are no mask bits */ + if (vcap_bitarray_zero(typefld->width, (u8 *)&mask)) + return false; + + /* Get the value of the type field in the stream and compare to the + * one define in the vcap keyset + */ + vcap_iter_init(&iter, vcap->sw_width, tgt, typefld->offset); + vcap_decode_field(keystream, &iter, typefld->width, (u8 *)&value); + + return (value & mask) == (info->type_id & mask); +} + +/* Verify that the typegroup bits have the correct values */ +static int vcap_verify_typegroups(u32 *stream, int sw_width, + const struct vcap_typegroup *tgt, bool mask, + int sw_max) +{ + struct vcap_stream_iter iter; + int sw_cnt, idx; + + vcap_iter_set(&iter, sw_width, tgt, 0); + sw_cnt = 0; + while (iter.tg->width) { + u32 value = 0; + u32 tg_value = iter.tg->value; + + if (mask) + tg_value = (1 << iter.tg->width) - 1; + /* Set position to current typegroup bit */ + iter.offset = iter.tg->offset; + vcap_iter_update(&iter); + for (idx = 0; idx < iter.tg->width; idx++) { + /* Decode one typegroup bit */ + if (vcap_get_bit(stream, &iter)) + value |= 1 << idx; + iter.offset++; + vcap_iter_update(&iter); + } + if (value != tg_value) + return -EINVAL; + iter.tg++; /* next typegroup */ + sw_cnt++; + /* Stop checking more typegroups */ + if (sw_max && sw_cnt >= sw_max) + break; + } + return 0; +} + +/* Find the subword width of the key typegroup that matches the stream data */ +static int vcap_find_keystream_typegroup_sw(struct vcap_control *vctrl, + enum vcap_type vt, u32 *stream, + bool mask, int sw_max) +{ + const struct vcap_typegroup **tgt; + int sw_idx, res; + + tgt = vctrl->vcaps[vt].keyfield_set_typegroups; + /* Try the longest subword match first */ + for (sw_idx = vctrl->vcaps[vt].sw_count; sw_idx >= 0; sw_idx--) { + if (!tgt[sw_idx]) + continue; + + res = vcap_verify_typegroups(stream, vctrl->vcaps[vt].sw_width, + tgt[sw_idx], mask, sw_max); + if (res == 0) + return sw_idx; + } + return -EINVAL; +} + +/* Verify that the typegroup information, subword count, keyset and type id + * are in sync and correct, return the list of matchin keysets + */ +int +vcap_find_keystream_keysets(struct vcap_control *vctrl, + enum vcap_type vt, + u32 *keystream, + u32 *mskstream, + bool mask, int sw_max, + struct vcap_keyset_list *kslist) +{ + const struct vcap_set *keyfield_set; + int sw_count, idx; + + sw_count = vcap_find_keystream_typegroup_sw(vctrl, vt, keystream, mask, + sw_max); + if (sw_count < 0) + return sw_count; + + keyfield_set = vctrl->vcaps[vt].keyfield_set; + for (idx = 0; idx < vctrl->vcaps[vt].keyfield_set_size; ++idx) { + if (keyfield_set[idx].sw_per_item != sw_count) + continue; + + if (vcap_verify_keystream_keyset(vctrl, vt, keystream, + mskstream, idx)) + vcap_keyset_list_add(kslist, idx); + } + if (kslist->cnt > 0) + return 0; + return -EINVAL; +} +EXPORT_SYMBOL_GPL(vcap_find_keystream_keysets); + +/* Read key data from a VCAP address and discover if there are any rule keysets + * here + */ +int vcap_addr_keysets(struct vcap_control *vctrl, + struct net_device *ndev, + struct vcap_admin *admin, + int addr, + struct vcap_keyset_list *kslist) +{ + enum vcap_type vt = admin->vtype; + int keyset_sw_regs, idx; + u32 key = 0, mask = 0; + + /* Read the cache at the specified address */ + keyset_sw_regs = DIV_ROUND_UP(vctrl->vcaps[vt].sw_width, 32); + vctrl->ops->update(ndev, admin, VCAP_CMD_READ, VCAP_SEL_ALL, addr); + vctrl->ops->cache_read(ndev, admin, VCAP_SEL_ENTRY, 0, + keyset_sw_regs); + /* Skip uninitialized key/mask entries */ + for (idx = 0; idx < keyset_sw_regs; ++idx) { + key |= ~admin->cache.keystream[idx]; + mask |= admin->cache.maskstream[idx]; + } + if (key == 0 && mask == 0) + return -EINVAL; + /* Decode and locate the keysets */ + return vcap_find_keystream_keysets(vctrl, vt, admin->cache.keystream, + admin->cache.maskstream, false, 0, + kslist); +} +EXPORT_SYMBOL_GPL(vcap_addr_keysets); + +/* Return the list of keyfields for the keyset */ +const struct vcap_field *vcap_keyfields(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_keyfield_set keyset) +{ + /* Check that the keyset exists in the vcap keyset list */ + if (keyset >= vctrl->vcaps[vt].keyfield_set_size) + return NULL; + return vctrl->vcaps[vt].keyfield_set_map[keyset]; +} + +/* Return the keyset information for the keyset */ +const struct vcap_set *vcap_keyfieldset(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_keyfield_set keyset) +{ + const struct vcap_set *kset; + + /* Check that the keyset exists in the vcap keyset list */ + if (keyset >= vctrl->vcaps[vt].keyfield_set_size) + return NULL; + kset = &vctrl->vcaps[vt].keyfield_set[keyset]; + if (kset->sw_per_item == 0 || kset->sw_per_item > vctrl->vcaps[vt].sw_count) + return NULL; + return kset; +} +EXPORT_SYMBOL_GPL(vcap_keyfieldset); + +/* Return the typegroup table for the matching keyset (using subword size) */ +const struct vcap_typegroup * +vcap_keyfield_typegroup(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_keyfield_set keyset) +{ + const struct vcap_set *kset = vcap_keyfieldset(vctrl, vt, keyset); + + /* Check that the keyset is valid */ + if (!kset) + return NULL; + return vctrl->vcaps[vt].keyfield_set_typegroups[kset->sw_per_item]; +} + +/* Return the number of keyfields in the keyset */ +int vcap_keyfield_count(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_keyfield_set keyset) +{ + /* Check that the keyset exists in the vcap keyset list */ + if (keyset >= vctrl->vcaps[vt].keyfield_set_size) + return 0; + return vctrl->vcaps[vt].keyfield_set_map_size[keyset]; +} + +static void vcap_encode_keyfield(struct vcap_rule_internal *ri, + const struct vcap_client_keyfield *kf, + const struct vcap_field *rf, + const struct vcap_typegroup *tgt) +{ + int sw_width = ri->vctrl->vcaps[ri->admin->vtype].sw_width; + struct vcap_cache_data *cache = &ri->admin->cache; + struct vcap_stream_iter iter; + const u8 *value, *mask; + + /* Encode the fields for the key and the mask in their respective + * streams, respecting the subword width. + */ + switch (kf->ctrl.type) { + case VCAP_FIELD_BIT: + value = &kf->data.u1.value; + mask = &kf->data.u1.mask; + break; + case VCAP_FIELD_U32: + value = (const u8 *)&kf->data.u32.value; + mask = (const u8 *)&kf->data.u32.mask; + break; + case VCAP_FIELD_U48: + value = kf->data.u48.value; + mask = kf->data.u48.mask; + break; + case VCAP_FIELD_U56: + value = kf->data.u56.value; + mask = kf->data.u56.mask; + break; + case VCAP_FIELD_U64: + value = kf->data.u64.value; + mask = kf->data.u64.mask; + break; + case VCAP_FIELD_U72: + value = kf->data.u72.value; + mask = kf->data.u72.mask; + break; + case VCAP_FIELD_U112: + value = kf->data.u112.value; + mask = kf->data.u112.mask; + break; + case VCAP_FIELD_U128: + value = kf->data.u128.value; + mask = kf->data.u128.mask; + break; + } + vcap_iter_init(&iter, sw_width, tgt, rf->offset); + vcap_encode_field(cache->keystream, &iter, rf->width, value); + vcap_iter_init(&iter, sw_width, tgt, rf->offset); + vcap_encode_field(cache->maskstream, &iter, rf->width, mask); +} + +static void vcap_encode_keyfield_typegroups(struct vcap_control *vctrl, + struct vcap_rule_internal *ri, + const struct vcap_typegroup *tgt) +{ + int sw_width = vctrl->vcaps[ri->admin->vtype].sw_width; + struct vcap_cache_data *cache = &ri->admin->cache; + + /* Encode the typegroup bits for the key and the mask in their streams, + * respecting the subword width. + */ + vcap_encode_typegroups(cache->keystream, sw_width, tgt, false); + vcap_encode_typegroups(cache->maskstream, sw_width, tgt, true); +} + +static int vcap_encode_rule_keyset(struct vcap_rule_internal *ri) +{ + const struct vcap_client_keyfield *ckf; + const struct vcap_typegroup *tg_table; + const struct vcap_field *kf_table; + int keyset_size; + + /* Get a valid set of fields for the specific keyset */ + kf_table = vcap_keyfields(ri->vctrl, ri->admin->vtype, ri->data.keyset); + if (!kf_table) { + pr_err("%s:%d: no fields available for this keyset: %d\n", + __func__, __LINE__, ri->data.keyset); + return -EINVAL; + } + /* Get a valid typegroup for the specific keyset */ + tg_table = vcap_keyfield_typegroup(ri->vctrl, ri->admin->vtype, + ri->data.keyset); + if (!tg_table) { + pr_err("%s:%d: no typegroups available for this keyset: %d\n", + __func__, __LINE__, ri->data.keyset); + return -EINVAL; + } + /* Get a valid size for the specific keyset */ + keyset_size = vcap_keyfield_count(ri->vctrl, ri->admin->vtype, + ri->data.keyset); + if (keyset_size == 0) { + pr_err("%s:%d: zero field count for this keyset: %d\n", + __func__, __LINE__, ri->data.keyset); + return -EINVAL; + } + /* Iterate over the keyfields (key, mask) in the rule + * and encode these bits + */ + if (list_empty(&ri->data.keyfields)) { + pr_err("%s:%d: no keyfields in the rule\n", __func__, __LINE__); + return -EINVAL; + } + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) { + /* Check that the client entry exists in the keyset */ + if (ckf->ctrl.key >= keyset_size) { + pr_err("%s:%d: key %d is not in vcap\n", + __func__, __LINE__, ckf->ctrl.key); + return -EINVAL; + } + vcap_encode_keyfield(ri, ckf, &kf_table[ckf->ctrl.key], tg_table); + } + /* Add typegroup bits to the key/mask bitstreams */ + vcap_encode_keyfield_typegroups(ri->vctrl, ri, tg_table); + return 0; +} + +/* Return the list of actionfields for the actionset */ +const struct vcap_field * +vcap_actionfields(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_actionfield_set actionset) +{ + /* Check that the actionset exists in the vcap actionset list */ + if (actionset >= vctrl->vcaps[vt].actionfield_set_size) + return NULL; + return vctrl->vcaps[vt].actionfield_set_map[actionset]; +} + +const struct vcap_set * +vcap_actionfieldset(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_actionfield_set actionset) +{ + const struct vcap_set *aset; + + /* Check that the actionset exists in the vcap actionset list */ + if (actionset >= vctrl->vcaps[vt].actionfield_set_size) + return NULL; + aset = &vctrl->vcaps[vt].actionfield_set[actionset]; + if (aset->sw_per_item == 0 || aset->sw_per_item > vctrl->vcaps[vt].sw_count) + return NULL; + return aset; +} + +/* Return the typegroup table for the matching actionset (using subword size) */ +const struct vcap_typegroup * +vcap_actionfield_typegroup(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_actionfield_set actionset) +{ + const struct vcap_set *aset = vcap_actionfieldset(vctrl, vt, actionset); + + /* Check that the actionset is valid */ + if (!aset) + return NULL; + return vctrl->vcaps[vt].actionfield_set_typegroups[aset->sw_per_item]; +} + +/* Return the number of actionfields in the actionset */ +int vcap_actionfield_count(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_actionfield_set actionset) +{ + /* Check that the actionset exists in the vcap actionset list */ + if (actionset >= vctrl->vcaps[vt].actionfield_set_size) + return 0; + return vctrl->vcaps[vt].actionfield_set_map_size[actionset]; +} + +static void vcap_encode_actionfield(struct vcap_rule_internal *ri, + const struct vcap_client_actionfield *af, + const struct vcap_field *rf, + const struct vcap_typegroup *tgt) +{ + int act_width = ri->vctrl->vcaps[ri->admin->vtype].act_width; + + struct vcap_cache_data *cache = &ri->admin->cache; + struct vcap_stream_iter iter; + const u8 *value; + + /* Encode the action field in the stream, respecting the subword width */ + switch (af->ctrl.type) { + case VCAP_FIELD_BIT: + value = &af->data.u1.value; + break; + case VCAP_FIELD_U32: + value = (const u8 *)&af->data.u32.value; + break; + case VCAP_FIELD_U48: + value = af->data.u48.value; + break; + case VCAP_FIELD_U56: + value = af->data.u56.value; + break; + case VCAP_FIELD_U64: + value = af->data.u64.value; + break; + case VCAP_FIELD_U72: + value = af->data.u72.value; + break; + case VCAP_FIELD_U112: + value = af->data.u112.value; + break; + case VCAP_FIELD_U128: + value = af->data.u128.value; + break; + } + vcap_iter_init(&iter, act_width, tgt, rf->offset); + vcap_encode_field(cache->actionstream, &iter, rf->width, value); +} + +static void vcap_encode_actionfield_typegroups(struct vcap_rule_internal *ri, + const struct vcap_typegroup *tgt) +{ + int sw_width = ri->vctrl->vcaps[ri->admin->vtype].act_width; + struct vcap_cache_data *cache = &ri->admin->cache; + + /* Encode the typegroup bits for the actionstream respecting the subword + * width. + */ + vcap_encode_typegroups(cache->actionstream, sw_width, tgt, false); +} + +static int vcap_encode_rule_actionset(struct vcap_rule_internal *ri) +{ + const struct vcap_client_actionfield *caf; + const struct vcap_typegroup *tg_table; + const struct vcap_field *af_table; + int actionset_size; + + /* Get a valid set of actionset fields for the specific actionset */ + af_table = vcap_actionfields(ri->vctrl, ri->admin->vtype, + ri->data.actionset); + if (!af_table) { + pr_err("%s:%d: no fields available for this actionset: %d\n", + __func__, __LINE__, ri->data.actionset); + return -EINVAL; + } + /* Get a valid typegroup for the specific actionset */ + tg_table = vcap_actionfield_typegroup(ri->vctrl, ri->admin->vtype, + ri->data.actionset); + if (!tg_table) { + pr_err("%s:%d: no typegroups available for this actionset: %d\n", + __func__, __LINE__, ri->data.actionset); + return -EINVAL; + } + /* Get a valid actionset size for the specific actionset */ + actionset_size = vcap_actionfield_count(ri->vctrl, ri->admin->vtype, + ri->data.actionset); + if (actionset_size == 0) { + pr_err("%s:%d: zero field count for this actionset: %d\n", + __func__, __LINE__, ri->data.actionset); + return -EINVAL; + } + /* Iterate over the actionfields in the rule + * and encode these bits + */ + if (list_empty(&ri->data.actionfields)) + pr_warn("%s:%d: no actionfields in the rule\n", + __func__, __LINE__); + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) { + /* Check that the client action exists in the actionset */ + if (caf->ctrl.action >= actionset_size) { + pr_err("%s:%d: action %d is not in vcap\n", + __func__, __LINE__, caf->ctrl.action); + return -EINVAL; + } + vcap_encode_actionfield(ri, caf, &af_table[caf->ctrl.action], + tg_table); + } + /* Add typegroup bits to the entry bitstreams */ + vcap_encode_actionfield_typegroups(ri, tg_table); + return 0; +} + +static int vcap_encode_rule(struct vcap_rule_internal *ri) +{ + int err; + + err = vcap_encode_rule_keyset(ri); + if (err) + return err; + err = vcap_encode_rule_actionset(ri); + if (err) + return err; + return 0; +} + +int vcap_api_check(struct vcap_control *ctrl) +{ + if (!ctrl) { + pr_err("%s:%d: vcap control is missing\n", __func__, __LINE__); + return -EINVAL; + } + if (!ctrl->ops || !ctrl->ops->validate_keyset || + !ctrl->ops->add_default_fields || !ctrl->ops->cache_erase || + !ctrl->ops->cache_write || !ctrl->ops->cache_read || + !ctrl->ops->init || !ctrl->ops->update || !ctrl->ops->move || + !ctrl->ops->port_info || !ctrl->ops->enable) { + pr_err("%s:%d: client operations are missing\n", + __func__, __LINE__); + return -ENOENT; + } + return 0; +} + +void vcap_erase_cache(struct vcap_rule_internal *ri) +{ + ri->vctrl->ops->cache_erase(ri->admin); +} + +/* Update the keyset for the rule */ +int vcap_set_rule_set_keyset(struct vcap_rule *rule, + enum vcap_keyfield_set keyset) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_set *kset; + int sw_width; + + kset = vcap_keyfieldset(ri->vctrl, ri->admin->vtype, keyset); + /* Check that the keyset is valid */ + if (!kset) + return -EINVAL; + ri->keyset_sw = kset->sw_per_item; + sw_width = ri->vctrl->vcaps[ri->admin->vtype].sw_width; + ri->keyset_sw_regs = DIV_ROUND_UP(sw_width, 32); + ri->data.keyset = keyset; + return 0; +} +EXPORT_SYMBOL_GPL(vcap_set_rule_set_keyset); + +/* Update the actionset for the rule */ +int vcap_set_rule_set_actionset(struct vcap_rule *rule, + enum vcap_actionfield_set actionset) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_set *aset; + int act_width; + + aset = vcap_actionfieldset(ri->vctrl, ri->admin->vtype, actionset); + /* Check that the actionset is valid */ + if (!aset) + return -EINVAL; + ri->actionset_sw = aset->sw_per_item; + act_width = ri->vctrl->vcaps[ri->admin->vtype].act_width; + ri->actionset_sw_regs = DIV_ROUND_UP(act_width, 32); + ri->data.actionset = actionset; + return 0; +} +EXPORT_SYMBOL_GPL(vcap_set_rule_set_actionset); + +/* Find a rule with a provided rule id */ +static struct vcap_rule_internal *vcap_lookup_rule(struct vcap_control *vctrl, + u32 id) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + + /* Look for the rule id in all vcaps */ + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(ri, &admin->rules, list) + if (ri->data.id == id) + return ri; + return NULL; +} + +/* Find a rule id with a provided cookie */ +int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + + /* Look for the rule id in all vcaps */ + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(ri, &admin->rules, list) + if (ri->data.cookie == cookie) + return ri->data.id; + return -ENOENT; +} +EXPORT_SYMBOL_GPL(vcap_lookup_rule_by_cookie); + +/* Make a shallow copy of the rule without the fields */ +struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri) +{ + struct vcap_rule_internal *duprule; + + /* Allocate the client part */ + duprule = kzalloc(sizeof(*duprule), GFP_KERNEL); + if (!duprule) + return ERR_PTR(-ENOMEM); + *duprule = *ri; + /* Not inserted in the VCAP */ + INIT_LIST_HEAD(&duprule->list); + /* No elements in these lists */ + INIT_LIST_HEAD(&duprule->data.keyfields); + INIT_LIST_HEAD(&duprule->data.actionfields); + return duprule; +} + +static void vcap_apply_width(u8 *dst, int width, int bytes) +{ + u8 bmask; + int idx; + + for (idx = 0; idx < bytes; idx++) { + if (width > 0) + if (width < 8) + bmask = (1 << width) - 1; + else + bmask = ~0; + else + bmask = 0; + dst[idx] &= bmask; + width -= 8; + } +} + +static void vcap_copy_from_w32be(u8 *dst, u8 *src, int size, int width) +{ + int idx, ridx, wstart, nidx; + int tail_bytes = (((size + 4) >> 2) << 2) - size; + + for (idx = 0, ridx = size - 1; idx < size; ++idx, --ridx) { + wstart = (idx >> 2) << 2; + nidx = wstart + 3 - (idx & 0x3); + if (nidx >= size) + nidx -= tail_bytes; + dst[nidx] = src[ridx]; + } + + vcap_apply_width(dst, width, size); +} + +static void vcap_copy_action_bit_field(struct vcap_u1_action *field, u8 *value) +{ + field->value = (*value) & 0x1; +} + +static void vcap_copy_limited_actionfield(u8 *dstvalue, u8 *srcvalue, + int width, int bytes) +{ + memcpy(dstvalue, srcvalue, bytes); + vcap_apply_width(dstvalue, width, bytes); +} + +static void vcap_copy_to_client_actionfield(struct vcap_rule_internal *ri, + struct vcap_client_actionfield *field, + u8 *value, u16 width) +{ + int field_size = actionfield_size_table[field->ctrl.type]; + + if (ri->admin->w32be) { + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + vcap_copy_action_bit_field(&field->data.u1, value); + break; + case VCAP_FIELD_U32: + vcap_copy_limited_actionfield((u8 *)&field->data.u32.value, + value, + width, field_size); + break; + case VCAP_FIELD_U48: + vcap_copy_from_w32be(field->data.u48.value, value, + field_size, width); + break; + case VCAP_FIELD_U56: + vcap_copy_from_w32be(field->data.u56.value, value, + field_size, width); + break; + case VCAP_FIELD_U64: + vcap_copy_from_w32be(field->data.u64.value, value, + field_size, width); + break; + case VCAP_FIELD_U72: + vcap_copy_from_w32be(field->data.u72.value, value, + field_size, width); + break; + case VCAP_FIELD_U112: + vcap_copy_from_w32be(field->data.u112.value, value, + field_size, width); + break; + case VCAP_FIELD_U128: + vcap_copy_from_w32be(field->data.u128.value, value, + field_size, width); + break; + }; + } else { + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + vcap_copy_action_bit_field(&field->data.u1, value); + break; + case VCAP_FIELD_U32: + vcap_copy_limited_actionfield((u8 *)&field->data.u32.value, + value, + width, field_size); + break; + case VCAP_FIELD_U48: + vcap_copy_limited_actionfield(field->data.u48.value, + value, + width, field_size); + break; + case VCAP_FIELD_U56: + vcap_copy_limited_actionfield(field->data.u56.value, + value, + width, field_size); + break; + case VCAP_FIELD_U64: + vcap_copy_limited_actionfield(field->data.u64.value, + value, + width, field_size); + break; + case VCAP_FIELD_U72: + vcap_copy_limited_actionfield(field->data.u72.value, + value, + width, field_size); + break; + case VCAP_FIELD_U112: + vcap_copy_limited_actionfield(field->data.u112.value, + value, + width, field_size); + break; + case VCAP_FIELD_U128: + vcap_copy_limited_actionfield(field->data.u128.value, + value, + width, field_size); + break; + }; + } +} + +static void vcap_copy_key_bit_field(struct vcap_u1_key *field, + u8 *value, u8 *mask) +{ + field->value = (*value) & 0x1; + field->mask = (*mask) & 0x1; +} + +static void vcap_copy_limited_keyfield(u8 *dstvalue, u8 *dstmask, + u8 *srcvalue, u8 *srcmask, + int width, int bytes) +{ + memcpy(dstvalue, srcvalue, bytes); + vcap_apply_width(dstvalue, width, bytes); + memcpy(dstmask, srcmask, bytes); + vcap_apply_width(dstmask, width, bytes); +} + +static void vcap_copy_to_client_keyfield(struct vcap_rule_internal *ri, + struct vcap_client_keyfield *field, + u8 *value, u8 *mask, u16 width) +{ + int field_size = keyfield_size_table[field->ctrl.type] / 2; + + if (ri->admin->w32be) { + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + vcap_copy_key_bit_field(&field->data.u1, value, mask); + break; + case VCAP_FIELD_U32: + vcap_copy_limited_keyfield((u8 *)&field->data.u32.value, + (u8 *)&field->data.u32.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U48: + vcap_copy_from_w32be(field->data.u48.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u48.mask, mask, + field_size, width); + break; + case VCAP_FIELD_U56: + vcap_copy_from_w32be(field->data.u56.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u56.mask, mask, + field_size, width); + break; + case VCAP_FIELD_U64: + vcap_copy_from_w32be(field->data.u64.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u64.mask, mask, + field_size, width); + break; + case VCAP_FIELD_U72: + vcap_copy_from_w32be(field->data.u72.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u72.mask, mask, + field_size, width); + break; + case VCAP_FIELD_U112: + vcap_copy_from_w32be(field->data.u112.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u112.mask, mask, + field_size, width); + break; + case VCAP_FIELD_U128: + vcap_copy_from_w32be(field->data.u128.value, value, + field_size, width); + vcap_copy_from_w32be(field->data.u128.mask, mask, + field_size, width); + break; + }; + } else { + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + vcap_copy_key_bit_field(&field->data.u1, value, mask); + break; + case VCAP_FIELD_U32: + vcap_copy_limited_keyfield((u8 *)&field->data.u32.value, + (u8 *)&field->data.u32.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U48: + vcap_copy_limited_keyfield(field->data.u48.value, + field->data.u48.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U56: + vcap_copy_limited_keyfield(field->data.u56.value, + field->data.u56.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U64: + vcap_copy_limited_keyfield(field->data.u64.value, + field->data.u64.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U72: + vcap_copy_limited_keyfield(field->data.u72.value, + field->data.u72.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U112: + vcap_copy_limited_keyfield(field->data.u112.value, + field->data.u112.mask, + value, mask, + width, field_size); + break; + case VCAP_FIELD_U128: + vcap_copy_limited_keyfield(field->data.u128.value, + field->data.u128.mask, + value, mask, + width, field_size); + break; + }; + } +} + +static void vcap_rule_alloc_keyfield(struct vcap_rule_internal *ri, + const struct vcap_field *keyfield, + enum vcap_key_field key, + u8 *value, u8 *mask) +{ + struct vcap_client_keyfield *field; + + field = kzalloc(sizeof(*field), GFP_KERNEL); + if (!field) + return; + INIT_LIST_HEAD(&field->ctrl.list); + field->ctrl.key = key; + field->ctrl.type = keyfield->type; + vcap_copy_to_client_keyfield(ri, field, value, mask, keyfield->width); + list_add_tail(&field->ctrl.list, &ri->data.keyfields); +} + +/* Read key data from a VCAP address and discover if there is a rule keyset + * here + */ +static bool +vcap_verify_actionstream_actionset(struct vcap_control *vctrl, + enum vcap_type vt, + u32 *actionstream, + enum vcap_actionfield_set actionset) +{ + const struct vcap_typegroup *tgt; + const struct vcap_field *fields; + const struct vcap_set *info; + + if (vcap_actionfield_count(vctrl, vt, actionset) == 0) + return false; + + info = vcap_actionfieldset(vctrl, vt, actionset); + /* Check that the actionset is valid */ + if (!info) + return false; + + /* a type_id of value -1 means that there is no type field */ + if (info->type_id == (u8)-1) + return true; + + /* Get a valid typegroup for the specific actionset */ + tgt = vcap_actionfield_typegroup(vctrl, vt, actionset); + if (!tgt) + return false; + + fields = vcap_actionfields(vctrl, vt, actionset); + if (!fields) + return false; + + /* Later this will be expanded with a check of the type id */ + return true; +} + +/* Find the subword width of the action typegroup that matches the stream data + */ +static int vcap_find_actionstream_typegroup_sw(struct vcap_control *vctrl, + enum vcap_type vt, u32 *stream, + int sw_max) +{ + const struct vcap_typegroup **tgt; + int sw_idx, res; + + tgt = vctrl->vcaps[vt].actionfield_set_typegroups; + /* Try the longest subword match first */ + for (sw_idx = vctrl->vcaps[vt].sw_count; sw_idx >= 0; sw_idx--) { + if (!tgt[sw_idx]) + continue; + res = vcap_verify_typegroups(stream, vctrl->vcaps[vt].act_width, + tgt[sw_idx], false, sw_max); + if (res == 0) + return sw_idx; + } + return -EINVAL; +} + +/* Verify that the typegroup information, subword count, actionset and type id + * are in sync and correct, return the actionset + */ +static enum vcap_actionfield_set +vcap_find_actionstream_actionset(struct vcap_control *vctrl, + enum vcap_type vt, + u32 *stream, + int sw_max) +{ + const struct vcap_set *actionfield_set; + int sw_count, idx; + bool res; + + sw_count = vcap_find_actionstream_typegroup_sw(vctrl, vt, stream, + sw_max); + if (sw_count < 0) + return sw_count; + + actionfield_set = vctrl->vcaps[vt].actionfield_set; + for (idx = 0; idx < vctrl->vcaps[vt].actionfield_set_size; ++idx) { + if (actionfield_set[idx].sw_per_item != sw_count) + continue; + + res = vcap_verify_actionstream_actionset(vctrl, vt, + stream, idx); + if (res) + return idx; + } + return -EINVAL; +} + +/* Store action value in an element in a list for the client */ +static void vcap_rule_alloc_actionfield(struct vcap_rule_internal *ri, + const struct vcap_field *actionfield, + enum vcap_action_field action, + u8 *value) +{ + struct vcap_client_actionfield *field; + + field = kzalloc(sizeof(*field), GFP_KERNEL); + if (!field) + return; + INIT_LIST_HEAD(&field->ctrl.list); + field->ctrl.action = action; + field->ctrl.type = actionfield->type; + vcap_copy_to_client_actionfield(ri, field, value, actionfield->width); + list_add_tail(&field->ctrl.list, &ri->data.actionfields); +} + +static int vcap_decode_actionset(struct vcap_rule_internal *ri) +{ + struct vcap_control *vctrl = ri->vctrl; + struct vcap_admin *admin = ri->admin; + const struct vcap_field *actionfield; + enum vcap_actionfield_set actionset; + enum vcap_type vt = admin->vtype; + const struct vcap_typegroup *tgt; + struct vcap_stream_iter iter; + int idx, res, actfield_count; + u32 *actstream; + u8 value[16]; + + actstream = admin->cache.actionstream; + res = vcap_find_actionstream_actionset(vctrl, vt, actstream, 0); + if (res < 0) { + pr_err("%s:%d: could not find valid actionset: %d\n", + __func__, __LINE__, res); + return -EINVAL; + } + actionset = res; + actfield_count = vcap_actionfield_count(vctrl, vt, actionset); + actionfield = vcap_actionfields(vctrl, vt, actionset); + tgt = vcap_actionfield_typegroup(vctrl, vt, actionset); + /* Start decoding the stream */ + for (idx = 0; idx < actfield_count; ++idx) { + if (actionfield[idx].width <= 0) + continue; + /* Get the action */ + memset(value, 0, DIV_ROUND_UP(actionfield[idx].width, 8)); + vcap_iter_init(&iter, vctrl->vcaps[vt].act_width, tgt, + actionfield[idx].offset); + vcap_decode_field(actstream, &iter, actionfield[idx].width, + value); + /* Skip if no bits are set */ + if (vcap_bitarray_zero(actionfield[idx].width, value)) + continue; + vcap_rule_alloc_actionfield(ri, &actionfield[idx], idx, value); + /* Later the action id will also be checked */ + } + return vcap_set_rule_set_actionset((struct vcap_rule *)ri, actionset); +} + +static int vcap_decode_keyset(struct vcap_rule_internal *ri) +{ + struct vcap_control *vctrl = ri->vctrl; + struct vcap_stream_iter kiter, miter; + struct vcap_admin *admin = ri->admin; + enum vcap_keyfield_set keysets[10]; + const struct vcap_field *keyfield; + enum vcap_type vt = admin->vtype; + const struct vcap_typegroup *tgt; + struct vcap_keyset_list matches; + enum vcap_keyfield_set keyset; + int idx, res, keyfield_count; + u32 *maskstream; + u32 *keystream; + u8 value[16]; + u8 mask[16]; + + keystream = admin->cache.keystream; + maskstream = admin->cache.maskstream; + matches.keysets = keysets; + matches.cnt = 0; + matches.max = ARRAY_SIZE(keysets); + res = vcap_find_keystream_keysets(vctrl, vt, keystream, maskstream, + false, 0, &matches); + if (res < 0) { + pr_err("%s:%d: could not find valid keysets: %d\n", + __func__, __LINE__, res); + return -EINVAL; + } + keyset = matches.keysets[0]; + keyfield_count = vcap_keyfield_count(vctrl, vt, keyset); + keyfield = vcap_keyfields(vctrl, vt, keyset); + tgt = vcap_keyfield_typegroup(vctrl, vt, keyset); + /* Start decoding the streams */ + for (idx = 0; idx < keyfield_count; ++idx) { + if (keyfield[idx].width <= 0) + continue; + /* First get the mask */ + memset(mask, 0, DIV_ROUND_UP(keyfield[idx].width, 8)); + vcap_iter_init(&miter, vctrl->vcaps[vt].sw_width, tgt, + keyfield[idx].offset); + vcap_decode_field(maskstream, &miter, keyfield[idx].width, + mask); + /* Skip if no mask bits are set */ + if (vcap_bitarray_zero(keyfield[idx].width, mask)) + continue; + /* Get the key */ + memset(value, 0, DIV_ROUND_UP(keyfield[idx].width, 8)); + vcap_iter_init(&kiter, vctrl->vcaps[vt].sw_width, tgt, + keyfield[idx].offset); + vcap_decode_field(keystream, &kiter, keyfield[idx].width, + value); + vcap_rule_alloc_keyfield(ri, &keyfield[idx], idx, value, mask); + } + return vcap_set_rule_set_keyset((struct vcap_rule *)ri, keyset); +} + +/* Read VCAP content into the VCAP cache */ +static int vcap_read_rule(struct vcap_rule_internal *ri) +{ + struct vcap_admin *admin = ri->admin; + int sw_idx, ent_idx = 0, act_idx = 0; + u32 addr = ri->addr; + + if (!ri->size || !ri->keyset_sw_regs || !ri->actionset_sw_regs) { + pr_err("%s:%d: rule is empty\n", __func__, __LINE__); + return -EINVAL; + } + vcap_erase_cache(ri); + /* Use the values in the streams to read the VCAP cache */ + for (sw_idx = 0; sw_idx < ri->size; sw_idx++, addr++) { + ri->vctrl->ops->update(ri->ndev, admin, VCAP_CMD_READ, + VCAP_SEL_ALL, addr); + ri->vctrl->ops->cache_read(ri->ndev, admin, + VCAP_SEL_ENTRY, ent_idx, + ri->keyset_sw_regs); + ri->vctrl->ops->cache_read(ri->ndev, admin, + VCAP_SEL_ACTION, act_idx, + ri->actionset_sw_regs); + if (sw_idx == 0) + ri->vctrl->ops->cache_read(ri->ndev, admin, + VCAP_SEL_COUNTER, + ri->counter_id, 0); + ent_idx += ri->keyset_sw_regs; + act_idx += ri->actionset_sw_regs; + } + return 0; +} + +/* Write VCAP cache content to the VCAP HW instance */ +static int vcap_write_rule(struct vcap_rule_internal *ri) +{ + struct vcap_admin *admin = ri->admin; + int sw_idx, ent_idx = 0, act_idx = 0; + u32 addr = ri->addr; + + if (!ri->size || !ri->keyset_sw_regs || !ri->actionset_sw_regs) { + pr_err("%s:%d: rule is empty\n", __func__, __LINE__); + return -EINVAL; + } + /* Use the values in the streams to write the VCAP cache */ + for (sw_idx = 0; sw_idx < ri->size; sw_idx++, addr++) { + ri->vctrl->ops->cache_write(ri->ndev, admin, + VCAP_SEL_ENTRY, ent_idx, + ri->keyset_sw_regs); + ri->vctrl->ops->cache_write(ri->ndev, admin, + VCAP_SEL_ACTION, act_idx, + ri->actionset_sw_regs); + ri->vctrl->ops->update(ri->ndev, admin, VCAP_CMD_WRITE, + VCAP_SEL_ALL, addr); + ent_idx += ri->keyset_sw_regs; + act_idx += ri->actionset_sw_regs; + } + return 0; +} + +static int vcap_write_counter(struct vcap_rule_internal *ri, + struct vcap_counter *ctr) +{ + struct vcap_admin *admin = ri->admin; + + admin->cache.counter = ctr->value; + admin->cache.sticky = ctr->sticky; + ri->vctrl->ops->cache_write(ri->ndev, admin, VCAP_SEL_COUNTER, + ri->counter_id, 0); + ri->vctrl->ops->update(ri->ndev, admin, VCAP_CMD_WRITE, + VCAP_SEL_COUNTER, ri->addr); + return 0; +} + +/* Convert a chain id to a VCAP lookup index */ +int vcap_chain_id_to_lookup(struct vcap_admin *admin, int cur_cid) +{ + int lookup_first = admin->vinst * admin->lookups_per_instance; + int lookup_last = lookup_first + admin->lookups_per_instance; + int cid_next = admin->first_cid + VCAP_CID_LOOKUP_SIZE; + int cid = admin->first_cid; + int lookup; + + for (lookup = lookup_first; lookup < lookup_last; ++lookup, + cid += VCAP_CID_LOOKUP_SIZE, cid_next += VCAP_CID_LOOKUP_SIZE) + if (cur_cid >= cid && cur_cid < cid_next) + return lookup; + return 0; +} +EXPORT_SYMBOL_GPL(vcap_chain_id_to_lookup); + +/* Lookup a vcap instance using chain id */ +struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid) +{ + struct vcap_admin *admin; + + if (vcap_api_check(vctrl)) + return NULL; + + list_for_each_entry(admin, &vctrl->list, list) { + if (cid >= admin->first_cid && cid <= admin->last_cid) + return admin; + } + return NULL; +} +EXPORT_SYMBOL_GPL(vcap_find_admin); + +/* Is the next chain id in the following lookup, possible in another VCAP */ +bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid) +{ + struct vcap_admin *admin, *next_admin; + int lookup, next_lookup; + + /* The offset must be at least one lookup */ + if (next_cid < cur_cid + VCAP_CID_LOOKUP_SIZE) + return false; + + if (vcap_api_check(vctrl)) + return false; + + admin = vcap_find_admin(vctrl, cur_cid); + if (!admin) + return false; + + /* If no VCAP contains the next chain, the next chain must be beyond + * the last chain in the current VCAP + */ + next_admin = vcap_find_admin(vctrl, next_cid); + if (!next_admin) + return next_cid > admin->last_cid; + + lookup = vcap_chain_id_to_lookup(admin, cur_cid); + next_lookup = vcap_chain_id_to_lookup(next_admin, next_cid); + + /* Next lookup must be the following lookup */ + if (admin == next_admin || admin->vtype == next_admin->vtype) + return next_lookup == lookup + 1; + + /* Must be the first lookup in the next VCAP instance */ + return next_lookup == 0; +} +EXPORT_SYMBOL_GPL(vcap_is_next_lookup); + +/* Check if there is room for a new rule */ +static int vcap_rule_space(struct vcap_admin *admin, int size) +{ + if (admin->last_used_addr - size < admin->first_valid_addr) { + pr_err("%s:%d: No room for rule size: %u, %u\n", + __func__, __LINE__, size, admin->first_valid_addr); + return -ENOSPC; + } + return 0; +} + +/* Add the keyset typefield to the list of rule keyfields */ +static int vcap_add_type_keyfield(struct vcap_rule *rule) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_keyfield_set keyset = rule->keyset; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + const struct vcap_set *kset; + int ret = -EINVAL; + + kset = vcap_keyfieldset(ri->vctrl, vt, keyset); + if (!kset) + return ret; + if (kset->type_id == (u8)-1) /* No type field is needed */ + return 0; + + fields = vcap_keyfields(ri->vctrl, vt, keyset); + if (!fields) + return -EINVAL; + if (fields[VCAP_KF_TYPE].width > 1) { + ret = vcap_rule_add_key_u32(rule, VCAP_KF_TYPE, + kset->type_id, 0xff); + } else { + if (kset->type_id) + ret = vcap_rule_add_key_bit(rule, VCAP_KF_TYPE, + VCAP_BIT_1); + else + ret = vcap_rule_add_key_bit(rule, VCAP_KF_TYPE, + VCAP_BIT_0); + } + return 0; +} + +/* Add a keyset to a keyset list */ +bool vcap_keyset_list_add(struct vcap_keyset_list *keysetlist, + enum vcap_keyfield_set keyset) +{ + int idx; + + if (keysetlist->cnt < keysetlist->max) { + /* Avoid duplicates */ + for (idx = 0; idx < keysetlist->cnt; ++idx) + if (keysetlist->keysets[idx] == keyset) + return keysetlist->cnt < keysetlist->max; + keysetlist->keysets[keysetlist->cnt++] = keyset; + } + return keysetlist->cnt < keysetlist->max; +} +EXPORT_SYMBOL_GPL(vcap_keyset_list_add); + +/* map keyset id to a string with the keyset name */ +const char *vcap_keyset_name(struct vcap_control *vctrl, + enum vcap_keyfield_set keyset) +{ + return vctrl->stats->keyfield_set_names[keyset]; +} +EXPORT_SYMBOL_GPL(vcap_keyset_name); + +/* map key field id to a string with the key name */ +const char *vcap_keyfield_name(struct vcap_control *vctrl, + enum vcap_key_field key) +{ + return vctrl->stats->keyfield_names[key]; +} +EXPORT_SYMBOL_GPL(vcap_keyfield_name); + +/* map actionset id to a string with the actionset name */ +const char *vcap_actionset_name(struct vcap_control *vctrl, + enum vcap_actionfield_set actionset) +{ + return vctrl->stats->actionfield_set_names[actionset]; +} + +/* map action field id to a string with the action name */ +const char *vcap_actionfield_name(struct vcap_control *vctrl, + enum vcap_action_field action) +{ + return vctrl->stats->actionfield_names[action]; +} + +/* Return the keyfield that matches a key in a keyset */ +static const struct vcap_field * +vcap_find_keyset_keyfield(struct vcap_control *vctrl, + enum vcap_type vtype, + enum vcap_keyfield_set keyset, + enum vcap_key_field key) +{ + const struct vcap_field *fields; + int idx, count; + + fields = vcap_keyfields(vctrl, vtype, keyset); + if (!fields) + return NULL; + + /* Iterate the keyfields of the keyset */ + count = vcap_keyfield_count(vctrl, vtype, keyset); + for (idx = 0; idx < count; ++idx) { + if (fields[idx].width == 0) + continue; + + if (key == idx) + return &fields[idx]; + } + + return NULL; +} + +/* Match a list of keys against the keysets available in a vcap type */ +static bool _vcap_rule_find_keysets(struct vcap_rule_internal *ri, + struct vcap_keyset_list *matches) +{ + const struct vcap_client_keyfield *ckf; + int keyset, found, keycount, map_size; + const struct vcap_field **map; + enum vcap_type vtype; + + vtype = ri->admin->vtype; + map = ri->vctrl->vcaps[vtype].keyfield_set_map; + map_size = ri->vctrl->vcaps[vtype].keyfield_set_size; + + /* Get a count of the keyfields we want to match */ + keycount = 0; + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + ++keycount; + + matches->cnt = 0; + /* Iterate the keysets of the VCAP */ + for (keyset = 0; keyset < map_size; ++keyset) { + if (!map[keyset]) + continue; + + /* Iterate the keys in the rule */ + found = 0; + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + if (vcap_find_keyset_keyfield(ri->vctrl, vtype, + keyset, ckf->ctrl.key)) + ++found; + + /* Save the keyset if all keyfields were found */ + if (found == keycount) + if (!vcap_keyset_list_add(matches, keyset)) + /* bail out when the quota is filled */ + break; + } + + return matches->cnt > 0; +} + +/* Match a list of keys against the keysets available in a vcap type */ +bool vcap_rule_find_keysets(struct vcap_rule *rule, + struct vcap_keyset_list *matches) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + + return _vcap_rule_find_keysets(ri, matches); +} +EXPORT_SYMBOL_GPL(vcap_rule_find_keysets); + +/* Validate a rule with respect to available port keys */ +int vcap_val_rule(struct vcap_rule *rule, u16 l3_proto) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_keyset_list matches = {}; + enum vcap_keyfield_set keysets[10]; + int ret; + + ret = vcap_api_check(ri->vctrl); + if (ret) + return ret; + if (!ri->admin) { + ri->data.exterr = VCAP_ERR_NO_ADMIN; + return -EINVAL; + } + if (!ri->ndev) { + ri->data.exterr = VCAP_ERR_NO_NETDEV; + return -EINVAL; + } + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + if (ri->data.keyset == VCAP_KFS_NO_VALUE) { + /* Iterate over rule keyfields and select keysets that fits */ + if (!_vcap_rule_find_keysets(ri, &matches)) { + ri->data.exterr = VCAP_ERR_NO_KEYSET_MATCH; + return -EINVAL; + } + } else { + /* prepare for keyset validation */ + keysets[0] = ri->data.keyset; + matches.cnt = 1; + } + + /* Pick a keyset that is supported in the port lookups */ + ret = ri->vctrl->ops->validate_keyset(ri->ndev, ri->admin, rule, + &matches, l3_proto); + if (ret < 0) { + pr_err("%s:%d: keyset validation failed: %d\n", + __func__, __LINE__, ret); + ri->data.exterr = VCAP_ERR_NO_PORT_KEYSET_MATCH; + return ret; + } + /* use the keyset that is supported in the port lookups */ + ret = vcap_set_rule_set_keyset(rule, ret); + if (ret < 0) { + pr_err("%s:%d: keyset was not updated: %d\n", + __func__, __LINE__, ret); + return ret; + } + if (ri->data.actionset == VCAP_AFS_NO_VALUE) { + /* Later also actionsets will be matched against actions in + * the rule, and the type will be set accordingly + */ + ri->data.exterr = VCAP_ERR_NO_ACTIONSET_MATCH; + return -EINVAL; + } + vcap_add_type_keyfield(rule); + /* Add default fields to this rule */ + ri->vctrl->ops->add_default_fields(ri->ndev, ri->admin, rule); + + /* Rule size is the maximum of the entry and action subword count */ + ri->size = max(ri->keyset_sw, ri->actionset_sw); + + /* Finally check if there is room for the rule in the VCAP */ + return vcap_rule_space(ri->admin, ri->size); +} +EXPORT_SYMBOL_GPL(vcap_val_rule); + +/* Entries are sorted with increasing values of sort_key. + * I.e. Lowest numerical sort_key is first in list. + * In order to locate largest keys first in list we negate the key size with + * (max_size - size). + */ +static u32 vcap_sort_key(u32 max_size, u32 size, u8 user, u16 prio) +{ + return ((max_size - size) << 24) | (user << 16) | prio; +} + +/* calculate the address of the next rule after this (lower address and prio) */ +static u32 vcap_next_rule_addr(u32 addr, struct vcap_rule_internal *ri) +{ + return ((addr - ri->size) / ri->size) * ri->size; +} + +/* Assign a unique rule id and autogenerate one if id == 0 */ +static u32 vcap_set_rule_id(struct vcap_rule_internal *ri) +{ + if (ri->data.id != 0) + return ri->data.id; + + for (u32 next_id = 1; next_id < ~0; ++next_id) { + if (!vcap_lookup_rule(ri->vctrl, next_id)) { + ri->data.id = next_id; + break; + } + } + return ri->data.id; +} + +static int vcap_insert_rule(struct vcap_rule_internal *ri, + struct vcap_rule_move *move) +{ + int sw_count = ri->vctrl->vcaps[ri->admin->vtype].sw_count; + struct vcap_rule_internal *duprule, *iter, *elem = NULL; + struct vcap_admin *admin = ri->admin; + u32 addr; + + ri->sort_key = vcap_sort_key(sw_count, ri->size, ri->data.user, + ri->data.priority); + + /* Insert the new rule in the list of rule based on the sort key + * If the rule needs to be inserted between existing rules then move + * these rules to make room for the new rule and update their start + * address. + */ + list_for_each_entry(iter, &admin->rules, list) { + if (ri->sort_key < iter->sort_key) { + elem = iter; + break; + } + } + + if (!elem) { + ri->addr = vcap_next_rule_addr(admin->last_used_addr, ri); + admin->last_used_addr = ri->addr; + + /* Add a shallow copy of the rule to the VCAP list */ + duprule = vcap_dup_rule(ri); + if (IS_ERR(duprule)) + return PTR_ERR(duprule); + + list_add_tail(&duprule->list, &admin->rules); + return 0; + } + + /* Reuse the space of the current rule */ + addr = elem->addr + elem->size; + ri->addr = vcap_next_rule_addr(addr, ri); + addr = ri->addr; + + /* Add a shallow copy of the rule to the VCAP list */ + duprule = vcap_dup_rule(ri); + if (IS_ERR(duprule)) + return PTR_ERR(duprule); + + /* Add before the current entry */ + list_add_tail(&duprule->list, &elem->list); + + /* Update the current rule */ + elem->addr = vcap_next_rule_addr(addr, elem); + addr = elem->addr; + + /* Update the address in the remaining rules in the list */ + list_for_each_entry_continue(elem, &admin->rules, list) { + elem->addr = vcap_next_rule_addr(addr, elem); + addr = elem->addr; + } + + /* Update the move info */ + move->addr = admin->last_used_addr; + move->count = ri->addr - addr; + move->offset = admin->last_used_addr - addr; + admin->last_used_addr = addr; + return 0; +} + +static void vcap_move_rules(struct vcap_rule_internal *ri, + struct vcap_rule_move *move) +{ + ri->vctrl->ops->move(ri->ndev, ri->admin, move->addr, + move->offset, move->count); +} + +/* Encode and write a validated rule to the VCAP */ +int vcap_add_rule(struct vcap_rule *rule) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_rule_move move = {0}; + int ret; + + ret = vcap_api_check(ri->vctrl); + if (ret) + return ret; + /* Insert the new rule in the list of vcap rules */ + mutex_lock(&ri->admin->lock); + ret = vcap_insert_rule(ri, &move); + if (ret < 0) { + pr_err("%s:%d: could not insert rule in vcap list: %d\n", + __func__, __LINE__, ret); + goto out; + } + if (move.count > 0) + vcap_move_rules(ri, &move); + ret = vcap_encode_rule(ri); + if (ret) { + pr_err("%s:%d: rule encoding error: %d\n", __func__, __LINE__, ret); + goto out; + } + + ret = vcap_write_rule(ri); + if (ret) + pr_err("%s:%d: rule write error: %d\n", __func__, __LINE__, ret); +out: + mutex_unlock(&ri->admin->lock); + return ret; +} +EXPORT_SYMBOL_GPL(vcap_add_rule); + +/* Allocate a new rule with the provided arguments */ +struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, + struct net_device *ndev, int vcap_chain_id, + enum vcap_user user, u16 priority, + u32 id) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + int err, maxsize; + + err = vcap_api_check(vctrl); + if (err) + return ERR_PTR(err); + if (!ndev) + return ERR_PTR(-ENODEV); + /* Get the VCAP instance */ + admin = vcap_find_admin(vctrl, vcap_chain_id); + if (!admin) + return ERR_PTR(-ENOENT); + /* Sanity check that this VCAP is supported on this platform */ + if (vctrl->vcaps[admin->vtype].rows == 0) + return ERR_PTR(-EINVAL); + /* Check if a rule with this id already exists */ + if (vcap_lookup_rule(vctrl, id)) + return ERR_PTR(-EEXIST); + /* Check if there is room for the rule in the block(s) of the VCAP */ + maxsize = vctrl->vcaps[admin->vtype].sw_count; /* worst case rule size */ + if (vcap_rule_space(admin, maxsize)) + return ERR_PTR(-ENOSPC); + /* Create a container for the rule and return it */ + ri = kzalloc(sizeof(*ri), GFP_KERNEL); + if (!ri) + return ERR_PTR(-ENOMEM); + ri->data.vcap_chain_id = vcap_chain_id; + ri->data.user = user; + ri->data.priority = priority; + ri->data.id = id; + ri->data.keyset = VCAP_KFS_NO_VALUE; + ri->data.actionset = VCAP_AFS_NO_VALUE; + INIT_LIST_HEAD(&ri->list); + INIT_LIST_HEAD(&ri->data.keyfields); + INIT_LIST_HEAD(&ri->data.actionfields); + ri->ndev = ndev; + ri->admin = admin; /* refer to the vcap instance */ + ri->vctrl = vctrl; /* refer to the client */ + if (vcap_set_rule_id(ri) == 0) + goto out_free; + vcap_erase_cache(ri); + return (struct vcap_rule *)ri; + +out_free: + kfree(ri); + return ERR_PTR(-EINVAL); +} +EXPORT_SYMBOL_GPL(vcap_alloc_rule); + +/* Free mem of a rule owned by client after the rule as been added to the VCAP */ +void vcap_free_rule(struct vcap_rule *rule) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_client_actionfield *caf, *next_caf; + struct vcap_client_keyfield *ckf, *next_ckf; + + /* Deallocate the list of keys and actions */ + list_for_each_entry_safe(ckf, next_ckf, &ri->data.keyfields, ctrl.list) { + list_del(&ckf->ctrl.list); + kfree(ckf); + } + list_for_each_entry_safe(caf, next_caf, &ri->data.actionfields, ctrl.list) { + list_del(&caf->ctrl.list); + kfree(caf); + } + /* Deallocate the rule */ + kfree(rule); +} +EXPORT_SYMBOL_GPL(vcap_free_rule); + +struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id) +{ + struct vcap_rule_internal *elem; + struct vcap_rule_internal *ri; + int err; + + ri = NULL; + + err = vcap_api_check(vctrl); + if (err) + return ERR_PTR(err); + elem = vcap_lookup_rule(vctrl, id); + if (!elem) + return NULL; + mutex_lock(&elem->admin->lock); + ri = vcap_dup_rule(elem); + if (IS_ERR(ri)) + goto unlock; + err = vcap_read_rule(ri); + if (err) { + ri = ERR_PTR(err); + goto unlock; + } + err = vcap_decode_keyset(ri); + if (err) { + ri = ERR_PTR(err); + goto unlock; + } + err = vcap_decode_actionset(ri); + if (err) { + ri = ERR_PTR(err); + goto unlock; + } + +unlock: + mutex_unlock(&elem->admin->lock); + return (struct vcap_rule *)ri; +} +EXPORT_SYMBOL_GPL(vcap_get_rule); + +/* Update existing rule */ +int vcap_mod_rule(struct vcap_rule *rule) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_counter ctr; + int err; + + err = vcap_api_check(ri->vctrl); + if (err) + return err; + + if (!vcap_lookup_rule(ri->vctrl, ri->data.id)) + return -ENOENT; + + mutex_lock(&ri->admin->lock); + /* Encode the bitstreams to the VCAP cache */ + vcap_erase_cache(ri); + err = vcap_encode_rule(ri); + if (err) + goto out; + + err = vcap_write_rule(ri); + if (err) + goto out; + + memset(&ctr, 0, sizeof(ctr)); + err = vcap_write_counter(ri, &ctr); + if (err) + goto out; + +out: + mutex_unlock(&ri->admin->lock); + return err; +} +EXPORT_SYMBOL_GPL(vcap_mod_rule); + +/* Return the alignment offset for a new rule address */ +static int vcap_valid_rule_move(struct vcap_rule_internal *el, int offset) +{ + return (el->addr + offset) % el->size; +} + +/* Update the rule address with an offset */ +static void vcap_adjust_rule_addr(struct vcap_rule_internal *el, int offset) +{ + el->addr += offset; +} + +/* Rules needs to be moved to fill the gap of the deleted rule */ +static int vcap_fill_rule_gap(struct vcap_rule_internal *ri) +{ + struct vcap_admin *admin = ri->admin; + struct vcap_rule_internal *elem; + struct vcap_rule_move move; + int gap = 0, offset = 0; + + /* If the first rule is deleted: Move other rules to the top */ + if (list_is_first(&ri->list, &admin->rules)) + offset = admin->last_valid_addr + 1 - ri->addr - ri->size; + + /* Locate gaps between odd size rules and adjust the move */ + elem = ri; + list_for_each_entry_continue(elem, &admin->rules, list) + gap += vcap_valid_rule_move(elem, ri->size); + + /* Update the address in the remaining rules in the list */ + elem = ri; + list_for_each_entry_continue(elem, &admin->rules, list) + vcap_adjust_rule_addr(elem, ri->size + gap + offset); + + /* Update the move info */ + move.addr = admin->last_used_addr; + move.count = ri->addr - admin->last_used_addr - gap; + move.offset = -(ri->size + gap + offset); + + /* Do the actual move operation */ + vcap_move_rules(ri, &move); + + return gap + offset; +} + +/* Delete rule in a VCAP instance */ +int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id) +{ + struct vcap_rule_internal *ri, *elem; + struct vcap_admin *admin; + int gap = 0, err; + + /* This will later also handle rule moving */ + if (!ndev) + return -ENODEV; + err = vcap_api_check(vctrl); + if (err) + return err; + /* Look for the rule id in all vcaps */ + ri = vcap_lookup_rule(vctrl, id); + if (!ri) + return -EINVAL; + admin = ri->admin; + + if (ri->addr > admin->last_used_addr) + gap = vcap_fill_rule_gap(ri); + + /* Delete the rule from the list of rules and the cache */ + mutex_lock(&admin->lock); + list_del(&ri->list); + vctrl->ops->init(ndev, admin, admin->last_used_addr, ri->size + gap); + kfree(ri); + mutex_unlock(&admin->lock); + + /* Update the last used address, set to default when no rules */ + if (list_empty(&admin->rules)) { + admin->last_used_addr = admin->last_valid_addr + 1; + } else { + elem = list_last_entry(&admin->rules, struct vcap_rule_internal, + list); + admin->last_used_addr = elem->addr; + } + return 0; +} +EXPORT_SYMBOL_GPL(vcap_del_rule); + +/* Delete all rules in the VCAP instance */ +int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) +{ + struct vcap_enabled_port *eport, *next_eport; + struct vcap_rule_internal *ri, *next_ri; + int ret = vcap_api_check(vctrl); + + if (ret) + return ret; + + mutex_lock(&admin->lock); + list_for_each_entry_safe(ri, next_ri, &admin->rules, list) { + vctrl->ops->init(ri->ndev, admin, ri->addr, ri->size); + list_del(&ri->list); + kfree(ri); + } + admin->last_used_addr = admin->last_valid_addr; + + /* Remove list of enabled ports */ + list_for_each_entry_safe(eport, next_eport, &admin->enabled, list) { + list_del(&eport->list); + kfree(eport); + } + mutex_unlock(&admin->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(vcap_del_rules); + +/* Find a client key field in a rule */ +static struct vcap_client_keyfield * +vcap_find_keyfield(struct vcap_rule *rule, enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_client_keyfield *ckf; + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + if (ckf->ctrl.key == key) + return ckf; + return NULL; +} + +/* Find information on a key field in a rule */ +const struct vcap_field *vcap_lookup_keyfield(struct vcap_rule *rule, + enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_keyfield_set keyset = rule->keyset; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + + if (keyset == VCAP_KFS_NO_VALUE) + return NULL; + fields = vcap_keyfields(ri->vctrl, vt, keyset); + if (!fields) + return NULL; + return &fields[key]; +} +EXPORT_SYMBOL_GPL(vcap_lookup_keyfield); + +/* Copy data from src to dst but reverse the data in chunks of 32bits. + * For example if src is 00:11:22:33:44:55 where 55 is LSB the dst will + * have the value 22:33:44:55:00:11. + */ +static void vcap_copy_to_w32be(u8 *dst, u8 *src, int size) +{ + for (int idx = 0; idx < size; ++idx) { + int first_byte_index = 0; + int nidx; + + first_byte_index = size - (((idx >> 2) + 1) << 2); + if (first_byte_index < 0) + first_byte_index = 0; + nidx = idx + first_byte_index - (idx & ~0x3); + dst[nidx] = src[idx]; + } +} + +static void vcap_copy_from_client_keyfield(struct vcap_rule *rule, + struct vcap_client_keyfield *field, + struct vcap_client_keyfield_data *data) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + int size; + + if (!ri->admin->w32be) { + memcpy(&field->data, data, sizeof(field->data)); + return; + } + + size = keyfield_size_table[field->ctrl.type] / 2; + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + case VCAP_FIELD_U32: + memcpy(&field->data, data, sizeof(field->data)); + break; + case VCAP_FIELD_U48: + vcap_copy_to_w32be(field->data.u48.value, data->u48.value, size); + vcap_copy_to_w32be(field->data.u48.mask, data->u48.mask, size); + break; + case VCAP_FIELD_U56: + vcap_copy_to_w32be(field->data.u56.value, data->u56.value, size); + vcap_copy_to_w32be(field->data.u56.mask, data->u56.mask, size); + break; + case VCAP_FIELD_U64: + vcap_copy_to_w32be(field->data.u64.value, data->u64.value, size); + vcap_copy_to_w32be(field->data.u64.mask, data->u64.mask, size); + break; + case VCAP_FIELD_U72: + vcap_copy_to_w32be(field->data.u72.value, data->u72.value, size); + vcap_copy_to_w32be(field->data.u72.mask, data->u72.mask, size); + break; + case VCAP_FIELD_U112: + vcap_copy_to_w32be(field->data.u112.value, data->u112.value, size); + vcap_copy_to_w32be(field->data.u112.mask, data->u112.mask, size); + break; + case VCAP_FIELD_U128: + vcap_copy_to_w32be(field->data.u128.value, data->u128.value, size); + vcap_copy_to_w32be(field->data.u128.mask, data->u128.mask, size); + break; + } +} + +/* Check if the keyfield is already in the rule */ +static bool vcap_keyfield_unique(struct vcap_rule *rule, + enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_keyfield *ckf; + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + if (ckf->ctrl.key == key) + return false; + return true; +} + +/* Check if the keyfield is in the keyset */ +static bool vcap_keyfield_match_keyset(struct vcap_rule *rule, + enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_keyfield_set keyset = rule->keyset; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + + /* the field is accepted if the rule has no keyset yet */ + if (keyset == VCAP_KFS_NO_VALUE) + return true; + fields = vcap_keyfields(ri->vctrl, vt, keyset); + if (!fields) + return false; + /* if there is a width there is a way */ + return fields[key].width > 0; +} + +static int vcap_rule_add_key(struct vcap_rule *rule, + enum vcap_key_field key, + enum vcap_field_type ftype, + struct vcap_client_keyfield_data *data) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_client_keyfield *field; + + if (!vcap_keyfield_unique(rule, key)) { + pr_warn("%s:%d: keyfield %s is already in the rule\n", + __func__, __LINE__, + vcap_keyfield_name(ri->vctrl, key)); + return -EINVAL; + } + + if (!vcap_keyfield_match_keyset(rule, key)) { + pr_err("%s:%d: keyfield %s does not belong in the rule keyset\n", + __func__, __LINE__, + vcap_keyfield_name(ri->vctrl, key)); + return -EINVAL; + } + + field = kzalloc(sizeof(*field), GFP_KERNEL); + if (!field) + return -ENOMEM; + field->ctrl.key = key; + field->ctrl.type = ftype; + vcap_copy_from_client_keyfield(rule, field, data); + list_add_tail(&field->ctrl.list, &rule->keyfields); + return 0; +} + +static void vcap_rule_set_key_bitsize(struct vcap_u1_key *u1, enum vcap_bit val) +{ + switch (val) { + case VCAP_BIT_0: + u1->value = 0; + u1->mask = 1; + break; + case VCAP_BIT_1: + u1->value = 1; + u1->mask = 1; + break; + case VCAP_BIT_ANY: + u1->value = 0; + u1->mask = 0; + break; + } +} + +/* Add a bit key with value and mask to the rule */ +int vcap_rule_add_key_bit(struct vcap_rule *rule, enum vcap_key_field key, + enum vcap_bit val) +{ + struct vcap_client_keyfield_data data; + + vcap_rule_set_key_bitsize(&data.u1, val); + return vcap_rule_add_key(rule, key, VCAP_FIELD_BIT, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_bit); + +/* Add a 32 bit key field with value and mask to the rule */ +int vcap_rule_add_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 value, u32 mask) +{ + struct vcap_client_keyfield_data data; + + data.u32.value = value; + data.u32.mask = mask; + return vcap_rule_add_key(rule, key, VCAP_FIELD_U32, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_u32); + +/* Add a 48 bit key with value and mask to the rule */ +int vcap_rule_add_key_u48(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u48_key *fieldval) +{ + struct vcap_client_keyfield_data data; + + memcpy(&data.u48, fieldval, sizeof(data.u48)); + return vcap_rule_add_key(rule, key, VCAP_FIELD_U48, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_u48); + +/* Add a 72 bit key with value and mask to the rule */ +int vcap_rule_add_key_u72(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u72_key *fieldval) +{ + struct vcap_client_keyfield_data data; + + memcpy(&data.u72, fieldval, sizeof(data.u72)); + return vcap_rule_add_key(rule, key, VCAP_FIELD_U72, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_u72); + +/* Add a 128 bit key with value and mask to the rule */ +int vcap_rule_add_key_u128(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u128_key *fieldval) +{ + struct vcap_client_keyfield_data data; + + memcpy(&data.u128, fieldval, sizeof(data.u128)); + return vcap_rule_add_key(rule, key, VCAP_FIELD_U128, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_u128); + +int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 *value, u32 *mask) +{ + struct vcap_client_keyfield *ckf; + + ckf = vcap_find_keyfield(rule, key); + if (!ckf) + return -ENOENT; + + *value = ckf->data.u32.value; + *mask = ckf->data.u32.mask; + + return 0; +} +EXPORT_SYMBOL_GPL(vcap_rule_get_key_u32); + +/* Find a client action field in a rule */ +static struct vcap_client_actionfield * +vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) +{ + struct vcap_rule_internal *ri = (struct vcap_rule_internal *)rule; + struct vcap_client_actionfield *caf; + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) + if (caf->ctrl.action == act) + return caf; + return NULL; +} + +static void vcap_copy_from_client_actionfield(struct vcap_rule *rule, + struct vcap_client_actionfield *field, + struct vcap_client_actionfield_data *data) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + int size; + + if (!ri->admin->w32be) { + memcpy(&field->data, data, sizeof(field->data)); + return; + } + + size = actionfield_size_table[field->ctrl.type]; + switch (field->ctrl.type) { + case VCAP_FIELD_BIT: + case VCAP_FIELD_U32: + memcpy(&field->data, data, sizeof(field->data)); + break; + case VCAP_FIELD_U48: + vcap_copy_to_w32be(field->data.u48.value, data->u48.value, size); + break; + case VCAP_FIELD_U56: + vcap_copy_to_w32be(field->data.u56.value, data->u56.value, size); + break; + case VCAP_FIELD_U64: + vcap_copy_to_w32be(field->data.u64.value, data->u64.value, size); + break; + case VCAP_FIELD_U72: + vcap_copy_to_w32be(field->data.u72.value, data->u72.value, size); + break; + case VCAP_FIELD_U112: + vcap_copy_to_w32be(field->data.u112.value, data->u112.value, size); + break; + case VCAP_FIELD_U128: + vcap_copy_to_w32be(field->data.u128.value, data->u128.value, size); + break; + } +} + +/* Check if the actionfield is already in the rule */ +static bool vcap_actionfield_unique(struct vcap_rule *rule, + enum vcap_action_field act) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_actionfield *caf; + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) + if (caf->ctrl.action == act) + return false; + return true; +} + +/* Check if the actionfield is in the actionset */ +static bool vcap_actionfield_match_actionset(struct vcap_rule *rule, + enum vcap_action_field action) +{ + enum vcap_actionfield_set actionset = rule->actionset; + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + + /* the field is accepted if the rule has no actionset yet */ + if (actionset == VCAP_AFS_NO_VALUE) + return true; + fields = vcap_actionfields(ri->vctrl, vt, actionset); + if (!fields) + return false; + /* if there is a width there is a way */ + return fields[action].width > 0; +} + +static int vcap_rule_add_action(struct vcap_rule *rule, + enum vcap_action_field action, + enum vcap_field_type ftype, + struct vcap_client_actionfield_data *data) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_client_actionfield *field; + + if (!vcap_actionfield_unique(rule, action)) { + pr_warn("%s:%d: actionfield %s is already in the rule\n", + __func__, __LINE__, + vcap_actionfield_name(ri->vctrl, action)); + return -EINVAL; + } + + if (!vcap_actionfield_match_actionset(rule, action)) { + pr_err("%s:%d: actionfield %s does not belong in the rule actionset\n", + __func__, __LINE__, + vcap_actionfield_name(ri->vctrl, action)); + return -EINVAL; + } + + field = kzalloc(sizeof(*field), GFP_KERNEL); + if (!field) + return -ENOMEM; + field->ctrl.action = action; + field->ctrl.type = ftype; + vcap_copy_from_client_actionfield(rule, field, data); + list_add_tail(&field->ctrl.list, &rule->actionfields); + return 0; +} + +static void vcap_rule_set_action_bitsize(struct vcap_u1_action *u1, + enum vcap_bit val) +{ + switch (val) { + case VCAP_BIT_0: + u1->value = 0; + break; + case VCAP_BIT_1: + u1->value = 1; + break; + case VCAP_BIT_ANY: + u1->value = 0; + break; + } +} + +/* Add a bit action with value to the rule */ +int vcap_rule_add_action_bit(struct vcap_rule *rule, + enum vcap_action_field action, + enum vcap_bit val) +{ + struct vcap_client_actionfield_data data; + + vcap_rule_set_action_bitsize(&data.u1, val); + return vcap_rule_add_action(rule, action, VCAP_FIELD_BIT, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_action_bit); + +/* Add a 32 bit action field with value to the rule */ +int vcap_rule_add_action_u32(struct vcap_rule *rule, + enum vcap_action_field action, + u32 value) +{ + struct vcap_client_actionfield_data data; + + data.u32.value = value; + return vcap_rule_add_action(rule, action, VCAP_FIELD_U32, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_action_u32); + +static int vcap_read_counter(struct vcap_rule_internal *ri, + struct vcap_counter *ctr) +{ + struct vcap_admin *admin = ri->admin; + + ri->vctrl->ops->update(ri->ndev, admin, VCAP_CMD_READ, VCAP_SEL_COUNTER, + ri->addr); + ri->vctrl->ops->cache_read(ri->ndev, admin, VCAP_SEL_COUNTER, + ri->counter_id, 0); + ctr->value = admin->cache.counter; + ctr->sticky = admin->cache.sticky; + return 0; +} + +/* Copy to host byte order */ +void vcap_netbytes_copy(u8 *dst, u8 *src, int count) +{ + int idx; + + for (idx = 0; idx < count; ++idx, ++dst) + *dst = src[count - idx - 1]; +} +EXPORT_SYMBOL_GPL(vcap_netbytes_copy); + +/* Convert validation error code into tc extact error message */ +void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule) +{ + switch (vrule->exterr) { + case VCAP_ERR_NONE: + break; + case VCAP_ERR_NO_ADMIN: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Missing VCAP instance"); + break; + case VCAP_ERR_NO_NETDEV: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Missing network interface"); + break; + case VCAP_ERR_NO_KEYSET_MATCH: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "No keyset matched the filter keys"); + break; + case VCAP_ERR_NO_ACTIONSET_MATCH: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "No actionset matched the filter actions"); + break; + case VCAP_ERR_NO_PORT_KEYSET_MATCH: + NL_SET_ERR_MSG_MOD(fco->common.extack, + "No port keyset matched the filter keys"); + break; + } +} +EXPORT_SYMBOL_GPL(vcap_set_tc_exterr); + +/* Check if this port is already enabled for this VCAP instance */ +static bool vcap_is_enabled(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + list_for_each_entry(eport, &admin->enabled, list) + if (eport->cookie == cookie || eport->ndev == ndev) + return true; + + return false; +} + +/* Enable this port for this VCAP instance */ +static int vcap_enable(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + eport = kzalloc(sizeof(*eport), GFP_KERNEL); + if (!eport) + return -ENOMEM; + + eport->ndev = ndev; + eport->cookie = cookie; + list_add_tail(&eport->list, &admin->enabled); + + return 0; +} + +/* Disable this port for this VCAP instance */ +static int vcap_disable(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + list_for_each_entry(eport, &admin->enabled, list) { + if (eport->cookie == cookie && eport->ndev == ndev) { + list_del(&eport->list); + kfree(eport); + return 0; + } + } + + return -ENOENT; +} + +/* Find the VCAP instance that enabled the port using a specific filter */ +static struct vcap_admin *vcap_find_admin_by_cookie(struct vcap_control *vctrl, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + struct vcap_admin *admin; + + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(eport, &admin->enabled, list) + if (eport->cookie == cookie) + return admin; + + return NULL; +} + +/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, + int chain_id, unsigned long cookie, bool enable) +{ + struct vcap_admin *admin; + int err; + + err = vcap_api_check(vctrl); + if (err) + return err; + + if (!ndev) + return -ENODEV; + + if (chain_id) + admin = vcap_find_admin(vctrl, chain_id); + else + admin = vcap_find_admin_by_cookie(vctrl, cookie); + if (!admin) + return -ENOENT; + + /* first instance and first chain */ + if (admin->vinst || chain_id > admin->first_cid) + return -EFAULT; + + err = vctrl->ops->enable(ndev, admin, enable); + if (err) + return err; + + if (chain_id) { + if (vcap_is_enabled(admin, ndev, cookie)) + return -EADDRINUSE; + mutex_lock(&admin->lock); + vcap_enable(admin, ndev, cookie); + } else { + mutex_lock(&admin->lock); + vcap_disable(admin, ndev, cookie); + } + mutex_unlock(&admin->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(vcap_enable_lookups); + +/* Set a rule counter id (for certain vcaps only) */ +void vcap_rule_set_counter_id(struct vcap_rule *rule, u32 counter_id) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + + ri->counter_id = counter_id; +} +EXPORT_SYMBOL_GPL(vcap_rule_set_counter_id); + +/* Provide all rules via a callback interface */ +int vcap_rule_iter(struct vcap_control *vctrl, + int (*callback)(void *, struct vcap_rule *), void *arg) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + int ret; + + ret = vcap_api_check(vctrl); + if (ret) + return ret; + + /* Iterate all rules in each VCAP instance */ + list_for_each_entry(admin, &vctrl->list, list) { + list_for_each_entry(ri, &admin->rules, list) { + ret = callback(arg, &ri->data); + if (ret) + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(vcap_rule_iter); + +int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + int err; + + err = vcap_api_check(ri->vctrl); + if (err) + return err; + if (!ctr) { + pr_err("%s:%d: counter is missing\n", __func__, __LINE__); + return -EINVAL; + } + return vcap_write_counter(ri, ctr); +} +EXPORT_SYMBOL_GPL(vcap_rule_set_counter); + +int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + int err; + + err = vcap_api_check(ri->vctrl); + if (err) + return err; + if (!ctr) { + pr_err("%s:%d: counter is missing\n", __func__, __LINE__); + return -EINVAL; + } + return vcap_read_counter(ri, ctr); +} +EXPORT_SYMBOL_GPL(vcap_rule_get_counter); + +static int vcap_rule_mod_key(struct vcap_rule *rule, + enum vcap_key_field key, + enum vcap_field_type ftype, + struct vcap_client_keyfield_data *data) +{ + struct vcap_client_keyfield *field; + + field = vcap_find_keyfield(rule, key); + if (!field) + return vcap_rule_add_key(rule, key, ftype, data); + vcap_copy_from_client_keyfield(rule, field, data); + return 0; +} + +/* Modify a 32 bit key field with value and mask in the rule */ +int vcap_rule_mod_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 value, u32 mask) +{ + struct vcap_client_keyfield_data data; + + data.u32.value = value; + data.u32.mask = mask; + return vcap_rule_mod_key(rule, key, VCAP_FIELD_U32, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_mod_key_u32); + +static int vcap_rule_mod_action(struct vcap_rule *rule, + enum vcap_action_field action, + enum vcap_field_type ftype, + struct vcap_client_actionfield_data *data) +{ + struct vcap_client_actionfield *field; + + field = vcap_find_actionfield(rule, action); + if (!field) + return vcap_rule_add_action(rule, action, ftype, data); + vcap_copy_from_client_actionfield(rule, field, data); + return 0; +} + +/* Modify a 32 bit action field with value in the rule */ +int vcap_rule_mod_action_u32(struct vcap_rule *rule, + enum vcap_action_field action, + u32 value) +{ + struct vcap_client_actionfield_data data; + + data.u32.value = value; + return vcap_rule_mod_action(rule, action, VCAP_FIELD_U32, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_mod_action_u32); + +/* Drop keys in a keylist and any keys that are not supported by the keyset */ +int vcap_filter_rule_keys(struct vcap_rule *rule, + enum vcap_key_field keylist[], int length, + bool drop_unsupported) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_client_keyfield *ckf, *next_ckf; + const struct vcap_field *fields; + enum vcap_key_field key; + int err = 0; + int idx; + + if (length > 0) { + err = -EEXIST; + list_for_each_entry_safe(ckf, next_ckf, + &ri->data.keyfields, ctrl.list) { + key = ckf->ctrl.key; + for (idx = 0; idx < length; ++idx) + if (key == keylist[idx]) { + list_del(&ckf->ctrl.list); + kfree(ckf); + idx++; + err = 0; + } + } + } + if (drop_unsupported) { + err = -EEXIST; + fields = vcap_keyfields(ri->vctrl, ri->admin->vtype, + rule->keyset); + if (!fields) + return err; + list_for_each_entry_safe(ckf, next_ckf, + &ri->data.keyfields, ctrl.list) { + key = ckf->ctrl.key; + if (fields[key].width == 0) { + list_del(&ckf->ctrl.list); + kfree(ckf); + err = 0; + } + } + } + return err; +} +EXPORT_SYMBOL_GPL(vcap_filter_rule_keys); + +/* Make a full copy of an existing rule with a new rule id */ +struct vcap_rule *vcap_copy_rule(struct vcap_rule *erule) +{ + struct vcap_rule_internal *ri = to_intrule(erule); + struct vcap_client_actionfield *caf; + struct vcap_client_keyfield *ckf; + struct vcap_rule *rule; + int err; + + err = vcap_api_check(ri->vctrl); + if (err) + return ERR_PTR(err); + + rule = vcap_alloc_rule(ri->vctrl, ri->ndev, ri->data.vcap_chain_id, + ri->data.user, ri->data.priority, 0); + if (IS_ERR(rule)) + return rule; + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) { + /* Add a key duplicate in the new rule */ + err = vcap_rule_add_key(rule, + ckf->ctrl.key, + ckf->ctrl.type, + &ckf->data); + if (err) + goto err; + } + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) { + /* Add a action duplicate in the new rule */ + err = vcap_rule_add_action(rule, + caf->ctrl.action, + caf->ctrl.type, + &caf->data); + if (err) + goto err; + } + return rule; +err: + vcap_free_rule(rule); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(vcap_copy_rule); + +#ifdef CONFIG_VCAP_KUNIT_TEST +#include "vcap_api_kunit.c" +#endif diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h new file mode 100644 index 000000000000..689c7270f2a8 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -0,0 +1,280 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +#ifndef __VCAP_API__ +#define __VCAP_API__ + +#include <linux/types.h> +#include <linux/list.h> +#include <linux/netdevice.h> + +/* Use the generated API model */ +#include "vcap_ag_api.h" + +#define VCAP_CID_LOOKUP_SIZE 100000 /* Chains in a lookup */ +#define VCAP_CID_INGRESS_L0 1000000 /* Ingress Stage 1 Lookup 0 */ +#define VCAP_CID_INGRESS_L1 1100000 /* Ingress Stage 1 Lookup 1 */ +#define VCAP_CID_INGRESS_L2 1200000 /* Ingress Stage 1 Lookup 2 */ +#define VCAP_CID_INGRESS_L3 1300000 /* Ingress Stage 1 Lookup 3 */ +#define VCAP_CID_INGRESS_L4 1400000 /* Ingress Stage 1 Lookup 4 */ +#define VCAP_CID_INGRESS_L5 1500000 /* Ingress Stage 1 Lookup 5 */ + +#define VCAP_CID_PREROUTING_IPV6 3000000 /* Prerouting Stage */ +#define VCAP_CID_PREROUTING 6000000 /* Prerouting Stage */ + +#define VCAP_CID_INGRESS_STAGE2_L0 8000000 /* Ingress Stage 2 Lookup 0 */ +#define VCAP_CID_INGRESS_STAGE2_L1 8100000 /* Ingress Stage 2 Lookup 1 */ +#define VCAP_CID_INGRESS_STAGE2_L2 8200000 /* Ingress Stage 2 Lookup 2 */ +#define VCAP_CID_INGRESS_STAGE2_L3 8300000 /* Ingress Stage 2 Lookup 3 */ + +#define VCAP_CID_EGRESS_L0 10000000 /* Egress Lookup 0 */ +#define VCAP_CID_EGRESS_L1 10100000 /* Egress Lookup 1 */ + +#define VCAP_CID_EGRESS_STAGE2_L0 20000000 /* Egress Stage 2 Lookup 0 */ +#define VCAP_CID_EGRESS_STAGE2_L1 20100000 /* Egress Stage 2 Lookup 1 */ + +/* Known users of the VCAP API */ +enum vcap_user { + VCAP_USER_PTP, + VCAP_USER_MRP, + VCAP_USER_CFM, + VCAP_USER_VLAN, + VCAP_USER_QOS, + VCAP_USER_VCAP_UTIL, + VCAP_USER_TC, + VCAP_USER_TC_EXTRA, + + /* add new users above here */ + + /* used to define VCAP_USER_MAX below */ + __VCAP_USER_AFTER_LAST, + VCAP_USER_MAX = __VCAP_USER_AFTER_LAST - 1, +}; + +/* VCAP information used for displaying data */ +struct vcap_statistics { + char *name; + int count; + const char * const *keyfield_set_names; + const char * const *actionfield_set_names; + const char * const *keyfield_names; + const char * const *actionfield_names; +}; + +/* VCAP key/action field type, position and width */ +struct vcap_field { + u16 type; + u16 width; + u16 offset; +}; + +/* VCAP keyset or actionset type and width */ +struct vcap_set { + u8 type_id; + u8 sw_per_item; + u8 sw_cnt; +}; + +/* VCAP typegroup position and bitvalue */ +struct vcap_typegroup { + u16 offset; + u16 width; + u16 value; +}; + +/* VCAP model data */ +struct vcap_info { + char *name; /* user-friendly name */ + u16 rows; /* number of row in instance */ + u16 sw_count; /* maximum subwords used per rule */ + u16 sw_width; /* bits per subword in a keyset */ + u16 sticky_width; /* sticky bits per rule */ + u16 act_width; /* bits per subword in an actionset */ + u16 default_cnt; /* number of default rules */ + u16 require_cnt_dis; /* not used */ + u16 version; /* vcap rtl version */ + const struct vcap_set *keyfield_set; /* keysets */ + int keyfield_set_size; /* number of keysets */ + const struct vcap_set *actionfield_set; /* actionsets */ + int actionfield_set_size; /* number of actionsets */ + /* map of keys per keyset */ + const struct vcap_field **keyfield_set_map; + /* number of entries in the above map */ + int *keyfield_set_map_size; + /* map of actions per actionset */ + const struct vcap_field **actionfield_set_map; + /* number of entries in the above map */ + int *actionfield_set_map_size; + /* map of keyset typegroups per subword size */ + const struct vcap_typegroup **keyfield_set_typegroups; + /* map of actionset typegroups per subword size */ + const struct vcap_typegroup **actionfield_set_typegroups; +}; + +enum vcap_field_type { + VCAP_FIELD_BIT, + VCAP_FIELD_U32, + VCAP_FIELD_U48, + VCAP_FIELD_U56, + VCAP_FIELD_U64, + VCAP_FIELD_U72, + VCAP_FIELD_U112, + VCAP_FIELD_U128, +}; + +/* VCAP rule data towards the VCAP cache */ +struct vcap_cache_data { + u32 *keystream; + u32 *maskstream; + u32 *actionstream; + u32 counter; + bool sticky; +}; + +/* Selects which part of the rule must be updated */ +enum vcap_selection { + VCAP_SEL_ENTRY = 0x01, + VCAP_SEL_ACTION = 0x02, + VCAP_SEL_COUNTER = 0x04, + VCAP_SEL_ALL = 0xff, +}; + +/* Commands towards the VCAP cache */ +enum vcap_command { + VCAP_CMD_WRITE = 0, + VCAP_CMD_READ = 1, + VCAP_CMD_MOVE_DOWN = 2, + VCAP_CMD_MOVE_UP = 3, + VCAP_CMD_INITIALIZE = 4, +}; + +enum vcap_rule_error { + VCAP_ERR_NONE = 0, /* No known error */ + VCAP_ERR_NO_ADMIN, /* No admin instance */ + VCAP_ERR_NO_NETDEV, /* No netdev instance */ + VCAP_ERR_NO_KEYSET_MATCH, /* No keyset matched the rule keys */ + VCAP_ERR_NO_ACTIONSET_MATCH, /* No actionset matched the rule actions */ + VCAP_ERR_NO_PORT_KEYSET_MATCH, /* No port keyset matched the rule keys */ +}; + +/* Administration of each VCAP instance */ +struct vcap_admin { + struct list_head list; /* for insertion in vcap_control */ + struct list_head rules; /* list of rules */ + struct list_head enabled; /* list of enabled ports */ + struct mutex lock; /* control access to rules */ + enum vcap_type vtype; /* type of vcap */ + int vinst; /* instance number within the same type */ + int first_cid; /* first chain id in this vcap */ + int last_cid; /* last chain id in this vcap */ + int tgt_inst; /* hardware instance number */ + int lookups; /* number of lookups in this vcap type */ + int lookups_per_instance; /* number of lookups in this instance */ + int last_valid_addr; /* top of address range to be used */ + int first_valid_addr; /* bottom of address range to be used */ + int last_used_addr; /* address of lowest added rule */ + bool w32be; /* vcap uses "32bit-word big-endian" encoding */ + struct vcap_cache_data cache; /* encoded rule data */ +}; + +/* Client supplied VCAP rule data */ +struct vcap_rule { + int vcap_chain_id; /* chain used for this rule */ + enum vcap_user user; /* rule owner */ + u16 priority; + u32 id; /* vcap rule id, must be unique, 0 will auto-generate a value */ + u64 cookie; /* used by the client to identify the rule */ + struct list_head keyfields; /* list of vcap_client_keyfield */ + struct list_head actionfields; /* list of vcap_client_actionfield */ + enum vcap_keyfield_set keyset; /* keyset used: may be derived from fields */ + enum vcap_actionfield_set actionset; /* actionset used: may be derived from fields */ + enum vcap_rule_error exterr; /* extended error - used by TC */ + u64 client; /* space for client defined data */ +}; + +/* List of keysets */ +struct vcap_keyset_list { + int max; /* size of the keyset list */ + int cnt; /* count of keysets actually in the list */ + enum vcap_keyfield_set *keysets; /* the list of keysets */ +}; + +/* Client output printf-like function with destination */ +struct vcap_output_print { + __printf(2, 3) + void (*prf)(void *out, const char *fmt, ...); + void *dst; +}; + +/* Client supplied VCAP callback operations */ +struct vcap_operations { + /* validate port keyset operation */ + enum vcap_keyfield_set (*validate_keyset) + (struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule, + struct vcap_keyset_list *kslist, + u16 l3_proto); + /* add default rule fields for the selected keyset operations */ + void (*add_default_fields) + (struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule); + /* cache operations */ + void (*cache_erase) + (struct vcap_admin *admin); + void (*cache_write) + (struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 idx, u32 count); + void (*cache_read) + (struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 idx, + u32 count); + /* block operations */ + void (*init) + (struct net_device *ndev, + struct vcap_admin *admin, + u32 addr, + u32 count); + void (*update) + (struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_command cmd, + enum vcap_selection sel, + u32 addr); + void (*move) + (struct net_device *ndev, + struct vcap_admin *admin, + u32 addr, + int offset, + int count); + /* informational */ + int (*port_info) + (struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out); + /* enable/disable the lookups in a vcap instance */ + int (*enable) + (struct net_device *ndev, + struct vcap_admin *admin, + bool enable); +}; + +/* VCAP API Client control interface */ +struct vcap_control { + struct vcap_operations *ops; /* client supplied operations */ + const struct vcap_info *vcaps; /* client supplied vcap models */ + const struct vcap_statistics *stats; /* client supplied vcap stats */ + struct list_head list; /* list of vcap instances */ +}; + +/* Set client control interface on the API */ +int vcap_api_set_client(struct vcap_control *vctrl); + +#endif /* __VCAP_API__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h new file mode 100644 index 000000000000..0319866f9c94 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +#ifndef __VCAP_API_CLIENT__ +#define __VCAP_API_CLIENT__ + +#include <linux/types.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <net/flow_offload.h> + +#include "vcap_api.h" + +/* Client supplied VCAP rule key control part */ +struct vcap_client_keyfield_ctrl { + struct list_head list; /* For insertion into a rule */ + enum vcap_key_field key; + enum vcap_field_type type; +}; + +struct vcap_u1_key { + u8 value; + u8 mask; +}; + +struct vcap_u32_key { + u32 value; + u32 mask; +}; + +struct vcap_u48_key { + u8 value[6]; + u8 mask[6]; +}; + +struct vcap_u56_key { + u8 value[7]; + u8 mask[7]; +}; + +struct vcap_u64_key { + u8 value[8]; + u8 mask[8]; +}; + +struct vcap_u72_key { + u8 value[9]; + u8 mask[9]; +}; + +struct vcap_u112_key { + u8 value[14]; + u8 mask[14]; +}; + +struct vcap_u128_key { + u8 value[16]; + u8 mask[16]; +}; + +/* Client supplied VCAP rule field data */ +struct vcap_client_keyfield_data { + union { + struct vcap_u1_key u1; + struct vcap_u32_key u32; + struct vcap_u48_key u48; + struct vcap_u56_key u56; + struct vcap_u64_key u64; + struct vcap_u72_key u72; + struct vcap_u112_key u112; + struct vcap_u128_key u128; + }; +}; + +/* Client supplied VCAP rule key (value, mask) */ +struct vcap_client_keyfield { + struct vcap_client_keyfield_ctrl ctrl; + struct vcap_client_keyfield_data data; +}; + +/* Client supplied VCAP rule action control part */ +struct vcap_client_actionfield_ctrl { + struct list_head list; /* For insertion into a rule */ + enum vcap_action_field action; + enum vcap_field_type type; +}; + +struct vcap_u1_action { + u8 value; +}; + +struct vcap_u32_action { + u32 value; +}; + +struct vcap_u48_action { + u8 value[6]; +}; + +struct vcap_u56_action { + u8 value[7]; +}; + +struct vcap_u64_action { + u8 value[8]; +}; + +struct vcap_u72_action { + u8 value[9]; +}; + +struct vcap_u112_action { + u8 value[14]; +}; + +struct vcap_u128_action { + u8 value[16]; +}; + +struct vcap_client_actionfield_data { + union { + struct vcap_u1_action u1; + struct vcap_u32_action u32; + struct vcap_u48_action u48; + struct vcap_u56_action u56; + struct vcap_u64_action u64; + struct vcap_u72_action u72; + struct vcap_u112_action u112; + struct vcap_u128_action u128; + }; +}; + +struct vcap_client_actionfield { + struct vcap_client_actionfield_ctrl ctrl; + struct vcap_client_actionfield_data data; +}; + +enum vcap_bit { + VCAP_BIT_ANY, + VCAP_BIT_0, + VCAP_BIT_1 +}; + +struct vcap_counter { + u32 value; + bool sticky; +}; + +/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, + int chain_id, unsigned long cookie, bool enable); + +/* VCAP rule operations */ +/* Allocate a rule and fill in the basic information */ +struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, + struct net_device *ndev, + int vcap_chain_id, + enum vcap_user user, + u16 priority, + u32 id); +/* Free mem of a rule owned by client */ +void vcap_free_rule(struct vcap_rule *rule); +/* Validate a rule before adding it to the VCAP */ +int vcap_val_rule(struct vcap_rule *rule, u16 l3_proto); +/* Add rule to a VCAP instance */ +int vcap_add_rule(struct vcap_rule *rule); +/* Delete rule in a VCAP instance */ +int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id); +/* Make a full copy of an existing rule with a new rule id */ +struct vcap_rule *vcap_copy_rule(struct vcap_rule *rule); +/* Get rule from a VCAP instance */ +struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id); +/* Update existing rule */ +int vcap_mod_rule(struct vcap_rule *rule); + +/* Update the keyset for the rule */ +int vcap_set_rule_set_keyset(struct vcap_rule *rule, + enum vcap_keyfield_set keyset); +/* Update the actionset for the rule */ +int vcap_set_rule_set_actionset(struct vcap_rule *rule, + enum vcap_actionfield_set actionset); +/* Set a rule counter id (for certain VCAPs only) */ +void vcap_rule_set_counter_id(struct vcap_rule *rule, u32 counter_id); + +/* VCAP rule field operations */ +int vcap_rule_add_key_bit(struct vcap_rule *rule, enum vcap_key_field key, + enum vcap_bit val); +int vcap_rule_add_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 value, u32 mask); +int vcap_rule_add_key_u48(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u48_key *fieldval); +int vcap_rule_add_key_u72(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u72_key *fieldval); +int vcap_rule_add_key_u128(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u128_key *fieldval); +int vcap_rule_add_action_bit(struct vcap_rule *rule, + enum vcap_action_field action, enum vcap_bit val); +int vcap_rule_add_action_u32(struct vcap_rule *rule, + enum vcap_action_field action, u32 value); + +/* VCAP rule counter operations */ +int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr); +int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr); + +/* VCAP lookup operations */ +/* Convert a chain id to a VCAP lookup index */ +int vcap_chain_id_to_lookup(struct vcap_admin *admin, int cur_cid); +/* Lookup a vcap instance using chain id */ +struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid); +/* Find information on a key field in a rule */ +const struct vcap_field *vcap_lookup_keyfield(struct vcap_rule *rule, + enum vcap_key_field key); +/* Find a rule id with a provided cookie */ +int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie); +/* Is the next chain id in the following lookup, possible in another VCAP */ +bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid); +/* Provide all rules via a callback interface */ +int vcap_rule_iter(struct vcap_control *vctrl, + int (*callback)(void *, struct vcap_rule *), void *arg); +/* Match a list of keys against the keysets available in a vcap type */ +bool vcap_rule_find_keysets(struct vcap_rule *rule, + struct vcap_keyset_list *matches); +/* Return the keyset information for the keyset */ +const struct vcap_set *vcap_keyfieldset(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_keyfield_set keyset); +/* Copy to host byte order */ +void vcap_netbytes_copy(u8 *dst, u8 *src, int count); + +/* Convert validation error code into tc extact error message */ +void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule); + +/* Cleanup a VCAP instance */ +int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin); + +/* Add a keyset to a keyset list */ +bool vcap_keyset_list_add(struct vcap_keyset_list *keysetlist, + enum vcap_keyfield_set keyset); +/* Drop keys in a keylist and any keys that are not supported by the keyset */ +int vcap_filter_rule_keys(struct vcap_rule *rule, + enum vcap_key_field keylist[], int length, + bool drop_unsupported); + +/* map keyset id to a string with the keyset name */ +const char *vcap_keyset_name(struct vcap_control *vctrl, + enum vcap_keyfield_set keyset); +/* map key field id to a string with the key name */ +const char *vcap_keyfield_name(struct vcap_control *vctrl, + enum vcap_key_field key); + +/* Modify a 32 bit key field with value and mask in the rule */ +int vcap_rule_mod_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 value, u32 mask); +/* Modify a 32 bit action field with value in the rule */ +int vcap_rule_mod_action_u32(struct vcap_rule *rule, + enum vcap_action_field action, + u32 value); + +/* Get a 32 bit key field value and mask from the rule */ +int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, + u32 *value, u32 *mask); + +#endif /* __VCAP_API_CLIENT__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c new file mode 100644 index 000000000000..895bfff550d2 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c @@ -0,0 +1,431 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP API debug file system support + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + * + */ + +#include "vcap_api_private.h" +#include "vcap_api_debugfs.h" + +struct vcap_admin_debugfs_info { + struct vcap_control *vctrl; + struct vcap_admin *admin; +}; + +struct vcap_port_debugfs_info { + struct vcap_control *vctrl; + struct net_device *ndev; +}; + +/* Dump the keyfields value and mask values */ +static void vcap_debugfs_show_rule_keyfield(struct vcap_control *vctrl, + struct vcap_output_print *out, + enum vcap_key_field key, + const struct vcap_field *keyfield, + struct vcap_client_keyfield_data *data) +{ + bool hex = false; + u8 *value, *mask; + int idx, bytes; + + out->prf(out->dst, " %s: W%d: ", vcap_keyfield_name(vctrl, key), + keyfield[key].width); + + switch (keyfield[key].type) { + case VCAP_FIELD_BIT: + out->prf(out->dst, "%d/%d", data->u1.value, data->u1.mask); + break; + case VCAP_FIELD_U32: + value = (u8 *)(&data->u32.value); + mask = (u8 *)(&data->u32.mask); + + if (key == VCAP_KF_L3_IP4_SIP || key == VCAP_KF_L3_IP4_DIP) { + out->prf(out->dst, "%pI4h/%pI4h", &data->u32.value, + &data->u32.mask); + } else if (key == VCAP_KF_ETYPE || + key == VCAP_KF_IF_IGR_PORT_MASK) { + hex = true; + } else { + u32 fmsk = (1 << keyfield[key].width) - 1; + + out->prf(out->dst, "%u/%u", data->u32.value & fmsk, + data->u32.mask & fmsk); + } + break; + case VCAP_FIELD_U48: + value = data->u48.value; + mask = data->u48.mask; + if (key == VCAP_KF_L2_SMAC || key == VCAP_KF_L2_DMAC) + out->prf(out->dst, "%pMR/%pMR", data->u48.value, + data->u48.mask); + else + hex = true; + break; + case VCAP_FIELD_U56: + value = data->u56.value; + mask = data->u56.mask; + hex = true; + break; + case VCAP_FIELD_U64: + value = data->u64.value; + mask = data->u64.mask; + hex = true; + break; + case VCAP_FIELD_U72: + value = data->u72.value; + mask = data->u72.mask; + hex = true; + break; + case VCAP_FIELD_U112: + value = data->u112.value; + mask = data->u112.mask; + hex = true; + break; + case VCAP_FIELD_U128: + if (key == VCAP_KF_L3_IP6_SIP || key == VCAP_KF_L3_IP6_DIP) { + u8 nvalue[16], nmask[16]; + + vcap_netbytes_copy(nvalue, data->u128.value, + sizeof(nvalue)); + vcap_netbytes_copy(nmask, data->u128.mask, + sizeof(nmask)); + out->prf(out->dst, "%pI6/%pI6", nvalue, nmask); + } else { + hex = true; + } + break; + } + if (hex) { + bytes = DIV_ROUND_UP(keyfield[key].width, BITS_PER_BYTE); + out->prf(out->dst, "0x"); + for (idx = 0; idx < bytes; ++idx) + out->prf(out->dst, "%02x", value[bytes - idx - 1]); + out->prf(out->dst, "/0x"); + for (idx = 0; idx < bytes; ++idx) + out->prf(out->dst, "%02x", mask[bytes - idx - 1]); + } + out->prf(out->dst, "\n"); +} + +static void +vcap_debugfs_show_rule_actionfield(struct vcap_control *vctrl, + struct vcap_output_print *out, + enum vcap_action_field action, + const struct vcap_field *actionfield, + u8 *value) +{ + bool hex = false; + int idx, bytes; + u32 fmsk, val; + + out->prf(out->dst, " %s: W%d: ", + vcap_actionfield_name(vctrl, action), + actionfield[action].width); + + switch (actionfield[action].type) { + case VCAP_FIELD_BIT: + out->prf(out->dst, "%d", value[0]); + break; + case VCAP_FIELD_U32: + fmsk = (1 << actionfield[action].width) - 1; + val = *(u32 *)value; + out->prf(out->dst, "%u", val & fmsk); + break; + case VCAP_FIELD_U48: + case VCAP_FIELD_U56: + case VCAP_FIELD_U64: + case VCAP_FIELD_U72: + case VCAP_FIELD_U112: + case VCAP_FIELD_U128: + hex = true; + break; + } + if (hex) { + bytes = DIV_ROUND_UP(actionfield[action].width, BITS_PER_BYTE); + out->prf(out->dst, "0x"); + for (idx = 0; idx < bytes; ++idx) + out->prf(out->dst, "%02x", value[bytes - idx - 1]); + } + out->prf(out->dst, "\n"); +} + +static int vcap_debugfs_show_rule_keyset(struct vcap_rule_internal *ri, + struct vcap_output_print *out) +{ + struct vcap_control *vctrl = ri->vctrl; + struct vcap_admin *admin = ri->admin; + enum vcap_keyfield_set keysets[10]; + const struct vcap_field *keyfield; + enum vcap_type vt = admin->vtype; + struct vcap_client_keyfield *ckf; + struct vcap_keyset_list matches; + u32 *maskstream; + u32 *keystream; + int res; + + keystream = admin->cache.keystream; + maskstream = admin->cache.maskstream; + matches.keysets = keysets; + matches.cnt = 0; + matches.max = ARRAY_SIZE(keysets); + res = vcap_find_keystream_keysets(vctrl, vt, keystream, maskstream, + false, 0, &matches); + if (res < 0) { + pr_err("%s:%d: could not find valid keysets: %d\n", + __func__, __LINE__, res); + return -EINVAL; + } + out->prf(out->dst, " keysets:"); + for (int idx = 0; idx < matches.cnt; ++idx) + out->prf(out->dst, " %s", + vcap_keyset_name(vctrl, matches.keysets[idx])); + out->prf(out->dst, "\n"); + out->prf(out->dst, " keyset_sw: %d\n", ri->keyset_sw); + out->prf(out->dst, " keyset_sw_regs: %d\n", ri->keyset_sw_regs); + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) { + keyfield = vcap_keyfields(vctrl, admin->vtype, ri->data.keyset); + vcap_debugfs_show_rule_keyfield(vctrl, out, ckf->ctrl.key, + keyfield, &ckf->data); + } + + return 0; +} + +static int vcap_debugfs_show_rule_actionset(struct vcap_rule_internal *ri, + struct vcap_output_print *out) +{ + struct vcap_control *vctrl = ri->vctrl; + struct vcap_admin *admin = ri->admin; + const struct vcap_field *actionfield; + struct vcap_client_actionfield *caf; + + out->prf(out->dst, " actionset: %s\n", + vcap_actionset_name(vctrl, ri->data.actionset)); + out->prf(out->dst, " actionset_sw: %d\n", ri->actionset_sw); + out->prf(out->dst, " actionset_sw_regs: %d\n", ri->actionset_sw_regs); + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) { + actionfield = vcap_actionfields(vctrl, admin->vtype, + ri->data.actionset); + vcap_debugfs_show_rule_actionfield(vctrl, out, caf->ctrl.action, + actionfield, + &caf->data.u1.value); + } + + return 0; +} + +static void vcap_show_admin_rule(struct vcap_control *vctrl, + struct vcap_admin *admin, + struct vcap_output_print *out, + struct vcap_rule_internal *ri) +{ + ri->counter.value = admin->cache.counter; + ri->counter.sticky = admin->cache.sticky; + out->prf(out->dst, + "rule: %u, addr: [%d,%d], X%d, ctr[%d]: %d, hit: %d\n", + ri->data.id, ri->addr, ri->addr + ri->size - 1, ri->size, + ri->counter_id, ri->counter.value, ri->counter.sticky); + out->prf(out->dst, " chain_id: %d\n", ri->data.vcap_chain_id); + out->prf(out->dst, " user: %d\n", ri->data.user); + out->prf(out->dst, " priority: %d\n", ri->data.priority); + vcap_debugfs_show_rule_keyset(ri, out); + vcap_debugfs_show_rule_actionset(ri, out); +} + +static void vcap_show_admin_info(struct vcap_control *vctrl, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + const struct vcap_info *vcap = &vctrl->vcaps[admin->vtype]; + + out->prf(out->dst, "name: %s\n", vcap->name); + out->prf(out->dst, "rows: %d\n", vcap->rows); + out->prf(out->dst, "sw_count: %d\n", vcap->sw_count); + out->prf(out->dst, "sw_width: %d\n", vcap->sw_width); + out->prf(out->dst, "sticky_width: %d\n", vcap->sticky_width); + out->prf(out->dst, "act_width: %d\n", vcap->act_width); + out->prf(out->dst, "default_cnt: %d\n", vcap->default_cnt); + out->prf(out->dst, "require_cnt_dis: %d\n", vcap->require_cnt_dis); + out->prf(out->dst, "version: %d\n", vcap->version); + out->prf(out->dst, "vtype: %d\n", admin->vtype); + out->prf(out->dst, "vinst: %d\n", admin->vinst); + out->prf(out->dst, "first_cid: %d\n", admin->first_cid); + out->prf(out->dst, "last_cid: %d\n", admin->last_cid); + out->prf(out->dst, "lookups: %d\n", admin->lookups); + out->prf(out->dst, "first_valid_addr: %d\n", admin->first_valid_addr); + out->prf(out->dst, "last_valid_addr: %d\n", admin->last_valid_addr); + out->prf(out->dst, "last_used_addr: %d\n", admin->last_used_addr); +} + +static int vcap_show_admin(struct vcap_control *vctrl, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + struct vcap_rule_internal *elem; + struct vcap_rule *vrule; + int ret = 0; + + vcap_show_admin_info(vctrl, admin, out); + list_for_each_entry(elem, &admin->rules, list) { + vrule = vcap_get_rule(vctrl, elem->data.id); + if (IS_ERR_OR_NULL(vrule)) { + ret = PTR_ERR(vrule); + break; + } + + out->prf(out->dst, "\n"); + vcap_show_admin_rule(vctrl, admin, out, to_intrule(vrule)); + vcap_free_rule(vrule); + } + return ret; +} + +static int vcap_show_admin_raw(struct vcap_control *vctrl, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + enum vcap_keyfield_set keysets[10]; + enum vcap_type vt = admin->vtype; + struct vcap_keyset_list kslist; + struct vcap_rule_internal *ri; + const struct vcap_set *info; + int addr, idx; + int ret; + + if (list_empty(&admin->rules)) + return 0; + + ret = vcap_api_check(vctrl); + if (ret) + return ret; + + ri = list_first_entry(&admin->rules, struct vcap_rule_internal, list); + + /* Go from higher to lower addresses searching for a keyset */ + kslist.keysets = keysets; + kslist.max = ARRAY_SIZE(keysets); + for (addr = admin->last_valid_addr; addr >= admin->first_valid_addr; + --addr) { + kslist.cnt = 0; + ret = vcap_addr_keysets(vctrl, ri->ndev, admin, addr, &kslist); + if (ret < 0) + continue; + info = vcap_keyfieldset(vctrl, vt, kslist.keysets[0]); + if (!info) + continue; + if (addr % info->sw_per_item) { + pr_info("addr: %d X%d error rule, keyset: %s\n", + addr, + info->sw_per_item, + vcap_keyset_name(vctrl, kslist.keysets[0])); + } else { + out->prf(out->dst, " addr: %d, X%d rule, keysets:", + addr, + info->sw_per_item); + for (idx = 0; idx < kslist.cnt; ++idx) + out->prf(out->dst, " %s", + vcap_keyset_name(vctrl, + kslist.keysets[idx])); + out->prf(out->dst, "\n"); + } + } + return 0; +} + +/* Show the port configuration and status */ +static int vcap_port_debugfs_show(struct seq_file *m, void *unused) +{ + struct vcap_port_debugfs_info *info = m->private; + struct vcap_admin *admin; + struct vcap_output_print out = { + .prf = (void *)seq_printf, + .dst = m, + }; + + list_for_each_entry(admin, &info->vctrl->list, list) { + if (admin->vinst) + continue; + info->vctrl->ops->port_info(info->ndev, admin, &out); + } + return 0; +} +DEFINE_SHOW_ATTRIBUTE(vcap_port_debugfs); + +void vcap_port_debugfs(struct device *dev, struct dentry *parent, + struct vcap_control *vctrl, + struct net_device *ndev) +{ + struct vcap_port_debugfs_info *info; + + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); + if (!info) + return; + + info->vctrl = vctrl; + info->ndev = ndev; + debugfs_create_file(netdev_name(ndev), 0444, parent, info, + &vcap_port_debugfs_fops); +} +EXPORT_SYMBOL_GPL(vcap_port_debugfs); + +/* Show the full VCAP instance data (rules with all fields) */ +static int vcap_debugfs_show(struct seq_file *m, void *unused) +{ + struct vcap_admin_debugfs_info *info = m->private; + struct vcap_output_print out = { + .prf = (void *)seq_printf, + .dst = m, + }; + + return vcap_show_admin(info->vctrl, info->admin, &out); +} +DEFINE_SHOW_ATTRIBUTE(vcap_debugfs); + +/* Show the raw VCAP instance data (rules with address info) */ +static int vcap_raw_debugfs_show(struct seq_file *m, void *unused) +{ + struct vcap_admin_debugfs_info *info = m->private; + struct vcap_output_print out = { + .prf = (void *)seq_printf, + .dst = m, + }; + + return vcap_show_admin_raw(info->vctrl, info->admin, &out); +} +DEFINE_SHOW_ATTRIBUTE(vcap_raw_debugfs); + +struct dentry *vcap_debugfs(struct device *dev, struct dentry *parent, + struct vcap_control *vctrl) +{ + struct vcap_admin_debugfs_info *info; + struct vcap_admin *admin; + struct dentry *dir; + char name[50]; + + dir = debugfs_create_dir("vcaps", parent); + if (PTR_ERR_OR_ZERO(dir)) + return NULL; + list_for_each_entry(admin, &vctrl->list, list) { + sprintf(name, "raw_%s_%d", vctrl->vcaps[admin->vtype].name, + admin->vinst); + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); + if (!info) + return NULL; + info->vctrl = vctrl; + info->admin = admin; + debugfs_create_file(name, 0444, dir, info, + &vcap_raw_debugfs_fops); + sprintf(name, "%s_%d", vctrl->vcaps[admin->vtype].name, + admin->vinst); + debugfs_create_file(name, 0444, dir, info, &vcap_debugfs_fops); + } + return dir; +} +EXPORT_SYMBOL_GPL(vcap_debugfs); + +#ifdef CONFIG_VCAP_KUNIT_TEST +#include "vcap_api_debugfs_kunit.c" +#endif diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.h b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.h new file mode 100644 index 000000000000..9f2c59b5f6f5 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +#ifndef __VCAP_API_DEBUGFS__ +#define __VCAP_API_DEBUGFS__ + +#include <linux/types.h> +#include <linux/debugfs.h> +#include <linux/netdevice.h> + +#include "vcap_api.h" + +#if defined(CONFIG_DEBUG_FS) + +void vcap_port_debugfs(struct device *dev, struct dentry *parent, + struct vcap_control *vctrl, + struct net_device *ndev); + +/* Create a debugFS entry for a vcap instance */ +struct dentry *vcap_debugfs(struct device *dev, struct dentry *parent, + struct vcap_control *vctrl); + +#else + +static inline void vcap_port_debugfs(struct device *dev, struct dentry *parent, + struct vcap_control *vctrl, + struct net_device *ndev) +{ +} + +static inline struct dentry *vcap_debugfs(struct device *dev, + struct dentry *parent, + struct vcap_control *vctrl) +{ + return NULL; +} + +#endif +#endif /* __VCAP_API_DEBUGFS__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c new file mode 100644 index 000000000000..cf594668d5d9 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API kunit test suite + */ + +#include <kunit/test.h> +#include "vcap_api.h" +#include "vcap_api_client.h" +#include "vcap_api_debugfs.h" +#include "vcap_model_kunit.h" + +/* First we have the test infrastructure that emulates the platform + * implementation + */ +#define TEST_BUF_CNT 100 +#define TEST_BUF_SZ 350 +#define STREAMWSIZE 64 + +static u32 test_updateaddr[STREAMWSIZE] = {}; +static int test_updateaddridx; +static int test_cache_erase_count; +static u32 test_init_start; +static u32 test_init_count; +static u32 test_hw_counter_id; +static struct vcap_cache_data test_hw_cache; +static struct net_device test_netdev = {}; +static int test_move_addr; +static int test_move_offset; +static int test_move_count; +static char test_pr_buffer[TEST_BUF_CNT][TEST_BUF_SZ]; +static int test_pr_bufferidx; +static int test_pr_idx; + +/* Callback used by the VCAP API */ +static enum vcap_keyfield_set test_val_keyset(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule, + struct vcap_keyset_list *kslist, + u16 l3_proto) +{ + int idx; + + if (kslist->cnt > 0) { + switch (admin->vtype) { + case VCAP_TYPE_IS0: + for (idx = 0; idx < kslist->cnt; idx++) { + if (kslist->keysets[idx] == VCAP_KFS_ETAG) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == + VCAP_KFS_PURE_5TUPLE_IP4) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == + VCAP_KFS_NORMAL_5TUPLE_IP4) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == + VCAP_KFS_NORMAL_7TUPLE) + return kslist->keysets[idx]; + } + break; + case VCAP_TYPE_IS2: + for (idx = 0; idx < kslist->cnt; idx++) { + if (kslist->keysets[idx] == VCAP_KFS_MAC_ETYPE) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_ARP) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_IP_7TUPLE) + return kslist->keysets[idx]; + } + break; + default: + pr_info("%s:%d: no validation for VCAP %d\n", + __func__, __LINE__, admin->vtype); + break; + } + } + return -EINVAL; +} + +/* Callback used by the VCAP API */ +static void test_add_def_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + if (admin->vinst == 0 || admin->vinst == 2) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_0); +} + +/* Callback used by the VCAP API */ +static void test_cache_erase(struct vcap_admin *admin) +{ + if (test_cache_erase_count) { + memset(admin->cache.keystream, 0, test_cache_erase_count); + memset(admin->cache.maskstream, 0, test_cache_erase_count); + memset(admin->cache.actionstream, 0, test_cache_erase_count); + test_cache_erase_count = 0; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_init(struct net_device *ndev, struct vcap_admin *admin, + u32 start, u32 count) +{ + test_init_start = start; + test_init_count = count; +} + +/* Callback used by the VCAP API */ +static void test_cache_read(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_selection sel, u32 start, u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + pr_debug("%s:%d: %d %d\n", __func__, __LINE__, start, count); + switch (sel) { + case VCAP_SEL_ENTRY: + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: keydata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, keystr[idx]); + } + for (idx = 0; idx < count; ++idx) { + /* Invert the mask before decoding starts */ + mskstr[idx] = ~mskstr[idx]; + pr_debug("%s:%d: mskdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, mskstr[idx]); + } + break; + case VCAP_SEL_ACTION: + actstr = &admin->cache.actionstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: actdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, actstr[idx]); + } + break; + case VCAP_SEL_COUNTER: + pr_debug("%s:%d\n", __func__, __LINE__); + test_hw_counter_id = start; + admin->cache.counter = test_hw_cache.counter; + admin->cache.sticky = test_hw_cache.sticky; + break; + case VCAP_SEL_ALL: + pr_debug("%s:%d\n", __func__, __LINE__); + break; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_write(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_selection sel, u32 start, u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + switch (sel) { + case VCAP_SEL_ENTRY: + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: keydata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, keystr[idx]); + } + for (idx = 0; idx < count; ++idx) { + /* Invert the mask before encoding starts */ + mskstr[idx] = ~mskstr[idx]; + pr_debug("%s:%d: mskdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, mskstr[idx]); + } + break; + case VCAP_SEL_ACTION: + actstr = &admin->cache.actionstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: actdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, actstr[idx]); + } + break; + case VCAP_SEL_COUNTER: + pr_debug("%s:%d\n", __func__, __LINE__); + test_hw_counter_id = start; + test_hw_cache.counter = admin->cache.counter; + test_hw_cache.sticky = admin->cache.sticky; + break; + case VCAP_SEL_ALL: + pr_err("%s:%d: cannot write all streams at once\n", + __func__, __LINE__); + break; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_update(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_command cmd, + enum vcap_selection sel, u32 addr) +{ + if (test_updateaddridx < ARRAY_SIZE(test_updateaddr)) + test_updateaddr[test_updateaddridx] = addr; + else + pr_err("%s:%d: overflow: %d\n", __func__, __LINE__, + test_updateaddridx); + test_updateaddridx++; +} + +static void test_cache_move(struct net_device *ndev, struct vcap_admin *admin, + u32 addr, int offset, int count) +{ + test_move_addr = addr; + test_move_offset = offset; + test_move_count = count; +} + +/* Provide port information via a callback interface */ +static int vcap_test_port_info(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + return 0; +} + +static int vcap_test_enable(struct net_device *ndev, + struct vcap_admin *admin, + bool enable) +{ + return 0; +} + +static struct vcap_operations test_callbacks = { + .validate_keyset = test_val_keyset, + .add_default_fields = test_add_def_fields, + .cache_erase = test_cache_erase, + .cache_write = test_cache_write, + .cache_read = test_cache_read, + .init = test_cache_init, + .update = test_cache_update, + .move = test_cache_move, + .port_info = vcap_test_port_info, + .enable = vcap_test_enable, +}; + +static struct vcap_control test_vctrl = { + .vcaps = kunit_test_vcaps, + .stats = &kunit_test_vcap_stats, + .ops = &test_callbacks, +}; + +static void vcap_test_api_init(struct vcap_admin *admin) +{ + /* Initialize the shared objects */ + INIT_LIST_HEAD(&test_vctrl.list); + INIT_LIST_HEAD(&admin->list); + INIT_LIST_HEAD(&admin->rules); + list_add_tail(&admin->list, &test_vctrl.list); + memset(test_updateaddr, 0, sizeof(test_updateaddr)); + test_updateaddridx = 0; + test_pr_bufferidx = 0; + test_pr_idx = 0; +} + +/* callback used by the show_admin function */ +static __printf(2, 3) +int test_prf(void *out, const char *fmt, ...) +{ + static char test_buffer[TEST_BUF_SZ]; + va_list args; + int idx, cnt; + + if (test_pr_bufferidx >= TEST_BUF_CNT) { + pr_err("%s:%d: overflow: %d\n", __func__, __LINE__, + test_pr_bufferidx); + return 0; + } + + va_start(args, fmt); + cnt = vscnprintf(test_buffer, TEST_BUF_SZ, fmt, args); + va_end(args); + + for (idx = 0; idx < cnt; ++idx) { + test_pr_buffer[test_pr_bufferidx][test_pr_idx] = + test_buffer[idx]; + if (test_buffer[idx] == '\n') { + test_pr_buffer[test_pr_bufferidx][++test_pr_idx] = 0; + test_pr_idx = 0; + test_pr_bufferidx++; + } else { + ++test_pr_idx; + } + } + + return cnt; +} + +/* Define the test cases. */ + +static void vcap_api_addr_keyset_test(struct kunit *test) +{ + u32 keydata[12] = { + 0x40450042, 0x000feaf3, 0x00000003, 0x00050600, + 0x10203040, 0x00075880, 0x633c6864, 0x00040003, + 0x00000020, 0x00000008, 0x00000240, 0x00000000, + }; + u32 mskdata[12] = { + 0x0030ff80, 0xfff00000, 0xfffffffc, 0xfff000ff, + 0x00000000, 0xfff00000, 0x00000000, 0xfff3fffc, + 0xffffffc0, 0xffffffff, 0xfffffc03, 0xffffffff, + }; + u32 actdata[12] = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + enum vcap_keyfield_set keysets[10]; + struct vcap_keyset_list matches; + int ret, idx, addr; + + vcap_test_api_init(&admin); + + /* Go from higher to lower addresses searching for a keyset */ + matches.keysets = keysets; + matches.cnt = 0; + matches.max = ARRAY_SIZE(keysets); + for (idx = ARRAY_SIZE(keydata) - 1, addr = 799; idx > 0; + --idx, --addr) { + admin.cache.keystream = &keydata[idx]; + admin.cache.maskstream = &mskdata[idx]; + ret = vcap_addr_keysets(&test_vctrl, &test_netdev, &admin, + addr, &matches); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + } + + /* Finally we hit the start of the rule */ + admin.cache.keystream = &keydata[idx]; + admin.cache.maskstream = &mskdata[idx]; + matches.cnt = 0; + ret = vcap_addr_keysets(&test_vctrl, &test_netdev, &admin, + addr, &matches); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, matches.cnt, 1); + KUNIT_EXPECT_EQ(test, matches.keysets[0], VCAP_KFS_MAC_ETYPE); +} + +static void vcap_api_show_admin_raw_test(struct kunit *test) +{ + u32 keydata[4] = { + 0x40450042, 0x000feaf3, 0x00000003, 0x00050600, + }; + u32 mskdata[4] = { + 0x0030ff80, 0xfff00000, 0xfffffffc, 0xfff000ff, + }; + u32 actdata[12] = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + .first_valid_addr = 786, + .last_valid_addr = 788, + }; + struct vcap_rule_internal ri = { + .ndev = &test_netdev, + }; + struct vcap_output_print out = { + .prf = (void *)test_prf, + }; + const char *test_expected = + " addr: 786, X6 rule, keysets: VCAP_KFS_MAC_ETYPE\n"; + int ret; + + vcap_test_api_init(&admin); + list_add_tail(&ri.list, &admin.rules); + + ret = vcap_show_admin_raw(&test_vctrl, &admin, &out); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_STREQ(test, test_expected, test_pr_buffer[0]); +} + +static const char * const test_admin_info_expect[] = { + "name: is2\n", + "rows: 256\n", + "sw_count: 12\n", + "sw_width: 52\n", + "sticky_width: 1\n", + "act_width: 110\n", + "default_cnt: 73\n", + "require_cnt_dis: 0\n", + "version: 1\n", + "vtype: 2\n", + "vinst: 0\n", + "first_cid: 10000\n", + "last_cid: 19999\n", + "lookups: 4\n", + "first_valid_addr: 0\n", + "last_valid_addr: 3071\n", + "last_used_addr: 794\n", +}; + +static void vcap_api_show_admin_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 794, + }; + struct vcap_output_print out = { + .prf = (void *)test_prf, + }; + int idx; + + vcap_test_api_init(&admin); + + vcap_show_admin_info(&test_vctrl, &admin, &out); + for (idx = 0; idx < test_pr_bufferidx; ++idx) { + /* pr_info("log[%02d]: %s", idx, test_pr_buffer[idx]); */ + KUNIT_EXPECT_STREQ(test, test_admin_info_expect[idx], + test_pr_buffer[idx]); + } +} + +static const char * const test_admin_expect[] = { + "name: is2\n", + "rows: 256\n", + "sw_count: 12\n", + "sw_width: 52\n", + "sticky_width: 1\n", + "act_width: 110\n", + "default_cnt: 73\n", + "require_cnt_dis: 0\n", + "version: 1\n", + "vtype: 2\n", + "vinst: 0\n", + "first_cid: 8000000\n", + "last_cid: 8199999\n", + "lookups: 4\n", + "first_valid_addr: 0\n", + "last_valid_addr: 3071\n", + "last_used_addr: 794\n", + "\n", + "rule: 100, addr: [794,799], X6, ctr[0]: 0, hit: 0\n", + " chain_id: 0\n", + " user: 0\n", + " priority: 0\n", + " keysets: VCAP_KFS_MAC_ETYPE\n", + " keyset_sw: 6\n", + " keyset_sw_regs: 2\n", + " ETYPE_LEN_IS: W1: 1/1\n", + " IF_IGR_PORT_MASK: W32: 0xffabcd01/0xffffffff\n", + " IF_IGR_PORT_MASK_RNG: W4: 5/15\n", + " L2_DMAC: W48: 01:02:03:04:05:06/ff:ff:ff:ff:ff:ff\n", + " L2_PAYLOAD_ETYPE: W64: 0x9000002000000081/0xff000000000000ff\n", + " L2_SMAC: W48: b1:9e:34:32:75:88/ff:ff:ff:ff:ff:ff\n", + " LOOKUP_FIRST_IS: W1: 1/1\n", + " TYPE: W4: 0/15\n", + " actionset: VCAP_AFS_BASE_TYPE\n", + " actionset_sw: 3\n", + " actionset_sw_regs: 4\n", + " CNT_ID: W12: 100\n", + " MATCH_ID: W16: 1\n", + " MATCH_ID_MASK: W16: 1\n", + " POLICE_ENA: W1: 1\n", + " PORT_MASK: W68: 0x0514670115f3324589\n", +}; + +static void vcap_api_show_admin_rule_test(struct kunit *test) +{ + u32 keydata[] = { + 0x40450042, 0x000feaf3, 0x00000003, 0x00050600, + 0x10203040, 0x00075880, 0x633c6864, 0x00040003, + 0x00000020, 0x00000008, 0x00000240, 0x00000000, + }; + u32 mskdata[] = { + 0x0030ff80, 0xfff00000, 0xfffffffc, 0xfff000ff, + 0x00000000, 0xfff00000, 0x00000000, 0xfff3fffc, + 0xffffffc0, 0xffffffff, 0xfffffc03, 0xffffffff, + }; + u32 actdata[] = { + 0x00040002, 0xf3324589, 0x14670115, 0x00000005, + 0x00000000, 0x00100000, 0x06400010, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + }; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .first_cid = 8000000, + .last_cid = 8199999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 794, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .data = { + .id = 100, + .keyset = VCAP_KFS_MAC_ETYPE, + .actionset = VCAP_AFS_BASE_TYPE, + }, + .size = 6, + .keyset_sw = 6, + .keyset_sw_regs = 2, + .actionset_sw = 3, + .actionset_sw_regs = 4, + .addr = 794, + .vctrl = &test_vctrl, + }; + struct vcap_output_print out = { + .prf = (void *)test_prf, + }; + int ret, idx; + + vcap_test_api_init(&admin); + list_add_tail(&ri.list, &admin.rules); + + ret = vcap_show_admin(&test_vctrl, &admin, &out); + KUNIT_EXPECT_EQ(test, 0, ret); + for (idx = 0; idx < test_pr_bufferidx; ++idx) { + /* pr_info("log[%02d]: %s", idx, test_pr_buffer[idx]); */ + KUNIT_EXPECT_STREQ(test, test_admin_expect[idx], + test_pr_buffer[idx]); + } +} + +static struct kunit_case vcap_api_debugfs_test_cases[] = { + KUNIT_CASE(vcap_api_addr_keyset_test), + KUNIT_CASE(vcap_api_show_admin_raw_test), + KUNIT_CASE(vcap_api_show_admin_test), + KUNIT_CASE(vcap_api_show_admin_rule_test), + {} +}; + +static struct kunit_suite vcap_api_debugfs_test_suite = { + .name = "VCAP_API_DebugFS_Testsuite", + .test_cases = vcap_api_debugfs_test_cases, +}; + +kunit_test_suite(vcap_api_debugfs_test_suite); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c new file mode 100644 index 000000000000..76a31215ebfb --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -0,0 +1,2245 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API kunit test suite + */ + +#include <kunit/test.h> +#include "vcap_api.h" +#include "vcap_api_client.h" +#include "vcap_model_kunit.h" + +/* First we have the test infrastructure that emulates the platform + * implementation + */ +#define TEST_BUF_CNT 100 +#define TEST_BUF_SZ 350 +#define STREAMWSIZE 64 + +static u32 test_updateaddr[STREAMWSIZE] = {}; +static int test_updateaddridx; +static int test_cache_erase_count; +static u32 test_init_start; +static u32 test_init_count; +static u32 test_hw_counter_id; +static struct vcap_cache_data test_hw_cache; +static struct net_device test_netdev = {}; +static int test_move_addr; +static int test_move_offset; +static int test_move_count; + +/* Callback used by the VCAP API */ +static enum vcap_keyfield_set test_val_keyset(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule, + struct vcap_keyset_list *kslist, + u16 l3_proto) +{ + int idx; + + if (kslist->cnt > 0) { + switch (admin->vtype) { + case VCAP_TYPE_IS0: + for (idx = 0; idx < kslist->cnt; idx++) { + if (kslist->keysets[idx] == VCAP_KFS_ETAG) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_PURE_5TUPLE_IP4) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_NORMAL_5TUPLE_IP4) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_NORMAL_7TUPLE) + return kslist->keysets[idx]; + } + break; + case VCAP_TYPE_IS2: + for (idx = 0; idx < kslist->cnt; idx++) { + if (kslist->keysets[idx] == VCAP_KFS_MAC_ETYPE) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_ARP) + return kslist->keysets[idx]; + if (kslist->keysets[idx] == VCAP_KFS_IP_7TUPLE) + return kslist->keysets[idx]; + } + break; + default: + pr_info("%s:%d: no validation for VCAP %d\n", + __func__, __LINE__, admin->vtype); + break; + } + } + return -EINVAL; +} + +/* Callback used by the VCAP API */ +static void test_add_def_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + if (admin->vinst == 0 || admin->vinst == 2) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_0); +} + +/* Callback used by the VCAP API */ +static void test_cache_erase(struct vcap_admin *admin) +{ + if (test_cache_erase_count) { + memset(admin->cache.keystream, 0, test_cache_erase_count); + memset(admin->cache.maskstream, 0, test_cache_erase_count); + memset(admin->cache.actionstream, 0, test_cache_erase_count); + test_cache_erase_count = 0; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_init(struct net_device *ndev, struct vcap_admin *admin, + u32 start, u32 count) +{ + test_init_start = start; + test_init_count = count; +} + +/* Callback used by the VCAP API */ +static void test_cache_read(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_selection sel, u32 start, u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + pr_debug("%s:%d: %d %d\n", __func__, __LINE__, start, count); + switch (sel) { + case VCAP_SEL_ENTRY: + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: keydata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, keystr[idx]); + } + for (idx = 0; idx < count; ++idx) { + /* Invert the mask before decoding starts */ + mskstr[idx] = ~mskstr[idx]; + pr_debug("%s:%d: mskdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, mskstr[idx]); + } + break; + case VCAP_SEL_ACTION: + actstr = &admin->cache.actionstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: actdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, actstr[idx]); + } + break; + case VCAP_SEL_COUNTER: + pr_debug("%s:%d\n", __func__, __LINE__); + test_hw_counter_id = start; + admin->cache.counter = test_hw_cache.counter; + admin->cache.sticky = test_hw_cache.sticky; + break; + case VCAP_SEL_ALL: + pr_debug("%s:%d\n", __func__, __LINE__); + break; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_write(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_selection sel, u32 start, u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + switch (sel) { + case VCAP_SEL_ENTRY: + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: keydata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, keystr[idx]); + } + for (idx = 0; idx < count; ++idx) { + /* Invert the mask before encoding starts */ + mskstr[idx] = ~mskstr[idx]; + pr_debug("%s:%d: mskdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, mskstr[idx]); + } + break; + case VCAP_SEL_ACTION: + actstr = &admin->cache.actionstream[start]; + for (idx = 0; idx < count; ++idx) { + pr_debug("%s:%d: actdata[%02d]: 0x%08x\n", __func__, + __LINE__, start + idx, actstr[idx]); + } + break; + case VCAP_SEL_COUNTER: + pr_debug("%s:%d\n", __func__, __LINE__); + test_hw_counter_id = start; + test_hw_cache.counter = admin->cache.counter; + test_hw_cache.sticky = admin->cache.sticky; + break; + case VCAP_SEL_ALL: + pr_err("%s:%d: cannot write all streams at once\n", + __func__, __LINE__); + break; + } +} + +/* Callback used by the VCAP API */ +static void test_cache_update(struct net_device *ndev, struct vcap_admin *admin, + enum vcap_command cmd, + enum vcap_selection sel, u32 addr) +{ + if (test_updateaddridx < ARRAY_SIZE(test_updateaddr)) + test_updateaddr[test_updateaddridx] = addr; + else + pr_err("%s:%d: overflow: %d\n", __func__, __LINE__, test_updateaddridx); + test_updateaddridx++; +} + +static void test_cache_move(struct net_device *ndev, struct vcap_admin *admin, + u32 addr, int offset, int count) +{ + test_move_addr = addr; + test_move_offset = offset; + test_move_count = count; +} + +/* Provide port information via a callback interface */ +static int vcap_test_port_info(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + return 0; +} + +static int vcap_test_enable(struct net_device *ndev, + struct vcap_admin *admin, + bool enable) +{ + return 0; +} + +static struct vcap_operations test_callbacks = { + .validate_keyset = test_val_keyset, + .add_default_fields = test_add_def_fields, + .cache_erase = test_cache_erase, + .cache_write = test_cache_write, + .cache_read = test_cache_read, + .init = test_cache_init, + .update = test_cache_update, + .move = test_cache_move, + .port_info = vcap_test_port_info, + .enable = vcap_test_enable, +}; + +static struct vcap_control test_vctrl = { + .vcaps = kunit_test_vcaps, + .stats = &kunit_test_vcap_stats, + .ops = &test_callbacks, +}; + +static void vcap_test_api_init(struct vcap_admin *admin) +{ + /* Initialize the shared objects */ + INIT_LIST_HEAD(&test_vctrl.list); + INIT_LIST_HEAD(&admin->list); + INIT_LIST_HEAD(&admin->rules); + list_add_tail(&admin->list, &test_vctrl.list); + memset(test_updateaddr, 0, sizeof(test_updateaddr)); + test_updateaddridx = 0; +} + +/* Helper function to create a rule of a specific size */ +static struct vcap_rule * +test_vcap_xn_rule_creator(struct kunit *test, int cid, enum vcap_user user, + u16 priority, + int id, int size, int expected_addr) +{ + struct vcap_rule *rule; + struct vcap_rule_internal *ri; + enum vcap_keyfield_set keyset = VCAP_KFS_NO_VALUE; + enum vcap_actionfield_set actionset = VCAP_AFS_NO_VALUE; + int ret; + + /* init before testing */ + memset(test_updateaddr, 0, sizeof(test_updateaddr)); + test_updateaddridx = 0; + test_move_addr = 0; + test_move_offset = 0; + test_move_count = 0; + + switch (size) { + case 2: + keyset = VCAP_KFS_ETAG; + actionset = VCAP_AFS_CLASS_REDUCED; + break; + case 3: + keyset = VCAP_KFS_PURE_5TUPLE_IP4; + actionset = VCAP_AFS_CLASSIFICATION; + break; + case 6: + keyset = VCAP_KFS_NORMAL_5TUPLE_IP4; + actionset = VCAP_AFS_CLASSIFICATION; + break; + case 12: + keyset = VCAP_KFS_NORMAL_7TUPLE; + actionset = VCAP_AFS_FULL; + break; + default: + break; + } + + /* Check that a valid size was used */ + KUNIT_ASSERT_NE(test, VCAP_KFS_NO_VALUE, keyset); + + /* Allocate the rule */ + rule = vcap_alloc_rule(&test_vctrl, &test_netdev, cid, user, priority, + id); + KUNIT_EXPECT_PTR_NE(test, NULL, rule); + + ri = (struct vcap_rule_internal *)rule; + + /* Override rule keyset */ + ret = vcap_set_rule_set_keyset(rule, keyset); + + /* Add rule actions : there must be at least one action */ + ret = vcap_rule_add_action_u32(rule, VCAP_AF_COSID_VAL, 0); + + /* Override rule actionset */ + ret = vcap_set_rule_set_actionset(rule, actionset); + + ret = vcap_val_rule(rule, ETH_P_ALL); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, keyset, rule->keyset); + KUNIT_EXPECT_EQ(test, actionset, rule->actionset); + KUNIT_EXPECT_EQ(test, size, ri->size); + + /* Add rule with write callback */ + ret = vcap_add_rule(rule); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, expected_addr, ri->addr); + return rule; +} + +/* Prepare testing rule deletion */ +static void test_init_rule_deletion(void) +{ + test_move_addr = 0; + test_move_offset = 0; + test_move_count = 0; + test_init_start = 0; + test_init_count = 0; +} + +/* Define the test cases. */ + +static void vcap_api_set_bit_1_test(struct kunit *test) +{ + struct vcap_stream_iter iter = { + .offset = 35, + .sw_width = 52, + .reg_idx = 1, + .reg_bitpos = 20, + .tg = NULL, + }; + u32 stream[2] = {0}; + + vcap_set_bit(stream, &iter, 1); + + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)BIT(20), stream[1]); +} + +static void vcap_api_set_bit_0_test(struct kunit *test) +{ + struct vcap_stream_iter iter = { + .offset = 35, + .sw_width = 52, + .reg_idx = 2, + .reg_bitpos = 11, + .tg = NULL, + }; + u32 stream[3] = {~0, ~0, ~0}; + + vcap_set_bit(stream, &iter, 0); + + KUNIT_EXPECT_EQ(test, (u32)~0, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)~0, stream[1]); + KUNIT_EXPECT_EQ(test, (u32)~BIT(11), stream[2]); +} + +static void vcap_api_iterator_init_test(struct kunit *test) +{ + struct vcap_stream_iter iter; + struct vcap_typegroup typegroups[] = { + { .offset = 0, .width = 2, .value = 2, }, + { .offset = 156, .width = 1, .value = 0, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + struct vcap_typegroup typegroups2[] = { + { .offset = 0, .width = 3, .value = 4, }, + { .offset = 49, .width = 2, .value = 0, }, + { .offset = 98, .width = 2, .value = 0, }, + }; + + vcap_iter_init(&iter, 52, typegroups, 86); + + KUNIT_EXPECT_EQ(test, 52, iter.sw_width); + KUNIT_EXPECT_EQ(test, 86 + 2, iter.offset); + KUNIT_EXPECT_EQ(test, 3, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 4, iter.reg_bitpos); + + vcap_iter_init(&iter, 49, typegroups2, 134); + + KUNIT_EXPECT_EQ(test, 49, iter.sw_width); + KUNIT_EXPECT_EQ(test, 134 + 7, iter.offset); + KUNIT_EXPECT_EQ(test, 5, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 11, iter.reg_bitpos); +} + +static void vcap_api_iterator_next_test(struct kunit *test) +{ + struct vcap_stream_iter iter; + struct vcap_typegroup typegroups[] = { + { .offset = 0, .width = 4, .value = 8, }, + { .offset = 49, .width = 1, .value = 0, }, + { .offset = 98, .width = 2, .value = 0, }, + { .offset = 147, .width = 3, .value = 0, }, + { .offset = 196, .width = 2, .value = 0, }, + { .offset = 245, .width = 1, .value = 0, }, + }; + int idx; + + vcap_iter_init(&iter, 49, typegroups, 86); + + KUNIT_EXPECT_EQ(test, 49, iter.sw_width); + KUNIT_EXPECT_EQ(test, 86 + 5, iter.offset); + KUNIT_EXPECT_EQ(test, 3, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 10, iter.reg_bitpos); + + vcap_iter_next(&iter); + + KUNIT_EXPECT_EQ(test, 91 + 1, iter.offset); + KUNIT_EXPECT_EQ(test, 3, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 11, iter.reg_bitpos); + + for (idx = 0; idx < 6; idx++) + vcap_iter_next(&iter); + + KUNIT_EXPECT_EQ(test, 92 + 6 + 2, iter.offset); + KUNIT_EXPECT_EQ(test, 4, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 2, iter.reg_bitpos); +} + +static void vcap_api_encode_typegroups_test(struct kunit *test) +{ + u32 stream[12] = {0}; + struct vcap_typegroup typegroups[] = { + { .offset = 0, .width = 4, .value = 8, }, + { .offset = 49, .width = 1, .value = 1, }, + { .offset = 98, .width = 2, .value = 3, }, + { .offset = 147, .width = 3, .value = 5, }, + { .offset = 196, .width = 2, .value = 2, }, + { .offset = 245, .width = 5, .value = 27, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + + vcap_encode_typegroups(stream, 49, typegroups, false); + + KUNIT_EXPECT_EQ(test, (u32)0x8, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[1]); + KUNIT_EXPECT_EQ(test, (u32)0x1, stream[2]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[3]); + KUNIT_EXPECT_EQ(test, (u32)0x3, stream[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[5]); + KUNIT_EXPECT_EQ(test, (u32)0x5, stream[6]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[7]); + KUNIT_EXPECT_EQ(test, (u32)0x2, stream[8]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[9]); + KUNIT_EXPECT_EQ(test, (u32)27, stream[10]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[11]); +} + +static void vcap_api_encode_bit_test(struct kunit *test) +{ + struct vcap_stream_iter iter; + u32 stream[4] = {0}; + struct vcap_typegroup typegroups[] = { + { .offset = 0, .width = 4, .value = 8, }, + { .offset = 49, .width = 1, .value = 1, }, + { .offset = 98, .width = 2, .value = 3, }, + { .offset = 147, .width = 3, .value = 5, }, + { .offset = 196, .width = 2, .value = 2, }, + { .offset = 245, .width = 1, .value = 0, }, + }; + + vcap_iter_init(&iter, 49, typegroups, 44); + + KUNIT_EXPECT_EQ(test, 48, iter.offset); + KUNIT_EXPECT_EQ(test, 1, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 16, iter.reg_bitpos); + + vcap_encode_bit(stream, &iter, 1); + + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)BIT(16), stream[1]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[2]); +} + +static void vcap_api_encode_field_test(struct kunit *test) +{ + struct vcap_stream_iter iter; + u32 stream[16] = {0}; + struct vcap_typegroup typegroups[] = { + { .offset = 0, .width = 4, .value = 8, }, + { .offset = 49, .width = 1, .value = 1, }, + { .offset = 98, .width = 2, .value = 3, }, + { .offset = 147, .width = 3, .value = 5, }, + { .offset = 196, .width = 2, .value = 2, }, + { .offset = 245, .width = 5, .value = 27, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + struct vcap_field rf = { + .type = VCAP_FIELD_U32, + .offset = 86, + .width = 4, + }; + u8 value[] = {0x5}; + + vcap_iter_init(&iter, 49, typegroups, rf.offset); + + KUNIT_EXPECT_EQ(test, 91, iter.offset); + KUNIT_EXPECT_EQ(test, 3, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 10, iter.reg_bitpos); + + vcap_encode_field(stream, &iter, rf.width, value); + + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[1]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[2]); + KUNIT_EXPECT_EQ(test, (u32)(0x5 << 10), stream[3]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[4]); + + vcap_encode_typegroups(stream, 49, typegroups, false); + + KUNIT_EXPECT_EQ(test, (u32)0x8, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[1]); + KUNIT_EXPECT_EQ(test, (u32)0x1, stream[2]); + KUNIT_EXPECT_EQ(test, (u32)(0x5 << 10), stream[3]); + KUNIT_EXPECT_EQ(test, (u32)0x3, stream[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[5]); + KUNIT_EXPECT_EQ(test, (u32)0x5, stream[6]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[7]); + KUNIT_EXPECT_EQ(test, (u32)0x2, stream[8]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[9]); + KUNIT_EXPECT_EQ(test, (u32)27, stream[10]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[11]); +} + +/* In this testcase the subword is smaller than a register */ +static void vcap_api_encode_short_field_test(struct kunit *test) +{ + struct vcap_stream_iter iter; + int sw_width = 21; + u32 stream[6] = {0}; + struct vcap_typegroup tgt[] = { + { .offset = 0, .width = 3, .value = 7, }, + { .offset = 21, .width = 2, .value = 3, }, + { .offset = 42, .width = 1, .value = 1, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + struct vcap_field rf = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 4, + }; + u8 value[] = {0x5}; + + vcap_iter_init(&iter, sw_width, tgt, rf.offset); + + KUNIT_EXPECT_EQ(test, 1, iter.regs_per_sw); + KUNIT_EXPECT_EQ(test, 21, iter.sw_width); + KUNIT_EXPECT_EQ(test, 25 + 3 + 2, iter.offset); + KUNIT_EXPECT_EQ(test, 1, iter.reg_idx); + KUNIT_EXPECT_EQ(test, 25 + 3 + 2 - sw_width, iter.reg_bitpos); + + vcap_encode_field(stream, &iter, rf.width, value); + + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)(0x5 << (25 + 3 + 2 - sw_width)), stream[1]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[2]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[3]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, stream[5]); + + vcap_encode_typegroups(stream, sw_width, tgt, false); + + KUNIT_EXPECT_EQ(test, (u32)7, stream[0]); + KUNIT_EXPECT_EQ(test, (u32)((0x5 << (25 + 3 + 2 - sw_width)) + 3), stream[1]); + KUNIT_EXPECT_EQ(test, (u32)1, stream[2]); + KUNIT_EXPECT_EQ(test, (u32)0, stream[3]); + KUNIT_EXPECT_EQ(test, (u32)0, stream[4]); + KUNIT_EXPECT_EQ(test, (u32)0, stream[5]); +} + +static void vcap_api_encode_keyfield_test(struct kunit *test) +{ + u32 keywords[16] = {0}; + u32 maskwords[16] = {0}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .cache = { + .keystream = keywords, + .maskstream = maskwords, + .actionstream = keywords, + }, + }; + struct vcap_rule_internal rule = { + .admin = &admin, + .data = { + .keyset = VCAP_KFS_MAC_ETYPE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf = { + .ctrl.list = {}, + .ctrl.key = VCAP_KF_ISDX_CLS, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0xeef014a1, + .data.u32.mask = 0xfff, + }; + struct vcap_field rf = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }; + struct vcap_typegroup tgt[] = { + { .offset = 0, .width = 2, .value = 2, }, + { .offset = 156, .width = 1, .value = 1, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + + vcap_test_api_init(&admin); + vcap_encode_keyfield(&rule, &ckf, &rf, tgt); + + /* Key */ + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[0]); + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[1]); + KUNIT_EXPECT_EQ(test, (u32)(0x04a1 << 6), keywords[2]); + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[3]); + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[5]); + KUNIT_EXPECT_EQ(test, (u32)0x0, keywords[6]); + + /* Mask */ + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[0]); + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[1]); + KUNIT_EXPECT_EQ(test, (u32)(0x0fff << 6), maskwords[2]); + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[3]); + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[5]); + KUNIT_EXPECT_EQ(test, (u32)0x0, maskwords[6]); +} + +static void vcap_api_encode_max_keyfield_test(struct kunit *test) +{ + int idx; + u32 keywords[6] = {0}; + u32 maskwords[6] = {0}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + /* IS2 sw_width = 52 bit */ + .cache = { + .keystream = keywords, + .maskstream = maskwords, + .actionstream = keywords, + }, + }; + struct vcap_rule_internal rule = { + .admin = &admin, + .data = { + .keyset = VCAP_KFS_IP_7TUPLE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf = { + .ctrl.list = {}, + .ctrl.key = VCAP_KF_L3_IP6_DIP, + .ctrl.type = VCAP_FIELD_U128, + .data.u128.value = { 0xa1, 0xa2, 0xa3, 0xa4, 0, 0, 0x43, 0, + 0, 0, 0, 0, 0, 0, 0x78, 0x8e, }, + .data.u128.mask = { 0xff, 0xff, 0xff, 0xff, 0, 0, 0xff, 0, + 0, 0, 0, 0, 0, 0, 0xff, 0xff }, + }; + struct vcap_field rf = { + .type = VCAP_FIELD_U128, + .offset = 0, + .width = 128, + }; + struct vcap_typegroup tgt[] = { + { .offset = 0, .width = 2, .value = 2, }, + { .offset = 156, .width = 1, .value = 1, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + u32 keyres[] = { + 0x928e8a84, + 0x000c0002, + 0x00000010, + 0x00000000, + 0x0239e000, + 0x00000000, + }; + u32 mskres[] = { + 0xfffffffc, + 0x000c0003, + 0x0000003f, + 0x00000000, + 0x03fffc00, + 0x00000000, + }; + + vcap_encode_keyfield(&rule, &ckf, &rf, tgt); + + /* Key */ + for (idx = 0; idx < ARRAY_SIZE(keyres); ++idx) + KUNIT_EXPECT_EQ(test, keyres[idx], keywords[idx]); + /* Mask */ + for (idx = 0; idx < ARRAY_SIZE(mskres); ++idx) + KUNIT_EXPECT_EQ(test, mskres[idx], maskwords[idx]); +} + +static void vcap_api_encode_actionfield_test(struct kunit *test) +{ + u32 actwords[16] = {0}; + int sw_width = 21; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_ES2, /* act_width = 21 */ + .cache = { + .actionstream = actwords, + }, + }; + struct vcap_rule_internal rule = { + .admin = &admin, + .data = { + .actionset = VCAP_AFS_BASE_TYPE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_client_actionfield caf = { + .ctrl.list = {}, + .ctrl.action = VCAP_AF_POLICE_IDX, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x67908032, + }; + struct vcap_field rf = { + .type = VCAP_FIELD_U32, + .offset = 35, + .width = 6, + }; + struct vcap_typegroup tgt[] = { + { .offset = 0, .width = 2, .value = 2, }, + { .offset = 21, .width = 1, .value = 1, }, + { .offset = 42, .width = 1, .value = 0, }, + { .offset = 0, .width = 0, .value = 0, }, + }; + + vcap_encode_actionfield(&rule, &caf, &rf, tgt); + + /* Action */ + KUNIT_EXPECT_EQ(test, (u32)0x0, actwords[0]); + KUNIT_EXPECT_EQ(test, (u32)((0x32 << (35 + 2 + 1 - sw_width)) & 0x1fffff), actwords[1]); + KUNIT_EXPECT_EQ(test, (u32)((0x32 >> ((2 * sw_width) - 38 - 1))), actwords[2]); + KUNIT_EXPECT_EQ(test, (u32)0x0, actwords[3]); + KUNIT_EXPECT_EQ(test, (u32)0x0, actwords[4]); + KUNIT_EXPECT_EQ(test, (u32)0x0, actwords[5]); + KUNIT_EXPECT_EQ(test, (u32)0x0, actwords[6]); +} + +static void vcap_api_keyfield_typegroup_test(struct kunit *test) +{ + const struct vcap_typegroup *tg; + + tg = vcap_keyfield_typegroup(&test_vctrl, VCAP_TYPE_IS2, VCAP_KFS_MAC_ETYPE); + KUNIT_EXPECT_PTR_NE(test, NULL, tg); + KUNIT_EXPECT_EQ(test, 0, tg[0].offset); + KUNIT_EXPECT_EQ(test, 2, tg[0].width); + KUNIT_EXPECT_EQ(test, 2, tg[0].value); + KUNIT_EXPECT_EQ(test, 156, tg[1].offset); + KUNIT_EXPECT_EQ(test, 1, tg[1].width); + KUNIT_EXPECT_EQ(test, 0, tg[1].value); + KUNIT_EXPECT_EQ(test, 0, tg[2].offset); + KUNIT_EXPECT_EQ(test, 0, tg[2].width); + KUNIT_EXPECT_EQ(test, 0, tg[2].value); + + tg = vcap_keyfield_typegroup(&test_vctrl, VCAP_TYPE_ES2, VCAP_KFS_LL_FULL); + KUNIT_EXPECT_PTR_EQ(test, NULL, tg); +} + +static void vcap_api_actionfield_typegroup_test(struct kunit *test) +{ + const struct vcap_typegroup *tg; + + tg = vcap_actionfield_typegroup(&test_vctrl, VCAP_TYPE_IS0, VCAP_AFS_FULL); + KUNIT_EXPECT_PTR_NE(test, NULL, tg); + KUNIT_EXPECT_EQ(test, 0, tg[0].offset); + KUNIT_EXPECT_EQ(test, 3, tg[0].width); + KUNIT_EXPECT_EQ(test, 4, tg[0].value); + KUNIT_EXPECT_EQ(test, 110, tg[1].offset); + KUNIT_EXPECT_EQ(test, 2, tg[1].width); + KUNIT_EXPECT_EQ(test, 0, tg[1].value); + KUNIT_EXPECT_EQ(test, 220, tg[2].offset); + KUNIT_EXPECT_EQ(test, 2, tg[2].width); + KUNIT_EXPECT_EQ(test, 0, tg[2].value); + KUNIT_EXPECT_EQ(test, 0, tg[3].offset); + KUNIT_EXPECT_EQ(test, 0, tg[3].width); + KUNIT_EXPECT_EQ(test, 0, tg[3].value); + + tg = vcap_actionfield_typegroup(&test_vctrl, VCAP_TYPE_IS2, VCAP_AFS_CLASSIFICATION); + KUNIT_EXPECT_PTR_EQ(test, NULL, tg); +} + +static void vcap_api_vcap_keyfields_test(struct kunit *test) +{ + const struct vcap_field *ft; + + ft = vcap_keyfields(&test_vctrl, VCAP_TYPE_IS2, VCAP_KFS_MAC_ETYPE); + KUNIT_EXPECT_PTR_NE(test, NULL, ft); + + /* Keyset that is not available and within the maximum keyset enum value */ + ft = vcap_keyfields(&test_vctrl, VCAP_TYPE_ES2, VCAP_KFS_PURE_5TUPLE_IP4); + KUNIT_EXPECT_PTR_EQ(test, NULL, ft); + + /* Keyset that is not available and beyond the maximum keyset enum value */ + ft = vcap_keyfields(&test_vctrl, VCAP_TYPE_ES2, VCAP_KFS_LL_FULL); + KUNIT_EXPECT_PTR_EQ(test, NULL, ft); +} + +static void vcap_api_vcap_actionfields_test(struct kunit *test) +{ + const struct vcap_field *ft; + + ft = vcap_actionfields(&test_vctrl, VCAP_TYPE_IS0, VCAP_AFS_FULL); + KUNIT_EXPECT_PTR_NE(test, NULL, ft); + + ft = vcap_actionfields(&test_vctrl, VCAP_TYPE_IS2, VCAP_AFS_FULL); + KUNIT_EXPECT_PTR_EQ(test, NULL, ft); + + ft = vcap_actionfields(&test_vctrl, VCAP_TYPE_IS2, VCAP_AFS_CLASSIFICATION); + KUNIT_EXPECT_PTR_EQ(test, NULL, ft); +} + +static void vcap_api_encode_rule_keyset_test(struct kunit *test) +{ + u32 keywords[16] = {0}; + u32 maskwords[16] = {0}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .cache = { + .keystream = keywords, + .maskstream = maskwords, + }, + }; + struct vcap_rule_internal rule = { + .admin = &admin, + .data = { + .keyset = VCAP_KFS_MAC_ETYPE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x00, + .data.u32.mask = 0x0f, + }, + { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + .ctrl.type = VCAP_FIELD_BIT, + .data.u1.value = 0x01, + .data.u1.mask = 0x01, + }, + { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_L3, + .ctrl.type = VCAP_FIELD_BIT, + .data.u1.value = 0x00, + .data.u1.mask = 0x01, + }, + { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_RNG, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x00, + .data.u32.mask = 0x0f, + }, + { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK, + .ctrl.type = VCAP_FIELD_U72, + .data.u72.value = {0x0, 0x00, 0x00, 0x00}, + .data.u72.mask = {0xfd, 0xff, 0xff, 0xff}, + }, + { + .ctrl.key = VCAP_KF_L2_DMAC, + .ctrl.type = VCAP_FIELD_U48, + /* Opposite endianness */ + .data.u48.value = {0x01, 0x02, 0x03, 0x04, 0x05, 0x06}, + .data.u48.mask = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}, + }, + { + .ctrl.key = VCAP_KF_ETYPE_LEN_IS, + .ctrl.type = VCAP_FIELD_BIT, + .data.u1.value = 0x01, + .data.u1.mask = 0x01, + }, + { + .ctrl.key = VCAP_KF_ETYPE, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0xaabb, + .data.u32.mask = 0xffff, + }, + }; + int idx; + int ret; + + /* Empty entry list */ + INIT_LIST_HEAD(&rule.data.keyfields); + ret = vcap_encode_rule_keyset(&rule); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &rule.data.keyfields); + ret = vcap_encode_rule_keyset(&rule); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* The key and mask values below are from an actual Sparx5 rule config */ + /* Key */ + KUNIT_EXPECT_EQ(test, (u32)0x00000042, keywords[0]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[1]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[2]); + KUNIT_EXPECT_EQ(test, (u32)0x00020100, keywords[3]); + KUNIT_EXPECT_EQ(test, (u32)0x60504030, keywords[4]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[5]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[6]); + KUNIT_EXPECT_EQ(test, (u32)0x0002aaee, keywords[7]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[8]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[9]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[10]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, keywords[11]); + + /* Mask: they will be inverted when applied to the register */ + KUNIT_EXPECT_EQ(test, (u32)~0x00b07f80, maskwords[0]); + KUNIT_EXPECT_EQ(test, (u32)~0xfff00000, maskwords[1]); + KUNIT_EXPECT_EQ(test, (u32)~0xfffffffc, maskwords[2]); + KUNIT_EXPECT_EQ(test, (u32)~0xfff000ff, maskwords[3]); + KUNIT_EXPECT_EQ(test, (u32)~0x00000000, maskwords[4]); + KUNIT_EXPECT_EQ(test, (u32)~0xfffffff0, maskwords[5]); + KUNIT_EXPECT_EQ(test, (u32)~0xfffffffe, maskwords[6]); + KUNIT_EXPECT_EQ(test, (u32)~0xfffc0001, maskwords[7]); + KUNIT_EXPECT_EQ(test, (u32)~0xffffffff, maskwords[8]); + KUNIT_EXPECT_EQ(test, (u32)~0xffffffff, maskwords[9]); + KUNIT_EXPECT_EQ(test, (u32)~0xffffffff, maskwords[10]); + KUNIT_EXPECT_EQ(test, (u32)~0xffffffff, maskwords[11]); +} + +static void vcap_api_encode_rule_actionset_test(struct kunit *test) +{ + u32 actwords[16] = {0}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + .cache = { + .actionstream = actwords, + }, + }; + struct vcap_rule_internal rule = { + .admin = &admin, + .data = { + .actionset = VCAP_AFS_BASE_TYPE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_client_actionfield caf[] = { + { + .ctrl.action = VCAP_AF_MATCH_ID, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x01, + }, + { + .ctrl.action = VCAP_AF_MATCH_ID_MASK, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x01, + }, + { + .ctrl.action = VCAP_AF_CNT_ID, + .ctrl.type = VCAP_FIELD_U32, + .data.u32.value = 0x64, + }, + }; + int idx; + int ret; + + /* Empty entry list */ + INIT_LIST_HEAD(&rule.data.actionfields); + ret = vcap_encode_rule_actionset(&rule); + /* We allow rules with no actions */ + KUNIT_EXPECT_EQ(test, 0, ret); + + for (idx = 0; idx < ARRAY_SIZE(caf); idx++) + list_add_tail(&caf[idx].ctrl.list, &rule.data.actionfields); + ret = vcap_encode_rule_actionset(&rule); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* The action values below are from an actual Sparx5 rule config */ + KUNIT_EXPECT_EQ(test, (u32)0x00000002, actwords[0]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[1]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[2]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[3]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[4]); + KUNIT_EXPECT_EQ(test, (u32)0x00100000, actwords[5]); + KUNIT_EXPECT_EQ(test, (u32)0x06400010, actwords[6]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[7]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[8]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[9]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[10]); + KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[11]); +} + +static void vcap_api_rule_add_keyvalue_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .data = { + .keyset = VCAP_KFS_NO_VALUE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_rule *rule = (struct vcap_rule *)&ri; + struct vcap_client_keyfield *kf; + int ret; + struct vcap_u128_key dip = { + .value = {0x17, 0x26, 0x35, 0x44, 0x63, 0x62, 0x71}, + .mask = {0xf1, 0xf2, 0xf3, 0xf4, 0x4f, 0x3f, 0x2f, 0x1f}, + }; + int idx; + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_0); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_TYPE, 0x98765432, 0xff00ffab); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_TYPE, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x98765432, kf->data.u32.value); + KUNIT_EXPECT_EQ(test, 0xff00ffab, kf->data.u32.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_u128(rule, VCAP_KF_L3_IP6_SIP, &dip); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_L3_IP6_SIP, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U128, kf->ctrl.type); + for (idx = 0; idx < ARRAY_SIZE(dip.value); ++idx) + KUNIT_EXPECT_EQ(test, dip.value[idx], kf->data.u128.value[idx]); + for (idx = 0; idx < ARRAY_SIZE(dip.mask); ++idx) + KUNIT_EXPECT_EQ(test, dip.mask[idx], kf->data.u128.mask[idx]); +} + +static void vcap_api_rule_add_actionvalue_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .data = { + .actionset = VCAP_AFS_NO_VALUE, + }, + }; + struct vcap_rule *rule = (struct vcap_rule *)&ri; + struct vcap_client_actionfield *af; + int ret; + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_0); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x1, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_TYPE, 0x98765432); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_TYPE, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x98765432, af->data.u32.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MASK_MODE, 0xaabbccdd); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_MASK_MODE, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0xaabbccdd, af->data.u32.value); +} + +static void vcap_api_rule_find_keyset_basic_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_L3, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_RNG, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK, + }, { + .ctrl.key = VCAP_KF_L2_DMAC, + }, { + .ctrl.key = VCAP_KF_ETYPE_LEN_IS, + }, { + .ctrl.key = VCAP_KF_ETYPE, + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri.data, &matches); + + KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, 1, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, matches.keysets[0]); +} + +static void vcap_api_rule_find_keyset_failed_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_ARP_OPCODE, + }, { + .ctrl.key = VCAP_KF_L3_IP4_SIP, + }, { + .ctrl.key = VCAP_KF_L3_IP4_DIP, + }, { + .ctrl.key = VCAP_KF_8021Q_PCP_CLS, + }, { + .ctrl.key = VCAP_KF_ETYPE_LEN_IS, /* Not with ARP */ + }, { + .ctrl.key = VCAP_KF_ETYPE, /* Not with ARP */ + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri.data, &matches); + + KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, 0, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_NO_VALUE, matches.keysets[0]); +} + +static void vcap_api_rule_find_keyset_many_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_8021Q_DEI_CLS, + }, { + .ctrl.key = VCAP_KF_8021Q_PCP_CLS, + }, { + .ctrl.key = VCAP_KF_8021Q_VID_CLS, + }, { + .ctrl.key = VCAP_KF_ISDX_CLS, + }, { + .ctrl.key = VCAP_KF_L2_MC_IS, + }, { + .ctrl.key = VCAP_KF_L2_BC_IS, + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri.data, &matches); + + KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, 6, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_ARP, matches.keysets[0]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP4_OTHER, matches.keysets[1]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP4_TCP_UDP, matches.keysets[2]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP6_STD, matches.keysets[3]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP_7TUPLE, matches.keysets[4]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, matches.keysets[5]); +} + +static void vcap_api_encode_rule_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin is2_admin = { + .vtype = VCAP_TYPE_IS2, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 800, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + struct vcap_rule *rule; + struct vcap_rule_internal *ri; + int vcap_chain_id = 10005; + enum vcap_user user = VCAP_USER_VCAP_UTIL; + u16 priority = 10; + int id = 100; + int ret; + struct vcap_u48_key smac = { + .value = { 0x88, 0x75, 0x32, 0x34, 0x9e, 0xb1 }, + .mask = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff } + }; + struct vcap_u48_key dmac = { + .value = { 0x06, 0x05, 0x04, 0x03, 0x02, 0x01 }, + .mask = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff } + }; + u32 port_mask_rng_value = 0x05; + u32 port_mask_rng_mask = 0x0f; + u32 igr_port_mask_value = 0xffabcd01; + u32 igr_port_mask_mask = ~0; + /* counter is not written yet, so it is not in expwriteaddr */ + u32 expwriteaddr[] = {792, 793, 794, 795, 796, 797, 0}; + int idx; + + vcap_test_api_init(&is2_admin); + + /* Allocate the rule */ + rule = vcap_alloc_rule(&test_vctrl, &test_netdev, vcap_chain_id, user, + priority, id); + KUNIT_EXPECT_PTR_NE(test, NULL, rule); + ri = (struct vcap_rule_internal *)rule; + + /* Add rule keys */ + ret = vcap_rule_add_key_u48(rule, VCAP_KF_L2_DMAC, &dmac); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u48(rule, VCAP_KF_L2_SMAC, &smac); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_ETYPE_LEN_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + /* Cannot add the same field twice */ + ret = vcap_rule_add_key_bit(rule, VCAP_KF_ETYPE_LEN_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_IF_IGR_PORT_MASK_L3, + VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK_RNG, + port_mask_rng_value, port_mask_rng_mask); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK, + igr_port_mask_value, igr_port_mask_mask); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Add rule actions */ + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_CNT_ID, id); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MATCH_ID, 1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MATCH_ID_MASK, 1); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* For now the actionset is hardcoded */ + ret = vcap_set_rule_set_actionset(rule, VCAP_AFS_BASE_TYPE); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Validation with validate keyset callback */ + ret = vcap_val_rule(rule, ETH_P_ALL); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, rule->keyset); + KUNIT_EXPECT_EQ(test, VCAP_AFS_BASE_TYPE, rule->actionset); + KUNIT_EXPECT_EQ(test, 6, ri->size); + KUNIT_EXPECT_EQ(test, 2, ri->keyset_sw_regs); + KUNIT_EXPECT_EQ(test, 4, ri->actionset_sw_regs); + + /* Add rule with write callback */ + ret = vcap_add_rule(rule); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 792, is2_admin.last_used_addr); + for (idx = 0; idx < ARRAY_SIZE(expwriteaddr); ++idx) + KUNIT_EXPECT_EQ(test, expwriteaddr[idx], test_updateaddr[idx]); + + /* Check that the rule has been added */ + ret = list_empty(&is2_admin.rules); + KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, 0, ret); + vcap_free_rule(rule); + + /* Check that the rule has been freed: tricky to access since this + * memory should not be accessible anymore + */ + KUNIT_EXPECT_PTR_NE(test, NULL, rule); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, true, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static void vcap_api_set_rule_counter_test(struct kunit *test) +{ + struct vcap_admin is2_admin = { + .cache = { + .counter = 100, + .sticky = true, + }, + }; + struct vcap_rule_internal ri = { + .data = { + .id = 1001, + }, + .addr = 600, + .admin = &is2_admin, + .counter_id = 1002, + .vctrl = &test_vctrl, + }; + struct vcap_rule_internal ri2 = { + .data = { + .id = 2001, + }, + .addr = 700, + .admin = &is2_admin, + .counter_id = 2002, + .vctrl = &test_vctrl, + }; + struct vcap_counter ctr = { .value = 0, .sticky = false}; + struct vcap_counter ctr2 = { .value = 101, .sticky = true}; + int ret; + + vcap_test_api_init(&is2_admin); + list_add_tail(&ri.list, &is2_admin.rules); + list_add_tail(&ri2.list, &is2_admin.rules); + + pr_info("%s:%d\n", __func__, __LINE__); + ret = vcap_rule_set_counter(&ri.data, &ctr); + pr_info("%s:%d\n", __func__, __LINE__); + KUNIT_EXPECT_EQ(test, 0, ret); + + KUNIT_EXPECT_EQ(test, 1002, test_hw_counter_id); + KUNIT_EXPECT_EQ(test, 0, test_hw_cache.counter); + KUNIT_EXPECT_EQ(test, false, test_hw_cache.sticky); + KUNIT_EXPECT_EQ(test, 600, test_updateaddr[0]); + + ret = vcap_rule_set_counter(&ri2.data, &ctr2); + KUNIT_EXPECT_EQ(test, 0, ret); + + KUNIT_EXPECT_EQ(test, 2002, test_hw_counter_id); + KUNIT_EXPECT_EQ(test, 101, test_hw_cache.counter); + KUNIT_EXPECT_EQ(test, true, test_hw_cache.sticky); + KUNIT_EXPECT_EQ(test, 700, test_updateaddr[1]); +} + +static void vcap_api_get_rule_counter_test(struct kunit *test) +{ + struct vcap_admin is2_admin = { + .cache = { + .counter = 100, + .sticky = true, + }, + }; + struct vcap_rule_internal ri = { + .data = { + .id = 1010, + }, + .addr = 400, + .admin = &is2_admin, + .counter_id = 1011, + .vctrl = &test_vctrl, + }; + struct vcap_rule_internal ri2 = { + .data = { + .id = 2011, + }, + .addr = 300, + .admin = &is2_admin, + .counter_id = 2012, + .vctrl = &test_vctrl, + }; + struct vcap_counter ctr = {}; + struct vcap_counter ctr2 = {}; + int ret; + + vcap_test_api_init(&is2_admin); + test_hw_cache.counter = 55; + test_hw_cache.sticky = true; + + list_add_tail(&ri.list, &is2_admin.rules); + list_add_tail(&ri2.list, &is2_admin.rules); + + ret = vcap_rule_get_counter(&ri.data, &ctr); + KUNIT_EXPECT_EQ(test, 0, ret); + + KUNIT_EXPECT_EQ(test, 1011, test_hw_counter_id); + KUNIT_EXPECT_EQ(test, 55, ctr.value); + KUNIT_EXPECT_EQ(test, true, ctr.sticky); + KUNIT_EXPECT_EQ(test, 400, test_updateaddr[0]); + + test_hw_cache.counter = 22; + test_hw_cache.sticky = false; + + ret = vcap_rule_get_counter(&ri2.data, &ctr2); + KUNIT_EXPECT_EQ(test, 0, ret); + + KUNIT_EXPECT_EQ(test, 2012, test_hw_counter_id); + KUNIT_EXPECT_EQ(test, 22, ctr2.value); + KUNIT_EXPECT_EQ(test, false, ctr2.sticky); + KUNIT_EXPECT_EQ(test, 300, test_updateaddr[1]); +} + +static void vcap_api_rule_insert_in_order_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 800, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + + vcap_test_api_init(&admin); + + /* Create rules with different sizes and check that they are placed + * at the correct address in the VCAP according to size + */ + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 10, 500, 12, 780); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 400, 6, 774); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 771); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 200, 2, 768); +} + +static void vcap_api_rule_insert_reverse_order_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 800, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + struct vcap_rule_internal *elem; + u32 exp_addr[] = {780, 774, 771, 768, 767}; + int idx; + + vcap_test_api_init(&admin); + + /* Create rules with different sizes and check that they are placed + * at the correct address in the VCAP according to size + */ + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 200, 2, 798); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 795); + KUNIT_EXPECT_EQ(test, 6, test_move_offset); + KUNIT_EXPECT_EQ(test, 3, test_move_count); + KUNIT_EXPECT_EQ(test, 798, test_move_addr); + + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 400, 6, 792); + KUNIT_EXPECT_EQ(test, 6, test_move_offset); + KUNIT_EXPECT_EQ(test, 6, test_move_count); + KUNIT_EXPECT_EQ(test, 792, test_move_addr); + + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 50, 500, 12, 780); + KUNIT_EXPECT_EQ(test, 18, test_move_offset); + KUNIT_EXPECT_EQ(test, 12, test_move_count); + KUNIT_EXPECT_EQ(test, 786, test_move_addr); + + idx = 0; + list_for_each_entry(elem, &admin.rules, list) { + KUNIT_EXPECT_EQ(test, exp_addr[idx], elem->addr); + ++idx; + } + KUNIT_EXPECT_EQ(test, 768, admin.last_used_addr); +} + +static void vcap_api_rule_remove_at_end_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 800, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + int ret; + + vcap_test_api_init(&admin); + test_init_rule_deletion(); + + /* Create rules with different sizes and check that they are placed + * at the correct address in the VCAP according to size + */ + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 10, 500, 12, 780); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 400, 6, 774); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 771); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 200, 2, 768); + + /* Remove rules again from the end */ + ret = vcap_del_rule(&test_vctrl, &test_netdev, 200); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 768, test_init_start); + KUNIT_EXPECT_EQ(test, 2, test_init_count); + KUNIT_EXPECT_EQ(test, 771, admin.last_used_addr); + + ret = vcap_del_rule(&test_vctrl, &test_netdev, 300); + KUNIT_EXPECT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 771, test_init_start); + KUNIT_EXPECT_EQ(test, 3, test_init_count); + KUNIT_EXPECT_EQ(test, 774, admin.last_used_addr); + + ret = vcap_del_rule(&test_vctrl, &test_netdev, 400); + KUNIT_EXPECT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 774, test_init_start); + KUNIT_EXPECT_EQ(test, 6, test_init_count); + KUNIT_EXPECT_EQ(test, 780, admin.last_used_addr); + + ret = vcap_del_rule(&test_vctrl, &test_netdev, 500); + KUNIT_EXPECT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 780, test_init_start); + KUNIT_EXPECT_EQ(test, 12, test_init_count); + KUNIT_EXPECT_EQ(test, 3072, admin.last_used_addr); +} + +static void vcap_api_rule_remove_in_middle_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .first_valid_addr = 0, + .last_used_addr = 800, + .last_valid_addr = 800 - 1, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + int ret; + + vcap_test_api_init(&admin); + + /* Create rules with different sizes and check that they are placed + * at the correct address in the VCAP according to size + */ + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 10, 500, 12, 780); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 400, 6, 774); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 771); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 200, 2, 768); + + /* Remove rules in the middle */ + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 400); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 768, test_move_addr); + KUNIT_EXPECT_EQ(test, -6, test_move_offset); + KUNIT_EXPECT_EQ(test, 6, test_move_count); + KUNIT_EXPECT_EQ(test, 768, test_init_start); + KUNIT_EXPECT_EQ(test, 6, test_init_count); + KUNIT_EXPECT_EQ(test, 774, admin.last_used_addr); + + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 300); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 774, test_move_addr); + KUNIT_EXPECT_EQ(test, -4, test_move_offset); + KUNIT_EXPECT_EQ(test, 2, test_move_count); + KUNIT_EXPECT_EQ(test, 774, test_init_start); + KUNIT_EXPECT_EQ(test, 4, test_init_count); + KUNIT_EXPECT_EQ(test, 778, admin.last_used_addr); + + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 500); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 778, test_move_addr); + KUNIT_EXPECT_EQ(test, -20, test_move_offset); + KUNIT_EXPECT_EQ(test, 2, test_move_count); + KUNIT_EXPECT_EQ(test, 778, test_init_start); + KUNIT_EXPECT_EQ(test, 20, test_init_count); + KUNIT_EXPECT_EQ(test, 798, admin.last_used_addr); + + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 200); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 798, test_init_start); + KUNIT_EXPECT_EQ(test, 2, test_init_count); + KUNIT_EXPECT_EQ(test, 800, admin.last_used_addr); +} + +static void vcap_api_rule_remove_in_front_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .first_valid_addr = 0, + .last_used_addr = 800, + .last_valid_addr = 800 - 1, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + int ret; + + vcap_test_api_init(&admin); + + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 10, 500, 12, 780); + KUNIT_EXPECT_EQ(test, 780, admin.last_used_addr); + + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 500); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 0, test_move_addr); + KUNIT_EXPECT_EQ(test, 0, test_move_offset); + KUNIT_EXPECT_EQ(test, 0, test_move_count); + KUNIT_EXPECT_EQ(test, 780, test_init_start); + KUNIT_EXPECT_EQ(test, 12, test_init_count); + KUNIT_EXPECT_EQ(test, 800, admin.last_used_addr); + + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 400, 6, 792); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 789); + test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 200, 2, 786); + + test_init_rule_deletion(); + ret = vcap_del_rule(&test_vctrl, &test_netdev, 400); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 786, test_move_addr); + KUNIT_EXPECT_EQ(test, -8, test_move_offset); + KUNIT_EXPECT_EQ(test, 6, test_move_count); + KUNIT_EXPECT_EQ(test, 786, test_init_start); + KUNIT_EXPECT_EQ(test, 8, test_init_count); + KUNIT_EXPECT_EQ(test, 794, admin.last_used_addr); +} + +static struct kunit_case vcap_api_rule_remove_test_cases[] = { + KUNIT_CASE(vcap_api_rule_remove_at_end_test), + KUNIT_CASE(vcap_api_rule_remove_in_middle_test), + KUNIT_CASE(vcap_api_rule_remove_in_front_test), + {} +}; + +static void vcap_api_next_lookup_basic_test(struct kunit *test) +{ + struct vcap_admin admin1 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 0, + .first_cid = 8000000, + .last_cid = 8199999, + .lookups = 4, + .lookups_per_instance = 2, + }; + struct vcap_admin admin2 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 1, + .first_cid = 8200000, + .last_cid = 8399999, + .lookups = 4, + .lookups_per_instance = 2, + }; + bool ret; + + vcap_test_api_init(&admin1); + list_add_tail(&admin2.list, &test_vctrl.list); + + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 1001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8100000, 8101000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8100000, 8201000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8200000, 8201000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8200000, 8301000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static void vcap_api_next_lookup_advanced_test(struct kunit *test) +{ + struct vcap_admin admin1 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 0, + .first_cid = 1000000, + .last_cid = 1199999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin2 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 1, + .first_cid = 1200000, + .last_cid = 1399999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin3 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 2, + .first_cid = 1400000, + .last_cid = 1599999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin4 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 0, + .first_cid = 8000000, + .last_cid = 8199999, + .lookups = 4, + .lookups_per_instance = 2, + }; + struct vcap_admin admin5 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 1, + .first_cid = 8200000, + .last_cid = 8399999, + .lookups = 4, + .lookups_per_instance = 2, + }; + bool ret; + + vcap_test_api_init(&admin1); + list_add_tail(&admin2.list, &test_vctrl.list); + list_add_tail(&admin3.list, &test_vctrl.list); + list_add_tail(&admin4.list, &test_vctrl.list); + list_add_tail(&admin5.list, &test_vctrl.list); + + ret = vcap_is_next_lookup(&test_vctrl, 1000000, 1001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1000000, 1101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1201000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 8101000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1300000, 1401000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1400000, 1501000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1500000, 8001000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static void vcap_api_filter_unsupported_keys_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + .data.keyset = VCAP_KFS_MAC_ETYPE, + }; + enum vcap_key_field keylist[] = { + VCAP_KF_TYPE, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_ARP_ADDR_SPACE_OK_IS, /* arp keys are not in keyset */ + VCAP_KF_ARP_PROTO_SPACE_OK_IS, + VCAP_KF_ARP_LEN_OK_IS, + VCAP_KF_ARP_TGT_MATCH_IS, + VCAP_KF_ARP_SENDER_MATCH_IS, + VCAP_KF_ARP_OPCODE_UNKNOWN_IS, + VCAP_KF_ARP_OPCODE, + VCAP_KF_8021Q_DEI_CLS, + VCAP_KF_8021Q_PCP_CLS, + VCAP_KF_8021Q_VID_CLS, + VCAP_KF_L2_MC_IS, + VCAP_KF_L2_BC_IS, + }; + enum vcap_key_field expected[] = { + VCAP_KF_TYPE, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_8021Q_DEI_CLS, + VCAP_KF_8021Q_PCP_CLS, + VCAP_KF_8021Q_VID_CLS, + VCAP_KF_L2_MC_IS, + VCAP_KF_L2_BC_IS, + }; + struct vcap_client_keyfield *ckf, *next; + bool ret; + int idx; + + /* Add all keys to the rule */ + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(keylist); idx++) { + ckf = kzalloc(sizeof(*ckf), GFP_KERNEL); + if (ckf) { + ckf->ctrl.key = keylist[idx]; + list_add_tail(&ckf->ctrl.list, &ri.data.keyfields); + } + } + + KUNIT_EXPECT_EQ(test, 14, ARRAY_SIZE(keylist)); + + /* Drop unsupported keys from the rule */ + ret = vcap_filter_rule_keys(&ri.data, NULL, 0, true); + + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Check remaining keys in the rule */ + idx = 0; + list_for_each_entry_safe(ckf, next, &ri.data.keyfields, ctrl.list) { + KUNIT_EXPECT_EQ(test, expected[idx], ckf->ctrl.key); + list_del(&ckf->ctrl.list); + kfree(ckf); + ++idx; + } + KUNIT_EXPECT_EQ(test, 7, idx); +} + +static void vcap_api_filter_keylist_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS0, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + .data.keyset = VCAP_KFS_NORMAL_7TUPLE, + }; + enum vcap_key_field keylist[] = { + VCAP_KF_TYPE, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_LOOKUP_GEN_IDX_SEL, + VCAP_KF_LOOKUP_GEN_IDX, + VCAP_KF_IF_IGR_PORT_MASK_SEL, + VCAP_KF_IF_IGR_PORT_MASK, + VCAP_KF_L2_MC_IS, + VCAP_KF_L2_BC_IS, + VCAP_KF_8021Q_VLAN_TAGS, + VCAP_KF_8021Q_TPID0, + VCAP_KF_8021Q_PCP0, + VCAP_KF_8021Q_DEI0, + VCAP_KF_8021Q_VID0, + VCAP_KF_8021Q_TPID1, + VCAP_KF_8021Q_PCP1, + VCAP_KF_8021Q_DEI1, + VCAP_KF_8021Q_VID1, + VCAP_KF_8021Q_TPID2, + VCAP_KF_8021Q_PCP2, + VCAP_KF_8021Q_DEI2, + VCAP_KF_8021Q_VID2, + VCAP_KF_L2_DMAC, + VCAP_KF_L2_SMAC, + VCAP_KF_IP_MC_IS, + VCAP_KF_ETYPE_LEN_IS, + VCAP_KF_ETYPE, + VCAP_KF_IP_SNAP_IS, + VCAP_KF_IP4_IS, + VCAP_KF_L3_FRAGMENT_TYPE, + VCAP_KF_L3_FRAG_INVLD_L4_LEN, + VCAP_KF_L3_OPTIONS_IS, + VCAP_KF_L3_DSCP, + VCAP_KF_L3_IP6_DIP, + VCAP_KF_L3_IP6_SIP, + VCAP_KF_TCP_UDP_IS, + VCAP_KF_TCP_IS, + VCAP_KF_L4_SPORT, + VCAP_KF_L4_RNG, + }; + enum vcap_key_field droplist[] = { + VCAP_KF_8021Q_TPID1, + VCAP_KF_8021Q_PCP1, + VCAP_KF_8021Q_DEI1, + VCAP_KF_8021Q_VID1, + VCAP_KF_8021Q_TPID2, + VCAP_KF_8021Q_PCP2, + VCAP_KF_8021Q_DEI2, + VCAP_KF_8021Q_VID2, + VCAP_KF_L3_IP6_DIP, + VCAP_KF_L3_IP6_SIP, + VCAP_KF_L4_SPORT, + VCAP_KF_L4_RNG, + }; + enum vcap_key_field expected[] = { + VCAP_KF_TYPE, + VCAP_KF_LOOKUP_FIRST_IS, + VCAP_KF_LOOKUP_GEN_IDX_SEL, + VCAP_KF_LOOKUP_GEN_IDX, + VCAP_KF_IF_IGR_PORT_MASK_SEL, + VCAP_KF_IF_IGR_PORT_MASK, + VCAP_KF_L2_MC_IS, + VCAP_KF_L2_BC_IS, + VCAP_KF_8021Q_VLAN_TAGS, + VCAP_KF_8021Q_TPID0, + VCAP_KF_8021Q_PCP0, + VCAP_KF_8021Q_DEI0, + VCAP_KF_8021Q_VID0, + VCAP_KF_L2_DMAC, + VCAP_KF_L2_SMAC, + VCAP_KF_IP_MC_IS, + VCAP_KF_ETYPE_LEN_IS, + VCAP_KF_ETYPE, + VCAP_KF_IP_SNAP_IS, + VCAP_KF_IP4_IS, + VCAP_KF_L3_FRAGMENT_TYPE, + VCAP_KF_L3_FRAG_INVLD_L4_LEN, + VCAP_KF_L3_OPTIONS_IS, + VCAP_KF_L3_DSCP, + VCAP_KF_TCP_UDP_IS, + VCAP_KF_TCP_IS, + }; + struct vcap_client_keyfield *ckf, *next; + bool ret; + int idx; + + /* Add all keys to the rule */ + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(keylist); idx++) { + ckf = kzalloc(sizeof(*ckf), GFP_KERNEL); + if (ckf) { + ckf->ctrl.key = keylist[idx]; + list_add_tail(&ckf->ctrl.list, &ri.data.keyfields); + } + } + + KUNIT_EXPECT_EQ(test, 38, ARRAY_SIZE(keylist)); + + /* Drop listed keys from the rule */ + ret = vcap_filter_rule_keys(&ri.data, droplist, ARRAY_SIZE(droplist), + false); + + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Check remaining keys in the rule */ + idx = 0; + list_for_each_entry_safe(ckf, next, &ri.data.keyfields, ctrl.list) { + KUNIT_EXPECT_EQ(test, expected[idx], ckf->ctrl.key); + list_del(&ckf->ctrl.list); + kfree(ckf); + ++idx; + } + KUNIT_EXPECT_EQ(test, 26, idx); +} + +static struct kunit_suite vcap_api_rule_remove_test_suite = { + .name = "VCAP_API_Rule_Remove_Testsuite", + .test_cases = vcap_api_rule_remove_test_cases, +}; + +static struct kunit_case vcap_api_rule_insert_test_cases[] = { + KUNIT_CASE(vcap_api_rule_insert_in_order_test), + KUNIT_CASE(vcap_api_rule_insert_reverse_order_test), + {} +}; + +static struct kunit_suite vcap_api_rule_insert_test_suite = { + .name = "VCAP_API_Rule_Insert_Testsuite", + .test_cases = vcap_api_rule_insert_test_cases, +}; + +static struct kunit_case vcap_api_rule_counter_test_cases[] = { + KUNIT_CASE(vcap_api_set_rule_counter_test), + KUNIT_CASE(vcap_api_get_rule_counter_test), + {} +}; + +static struct kunit_suite vcap_api_rule_counter_test_suite = { + .name = "VCAP_API_Rule_Counter_Testsuite", + .test_cases = vcap_api_rule_counter_test_cases, +}; + +static struct kunit_case vcap_api_support_test_cases[] = { + KUNIT_CASE(vcap_api_next_lookup_basic_test), + KUNIT_CASE(vcap_api_next_lookup_advanced_test), + KUNIT_CASE(vcap_api_filter_unsupported_keys_test), + KUNIT_CASE(vcap_api_filter_keylist_test), + {} +}; + +static struct kunit_suite vcap_api_support_test_suite = { + .name = "VCAP_API_Support_Testsuite", + .test_cases = vcap_api_support_test_cases, +}; + +static struct kunit_case vcap_api_full_rule_test_cases[] = { + KUNIT_CASE(vcap_api_rule_find_keyset_basic_test), + KUNIT_CASE(vcap_api_rule_find_keyset_failed_test), + KUNIT_CASE(vcap_api_rule_find_keyset_many_test), + KUNIT_CASE(vcap_api_encode_rule_test), + {} +}; + +static struct kunit_suite vcap_api_full_rule_test_suite = { + .name = "VCAP_API_Full_Rule_Testsuite", + .test_cases = vcap_api_full_rule_test_cases, +}; + +static struct kunit_case vcap_api_rule_value_test_cases[] = { + KUNIT_CASE(vcap_api_rule_add_keyvalue_test), + KUNIT_CASE(vcap_api_rule_add_actionvalue_test), + {} +}; + +static struct kunit_suite vcap_api_rule_value_test_suite = { + .name = "VCAP_API_Rule_Value_Testsuite", + .test_cases = vcap_api_rule_value_test_cases, +}; + +static struct kunit_case vcap_api_encoding_test_cases[] = { + KUNIT_CASE(vcap_api_set_bit_1_test), + KUNIT_CASE(vcap_api_set_bit_0_test), + KUNIT_CASE(vcap_api_iterator_init_test), + KUNIT_CASE(vcap_api_iterator_next_test), + KUNIT_CASE(vcap_api_encode_typegroups_test), + KUNIT_CASE(vcap_api_encode_bit_test), + KUNIT_CASE(vcap_api_encode_field_test), + KUNIT_CASE(vcap_api_encode_short_field_test), + KUNIT_CASE(vcap_api_encode_keyfield_test), + KUNIT_CASE(vcap_api_encode_max_keyfield_test), + KUNIT_CASE(vcap_api_encode_actionfield_test), + KUNIT_CASE(vcap_api_keyfield_typegroup_test), + KUNIT_CASE(vcap_api_actionfield_typegroup_test), + KUNIT_CASE(vcap_api_vcap_keyfields_test), + KUNIT_CASE(vcap_api_vcap_actionfields_test), + KUNIT_CASE(vcap_api_encode_rule_keyset_test), + KUNIT_CASE(vcap_api_encode_rule_actionset_test), + {} +}; + +static struct kunit_suite vcap_api_encoding_test_suite = { + .name = "VCAP_API_Encoding_Testsuite", + .test_cases = vcap_api_encoding_test_cases, +}; + +kunit_test_suite(vcap_api_rule_remove_test_suite); +kunit_test_suite(vcap_api_rule_insert_test_suite); +kunit_test_suite(vcap_api_rule_counter_test_suite); +kunit_test_suite(vcap_api_support_test_suite); +kunit_test_suite(vcap_api_full_rule_test_suite); +kunit_test_suite(vcap_api_rule_value_test_suite); +kunit_test_suite(vcap_api_encoding_test_suite); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h new file mode 100644 index 000000000000..4fd21da97679 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +#ifndef __VCAP_API_PRIVATE__ +#define __VCAP_API_PRIVATE__ + +#include <linux/types.h> + +#include "vcap_api.h" +#include "vcap_api_client.h" + +#define to_intrule(rule) container_of((rule), struct vcap_rule_internal, data) + +/* Private VCAP API rule data */ +struct vcap_rule_internal { + struct vcap_rule data; /* provided by the client */ + struct list_head list; /* the vcap admin list of rules */ + struct vcap_admin *admin; /* vcap hw instance */ + struct net_device *ndev; /* the interface that the rule applies to */ + struct vcap_control *vctrl; /* the client control */ + u32 sort_key; /* defines the position in the VCAP */ + int keyset_sw; /* subwords in a keyset */ + int actionset_sw; /* subwords in an actionset */ + int keyset_sw_regs; /* registers in a subword in an keyset */ + int actionset_sw_regs; /* registers in a subword in an actionset */ + int size; /* the size of the rule: max(entry, action) */ + u32 addr; /* address in the VCAP at insertion */ + u32 counter_id; /* counter id (if a dedicated counter is available) */ + struct vcap_counter counter; /* last read counter value */ +}; + +/* Bit iterator for the VCAP cache streams */ +struct vcap_stream_iter { + u32 offset; /* bit offset from the stream start */ + u32 sw_width; /* subword width in bits */ + u32 regs_per_sw; /* registers per subword */ + u32 reg_idx; /* current register index */ + u32 reg_bitpos; /* bit offset in current register */ + const struct vcap_typegroup *tg; /* current typegroup */ +}; + +/* Check that the control has a valid set of callbacks */ +int vcap_api_check(struct vcap_control *ctrl); +/* Make a shallow copy of the rule without the fields */ +struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri); +/* Erase the VCAP cache area used or encoding and decoding */ +void vcap_erase_cache(struct vcap_rule_internal *ri); + +/* Iterator functionality */ + +void vcap_iter_init(struct vcap_stream_iter *itr, int sw_width, + const struct vcap_typegroup *tg, u32 offset); +void vcap_iter_next(struct vcap_stream_iter *itr); +void vcap_iter_set(struct vcap_stream_iter *itr, int sw_width, + const struct vcap_typegroup *tg, u32 offset); +void vcap_iter_update(struct vcap_stream_iter *itr); + +/* Keyset and keyfield functionality */ + +/* Return the number of keyfields in the keyset */ +int vcap_keyfield_count(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_keyfield_set keyset); +/* Return the typegroup table for the matching keyset (using subword size) */ +const struct vcap_typegroup * +vcap_keyfield_typegroup(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_keyfield_set keyset); +/* Return the list of keyfields for the keyset */ +const struct vcap_field *vcap_keyfields(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_keyfield_set keyset); + +/* Actionset and actionfield functionality */ + +/* Return the actionset information for the actionset */ +const struct vcap_set * +vcap_actionfieldset(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_actionfield_set actionset); +/* Return the number of actionfields in the actionset */ +int vcap_actionfield_count(struct vcap_control *vctrl, + enum vcap_type vt, + enum vcap_actionfield_set actionset); +/* Return the typegroup table for the matching actionset (using subword size) */ +const struct vcap_typegroup * +vcap_actionfield_typegroup(struct vcap_control *vctrl, enum vcap_type vt, + enum vcap_actionfield_set actionset); +/* Return the list of actionfields for the actionset */ +const struct vcap_field * +vcap_actionfields(struct vcap_control *vctrl, + enum vcap_type vt, enum vcap_actionfield_set actionset); +/* Map actionset id to a string with the actionset name */ +const char *vcap_actionset_name(struct vcap_control *vctrl, + enum vcap_actionfield_set actionset); +/* Map key field id to a string with the key name */ +const char *vcap_actionfield_name(struct vcap_control *vctrl, + enum vcap_action_field action); + +/* Read key data from a VCAP address and discover if there are any rule keysets + * here + */ +int vcap_addr_keysets(struct vcap_control *vctrl, struct net_device *ndev, + struct vcap_admin *admin, int addr, + struct vcap_keyset_list *kslist); + +/* Verify that the typegroup information, subword count, keyset and type id + * are in sync and correct, return the list of matchin keysets + */ +int vcap_find_keystream_keysets(struct vcap_control *vctrl, enum vcap_type vt, + u32 *keystream, u32 *mskstream, bool mask, + int sw_max, struct vcap_keyset_list *kslist); + +#endif /* __VCAP_API_PRIVATE__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c new file mode 100644 index 000000000000..5d681d2697cd --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c @@ -0,0 +1,5570 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API Test VCAP Model Data + */ + +#include <linux/types.h> +#include <linux/kernel.h> + +#include "vcap_api.h" +#include "vcap_model_kunit.h" + +/* keyfields */ +static const struct vcap_field is0_mll_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 7, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 3, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 3, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 31, + .width = 12, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 43, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 91, + .width = 48, + }, + [VCAP_KF_ETYPE_MPLS] = { + .type = VCAP_FIELD_U32, + .offset = 139, + .width = 2, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 141, + .width = 8, + }, +}; + +static const struct vcap_field is0_tri_vid_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 7, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 24, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 30, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 33, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 34, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 46, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 49, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 53, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 65, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 71, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 72, + .width = 12, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 8, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_OAM_MEL_FLAGS] = { + .type = VCAP_FIELD_U32, + .offset = 93, + .width = 7, + }, +}; + +static const struct vcap_field is0_ll_full_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 7, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 32, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 35, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 38, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 39, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 51, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 54, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 57, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 58, + .width = 12, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 70, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 118, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 166, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 167, + .width = 16, + }, + [VCAP_KF_IP_SNAP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 183, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 184, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 185, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 187, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 188, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 189, + .width = 6, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 195, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 227, + .width = 32, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 259, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 260, + .width = 1, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 261, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 277, + .width = 8, + }, +}; + +static const struct vcap_field is0_normal_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 12, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 19, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 86, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 89, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 92, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 108, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 111, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 114, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 115, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 130, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 133, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 134, + .width = 12, + }, + [VCAP_KF_DST_ENTRY] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 147, + .width = 48, + }, + [VCAP_KF_IP_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 195, + .width = 1, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 196, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 197, + .width = 16, + }, + [VCAP_KF_IP_SNAP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 213, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 214, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 215, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 217, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 219, + .width = 6, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 225, + .width = 32, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 257, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 258, + .width = 1, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 259, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 275, + .width = 8, + }, +}; + +static const struct vcap_field is0_normal_7tuple_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 12, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 18, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 85, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 95, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 107, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 110, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 113, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 114, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 126, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 129, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 132, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 133, + .width = 12, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 145, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 193, + .width = 48, + }, + [VCAP_KF_IP_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 241, + .width = 1, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 242, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 243, + .width = 16, + }, + [VCAP_KF_IP_SNAP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 259, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 260, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 261, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 263, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 264, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 265, + .width = 6, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 271, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 399, + .width = 128, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 527, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 528, + .width = 1, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 529, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 545, + .width = 8, + }, +}; + +static const struct vcap_field is0_normal_5tuple_ip4_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 12, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 19, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 86, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 89, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 92, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 108, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 111, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 114, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 115, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 130, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 133, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 134, + .width = 12, + }, + [VCAP_KF_IP_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 147, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 148, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 151, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 152, + .width = 6, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 158, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 190, + .width = 32, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 222, + .width = 8, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 230, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 231, + .width = 1, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 232, + .width = 8, + }, + [VCAP_KF_IP_PAYLOAD_5TUPLE] = { + .type = VCAP_FIELD_U32, + .offset = 240, + .width = 32, + }, +}; + +static const struct vcap_field is0_pure_5tuple_ip4_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 12, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 21, + .width = 6, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 59, + .width = 32, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 8, + }, + [VCAP_KF_IP_PAYLOAD_5TUPLE] = { + .type = VCAP_FIELD_U32, + .offset = 107, + .width = 32, + }, +}; + +static const struct vcap_field is0_etag_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 7, + }, + [VCAP_KF_8021BR_E_TAGGED] = { + .type = VCAP_FIELD_BIT, + .offset = 10, + .width = 1, + }, + [VCAP_KF_8021BR_GRP] = { + .type = VCAP_FIELD_U32, + .offset = 11, + .width = 2, + }, + [VCAP_KF_8021BR_ECID_EXT] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 8, + }, + [VCAP_KF_8021BR_ECID_BASE] = { + .type = VCAP_FIELD_U32, + .offset = 21, + .width = 12, + }, + [VCAP_KF_8021BR_IGR_ECID_EXT] = { + .type = VCAP_FIELD_U32, + .offset = 33, + .width = 8, + }, + [VCAP_KF_8021BR_IGR_ECID_BASE] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 12, + }, +}; + +static const struct vcap_field is2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 90, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 138, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 186, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 187, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 203, + .width = 64, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 267, + .width = 16, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 283, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 284, + .width = 1, + }, +}; + +static const struct vcap_field is2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 86, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 134, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 135, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 136, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 137, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 138, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 139, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 140, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 142, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 174, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 206, + .width = 1, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 207, + .width = 16, + }, +}; + +static const struct vcap_field is2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 136, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 169, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 170, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 186, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 202, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 220, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 221, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 222, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 223, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 224, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 225, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 226, + .width = 64, + }, +}; + +static const struct vcap_field is2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 136, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 169, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 177, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 193, + .width = 96, + }, +}; + +static const struct vcap_field is2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 56, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 91, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 220, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 228, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U48, + .offset = 244, + .width = 40, + }, +}; + +static const struct vcap_field is2_ip_7tuple_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 18, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 86, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 112, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 113, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 116, + .width = 1, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 117, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 118, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 119, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 120, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 121, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 169, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 217, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 219, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 227, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 355, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 483, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 484, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 485, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 486, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 502, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 518, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 534, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 535, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 536, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 537, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 538, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 539, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 540, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 541, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 542, + .width = 64, + }, +}; + +static const struct vcap_field is2_ip6_vid_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 12, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 13, + }, + [VCAP_KF_L3_SMAC_SIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_KF_L3_DMAC_DIP_MATCH] = { + .type = VCAP_FIELD_BIT, + .offset = 40, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 41, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 42, + .width = 1, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 43, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 171, + .width = 128, + }, +}; + +static const struct vcap_field es2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 99, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 147, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 195, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 196, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 212, + .width = 64, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 276, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 277, + .width = 1, + }, +}; + +static const struct vcap_field es2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 96, + .width = 2, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 98, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 147, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 148, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 149, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 151, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 152, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 154, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 186, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, +}; + +static const struct vcap_field es2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 100, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 102, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 103, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 144, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 176, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 177, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 178, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 194, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 210, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 226, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 227, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 228, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 229, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 230, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 231, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 232, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 233, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 234, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 100, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 102, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 103, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 144, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 176, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 177, + .width = 8, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 185, + .width = 96, + }, +}; + +static const struct vcap_field es2_ip_7tuple_keyfield[] = { + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 10, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 39, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 74, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 75, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 94, + .width = 2, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 96, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 144, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 192, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 193, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 194, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 202, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 330, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 458, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 459, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 460, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 461, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 477, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 493, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 509, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 510, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 511, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 512, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 513, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 514, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 515, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 516, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 517, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip4_vid_keyfield[] = { + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 10, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 13, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 39, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 42, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 43, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 47, + .width = 1, + }, + [VCAP_KF_ES0_ISDX_KEY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 48, + .width = 1, + }, + [VCAP_KF_MIRROR_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 49, + .width = 2, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 51, + .width = 1, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 52, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 32, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 116, + .width = 16, + }, +}; + +static const struct vcap_field es2_ip6_vid_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_ACL_GRP_ID] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 8, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 42, + .width = 1, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 43, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 171, + .width = 128, + }, +}; + +/* keyfield_set */ +static const struct vcap_set is0_keyfield_set[] = { + [VCAP_KFS_MLL] = { + .type_id = 0, + .sw_per_item = 3, + .sw_cnt = 4, + }, + [VCAP_KFS_TRI_VID] = { + .type_id = 0, + .sw_per_item = 2, + .sw_cnt = 6, + }, + [VCAP_KFS_LL_FULL] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_NORMAL] = { + .type_id = 1, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_NORMAL_7TUPLE] = { + .type_id = 0, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_NORMAL_5TUPLE_IP4] = { + .type_id = 2, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_PURE_5TUPLE_IP4] = { + .type_id = 2, + .sw_per_item = 3, + .sw_cnt = 4, + }, + [VCAP_KFS_ETAG] = { + .type_id = 3, + .sw_per_item = 2, + .sw_cnt = 6, + }, +}; + +static const struct vcap_set is2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 4, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 5, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 6, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = 1, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_IP6_VID] = { + .type_id = 9, + .sw_per_item = 6, + .sw_cnt = 2, + }, +}; + +static const struct vcap_set es2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 1, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 2, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = -1, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_IP4_VID] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, + [VCAP_KFS_IP6_VID] = { + .type_id = 5, + .sw_per_item = 6, + .sw_cnt = 2, + }, +}; + +/* keyfield_set map */ +static const struct vcap_field *is0_keyfield_set_map[] = { + [VCAP_KFS_MLL] = is0_mll_keyfield, + [VCAP_KFS_TRI_VID] = is0_tri_vid_keyfield, + [VCAP_KFS_LL_FULL] = is0_ll_full_keyfield, + [VCAP_KFS_NORMAL] = is0_normal_keyfield, + [VCAP_KFS_NORMAL_7TUPLE] = is0_normal_7tuple_keyfield, + [VCAP_KFS_NORMAL_5TUPLE_IP4] = is0_normal_5tuple_ip4_keyfield, + [VCAP_KFS_PURE_5TUPLE_IP4] = is0_pure_5tuple_ip4_keyfield, + [VCAP_KFS_ETAG] = is0_etag_keyfield, +}; + +static const struct vcap_field *is2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = is2_mac_etype_keyfield, + [VCAP_KFS_ARP] = is2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = is2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = is2_ip4_other_keyfield, + [VCAP_KFS_IP6_STD] = is2_ip6_std_keyfield, + [VCAP_KFS_IP_7TUPLE] = is2_ip_7tuple_keyfield, + [VCAP_KFS_IP6_VID] = is2_ip6_vid_keyfield, +}; + +static const struct vcap_field *es2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = es2_mac_etype_keyfield, + [VCAP_KFS_ARP] = es2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = es2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = es2_ip4_other_keyfield, + [VCAP_KFS_IP_7TUPLE] = es2_ip_7tuple_keyfield, + [VCAP_KFS_IP4_VID] = es2_ip4_vid_keyfield, + [VCAP_KFS_IP6_VID] = es2_ip6_vid_keyfield, +}; + +/* keyfield_set map sizes */ +static int is0_keyfield_set_map_size[] = { + [VCAP_KFS_MLL] = ARRAY_SIZE(is0_mll_keyfield), + [VCAP_KFS_TRI_VID] = ARRAY_SIZE(is0_tri_vid_keyfield), + [VCAP_KFS_LL_FULL] = ARRAY_SIZE(is0_ll_full_keyfield), + [VCAP_KFS_NORMAL] = ARRAY_SIZE(is0_normal_keyfield), + [VCAP_KFS_NORMAL_7TUPLE] = ARRAY_SIZE(is0_normal_7tuple_keyfield), + [VCAP_KFS_NORMAL_5TUPLE_IP4] = ARRAY_SIZE(is0_normal_5tuple_ip4_keyfield), + [VCAP_KFS_PURE_5TUPLE_IP4] = ARRAY_SIZE(is0_pure_5tuple_ip4_keyfield), + [VCAP_KFS_ETAG] = ARRAY_SIZE(is0_etag_keyfield), +}; + +static int is2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(is2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(is2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(is2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(is2_ip4_other_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(is2_ip6_std_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(is2_ip_7tuple_keyfield), + [VCAP_KFS_IP6_VID] = ARRAY_SIZE(is2_ip6_vid_keyfield), +}; + +static int es2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(es2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(es2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(es2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(es2_ip4_other_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(es2_ip_7tuple_keyfield), + [VCAP_KFS_IP4_VID] = ARRAY_SIZE(es2_ip4_vid_keyfield), + [VCAP_KFS_IP6_VID] = ARRAY_SIZE(es2_ip6_vid_keyfield), +}; + +/* actionfields */ +static const struct vcap_field is0_mlbs_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_COSID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_COSID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 3, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 5, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 6, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 2, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 3, + }, + [VCAP_AF_MAP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 9, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 3, + }, + [VCAP_AF_GVID_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 32, + .width = 13, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 45, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 46, + .width = 12, + }, + [VCAP_AF_FWD_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 58, + .width = 1, + }, + [VCAP_AF_CPU_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 59, + .width = 1, + }, + [VCAP_AF_CPU_Q] = { + .type = VCAP_FIELD_U32, + .offset = 60, + .width = 3, + }, + [VCAP_AF_OAM_Y1731_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 63, + .width = 3, + }, + [VCAP_AF_OAM_TWAMP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 66, + .width = 1, + }, + [VCAP_AF_OAM_IP_BFD_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 67, + .width = 1, + }, + [VCAP_AF_TC_LABEL] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 3, + }, + [VCAP_AF_TTL_LABEL] = { + .type = VCAP_FIELD_U32, + .offset = 71, + .width = 3, + }, + [VCAP_AF_NUM_VLD_LABELS] = { + .type = VCAP_FIELD_U32, + .offset = 74, + .width = 2, + }, + [VCAP_AF_FWD_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 76, + .width = 3, + }, + [VCAP_AF_MPLS_OAM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 79, + .width = 3, + }, + [VCAP_AF_MPLS_MEP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 82, + .width = 1, + }, + [VCAP_AF_MPLS_MIP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_AF_MPLS_OAM_FLAVOR] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_AF_MPLS_IP_CTRL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_AF_PAG_OVERRIDE_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 86, + .width = 8, + }, + [VCAP_AF_PAG_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 94, + .width = 8, + }, + [VCAP_AF_S2_KEY_SEL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 102, + .width = 1, + }, + [VCAP_AF_S2_KEY_SEL_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 103, + .width = 6, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 109, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 111, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 5, + }, + [VCAP_AF_NXT_KEY_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 117, + .width = 5, + }, + [VCAP_AF_NXT_NORM_W16_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 122, + .width = 5, + }, + [VCAP_AF_NXT_OFFSET_FROM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 2, + }, + [VCAP_AF_NXT_TYPE_AFTER_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 129, + .width = 2, + }, + [VCAP_AF_NXT_NORMALIZE] = { + .type = VCAP_FIELD_BIT, + .offset = 131, + .width = 1, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 132, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 135, + .width = 12, + }, +}; + +static const struct vcap_field is0_mlbs_reduced_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_COSID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_COSID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 3, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 5, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 6, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 2, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 2, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 15, + .width = 12, + }, + [VCAP_AF_FWD_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 27, + .width = 1, + }, + [VCAP_AF_CPU_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_AF_CPU_Q] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 3, + }, + [VCAP_AF_TC_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 32, + .width = 1, + }, + [VCAP_AF_TTL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 33, + .width = 1, + }, + [VCAP_AF_FWD_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 34, + .width = 3, + }, + [VCAP_AF_MPLS_OAM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 37, + .width = 3, + }, + [VCAP_AF_MPLS_MEP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 40, + .width = 1, + }, + [VCAP_AF_MPLS_MIP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 41, + .width = 1, + }, + [VCAP_AF_MPLS_OAM_FLAVOR] = { + .type = VCAP_FIELD_BIT, + .offset = 42, + .width = 1, + }, + [VCAP_AF_MPLS_IP_CTRL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 43, + .width = 1, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT_REDUCED] = { + .type = VCAP_FIELD_U32, + .offset = 47, + .width = 3, + }, + [VCAP_AF_NXT_KEY_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 50, + .width = 5, + }, + [VCAP_AF_NXT_NORM_W32_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 55, + .width = 2, + }, + [VCAP_AF_NXT_TYPE_AFTER_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 2, + }, + [VCAP_AF_NXT_NORMALIZE] = { + .type = VCAP_FIELD_BIT, + .offset = 59, + .width = 1, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 60, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 63, + .width = 12, + }, +}; + +static const struct vcap_field is0_classification_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_DSCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_DSCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 6, + }, + [VCAP_AF_COSID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 8, + .width = 1, + }, + [VCAP_AF_COSID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 9, + .width = 3, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 16, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_AF_DEI_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_AF_DEI_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_AF_PCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 21, + .width = 1, + }, + [VCAP_AF_PCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 22, + .width = 3, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_MAP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 30, + .width = 9, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 39, + .width = 3, + }, + [VCAP_AF_GVID_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 13, + }, + [VCAP_AF_VLAN_POP_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 58, + .width = 1, + }, + [VCAP_AF_VLAN_POP_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 59, + .width = 2, + }, + [VCAP_AF_VLAN_PUSH_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 61, + .width = 1, + }, + [VCAP_AF_VLAN_PUSH_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 62, + .width = 2, + }, + [VCAP_AF_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 64, + .width = 2, + }, + [VCAP_AF_VLAN_WAS_TAGGED] = { + .type = VCAP_FIELD_U32, + .offset = 66, + .width = 2, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 68, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 69, + .width = 12, + }, + [VCAP_AF_RT_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 2, + }, + [VCAP_AF_LPM_AFFIX_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_AF_LPM_AFFIX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 10, + }, + [VCAP_AF_RLEG_DMAC_CHK_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_AF_TTL_DECR_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_AF_L3_MAC_UPDATE_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_AF_FWD_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 97, + .width = 1, + }, + [VCAP_AF_CPU_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 98, + .width = 1, + }, + [VCAP_AF_CPU_Q] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 3, + }, + [VCAP_AF_MIP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 102, + .width = 2, + }, + [VCAP_AF_OAM_Y1731_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 3, + }, + [VCAP_AF_OAM_TWAMP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 107, + .width = 1, + }, + [VCAP_AF_OAM_IP_BFD_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 108, + .width = 1, + }, + [VCAP_AF_PAG_OVERRIDE_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 109, + .width = 8, + }, + [VCAP_AF_PAG_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 117, + .width = 8, + }, + [VCAP_AF_S2_KEY_SEL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 125, + .width = 1, + }, + [VCAP_AF_S2_KEY_SEL_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 126, + .width = 6, + }, + [VCAP_AF_INJ_MASQ_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 132, + .width = 1, + }, + [VCAP_AF_INJ_MASQ_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 133, + .width = 7, + }, + [VCAP_AF_LPORT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 140, + .width = 1, + }, + [VCAP_AF_INJ_MASQ_LPORT] = { + .type = VCAP_FIELD_U32, + .offset = 141, + .width = 7, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 148, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 151, + .width = 5, + }, + [VCAP_AF_NXT_KEY_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 156, + .width = 5, + }, + [VCAP_AF_NXT_NORM_W16_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 161, + .width = 5, + }, + [VCAP_AF_NXT_OFFSET_FROM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 166, + .width = 2, + }, + [VCAP_AF_NXT_TYPE_AFTER_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 168, + .width = 2, + }, + [VCAP_AF_NXT_NORMALIZE] = { + .type = VCAP_FIELD_BIT, + .offset = 170, + .width = 1, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 171, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 174, + .width = 12, + }, +}; + +static const struct vcap_field is0_full_actionfield[] = { + [VCAP_AF_DSCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_DSCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 6, + }, + [VCAP_AF_COSID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 7, + .width = 1, + }, + [VCAP_AF_COSID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 8, + .width = 3, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_AF_DEI_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 18, + .width = 1, + }, + [VCAP_AF_DEI_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_AF_PCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_AF_PCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 21, + .width = 3, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 24, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 3, + }, + [VCAP_AF_MAP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 9, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 38, + .width = 3, + }, + [VCAP_AF_GVID_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 13, + }, + [VCAP_AF_VLAN_POP_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 57, + .width = 1, + }, + [VCAP_AF_VLAN_POP_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 58, + .width = 2, + }, + [VCAP_AF_VLAN_PUSH_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 60, + .width = 1, + }, + [VCAP_AF_VLAN_PUSH_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 61, + .width = 2, + }, + [VCAP_AF_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 63, + .width = 2, + }, + [VCAP_AF_VLAN_WAS_TAGGED] = { + .type = VCAP_FIELD_U32, + .offset = 65, + .width = 2, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 67, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 68, + .width = 12, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 80, + .width = 3, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 83, + .width = 65, + }, + [VCAP_AF_RT_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 148, + .width = 2, + }, + [VCAP_AF_LPM_AFFIX_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_AF_LPM_AFFIX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 151, + .width = 10, + }, + [VCAP_AF_RLEG_DMAC_CHK_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 161, + .width = 1, + }, + [VCAP_AF_TTL_DECR_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 162, + .width = 1, + }, + [VCAP_AF_L3_MAC_UPDATE_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 163, + .width = 1, + }, + [VCAP_AF_CPU_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 164, + .width = 1, + }, + [VCAP_AF_CPU_Q] = { + .type = VCAP_FIELD_U32, + .offset = 165, + .width = 3, + }, + [VCAP_AF_MIP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 168, + .width = 2, + }, + [VCAP_AF_OAM_Y1731_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 170, + .width = 3, + }, + [VCAP_AF_OAM_TWAMP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 173, + .width = 1, + }, + [VCAP_AF_OAM_IP_BFD_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 174, + .width = 1, + }, + [VCAP_AF_RSVD_LBL_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 175, + .width = 4, + }, + [VCAP_AF_TC_LABEL] = { + .type = VCAP_FIELD_U32, + .offset = 179, + .width = 3, + }, + [VCAP_AF_TTL_LABEL] = { + .type = VCAP_FIELD_U32, + .offset = 182, + .width = 3, + }, + [VCAP_AF_NUM_VLD_LABELS] = { + .type = VCAP_FIELD_U32, + .offset = 185, + .width = 2, + }, + [VCAP_AF_FWD_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 187, + .width = 3, + }, + [VCAP_AF_MPLS_OAM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 190, + .width = 3, + }, + [VCAP_AF_MPLS_MEP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 193, + .width = 1, + }, + [VCAP_AF_MPLS_MIP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 194, + .width = 1, + }, + [VCAP_AF_MPLS_OAM_FLAVOR] = { + .type = VCAP_FIELD_BIT, + .offset = 195, + .width = 1, + }, + [VCAP_AF_MPLS_IP_CTRL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 196, + .width = 1, + }, + [VCAP_AF_CUSTOM_ACE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 197, + .width = 5, + }, + [VCAP_AF_CUSTOM_ACE_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 202, + .width = 2, + }, + [VCAP_AF_PAG_OVERRIDE_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 204, + .width = 8, + }, + [VCAP_AF_PAG_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 212, + .width = 8, + }, + [VCAP_AF_S2_KEY_SEL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 220, + .width = 1, + }, + [VCAP_AF_S2_KEY_SEL_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 221, + .width = 6, + }, + [VCAP_AF_INJ_MASQ_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 227, + .width = 1, + }, + [VCAP_AF_INJ_MASQ_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 228, + .width = 7, + }, + [VCAP_AF_LPORT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 235, + .width = 1, + }, + [VCAP_AF_INJ_MASQ_LPORT] = { + .type = VCAP_FIELD_U32, + .offset = 236, + .width = 7, + }, + [VCAP_AF_MATCH_ID] = { + .type = VCAP_FIELD_U32, + .offset = 243, + .width = 16, + }, + [VCAP_AF_MATCH_ID_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 259, + .width = 16, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 275, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 277, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 278, + .width = 5, + }, + [VCAP_AF_NXT_KEY_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 283, + .width = 5, + }, + [VCAP_AF_NXT_NORM_W16_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 288, + .width = 5, + }, + [VCAP_AF_NXT_OFFSET_FROM_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 293, + .width = 2, + }, + [VCAP_AF_NXT_TYPE_AFTER_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 295, + .width = 2, + }, + [VCAP_AF_NXT_NORMALIZE] = { + .type = VCAP_FIELD_BIT, + .offset = 297, + .width = 1, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 298, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 301, + .width = 12, + }, +}; + +static const struct vcap_field is0_class_reduced_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_COSID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_COSID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 3, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 5, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 6, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 2, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 3, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 3, + }, + [VCAP_AF_GVID_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 23, + .width = 13, + }, + [VCAP_AF_VLAN_POP_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 36, + .width = 1, + }, + [VCAP_AF_VLAN_POP_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 37, + .width = 2, + }, + [VCAP_AF_VLAN_PUSH_CNT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 39, + .width = 1, + }, + [VCAP_AF_VLAN_PUSH_CNT] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 2, + }, + [VCAP_AF_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 2, + }, + [VCAP_AF_VLAN_WAS_TAGGED] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 2, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 47, + .width = 12, + }, + [VCAP_AF_FWD_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 59, + .width = 1, + }, + [VCAP_AF_CPU_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 60, + .width = 1, + }, + [VCAP_AF_CPU_Q] = { + .type = VCAP_FIELD_U32, + .offset = 61, + .width = 3, + }, + [VCAP_AF_MIP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 64, + .width = 2, + }, + [VCAP_AF_OAM_Y1731_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 66, + .width = 3, + }, + [VCAP_AF_LPORT_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 69, + .width = 1, + }, + [VCAP_AF_INJ_MASQ_LPORT] = { + .type = VCAP_FIELD_U32, + .offset = 70, + .width = 7, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 79, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 80, + .width = 5, + }, + [VCAP_AF_NXT_KEY_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 85, + .width = 5, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 90, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 93, + .width = 12, + }, +}; + +static const struct vcap_field is2_base_type_actionfield[] = { + [VCAP_AF_IS_INNER_ACL] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 5, + }, + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 7, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 8, + .width = 1, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 3, + }, + [VCAP_AF_CPU_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_AF_LRN_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_AF_RT_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 16, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 6, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_AF_DLB_OFFSET] = { + .type = VCAP_FIELD_U32, + .offset = 24, + .width = 3, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 30, + .width = 68, + }, + [VCAP_AF_RSDX_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 98, + .width = 1, + }, + [VCAP_AF_RSDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 99, + .width = 12, + }, + [VCAP_AF_MIRROR_PROBE] = { + .type = VCAP_FIELD_U32, + .offset = 111, + .width = 2, + }, + [VCAP_AF_REW_CMD] = { + .type = VCAP_FIELD_U32, + .offset = 113, + .width = 11, + }, + [VCAP_AF_TTL_UPDATE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 124, + .width = 1, + }, + [VCAP_AF_SAM_SEQ_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 125, + .width = 1, + }, + [VCAP_AF_TCP_UDP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 126, + .width = 1, + }, + [VCAP_AF_TCP_UDP_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 16, + }, + [VCAP_AF_TCP_UDP_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 143, + .width = 16, + }, + [VCAP_AF_MATCH_ID] = { + .type = VCAP_FIELD_U32, + .offset = 159, + .width = 16, + }, + [VCAP_AF_MATCH_ID_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 175, + .width = 16, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 191, + .width = 12, + }, + [VCAP_AF_SWAP_MAC_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 203, + .width = 1, + }, + [VCAP_AF_ACL_RT_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 204, + .width = 4, + }, + [VCAP_AF_ACL_MAC] = { + .type = VCAP_FIELD_U48, + .offset = 208, + .width = 48, + }, + [VCAP_AF_DMAC_OFFSET_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 256, + .width = 1, + }, + [VCAP_AF_PTP_MASTER_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 257, + .width = 2, + }, + [VCAP_AF_LOG_MSG_INTERVAL] = { + .type = VCAP_FIELD_U32, + .offset = 259, + .width = 4, + }, + [VCAP_AF_SIP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 263, + .width = 5, + }, + [VCAP_AF_RLEG_STAT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 268, + .width = 3, + }, + [VCAP_AF_IGR_ACL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 271, + .width = 1, + }, + [VCAP_AF_EGR_ACL_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 272, + .width = 1, + }, +}; + +static const struct vcap_field es2_base_type_actionfield[] = { + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_FWD_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 2, + }, + [VCAP_AF_COPY_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 16, + }, + [VCAP_AF_COPY_PORT_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 7, + }, + [VCAP_AF_MIRROR_PROBE_ID] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 2, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 29, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 30, + .width = 3, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 33, + .width = 1, + }, + [VCAP_AF_POLICE_REMARK] = { + .type = VCAP_FIELD_BIT, + .offset = 34, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 35, + .width = 6, + }, + [VCAP_AF_ES2_REW_CMD] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 11, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, +}; + +/* actionfield_set */ +static const struct vcap_set is0_actionfield_set[] = { + [VCAP_AFS_MLBS] = { + .type_id = 0, + .sw_per_item = 2, + .sw_cnt = 6, + }, + [VCAP_AFS_MLBS_REDUCED] = { + .type_id = 0, + .sw_per_item = 1, + .sw_cnt = 12, + }, + [VCAP_AFS_CLASSIFICATION] = { + .type_id = 1, + .sw_per_item = 2, + .sw_cnt = 6, + }, + [VCAP_AFS_FULL] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, + [VCAP_AFS_CLASS_REDUCED] = { + .type_id = 1, + .sw_per_item = 1, + .sw_cnt = 12, + }, +}; + +static const struct vcap_set is2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + +static const struct vcap_set es2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + +/* actionfield_set map */ +static const struct vcap_field *is0_actionfield_set_map[] = { + [VCAP_AFS_MLBS] = is0_mlbs_actionfield, + [VCAP_AFS_MLBS_REDUCED] = is0_mlbs_reduced_actionfield, + [VCAP_AFS_CLASSIFICATION] = is0_classification_actionfield, + [VCAP_AFS_FULL] = is0_full_actionfield, + [VCAP_AFS_CLASS_REDUCED] = is0_class_reduced_actionfield, +}; + +static const struct vcap_field *is2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = is2_base_type_actionfield, +}; + +static const struct vcap_field *es2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = es2_base_type_actionfield, +}; + +/* actionfield_set map size */ +static int is0_actionfield_set_map_size[] = { + [VCAP_AFS_MLBS] = ARRAY_SIZE(is0_mlbs_actionfield), + [VCAP_AFS_MLBS_REDUCED] = ARRAY_SIZE(is0_mlbs_reduced_actionfield), + [VCAP_AFS_CLASSIFICATION] = ARRAY_SIZE(is0_classification_actionfield), + [VCAP_AFS_FULL] = ARRAY_SIZE(is0_full_actionfield), + [VCAP_AFS_CLASS_REDUCED] = ARRAY_SIZE(is0_class_reduced_actionfield), +}; + +static int is2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(is2_base_type_actionfield), +}; + +static int es2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(es2_base_type_actionfield), +}; + +/* Type Groups */ +static const struct vcap_typegroup is0_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 5, + .value = 16, + }, + { + .offset = 52, + .width = 1, + .value = 0, + }, + { + .offset = 104, + .width = 2, + .value = 0, + }, + { + .offset = 156, + .width = 3, + .value = 0, + }, + { + .offset = 208, + .width = 2, + .value = 0, + }, + { + .offset = 260, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 4, + .value = 0, + }, + { + .offset = 364, + .width = 1, + .value = 0, + }, + { + .offset = 416, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 3, + .value = 0, + }, + { + .offset = 520, + .width = 2, + .value = 0, + }, + { + .offset = 572, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 4, + .value = 8, + }, + { + .offset = 52, + .width = 1, + .value = 0, + }, + { + .offset = 104, + .width = 2, + .value = 0, + }, + { + .offset = 156, + .width = 3, + .value = 0, + }, + { + .offset = 208, + .width = 2, + .value = 0, + }, + { + .offset = 260, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x3_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 52, + .width = 2, + .value = 0, + }, + { + .offset = 104, + .width = 2, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x2_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 52, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is2_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x3_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 1, + .value = 1, + }, + {} +}; + +static const struct vcap_typegroup es2_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is0_keyfield_set_typegroups[] = { + [12] = is0_x12_keyfield_set_typegroups, + [6] = is0_x6_keyfield_set_typegroups, + [3] = is0_x3_keyfield_set_typegroups, + [2] = is0_x2_keyfield_set_typegroups, + [1] = is0_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *is2_keyfield_set_typegroups[] = { + [12] = is2_x12_keyfield_set_typegroups, + [6] = is2_x6_keyfield_set_typegroups, + [3] = is2_x3_keyfield_set_typegroups, + [1] = is2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *es2_keyfield_set_typegroups[] = { + [12] = es2_x12_keyfield_set_typegroups, + [6] = es2_x6_keyfield_set_typegroups, + [3] = es2_x3_keyfield_set_typegroups, + [1] = es2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup is0_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 110, + .width = 2, + .value = 0, + }, + { + .offset = 220, + .width = 2, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x2_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 110, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x1_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 1, + .value = 1, + }, + {} +}; + +static const struct vcap_typegroup is2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 110, + .width = 1, + .value = 0, + }, + { + .offset = 220, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 21, + .width = 1, + .value = 0, + }, + { + .offset = 42, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is0_actionfield_set_typegroups[] = { + [3] = is0_x3_actionfield_set_typegroups, + [2] = is0_x2_actionfield_set_typegroups, + [1] = is0_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *is2_actionfield_set_typegroups[] = { + [3] = is2_x3_actionfield_set_typegroups, + [1] = is2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *es2_actionfield_set_typegroups[] = { + [3] = es2_x3_actionfield_set_typegroups, + [1] = es2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +/* Keyfieldset names */ +static const char * const vcap_keyfield_set_names[] = { + [VCAP_KFS_NO_VALUE] = "(None)", + [VCAP_KFS_ARP] = "VCAP_KFS_ARP", + [VCAP_KFS_ETAG] = "VCAP_KFS_ETAG", + [VCAP_KFS_IP4_OTHER] = "VCAP_KFS_IP4_OTHER", + [VCAP_KFS_IP4_TCP_UDP] = "VCAP_KFS_IP4_TCP_UDP", + [VCAP_KFS_IP4_VID] = "VCAP_KFS_IP4_VID", + [VCAP_KFS_IP6_STD] = "VCAP_KFS_IP6_STD", + [VCAP_KFS_IP6_VID] = "VCAP_KFS_IP6_VID", + [VCAP_KFS_IP_7TUPLE] = "VCAP_KFS_IP_7TUPLE", + [VCAP_KFS_LL_FULL] = "VCAP_KFS_LL_FULL", + [VCAP_KFS_MAC_ETYPE] = "VCAP_KFS_MAC_ETYPE", + [VCAP_KFS_MLL] = "VCAP_KFS_MLL", + [VCAP_KFS_NORMAL] = "VCAP_KFS_NORMAL", + [VCAP_KFS_NORMAL_5TUPLE_IP4] = "VCAP_KFS_NORMAL_5TUPLE_IP4", + [VCAP_KFS_NORMAL_7TUPLE] = "VCAP_KFS_NORMAL_7TUPLE", + [VCAP_KFS_PURE_5TUPLE_IP4] = "VCAP_KFS_PURE_5TUPLE_IP4", + [VCAP_KFS_TRI_VID] = "VCAP_KFS_TRI_VID", +}; + +/* Actionfieldset names */ +static const char * const vcap_actionfield_set_names[] = { + [VCAP_AFS_NO_VALUE] = "(None)", + [VCAP_AFS_BASE_TYPE] = "VCAP_AFS_BASE_TYPE", + [VCAP_AFS_CLASSIFICATION] = "VCAP_AFS_CLASSIFICATION", + [VCAP_AFS_CLASS_REDUCED] = "VCAP_AFS_CLASS_REDUCED", + [VCAP_AFS_FULL] = "VCAP_AFS_FULL", + [VCAP_AFS_MLBS] = "VCAP_AFS_MLBS", + [VCAP_AFS_MLBS_REDUCED] = "VCAP_AFS_MLBS_REDUCED", +}; + +/* Keyfield names */ +static const char * const vcap_keyfield_names[] = { + [VCAP_KF_NO_VALUE] = "(None)", + [VCAP_KF_8021BR_ECID_BASE] = "8021BR_ECID_BASE", + [VCAP_KF_8021BR_ECID_EXT] = "8021BR_ECID_EXT", + [VCAP_KF_8021BR_E_TAGGED] = "8021BR_E_TAGGED", + [VCAP_KF_8021BR_GRP] = "8021BR_GRP", + [VCAP_KF_8021BR_IGR_ECID_BASE] = "8021BR_IGR_ECID_BASE", + [VCAP_KF_8021BR_IGR_ECID_EXT] = "8021BR_IGR_ECID_EXT", + [VCAP_KF_8021Q_DEI0] = "8021Q_DEI0", + [VCAP_KF_8021Q_DEI1] = "8021Q_DEI1", + [VCAP_KF_8021Q_DEI2] = "8021Q_DEI2", + [VCAP_KF_8021Q_DEI_CLS] = "8021Q_DEI_CLS", + [VCAP_KF_8021Q_PCP0] = "8021Q_PCP0", + [VCAP_KF_8021Q_PCP1] = "8021Q_PCP1", + [VCAP_KF_8021Q_PCP2] = "8021Q_PCP2", + [VCAP_KF_8021Q_PCP_CLS] = "8021Q_PCP_CLS", + [VCAP_KF_8021Q_TPID0] = "8021Q_TPID0", + [VCAP_KF_8021Q_TPID1] = "8021Q_TPID1", + [VCAP_KF_8021Q_TPID2] = "8021Q_TPID2", + [VCAP_KF_8021Q_VID0] = "8021Q_VID0", + [VCAP_KF_8021Q_VID1] = "8021Q_VID1", + [VCAP_KF_8021Q_VID2] = "8021Q_VID2", + [VCAP_KF_8021Q_VID_CLS] = "8021Q_VID_CLS", + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = "8021Q_VLAN_TAGGED_IS", + [VCAP_KF_8021Q_VLAN_TAGS] = "8021Q_VLAN_TAGS", + [VCAP_KF_ACL_GRP_ID] = "ACL_GRP_ID", + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = "ARP_ADDR_SPACE_OK_IS", + [VCAP_KF_ARP_LEN_OK_IS] = "ARP_LEN_OK_IS", + [VCAP_KF_ARP_OPCODE] = "ARP_OPCODE", + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = "ARP_OPCODE_UNKNOWN_IS", + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = "ARP_PROTO_SPACE_OK_IS", + [VCAP_KF_ARP_SENDER_MATCH_IS] = "ARP_SENDER_MATCH_IS", + [VCAP_KF_ARP_TGT_MATCH_IS] = "ARP_TGT_MATCH_IS", + [VCAP_KF_COSID_CLS] = "COSID_CLS", + [VCAP_KF_DST_ENTRY] = "DST_ENTRY", + [VCAP_KF_ES0_ISDX_KEY_ENA] = "ES0_ISDX_KEY_ENA", + [VCAP_KF_ETYPE] = "ETYPE", + [VCAP_KF_ETYPE_LEN_IS] = "ETYPE_LEN_IS", + [VCAP_KF_ETYPE_MPLS] = "ETYPE_MPLS", + [VCAP_KF_IF_EGR_PORT_MASK] = "IF_EGR_PORT_MASK", + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = "IF_EGR_PORT_MASK_RNG", + [VCAP_KF_IF_IGR_PORT] = "IF_IGR_PORT", + [VCAP_KF_IF_IGR_PORT_MASK] = "IF_IGR_PORT_MASK", + [VCAP_KF_IF_IGR_PORT_MASK_L3] = "IF_IGR_PORT_MASK_L3", + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = "IF_IGR_PORT_MASK_RNG", + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = "IF_IGR_PORT_MASK_SEL", + [VCAP_KF_IF_IGR_PORT_SEL] = "IF_IGR_PORT_SEL", + [VCAP_KF_IP4_IS] = "IP4_IS", + [VCAP_KF_IP_MC_IS] = "IP_MC_IS", + [VCAP_KF_IP_PAYLOAD_5TUPLE] = "IP_PAYLOAD_5TUPLE", + [VCAP_KF_IP_SNAP_IS] = "IP_SNAP_IS", + [VCAP_KF_ISDX_CLS] = "ISDX_CLS", + [VCAP_KF_ISDX_GT0_IS] = "ISDX_GT0_IS", + [VCAP_KF_L2_BC_IS] = "L2_BC_IS", + [VCAP_KF_L2_DMAC] = "L2_DMAC", + [VCAP_KF_L2_FWD_IS] = "L2_FWD_IS", + [VCAP_KF_L2_MC_IS] = "L2_MC_IS", + [VCAP_KF_L2_PAYLOAD_ETYPE] = "L2_PAYLOAD_ETYPE", + [VCAP_KF_L2_SMAC] = "L2_SMAC", + [VCAP_KF_L3_DIP_EQ_SIP_IS] = "L3_DIP_EQ_SIP_IS", + [VCAP_KF_L3_DMAC_DIP_MATCH] = "L3_DMAC_DIP_MATCH", + [VCAP_KF_L3_DPL_CLS] = "L3_DPL_CLS", + [VCAP_KF_L3_DSCP] = "L3_DSCP", + [VCAP_KF_L3_DST_IS] = "L3_DST_IS", + [VCAP_KF_L3_FRAGMENT_TYPE] = "L3_FRAGMENT_TYPE", + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = "L3_FRAG_INVLD_L4_LEN", + [VCAP_KF_L3_IP4_DIP] = "L3_IP4_DIP", + [VCAP_KF_L3_IP4_SIP] = "L3_IP4_SIP", + [VCAP_KF_L3_IP6_DIP] = "L3_IP6_DIP", + [VCAP_KF_L3_IP6_SIP] = "L3_IP6_SIP", + [VCAP_KF_L3_IP_PROTO] = "L3_IP_PROTO", + [VCAP_KF_L3_OPTIONS_IS] = "L3_OPTIONS_IS", + [VCAP_KF_L3_PAYLOAD] = "L3_PAYLOAD", + [VCAP_KF_L3_RT_IS] = "L3_RT_IS", + [VCAP_KF_L3_SMAC_SIP_MATCH] = "L3_SMAC_SIP_MATCH", + [VCAP_KF_L3_TOS] = "L3_TOS", + [VCAP_KF_L3_TTL_GT0] = "L3_TTL_GT0", + [VCAP_KF_L4_ACK] = "L4_ACK", + [VCAP_KF_L4_DPORT] = "L4_DPORT", + [VCAP_KF_L4_FIN] = "L4_FIN", + [VCAP_KF_L4_PAYLOAD] = "L4_PAYLOAD", + [VCAP_KF_L4_PSH] = "L4_PSH", + [VCAP_KF_L4_RNG] = "L4_RNG", + [VCAP_KF_L4_RST] = "L4_RST", + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = "L4_SEQUENCE_EQ0_IS", + [VCAP_KF_L4_SPORT] = "L4_SPORT", + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = "L4_SPORT_EQ_DPORT_IS", + [VCAP_KF_L4_SYN] = "L4_SYN", + [VCAP_KF_L4_URG] = "L4_URG", + [VCAP_KF_LOOKUP_FIRST_IS] = "LOOKUP_FIRST_IS", + [VCAP_KF_LOOKUP_GEN_IDX] = "LOOKUP_GEN_IDX", + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = "LOOKUP_GEN_IDX_SEL", + [VCAP_KF_LOOKUP_PAG] = "LOOKUP_PAG", + [VCAP_KF_MIRROR_ENA] = "MIRROR_ENA", + [VCAP_KF_OAM_CCM_CNTS_EQ0] = "OAM_CCM_CNTS_EQ0", + [VCAP_KF_OAM_MEL_FLAGS] = "OAM_MEL_FLAGS", + [VCAP_KF_OAM_Y1731_IS] = "OAM_Y1731_IS", + [VCAP_KF_PROT_ACTIVE] = "PROT_ACTIVE", + [VCAP_KF_TCP_IS] = "TCP_IS", + [VCAP_KF_TCP_UDP_IS] = "TCP_UDP_IS", + [VCAP_KF_TYPE] = "TYPE", +}; + +/* Actionfield names */ +static const char * const vcap_actionfield_names[] = { + [VCAP_AF_NO_VALUE] = "(None)", + [VCAP_AF_ACL_MAC] = "ACL_MAC", + [VCAP_AF_ACL_RT_MODE] = "ACL_RT_MODE", + [VCAP_AF_CLS_VID_SEL] = "CLS_VID_SEL", + [VCAP_AF_CNT_ID] = "CNT_ID", + [VCAP_AF_COPY_PORT_NUM] = "COPY_PORT_NUM", + [VCAP_AF_COPY_QUEUE_NUM] = "COPY_QUEUE_NUM", + [VCAP_AF_COSID_ENA] = "COSID_ENA", + [VCAP_AF_COSID_VAL] = "COSID_VAL", + [VCAP_AF_CPU_COPY_ENA] = "CPU_COPY_ENA", + [VCAP_AF_CPU_DIS] = "CPU_DIS", + [VCAP_AF_CPU_ENA] = "CPU_ENA", + [VCAP_AF_CPU_Q] = "CPU_Q", + [VCAP_AF_CPU_QUEUE_NUM] = "CPU_QUEUE_NUM", + [VCAP_AF_CUSTOM_ACE_ENA] = "CUSTOM_ACE_ENA", + [VCAP_AF_CUSTOM_ACE_OFFSET] = "CUSTOM_ACE_OFFSET", + [VCAP_AF_DEI_ENA] = "DEI_ENA", + [VCAP_AF_DEI_VAL] = "DEI_VAL", + [VCAP_AF_DLB_OFFSET] = "DLB_OFFSET", + [VCAP_AF_DMAC_OFFSET_ENA] = "DMAC_OFFSET_ENA", + [VCAP_AF_DP_ENA] = "DP_ENA", + [VCAP_AF_DP_VAL] = "DP_VAL", + [VCAP_AF_DSCP_ENA] = "DSCP_ENA", + [VCAP_AF_DSCP_VAL] = "DSCP_VAL", + [VCAP_AF_EGR_ACL_ENA] = "EGR_ACL_ENA", + [VCAP_AF_ES2_REW_CMD] = "ES2_REW_CMD", + [VCAP_AF_FWD_DIS] = "FWD_DIS", + [VCAP_AF_FWD_MODE] = "FWD_MODE", + [VCAP_AF_FWD_TYPE] = "FWD_TYPE", + [VCAP_AF_GVID_ADD_REPLACE_SEL] = "GVID_ADD_REPLACE_SEL", + [VCAP_AF_HIT_ME_ONCE] = "HIT_ME_ONCE", + [VCAP_AF_IGNORE_PIPELINE_CTRL] = "IGNORE_PIPELINE_CTRL", + [VCAP_AF_IGR_ACL_ENA] = "IGR_ACL_ENA", + [VCAP_AF_INJ_MASQ_ENA] = "INJ_MASQ_ENA", + [VCAP_AF_INJ_MASQ_LPORT] = "INJ_MASQ_LPORT", + [VCAP_AF_INJ_MASQ_PORT] = "INJ_MASQ_PORT", + [VCAP_AF_INTR_ENA] = "INTR_ENA", + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = "ISDX_ADD_REPLACE_SEL", + [VCAP_AF_ISDX_VAL] = "ISDX_VAL", + [VCAP_AF_IS_INNER_ACL] = "IS_INNER_ACL", + [VCAP_AF_L3_MAC_UPDATE_DIS] = "L3_MAC_UPDATE_DIS", + [VCAP_AF_LOG_MSG_INTERVAL] = "LOG_MSG_INTERVAL", + [VCAP_AF_LPM_AFFIX_ENA] = "LPM_AFFIX_ENA", + [VCAP_AF_LPM_AFFIX_VAL] = "LPM_AFFIX_VAL", + [VCAP_AF_LPORT_ENA] = "LPORT_ENA", + [VCAP_AF_LRN_DIS] = "LRN_DIS", + [VCAP_AF_MAP_IDX] = "MAP_IDX", + [VCAP_AF_MAP_KEY] = "MAP_KEY", + [VCAP_AF_MAP_LOOKUP_SEL] = "MAP_LOOKUP_SEL", + [VCAP_AF_MASK_MODE] = "MASK_MODE", + [VCAP_AF_MATCH_ID] = "MATCH_ID", + [VCAP_AF_MATCH_ID_MASK] = "MATCH_ID_MASK", + [VCAP_AF_MIP_SEL] = "MIP_SEL", + [VCAP_AF_MIRROR_PROBE] = "MIRROR_PROBE", + [VCAP_AF_MIRROR_PROBE_ID] = "MIRROR_PROBE_ID", + [VCAP_AF_MPLS_IP_CTRL_ENA] = "MPLS_IP_CTRL_ENA", + [VCAP_AF_MPLS_MEP_ENA] = "MPLS_MEP_ENA", + [VCAP_AF_MPLS_MIP_ENA] = "MPLS_MIP_ENA", + [VCAP_AF_MPLS_OAM_FLAVOR] = "MPLS_OAM_FLAVOR", + [VCAP_AF_MPLS_OAM_TYPE] = "MPLS_OAM_TYPE", + [VCAP_AF_NUM_VLD_LABELS] = "NUM_VLD_LABELS", + [VCAP_AF_NXT_IDX] = "NXT_IDX", + [VCAP_AF_NXT_IDX_CTRL] = "NXT_IDX_CTRL", + [VCAP_AF_NXT_KEY_TYPE] = "NXT_KEY_TYPE", + [VCAP_AF_NXT_NORMALIZE] = "NXT_NORMALIZE", + [VCAP_AF_NXT_NORM_W16_OFFSET] = "NXT_NORM_W16_OFFSET", + [VCAP_AF_NXT_NORM_W32_OFFSET] = "NXT_NORM_W32_OFFSET", + [VCAP_AF_NXT_OFFSET_FROM_TYPE] = "NXT_OFFSET_FROM_TYPE", + [VCAP_AF_NXT_TYPE_AFTER_OFFSET] = "NXT_TYPE_AFTER_OFFSET", + [VCAP_AF_OAM_IP_BFD_ENA] = "OAM_IP_BFD_ENA", + [VCAP_AF_OAM_TWAMP_ENA] = "OAM_TWAMP_ENA", + [VCAP_AF_OAM_Y1731_SEL] = "OAM_Y1731_SEL", + [VCAP_AF_PAG_OVERRIDE_MASK] = "PAG_OVERRIDE_MASK", + [VCAP_AF_PAG_VAL] = "PAG_VAL", + [VCAP_AF_PCP_ENA] = "PCP_ENA", + [VCAP_AF_PCP_VAL] = "PCP_VAL", + [VCAP_AF_PIPELINE_ACT_SEL] = "PIPELINE_ACT_SEL", + [VCAP_AF_PIPELINE_FORCE_ENA] = "PIPELINE_FORCE_ENA", + [VCAP_AF_PIPELINE_PT] = "PIPELINE_PT", + [VCAP_AF_PIPELINE_PT_REDUCED] = "PIPELINE_PT_REDUCED", + [VCAP_AF_POLICE_ENA] = "POLICE_ENA", + [VCAP_AF_POLICE_IDX] = "POLICE_IDX", + [VCAP_AF_POLICE_REMARK] = "POLICE_REMARK", + [VCAP_AF_PORT_MASK] = "PORT_MASK", + [VCAP_AF_PTP_MASTER_SEL] = "PTP_MASTER_SEL", + [VCAP_AF_QOS_ENA] = "QOS_ENA", + [VCAP_AF_QOS_VAL] = "QOS_VAL", + [VCAP_AF_REW_CMD] = "REW_CMD", + [VCAP_AF_RLEG_DMAC_CHK_DIS] = "RLEG_DMAC_CHK_DIS", + [VCAP_AF_RLEG_STAT_IDX] = "RLEG_STAT_IDX", + [VCAP_AF_RSDX_ENA] = "RSDX_ENA", + [VCAP_AF_RSDX_VAL] = "RSDX_VAL", + [VCAP_AF_RSVD_LBL_VAL] = "RSVD_LBL_VAL", + [VCAP_AF_RT_DIS] = "RT_DIS", + [VCAP_AF_RT_SEL] = "RT_SEL", + [VCAP_AF_S2_KEY_SEL_ENA] = "S2_KEY_SEL_ENA", + [VCAP_AF_S2_KEY_SEL_IDX] = "S2_KEY_SEL_IDX", + [VCAP_AF_SAM_SEQ_ENA] = "SAM_SEQ_ENA", + [VCAP_AF_SIP_IDX] = "SIP_IDX", + [VCAP_AF_SWAP_MAC_ENA] = "SWAP_MAC_ENA", + [VCAP_AF_TCP_UDP_DPORT] = "TCP_UDP_DPORT", + [VCAP_AF_TCP_UDP_ENA] = "TCP_UDP_ENA", + [VCAP_AF_TCP_UDP_SPORT] = "TCP_UDP_SPORT", + [VCAP_AF_TC_ENA] = "TC_ENA", + [VCAP_AF_TC_LABEL] = "TC_LABEL", + [VCAP_AF_TPID_SEL] = "TPID_SEL", + [VCAP_AF_TTL_DECR_DIS] = "TTL_DECR_DIS", + [VCAP_AF_TTL_ENA] = "TTL_ENA", + [VCAP_AF_TTL_LABEL] = "TTL_LABEL", + [VCAP_AF_TTL_UPDATE_ENA] = "TTL_UPDATE_ENA", + [VCAP_AF_TYPE] = "TYPE", + [VCAP_AF_VID_VAL] = "VID_VAL", + [VCAP_AF_VLAN_POP_CNT] = "VLAN_POP_CNT", + [VCAP_AF_VLAN_POP_CNT_ENA] = "VLAN_POP_CNT_ENA", + [VCAP_AF_VLAN_PUSH_CNT] = "VLAN_PUSH_CNT", + [VCAP_AF_VLAN_PUSH_CNT_ENA] = "VLAN_PUSH_CNT_ENA", + [VCAP_AF_VLAN_WAS_TAGGED] = "VLAN_WAS_TAGGED", +}; + +/* VCAPs */ +const struct vcap_info kunit_test_vcaps[] = { + [VCAP_TYPE_IS0] = { + .name = "is0", + .rows = 1024, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 110, + .default_cnt = 140, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = is0_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is0_keyfield_set), + .actionfield_set = is0_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is0_actionfield_set), + .keyfield_set_map = is0_keyfield_set_map, + .keyfield_set_map_size = is0_keyfield_set_map_size, + .actionfield_set_map = is0_actionfield_set_map, + .actionfield_set_map_size = is0_actionfield_set_map_size, + .keyfield_set_typegroups = is0_keyfield_set_typegroups, + .actionfield_set_typegroups = is0_actionfield_set_typegroups, + }, + [VCAP_TYPE_IS2] = { + .name = "is2", + .rows = 256, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 110, + .default_cnt = 73, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = is2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is2_keyfield_set), + .actionfield_set = is2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is2_actionfield_set), + .keyfield_set_map = is2_keyfield_set_map, + .keyfield_set_map_size = is2_keyfield_set_map_size, + .actionfield_set_map = is2_actionfield_set_map, + .actionfield_set_map_size = is2_actionfield_set_map_size, + .keyfield_set_typegroups = is2_keyfield_set_typegroups, + .actionfield_set_typegroups = is2_actionfield_set_typegroups, + }, + [VCAP_TYPE_ES2] = { + .name = "es2", + .rows = 1024, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 21, + .default_cnt = 74, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = es2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(es2_keyfield_set), + .actionfield_set = es2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(es2_actionfield_set), + .keyfield_set_map = es2_keyfield_set_map, + .keyfield_set_map_size = es2_keyfield_set_map_size, + .actionfield_set_map = es2_actionfield_set_map, + .actionfield_set_map_size = es2_actionfield_set_map_size, + .keyfield_set_typegroups = es2_keyfield_set_typegroups, + .actionfield_set_typegroups = es2_actionfield_set_typegroups, + }, +}; + +const struct vcap_statistics kunit_test_vcap_stats = { + .name = "kunit_test", + .count = 3, + .keyfield_set_names = vcap_keyfield_set_names, + .actionfield_set_names = vcap_actionfield_set_names, + .keyfield_names = vcap_keyfield_names, + .actionfield_names = vcap_actionfield_names, +}; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.h b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.h new file mode 100644 index 000000000000..b5a74f0eef9b --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP test model interface for kunit testing + */ + +#ifndef __VCAP_MODEL_KUNIT_H__ +#define __VCAP_MODEL_KUNIT_H__ +extern const struct vcap_info kunit_test_vcaps[]; +extern const struct vcap_statistics kunit_test_vcap_stats; +#endif /* __VCAP_MODEL_KUNIT_H__ */ diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index fe4e7a7d9c0b..090e6b983243 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -19,6 +19,7 @@ config MICROSOFT_MANA tristate "Microsoft Azure Network Adapter (MANA) support" depends on PCI_MSI && X86_64 depends on PCI_HYPERV + select AUXILIARY_BUS help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64. diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h deleted file mode 100644 index 65c24ee49efd..000000000000 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ /dev/null @@ -1,692 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _GDMA_H -#define _GDMA_H - -#include <linux/dma-mapping.h> -#include <linux/netdevice.h> - -#include "shm_channel.h" - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -enum gdma_request_type { - GDMA_VERIFY_VF_DRIVER_VERSION = 1, - GDMA_QUERY_MAX_RESOURCES = 2, - GDMA_LIST_DEVICES = 3, - GDMA_REGISTER_DEVICE = 4, - GDMA_DEREGISTER_DEVICE = 5, - GDMA_GENERATE_TEST_EQE = 10, - GDMA_CREATE_QUEUE = 12, - GDMA_DISABLE_QUEUE = 13, - GDMA_CREATE_DMA_REGION = 25, - GDMA_DMA_REGION_ADD_PAGES = 26, - GDMA_DESTROY_DMA_REGION = 27, -}; - -enum gdma_queue_type { - GDMA_INVALID_QUEUE, - GDMA_SQ, - GDMA_RQ, - GDMA_CQ, - GDMA_EQ, -}; - -enum gdma_work_request_flags { - GDMA_WR_NONE = 0, - GDMA_WR_OOB_IN_SGL = BIT(0), - GDMA_WR_PAD_BY_SGE0 = BIT(1), -}; - -enum gdma_eqe_type { - GDMA_EQE_COMPLETION = 3, - GDMA_EQE_TEST_EVENT = 64, - GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, - GDMA_EQE_HWC_INIT_DATA = 130, - GDMA_EQE_HWC_INIT_DONE = 131, -}; - -enum { - GDMA_DEVICE_NONE = 0, - GDMA_DEVICE_HWC = 1, - GDMA_DEVICE_MANA = 2, -}; - -struct gdma_resource { - /* Protect the bitmap */ - spinlock_t lock; - - /* The bitmap size in bits. */ - u32 size; - - /* The bitmap tracks the resources. */ - unsigned long *map; -}; - -union gdma_doorbell_entry { - u64 as_uint64; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 31; - u64 arm : 1; - } cq; - - struct { - u64 id : 24; - u64 wqe_cnt : 8; - u64 tail_ptr : 32; - } rq; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 32; - } sq; - - struct { - u64 id : 16; - u64 reserved : 16; - u64 tail_ptr : 31; - u64 arm : 1; - } eq; -}; /* HW DATA */ - -struct gdma_msg_hdr { - u32 hdr_type; - u32 msg_type; - u16 msg_version; - u16 hwc_msg_id; - u32 msg_size; -}; /* HW DATA */ - -struct gdma_dev_id { - union { - struct { - u16 type; - u16 instance; - }; - - u32 as_uint32; - }; -}; /* HW DATA */ - -struct gdma_req_hdr { - struct gdma_msg_hdr req; - struct gdma_msg_hdr resp; /* The expected response */ - struct gdma_dev_id dev_id; - u32 activity_id; -}; /* HW DATA */ - -struct gdma_resp_hdr { - struct gdma_msg_hdr response; - struct gdma_dev_id dev_id; - u32 activity_id; - u32 status; - u32 reserved; -}; /* HW DATA */ - -struct gdma_general_req { - struct gdma_req_hdr hdr; -}; /* HW DATA */ - -#define GDMA_MESSAGE_V1 1 - -struct gdma_general_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define GDMA_STANDARD_HEADER_TYPE 0 - -static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code, - u32 req_size, u32 resp_size) -{ - hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->req.msg_type = code; - hdr->req.msg_version = GDMA_MESSAGE_V1; - hdr->req.msg_size = req_size; - - hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->resp.msg_type = code; - hdr->resp.msg_version = GDMA_MESSAGE_V1; - hdr->resp.msg_size = resp_size; -} - -/* The 16-byte struct is part of the GDMA work queue entry (WQE). */ -struct gdma_sge { - u64 address; - u32 mem_key; - u32 size; -}; /* HW DATA */ - -struct gdma_wqe_request { - struct gdma_sge *sgl; - u32 num_sge; - - u32 inline_oob_size; - const void *inline_oob_data; - - u32 flags; - u32 client_data_unit; -}; - -enum gdma_page_type { - GDMA_PAGE_TYPE_4K, -}; - -#define GDMA_INVALID_DMA_REGION 0 - -struct gdma_mem_info { - struct device *dev; - - dma_addr_t dma_handle; - void *virt_addr; - u64 length; - - /* Allocated by the PF driver */ - u64 gdma_region; -}; - -#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 - -struct gdma_dev { - struct gdma_context *gdma_context; - - struct gdma_dev_id dev_id; - - u32 pdid; - u32 doorbell; - u32 gpa_mkey; - - /* GDMA driver specific pointer */ - void *driver_data; -}; - -#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE - -#define GDMA_CQE_SIZE 64 -#define GDMA_EQE_SIZE 16 -#define GDMA_MAX_SQE_SIZE 512 -#define GDMA_MAX_RQE_SIZE 256 - -#define GDMA_COMP_DATA_SIZE 0x3C - -#define GDMA_EVENT_DATA_SIZE 0xC - -/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */ -#define GDMA_WQE_BU_SIZE 32 - -#define INVALID_PDID UINT_MAX -#define INVALID_DOORBELL UINT_MAX -#define INVALID_MEM_KEY UINT_MAX -#define INVALID_QUEUE_ID UINT_MAX -#define INVALID_PCI_MSIX_INDEX UINT_MAX - -struct gdma_comp { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - u32 wq_num; - bool is_sq; -}; - -struct gdma_event { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u8 type; -}; - -struct gdma_queue; - -struct mana_eq { - struct gdma_queue *eq; -}; - -typedef void gdma_eq_callback(void *context, struct gdma_queue *q, - struct gdma_event *e); - -typedef void gdma_cq_callback(void *context, struct gdma_queue *q); - -/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE - * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the - * driver increases the 'head' in BUs rather than in bytes, and notifies - * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track - * the HW head, and increases the 'head' by 1 for every processed EQE/CQE. - * - * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is - * processed, the driver increases the 'tail' to indicate that WQEs have - * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ. - * - * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures - * that the EQ/CQ is big enough so they can't overflow, and the driver uses - * the owner bits mechanism to detect if the queue has become empty. - */ -struct gdma_queue { - struct gdma_dev *gdma_dev; - - enum gdma_queue_type type; - u32 id; - - struct gdma_mem_info mem_info; - - void *queue_mem_ptr; - u32 queue_size; - - bool monitor_avl_buf; - - u32 head; - u32 tail; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - bool disable_needed; - - gdma_eq_callback *callback; - void *context; - - unsigned int msix_index; - - u32 log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent; /* For CQ/EQ relationship */ - } cq; - }; -}; - -struct gdma_queue_spec { - enum gdma_queue_type type; - bool monitor_avl_buf; - unsigned int queue_size; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - gdma_eq_callback *callback; - void *context; - - unsigned long log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent_eq; - - } cq; - }; -}; - -struct gdma_irq_context { - void (*handler)(void *arg); - void *arg; -}; - -struct gdma_context { - struct device *dev; - - /* Per-vPort max number of queues */ - unsigned int max_num_queues; - unsigned int max_num_msix; - unsigned int num_msix_usable; - struct gdma_resource msix_resource; - struct gdma_irq_context *irq_contexts; - - /* This maps a CQ index to the queue structure. */ - unsigned int max_num_cqs; - struct gdma_queue **cq_table; - - /* Protect eq_test_event and test_event_eq_id */ - struct mutex eq_test_event_mutex; - struct completion eq_test_event; - u32 test_event_eq_id; - - bool is_pf; - void __iomem *bar0_va; - void __iomem *shm_base; - void __iomem *db_page_base; - u32 db_page_size; - - /* Shared memory chanenl (used to bootstrap HWC) */ - struct shm_channel shm_channel; - - /* Hardware communication channel (HWC) */ - struct gdma_dev hwc; - - /* Azure network adapter */ - struct gdma_dev mana; -}; - -#define MAX_NUM_GDMA_DEVICES 4 - -static inline bool mana_gd_is_mana(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_MANA; -} - -static inline bool mana_gd_is_hwc(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_HWC; -} - -u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset); -u32 mana_gd_wq_avail_space(struct gdma_queue *wq); - -int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq); - -int mana_gd_create_hwc_queue(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_eq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); - -int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); - -void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); - -struct gdma_wqe { - u32 reserved :24; - u32 last_vbytes :8; - - union { - u32 flags; - - struct { - u32 num_sge :8; - u32 inline_oob_size_div4:3; - u32 client_oob_in_sgl :1; - u32 reserved1 :4; - u32 client_data_unit :14; - u32 reserved2 :2; - }; - }; -}; /* HW DATA */ - -#define INLINE_OOB_SMALL_SIZE 8 -#define INLINE_OOB_LARGE_SIZE 24 - -#define MAX_TX_WQE_SIZE 512 -#define MAX_RX_WQE_SIZE 256 - -struct gdma_cqe { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - - union { - u32 as_uint32; - - struct { - u32 wq_num : 24; - u32 is_sq : 1; - u32 reserved : 4; - u32 owner_bits : 3; - }; - } cqe_info; -}; /* HW DATA */ - -#define GDMA_CQE_OWNER_BITS 3 - -#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1) - -#define SET_ARM_BIT 1 - -#define GDMA_EQE_OWNER_BITS 3 - -union gdma_eqe_info { - u32 as_uint32; - - struct { - u32 type : 8; - u32 reserved1 : 8; - u32 client_id : 2; - u32 reserved2 : 11; - u32 owner_bits : 3; - }; -}; /* HW DATA */ - -#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1) -#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries)) - -struct gdma_eqe { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u32 eqe_info; -}; /* HW DATA */ - -#define GDMA_REG_DB_PAGE_OFFSET 8 -#define GDMA_REG_DB_PAGE_SIZE 0x10 -#define GDMA_REG_SHM_OFFSET 0x18 - -#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 -#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 -#define GDMA_PF_REG_SHM_OFF 0x70 - -#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 - -#define MANA_PF_DEVICE_ID 0x00B9 -#define MANA_VF_DEVICE_ID 0x00BA - -struct gdma_posted_wqe_info { - u32 wqe_size_in_bu; -}; - -/* GDMA_GENERATE_TEST_EQE */ -struct gdma_generate_test_event_req { - struct gdma_req_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_VERIFY_VF_DRIVER_VERSION */ -enum { - GDMA_PROTOCOL_V1 = 1, - GDMA_PROTOCOL_FIRST = GDMA_PROTOCOL_V1, - GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, -}; - -#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) - -/* Advertise to the NIC firmware: the NAPI work_done variable race is fixed, - * so the driver is able to reliably support features like busy_poll. - */ -#define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) - -#define GDMA_DRV_CAP_FLAGS1 \ - (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ - GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) - -#define GDMA_DRV_CAP_FLAGS2 0 - -#define GDMA_DRV_CAP_FLAGS3 0 - -#define GDMA_DRV_CAP_FLAGS4 0 - -struct gdma_verify_ver_req { - struct gdma_req_hdr hdr; - - /* Mandatory fields required for protocol establishment */ - u64 protocol_ver_min; - u64 protocol_ver_max; - - /* Gdma Driver Capability Flags */ - u64 gd_drv_cap_flags1; - u64 gd_drv_cap_flags2; - u64 gd_drv_cap_flags3; - u64 gd_drv_cap_flags4; - - /* Advisory fields */ - u64 drv_ver; - u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */ - u32 reserved; - u32 os_ver_major; - u32 os_ver_minor; - u32 os_ver_build; - u32 os_ver_platform; - u64 reserved_2; - u8 os_ver_str1[128]; - u8 os_ver_str2[128]; - u8 os_ver_str3[128]; - u8 os_ver_str4[128]; -}; /* HW DATA */ - -struct gdma_verify_ver_resp { - struct gdma_resp_hdr hdr; - u64 gdma_protocol_ver; - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; -}; /* HW DATA */ - -/* GDMA_QUERY_MAX_RESOURCES */ -struct gdma_query_max_resources_resp { - struct gdma_resp_hdr hdr; - u32 status; - u32 max_sq; - u32 max_rq; - u32 max_cq; - u32 max_eq; - u32 max_db; - u32 max_mst; - u32 max_cq_mod_ctx; - u32 max_mod_cq; - u32 max_msix; -}; /* HW DATA */ - -/* GDMA_LIST_DEVICES */ -struct gdma_list_devices_resp { - struct gdma_resp_hdr hdr; - u32 num_of_devs; - u32 reserved; - struct gdma_dev_id devs[64]; -}; /* HW DATA */ - -/* GDMA_REGISTER_DEVICE */ -struct gdma_register_device_resp { - struct gdma_resp_hdr hdr; - u32 pdid; - u32 gpa_mkey; - u32 db_id; -}; /* HW DATA */ - -/* GDMA_CREATE_QUEUE */ -struct gdma_create_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 reserved1; - u32 pdid; - u32 doolbell_id; - u64 gdma_region; - u32 reserved2; - u32 queue_size; - u32 log2_throttle_limit; - u32 eq_pci_msix_index; - u32 cq_mod_ctx_id; - u32 cq_parent_eq_id; - u8 rq_drop_on_overrun; - u8 rq_err_on_wqe_overflow; - u8 rq_chain_rec_wqes; - u8 sq_hw_db; - u32 reserved3; -}; /* HW DATA */ - -struct gdma_create_queue_resp { - struct gdma_resp_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_DISABLE_QUEUE */ -struct gdma_disable_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 queue_index; - u32 alloc_res_id_on_creation; -}; /* HW DATA */ - -/* GDMA_CREATE_DMA_REGION */ -struct gdma_create_dma_region_req { - struct gdma_req_hdr hdr; - - /* The total size of the DMA region */ - u64 length; - - /* The offset in the first page */ - u32 offset_in_page; - - /* enum gdma_page_type */ - u32 gdma_page_type; - - /* The total number of pages */ - u32 page_count; - - /* If page_addr_list_len is smaller than page_count, - * the remaining page addresses will be added via the - * message GDMA_DMA_REGION_ADD_PAGES. - */ - u32 page_addr_list_len; - u64 page_addr_list[]; -}; /* HW DATA */ - -struct gdma_create_dma_region_resp { - struct gdma_resp_hdr hdr; - u64 gdma_region; -}; /* HW DATA */ - -/* GDMA_DMA_REGION_ADD_PAGES */ -struct gdma_dma_region_add_pages_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; - - u32 page_addr_list_len; - u32 reserved3; - - u64 page_addr_list[]; -}; /* HW DATA */ - -/* GDMA_DESTROY_DMA_REGION */ -struct gdma_destroy_dma_region_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; -}; /* HW DATA */ - -int mana_gd_verify_vf_version(struct pci_dev *pdev); - -int mana_gd_register_device(struct gdma_dev *gd); -int mana_gd_deregister_device(struct gdma_dev *gd); - -int mana_gd_post_work_request(struct gdma_queue *wq, - const struct gdma_wqe_request *wqe_req, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_post_and_ring(struct gdma_queue *queue, - const struct gdma_wqe_request *wqe, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r); -void mana_gd_free_res_map(struct gdma_resource *r); - -void mana_gd_wq_ring_doorbell(struct gdma_context *gc, - struct gdma_queue *queue); - -int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, - struct gdma_mem_info *gmi); - -void mana_gd_free_memory(struct gdma_mem_info *gmi); - -int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, - u32 resp_len, void *resp); -#endif /* _GDMA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index a6f99b4344d9..690b69cae4e3 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,7 +6,7 @@ #include <linux/utsname.h> #include <linux/version.h> -#include "mana.h" +#include <net/mana/mana.h> static u32 mana_gd_r32(struct gdma_context *g, u64 offset) { @@ -44,6 +44,9 @@ static void mana_gd_init_vf_regs(struct pci_dev *pdev) gc->db_page_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); + gc->phys_db_page_base = gc->bar0_pa + + mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); + gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); } @@ -149,6 +152,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, return mana_hwc_send_request(hwc, req_len, req, resp_len, resp); } +EXPORT_SYMBOL_NS(mana_gd_send_request, NET_MANA); int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, struct gdma_mem_info *gmi) @@ -194,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, req.type = queue->type; req.pdid = queue->gdma_dev->pdid; req.doolbell_id = queue->gdma_dev->doorbell; - req.gdma_region = queue->mem_info.gdma_region; + req.gdma_region = queue->mem_info.dma_region_handle; req.queue_size = queue->queue_size; req.log2_throttle_limit = queue->eq.log2_throttle_limit; req.eq_pci_msix_index = queue->eq.msix_index; @@ -208,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, queue->id = resp.queue_index; queue->eq.disable_needed = true; - queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; return 0; } @@ -667,24 +671,30 @@ free_q: return err; } -static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region) +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle) { struct gdma_destroy_dma_region_req req = {}; struct gdma_general_resp resp = {}; int err; - if (gdma_region == GDMA_INVALID_DMA_REGION) - return; + if (dma_region_handle == GDMA_INVALID_DMA_REGION) + return 0; mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req), sizeof(resp)); - req.gdma_region = gdma_region; + req.dma_region_handle = dma_region_handle; err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); - if (err || resp.hdr.status) + if (err || resp.hdr.status) { dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", err, resp.hdr.status); + return -EPROTO; + } + + return 0; } +EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_mem_info *gmi) @@ -729,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, if (err) goto out; - if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) { + if (resp.hdr.status || + resp.dma_region_handle == GDMA_INVALID_DMA_REGION) { dev_err(gc->dev, "Failed to create DMA region: 0x%x\n", resp.hdr.status); err = -EPROTO; goto out; } - gmi->gdma_region = resp.gdma_region; + gmi->dma_region_handle = resp.dma_region_handle; out: kfree(req); return err; @@ -859,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue) return; } - mana_gd_destroy_dma_region(gc, gmi->gdma_region); + mana_gd_destroy_dma_region(gc, gmi->dma_region_handle); mana_gd_free_memory(gmi); kfree(queue); } @@ -1208,8 +1219,10 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_irq_context *gic; unsigned int max_irqs; + u16 *cpus; + cpumask_var_t req_mask; int nvec, irq; - int err, i, j; + int err, i = 0, j; if (max_queues_per_port > MANA_MAX_NUM_QUEUES) max_queues_per_port = MANA_MAX_NUM_QUEUES; @@ -1228,7 +1241,21 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) goto free_irq_vector; } + if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { + err = -ENOMEM; + goto free_irq; + } + + cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); + if (!cpus) { + err = -ENOMEM; + goto free_mask; + } + for (i = 0; i < nvec; i++) + cpus[i] = cpumask_local_spread(i, gc->numa_node); + for (i = 0; i < nvec; i++) { + cpumask_set_cpu(cpus[i], req_mask); gic = &gc->irq_contexts[i]; gic->handler = NULL; gic->arg = NULL; @@ -1236,13 +1263,17 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; - goto free_irq; + goto free_mask; } err = request_irq(irq, mana_gd_intr, 0, "mana_intr", gic); if (err) - goto free_irq; + goto free_mask; + irq_set_affinity_and_hint(irq, req_mask); + cpumask_clear(req_mask); } + free_cpumask_var(req_mask); + kfree(cpus); err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); if (err) @@ -1253,6 +1284,9 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) return 0; +free_mask: + free_cpumask_var(req_mask); + kfree(cpus); free_irq: for (j = i - 1; j >= 0; j--) { irq = pci_irq_vector(pdev, j); @@ -1370,6 +1404,12 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto release_region; + err = dma_set_max_seg_size(&pdev->dev, UINT_MAX); + if (err) { + dev_err(&pdev->dev, "Failed to set dma device segment size\n"); + goto release_region; + } + err = -ENOMEM; gc = vzalloc(sizeof(*gc)); if (!gc) @@ -1377,11 +1417,13 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&gc->eq_test_event_mutex); pci_set_drvdata(pdev, gc); + gc->bar0_pa = pci_resource_start(pdev, 0); bar0_va = pci_iomap(pdev, bar, 0); if (!bar0_va) goto free_gc; + gc->numa_node = dev_to_node(&pdev->dev); gc->is_pf = mana_is_pf(pdev->device); gc->bar0_va = bar0_va; gc->dev = &pdev->dev; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 543a5d5c304f..9d1507eba5b9 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Copyright (c) 2021, Microsoft Corporation. */ -#include "gdma.h" -#include "hw_channel.h" +#include <net/mana/gdma.h> +#include <net/mana/hw_channel.h> static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) { @@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (ctx->status_code) { + if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", ctx->status_code); err = -EPROTO; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/drivers/net/ethernet/microsoft/mana/hw_channel.h deleted file mode 100644 index 6a757a6e2732..000000000000 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.h +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _HW_CHANNEL_H -#define _HW_CHANNEL_H - -#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4 - -#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000 -#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000 - -#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1 - -#define HWC_INIT_DATA_CQID 1 -#define HWC_INIT_DATA_RQID 2 -#define HWC_INIT_DATA_SQID 3 -#define HWC_INIT_DATA_QUEUE_DEPTH 4 -#define HWC_INIT_DATA_MAX_REQUEST 5 -#define HWC_INIT_DATA_MAX_RESPONSE 6 -#define HWC_INIT_DATA_MAX_NUM_CQS 7 -#define HWC_INIT_DATA_PDID 8 -#define HWC_INIT_DATA_GPA_MKEY 9 -#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 -#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -union hwc_init_eq_id_db { - u32 as_uint32; - - struct { - u32 eq_id : 16; - u32 doorbell : 16; - }; -}; /* HW DATA */ - -union hwc_init_type_data { - u32 as_uint32; - - struct { - u32 value : 24; - u32 type : 8; - }; -}; /* HW DATA */ - -struct hwc_rx_oob { - u32 type : 6; - u32 eom : 1; - u32 som : 1; - u32 vendor_err : 8; - u32 reserved1 : 16; - - u32 src_virt_wq : 24; - u32 src_vfid : 8; - - u32 reserved2; - - union { - u32 wqe_addr_low; - u32 wqe_offset; - }; - - u32 wqe_addr_high; - - u32 client_data_unit : 14; - u32 reserved3 : 18; - - u32 tx_oob_data_size; - - u32 chunk_offset : 21; - u32 reserved4 : 11; -}; /* HW DATA */ - -struct hwc_tx_oob { - u32 reserved1; - - u32 reserved2; - - u32 vrq_id : 24; - u32 dest_vfid : 8; - - u32 vrcq_id : 24; - u32 reserved3 : 8; - - u32 vscq_id : 24; - u32 loopback : 1; - u32 lso_override: 1; - u32 dest_pf : 1; - u32 reserved4 : 5; - - u32 vsq_id : 24; - u32 reserved5 : 8; -}; /* HW DATA */ - -struct hwc_work_request { - void *buf_va; - void *buf_sge_addr; - u32 buf_len; - u32 msg_size; - - struct gdma_wqe_request wqe_req; - struct hwc_tx_oob tx_oob; - - struct gdma_sge sge; -}; - -/* hwc_dma_buf represents the array of in-flight WQEs. - * mem_info as know as the GDMA mapped memory is partitioned and used by - * in-flight WQEs. - * The number of WQEs is determined by the number of in-flight messages. - */ -struct hwc_dma_buf { - struct gdma_mem_info mem_info; - - u32 gpa_mkey; - - u32 num_reqs; - struct hwc_work_request reqs[]; -}; - -typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id, - const struct hwc_rx_oob *rx_oob); - -typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id, - const struct hwc_rx_oob *rx_oob); - -struct hwc_cq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_cq; - struct gdma_queue *gdma_eq; - struct gdma_comp *comp_buf; - u16 queue_depth; - - hwc_rx_event_handler_t *rx_event_handler; - void *rx_event_ctx; - - hwc_tx_event_handler_t *tx_event_handler; - void *tx_event_ctx; -}; - -struct hwc_wq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_wq; - struct hwc_dma_buf *msg_buf; - u16 queue_depth; - - struct hwc_cq *hwc_cq; -}; - -struct hwc_caller_ctx { - struct completion comp_event; - void *output_buf; - u32 output_buflen; - - u32 error; /* Linux error code */ - u32 status_code; -}; - -struct hw_channel_context { - struct gdma_dev *gdma_dev; - struct device *dev; - - u16 num_inflight_msg; - u32 max_req_msg_size; - - u16 hwc_init_q_depth_max; - u32 hwc_init_max_req_msg_size; - u32 hwc_init_max_resp_msg_size; - - struct completion hwc_init_eqe_comp; - - struct hwc_wq *rxq; - struct hwc_wq *txq; - struct hwc_cq *cq; - - struct semaphore sema; - struct gdma_resource inflight_msg_res; - - u32 pf_dest_vrq_id; - u32 pf_dest_vrcq_id; - - struct hwc_caller_ctx *caller_ctx; -}; - -int mana_hwc_create_channel(struct gdma_context *gc); -void mana_hwc_destroy_channel(struct gdma_context *gc); - -int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, - const void *req, u32 resp_len, void *resp); - -#endif /* _HW_CHANNEL_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h deleted file mode 100644 index d58be64374c8..000000000000 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ /dev/null @@ -1,634 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _MANA_H -#define _MANA_H - -#include "gdma.h" -#include "hw_channel.h" - -/* Microsoft Azure Network Adapter (MANA)'s definitions - * - * Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -/* MANA protocol version */ -#define MANA_MAJOR_VERSION 0 -#define MANA_MINOR_VERSION 1 -#define MANA_MICRO_VERSION 1 - -typedef u64 mana_handle_t; -#define INVALID_MANA_HANDLE ((mana_handle_t)-1) - -enum TRI_STATE { - TRI_STATE_UNKNOWN = -1, - TRI_STATE_FALSE = 0, - TRI_STATE_TRUE = 1 -}; - -/* Number of entries for hardware indirection table must be in power of 2 */ -#define MANA_INDIRECT_TABLE_SIZE 64 -#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) - -/* The Toeplitz hash key's length in bytes: should be multiple of 8 */ -#define MANA_HASH_KEY_SIZE 40 - -#define COMP_ENTRY_SIZE 64 - -#define ADAPTER_MTU_SIZE 1500 -#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) - -#define RX_BUFFERS_PER_QUEUE 512 - -#define MAX_SEND_BUFFERS_PER_QUEUE 256 - -#define EQ_SIZE (8 * PAGE_SIZE) -#define LOG2_EQ_THROTTLE 3 - -#define MAX_PORTS_IN_MANA_DEV 256 - -struct mana_stats_rx { - u64 packets; - u64 bytes; - u64 xdp_drop; - u64 xdp_tx; - u64 xdp_redirect; - struct u64_stats_sync syncp; -}; - -struct mana_stats_tx { - u64 packets; - u64 bytes; - u64 xdp_xmit; - struct u64_stats_sync syncp; -}; - -struct mana_txq { - struct gdma_queue *gdma_sq; - - union { - u32 gdma_txq_id; - struct { - u32 reserved1 : 10; - u32 vsq_frame : 14; - u32 reserved2 : 8; - }; - }; - - u16 vp_offset; - - struct net_device *ndev; - - /* The SKBs are sent to the HW and we are waiting for the CQEs. */ - struct sk_buff_head pending_skbs; - struct netdev_queue *net_txq; - - atomic_t pending_sends; - - struct mana_stats_tx stats; -}; - -/* skb data and frags dma mappings */ -struct mana_skb_head { - dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; - - u32 size[MAX_SKB_FRAGS + 1]; -}; - -#define MANA_HEADROOM sizeof(struct mana_skb_head) - -enum mana_tx_pkt_format { - MANA_SHORT_PKT_FMT = 0, - MANA_LONG_PKT_FMT = 1, -}; - -struct mana_tx_short_oob { - u32 pkt_fmt : 2; - u32 is_outer_ipv4 : 1; - u32 is_outer_ipv6 : 1; - u32 comp_iphdr_csum : 1; - u32 comp_tcp_csum : 1; - u32 comp_udp_csum : 1; - u32 supress_txcqe_gen : 1; - u32 vcq_num : 24; - - u32 trans_off : 10; /* Transport header offset */ - u32 vsq_frame : 14; - u32 short_vp_offset : 8; -}; /* HW DATA */ - -struct mana_tx_long_oob { - u32 is_encap : 1; - u32 inner_is_ipv6 : 1; - u32 inner_tcp_opt : 1; - u32 inject_vlan_pri_tag : 1; - u32 reserved1 : 12; - u32 pcp : 3; /* 802.1Q */ - u32 dei : 1; /* 802.1Q */ - u32 vlan_id : 12; /* 802.1Q */ - - u32 inner_frame_offset : 10; - u32 inner_ip_rel_offset : 6; - u32 long_vp_offset : 12; - u32 reserved2 : 4; - - u32 reserved3; - u32 reserved4; -}; /* HW DATA */ - -struct mana_tx_oob { - struct mana_tx_short_oob s_oob; - struct mana_tx_long_oob l_oob; -}; /* HW DATA */ - -enum mana_cq_type { - MANA_CQ_TYPE_RX, - MANA_CQ_TYPE_TX, -}; - -enum mana_cqe_type { - CQE_INVALID = 0, - CQE_RX_OKAY = 1, - CQE_RX_COALESCED_4 = 2, - CQE_RX_OBJECT_FENCE = 3, - CQE_RX_TRUNCATED = 4, - - CQE_TX_OKAY = 32, - CQE_TX_SA_DROP = 33, - CQE_TX_MTU_DROP = 34, - CQE_TX_INVALID_OOB = 35, - CQE_TX_INVALID_ETH_TYPE = 36, - CQE_TX_HDR_PROCESSING_ERROR = 37, - CQE_TX_VF_DISABLED = 38, - CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39, - CQE_TX_VPORT_DISABLED = 40, - CQE_TX_VLAN_TAGGING_VIOLATION = 41, -}; - -#define MANA_CQE_COMPLETION 1 - -struct mana_cqe_header { - u32 cqe_type : 6; - u32 client_type : 2; - u32 vendor_err : 24; -}; /* HW DATA */ - -/* NDIS HASH Types */ -#define NDIS_HASH_IPV4 BIT(0) -#define NDIS_HASH_TCP_IPV4 BIT(1) -#define NDIS_HASH_UDP_IPV4 BIT(2) -#define NDIS_HASH_IPV6 BIT(3) -#define NDIS_HASH_TCP_IPV6 BIT(4) -#define NDIS_HASH_UDP_IPV6 BIT(5) -#define NDIS_HASH_IPV6_EX BIT(6) -#define NDIS_HASH_TCP_IPV6_EX BIT(7) -#define NDIS_HASH_UDP_IPV6_EX BIT(8) - -#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX) -#define MANA_HASH_L4 \ - (NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 | \ - NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX) - -struct mana_rxcomp_perpkt_info { - u32 pkt_len : 16; - u32 reserved1 : 16; - u32 reserved2; - u32 pkt_hash; -}; /* HW DATA */ - -#define MANA_RXCOMP_OOB_NUM_PPI 4 - -/* Receive completion OOB */ -struct mana_rxcomp_oob { - struct mana_cqe_header cqe_hdr; - - u32 rx_vlan_id : 12; - u32 rx_vlantag_present : 1; - u32 rx_outer_iphdr_csum_succeed : 1; - u32 rx_outer_iphdr_csum_fail : 1; - u32 reserved1 : 1; - u32 rx_hashtype : 9; - u32 rx_iphdr_csum_succeed : 1; - u32 rx_iphdr_csum_fail : 1; - u32 rx_tcp_csum_succeed : 1; - u32 rx_tcp_csum_fail : 1; - u32 rx_udp_csum_succeed : 1; - u32 rx_udp_csum_fail : 1; - u32 reserved2 : 1; - - struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI]; - - u32 rx_wqe_offset; -}; /* HW DATA */ - -struct mana_tx_comp_oob { - struct mana_cqe_header cqe_hdr; - - u32 tx_data_offset; - - u32 tx_sgl_offset : 5; - u32 tx_wqe_offset : 27; - - u32 reserved[12]; -}; /* HW DATA */ - -struct mana_rxq; - -#define CQE_POLLING_BUFFER 512 - -struct mana_cq { - struct gdma_queue *gdma_cq; - - /* Cache the CQ id (used to verify if each CQE comes to the right CQ. */ - u32 gdma_id; - - /* Type of the CQ: TX or RX */ - enum mana_cq_type type; - - /* Pointer to the mana_rxq that is pushing RX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_RX. - */ - struct mana_rxq *rxq; - - /* Pointer to the mana_txq that is pushing TX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_TX. - */ - struct mana_txq *txq; - - /* Buffer which the CQ handler can copy the CQE's into. */ - struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; - - /* NAPI data */ - struct napi_struct napi; - int work_done; - int budget; -}; - -#define GDMA_MAX_RQE_SGES 15 - -struct mana_recv_buf_oob { - /* A valid GDMA work request representing the data buffer. */ - struct gdma_wqe_request wqe_req; - - void *buf_va; - dma_addr_t buf_dma_addr; - - /* SGL of the buffer going to be sent has part of the work request. */ - u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; - - /* Required to store the result of mana_gd_post_work_request. - * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the - * work queue when the WQE is consumed. - */ - struct gdma_posted_wqe_info wqe_inf; -}; - -struct mana_rxq { - struct gdma_queue *gdma_rq; - /* Cache the gdma receive queue id */ - u32 gdma_id; - - /* Index of RQ in the vPort, not gdma receive queue id */ - u32 rxq_idx; - - u32 datasize; - - mana_handle_t rxobj; - - struct mana_cq rx_cq; - - struct completion fence_event; - - struct net_device *ndev; - - /* Total number of receive buffers to be allocated */ - u32 num_rx_buf; - - u32 buf_index; - - struct mana_stats_rx stats; - - struct bpf_prog __rcu *bpf_prog; - struct xdp_rxq_info xdp_rxq; - struct page *xdp_save_page; - bool xdp_flush; - int xdp_rc; /* XDP redirect return code */ - - /* MUST BE THE LAST MEMBER: - * Each receive buffer has an associated mana_recv_buf_oob. - */ - struct mana_recv_buf_oob rx_oobs[]; -}; - -struct mana_tx_qp { - struct mana_txq txq; - - struct mana_cq tx_cq; - - mana_handle_t tx_object; -}; - -struct mana_ethtool_stats { - u64 stop_queue; - u64 wake_queue; -}; - -struct mana_context { - struct gdma_dev *gdma_dev; - - u16 num_ports; - - struct mana_eq *eqs; - - struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; -}; - -struct mana_port_context { - struct mana_context *ac; - struct net_device *ndev; - - u8 mac_addr[ETH_ALEN]; - - enum TRI_STATE rss_state; - - mana_handle_t default_rxobj; - bool tx_shortform_allowed; - u16 tx_vp_offset; - - struct mana_tx_qp *tx_qp; - - /* Indirection Table for RX & TX. The values are queue indexes */ - u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Indirection table containing RxObject Handles */ - mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Hash key used by the NIC */ - u8 hashkey[MANA_HASH_KEY_SIZE]; - - /* This points to an array of num_queues of RQ pointers. */ - struct mana_rxq **rxqs; - - struct bpf_prog *bpf_prog; - - /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ - unsigned int max_queues; - unsigned int num_queues; - - mana_handle_t port_handle; - mana_handle_t pf_filter_handle; - - u16 port_idx; - - bool port_is_up; - bool port_st_save; /* Saved port state */ - - struct mana_ethtool_stats eth_stats; -}; - -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); -int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, - bool update_hash, bool update_tab); - -int mana_alloc_queues(struct net_device *ndev); -int mana_attach(struct net_device *ndev); -int mana_detach(struct net_device *ndev, bool from_close); - -int mana_probe(struct gdma_dev *gd, bool resuming); -void mana_remove(struct gdma_dev *gd, bool suspending); - -void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); -int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, - u32 flags); -u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, - struct xdp_buff *xdp, void *buf_va, uint pkt_len); -struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); -void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); -int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); - -extern const struct ethtool_ops mana_ethtool_ops; - -struct mana_obj_spec { - u32 queue_index; - u64 gdma_region; - u32 queue_size; - u32 attached_eq; - u32 modr_ctx_id; -}; - -enum mana_command_code { - MANA_QUERY_DEV_CONFIG = 0x20001, - MANA_QUERY_GF_STAT = 0x20002, - MANA_CONFIG_VPORT_TX = 0x20003, - MANA_CREATE_WQ_OBJ = 0x20004, - MANA_DESTROY_WQ_OBJ = 0x20005, - MANA_FENCE_RQ = 0x20006, - MANA_CONFIG_VPORT_RX = 0x20007, - MANA_QUERY_VPORT_CONFIG = 0x20008, - - /* Privileged commands for the PF mode */ - MANA_REGISTER_FILTER = 0x28000, - MANA_DEREGISTER_FILTER = 0x28001, - MANA_REGISTER_HW_PORT = 0x28003, - MANA_DEREGISTER_HW_PORT = 0x28004, -}; - -/* Query Device Configuration */ -struct mana_query_device_cfg_req { - struct gdma_req_hdr hdr; - - /* MANA Nic Driver Capability flags */ - u64 mn_drv_cap_flags1; - u64 mn_drv_cap_flags2; - u64 mn_drv_cap_flags3; - u64 mn_drv_cap_flags4; - - u32 proto_major_ver; - u32 proto_minor_ver; - u32 proto_micro_ver; - - u32 reserved; -}; /* HW DATA */ - -struct mana_query_device_cfg_resp { - struct gdma_resp_hdr hdr; - - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; - - u16 max_num_vports; - u16 reserved; - u32 max_num_eqs; -}; /* HW DATA */ - -/* Query vPort Configuration */ -struct mana_query_vport_cfg_req { - struct gdma_req_hdr hdr; - u32 vport_index; -}; /* HW DATA */ - -struct mana_query_vport_cfg_resp { - struct gdma_resp_hdr hdr; - u32 max_num_sq; - u32 max_num_rq; - u32 num_indirection_ent; - u32 reserved1; - u8 mac_addr[6]; - u8 reserved2[2]; - mana_handle_t vport; -}; /* HW DATA */ - -/* Configure vPort */ -struct mana_config_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 pdid; - u32 doorbell_pageid; -}; /* HW DATA */ - -struct mana_config_vport_resp { - struct gdma_resp_hdr hdr; - u16 tx_vport_offset; - u8 short_form_allowed; - u8 reserved; -}; /* HW DATA */ - -/* Create WQ Object */ -struct mana_create_wqobj_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 wq_type; - u32 reserved; - u64 wq_gdma_region; - u64 cq_gdma_region; - u32 wq_size; - u32 cq_size; - u32 cq_moderation_ctx_id; - u32 cq_parent_qid; -}; /* HW DATA */ - -struct mana_create_wqobj_resp { - struct gdma_resp_hdr hdr; - u32 wq_id; - u32 cq_id; - mana_handle_t wq_obj; -}; /* HW DATA */ - -/* Destroy WQ Object */ -struct mana_destroy_wqobj_req { - struct gdma_req_hdr hdr; - u32 wq_type; - u32 reserved; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_destroy_wqobj_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Fence RQ */ -struct mana_fence_rq_req { - struct gdma_req_hdr hdr; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_fence_rq_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Configure vPort Rx Steering */ -struct mana_cfg_rx_steer_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u16 num_indir_entries; - u16 indir_tab_offset; - u32 rx_enable; - u32 rss_enable; - u8 update_default_rxobj; - u8 update_hashkey; - u8 update_indir_tab; - u8 reserved; - mana_handle_t default_rxobj; - u8 hashkey[MANA_HASH_KEY_SIZE]; -}; /* HW DATA */ - -struct mana_cfg_rx_steer_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register HW vPort */ -struct mana_register_hw_vport_req { - struct gdma_req_hdr hdr; - u16 attached_gfid; - u8 is_pf_default_vport; - u8 reserved1; - u8 allow_all_ether_types; - u8 reserved2; - u8 reserved3; - u8 reserved4; -}; /* HW DATA */ - -struct mana_register_hw_vport_resp { - struct gdma_resp_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -/* Deregister HW vPort */ -struct mana_deregister_hw_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -struct mana_deregister_hw_vport_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register filter */ -struct mana_register_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u8 mac_addr[6]; - u8 reserved1; - u8 reserved2; - u8 reserved3; - u8 reserved4; - u16 reserved5; - u32 reserved6; - u32 reserved7; - u32 reserved8; -}; /* HW DATA */ - -struct mana_register_filter_resp { - struct gdma_resp_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -/* Deregister filter */ -struct mana_deregister_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -struct mana_deregister_filter_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define MANA_MAX_NUM_QUEUES 64 - -#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) - -struct mana_tx_package { - struct gdma_wqe_request wqe_req; - struct gdma_sge sgl_array[5]; - struct gdma_sge *sgl_ptr; - - struct mana_tx_oob tx_oob; - - struct gdma_posted_wqe_info wqe_info; -}; - -#endif /* _MANA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 421fd39ff3a8..3caea631229c 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -8,7 +8,7 @@ #include <linux/bpf_trace.h> #include <net/xdp.h> -#include "mana.h" +#include <net/mana/mana.h> void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 27a0f3af8aab..2f6a048dee90 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -12,7 +12,20 @@ #include <net/checksum.h> #include <net/ip6_checksum.h> -#include "mana.h" +#include <net/mana/mana.h> +#include <net/mana/mana_auxiliary.h> + +static DEFINE_IDA(mana_adev_ida); + +static int mana_adev_idx_alloc(void) +{ + return ida_alloc(&mana_adev_ida, GFP_KERNEL); +} + +static void mana_adev_idx_free(int idx) +{ + ida_free(&mana_adev_ida, idx); +} /* Microsoft Azure Network Adapter (MANA) functions */ @@ -128,7 +141,7 @@ frag_err: return -ENOMEM; } -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) +netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) { enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; struct mana_port_context *apc = netdev_priv(ndev); @@ -176,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > 30); + WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; @@ -315,10 +328,10 @@ static void mana_get_stats64(struct net_device *ndev, rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + start = u64_stats_fetch_begin(&rx_stats->syncp); packets = rx_stats->packets; bytes = rx_stats->bytes; - } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); + } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); st->rx_packets += packets; st->rx_bytes += bytes; @@ -328,10 +341,10 @@ static void mana_get_stats64(struct net_device *ndev, tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + start = u64_stats_fetch_begin(&tx_stats->syncp); packets = tx_stats->packets; bytes = tx_stats->bytes; - } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); + } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); st->tx_packets += packets; st->tx_bytes += bytes; @@ -633,13 +646,48 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index, return 0; } -static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, - u32 doorbell_pg_id) +void mana_uncfg_vport(struct mana_port_context *apc) +{ + mutex_lock(&apc->vport_mutex); + apc->vport_use_count--; + WARN_ON(apc->vport_use_count < 0); + mutex_unlock(&apc->vport_mutex); +} +EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA); + +int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id) { struct mana_config_vport_resp resp = {}; struct mana_config_vport_req req = {}; int err; + /* This function is used to program the Ethernet port in the hardware + * table. It can be called from the Ethernet driver or the RDMA driver. + * + * For Ethernet usage, the hardware supports only one active user on a + * physical port. The driver checks on the port usage before programming + * the hardware when creating the RAW QP (RDMA driver) or exposing the + * device to kernel NET layer (Ethernet driver). + * + * Because the RDMA driver doesn't know in advance which QP type the + * user will create, it exposes the device with all its ports. The user + * may not be able to create RAW QP on a port if this port is already + * in used by the Ethernet driver from the kernel. + * + * This physical port limitation only applies to the RAW QP. For RC QP, + * the hardware doesn't have this limitation. The user can create RC + * QPs on a physical port up to the hardware limits independent of the + * Ethernet usage on the same port. + */ + mutex_lock(&apc->vport_mutex); + if (apc->vport_use_count > 0) { + mutex_unlock(&apc->vport_mutex); + return -EBUSY; + } + apc->vport_use_count++; + mutex_unlock(&apc->vport_mutex); + mana_gd_init_req_hdr(&req.hdr, MANA_CONFIG_VPORT_TX, sizeof(req), sizeof(resp)); req.vport = apc->port_handle; @@ -666,9 +714,16 @@ static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, apc->tx_shortform_allowed = resp.short_form_allowed; apc->tx_vp_offset = resp.tx_vport_offset; + + netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n", + apc->port_handle, protection_dom_id, doorbell_pg_id); out: + if (err) + mana_uncfg_vport(apc); + return err; } +EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA); static int mana_cfg_vport_steering(struct mana_port_context *apc, enum TRI_STATE rx, @@ -729,16 +784,19 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, resp.hdr.status); err = -EPROTO; } + + netdev_info(ndev, "Configured steering vPort %llu entries %u\n", + apc->port_handle, num_entries); out: kfree(req); return err; } -static int mana_create_wq_obj(struct mana_port_context *apc, - mana_handle_t vport, - u32 wq_type, struct mana_obj_spec *wq_spec, - struct mana_obj_spec *cq_spec, - mana_handle_t *wq_obj) +int mana_create_wq_obj(struct mana_port_context *apc, + mana_handle_t vport, + u32 wq_type, struct mana_obj_spec *wq_spec, + struct mana_obj_spec *cq_spec, + mana_handle_t *wq_obj) { struct mana_create_wqobj_resp resp = {}; struct mana_create_wqobj_req req = {}; @@ -787,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc, out: return err; } +EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA); -static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, - mana_handle_t wq_obj) +void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + mana_handle_t wq_obj) { struct mana_destroy_wqobj_resp resp = {}; struct mana_destroy_wqobj_req req = {}; @@ -814,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err, resp.hdr.status); } +EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA); static void mana_destroy_eq(struct mana_context *ac) { @@ -1469,10 +1529,10 @@ static int mana_create_txq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; + wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; wq_spec.queue_size = txq->gdma_sq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1487,8 +1547,10 @@ static int mana_create_txq(struct mana_port_context *apc, txq->gdma_sq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + txq->gdma_sq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; txq->gdma_txq_id = txq->gdma_sq->id; @@ -1699,10 +1761,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; + wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; wq_spec.queue_size = rxq->gdma_rq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1715,8 +1777,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->gdma_rq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; rxq->gdma_id = rxq->gdma_rq->id; cq->gdma_id = cq->gdma_cq->id; @@ -1797,6 +1859,7 @@ static void mana_destroy_vport(struct mana_port_context *apc) } mana_destroy_txq(apc); + mana_uncfg_vport(apc); if (gd->gdma_context->is_pf) mana_pf_deregister_hw_vport(apc); @@ -2069,12 +2132,16 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; + mutex_init(&apc->vport_mutex); + apc->vport_use_count = 0; + ndev->netdev_ops = &mana_devops; ndev->ethtool_ops = &mana_ethtool_ops; ndev->mtu = ETH_DATA_LEN; ndev->max_mtu = ndev->mtu; ndev->min_mtu = ndev->mtu; ndev->needed_headroom = MANA_HEADROOM; + ndev->dev_port = port_idx; SET_NETDEV_DEV(ndev, gc->dev); netif_carrier_off(ndev); @@ -2112,6 +2179,69 @@ free_net: return err; } +static void adev_release(struct device *dev) +{ + struct mana_adev *madev = container_of(dev, struct mana_adev, adev.dev); + + kfree(madev); +} + +static void remove_adev(struct gdma_dev *gd) +{ + struct auxiliary_device *adev = gd->adev; + int id = adev->id; + + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); + + mana_adev_idx_free(id); + gd->adev = NULL; +} + +static int add_adev(struct gdma_dev *gd) +{ + struct auxiliary_device *adev; + struct mana_adev *madev; + int ret; + + madev = kzalloc(sizeof(*madev), GFP_KERNEL); + if (!madev) + return -ENOMEM; + + adev = &madev->adev; + ret = mana_adev_idx_alloc(); + if (ret < 0) + goto idx_fail; + adev->id = ret; + + adev->name = "rdma"; + adev->dev.parent = gd->gdma_context->dev; + adev->dev.release = adev_release; + madev->mdev = gd; + + ret = auxiliary_device_init(adev); + if (ret) + goto init_fail; + + ret = auxiliary_device_add(adev); + if (ret) + goto add_fail; + + gd->adev = adev; + return 0; + +add_fail: + auxiliary_device_uninit(adev); + +init_fail: + mana_adev_idx_free(adev->id); + +idx_fail: + kfree(madev); + + return ret; +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; @@ -2179,6 +2309,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) break; } } + + err = add_adev(gd); out: if (err) mana_remove(gd, false); @@ -2195,6 +2327,10 @@ void mana_remove(struct gdma_dev *gd, bool suspending) int err; int i; + /* adev currently doesn't support suspending, always remove it */ + if (gd->adev) + remove_adev(gd); + for (i = 0; i < ac->num_ports; i++) { ndev = ac->ports[i]; if (!ndev) { @@ -2227,7 +2363,6 @@ void mana_remove(struct gdma_dev *gd, bool suspending) } mana_destroy_eq(ac); - out: mana_gd_deregister_device(gd); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index c530db76880f..5b776a33a817 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -5,7 +5,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include "mana.h" +#include <net/mana/mana.h> static const struct { char name[ETH_GSTRING_LEN]; @@ -90,13 +90,13 @@ static void mana_get_ethtool_stats(struct net_device *ndev, rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + start = u64_stats_fetch_begin(&rx_stats->syncp); packets = rx_stats->packets; bytes = rx_stats->bytes; xdp_drop = rx_stats->xdp_drop; xdp_tx = rx_stats->xdp_tx; xdp_redirect = rx_stats->xdp_redirect; - } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); + } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; @@ -109,11 +109,11 @@ static void mana_get_ethtool_stats(struct net_device *ndev, tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + start = u64_stats_fetch_begin(&tx_stats->syncp); packets = tx_stats->packets; bytes = tx_stats->bytes; xdp_xmit = tx_stats->xdp_xmit; - } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); + } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index da255da62176..5553af9c8085 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -6,7 +6,7 @@ #include <linux/io.h> #include <linux/mm.h> -#include "shm_channel.h" +#include <net/mana/shm_channel.h> #define PAGE_FRAME_L48_WIDTH_BYTES 6 #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8) diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.h b/drivers/net/ethernet/microsoft/mana/shm_channel.h deleted file mode 100644 index 5199b41497ff..000000000000 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _SHM_CHANNEL_H -#define _SHM_CHANNEL_H - -struct shm_channel { - struct device *dev; - void __iomem *base; -}; - -void mana_smc_init(struct shm_channel *sc, struct device *dev, - void __iomem *base); - -int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, - u64 cq_addr, u64 rq_addr, u64 sq_addr, - u32 eq_msix_index); - -int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); - -#endif /* _SHM_CHANNEL_H */ diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 13b14110a060..da56f9bfeaf0 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -872,10 +872,8 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, return; } - /* Handle RX pause in all cases, with 2500base-X this is used for rate - * adaptation. - */ - mac_fc_cfg |= SYS_MAC_FC_CFG_RX_FC_ENA; + if (rx_pause) + mac_fc_cfg |= SYS_MAC_FC_CFG_RX_FC_ENA; if (tx_pause) mac_fc_cfg |= SYS_MAC_FC_CFG_TX_FC_ENA | diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 50858cc10fef..ca4bde861397 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -194,15 +194,6 @@ void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port) devlink_port_unregister(dlp); } -static struct devlink_port *ocelot_get_devlink_port(struct net_device *dev) -{ - struct ocelot_port_private *priv = netdev_priv(dev); - struct ocelot *ocelot = priv->port.ocelot; - int port = priv->port.index; - - return &ocelot->devlink_ports[port]; -} - int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv, struct flow_cls_offload *f, bool ingress) @@ -925,7 +916,6 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_set_features = ocelot_set_features, .ndo_setup_tc = ocelot_setup_tc, .ndo_eth_ioctl = ocelot_ioctl, - .ndo_get_devlink_port = ocelot_get_devlink_port, }; struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port) @@ -1737,7 +1727,6 @@ static void vsc7514_phylink_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ocelot_phylink_ops = { - .validate = phylink_generic_validate, .mac_config = vsc7514_phylink_mac_config, .mac_link_down = vsc7514_phylink_mac_link_down, .mac_link_up = vsc7514_phylink_mac_link_up, @@ -1873,6 +1862,7 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, if (ocelot->fdma) ocelot_fdma_netdev_init(ocelot, dev); + SET_NETDEV_DEVLINK_PORT(dev, &ocelot->devlink_ports[port]); err = register_netdev(dev); if (err) { dev_err(ocelot->dev, "register_netdev failed\n"); diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index dbd20b125cea..1478c3b21af1 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -9,6 +9,225 @@ #include <linux/workqueue.h> #include "ocelot.h" +enum ocelot_stat { + OCELOT_STAT_RX_OCTETS, + OCELOT_STAT_RX_UNICAST, + OCELOT_STAT_RX_MULTICAST, + OCELOT_STAT_RX_BROADCAST, + OCELOT_STAT_RX_SHORTS, + OCELOT_STAT_RX_FRAGMENTS, + OCELOT_STAT_RX_JABBERS, + OCELOT_STAT_RX_CRC_ALIGN_ERRS, + OCELOT_STAT_RX_SYM_ERRS, + OCELOT_STAT_RX_64, + OCELOT_STAT_RX_65_127, + OCELOT_STAT_RX_128_255, + OCELOT_STAT_RX_256_511, + OCELOT_STAT_RX_512_1023, + OCELOT_STAT_RX_1024_1526, + OCELOT_STAT_RX_1527_MAX, + OCELOT_STAT_RX_PAUSE, + OCELOT_STAT_RX_CONTROL, + OCELOT_STAT_RX_LONGS, + OCELOT_STAT_RX_CLASSIFIED_DROPS, + OCELOT_STAT_RX_RED_PRIO_0, + OCELOT_STAT_RX_RED_PRIO_1, + OCELOT_STAT_RX_RED_PRIO_2, + OCELOT_STAT_RX_RED_PRIO_3, + OCELOT_STAT_RX_RED_PRIO_4, + OCELOT_STAT_RX_RED_PRIO_5, + OCELOT_STAT_RX_RED_PRIO_6, + OCELOT_STAT_RX_RED_PRIO_7, + OCELOT_STAT_RX_YELLOW_PRIO_0, + OCELOT_STAT_RX_YELLOW_PRIO_1, + OCELOT_STAT_RX_YELLOW_PRIO_2, + OCELOT_STAT_RX_YELLOW_PRIO_3, + OCELOT_STAT_RX_YELLOW_PRIO_4, + OCELOT_STAT_RX_YELLOW_PRIO_5, + OCELOT_STAT_RX_YELLOW_PRIO_6, + OCELOT_STAT_RX_YELLOW_PRIO_7, + OCELOT_STAT_RX_GREEN_PRIO_0, + OCELOT_STAT_RX_GREEN_PRIO_1, + OCELOT_STAT_RX_GREEN_PRIO_2, + OCELOT_STAT_RX_GREEN_PRIO_3, + OCELOT_STAT_RX_GREEN_PRIO_4, + OCELOT_STAT_RX_GREEN_PRIO_5, + OCELOT_STAT_RX_GREEN_PRIO_6, + OCELOT_STAT_RX_GREEN_PRIO_7, + OCELOT_STAT_TX_OCTETS, + OCELOT_STAT_TX_UNICAST, + OCELOT_STAT_TX_MULTICAST, + OCELOT_STAT_TX_BROADCAST, + OCELOT_STAT_TX_COLLISION, + OCELOT_STAT_TX_DROPS, + OCELOT_STAT_TX_PAUSE, + OCELOT_STAT_TX_64, + OCELOT_STAT_TX_65_127, + OCELOT_STAT_TX_128_255, + OCELOT_STAT_TX_256_511, + OCELOT_STAT_TX_512_1023, + OCELOT_STAT_TX_1024_1526, + OCELOT_STAT_TX_1527_MAX, + OCELOT_STAT_TX_YELLOW_PRIO_0, + OCELOT_STAT_TX_YELLOW_PRIO_1, + OCELOT_STAT_TX_YELLOW_PRIO_2, + OCELOT_STAT_TX_YELLOW_PRIO_3, + OCELOT_STAT_TX_YELLOW_PRIO_4, + OCELOT_STAT_TX_YELLOW_PRIO_5, + OCELOT_STAT_TX_YELLOW_PRIO_6, + OCELOT_STAT_TX_YELLOW_PRIO_7, + OCELOT_STAT_TX_GREEN_PRIO_0, + OCELOT_STAT_TX_GREEN_PRIO_1, + OCELOT_STAT_TX_GREEN_PRIO_2, + OCELOT_STAT_TX_GREEN_PRIO_3, + OCELOT_STAT_TX_GREEN_PRIO_4, + OCELOT_STAT_TX_GREEN_PRIO_5, + OCELOT_STAT_TX_GREEN_PRIO_6, + OCELOT_STAT_TX_GREEN_PRIO_7, + OCELOT_STAT_TX_AGED, + OCELOT_STAT_DROP_LOCAL, + OCELOT_STAT_DROP_TAIL, + OCELOT_STAT_DROP_YELLOW_PRIO_0, + OCELOT_STAT_DROP_YELLOW_PRIO_1, + OCELOT_STAT_DROP_YELLOW_PRIO_2, + OCELOT_STAT_DROP_YELLOW_PRIO_3, + OCELOT_STAT_DROP_YELLOW_PRIO_4, + OCELOT_STAT_DROP_YELLOW_PRIO_5, + OCELOT_STAT_DROP_YELLOW_PRIO_6, + OCELOT_STAT_DROP_YELLOW_PRIO_7, + OCELOT_STAT_DROP_GREEN_PRIO_0, + OCELOT_STAT_DROP_GREEN_PRIO_1, + OCELOT_STAT_DROP_GREEN_PRIO_2, + OCELOT_STAT_DROP_GREEN_PRIO_3, + OCELOT_STAT_DROP_GREEN_PRIO_4, + OCELOT_STAT_DROP_GREEN_PRIO_5, + OCELOT_STAT_DROP_GREEN_PRIO_6, + OCELOT_STAT_DROP_GREEN_PRIO_7, + OCELOT_NUM_STATS, +}; + +struct ocelot_stat_layout { + u32 reg; + char name[ETH_GSTRING_LEN]; +}; + +/* 32-bit counter checked for wraparound by ocelot_port_update_stats() + * and copied to ocelot->stats. + */ +#define OCELOT_STAT(kind) \ + [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind } +/* Same as above, except also exported to ethtool -S. Standard counters should + * only be exposed to more specific interfaces rather than by their string name. + */ +#define OCELOT_STAT_ETHTOOL(kind, ethtool_name) \ + [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind, .name = ethtool_name } + +#define OCELOT_COMMON_STATS \ + OCELOT_STAT_ETHTOOL(RX_OCTETS, "rx_octets"), \ + OCELOT_STAT_ETHTOOL(RX_UNICAST, "rx_unicast"), \ + OCELOT_STAT_ETHTOOL(RX_MULTICAST, "rx_multicast"), \ + OCELOT_STAT_ETHTOOL(RX_BROADCAST, "rx_broadcast"), \ + OCELOT_STAT_ETHTOOL(RX_SHORTS, "rx_shorts"), \ + OCELOT_STAT_ETHTOOL(RX_FRAGMENTS, "rx_fragments"), \ + OCELOT_STAT_ETHTOOL(RX_JABBERS, "rx_jabbers"), \ + OCELOT_STAT_ETHTOOL(RX_CRC_ALIGN_ERRS, "rx_crc_align_errs"), \ + OCELOT_STAT_ETHTOOL(RX_SYM_ERRS, "rx_sym_errs"), \ + OCELOT_STAT_ETHTOOL(RX_64, "rx_frames_below_65_octets"), \ + OCELOT_STAT_ETHTOOL(RX_65_127, "rx_frames_65_to_127_octets"), \ + OCELOT_STAT_ETHTOOL(RX_128_255, "rx_frames_128_to_255_octets"), \ + OCELOT_STAT_ETHTOOL(RX_256_511, "rx_frames_256_to_511_octets"), \ + OCELOT_STAT_ETHTOOL(RX_512_1023, "rx_frames_512_to_1023_octets"), \ + OCELOT_STAT_ETHTOOL(RX_1024_1526, "rx_frames_1024_to_1526_octets"), \ + OCELOT_STAT_ETHTOOL(RX_1527_MAX, "rx_frames_over_1526_octets"), \ + OCELOT_STAT_ETHTOOL(RX_PAUSE, "rx_pause"), \ + OCELOT_STAT_ETHTOOL(RX_CONTROL, "rx_control"), \ + OCELOT_STAT_ETHTOOL(RX_LONGS, "rx_longs"), \ + OCELOT_STAT_ETHTOOL(RX_CLASSIFIED_DROPS, "rx_classified_drops"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_0, "rx_red_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_1, "rx_red_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_2, "rx_red_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_3, "rx_red_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_4, "rx_red_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_5, "rx_red_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_6, "rx_red_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_7, "rx_red_prio_7"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_0, "rx_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_1, "rx_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_2, "rx_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_3, "rx_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_4, "rx_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_5, "rx_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_6, "rx_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_7, "rx_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_0, "rx_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_1, "rx_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_2, "rx_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_3, "rx_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_4, "rx_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_5, "rx_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_6, "rx_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_7, "rx_green_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_OCTETS, "tx_octets"), \ + OCELOT_STAT_ETHTOOL(TX_UNICAST, "tx_unicast"), \ + OCELOT_STAT_ETHTOOL(TX_MULTICAST, "tx_multicast"), \ + OCELOT_STAT_ETHTOOL(TX_BROADCAST, "tx_broadcast"), \ + OCELOT_STAT_ETHTOOL(TX_COLLISION, "tx_collision"), \ + OCELOT_STAT_ETHTOOL(TX_DROPS, "tx_drops"), \ + OCELOT_STAT_ETHTOOL(TX_PAUSE, "tx_pause"), \ + OCELOT_STAT_ETHTOOL(TX_64, "tx_frames_below_65_octets"), \ + OCELOT_STAT_ETHTOOL(TX_65_127, "tx_frames_65_to_127_octets"), \ + OCELOT_STAT_ETHTOOL(TX_128_255, "tx_frames_128_255_octets"), \ + OCELOT_STAT_ETHTOOL(TX_256_511, "tx_frames_256_511_octets"), \ + OCELOT_STAT_ETHTOOL(TX_512_1023, "tx_frames_512_1023_octets"), \ + OCELOT_STAT_ETHTOOL(TX_1024_1526, "tx_frames_1024_1526_octets"), \ + OCELOT_STAT_ETHTOOL(TX_1527_MAX, "tx_frames_over_1526_octets"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_0, "tx_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_1, "tx_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_2, "tx_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_3, "tx_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_4, "tx_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_5, "tx_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_6, "tx_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_7, "tx_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_0, "tx_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_1, "tx_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_2, "tx_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_3, "tx_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_4, "tx_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_5, "tx_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_6, "tx_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_7, "tx_green_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_AGED, "tx_aged"), \ + OCELOT_STAT_ETHTOOL(DROP_LOCAL, "drop_local"), \ + OCELOT_STAT_ETHTOOL(DROP_TAIL, "drop_tail"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_0, "drop_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_1, "drop_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_2, "drop_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_3, "drop_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_4, "drop_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_5, "drop_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_6, "drop_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_7, "drop_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_0, "drop_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_1, "drop_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_2, "drop_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_3, "drop_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_4, "drop_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_5, "drop_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_6, "drop_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_7, "drop_green_prio_7") + +struct ocelot_stats_region { + struct list_head node; + u32 base; + int count; + u32 *buf; +}; + +static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = { + OCELOT_COMMON_STATS, +}; + /* Read the counters from hardware and keep them in region->buf. * Caller must hold &ocelot->stat_view_lock. */ @@ -93,10 +312,10 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data) return; for (i = 0; i < OCELOT_NUM_STATS; i++) { - if (ocelot->stats_layout[i].name[0] == '\0') + if (ocelot_stats_layout[i].name[0] == '\0') continue; - memcpy(data + i * ETH_GSTRING_LEN, ocelot->stats_layout[i].name, + memcpy(data + i * ETH_GSTRING_LEN, ocelot_stats_layout[i].name, ETH_GSTRING_LEN); } } @@ -137,7 +356,7 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset) return -EOPNOTSUPP; for (i = 0; i < OCELOT_NUM_STATS; i++) - if (ocelot->stats_layout[i].name[0] != '\0') + if (ocelot_stats_layout[i].name[0] != '\0') num_stats++; return num_stats; @@ -154,7 +373,7 @@ static void ocelot_port_ethtool_stats_cb(struct ocelot *ocelot, int port, for (i = 0; i < OCELOT_NUM_STATS; i++) { int index = port * OCELOT_NUM_STATS + i; - if (ocelot->stats_layout[i].name[0] == '\0') + if (ocelot_stats_layout[i].name[0] == '\0') continue; *data++ = ocelot->stats[index]; @@ -383,16 +602,16 @@ EXPORT_SYMBOL(ocelot_port_get_stats64); static int ocelot_prepare_stats_regions(struct ocelot *ocelot) { struct ocelot_stats_region *region = NULL; - unsigned int last; + unsigned int last = 0; int i; INIT_LIST_HEAD(&ocelot->stats_regions); for (i = 0; i < OCELOT_NUM_STATS; i++) { - if (!ocelot->stats_layout[i].reg) + if (!ocelot_stats_layout[i].reg) continue; - if (region && ocelot->stats_layout[i].reg == last + 4) { + if (region && ocelot_stats_layout[i].reg == last + 4) { region->count++; } else { region = devm_kzalloc(ocelot->dev, sizeof(*region), @@ -400,12 +619,18 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot) if (!region) return -ENOMEM; - region->base = ocelot->stats_layout[i].reg; + /* enum ocelot_stat must be kept sorted in the same + * order as ocelot_stats_layout[i].reg in order to have + * efficient bulking + */ + WARN_ON(last >= ocelot_stats_layout[i].reg); + + region->base = ocelot_stats_layout[i].reg; region->count = 1; list_add_tail(®ion->node, &ocelot->stats_regions); } - last = ocelot->stats_layout[i].reg; + last = ocelot_stats_layout[i].reg; } list_for_each_entry(region, &ocelot->stats_regions, node) { @@ -456,3 +681,4 @@ void ocelot_stats_deinit(struct ocelot *ocelot) cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); } + diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 6f22aea08a64..b097fd4a4061 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -100,10 +100,6 @@ static const struct reg_field ocelot_regfields[REGFIELD_MAX] = { [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4), }; -static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = { - OCELOT_COMMON_STATS, -}; - static void ocelot_pll5_init(struct ocelot *ocelot) { /* Configure PLL5. This will need a proper CCF driver @@ -138,7 +134,6 @@ static int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) int ret; ocelot->map = ocelot_regmap; - ocelot->stats_layout = ocelot_stats_layout; ocelot->num_mact_rows = 1024; ocelot->ops = ops; @@ -377,9 +372,6 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev, return -ENOMEM; for_each_available_child_of_node(ports, portnp) { - struct ocelot_port_private *priv; - struct ocelot_port *ocelot_port; - struct devlink_port *dlp; struct regmap *target; struct resource *res; char res_name[8]; @@ -420,12 +412,6 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev, } devlink_ports_registered |= BIT(port); - - ocelot_port = ocelot->ports[port]; - priv = container_of(ocelot_port, struct ocelot_port_private, - port); - dlp = &ocelot->devlink_ports[port]; - devlink_port_type_eth_set(dlp, priv->dev); } /* Initialize unused devlink ports at the end */ diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 9063e2e22cd5..8073d7a90a26 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -552,8 +552,7 @@ myri10ge_validate_firmware(struct myri10ge_priv *mgp, } /* save firmware version for ethtool */ - strncpy(mgp->fw_version, hdr->version, sizeof(mgp->fw_version)); - mgp->fw_version[sizeof(mgp->fw_version) - 1] = '\0'; + strscpy(mgp->fw_version, hdr->version, sizeof(mgp->fw_version)); sscanf(mgp->fw_version, "%d.%d.%d", &mgp->fw_ver_major, &mgp->fw_ver_minor, &mgp->fw_ver_tiny); diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig index 8844d1ac053a..e785c00b5845 100644 --- a/drivers/net/ethernet/netronome/Kconfig +++ b/drivers/net/ethernet/netronome/Kconfig @@ -54,6 +54,17 @@ config NFP_APP_ABM_NIC functionality. Code will be built into the nfp.ko driver. +config NFP_NET_IPSEC + bool "NFP IPsec crypto offload support" + depends on NFP + depends on XFRM_OFFLOAD + default y + help + Enable driver support IPsec crypto offload on NFP NIC. + Say Y, if you are planning to make use of IPsec crypto + offload. NOTE that IPsec crypto offload on NFP NIC + requires specific FW to work. + config NFP_DEBUG bool "Debug support for Netronome(R) NFP4000/NFP6000 NIC drivers" depends on NFP diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index 9c0861d03634..8a250214e289 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -80,4 +80,6 @@ nfp-objs += \ abm/main.o endif +nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o + nfp-$(CONFIG_NFP_DEBUG) += nfp_net_debugfs.o diff --git a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c index 4247bca09807..aa8aba4ff7aa 100644 --- a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c +++ b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c @@ -503,7 +503,7 @@ nfp_ccm_mbox_msg_prepare(struct nfp_net *nn, struct sk_buff *skb, max_len = max(max_reply_size, round_up(skb->len, 4)); if (max_len > mbox_max) { nn_dp_warn(&nn->dp, - "message too big for tha mailbox: %u/%u vs %u\n", + "message too big for the mailbox: %u/%u vs %u\n", skb->len, max_reply_size, mbox_max); return -EMSGSIZE; } diff --git a/drivers/net/ethernet/netronome/nfp/crypto/crypto.h b/drivers/net/ethernet/netronome/nfp/crypto/crypto.h index bffe58bb2f27..1df73d658938 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/crypto.h +++ b/drivers/net/ethernet/netronome/nfp/crypto/crypto.h @@ -39,4 +39,27 @@ nfp_net_tls_rx_resync_req(struct net_device *netdev, } #endif +/* IPsec related structures and functions */ +struct nfp_ipsec_offload { + u32 seq_hi; + u32 seq_low; + u32 handle; +}; + +#ifndef CONFIG_NFP_NET_IPSEC +static inline void nfp_net_ipsec_init(struct nfp_net *nn) +{ +} + +static inline void nfp_net_ipsec_clean(struct nfp_net *nn) +{ +} +#else +void nfp_net_ipsec_init(struct nfp_net *nn); +void nfp_net_ipsec_clean(struct nfp_net *nn); +bool nfp_net_ipsec_tx_prep(struct nfp_net_dp *dp, struct sk_buff *skb, + struct nfp_ipsec_offload *offload_info); +int nfp_net_ipsec_rx(struct nfp_meta_parsed *meta, struct sk_buff *skb); +#endif + #endif diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c new file mode 100644 index 000000000000..4632268695cb --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c @@ -0,0 +1,592 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc */ +/* Copyright (C) 2021 Corigine, Inc */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <asm/unaligned.h> +#include <linux/ktime.h> +#include <net/xfrm.h> + +#include "../nfp_net_ctrl.h" +#include "../nfp_net.h" +#include "crypto.h" + +#define NFP_NET_IPSEC_MAX_SA_CNT (16 * 1024) /* Firmware support a maximum of 16K SA offload */ + +/* IPsec config message cmd codes */ +enum nfp_ipsec_cfg_mssg_cmd_codes { + NFP_IPSEC_CFG_MSSG_ADD_SA, /* Add a new SA */ + NFP_IPSEC_CFG_MSSG_INV_SA /* Invalidate an existing SA */ +}; + +/* IPsec config message response codes */ +enum nfp_ipsec_cfg_mssg_rsp_codes { + NFP_IPSEC_CFG_MSSG_OK, + NFP_IPSEC_CFG_MSSG_FAILED, + NFP_IPSEC_CFG_MSSG_SA_VALID, + NFP_IPSEC_CFG_MSSG_SA_HASH_ADD_FAILED, + NFP_IPSEC_CFG_MSSG_SA_HASH_DEL_FAILED, + NFP_IPSEC_CFG_MSSG_SA_INVALID_CMD +}; + +/* Protocol */ +enum nfp_ipsec_sa_prot { + NFP_IPSEC_PROTOCOL_AH = 0, + NFP_IPSEC_PROTOCOL_ESP = 1 +}; + +/* Mode */ +enum nfp_ipsec_sa_mode { + NFP_IPSEC_PROTMODE_TRANSPORT = 0, + NFP_IPSEC_PROTMODE_TUNNEL = 1 +}; + +/* Cipher types */ +enum nfp_ipsec_sa_cipher { + NFP_IPSEC_CIPHER_NULL, + NFP_IPSEC_CIPHER_3DES, + NFP_IPSEC_CIPHER_AES128, + NFP_IPSEC_CIPHER_AES192, + NFP_IPSEC_CIPHER_AES256, + NFP_IPSEC_CIPHER_AES128_NULL, + NFP_IPSEC_CIPHER_AES192_NULL, + NFP_IPSEC_CIPHER_AES256_NULL, + NFP_IPSEC_CIPHER_CHACHA20 +}; + +/* Cipher modes */ +enum nfp_ipsec_sa_cipher_mode { + NFP_IPSEC_CIMODE_ECB, + NFP_IPSEC_CIMODE_CBC, + NFP_IPSEC_CIMODE_CFB, + NFP_IPSEC_CIMODE_OFB, + NFP_IPSEC_CIMODE_CTR +}; + +/* Hash types */ +enum nfp_ipsec_sa_hash_type { + NFP_IPSEC_HASH_NONE, + NFP_IPSEC_HASH_MD5_96, + NFP_IPSEC_HASH_SHA1_96, + NFP_IPSEC_HASH_SHA256_96, + NFP_IPSEC_HASH_SHA384_96, + NFP_IPSEC_HASH_SHA512_96, + NFP_IPSEC_HASH_MD5_128, + NFP_IPSEC_HASH_SHA1_80, + NFP_IPSEC_HASH_SHA256_128, + NFP_IPSEC_HASH_SHA384_192, + NFP_IPSEC_HASH_SHA512_256, + NFP_IPSEC_HASH_GF128_128, + NFP_IPSEC_HASH_POLY1305_128 +}; + +/* IPSEC_CFG_MSSG_ADD_SA */ +struct nfp_ipsec_cfg_add_sa { + u32 ciph_key[8]; /* Cipher Key */ + union { + u32 auth_key[16]; /* Authentication Key */ + struct nfp_ipsec_aesgcm { /* AES-GCM-ESP fields */ + u32 salt; /* Initialized with SA */ + u32 resv[15]; + } aesgcm_fields; + }; + struct sa_ctrl_word { + uint32_t hash :4; /* From nfp_ipsec_sa_hash_type */ + uint32_t cimode :4; /* From nfp_ipsec_sa_cipher_mode */ + uint32_t cipher :4; /* From nfp_ipsec_sa_cipher */ + uint32_t mode :2; /* From nfp_ipsec_sa_mode */ + uint32_t proto :2; /* From nfp_ipsec_sa_prot */ + uint32_t dir :1; /* SA direction */ + uint32_t resv0 :12; + uint32_t encap_dsbl:1; /* Encap/Decap disable */ + uint32_t resv1 :2; /* Must be set to 0 */ + } ctrl_word; + u32 spi; /* SPI Value */ + uint32_t pmtu_limit :16; /* PMTU Limit */ + uint32_t resv0 :5; + uint32_t ipv6 :1; /* Outbound IPv6 addr format */ + uint32_t resv1 :10; + u32 resv2[2]; + u32 src_ip[4]; /* Src IP addr */ + u32 dst_ip[4]; /* Dst IP addr */ + u32 resv3[6]; +}; + +/* IPSEC_CFG_MSSG */ +struct nfp_ipsec_cfg_mssg { + union { + struct{ + uint32_t cmd:16; /* One of nfp_ipsec_cfg_mssg_cmd_codes */ + uint32_t rsp:16; /* One of nfp_ipsec_cfg_mssg_rsp_codes */ + uint32_t sa_idx:16; /* SA table index */ + uint32_t spare0:16; + struct nfp_ipsec_cfg_add_sa cfg_add_sa; + }; + u32 raw[64]; + }; +}; + +static int nfp_ipsec_cfg_cmd_issue(struct nfp_net *nn, int type, int saidx, + struct nfp_ipsec_cfg_mssg *msg) +{ + int i, msg_size, ret; + + msg->cmd = type; + msg->sa_idx = saidx; + msg->rsp = 0; + msg_size = ARRAY_SIZE(msg->raw); + + for (i = 0; i < msg_size; i++) + nn_writel(nn, NFP_NET_CFG_MBOX_VAL + 4 * i, msg->raw[i]); + + ret = nfp_net_mbox_reconfig(nn, NFP_NET_CFG_MBOX_CMD_IPSEC); + if (ret < 0) + return ret; + + /* For now we always read the whole message response back */ + for (i = 0; i < msg_size; i++) + msg->raw[i] = nn_readl(nn, NFP_NET_CFG_MBOX_VAL + 4 * i); + + switch (msg->rsp) { + case NFP_IPSEC_CFG_MSSG_OK: + return 0; + case NFP_IPSEC_CFG_MSSG_SA_INVALID_CMD: + return -EINVAL; + case NFP_IPSEC_CFG_MSSG_SA_VALID: + return -EEXIST; + case NFP_IPSEC_CFG_MSSG_FAILED: + case NFP_IPSEC_CFG_MSSG_SA_HASH_ADD_FAILED: + case NFP_IPSEC_CFG_MSSG_SA_HASH_DEL_FAILED: + return -EIO; + default: + return -EINVAL; + } +} + +static int set_aes_keylen(struct nfp_ipsec_cfg_add_sa *cfg, int alg, int keylen) +{ + bool aes_gmac = (alg == SADB_X_EALG_NULL_AES_GMAC); + + switch (keylen) { + case 128: + cfg->ctrl_word.cipher = aes_gmac ? NFP_IPSEC_CIPHER_AES128_NULL : + NFP_IPSEC_CIPHER_AES128; + break; + case 192: + cfg->ctrl_word.cipher = aes_gmac ? NFP_IPSEC_CIPHER_AES192_NULL : + NFP_IPSEC_CIPHER_AES192; + break; + case 256: + cfg->ctrl_word.cipher = aes_gmac ? NFP_IPSEC_CIPHER_AES256_NULL : + NFP_IPSEC_CIPHER_AES256; + break; + default: + return -EINVAL; + } + + return 0; +} + +static void set_md5hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len) +{ + switch (*trunc_len) { + case 96: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_MD5_96; + break; + case 128: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_MD5_128; + break; + default: + *trunc_len = 0; + } +} + +static void set_sha1hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len) +{ + switch (*trunc_len) { + case 96: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA1_96; + break; + case 80: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA1_80; + break; + default: + *trunc_len = 0; + } +} + +static void set_sha2_256hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len) +{ + switch (*trunc_len) { + case 96: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA256_96; + break; + case 128: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA256_128; + break; + default: + *trunc_len = 0; + } +} + +static void set_sha2_384hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len) +{ + switch (*trunc_len) { + case 96: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA384_96; + break; + case 192: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA384_192; + break; + default: + *trunc_len = 0; + } +} + +static void set_sha2_512hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len) +{ + switch (*trunc_len) { + case 96: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA512_96; + break; + case 256: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_SHA512_256; + break; + default: + *trunc_len = 0; + } +} + +static int nfp_net_xfrm_add_state(struct xfrm_state *x) +{ + struct net_device *netdev = x->xso.dev; + struct nfp_ipsec_cfg_mssg msg = {}; + int i, key_len, trunc_len, err = 0; + struct nfp_ipsec_cfg_add_sa *cfg; + struct nfp_net *nn; + unsigned int saidx; + + nn = netdev_priv(netdev); + cfg = &msg.cfg_add_sa; + + /* General */ + switch (x->props.mode) { + case XFRM_MODE_TUNNEL: + cfg->ctrl_word.mode = NFP_IPSEC_PROTMODE_TUNNEL; + break; + case XFRM_MODE_TRANSPORT: + cfg->ctrl_word.mode = NFP_IPSEC_PROTMODE_TRANSPORT; + break; + default: + nn_err(nn, "Unsupported mode for xfrm offload\n"); + return -EINVAL; + } + + switch (x->id.proto) { + case IPPROTO_ESP: + cfg->ctrl_word.proto = NFP_IPSEC_PROTOCOL_ESP; + break; + case IPPROTO_AH: + cfg->ctrl_word.proto = NFP_IPSEC_PROTOCOL_AH; + break; + default: + nn_err(nn, "Unsupported protocol for xfrm offload\n"); + return -EINVAL; + } + + if (x->props.flags & XFRM_STATE_ESN) { + nn_err(nn, "Unsupported XFRM_REPLAY_MODE_ESN for xfrm offload\n"); + return -EINVAL; + } + + if (x->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { + nn_err(nn, "Unsupported xfrm offload tyoe\n"); + return -EINVAL; + } + + cfg->spi = ntohl(x->id.spi); + + /* Hash/Authentication */ + if (x->aalg) + trunc_len = x->aalg->alg_trunc_len; + else + trunc_len = 0; + + switch (x->props.aalgo) { + case SADB_AALG_NONE: + if (x->aead) { + trunc_len = -1; + } else { + nn_err(nn, "Unsupported authentication algorithm\n"); + return -EINVAL; + } + break; + case SADB_X_AALG_NULL: + cfg->ctrl_word.hash = NFP_IPSEC_HASH_NONE; + trunc_len = -1; + break; + case SADB_AALG_MD5HMAC: + set_md5hmac(cfg, &trunc_len); + break; + case SADB_AALG_SHA1HMAC: + set_sha1hmac(cfg, &trunc_len); + break; + case SADB_X_AALG_SHA2_256HMAC: + set_sha2_256hmac(cfg, &trunc_len); + break; + case SADB_X_AALG_SHA2_384HMAC: + set_sha2_384hmac(cfg, &trunc_len); + break; + case SADB_X_AALG_SHA2_512HMAC: + set_sha2_512hmac(cfg, &trunc_len); + break; + default: + nn_err(nn, "Unsupported authentication algorithm\n"); + return -EINVAL; + } + + if (!trunc_len) { + nn_err(nn, "Unsupported authentication algorithm trunc length\n"); + return -EINVAL; + } + + if (x->aalg) { + key_len = DIV_ROUND_UP(x->aalg->alg_key_len, BITS_PER_BYTE); + if (key_len > sizeof(cfg->auth_key)) { + nn_err(nn, "Insufficient space for offloaded auth key\n"); + return -EINVAL; + } + for (i = 0; i < key_len / sizeof(cfg->auth_key[0]) ; i++) + cfg->auth_key[i] = get_unaligned_be32(x->aalg->alg_key + + sizeof(cfg->auth_key[0]) * i); + } + + /* Encryption */ + switch (x->props.ealgo) { + case SADB_EALG_NONE: + case SADB_EALG_NULL: + cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CBC; + cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_NULL; + break; + case SADB_EALG_3DESCBC: + cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CBC; + cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_3DES; + break; + case SADB_X_EALG_AES_GCM_ICV16: + case SADB_X_EALG_NULL_AES_GMAC: + if (!x->aead) { + nn_err(nn, "Invalid AES key data\n"); + return -EINVAL; + } + + if (x->aead->alg_icv_len != 128) { + nn_err(nn, "ICV must be 128bit with SADB_X_EALG_AES_GCM_ICV16\n"); + return -EINVAL; + } + cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CTR; + cfg->ctrl_word.hash = NFP_IPSEC_HASH_GF128_128; + + /* Aead->alg_key_len includes 32-bit salt */ + if (set_aes_keylen(cfg, x->props.ealgo, x->aead->alg_key_len - 32)) { + nn_err(nn, "Unsupported AES key length %d\n", x->aead->alg_key_len); + return -EINVAL; + } + break; + case SADB_X_EALG_AESCBC: + cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CBC; + if (!x->ealg) { + nn_err(nn, "Invalid AES key data\n"); + return -EINVAL; + } + if (set_aes_keylen(cfg, x->props.ealgo, x->ealg->alg_key_len) < 0) { + nn_err(nn, "Unsupported AES key length %d\n", x->ealg->alg_key_len); + return -EINVAL; + } + break; + default: + nn_err(nn, "Unsupported encryption algorithm for offload\n"); + return -EINVAL; + } + + if (x->aead) { + int salt_len = 4; + + key_len = DIV_ROUND_UP(x->aead->alg_key_len, BITS_PER_BYTE); + key_len -= salt_len; + + if (key_len > sizeof(cfg->ciph_key)) { + nn_err(nn, "aead: Insufficient space for offloaded key\n"); + return -EINVAL; + } + + for (i = 0; i < key_len / sizeof(cfg->ciph_key[0]) ; i++) + cfg->ciph_key[i] = get_unaligned_be32(x->aead->alg_key + + sizeof(cfg->ciph_key[0]) * i); + + /* Load up the salt */ + cfg->aesgcm_fields.salt = get_unaligned_be32(x->aead->alg_key + key_len); + } + + if (x->ealg) { + key_len = DIV_ROUND_UP(x->ealg->alg_key_len, BITS_PER_BYTE); + + if (key_len > sizeof(cfg->ciph_key)) { + nn_err(nn, "ealg: Insufficient space for offloaded key\n"); + return -EINVAL; + } + for (i = 0; i < key_len / sizeof(cfg->ciph_key[0]) ; i++) + cfg->ciph_key[i] = get_unaligned_be32(x->ealg->alg_key + + sizeof(cfg->ciph_key[0]) * i); + } + + /* IP related info */ + switch (x->props.family) { + case AF_INET: + cfg->ipv6 = 0; + cfg->src_ip[0] = ntohl(x->props.saddr.a4); + cfg->dst_ip[0] = ntohl(x->id.daddr.a4); + break; + case AF_INET6: + cfg->ipv6 = 1; + for (i = 0; i < 4; i++) { + cfg->src_ip[i] = ntohl(x->props.saddr.a6[i]); + cfg->dst_ip[i] = ntohl(x->id.daddr.a6[i]); + } + break; + default: + nn_err(nn, "Unsupported address family\n"); + return -EINVAL; + } + + /* Maximum nic IPsec code could handle. Other limits may apply. */ + cfg->pmtu_limit = 0xffff; + cfg->ctrl_word.encap_dsbl = 1; + + /* SA direction */ + cfg->ctrl_word.dir = x->xso.dir; + + /* Find unused SA data*/ + err = xa_alloc(&nn->xa_ipsec, &saidx, x, + XA_LIMIT(0, NFP_NET_IPSEC_MAX_SA_CNT - 1), GFP_KERNEL); + if (err < 0) { + nn_err(nn, "Unable to get sa_data number for IPsec\n"); + return err; + } + + /* Allocate saidx and commit the SA */ + err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_ADD_SA, saidx, &msg); + if (err) { + xa_erase(&nn->xa_ipsec, saidx); + nn_err(nn, "Failed to issue IPsec command err ret=%d\n", err); + return err; + } + + /* 0 is invalid offload_handle for kernel */ + x->xso.offload_handle = saidx + 1; + return 0; +} + +static void nfp_net_xfrm_del_state(struct xfrm_state *x) +{ + struct net_device *netdev = x->xso.dev; + struct nfp_ipsec_cfg_mssg msg; + struct nfp_net *nn; + int err; + + nn = netdev_priv(netdev); + err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_INV_SA, + x->xso.offload_handle - 1, &msg); + if (err) + nn_warn(nn, "Failed to invalidate SA in hardware\n"); + + xa_erase(&nn->xa_ipsec, x->xso.offload_handle - 1); +} + +static bool nfp_net_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + if (x->props.family == AF_INET) + /* Offload with IPv4 options is not supported yet */ + return ip_hdr(skb)->ihl == 5; + + /* Offload with IPv6 extension headers is not support yet */ + return !(ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)); +} + +static const struct xfrmdev_ops nfp_net_ipsec_xfrmdev_ops = { + .xdo_dev_state_add = nfp_net_xfrm_add_state, + .xdo_dev_state_delete = nfp_net_xfrm_del_state, + .xdo_dev_offload_ok = nfp_net_ipsec_offload_ok, +}; + +void nfp_net_ipsec_init(struct nfp_net *nn) +{ + if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_IPSEC)) + return; + + xa_init_flags(&nn->xa_ipsec, XA_FLAGS_ALLOC); + nn->dp.netdev->xfrmdev_ops = &nfp_net_ipsec_xfrmdev_ops; +} + +void nfp_net_ipsec_clean(struct nfp_net *nn) +{ + if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_IPSEC)) + return; + + WARN_ON(!xa_empty(&nn->xa_ipsec)); + xa_destroy(&nn->xa_ipsec); +} + +bool nfp_net_ipsec_tx_prep(struct nfp_net_dp *dp, struct sk_buff *skb, + struct nfp_ipsec_offload *offload_info) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + struct xfrm_state *x; + + x = xfrm_input_state(skb); + if (!x) + return false; + + offload_info->seq_hi = xo->seq.hi; + offload_info->seq_low = xo->seq.low; + offload_info->handle = x->xso.offload_handle; + + return true; +} + +int nfp_net_ipsec_rx(struct nfp_meta_parsed *meta, struct sk_buff *skb) +{ + struct net_device *netdev = skb->dev; + struct xfrm_offload *xo; + struct xfrm_state *x; + struct sec_path *sp; + struct nfp_net *nn; + u32 saidx; + + nn = netdev_priv(netdev); + + saidx = meta->ipsec_saidx - 1; + if (saidx >= NFP_NET_IPSEC_MAX_SA_CNT) + return -EINVAL; + + sp = secpath_set(skb); + if (unlikely(!sp)) + return -ENOMEM; + + xa_lock(&nn->xa_ipsec); + x = xa_load(&nn->xa_ipsec, saidx); + xa_unlock(&nn->xa_ipsec); + if (!x) + return -EINVAL; + + xfrm_state_hold(x); + sp->xvec[sp->len++] = x; + sp->olen++; + xo = xfrm_offload(skb); + xo->flags = CRYPTO_DONE; + xo->status = CRYPTO_SUCCESS; + + return 0; +} diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c index e92860e20a24..88d6d992e7d0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c @@ -154,10 +154,11 @@ nfp_fl_lag_find_group_for_master_with_lag(struct nfp_fl_lag *lag, return NULL; } -int nfp_flower_lag_populate_pre_action(struct nfp_app *app, - struct net_device *master, - struct nfp_fl_pre_lag *pre_act, - struct netlink_ext_ack *extack) +static int nfp_fl_lag_get_group_info(struct nfp_app *app, + struct net_device *netdev, + __be16 *group_id, + u8 *batch_ver, + u8 *group_inst) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_lag_group *group = NULL; @@ -165,23 +166,52 @@ int nfp_flower_lag_populate_pre_action(struct nfp_app *app, mutex_lock(&priv->nfp_lag.lock); group = nfp_fl_lag_find_group_for_master_with_lag(&priv->nfp_lag, - master); + netdev); if (!group) { mutex_unlock(&priv->nfp_lag.lock); - NL_SET_ERR_MSG_MOD(extack, "invalid entry: group does not exist for LAG action"); return -ENOENT; } - pre_act->group_id = cpu_to_be16(group->group_id); - temp_vers = cpu_to_be32(priv->nfp_lag.batch_ver << - NFP_FL_PRE_LAG_VER_OFF); - memcpy(pre_act->lag_version, &temp_vers, 3); - pre_act->instance = group->group_inst; + if (group_id) + *group_id = cpu_to_be16(group->group_id); + + if (batch_ver) { + temp_vers = cpu_to_be32(priv->nfp_lag.batch_ver << + NFP_FL_PRE_LAG_VER_OFF); + memcpy(batch_ver, &temp_vers, 3); + } + + if (group_inst) + *group_inst = group->group_inst; + mutex_unlock(&priv->nfp_lag.lock); return 0; } +int nfp_flower_lag_populate_pre_action(struct nfp_app *app, + struct net_device *master, + struct nfp_fl_pre_lag *pre_act, + struct netlink_ext_ack *extack) +{ + if (nfp_fl_lag_get_group_info(app, master, &pre_act->group_id, + pre_act->lag_version, + &pre_act->instance)) { + NL_SET_ERR_MSG_MOD(extack, "invalid entry: group does not exist for LAG action"); + return -ENOENT; + } + + return 0; +} + +void nfp_flower_lag_get_info_from_netdev(struct nfp_app *app, + struct net_device *netdev, + struct nfp_tun_neigh_lag *lag) +{ + nfp_fl_lag_get_group_info(app, netdev, NULL, + lag->lag_version, &lag->lag_instance); +} + int nfp_flower_lag_get_output_id(struct nfp_app *app, struct net_device *master) { struct nfp_flower_priv *priv = app->priv; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 4d960a9641b3..83eaa5ae3cd4 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -76,7 +76,9 @@ nfp_flower_get_internal_port_id(struct nfp_app *app, struct net_device *netdev) u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, struct net_device *netdev) { + struct nfp_flower_priv *priv = app->priv; int ext_port; + int gid; if (nfp_netdev_is_nfp_repr(netdev)) { return nfp_repr_get_port_id(netdev); @@ -86,6 +88,13 @@ u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, return 0; return nfp_flower_internal_port_get_port_id(ext_port); + } else if (netif_is_lag_master(netdev) && + priv->flower_ext_feats & NFP_FL_FEATS_TUNNEL_NEIGH_LAG) { + gid = nfp_flower_lag_get_output_id(app, netdev); + if (gid < 0) + return 0; + + return (NFP_FL_LAG_OUT | gid); } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index cb799d18682d..40372545148e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -52,6 +52,7 @@ struct nfp_app; #define NFP_FL_FEATS_QOS_PPS BIT(9) #define NFP_FL_FEATS_QOS_METER BIT(10) #define NFP_FL_FEATS_DECAP_V2 BIT(11) +#define NFP_FL_FEATS_TUNNEL_NEIGH_LAG BIT(12) #define NFP_FL_FEATS_HOST_ACK BIT(31) #define NFP_FL_ENABLE_FLOW_MERGE BIT(0) @@ -69,7 +70,8 @@ struct nfp_app; NFP_FL_FEATS_VLAN_QINQ | \ NFP_FL_FEATS_QOS_PPS | \ NFP_FL_FEATS_QOS_METER | \ - NFP_FL_FEATS_DECAP_V2) + NFP_FL_FEATS_DECAP_V2 | \ + NFP_FL_FEATS_TUNNEL_NEIGH_LAG) struct nfp_fl_mask_id { struct circ_buf mask_id_free_list; @@ -104,6 +106,16 @@ struct nfp_fl_tunnel_offloads { }; /** + * struct nfp_tun_neigh_lag - lag info + * @lag_version: lag version + * @lag_instance: lag instance + */ +struct nfp_tun_neigh_lag { + u8 lag_version[3]; + u8 lag_instance; +}; + +/** * struct nfp_tun_neigh - basic neighbour data * @dst_addr: Destination MAC address * @src_addr: Source MAC address @@ -133,12 +145,14 @@ struct nfp_tun_neigh_ext { * @src_ipv4: Source IPv4 address * @common: Neighbour/route common info * @ext: Neighbour/route extended info + * @lag: lag port info */ struct nfp_tun_neigh_v4 { __be32 dst_ipv4; __be32 src_ipv4; struct nfp_tun_neigh common; struct nfp_tun_neigh_ext ext; + struct nfp_tun_neigh_lag lag; }; /** @@ -147,12 +161,14 @@ struct nfp_tun_neigh_v4 { * @src_ipv6: Source IPv6 address * @common: Neighbour/route common info * @ext: Neighbour/route extended info + * @lag: lag port info */ struct nfp_tun_neigh_v6 { struct in6_addr dst_ipv6; struct in6_addr src_ipv6; struct nfp_tun_neigh common; struct nfp_tun_neigh_ext ext; + struct nfp_tun_neigh_lag lag; }; /** @@ -647,6 +663,9 @@ int nfp_flower_lag_populate_pre_action(struct nfp_app *app, struct netlink_ext_ack *extack); int nfp_flower_lag_get_output_id(struct nfp_app *app, struct net_device *master); +void nfp_flower_lag_get_info_from_netdev(struct nfp_app *app, + struct net_device *netdev, + struct nfp_tun_neigh_lag *lag); void nfp_flower_qos_init(struct nfp_app *app); void nfp_flower_qos_cleanup(struct nfp_app *app); int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev, diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 52f67157bd0f..a8678d5612ee 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -290,6 +290,11 @@ nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata, mtype == NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6)) plen -= sizeof(struct nfp_tun_neigh_ext); + if (!(priv->flower_ext_feats & NFP_FL_FEATS_TUNNEL_NEIGH_LAG) && + (mtype == NFP_FLOWER_CMSG_TYPE_TUN_NEIGH || + mtype == NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6)) + plen -= sizeof(struct nfp_tun_neigh_lag); + skb = nfp_flower_cmsg_alloc(app, plen, mtype, flag); if (!skb) return -ENOMEM; @@ -468,6 +473,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, neigh_table_params); if (!nn_entry && !neigh_invalid) { struct nfp_tun_neigh_ext *ext; + struct nfp_tun_neigh_lag *lag; struct nfp_tun_neigh *common; nn_entry = kzalloc(sizeof(*nn_entry) + neigh_size, @@ -488,6 +494,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload->dst_ipv6 = flowi6->daddr; common = &payload->common; ext = &payload->ext; + lag = &payload->lag; mtype = NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6; } else { struct flowi4 *flowi4 = (struct flowi4 *)flow; @@ -498,6 +505,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload->dst_ipv4 = flowi4->daddr; common = &payload->common; ext = &payload->ext; + lag = &payload->lag; mtype = NFP_FLOWER_CMSG_TYPE_TUN_NEIGH; } ext->host_ctx = cpu_to_be32(U32_MAX); @@ -505,6 +513,9 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, ext->vlan_tci = cpu_to_be16(U16_MAX); ether_addr_copy(common->src_addr, netdev->dev_addr); neigh_ha_snapshot(common->dst_addr, neigh, netdev); + + if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) + nfp_flower_lag_get_info_from_netdev(app, netdev, lag); common->port_id = cpu_to_be32(port_id); if (rhashtable_insert_fast(&priv->neigh_table, @@ -547,13 +558,38 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, if (nn_entry->flow) list_del(&nn_entry->list_head); kfree(nn_entry); - } else if (nn_entry && !neigh_invalid && override) { - mtype = is_ipv6 ? NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6 : - NFP_FLOWER_CMSG_TYPE_TUN_NEIGH; - nfp_tun_link_predt_entries(app, nn_entry); - nfp_flower_xmit_tun_conf(app, mtype, neigh_size, - nn_entry->payload, - GFP_ATOMIC); + } else if (nn_entry && !neigh_invalid) { + struct nfp_tun_neigh *common; + u8 dst_addr[ETH_ALEN]; + bool is_mac_change; + + if (is_ipv6) { + struct nfp_tun_neigh_v6 *payload; + + payload = (struct nfp_tun_neigh_v6 *)nn_entry->payload; + common = &payload->common; + mtype = NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6; + } else { + struct nfp_tun_neigh_v4 *payload; + + payload = (struct nfp_tun_neigh_v4 *)nn_entry->payload; + common = &payload->common; + mtype = NFP_FLOWER_CMSG_TYPE_TUN_NEIGH; + } + + ether_addr_copy(dst_addr, common->dst_addr); + neigh_ha_snapshot(common->dst_addr, neigh, netdev); + is_mac_change = !ether_addr_equal(dst_addr, common->dst_addr); + if (override || is_mac_change) { + if (is_mac_change && nn_entry->flow) { + list_del(&nn_entry->list_head); + nn_entry->flow = NULL; + } + nfp_tun_link_predt_entries(app, nn_entry); + nfp_flower_xmit_tun_conf(app, mtype, neigh_size, + nn_entry->payload, + GFP_ATOMIC); + } } spin_unlock_bh(&priv->predt_lock); @@ -593,8 +629,7 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb); app = app_priv->app; - if (!nfp_netdev_is_nfp_repr(n->dev) && - !nfp_flower_internal_port_can_offload(app, n->dev)) + if (!nfp_flower_get_port_id_from_netdev(app, n->dev)) return NOTIFY_DONE; #if IS_ENABLED(CONFIG_INET) diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c index 448c1c1afaee..861082c5dbff 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c @@ -4,6 +4,7 @@ #include <linux/bpf_trace.h> #include <linux/netdevice.h> #include <linux/bitfield.h> +#include <net/xfrm.h> #include "../nfp_app.h" #include "../nfp_net.h" @@ -167,28 +168,34 @@ nfp_nfd3_tx_csum(struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec, u64_stats_update_end(&r_vec->tx_sync); } -static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, u64 tls_handle) +static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, + u64 tls_handle, bool *ipsec) { struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct nfp_ipsec_offload offload_info; unsigned char *data; bool vlan_insert; u32 meta_id = 0; int md_bytes; - if (unlikely(md_dst || tls_handle)) { - if (unlikely(md_dst && md_dst->type != METADATA_HW_PORT_MUX)) - md_dst = NULL; - } +#ifdef CONFIG_NFP_NET_IPSEC + if (xfrm_offload(skb)) + *ipsec = nfp_net_ipsec_tx_prep(dp, skb, &offload_info); +#endif + + if (unlikely(md_dst && md_dst->type != METADATA_HW_PORT_MUX)) + md_dst = NULL; vlan_insert = skb_vlan_tag_present(skb) && (dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN_V2); - if (!(md_dst || tls_handle || vlan_insert)) + if (!(md_dst || tls_handle || vlan_insert || *ipsec)) return 0; md_bytes = sizeof(meta_id) + !!md_dst * NFP_NET_META_PORTID_SIZE + !!tls_handle * NFP_NET_META_CONN_HANDLE_SIZE + - vlan_insert * NFP_NET_META_VLAN_SIZE; + vlan_insert * NFP_NET_META_VLAN_SIZE + + *ipsec * NFP_NET_META_IPSEC_FIELD_SIZE; /* IPsec has 12 bytes of metadata */ if (unlikely(skb_cow_head(skb, md_bytes))) return -ENOMEM; @@ -218,6 +225,19 @@ static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, u64 meta_id <<= NFP_NET_META_FIELD_SIZE; meta_id |= NFP_NET_META_VLAN; } + if (*ipsec) { + /* IPsec has three consecutive 4-bit IPsec metadata types, + * so in total IPsec has three 4 bytes of metadata. + */ + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_hi, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_low, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.handle - 1, data); + meta_id <<= NFP_NET_META_IPSEC_FIELD_SIZE; + meta_id |= NFP_NET_META_IPSEC << 8 | NFP_NET_META_IPSEC << 4 | NFP_NET_META_IPSEC; + } data -= sizeof(meta_id); put_unaligned_be32(meta_id, data); @@ -246,6 +266,7 @@ netdev_tx_t nfp_nfd3_tx(struct sk_buff *skb, struct net_device *netdev) dma_addr_t dma_addr; unsigned int fsize; u64 tls_handle = 0; + bool ipsec = false; u16 qidx; dp = &nn->dp; @@ -273,7 +294,7 @@ netdev_tx_t nfp_nfd3_tx(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - md_bytes = nfp_nfd3_prep_tx_meta(dp, skb, tls_handle); + md_bytes = nfp_nfd3_prep_tx_meta(dp, skb, tls_handle, &ipsec); if (unlikely(md_bytes < 0)) goto err_flush; @@ -312,6 +333,8 @@ netdev_tx_t nfp_nfd3_tx(struct sk_buff *skb, struct net_device *netdev) txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb)); } + if (ipsec) + nfp_nfd3_ipsec_tx(txd, skb); /* Gather DMA */ if (nr_frags > 0) { __le64 second_half; @@ -764,6 +787,15 @@ nfp_nfd3_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta, return false; data += sizeof(struct nfp_net_tls_resync_req); break; +#ifdef CONFIG_NFP_NET_IPSEC + case NFP_NET_META_IPSEC: + /* Note: IPsec packet will have zero saidx, so need add 1 + * to indicate packet is IPsec packet within driver. + */ + meta->ipsec_saidx = get_unaligned_be32(data) + 1; + data += 4; + break; +#endif default: return true; } @@ -876,12 +908,11 @@ static int nfp_nfd3_rx(struct nfp_net_rx_ring *rx_ring, int budget) struct nfp_net_dp *dp = &r_vec->nfp_net->dp; struct nfp_net_tx_ring *tx_ring; struct bpf_prog *xdp_prog; + int idx, pkts_polled = 0; bool xdp_tx_cmpl = false; unsigned int true_bufsz; struct sk_buff *skb; - int pkts_polled = 0; struct xdp_buff xdp; - int idx; xdp_prog = READ_ONCE(dp->xdp_prog); true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; @@ -1081,6 +1112,13 @@ static int nfp_nfd3_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; } +#ifdef CONFIG_NFP_NET_IPSEC + if (meta.ipsec_saidx != 0 && unlikely(nfp_net_ipsec_rx(&meta, skb))) { + nfp_nfd3_rx_drop(dp, r_vec, rx_ring, NULL, skb); + continue; + } +#endif + if (meta_len_xdp) skb_metadata_set(skb, meta_len_xdp); diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/ipsec.c b/drivers/net/ethernet/netronome/nfp/nfd3/ipsec.c new file mode 100644 index 000000000000..e90f8c975903 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfd3/ipsec.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc */ +/* Copyright (C) 2021 Corigine, Inc */ + +#include <net/xfrm.h> + +#include "../nfp_net.h" +#include "nfd3.h" + +void nfp_nfd3_ipsec_tx(struct nfp_nfd3_tx_desc *txd, struct sk_buff *skb) +{ + struct xfrm_state *x = xfrm_input_state(skb); + + if (x->xso.dev && (x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)) { + txd->flags |= NFD3_DESC_TX_CSUM | NFD3_DESC_TX_IP4_CSUM | + NFD3_DESC_TX_TCP_CSUM | NFD3_DESC_TX_UDP_CSUM; + } +} diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/nfd3.h b/drivers/net/ethernet/netronome/nfp/nfd3/nfd3.h index 7a0df9e6c3c4..9c1c10dcbaee 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/nfd3.h +++ b/drivers/net/ethernet/netronome/nfp/nfd3/nfd3.h @@ -103,4 +103,12 @@ void nfp_nfd3_rx_ring_fill_freelist(struct nfp_net_dp *dp, void nfp_nfd3_xsk_tx_free(struct nfp_nfd3_tx_buf *txbuf); int nfp_nfd3_xsk_poll(struct napi_struct *napi, int budget); +#ifndef CONFIG_NFP_NET_IPSEC +static inline void nfp_nfd3_ipsec_tx(struct nfp_nfd3_tx_desc *txd, struct sk_buff *skb) +{ +} +#else +void nfp_nfd3_ipsec_tx(struct nfp_nfd3_tx_desc *txd, struct sk_buff *skb); +#endif + #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index dd56207df246..90707346a4ef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -445,6 +445,4 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, struct nfp_net *nn, unsigned int id); -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev); - #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index cb08d7bf9524..bf6bae557158 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -239,10 +239,6 @@ nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, char *buf = NULL; int err; - err = devlink_info_driver_name_put(req, "nfp"); - if (err) - return err; - vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor"); part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno"); sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial"); @@ -334,6 +330,8 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) int serial_len; int ret; + SET_NETDEV_DEVLINK_PORT(port->netdev, &port->dl_port); + rtnl_lock(); ret = nfp_devlink_fill_eth_port(port, ð_port); rtnl_unlock(); @@ -360,24 +358,3 @@ void nfp_devlink_port_unregister(struct nfp_port *port) { devl_port_unregister(&port->dl_port); } - -void nfp_devlink_port_type_eth_set(struct nfp_port *port) -{ - devlink_port_type_eth_set(&port->dl_port, port->netdev); -} - -void nfp_devlink_port_type_clear(struct nfp_port *port) -{ - devlink_port_type_clear(&port->dl_port); -} - -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev) -{ - struct nfp_port *port; - - port = nfp_port_from_netdev(netdev); - if (!port) - return NULL; - - return &port->dl_port; -} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index afd3edfa2428..14a751bfe1fe 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -12,7 +12,6 @@ #include <linux/ethtool.h> #include <linux/list.h> #include <linux/types.h> -#include <linux/msi.h> #include <linux/pci.h> #include <linux/workqueue.h> #include <net/devlink.h> @@ -28,6 +27,7 @@ struct nfp_hwinfo; struct nfp_mip; struct nfp_net; struct nfp_nsp_identify; +struct nfp_eth_media_buf; struct nfp_port; struct nfp_rtsym; struct nfp_rtsym_table; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index a101ff30a1ae..da33f09facb9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -88,6 +88,9 @@ #define NFP_NET_FL_BATCH 16 /* Add freelist in this Batch size */ #define NFP_NET_XDP_MAX_COMPLETE 2048 /* XDP bufs to reclaim in NAPI poll */ +/* MC definitions */ +#define NFP_NET_CFG_MAC_MC_MAX 1024 /* The maximum number of MC address per port*/ + /* Offload definitions */ #define NFP_NET_N_VXLAN_PORTS (NFP_NET_CFG_VXLAN_SZ / sizeof(__be16)) @@ -263,6 +266,10 @@ struct nfp_meta_parsed { u8 tpid; u16 tci; } vlan; + +#ifdef CONFIG_NFP_NET_IPSEC + u32 ipsec_saidx; +#endif }; struct nfp_net_rx_hash { @@ -472,6 +479,7 @@ struct nfp_stat_pair { * @rx_dma_off: Offset at which DMA packets (for XDP headroom) * @rx_offset: Offset in the RX buffers where packet data starts * @ctrl: Local copy of the control register/word. + * @ctrl_w1: Local copy of the control register/word1. * @fl_bufsz: Currently configured size of the freelist buffers * @xdp_prog: Installed XDP program * @tx_rings: Array of pre-allocated TX ring structures @@ -504,6 +512,7 @@ struct nfp_net_dp { u32 rx_dma_off; u32 ctrl; + u32 ctrl_w1; u32 fl_bufsz; struct bpf_prog *xdp_prog; @@ -541,6 +550,7 @@ struct nfp_net_dp { * @id: vNIC id within the PF (0 for VFs) * @fw_ver: Firmware version * @cap: Capabilities advertised by the Firmware + * @cap_w1: Extended capabilities word advertised by the Firmware * @max_mtu: Maximum support MTU advertised by the Firmware * @rss_hfunc: RSS selected hash function * @rss_cfg: RSS configuration @@ -583,6 +593,7 @@ struct nfp_net_dp { * @qcp_cfg: Pointer to QCP queue used for configuration notification * @tx_bar: Pointer to mapped TX queues * @rx_bar: Pointer to mapped FL/RX queues + * @xa_ipsec: IPsec xarray SA data * @tlv_caps: Parsed TLV capabilities * @ktls_tx_conn_cnt: Number of offloaded kTLS TX connections * @ktls_rx_conn_cnt: Number of offloaded kTLS RX connections @@ -617,6 +628,7 @@ struct nfp_net { u32 id; u32 cap; + u32 cap_w1; u32 max_mtu; u8 rss_hfunc; @@ -670,6 +682,10 @@ struct nfp_net { u8 __iomem *tx_bar; u8 __iomem *rx_bar; +#ifdef CONFIG_NFP_NET_IPSEC + struct xarray xa_ipsec; +#endif + struct nfp_net_tlv_caps tlv_caps; unsigned int ktls_tx_conn_cnt; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 27f4786ace4f..2314cf55e821 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -27,7 +27,6 @@ #include <linux/page_ref.h> #include <linux/pci.h> #include <linux/pci_regs.h> -#include <linux/msi.h> #include <linux/ethtool.h> #include <linux/log2.h> #include <linux/if_vlan.h> @@ -735,8 +734,9 @@ static unsigned int nfp_net_calc_fl_bufsz_xsk(struct nfp_net_dp *dp) */ static void nfp_net_vecs_init(struct nfp_net *nn) { + int numa_node = dev_to_node(&nn->pdev->dev); struct nfp_net_r_vector *r_vec; - int r; + unsigned int r; nn->lsc_handler = nfp_net_irq_lsc; nn->exn_handler = nfp_net_irq_exn; @@ -762,7 +762,7 @@ static void nfp_net_vecs_init(struct nfp_net *nn) tasklet_disable(&r_vec->tasklet); } - cpumask_set_cpu(r, &r_vec->affinity_mask); + cpumask_set_cpu(cpumask_local_spread(r, numa_node), &r_vec->affinity_mask); } } @@ -1007,6 +1007,7 @@ static int nfp_net_set_config_and_enable(struct nfp_net *nn) new_ctrl |= NFP_NET_CFG_CTRL_RINGCFG; nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); + nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, nn->dp.ctrl_w1); err = nfp_net_reconfig(nn, update); if (err) { nfp_net_clear_config_and_disable(nn); @@ -1333,18 +1334,59 @@ err_unlock: return err; } +static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr, const u32 cmd) +{ + struct nfp_net *nn = netdev_priv(netdev); + int ret; + + ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ); + if (ret) + return ret; + + nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MULTICAST_MAC_HI, + get_unaligned_be32(addr)); + nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MULTICAST_MAC_LO, + get_unaligned_be16(addr + 4)); + + return nfp_net_mbox_reconfig_and_unlock(nn, cmd); +} + +static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr) +{ + struct nfp_net *nn = netdev_priv(netdev); + + if (netdev_mc_count(netdev) > NFP_NET_CFG_MAC_MC_MAX) { + nn_err(nn, "Requested number of MC addresses (%d) exceeds maximum (%d).\n", + netdev_mc_count(netdev), NFP_NET_CFG_MAC_MC_MAX); + return -EINVAL; + } + + return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD); +} + +static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr) +{ + return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL); +} + static void nfp_net_set_rx_mode(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - u32 new_ctrl; + u32 new_ctrl, new_ctrl_w1; new_ctrl = nn->dp.ctrl; + new_ctrl_w1 = nn->dp.ctrl_w1; if (!netdev_mc_empty(netdev) || netdev->flags & IFF_ALLMULTI) new_ctrl |= nn->cap & NFP_NET_CFG_CTRL_L2MC; else new_ctrl &= ~NFP_NET_CFG_CTRL_L2MC; + if (netdev->flags & IFF_ALLMULTI) + new_ctrl_w1 &= ~NFP_NET_CFG_CTRL_MCAST_FILTER; + else + new_ctrl_w1 |= nn->cap_w1 & NFP_NET_CFG_CTRL_MCAST_FILTER; + if (netdev->flags & IFF_PROMISC) { if (nn->cap & NFP_NET_CFG_CTRL_PROMISC) new_ctrl |= NFP_NET_CFG_CTRL_PROMISC; @@ -1354,13 +1396,21 @@ static void nfp_net_set_rx_mode(struct net_device *netdev) new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC; } - if (new_ctrl == nn->dp.ctrl) + if ((nn->cap_w1 & NFP_NET_CFG_CTRL_MCAST_FILTER) && + __dev_mc_sync(netdev, nfp_net_mc_sync, nfp_net_mc_unsync)) + netdev_err(netdev, "Sync mc address failed\n"); + + if (new_ctrl == nn->dp.ctrl && new_ctrl_w1 == nn->dp.ctrl_w1) return; - nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); + if (new_ctrl != nn->dp.ctrl) + nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); + if (new_ctrl_w1 != nn->dp.ctrl_w1) + nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, new_ctrl_w1); nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN); nn->dp.ctrl = new_ctrl; + nn->dp.ctrl_w1 = new_ctrl_w1; } static void nfp_net_rss_init_itbl(struct nfp_net *nn) @@ -1631,21 +1681,21 @@ static void nfp_net_stat64(struct net_device *netdev, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&r_vec->rx_sync); + start = u64_stats_fetch_begin(&r_vec->rx_sync); data[0] = r_vec->rx_pkts; data[1] = r_vec->rx_bytes; data[2] = r_vec->rx_drops; - } while (u64_stats_fetch_retry_irq(&r_vec->rx_sync, start)); + } while (u64_stats_fetch_retry(&r_vec->rx_sync, start)); stats->rx_packets += data[0]; stats->rx_bytes += data[1]; stats->rx_dropped += data[2]; do { - start = u64_stats_fetch_begin_irq(&r_vec->tx_sync); + start = u64_stats_fetch_begin(&r_vec->tx_sync); data[0] = r_vec->tx_pkts; data[1] = r_vec->tx_bytes; data[2] = r_vec->tx_errors; - } while (u64_stats_fetch_retry_irq(&r_vec->tx_sync, start)); + } while (u64_stats_fetch_retry(&r_vec->tx_sync, start)); stats->tx_packets += data[0]; stats->tx_bytes += data[1]; stats->tx_errors += data[2]; @@ -2013,7 +2063,6 @@ const struct net_device_ops nfp_nfd3_netdev_ops = { .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, .ndo_xsk_wakeup = nfp_net_xsk_wakeup, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; @@ -2044,7 +2093,6 @@ const struct net_device_ops nfp_nfdk_netdev_ops = { .ndo_features_check = nfp_net_features_check, .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; @@ -2094,7 +2142,7 @@ void nfp_net_info(struct nfp_net *nn) nn->fw_ver.extend, nn->fw_ver.class, nn->fw_ver.major, nn->fw_ver.minor, nn->max_mtu); - nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", nn->cap, nn->cap & NFP_NET_CFG_CTRL_PROMISC ? "PROMISC " : "", nn->cap & NFP_NET_CFG_CTRL_L2BC ? "L2BCFILT " : "", @@ -2122,6 +2170,7 @@ void nfp_net_info(struct nfp_net *nn) nn->cap & NFP_NET_CFG_CTRL_CSUM_COMPLETE ? "RXCSUM_COMPLETE " : "", nn->cap & NFP_NET_CFG_CTRL_LIVE_ADDR ? "LIVE_ADDR " : "", + nn->cap_w1 & NFP_NET_CFG_CTRL_MCAST_FILTER ? "MULTICAST_FILTER " : "", nfp_app_extra_cap(nn->app, nn)); } @@ -2373,6 +2422,12 @@ static void nfp_net_netdev_init(struct nfp_net *nn) } if (nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) netdev->hw_features |= NETIF_F_RXHASH; + +#ifdef CONFIG_NFP_NET_IPSEC + if (nn->cap_w1 & NFP_NET_CFG_CTRL_IPSEC) + netdev->hw_features |= NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM; +#endif + if (nn->cap & NFP_NET_CFG_CTRL_VXLAN) { if (nn->cap & NFP_NET_CFG_CTRL_LSO) { netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | @@ -2454,6 +2509,7 @@ static int nfp_net_read_caps(struct nfp_net *nn) { /* Get some of the read-only fields from the BAR */ nn->cap = nn_readl(nn, NFP_NET_CFG_CAP); + nn->cap_w1 = nn_readq(nn, NFP_NET_CFG_CAP_WORD1); nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU); /* ABI 4.x and ctrl vNIC always use chained metadata, in other cases @@ -2543,6 +2599,9 @@ int nfp_net_init(struct nfp_net *nn) if (nn->cap & NFP_NET_CFG_CTRL_TXRWB) nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXRWB; + if (nn->cap_w1 & NFP_NET_CFG_CTRL_MCAST_FILTER) + nn->dp.ctrl_w1 |= NFP_NET_CFG_CTRL_MCAST_FILTER; + /* Stash the re-configuration queue away. First odd queue in TX Bar */ nn->qcp_cfg = nn->tx_bar + NFP_QCP_QUEUE_ADDR_SZ; @@ -2550,6 +2609,7 @@ int nfp_net_init(struct nfp_net *nn) nn_writel(nn, NFP_NET_CFG_CTRL, 0); nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, 0); nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, 0); + nn_writel(nn, NFP_NET_CFG_CTRL_WORD1, 0); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RING | NFP_NET_CFG_UPDATE_GEN); if (err) @@ -2565,6 +2625,8 @@ int nfp_net_init(struct nfp_net *nn) err = nfp_net_tls_init(nn); if (err) goto err_clean_mbox; + + nfp_net_ipsec_init(nn); } nfp_net_vecs_init(nn); @@ -2588,6 +2650,7 @@ void nfp_net_clean(struct nfp_net *nn) return; unregister_netdev(nn->dp.netdev); + nfp_net_ipsec_clean(nn); nfp_ccm_mbox_clean(nn); nfp_net_reconfig_wait_posted(nn); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 6714d5e8fdab..51124309ae1f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -48,6 +48,7 @@ #define NFP_NET_META_CSUM 6 /* checksum complete type */ #define NFP_NET_META_CONN_HANDLE 7 #define NFP_NET_META_RESYNC_INFO 8 /* RX resync info request */ +#define NFP_NET_META_IPSEC 9 /* IPsec SA index for tx and rx */ #define NFP_META_PORT_ID_CTRL ~0U @@ -55,6 +56,8 @@ #define NFP_NET_META_VLAN_SIZE 4 #define NFP_NET_META_PORTID_SIZE 4 #define NFP_NET_META_CONN_HANDLE_SIZE 8 +#define NFP_NET_META_IPSEC_SIZE 4 +#define NFP_NET_META_IPSEC_FIELD_SIZE 12 /* Hash type pre-pended when a RSS hash was computed */ #define NFP_NET_RSS_NONE 0 #define NFP_NET_RSS_IPV4 1 @@ -257,10 +260,20 @@ #define NFP_NET_CFG_BPF_CFG_MASK 7ULL #define NFP_NET_CFG_BPF_ADDR_MASK (~NFP_NET_CFG_BPF_CFG_MASK) -/* 40B reserved for future use (0x0098 - 0x00c0) +/* 3 words reserved for extended ctrl words (0x0098 - 0x00a4) + * 3 words reserved for extended cap words (0x00a4 - 0x00b0) + * Currently only one word is used, can be extended in future. */ -#define NFP_NET_CFG_RESERVED 0x0098 -#define NFP_NET_CFG_RESERVED_SZ 0x0028 +#define NFP_NET_CFG_CTRL_WORD1 0x0098 +#define NFP_NET_CFG_CTRL_PKT_TYPE (0x1 << 0) /* Pkttype offload */ +#define NFP_NET_CFG_CTRL_IPSEC (0x1 << 1) /* IPsec offload */ +#define NFP_NET_CFG_CTRL_MCAST_FILTER (0x1 << 2) /* Multicast Filter */ + +#define NFP_NET_CFG_CAP_WORD1 0x00a4 + +/* 16B reserved for future use (0x00b0 - 0x00c0) */ +#define NFP_NET_CFG_RESERVED 0x00b0 +#define NFP_NET_CFG_RESERVED_SZ 0x0010 /* RSS configuration (0x0100 - 0x01ac): * Used only when NFP_NET_CFG_CTRL_RSS is enabled @@ -390,17 +403,20 @@ */ #define NFP_NET_CFG_MBOX_BASE 0x1800 #define NFP_NET_CFG_MBOX_VAL_MAX_SZ 0x1F8 - +#define NFP_NET_CFG_MBOX_VAL 0x1808 #define NFP_NET_CFG_MBOX_SIMPLE_CMD 0x0 #define NFP_NET_CFG_MBOX_SIMPLE_RET 0x4 #define NFP_NET_CFG_MBOX_SIMPLE_VAL 0x8 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2 - +#define NFP_NET_CFG_MBOX_CMD_IPSEC 3 #define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET 5 #define NFP_NET_CFG_MBOX_CMD_TLV_CMSG 6 +#define NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD 8 +#define NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL 9 + /* VLAN filtering using general use mailbox * %NFP_NET_CFG_VLAN_FILTER: Base address of VLAN filter mailbox * %NFP_NET_CFG_VLAN_FILTER_VID: VLAN ID to filter @@ -412,6 +428,17 @@ #define NFP_NET_CFG_VLAN_FILTER_PROTO (NFP_NET_CFG_VLAN_FILTER + 2) #define NFP_NET_CFG_VLAN_FILTER_SZ 0x0004 +/* Multicast filtering using general use mailbox + * %NFP_NET_CFG_MULTICAST: Base address of Multicast filter mailbox + * %NFP_NET_CFG_MULTICAST_MAC_HI: High 32-bits of Multicast MAC address + * %NFP_NET_CFG_MULTICAST_MAC_LO: Low 16-bits of Multicast MAC address + * %NFP_NET_CFG_MULTICAST_SZ: Size of the Multicast filter mailbox in bytes + */ +#define NFP_NET_CFG_MULTICAST NFP_NET_CFG_MBOX_SIMPLE_VAL +#define NFP_NET_CFG_MULTICAST_MAC_HI NFP_NET_CFG_MULTICAST +#define NFP_NET_CFG_MULTICAST_MAC_LO (NFP_NET_CFG_MULTICAST + 6) +#define NFP_NET_CFG_MULTICAST_SZ 0x0006 + /* TLV capabilities * %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 991059d6cb32..a4a89ef3f18b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -293,6 +293,76 @@ nfp_net_set_fec_link_mode(struct nfp_eth_table_port *eth_port, } } +static const u16 nfp_eth_media_table[] = { + [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, +}; + +static void nfp_add_media_link_mode(struct nfp_port *port, + struct nfp_eth_table_port *eth_port, + struct ethtool_link_ksettings *cmd) +{ + u64 supported_modes[2], advertised_modes[2]; + struct nfp_eth_media_buf ethm = { + .eth_index = eth_port->eth_index, + }; + struct nfp_cpp *cpp = port->app->cpp; + + if (nfp_eth_read_media(cpp, ðm)) + return; + + for (u32 i = 0; i < 2; i++) { + supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]); + advertised_modes[i] = le64_to_cpu(ethm.advertised_modes[i]); + } + + for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) { + if (i < 64) { + if (supported_modes[0] & BIT_ULL(i)) + __set_bit(nfp_eth_media_table[i], + cmd->link_modes.supported); + + if (advertised_modes[0] & BIT_ULL(i)) + __set_bit(nfp_eth_media_table[i], + cmd->link_modes.advertising); + } else { + if (supported_modes[1] & BIT_ULL(i - 64)) + __set_bit(nfp_eth_media_table[i], + cmd->link_modes.supported); + + if (advertised_modes[1] & BIT_ULL(i - 64)) + __set_bit(nfp_eth_media_table[i], + cmd->link_modes.advertising); + } + } +} + /** * nfp_net_get_link_ksettings - Get Link Speed settings * @netdev: network interface device structure @@ -311,6 +381,8 @@ nfp_net_get_link_ksettings(struct net_device *netdev, u16 sts; /* Init to unknowns */ + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; @@ -321,6 +393,7 @@ nfp_net_get_link_ksettings(struct net_device *netdev, if (eth_port) { ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + nfp_add_media_link_mode(port, eth_port, cmd); if (eth_port->supp_aneg) { ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); if (eth_port->aneg == NFP_ANEG_AUTO) { @@ -686,7 +759,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) unsigned int start; do { - start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].rx_sync); + start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync); data[0] = nn->r_vecs[i].rx_pkts; tmp[0] = nn->r_vecs[i].hw_csum_rx_ok; tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok; @@ -694,10 +767,10 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) tmp[3] = nn->r_vecs[i].hw_csum_rx_error; tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail; tmp[5] = nn->r_vecs[i].hw_tls_rx; - } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].rx_sync, start)); + } while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start)); do { - start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].tx_sync); + start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync); data[1] = nn->r_vecs[i].tx_pkts; data[2] = nn->r_vecs[i].tx_busy; tmp[6] = nn->r_vecs[i].hw_csum_tx; @@ -707,7 +780,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) tmp[10] = nn->r_vecs[i].hw_tls_tx; tmp[11] = nn->r_vecs[i].tls_tx_fallback; tmp[12] = nn->r_vecs[i].tls_tx_no_fallback; - } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].tx_sync, start)); + } while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start)); data += NN_RVEC_PER_Q_STATS; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3bae92dc899e..abfe788d558f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -16,7 +16,6 @@ #include <linux/lockdep.h> #include <linux/pci.h> #include <linux/pci_regs.h> -#include <linux/msi.h> #include <linux/random.h> #include <linux/rtnetlink.h> @@ -156,22 +155,17 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id) nfp_net_debugfs_vnic_add(nn, pf->ddir); - if (nn->port) - nfp_devlink_port_type_eth_set(nn->port); - nfp_net_info(nn); if (nfp_net_is_data_vnic(nn)) { err = nfp_app_vnic_init(pf->app, nn); if (err) - goto err_devlink_port_type_clean; + goto err_debugfs_vnic_clean; } return 0; -err_devlink_port_type_clean: - if (nn->port) - nfp_devlink_port_type_clear(nn->port); +err_debugfs_vnic_clean: nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); err_devlink_port_clean: @@ -220,8 +214,6 @@ static void nfp_net_pf_clean_vnic(struct nfp_pf *pf, struct nfp_net *nn) { if (nfp_net_is_data_vnic(nn)) nfp_app_vnic_clean(pf->app, nn); - if (nn->port) - nfp_devlink_port_type_clear(nn->port); nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); if (nn->port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 8b77582bdfa0..3af1229a3f08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -134,13 +134,13 @@ nfp_repr_get_host_stats64(const struct net_device *netdev, repr_stats = per_cpu_ptr(repr->stats, i); do { - start = u64_stats_fetch_begin_irq(&repr_stats->syncp); + start = u64_stats_fetch_begin(&repr_stats->syncp); tbytes = repr_stats->tx_bytes; tpkts = repr_stats->tx_packets; tdrops = repr_stats->tx_drops; rbytes = repr_stats->rx_bytes; rpkts = repr_stats->rx_packets; - } while (u64_stats_fetch_retry_irq(&repr_stats->syncp, start)); + } while (u64_stats_fetch_retry(&repr_stats->syncp, start)); stats->tx_bytes += tbytes; stats->tx_packets += tpkts; @@ -275,7 +275,6 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_set_features = nfp_port_set_features, .ndo_set_mac_address = eth_mac_addr, .ndo_get_port_parent_id = nfp_port_get_port_parent_id, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, }; void diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index 6793cdf9ff11..f8cd157ca1d7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -129,8 +129,6 @@ int nfp_net_refresh_port_table_sync(struct nfp_pf *pf); int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port); void nfp_devlink_port_unregister(struct nfp_port *port); -void nfp_devlink_port_type_eth_set(struct nfp_port *port); -void nfp_devlink_port_type_clear(struct nfp_port *port); /* Mac stats (0x0000 - 0x0200) * all counters are 64bit. diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 730fea214b8a..7136bc48530b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -100,6 +100,7 @@ enum nfp_nsp_cmd { SPCODE_FW_LOADED = 19, /* Is application firmware loaded */ SPCODE_VERSIONS = 21, /* Report FW versions */ SPCODE_READ_SFF_EEPROM = 22, /* Read module EEPROM */ + SPCODE_READ_MEDIA = 23, /* Get either the supported or advertised media for a port */ }; struct nfp_nsp_dma_buf { @@ -1100,4 +1101,20 @@ int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index, kfree(buf); return ret; +}; + +int nfp_nsp_read_media(struct nfp_nsp *state, void *buf, unsigned int size) +{ + struct nfp_nsp_command_buf_arg media = { + { + .code = SPCODE_READ_MEDIA, + .option = size, + }, + .in_buf = buf, + .in_size = size, + .out_buf = buf, + .out_size = size, + }; + + return nfp_nsp_command_buf(state, &media); } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index 992d72ac98d3..8f5cab0032d0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -65,6 +65,11 @@ static inline bool nfp_nsp_has_read_module_eeprom(struct nfp_nsp *state) return nfp_nsp_get_abi_ver_minor(state) > 28; } +static inline bool nfp_nsp_has_read_media(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 33; +} + enum nfp_eth_interface { NFP_INTERFACE_NONE = 0, NFP_INTERFACE_SFP = 1, @@ -97,6 +102,47 @@ enum nfp_eth_fec { NFP_FEC_DISABLED_BIT, }; +/* link modes about RJ45 haven't been used, so there's no mapping to them */ +enum nfp_ethtool_link_mode_list { + NFP_MEDIA_W0_RJ45_10M, + NFP_MEDIA_W0_RJ45_10M_HD, + NFP_MEDIA_W0_RJ45_100M, + NFP_MEDIA_W0_RJ45_100M_HD, + NFP_MEDIA_W0_RJ45_1G, + NFP_MEDIA_W0_RJ45_2P5G, + NFP_MEDIA_W0_RJ45_5G, + NFP_MEDIA_W0_RJ45_10G, + NFP_MEDIA_1000BASE_CX, + NFP_MEDIA_1000BASE_KX, + NFP_MEDIA_10GBASE_KX4, + NFP_MEDIA_10GBASE_KR, + NFP_MEDIA_10GBASE_CX4, + NFP_MEDIA_10GBASE_CR, + NFP_MEDIA_10GBASE_SR, + NFP_MEDIA_10GBASE_ER, + NFP_MEDIA_25GBASE_KR, + NFP_MEDIA_25GBASE_KR_S, + NFP_MEDIA_25GBASE_CR, + NFP_MEDIA_25GBASE_CR_S, + NFP_MEDIA_25GBASE_SR, + NFP_MEDIA_40GBASE_CR4, + NFP_MEDIA_40GBASE_KR4, + NFP_MEDIA_40GBASE_SR4, + NFP_MEDIA_40GBASE_LR4, + NFP_MEDIA_50GBASE_KR, + NFP_MEDIA_50GBASE_SR, + NFP_MEDIA_50GBASE_CR, + NFP_MEDIA_50GBASE_LR, + NFP_MEDIA_50GBASE_ER, + NFP_MEDIA_50GBASE_FR, + NFP_MEDIA_100GBASE_KR4, + NFP_MEDIA_100GBASE_SR4, + NFP_MEDIA_100GBASE_CR4, + NFP_MEDIA_100GBASE_KP4, + NFP_MEDIA_100GBASE_CR10, + NFP_MEDIA_LINK_MODES_NUMBER +}; + #define NFP_FEC_AUTO BIT(NFP_FEC_AUTO_BIT) #define NFP_FEC_BASER BIT(NFP_FEC_BASER_BIT) #define NFP_FEC_REED_SOLOMON BIT(NFP_FEC_REED_SOLOMON_BIT) @@ -256,6 +302,16 @@ enum nfp_nsp_sensor_id { int nfp_hwmon_read_sensor(struct nfp_cpp *cpp, enum nfp_nsp_sensor_id id, long *val); +struct nfp_eth_media_buf { + u8 eth_index; + u8 reserved[7]; + __le64 supported_modes[2]; + __le64 advertised_modes[2]; +}; + +int nfp_nsp_read_media(struct nfp_nsp *state, void *buf, unsigned int size); +int nfp_eth_read_media(struct nfp_cpp *cpp, struct nfp_eth_media_buf *ethm); + #define NFP_NSP_VERSION_BUFSZ 1024 /* reasonable size, not in the ABI */ enum nfp_nsp_versions { diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index bb64efec4c46..570ac1bb2122 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -647,3 +647,29 @@ int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes) return NFP_ETH_SET_BIT_CONFIG(nsp, NSP_ETH_RAW_PORT, NSP_ETH_PORT_LANES, lanes, NSP_ETH_CTRL_SET_LANES); } + +int nfp_eth_read_media(struct nfp_cpp *cpp, struct nfp_eth_media_buf *ethm) +{ + struct nfp_nsp *nsp; + int ret; + + nsp = nfp_nsp_open(cpp); + if (IS_ERR(nsp)) { + nfp_err(cpp, "Failed to access the NSP: %pe\n", nsp); + return PTR_ERR(nsp); + } + + if (!nfp_nsp_has_read_media(nsp)) { + nfp_warn(cpp, "Reading media link modes not supported. Please update flash\n"); + ret = -EOPNOTSUPP; + goto exit_close_nsp; + } + + ret = nfp_nsp_read_media(nsp, ethm, sizeof(*ethm)); + if (ret) + nfp_err(cpp, "Reading media link modes failed: %pe\n", ERR_PTR(ret)); + +exit_close_nsp: + nfp_nsp_close(nsp); + return ret; +} diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index daa028729d44..0605d1ee490d 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1734,12 +1734,12 @@ static void nv_get_stats(int cpu, struct fe_priv *np, u64 tx_packets, tx_bytes, tx_dropped; do { - syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp); + syncp_start = u64_stats_fetch_begin(&np->swstats_rx_syncp); rx_packets = src->stat_rx_packets; rx_bytes = src->stat_rx_bytes; rx_dropped = src->stat_rx_dropped; rx_missed_errors = src->stat_rx_missed_errors; - } while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start)); + } while (u64_stats_fetch_retry(&np->swstats_rx_syncp, syncp_start)); storage->rx_packets += rx_packets; storage->rx_bytes += rx_bytes; @@ -1747,11 +1747,11 @@ static void nv_get_stats(int cpu, struct fe_priv *np, storage->rx_missed_errors += rx_missed_errors; do { - syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp); + syncp_start = u64_stats_fetch_begin(&np->swstats_tx_syncp); tx_packets = src->stat_tx_packets; tx_bytes = src->stat_tx_bytes; tx_dropped = src->stat_tx_dropped; - } while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start)); + } while (u64_stats_fetch_retry(&np->swstats_tx_syncp, syncp_start)); storage->tx_packets += tx_packets; storage->tx_bytes += tx_bytes; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9d0514cfeb5c..626b9113e7c4 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -481,6 +481,20 @@ int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, return err; } +void ionic_vf_start(struct ionic *ionic) +{ + union ionic_dev_cmd cmd = { + .vf_ctrl.opcode = IONIC_CMD_VF_CTRL, + .vf_ctrl.ctrl_opcode = IONIC_VF_CTRL_START_ALL, + }; + + if (!(ionic->ident.dev.capabilities & cpu_to_le64(IONIC_DEV_CAP_VF_CTRL))) + return; + + ionic_dev_cmd_go(&ionic->idev, &cmd); + ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); +} + /* LIF commands */ void ionic_dev_cmd_queue_identify(struct ionic_dev *idev, u16 lif_type, u8 qtype, u8 qver) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 563c302eb033..2a1d7b9c07e7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -124,6 +124,8 @@ static_assert(sizeof(struct ionic_vf_setattr_cmd) == 64); static_assert(sizeof(struct ionic_vf_setattr_comp) == 16); static_assert(sizeof(struct ionic_vf_getattr_cmd) == 64); static_assert(sizeof(struct ionic_vf_getattr_comp) == 16); +static_assert(sizeof(struct ionic_vf_ctrl_cmd) == 64); +static_assert(sizeof(struct ionic_vf_ctrl_comp) == 16); #endif /* __CHECKER__ */ struct ionic_devinfo { @@ -324,6 +326,7 @@ int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, struct ionic_vf_getattr_comp *comp); void ionic_dev_cmd_queue_identify(struct ionic_dev *idev, u16 lif_type, u8 qtype, u8 qver); +void ionic_vf_start(struct ionic *ionic); void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver); void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index, dma_addr_t addr); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 4297ed9024c0..e6ff757895ab 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -26,10 +26,6 @@ static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req, char buf[16]; int err = 0; - err = devlink_info_driver_name_put(req, IONIC_DRV_NAME); - if (err) - return err; - err = devlink_info_version_running_put(req, DEVLINK_INFO_VERSION_GENERIC_FW, idev->dev_info.fw_version); @@ -90,7 +86,7 @@ int ionic_devlink_register(struct ionic *ionic) return err; } - devlink_port_type_eth_set(&ionic->dl_port, ionic->lif->netdev); + SET_NETDEV_DEVLINK_PORT(ionic->lif->netdev, &ionic->dl_port); devlink_register(dl); return 0; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index 4a90f611c611..eac09b2375b8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -8,7 +8,7 @@ #define IONIC_DEV_INFO_VERSION 1 #define IONIC_IFNAMSIZ 16 -/** +/* * enum ionic_cmd_opcode - Device commands */ enum ionic_cmd_opcode { @@ -54,6 +54,7 @@ enum ionic_cmd_opcode { /* SR/IOV commands */ IONIC_CMD_VF_GETATTR = 60, IONIC_CMD_VF_SETATTR = 61, + IONIC_CMD_VF_CTRL = 62, /* QoS commands */ IONIC_CMD_QOS_CLASS_IDENTIFY = 240, @@ -200,6 +201,7 @@ struct ionic_dev_reset_comp { }; #define IONIC_IDENTITY_VERSION_1 1 +#define IONIC_DEV_IDENTITY_VERSION_2 2 /** * struct ionic_dev_identify_cmd - Driver/device identify command @@ -254,6 +256,14 @@ union ionic_drv_identity { }; /** + * enum ionic_dev_capability - Device capabilities + * @IONIC_DEV_CAP_VF_CTRL: Device supports VF ctrl operations + */ +enum ionic_dev_capability { + IONIC_DEV_CAP_VF_CTRL = BIT(0), +}; + +/** * union ionic_dev_identity - device identity information * @version: Version of device identify * @type: Identify type (0 for now) @@ -273,6 +283,7 @@ union ionic_drv_identity { * @hwstamp_mask: Bitmask for subtraction of hardware tick values. * @hwstamp_mult: Hardware tick to nanosecond multiplier. * @hwstamp_shift: Hardware tick to nanosecond divisor (power of two). + * @capabilities: Device capabilities */ union ionic_dev_identity { struct { @@ -290,6 +301,7 @@ union ionic_dev_identity { __le64 hwstamp_mask; __le32 hwstamp_mult; __le32 hwstamp_shift; + __le64 capabilities; }; __le32 words[478]; }; @@ -2044,6 +2056,35 @@ struct ionic_vf_getattr_comp { u8 color; }; +enum ionic_vf_ctrl_opcode { + IONIC_VF_CTRL_START_ALL = 0, + IONIC_VF_CTRL_START = 1, +}; + +/** + * struct ionic_vf_ctrl_cmd - VF control command + * @opcode: Opcode for the command + * @vf_index: VF Index. It is unused if op START_ALL is used. + * @ctrl_opcode: VF control operation type + */ +struct ionic_vf_ctrl_cmd { + u8 opcode; + u8 ctrl_opcode; + __le16 vf_index; + /* private: */ + u8 rsvd1[60]; +}; + +/** + * struct ionic_vf_ctrl_comp - VF_CTRL command completion. + * @status: Status of the command (enum ionic_status_code) + */ +struct ionic_vf_ctrl_comp { + u8 status; + /* private: */ + u8 rsvd[15]; +}; + /** * struct ionic_qos_identify_cmd - QoS identify command * @opcode: opcode @@ -2865,6 +2906,7 @@ union ionic_dev_cmd { struct ionic_vf_setattr_cmd vf_setattr; struct ionic_vf_getattr_cmd vf_getattr; + struct ionic_vf_ctrl_cmd vf_ctrl; struct ionic_lif_identify_cmd lif_identify; struct ionic_lif_init_cmd lif_init; @@ -2903,6 +2945,7 @@ union ionic_dev_cmd_comp { struct ionic_vf_setattr_comp vf_setattr; struct ionic_vf_getattr_comp vf_getattr; + struct ionic_vf_ctrl_comp vf_ctrl; struct ionic_lif_identify_comp lif_identify; struct ionic_lif_init_comp lif_init; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 19d4848df17d..4dd16c487f2b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1491,7 +1491,13 @@ static int ionic_init_nic_features(struct ionic_lif *lif) NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_TSO_ECN; + NETIF_F_TSO_ECN | + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; if (lif->nxqs > 1) features |= NETIF_F_RXHASH; @@ -2220,7 +2226,7 @@ static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd } } -static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) +static int ionic_get_fw_vf_config(struct ionic *ionic, int vf, struct ionic_vf *vfdata) { struct ionic_vf_getattr_comp comp = { 0 }; int err; @@ -2231,14 +2237,14 @@ static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) if (err && comp.status != IONIC_RC_ENOSUPP) goto err_out; if (!err) - ionic->vfs[vf].vlanid = comp.vlanid; + vfdata->vlanid = comp.vlanid; attr = IONIC_VF_ATTR_SPOOFCHK; err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); if (err && comp.status != IONIC_RC_ENOSUPP) goto err_out; if (!err) - ionic->vfs[vf].spoofchk = comp.spoofchk; + vfdata->spoofchk = comp.spoofchk; attr = IONIC_VF_ATTR_LINKSTATE; err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); @@ -2247,13 +2253,13 @@ static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) if (!err) { switch (comp.linkstate) { case IONIC_VF_LINK_STATUS_UP: - ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_ENABLE; + vfdata->linkstate = IFLA_VF_LINK_STATE_ENABLE; break; case IONIC_VF_LINK_STATUS_DOWN: - ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_DISABLE; + vfdata->linkstate = IFLA_VF_LINK_STATE_DISABLE; break; case IONIC_VF_LINK_STATUS_AUTO: - ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_AUTO; + vfdata->linkstate = IFLA_VF_LINK_STATE_AUTO; break; default: dev_warn(ionic->dev, "Unexpected link state %u\n", comp.linkstate); @@ -2266,21 +2272,21 @@ static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) if (err && comp.status != IONIC_RC_ENOSUPP) goto err_out; if (!err) - ionic->vfs[vf].maxrate = comp.maxrate; + vfdata->maxrate = comp.maxrate; attr = IONIC_VF_ATTR_TRUST; err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); if (err && comp.status != IONIC_RC_ENOSUPP) goto err_out; if (!err) - ionic->vfs[vf].trusted = comp.trust; + vfdata->trusted = comp.trust; attr = IONIC_VF_ATTR_MAC; err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); if (err && comp.status != IONIC_RC_ENOSUPP) goto err_out; if (!err) - ether_addr_copy(ionic->vfs[vf].macaddr, comp.macaddr); + ether_addr_copy(vfdata->macaddr, comp.macaddr); err_out: if (err) @@ -2295,6 +2301,7 @@ static int ionic_get_vf_config(struct net_device *netdev, { struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; + struct ionic_vf vfdata = { 0 }; int ret = 0; if (!netif_device_present(netdev)) @@ -2308,14 +2315,14 @@ static int ionic_get_vf_config(struct net_device *netdev, ivf->vf = vf; ivf->qos = 0; - ret = ionic_update_cached_vf_config(ionic, vf); + ret = ionic_get_fw_vf_config(ionic, vf, &vfdata); if (!ret) { - ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid); - ivf->spoofchk = ionic->vfs[vf].spoofchk; - ivf->linkstate = ionic->vfs[vf].linkstate; - ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate); - ivf->trusted = ionic->vfs[vf].trusted; - ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr); + ivf->vlan = le16_to_cpu(vfdata.vlanid); + ivf->spoofchk = vfdata.spoofchk; + ivf->linkstate = vfdata.linkstate; + ivf->max_tx_rate = le32_to_cpu(vfdata.maxrate); + ivf->trusted = vfdata.trusted; + ether_addr_copy(ivf->mac, vfdata.macaddr); } } @@ -2562,6 +2569,76 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) return ret; } +static void ionic_vf_attr_replay(struct ionic_lif *lif) +{ + struct ionic_vf_setattr_cmd vfc = { }; + struct ionic *ionic = lif->ionic; + struct ionic_vf *v; + int i; + + if (!ionic->vfs) + return; + + down_read(&ionic->vf_op_lock); + + for (i = 0; i < ionic->num_vfs; i++) { + v = &ionic->vfs[i]; + + if (v->stats_pa) { + vfc.attr = IONIC_VF_ATTR_STATSADDR; + vfc.stats_pa = cpu_to_le64(v->stats_pa); + ionic_set_vf_config(ionic, i, &vfc); + vfc.stats_pa = 0; + } + + if (!is_zero_ether_addr(v->macaddr)) { + vfc.attr = IONIC_VF_ATTR_MAC; + ether_addr_copy(vfc.macaddr, v->macaddr); + ionic_set_vf_config(ionic, i, &vfc); + eth_zero_addr(vfc.macaddr); + } + + if (v->vlanid) { + vfc.attr = IONIC_VF_ATTR_VLAN; + vfc.vlanid = v->vlanid; + ionic_set_vf_config(ionic, i, &vfc); + vfc.vlanid = 0; + } + + if (v->maxrate) { + vfc.attr = IONIC_VF_ATTR_RATE; + vfc.maxrate = v->maxrate; + ionic_set_vf_config(ionic, i, &vfc); + vfc.maxrate = 0; + } + + if (v->spoofchk) { + vfc.attr = IONIC_VF_ATTR_SPOOFCHK; + vfc.spoofchk = v->spoofchk; + ionic_set_vf_config(ionic, i, &vfc); + vfc.spoofchk = 0; + } + + if (v->trusted) { + vfc.attr = IONIC_VF_ATTR_TRUST; + vfc.trust = v->trusted; + ionic_set_vf_config(ionic, i, &vfc); + vfc.trust = 0; + } + + if (v->linkstate) { + vfc.attr = IONIC_VF_ATTR_LINKSTATE; + vfc.linkstate = v->linkstate; + ionic_set_vf_config(ionic, i, &vfc); + vfc.linkstate = 0; + } + } + + up_read(&ionic->vf_op_lock); + + ionic_vf_start(ionic); +} + static const struct net_device_ops ionic_netdev_ops = { .ndo_open = ionic_open, .ndo_stop = ionic_stop, @@ -3042,6 +3119,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) if (err) goto err_qcqs_free; + ionic_vf_attr_replay(lif); + if (lif->registered) ionic_lif_set_netdev_info(lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 5456c2b15d9b..a13530ec4dd8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -533,7 +533,7 @@ int ionic_identify(struct ionic *ionic) sz = min(sizeof(ident->drv), sizeof(idev->dev_cmd_regs->data)); memcpy_toio(&idev->dev_cmd_regs->data, &ident->drv, sz); - ionic_dev_cmd_identify(idev, IONIC_IDENTITY_VERSION_1); + ionic_dev_cmd_identify(idev, IONIC_DEV_IDENTITY_VERSION_2); err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); if (!err) { sz = min(sizeof(ident->dev), sizeof(idev->dev_cmd_regs->data)); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index c03986bf2628..0c3977416cd1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -348,16 +348,25 @@ void ionic_rx_fill(struct ionic_queue *q) struct ionic_rxq_sg_desc *sg_desc; struct ionic_rxq_sg_elem *sg_elem; struct ionic_buf_info *buf_info; + unsigned int fill_threshold; struct ionic_rxq_desc *desc; unsigned int remain_len; unsigned int frag_len; unsigned int nfrags; + unsigned int n_fill; unsigned int i, j; unsigned int len; + n_fill = ionic_q_space_avail(q); + + fill_threshold = min_t(unsigned int, IONIC_RX_FILL_THRESHOLD, + q->num_descs / IONIC_RX_FILL_DIV); + if (n_fill < fill_threshold) + return; + len = netdev->mtu + ETH_HLEN + VLAN_HLEN; - for (i = ionic_q_space_avail(q); i; i--) { + for (i = n_fill; i; i--) { nfrags = 0; remain_len = len; desc_info = &q->info[q->head_idx]; @@ -511,7 +520,6 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) struct ionic_cq *cq = napi_to_cq(napi); struct ionic_dev *idev; struct ionic_lif *lif; - u16 rx_fill_threshold; u32 work_done = 0; u32 flags = 0; @@ -521,10 +529,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) work_done = ionic_cq_service(cq, budget, ionic_rx_service, NULL, NULL); - rx_fill_threshold = min_t(u16, IONIC_RX_FILL_THRESHOLD, - cq->num_descs / IONIC_RX_FILL_DIV); - if (work_done && ionic_q_space_avail(cq->bound_q) >= rx_fill_threshold) - ionic_rx_fill(cq->bound_q); + ionic_rx_fill(cq->bound_q); if (work_done < budget && napi_complete_done(napi, work_done)) { ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR); @@ -550,7 +555,6 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; - u16 rx_fill_threshold; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; @@ -565,10 +569,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) rx_work_done = ionic_cq_service(rxcq, budget, ionic_rx_service, NULL, NULL); - rx_fill_threshold = min_t(u16, IONIC_RX_FILL_THRESHOLD, - rxcq->num_descs / IONIC_RX_FILL_DIV); - if (rx_work_done && ionic_q_space_avail(rxcq->bound_q) >= rx_fill_threshold) - ionic_rx_fill(rxcq->bound_q); + ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { ionic_dim_update(qcq, 0); @@ -925,8 +926,12 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) len = skb->len; mss = skb_shinfo(skb)->gso_size; - outer_csum = (skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM) || - (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + outer_csum = (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_IPXIP4 | + SKB_GSO_IPXIP6 | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM)); has_vlan = !!skb_vlan_tag_present(skb); vlan_tci = skb_vlan_tag_get(skb); encap = skb->encapsulation; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 5250d1d1e49c..86ecb080b153 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1972,9 +1972,10 @@ static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn, u8 split_id) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u8 port_id = 0, pf_id = 0, vf_id = 0, fid = 0; + u8 port_id = 0, pf_id = 0, vf_id = 0; bool read_using_dmae = false; u32 thresh; + u16 fid; if (!dump) return len; diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index 6bb4e165b592..922c47797af6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -162,10 +162,6 @@ static int qed_devlink_info_get(struct devlink *devlink, dev_info = &cdev->common_dev_info; - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; - memcpy(buf, cdev->hwfns[0].hw_info.part_num, sizeof(cdev->hwfns[0].hw_info.part_num)); buf[sizeof(cdev->hwfns[0].hw_info.part_num)] = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index ed274f033626..e5116a86cfbc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -200,7 +200,7 @@ static void qed_ll2b_complete_rx_packet(void *cxt, dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr, cdev->ll2->rx_size, DMA_FROM_DEVICE); - skb = build_skb(buffer->data, 0); + skb = slab_build_skb(buffer->data); if (!skb) { DP_INFO(cdev, "Failed to build SKB\n"); kfree(buffer->data); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index c9c8225f04d6..747cc5e2bb78 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -28,16 +28,19 @@ struct qede_ptp { }; /** - * qede_ptp_adjfreq() - Adjust the frequency of the PTP cycle counter. + * qede_ptp_adjfine() - Adjust the frequency of the PTP cycle counter. * * @info: The PTP clock info structure. - * @ppb: Parts per billion adjustment from base. + * @scaled_ppm: Scaled parts per million adjustment from base. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. * * Return: Zero on success, negative errno otherwise. */ -static int qede_ptp_adjfreq(struct ptp_clock_info *info, s32 ppb) +static int qede_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct qede_ptp *ptp = container_of(info, struct qede_ptp, clock_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); struct qede_dev *edev = ptp->edev; int rc; @@ -47,7 +50,7 @@ static int qede_ptp_adjfreq(struct ptp_clock_info *info, s32 ppb) rc = ptp->ops->adjfreq(edev->cdev, ppb); spin_unlock_bh(&ptp->lock); } else { - DP_ERR(edev, "PTP adjfreq called while interface is down\n"); + DP_ERR(edev, "PTP adjfine called while interface is down\n"); rc = -EFAULT; } __qede_unlock(edev); @@ -462,7 +465,7 @@ int qede_ptp_enable(struct qede_dev *edev) ptp->clock_info.n_ext_ts = 0; ptp->clock_info.n_per_out = 0; ptp->clock_info.pps = 0; - ptp->clock_info.adjfreq = qede_ptp_adjfreq; + ptp->clock_info.adjfine = qede_ptp_adjfine; ptp->clock_info.adjtime = qede_ptp_adjtime; ptp->clock_info.gettime64 = qede_ptp_gettime; ptp->clock_info.settime64 = qede_ptp_settime; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 1ee491f78c6b..c1436e1554de 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -711,7 +711,7 @@ static int qlcnic_validate_ring_count(struct qlcnic_adapter *adapter, } } - if (tx_ring != 0) { + if (tx_ring != 0) { if (tx_ring > adapter->max_tx_rings) { netdev_err(adapter->netdev, "Invalid ring count, Tx ring count %d should not be greater than max %d driver Tx rings.\n", diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 1b2119b1d48a..3f5e6572d20e 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -135,9 +135,9 @@ static void rmnet_get_stats64(struct net_device *dev, pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); do { - start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); + start = u64_stats_fetch_begin(&pcpu_ptr->syncp); snapshot = pcpu_ptr->stats; /* struct assignment */ - } while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start)); + } while (u64_stats_fetch_retry(&pcpu_ptr->syncp, start)); total_stats.rx_pkts += snapshot.rx_pkts; total_stats.rx_bytes += snapshot.rx_bytes; diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 469e2e229c6e..9ce0e8a64ba8 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2532,16 +2532,16 @@ rtl8139_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) netdev_stats_to_stats64(stats, &dev->stats); do { - start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp); + start = u64_stats_fetch_begin(&tp->rx_stats.syncp); stats->rx_packets = tp->rx_stats.packets; stats->rx_bytes = tp->rx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&tp->rx_stats.syncp, start)); do { - start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp); + start = u64_stats_fetch_begin(&tp->tx_stats.syncp); stats->tx_packets = tp->tx_stats.packets; stats->tx_bytes = tp->tx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&tp->tx_stats.syncp, start)); } /* Set or clear the multicast filter for this adaptor. diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a73d061d9fcb..a9dcc98b6af1 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4559,12 +4559,13 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) static void r8169_phylink_handler(struct net_device *ndev) { struct rtl8169_private *tp = netdev_priv(ndev); + struct device *d = tp_to_dev(tp); if (netif_carrier_ok(ndev)) { rtl_link_chg_patch(tp); - pm_request_resume(&tp->pci_dev->dev); + pm_request_resume(d); } else { - pm_runtime_idle(&tp->pci_dev->dev); + pm_runtime_idle(d); } phy_print_status(tp->phydev); @@ -5018,7 +5019,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp) return -EUNATCH; } - tp->phydev->mac_managed_pm = 1; + tp->phydev->mac_managed_pm = true; phy_support_asym_pause(tp->phydev); @@ -5282,6 +5283,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; + netdev_sw_irq_coalesce_default_on(dev); + /* configure chip for default features */ rtl8169_set_features(dev, dev->features); diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 8008b2f45934..3ceb57408ed0 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -42,4 +42,16 @@ config RAVB This driver supports the following SoCs: - R8A779x. +config RENESAS_ETHER_SWITCH + tristate "Renesas Ethernet Switch support" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PTP_1588_CLOCK_OPTIONAL + select CRC32 + select MII + select PHYLINK + help + Renesas Ethernet Switch device driver. + This driver supports the following SoCs: + - R8A779Fx. + endif # NET_VENDOR_RENESAS diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index f21ab8c02af0..592005893464 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -8,3 +8,7 @@ obj-$(CONFIG_SH_ETH) += sh_eth.o ravb-objs := ravb_main.o ravb_ptp.o obj-$(CONFIG_RAVB) += ravb.o + +rswitch_drv-objs := rswitch.o rcar_gen4_ptp.o + +obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch_drv.o diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index 87c4306d66ec..6e4ef7af27bf 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -88,24 +88,17 @@ static int ravb_ptp_update_compare(struct ravb_private *priv, u32 ns) } /* PTP clock operations */ -static int ravb_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int ravb_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct ravb_private *priv = container_of(ptp, struct ravb_private, ptp.info); struct net_device *ndev = priv->ndev; unsigned long flags; - u32 diff, addend; - bool neg_adj = false; + u32 addend; u32 gccr; - if (ppb < 0) { - neg_adj = true; - ppb = -ppb; - } - addend = priv->ptp.default_addend; - diff = div_u64((u64)addend * ppb, NSEC_PER_SEC); - - addend = neg_adj ? addend - diff : addend + diff; + addend = (u32)adjust_by_scaled_ppm(priv->ptp.default_addend, + scaled_ppm); spin_lock_irqsave(&priv->lock, flags); @@ -295,7 +288,7 @@ static const struct ptp_clock_info ravb_ptp_info = { .max_adj = 50000000, .n_ext_ts = N_EXT_TS, .n_per_out = N_PER_OUT, - .adjfreq = ravb_ptp_adjfreq, + .adjfine = ravb_ptp_adjfine, .adjtime = ravb_ptp_adjtime, .gettime64 = ravb_ptp_gettime64, .settime64 = ravb_ptp_settime64, diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c new file mode 100644 index 000000000000..c007e33c47e1 --- /dev/null +++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Renesas R-Car Gen4 gPTP device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#include <linux/err.h> +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "rcar_gen4_ptp.h" +#define ptp_to_priv(ptp) container_of(ptp, struct rcar_gen4_ptp_private, info) + +static const struct rcar_gen4_ptp_reg_offset s4_offs = { + .enable = PTPTMEC, + .disable = PTPTMDC, + .increment = PTPTIVC0, + .config_t0 = PTPTOVC00, + .config_t1 = PTPTOVC10, + .config_t2 = PTPTOVC20, + .monitor_t0 = PTPGPTPTM00, + .monitor_t1 = PTPGPTPTM10, + .monitor_t2 = PTPGPTPTM20, +}; + +static int rcar_gen4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + bool neg_adj = scaled_ppm < 0 ? true : false; + s64 addend = ptp_priv->default_addend; + s64 diff; + + if (neg_adj) + scaled_ppm = -scaled_ppm; + diff = div_s64(addend * scaled_ppm_to_ppb(scaled_ppm), NSEC_PER_SEC); + addend = neg_adj ? addend - diff : addend + diff; + + iowrite32(addend, ptp_priv->addr + ptp_priv->offs->increment); + + return 0; +} + +/* Caller must hold the lock */ +static void _rcar_gen4_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + + ts->tv_nsec = ioread32(ptp_priv->addr + ptp_priv->offs->monitor_t0); + ts->tv_sec = ioread32(ptp_priv->addr + ptp_priv->offs->monitor_t1) | + ((s64)ioread32(ptp_priv->addr + ptp_priv->offs->monitor_t2) << 32); +} + +static int rcar_gen4_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + unsigned long flags; + + spin_lock_irqsave(&ptp_priv->lock, flags); + _rcar_gen4_ptp_gettime(ptp, ts); + spin_unlock_irqrestore(&ptp_priv->lock, flags); + + return 0; +} + +/* Caller must hold the lock */ +static void _rcar_gen4_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + + iowrite32(1, ptp_priv->addr + ptp_priv->offs->disable); + iowrite32(0, ptp_priv->addr + ptp_priv->offs->config_t2); + iowrite32(0, ptp_priv->addr + ptp_priv->offs->config_t1); + iowrite32(0, ptp_priv->addr + ptp_priv->offs->config_t0); + iowrite32(1, ptp_priv->addr + ptp_priv->offs->enable); + iowrite32(ts->tv_sec >> 32, ptp_priv->addr + ptp_priv->offs->config_t2); + iowrite32(ts->tv_sec, ptp_priv->addr + ptp_priv->offs->config_t1); + iowrite32(ts->tv_nsec, ptp_priv->addr + ptp_priv->offs->config_t0); +} + +static int rcar_gen4_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + unsigned long flags; + + spin_lock_irqsave(&ptp_priv->lock, flags); + _rcar_gen4_ptp_settime(ptp, ts); + spin_unlock_irqrestore(&ptp_priv->lock, flags); + + return 0; +} + +static int rcar_gen4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp); + struct timespec64 ts; + unsigned long flags; + s64 now; + + spin_lock_irqsave(&ptp_priv->lock, flags); + _rcar_gen4_ptp_gettime(ptp, &ts); + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + _rcar_gen4_ptp_settime(ptp, &ts); + spin_unlock_irqrestore(&ptp_priv->lock, flags); + + return 0; +} + +static int rcar_gen4_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +static struct ptp_clock_info rcar_gen4_ptp_info = { + .owner = THIS_MODULE, + .name = "rcar_gen4_ptp", + .max_adj = 50000000, + .adjfine = rcar_gen4_ptp_adjfine, + .adjtime = rcar_gen4_ptp_adjtime, + .gettime64 = rcar_gen4_ptp_gettime, + .settime64 = rcar_gen4_ptp_settime, + .enable = rcar_gen4_ptp_enable, +}; + +static void rcar_gen4_ptp_set_offs(struct rcar_gen4_ptp_private *ptp_priv, + enum rcar_gen4_ptp_reg_layout layout) +{ + WARN_ON(layout != RCAR_GEN4_PTP_REG_LAYOUT_S4); + + ptp_priv->offs = &s4_offs; +} + +int rcar_gen4_ptp_register(struct rcar_gen4_ptp_private *ptp_priv, + enum rcar_gen4_ptp_reg_layout layout, u32 clock) +{ + if (ptp_priv->initialized) + return 0; + + spin_lock_init(&ptp_priv->lock); + + rcar_gen4_ptp_set_offs(ptp_priv, layout); + + ptp_priv->default_addend = clock; + iowrite32(ptp_priv->default_addend, ptp_priv->addr + ptp_priv->offs->increment); + ptp_priv->clock = ptp_clock_register(&ptp_priv->info, NULL); + if (IS_ERR(ptp_priv->clock)) + return PTR_ERR(ptp_priv->clock); + + iowrite32(0x01, ptp_priv->addr + ptp_priv->offs->enable); + ptp_priv->initialized = true; + + return 0; +} + +int rcar_gen4_ptp_unregister(struct rcar_gen4_ptp_private *ptp_priv) +{ + iowrite32(1, ptp_priv->addr + ptp_priv->offs->disable); + + return ptp_clock_unregister(ptp_priv->clock); +} + +struct rcar_gen4_ptp_private *rcar_gen4_ptp_alloc(struct platform_device *pdev) +{ + struct rcar_gen4_ptp_private *ptp; + + ptp = devm_kzalloc(&pdev->dev, sizeof(*ptp), GFP_KERNEL); + if (!ptp) + return NULL; + + ptp->info = rcar_gen4_ptp_info; + + return ptp; +} diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.h b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h new file mode 100644 index 000000000000..b1bbea8d3a52 --- /dev/null +++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Renesas R-Car Gen4 gPTP device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#ifndef __RCAR_GEN4_PTP_H__ +#define __RCAR_GEN4_PTP_H__ + +#include <linux/ptp_clock_kernel.h> + +#define PTPTIVC_INIT 0x19000000 /* 320MHz */ +#define RCAR_GEN4_PTP_CLOCK_S4 PTPTIVC_INIT +#define RCAR_GEN4_GPTP_OFFSET_S4 0x00018000 + +/* for rcar_gen4_ptp_init */ +enum rcar_gen4_ptp_reg_layout { + RCAR_GEN4_PTP_REG_LAYOUT_S4 +}; + +/* driver's definitions */ +#define RCAR_GEN4_RXTSTAMP_ENABLED BIT(0) +#define RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT BIT(1) +#define RCAR_GEN4_RXTSTAMP_TYPE_ALL (RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT | BIT(2)) +#define RCAR_GEN4_RXTSTAMP_TYPE RCAR_GEN4_RXTSTAMP_TYPE_ALL + +#define RCAR_GEN4_TXTSTAMP_ENABLED BIT(0) + +#define PTPRO 0 + +enum rcar_gen4_ptp_reg_s4 { + PTPTMEC = PTPRO + 0x0010, + PTPTMDC = PTPRO + 0x0014, + PTPTIVC0 = PTPRO + 0x0020, + PTPTOVC00 = PTPRO + 0x0030, + PTPTOVC10 = PTPRO + 0x0034, + PTPTOVC20 = PTPRO + 0x0038, + PTPGPTPTM00 = PTPRO + 0x0050, + PTPGPTPTM10 = PTPRO + 0x0054, + PTPGPTPTM20 = PTPRO + 0x0058, +}; + +struct rcar_gen4_ptp_reg_offset { + u16 enable; + u16 disable; + u16 increment; + u16 config_t0; + u16 config_t1; + u16 config_t2; + u16 monitor_t0; + u16 monitor_t1; + u16 monitor_t2; +}; + +struct rcar_gen4_ptp_private { + void __iomem *addr; + struct ptp_clock *clock; + struct ptp_clock_info info; + const struct rcar_gen4_ptp_reg_offset *offs; + spinlock_t lock; /* For multiple registers access */ + u32 tstamp_tx_ctrl; + u32 tstamp_rx_ctrl; + s64 default_addend; + bool initialized; +}; + +int rcar_gen4_ptp_register(struct rcar_gen4_ptp_private *ptp_priv, + enum rcar_gen4_ptp_reg_layout layout, u32 clock); +int rcar_gen4_ptp_unregister(struct rcar_gen4_ptp_private *ptp_priv); +struct rcar_gen4_ptp_private *rcar_gen4_ptp_alloc(struct platform_device *pdev); + +#endif /* #ifndef __RCAR_GEN4_PTP_H__ */ diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c new file mode 100644 index 000000000000..e42ceaa0099f --- /dev/null +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -0,0 +1,1841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Renesas Ethernet Switch device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#include <linux/dma-mapping.h> +#include <linux/err.h> +#include <linux/etherdevice.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/net_tstamp.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/phylink.h> +#include <linux/phy/phy.h> +#include <linux/pm_runtime.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "rswitch.h" + +static int rswitch_reg_wait(void __iomem *addr, u32 offs, u32 mask, u32 expected) +{ + u32 val; + + return readl_poll_timeout_atomic(addr + offs, val, (val & mask) == expected, + 1, RSWITCH_TIMEOUT_US); +} + +static void rswitch_modify(void __iomem *addr, enum rswitch_reg reg, u32 clear, u32 set) +{ + iowrite32((ioread32(addr + reg) & ~clear) | set, addr + reg); +} + +/* Common Agent block (COMA) */ +static void rswitch_reset(struct rswitch_private *priv) +{ + iowrite32(RRC_RR, priv->addr + RRC); + iowrite32(RRC_RR_CLR, priv->addr + RRC); +} + +static void rswitch_clock_enable(struct rswitch_private *priv) +{ + iowrite32(RCEC_ACE_DEFAULT | RCEC_RCE, priv->addr + RCEC); +} + +static void rswitch_clock_disable(struct rswitch_private *priv) +{ + iowrite32(RCDC_RCD, priv->addr + RCDC); +} + +static bool rswitch_agent_clock_is_enabled(void __iomem *coma_addr, int port) +{ + u32 val = ioread32(coma_addr + RCEC); + + if (val & RCEC_RCE) + return (val & BIT(port)) ? true : false; + else + return false; +} + +static void rswitch_agent_clock_ctrl(void __iomem *coma_addr, int port, int enable) +{ + u32 val; + + if (enable) { + val = ioread32(coma_addr + RCEC); + iowrite32(val | RCEC_RCE | BIT(port), coma_addr + RCEC); + } else { + val = ioread32(coma_addr + RCDC); + iowrite32(val | BIT(port), coma_addr + RCDC); + } +} + +static int rswitch_bpool_config(struct rswitch_private *priv) +{ + u32 val; + + val = ioread32(priv->addr + CABPIRM); + if (val & CABPIRM_BPR) + return 0; + + iowrite32(CABPIRM_BPIOG, priv->addr + CABPIRM); + + return rswitch_reg_wait(priv->addr, CABPIRM, CABPIRM_BPR, CABPIRM_BPR); +} + +/* R-Switch-2 block (TOP) */ +static void rswitch_top_init(struct rswitch_private *priv) +{ + int i; + + for (i = 0; i < RSWITCH_MAX_NUM_QUEUES; i++) + iowrite32((i / 16) << (GWCA_INDEX * 8), priv->addr + TPEMIMC7(i)); +} + +/* Forwarding engine block (MFWD) */ +static void rswitch_fwd_init(struct rswitch_private *priv) +{ + int i; + + /* For ETHA */ + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(i)); + iowrite32(0, priv->addr + FWPBFC(i)); + } + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + iowrite32(priv->rdev[i]->rx_queue->index, + priv->addr + FWPBFCSDC(GWCA_INDEX, i)); + iowrite32(BIT(priv->gwca.index), priv->addr + FWPBFC(i)); + } + + /* For GWCA */ + iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(priv->gwca.index)); + iowrite32(FWPC1_DDE, priv->addr + FWPC1(priv->gwca.index)); + iowrite32(0, priv->addr + FWPBFC(priv->gwca.index)); + iowrite32(GENMASK(RSWITCH_NUM_PORTS - 1, 0), priv->addr + FWPBFC(priv->gwca.index)); +} + +/* gPTP timer (gPTP) */ +static void rswitch_get_timestamp(struct rswitch_private *priv, + struct timespec64 *ts) +{ + priv->ptp_priv->info.gettime64(&priv->ptp_priv->info, ts); +} + +/* Gateway CPU agent block (GWCA) */ +static int rswitch_gwca_change_mode(struct rswitch_private *priv, + enum rswitch_gwca_mode mode) +{ + int ret; + + if (!rswitch_agent_clock_is_enabled(priv->addr, priv->gwca.index)) + rswitch_agent_clock_ctrl(priv->addr, priv->gwca.index, 1); + + iowrite32(mode, priv->addr + GWMC); + + ret = rswitch_reg_wait(priv->addr, GWMS, GWMS_OPS_MASK, mode); + + if (mode == GWMC_OPC_DISABLE) + rswitch_agent_clock_ctrl(priv->addr, priv->gwca.index, 0); + + return ret; +} + +static int rswitch_gwca_mcast_table_reset(struct rswitch_private *priv) +{ + iowrite32(GWMTIRM_MTIOG, priv->addr + GWMTIRM); + + return rswitch_reg_wait(priv->addr, GWMTIRM, GWMTIRM_MTR, GWMTIRM_MTR); +} + +static int rswitch_gwca_axi_ram_reset(struct rswitch_private *priv) +{ + iowrite32(GWARIRM_ARIOG, priv->addr + GWARIRM); + + return rswitch_reg_wait(priv->addr, GWARIRM, GWARIRM_ARR, GWARIRM_ARR); +} + +static void rswitch_gwca_set_rate_limit(struct rswitch_private *priv, int rate) +{ + u32 gwgrlulc, gwgrlc; + + switch (rate) { + case 1000: + gwgrlulc = 0x0000005f; + gwgrlc = 0x00010260; + break; + default: + dev_err(&priv->pdev->dev, "%s: This rate is not supported (%d)\n", __func__, rate); + return; + } + + iowrite32(gwgrlulc, priv->addr + GWGRLULC); + iowrite32(gwgrlc, priv->addr + GWGRLC); +} + +static bool rswitch_is_any_data_irq(struct rswitch_private *priv, u32 *dis, bool tx) +{ + u32 *mask = tx ? priv->gwca.tx_irq_bits : priv->gwca.rx_irq_bits; + int i; + + for (i = 0; i < RSWITCH_NUM_IRQ_REGS; i++) { + if (dis[i] & mask[i]) + return true; + } + + return false; +} + +static void rswitch_get_data_irq_status(struct rswitch_private *priv, u32 *dis) +{ + int i; + + for (i = 0; i < RSWITCH_NUM_IRQ_REGS; i++) { + dis[i] = ioread32(priv->addr + GWDIS(i)); + dis[i] &= ioread32(priv->addr + GWDIE(i)); + } +} + +static void rswitch_enadis_data_irq(struct rswitch_private *priv, int index, bool enable) +{ + u32 offs = enable ? GWDIE(index / 32) : GWDID(index / 32); + + iowrite32(BIT(index % 32), priv->addr + offs); +} + +static void rswitch_ack_data_irq(struct rswitch_private *priv, int index) +{ + u32 offs = GWDIS(index / 32); + + iowrite32(BIT(index % 32), priv->addr + offs); +} + +static int rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, int num) +{ + int index = cur ? gq->cur : gq->dirty; + + if (index + num >= gq->ring_size) + index = (index + num) % gq->ring_size; + else + index += num; + + return index; +} + +static int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq) +{ + if (gq->cur >= gq->dirty) + return gq->cur - gq->dirty; + else + return gq->ring_size - gq->dirty + gq->cur; +} + +static bool rswitch_is_queue_rxed(struct rswitch_gwca_queue *gq) +{ + struct rswitch_ext_ts_desc *desc = &gq->ts_ring[gq->dirty]; + + if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) + return true; + + return false; +} + +static int rswitch_gwca_queue_alloc_skb(struct rswitch_gwca_queue *gq, + int start_index, int num) +{ + int i, index; + + for (i = 0; i < num; i++) { + index = (i + start_index) % gq->ring_size; + if (gq->skbs[index]) + continue; + gq->skbs[index] = netdev_alloc_skb_ip_align(gq->ndev, + PKT_BUF_SZ + RSWITCH_ALIGN - 1); + if (!gq->skbs[index]) + goto err; + } + + return 0; + +err: + for (i--; i >= 0; i--) { + index = (i + start_index) % gq->ring_size; + dev_kfree_skb(gq->skbs[index]); + gq->skbs[index] = NULL; + } + + return -ENOMEM; +} + +static void rswitch_gwca_queue_free(struct net_device *ndev, + struct rswitch_gwca_queue *gq) +{ + int i; + + if (gq->gptp) { + dma_free_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_ts_desc) * + (gq->ring_size + 1), gq->ts_ring, gq->ring_dma); + gq->ts_ring = NULL; + } else { + dma_free_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_desc) * + (gq->ring_size + 1), gq->ring, gq->ring_dma); + gq->ring = NULL; + } + + if (!gq->dir_tx) { + for (i = 0; i < gq->ring_size; i++) + dev_kfree_skb(gq->skbs[i]); + } + + kfree(gq->skbs); + gq->skbs = NULL; +} + +static int rswitch_gwca_queue_alloc(struct net_device *ndev, + struct rswitch_private *priv, + struct rswitch_gwca_queue *gq, + bool dir_tx, bool gptp, int ring_size) +{ + int i, bit; + + gq->dir_tx = dir_tx; + gq->gptp = gptp; + gq->ring_size = ring_size; + gq->ndev = ndev; + + gq->skbs = kcalloc(gq->ring_size, sizeof(*gq->skbs), GFP_KERNEL); + if (!gq->skbs) + return -ENOMEM; + + if (!dir_tx) + rswitch_gwca_queue_alloc_skb(gq, 0, gq->ring_size); + + if (gptp) + gq->ts_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_ts_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + else + gq->ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + if (!gq->ts_ring && !gq->ring) + goto out; + + i = gq->index / 32; + bit = BIT(gq->index % 32); + if (dir_tx) + priv->gwca.tx_irq_bits[i] |= bit; + else + priv->gwca.rx_irq_bits[i] |= bit; + + return 0; + +out: + rswitch_gwca_queue_free(ndev, gq); + + return -ENOMEM; +} + +static void rswitch_desc_set_dptr(struct rswitch_desc *desc, dma_addr_t addr) +{ + desc->dptrl = cpu_to_le32(lower_32_bits(addr)); + desc->dptrh = upper_32_bits(addr) & 0xff; +} + +static dma_addr_t rswitch_desc_get_dptr(const struct rswitch_desc *desc) +{ + return __le32_to_cpu(desc->dptrl) | (u64)(desc->dptrh) << 32; +} + +static int rswitch_gwca_queue_format(struct net_device *ndev, + struct rswitch_private *priv, + struct rswitch_gwca_queue *gq) +{ + int tx_ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size; + struct rswitch_ext_desc *desc; + struct rswitch_desc *linkfix; + dma_addr_t dma_addr; + int i; + + memset(gq->ring, 0, tx_ring_size); + for (i = 0, desc = gq->ring; i < gq->ring_size; i++, desc++) { + if (!gq->dir_tx) { + dma_addr = dma_map_single(ndev->dev.parent, + gq->skbs[i]->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto err; + + desc->desc.info_ds = cpu_to_le16(PKT_BUF_SZ); + rswitch_desc_set_dptr(&desc->desc, dma_addr); + desc->desc.die_dt = DT_FEMPTY | DIE; + } else { + desc->desc.die_dt = DT_EEMPTY | DIE; + } + } + rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); + desc->desc.die_dt = DT_LINKFIX; + + linkfix = &priv->linkfix_table[gq->index]; + linkfix->die_dt = DT_LINKFIX; + rswitch_desc_set_dptr(linkfix, gq->ring_dma); + + iowrite32(GWDCC_BALR | (gq->dir_tx ? GWDCC_DQT : 0) | GWDCC_EDE, + priv->addr + GWDCC_OFFS(gq->index)); + + return 0; + +err: + if (!gq->dir_tx) { + for (i--, desc = gq->ring; i >= 0; i--, desc++) { + dma_addr = rswitch_desc_get_dptr(&desc->desc); + dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); + } + } + + return -ENOMEM; +} + +static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, + struct rswitch_gwca_queue *gq, + int start_index, int num) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_ext_ts_desc *desc; + dma_addr_t dma_addr; + int i, index; + + for (i = 0; i < num; i++) { + index = (i + start_index) % gq->ring_size; + desc = &gq->ts_ring[index]; + if (!gq->dir_tx) { + dma_addr = dma_map_single(ndev->dev.parent, + gq->skbs[index]->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto err; + + desc->desc.info_ds = cpu_to_le16(PKT_BUF_SZ); + rswitch_desc_set_dptr(&desc->desc, dma_addr); + dma_wmb(); + desc->desc.die_dt = DT_FEMPTY | DIE; + desc->info1 = cpu_to_le64(INFO1_SPN(rdev->etha->index)); + } else { + desc->desc.die_dt = DT_EEMPTY | DIE; + } + } + + return 0; + +err: + if (!gq->dir_tx) { + for (i--; i >= 0; i--) { + index = (i + start_index) % gq->ring_size; + desc = &gq->ts_ring[index]; + dma_addr = rswitch_desc_get_dptr(&desc->desc); + dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); + } + } + + return -ENOMEM; +} + +static int rswitch_gwca_queue_ts_format(struct net_device *ndev, + struct rswitch_private *priv, + struct rswitch_gwca_queue *gq) +{ + int tx_ts_ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size; + struct rswitch_ext_ts_desc *desc; + struct rswitch_desc *linkfix; + int err; + + memset(gq->ts_ring, 0, tx_ts_ring_size); + err = rswitch_gwca_queue_ts_fill(ndev, gq, 0, gq->ring_size); + if (err < 0) + return err; + + desc = &gq->ts_ring[gq->ring_size]; /* Last */ + rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); + desc->desc.die_dt = DT_LINKFIX; + + linkfix = &priv->linkfix_table[gq->index]; + linkfix->die_dt = DT_LINKFIX; + rswitch_desc_set_dptr(linkfix, gq->ring_dma); + + iowrite32(GWDCC_BALR | (gq->dir_tx ? GWDCC_DQT : 0) | GWDCC_ETS | GWDCC_EDE, + priv->addr + GWDCC_OFFS(gq->index)); + + return 0; +} + +static int rswitch_gwca_desc_alloc(struct rswitch_private *priv) +{ + int i, num_queues = priv->gwca.num_queues; + struct device *dev = &priv->pdev->dev; + + priv->linkfix_table_size = sizeof(struct rswitch_desc) * num_queues; + priv->linkfix_table = dma_alloc_coherent(dev, priv->linkfix_table_size, + &priv->linkfix_table_dma, GFP_KERNEL); + if (!priv->linkfix_table) + return -ENOMEM; + for (i = 0; i < num_queues; i++) + priv->linkfix_table[i].die_dt = DT_EOS; + + return 0; +} + +static void rswitch_gwca_desc_free(struct rswitch_private *priv) +{ + if (priv->linkfix_table) + dma_free_coherent(&priv->pdev->dev, priv->linkfix_table_size, + priv->linkfix_table, priv->linkfix_table_dma); + priv->linkfix_table = NULL; +} + +static struct rswitch_gwca_queue *rswitch_gwca_get(struct rswitch_private *priv) +{ + struct rswitch_gwca_queue *gq; + int index; + + index = find_first_zero_bit(priv->gwca.used, priv->gwca.num_queues); + if (index >= priv->gwca.num_queues) + return NULL; + set_bit(index, priv->gwca.used); + gq = &priv->gwca.queues[index]; + memset(gq, 0, sizeof(*gq)); + gq->index = index; + + return gq; +} + +static void rswitch_gwca_put(struct rswitch_private *priv, + struct rswitch_gwca_queue *gq) +{ + clear_bit(gq->index, priv->gwca.used); +} + +static int rswitch_txdmac_alloc(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_private *priv = rdev->priv; + int err; + + rdev->tx_queue = rswitch_gwca_get(priv); + if (!rdev->tx_queue) + return -EBUSY; + + err = rswitch_gwca_queue_alloc(ndev, priv, rdev->tx_queue, true, false, + TX_RING_SIZE); + if (err < 0) { + rswitch_gwca_put(priv, rdev->tx_queue); + return err; + } + + return 0; +} + +static void rswitch_txdmac_free(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + rswitch_gwca_queue_free(ndev, rdev->tx_queue); + rswitch_gwca_put(rdev->priv, rdev->tx_queue); +} + +static int rswitch_txdmac_init(struct rswitch_private *priv, int index) +{ + struct rswitch_device *rdev = priv->rdev[index]; + + return rswitch_gwca_queue_format(rdev->ndev, priv, rdev->tx_queue); +} + +static int rswitch_rxdmac_alloc(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_private *priv = rdev->priv; + int err; + + rdev->rx_queue = rswitch_gwca_get(priv); + if (!rdev->rx_queue) + return -EBUSY; + + err = rswitch_gwca_queue_alloc(ndev, priv, rdev->rx_queue, false, true, + RX_RING_SIZE); + if (err < 0) { + rswitch_gwca_put(priv, rdev->rx_queue); + return err; + } + + return 0; +} + +static void rswitch_rxdmac_free(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + rswitch_gwca_queue_free(ndev, rdev->rx_queue); + rswitch_gwca_put(rdev->priv, rdev->rx_queue); +} + +static int rswitch_rxdmac_init(struct rswitch_private *priv, int index) +{ + struct rswitch_device *rdev = priv->rdev[index]; + struct net_device *ndev = rdev->ndev; + + return rswitch_gwca_queue_ts_format(ndev, priv, rdev->rx_queue); +} + +static int rswitch_gwca_hw_init(struct rswitch_private *priv) +{ + int i, err; + + err = rswitch_gwca_change_mode(priv, GWMC_OPC_DISABLE); + if (err < 0) + return err; + err = rswitch_gwca_change_mode(priv, GWMC_OPC_CONFIG); + if (err < 0) + return err; + + err = rswitch_gwca_mcast_table_reset(priv); + if (err < 0) + return err; + err = rswitch_gwca_axi_ram_reset(priv); + if (err < 0) + return err; + + iowrite32(GWVCC_VEM_SC_TAG, priv->addr + GWVCC); + iowrite32(0, priv->addr + GWTTFC); + iowrite32(lower_32_bits(priv->linkfix_table_dma), priv->addr + GWDCBAC1); + iowrite32(upper_32_bits(priv->linkfix_table_dma), priv->addr + GWDCBAC0); + rswitch_gwca_set_rate_limit(priv, priv->gwca.speed); + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + err = rswitch_rxdmac_init(priv, i); + if (err < 0) + return err; + err = rswitch_txdmac_init(priv, i); + if (err < 0) + return err; + } + + err = rswitch_gwca_change_mode(priv, GWMC_OPC_DISABLE); + if (err < 0) + return err; + return rswitch_gwca_change_mode(priv, GWMC_OPC_OPERATION); +} + +static int rswitch_gwca_hw_deinit(struct rswitch_private *priv) +{ + int err; + + err = rswitch_gwca_change_mode(priv, GWMC_OPC_DISABLE); + if (err < 0) + return err; + err = rswitch_gwca_change_mode(priv, GWMC_OPC_RESET); + if (err < 0) + return err; + + return rswitch_gwca_change_mode(priv, GWMC_OPC_DISABLE); +} + +static int rswitch_gwca_halt(struct rswitch_private *priv) +{ + int err; + + priv->gwca_halt = true; + err = rswitch_gwca_hw_deinit(priv); + dev_err(&priv->pdev->dev, "halted (%d)\n", err); + + return err; +} + +static bool rswitch_rx(struct net_device *ndev, int *quota) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_gwca_queue *gq = rdev->rx_queue; + struct rswitch_ext_ts_desc *desc; + int limit, boguscnt, num, ret; + struct sk_buff *skb; + dma_addr_t dma_addr; + u16 pkt_len; + u32 get_ts; + + boguscnt = min_t(int, gq->ring_size, *quota); + limit = boguscnt; + + desc = &gq->ts_ring[gq->cur]; + while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) { + if (--boguscnt < 0) + break; + dma_rmb(); + pkt_len = le16_to_cpu(desc->desc.info_ds) & RX_DS; + skb = gq->skbs[gq->cur]; + gq->skbs[gq->cur] = NULL; + dma_addr = rswitch_desc_get_dptr(&desc->desc); + dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE); + get_ts = rdev->priv->ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + if (get_ts) { + struct skb_shared_hwtstamps *shhwtstamps; + struct timespec64 ts; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps->hwtstamp = timespec64_to_ktime(ts); + } + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + netif_receive_skb(skb); + rdev->ndev->stats.rx_packets++; + rdev->ndev->stats.rx_bytes += pkt_len; + + gq->cur = rswitch_next_queue_index(gq, true, 1); + desc = &gq->ts_ring[gq->cur]; + } + + num = rswitch_get_num_cur_queues(gq); + ret = rswitch_gwca_queue_alloc_skb(gq, gq->dirty, num); + if (ret < 0) + goto err; + ret = rswitch_gwca_queue_ts_fill(ndev, gq, gq->dirty, num); + if (ret < 0) + goto err; + gq->dirty = rswitch_next_queue_index(gq, false, num); + + *quota -= limit - (++boguscnt); + + return boguscnt <= 0; + +err: + rswitch_gwca_halt(rdev->priv); + + return 0; +} + +static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_gwca_queue *gq = rdev->tx_queue; + struct rswitch_ext_desc *desc; + dma_addr_t dma_addr; + struct sk_buff *skb; + int free_num = 0; + int size; + + for (; rswitch_get_num_cur_queues(gq) > 0; + gq->dirty = rswitch_next_queue_index(gq, false, 1)) { + desc = &gq->ring[gq->dirty]; + if (free_txed_only && (desc->desc.die_dt & DT_MASK) != DT_FEMPTY) + break; + + dma_rmb(); + size = le16_to_cpu(desc->desc.info_ds) & TX_DS; + skb = gq->skbs[gq->dirty]; + if (skb) { + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + struct skb_shared_hwtstamps shhwtstamps; + struct timespec64 ts; + + rswitch_get_timestamp(rdev->priv, &ts); + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(skb, &shhwtstamps); + } + dma_addr = rswitch_desc_get_dptr(&desc->desc); + dma_unmap_single(ndev->dev.parent, dma_addr, + size, DMA_TO_DEVICE); + dev_kfree_skb_any(gq->skbs[gq->dirty]); + gq->skbs[gq->dirty] = NULL; + free_num++; + } + desc->desc.die_dt = DT_EEMPTY; + rdev->ndev->stats.tx_packets++; + rdev->ndev->stats.tx_bytes += size; + } + + return free_num; +} + +static int rswitch_poll(struct napi_struct *napi, int budget) +{ + struct net_device *ndev = napi->dev; + struct rswitch_private *priv; + struct rswitch_device *rdev; + int quota = budget; + + rdev = netdev_priv(ndev); + priv = rdev->priv; + +retry: + rswitch_tx_free(ndev, true); + + if (rswitch_rx(ndev, "a)) + goto out; + else if (rdev->priv->gwca_halt) + goto err; + else if (rswitch_is_queue_rxed(rdev->rx_queue)) + goto retry; + + netif_wake_subqueue(ndev, 0); + + napi_complete(napi); + + rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true); + rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true); + +out: + return budget - quota; + +err: + napi_complete(napi); + + return 0; +} + +static void rswitch_queue_interrupt(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + if (napi_schedule_prep(&rdev->napi)) { + rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); + rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); + __napi_schedule(&rdev->napi); + } +} + +static irqreturn_t rswitch_data_irq(struct rswitch_private *priv, u32 *dis) +{ + struct rswitch_gwca_queue *gq; + int i, index, bit; + + for (i = 0; i < priv->gwca.num_queues; i++) { + gq = &priv->gwca.queues[i]; + index = gq->index / 32; + bit = BIT(gq->index % 32); + if (!(dis[index] & bit)) + continue; + + rswitch_ack_data_irq(priv, gq->index); + rswitch_queue_interrupt(gq->ndev); + } + + return IRQ_HANDLED; +} + +static irqreturn_t rswitch_gwca_irq(int irq, void *dev_id) +{ + struct rswitch_private *priv = dev_id; + u32 dis[RSWITCH_NUM_IRQ_REGS]; + irqreturn_t ret = IRQ_NONE; + + rswitch_get_data_irq_status(priv, dis); + + if (rswitch_is_any_data_irq(priv, dis, true) || + rswitch_is_any_data_irq(priv, dis, false)) + ret = rswitch_data_irq(priv, dis); + + return ret; +} + +static int rswitch_gwca_request_irqs(struct rswitch_private *priv) +{ + char *resource_name, *irq_name; + int i, ret, irq; + + for (i = 0; i < GWCA_NUM_IRQS; i++) { + resource_name = kasprintf(GFP_KERNEL, GWCA_IRQ_RESOURCE_NAME, i); + if (!resource_name) + return -ENOMEM; + + irq = platform_get_irq_byname(priv->pdev, resource_name); + kfree(resource_name); + if (irq < 0) + return irq; + + irq_name = devm_kasprintf(&priv->pdev->dev, GFP_KERNEL, + GWCA_IRQ_NAME, i); + if (!irq_name) + return -ENOMEM; + + ret = devm_request_irq(&priv->pdev->dev, irq, rswitch_gwca_irq, + 0, irq_name, priv); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Ethernet TSN Agent block (ETHA) and Ethernet MAC IP block (RMAC) */ +static int rswitch_etha_change_mode(struct rswitch_etha *etha, + enum rswitch_etha_mode mode) +{ + int ret; + + if (!rswitch_agent_clock_is_enabled(etha->coma_addr, etha->index)) + rswitch_agent_clock_ctrl(etha->coma_addr, etha->index, 1); + + iowrite32(mode, etha->addr + EAMC); + + ret = rswitch_reg_wait(etha->addr, EAMS, EAMS_OPS_MASK, mode); + + if (mode == EAMC_OPC_DISABLE) + rswitch_agent_clock_ctrl(etha->coma_addr, etha->index, 0); + + return ret; +} + +static void rswitch_etha_read_mac_address(struct rswitch_etha *etha) +{ + u32 mrmac0 = ioread32(etha->addr + MRMAC0); + u32 mrmac1 = ioread32(etha->addr + MRMAC1); + u8 *mac = ða->mac_addr[0]; + + mac[0] = (mrmac0 >> 8) & 0xFF; + mac[1] = (mrmac0 >> 0) & 0xFF; + mac[2] = (mrmac1 >> 24) & 0xFF; + mac[3] = (mrmac1 >> 16) & 0xFF; + mac[4] = (mrmac1 >> 8) & 0xFF; + mac[5] = (mrmac1 >> 0) & 0xFF; +} + +static void rswitch_etha_write_mac_address(struct rswitch_etha *etha, const u8 *mac) +{ + iowrite32((mac[0] << 8) | mac[1], etha->addr + MRMAC0); + iowrite32((mac[2] << 24) | (mac[3] << 16) | (mac[4] << 8) | mac[5], + etha->addr + MRMAC1); +} + +static int rswitch_etha_wait_link_verification(struct rswitch_etha *etha) +{ + iowrite32(MLVC_PLV, etha->addr + MLVC); + + return rswitch_reg_wait(etha->addr, MLVC, MLVC_PLV, 0); +} + +static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac) +{ + u32 val; + + rswitch_etha_write_mac_address(etha, mac); + + switch (etha->speed) { + case 100: + val = MPIC_LSC_100M; + break; + case 1000: + val = MPIC_LSC_1G; + break; + case 2500: + val = MPIC_LSC_2_5G; + break; + default: + return; + } + + iowrite32(MPIC_PIS_GMII | val, etha->addr + MPIC); +} + +static void rswitch_etha_enable_mii(struct rswitch_etha *etha) +{ + rswitch_modify(etha->addr, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, + MPIC_PSMCS(0x05) | MPIC_PSMHT(0x06)); + rswitch_modify(etha->addr, MPSM, 0, MPSM_MFF_C45); +} + +static int rswitch_etha_hw_init(struct rswitch_etha *etha, const u8 *mac) +{ + int err; + + err = rswitch_etha_change_mode(etha, EAMC_OPC_DISABLE); + if (err < 0) + return err; + err = rswitch_etha_change_mode(etha, EAMC_OPC_CONFIG); + if (err < 0) + return err; + + iowrite32(EAVCC_VEM_SC_TAG, etha->addr + EAVCC); + rswitch_rmac_setting(etha, mac); + rswitch_etha_enable_mii(etha); + + err = rswitch_etha_wait_link_verification(etha); + if (err < 0) + return err; + + err = rswitch_etha_change_mode(etha, EAMC_OPC_DISABLE); + if (err < 0) + return err; + + return rswitch_etha_change_mode(etha, EAMC_OPC_OPERATION); +} + +static int rswitch_etha_set_access(struct rswitch_etha *etha, bool read, + int phyad, int devad, int regad, int data) +{ + int pop = read ? MDIO_READ_C45 : MDIO_WRITE_C45; + u32 val; + int ret; + + if (devad == 0xffffffff) + return -ENODEV; + + writel(MMIS1_CLEAR_FLAGS, etha->addr + MMIS1); + + val = MPSM_PSME | MPSM_MFF_C45; + iowrite32((regad << 16) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM); + + ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS); + if (ret) + return ret; + + rswitch_modify(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS); + + if (read) { + writel((pop << 13) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM); + + ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS); + if (ret) + return ret; + + ret = (ioread32(etha->addr + MPSM) & MPSM_PRD_MASK) >> 16; + + rswitch_modify(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS); + } else { + iowrite32((data << 16) | (pop << 13) | (devad << 8) | (phyad << 3) | val, + etha->addr + MPSM); + + ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PWACS, MMIS1_PWACS); + } + + return ret; +} + +static int rswitch_etha_mii_read(struct mii_bus *bus, int addr, int regnum) +{ + struct rswitch_etha *etha = bus->priv; + int mode, devad, regad; + + mode = regnum & MII_ADDR_C45; + devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; + regad = regnum & MII_REGADDR_C45_MASK; + + /* Not support Clause 22 access method */ + if (!mode) + return -EOPNOTSUPP; + + return rswitch_etha_set_access(etha, true, addr, devad, regad, 0); +} + +static int rswitch_etha_mii_write(struct mii_bus *bus, int addr, int regnum, u16 val) +{ + struct rswitch_etha *etha = bus->priv; + int mode, devad, regad; + + mode = regnum & MII_ADDR_C45; + devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; + regad = regnum & MII_REGADDR_C45_MASK; + + /* Not support Clause 22 access method */ + if (!mode) + return -EOPNOTSUPP; + + return rswitch_etha_set_access(etha, false, addr, devad, regad, val); +} + +/* Call of_node_put(port) after done */ +static struct device_node *rswitch_get_port_node(struct rswitch_device *rdev) +{ + struct device_node *ports, *port; + int err = 0; + u32 index; + + ports = of_get_child_by_name(rdev->ndev->dev.parent->of_node, + "ethernet-ports"); + if (!ports) + return NULL; + + for_each_child_of_node(ports, port) { + err = of_property_read_u32(port, "reg", &index); + if (err < 0) { + port = NULL; + goto out; + } + if (index == rdev->etha->index) + break; + } + +out: + of_node_put(ports); + + return port; +} + +/* Call of_node_put(mdio) after done */ +static struct device_node *rswitch_get_mdio_node(struct rswitch_device *rdev) +{ + struct device_node *port, *mdio; + + port = rswitch_get_port_node(rdev); + if (!port) + return NULL; + + mdio = of_get_child_by_name(port, "mdio"); + of_node_put(port); + + return mdio; +} + +static int rswitch_etha_get_params(struct rswitch_device *rdev) +{ + struct device_node *port; + int err; + + port = rswitch_get_port_node(rdev); + if (!port) + return -ENODEV; + + err = of_get_phy_mode(port, &rdev->etha->phy_interface); + of_node_put(port); + + switch (rdev->etha->phy_interface) { + case PHY_INTERFACE_MODE_MII: + rdev->etha->speed = SPEED_100; + break; + case PHY_INTERFACE_MODE_SGMII: + rdev->etha->speed = SPEED_1000; + break; + case PHY_INTERFACE_MODE_USXGMII: + rdev->etha->speed = SPEED_2500; + break; + default: + err = -EINVAL; + break; + } + + return err; +} + +static int rswitch_mii_register(struct rswitch_device *rdev) +{ + struct device_node *mdio_np; + struct mii_bus *mii_bus; + int err; + + mii_bus = mdiobus_alloc(); + if (!mii_bus) + return -ENOMEM; + + mii_bus->name = "rswitch_mii"; + sprintf(mii_bus->id, "etha%d", rdev->etha->index); + mii_bus->priv = rdev->etha; + mii_bus->read = rswitch_etha_mii_read; + mii_bus->write = rswitch_etha_mii_write; + mii_bus->parent = &rdev->priv->pdev->dev; + + mdio_np = rswitch_get_mdio_node(rdev); + err = of_mdiobus_register(mii_bus, mdio_np); + if (err < 0) { + mdiobus_free(mii_bus); + goto out; + } + + rdev->etha->mii = mii_bus; + +out: + of_node_put(mdio_np); + + return err; +} + +static void rswitch_mii_unregister(struct rswitch_device *rdev) +{ + if (rdev->etha->mii) { + mdiobus_unregister(rdev->etha->mii); + mdiobus_free(rdev->etha->mii); + rdev->etha->mii = NULL; + } +} + +static void rswitch_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) +{ +} + +static void rswitch_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ +} + +static void rswitch_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int mode, + phy_interface_t interface, int speed, + int duplex, bool tx_pause, bool rx_pause) +{ + /* Current hardware cannot change speed at runtime */ +} + +static const struct phylink_mac_ops rswitch_phylink_ops = { + .mac_config = rswitch_mac_config, + .mac_link_down = rswitch_mac_link_down, + .mac_link_up = rswitch_mac_link_up, +}; + +static int rswitch_phylink_init(struct rswitch_device *rdev) +{ + struct device_node *port; + struct phylink *phylink; + int err; + + port = rswitch_get_port_node(rdev); + if (!port) + return -ENODEV; + + rdev->phylink_config.dev = &rdev->ndev->dev; + rdev->phylink_config.type = PHYLINK_NETDEV; + __set_bit(PHY_INTERFACE_MODE_SGMII, rdev->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_USXGMII, rdev->phylink_config.supported_interfaces); + rdev->phylink_config.mac_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD; + + phylink = phylink_create(&rdev->phylink_config, &port->fwnode, + rdev->etha->phy_interface, &rswitch_phylink_ops); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + goto out; + } + + rdev->phylink = phylink; + err = phylink_of_phy_connect(rdev->phylink, port, rdev->etha->phy_interface); +out: + of_node_put(port); + + return err; +} + +static void rswitch_phylink_deinit(struct rswitch_device *rdev) +{ + rtnl_lock(); + phylink_disconnect_phy(rdev->phylink); + rtnl_unlock(); + phylink_destroy(rdev->phylink); +} + +static int rswitch_serdes_set_params(struct rswitch_device *rdev) +{ + struct device_node *port = rswitch_get_port_node(rdev); + struct phy *serdes; + int err; + + serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); + of_node_put(port); + if (IS_ERR(serdes)) + return PTR_ERR(serdes); + + err = phy_set_mode_ext(serdes, PHY_MODE_ETHERNET, + rdev->etha->phy_interface); + if (err < 0) + return err; + + return phy_set_speed(serdes, rdev->etha->speed); +} + +static int rswitch_serdes_init(struct rswitch_device *rdev) +{ + struct device_node *port = rswitch_get_port_node(rdev); + struct phy *serdes; + + serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); + of_node_put(port); + if (IS_ERR(serdes)) + return PTR_ERR(serdes); + + return phy_init(serdes); +} + +static int rswitch_serdes_deinit(struct rswitch_device *rdev) +{ + struct device_node *port = rswitch_get_port_node(rdev); + struct phy *serdes; + + serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); + of_node_put(port); + if (IS_ERR(serdes)) + return PTR_ERR(serdes); + + return phy_exit(serdes); +} + +static int rswitch_ether_port_init_one(struct rswitch_device *rdev) +{ + int err; + + if (!rdev->etha->operated) { + err = rswitch_etha_hw_init(rdev->etha, rdev->ndev->dev_addr); + if (err < 0) + return err; + rdev->etha->operated = true; + } + + err = rswitch_mii_register(rdev); + if (err < 0) + return err; + + err = rswitch_phylink_init(rdev); + if (err < 0) + goto err_phylink_init; + + err = rswitch_serdes_set_params(rdev); + if (err < 0) + goto err_serdes_set_params; + + return 0; + +err_serdes_set_params: + rswitch_phylink_deinit(rdev); + +err_phylink_init: + rswitch_mii_unregister(rdev); + + return err; +} + +static void rswitch_ether_port_deinit_one(struct rswitch_device *rdev) +{ + rswitch_phylink_deinit(rdev); + rswitch_mii_unregister(rdev); +} + +static int rswitch_ether_port_init_all(struct rswitch_private *priv) +{ + int i, err; + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + err = rswitch_ether_port_init_one(priv->rdev[i]); + if (err) + goto err_init_one; + } + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + err = rswitch_serdes_init(priv->rdev[i]); + if (err) + goto err_serdes; + } + + return 0; + +err_serdes: + for (i--; i >= 0; i--) + rswitch_serdes_deinit(priv->rdev[i]); + i = RSWITCH_NUM_PORTS; + +err_init_one: + for (i--; i >= 0; i--) + rswitch_ether_port_deinit_one(priv->rdev[i]); + + return err; +} + +static void rswitch_ether_port_deinit_all(struct rswitch_private *priv) +{ + int i; + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_serdes_deinit(priv->rdev[i]); + rswitch_ether_port_deinit_one(priv->rdev[i]); + } +} + +static int rswitch_open(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + phylink_start(rdev->phylink); + + napi_enable(&rdev->napi); + netif_start_queue(ndev); + + rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true); + rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true); + + return 0; +}; + +static int rswitch_stop(struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + netif_tx_stop_all_queues(ndev); + + rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); + rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); + + phylink_stop(rdev->phylink); + napi_disable(&rdev->napi); + + return 0; +}; + +static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_gwca_queue *gq = rdev->tx_queue; + struct rswitch_ext_desc *desc; + int ret = NETDEV_TX_OK; + dma_addr_t dma_addr; + + if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) { + netif_stop_subqueue(ndev, 0); + return ret; + } + + if (skb_put_padto(skb, ETH_ZLEN)) + return ret; + + dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) { + dev_kfree_skb_any(skb); + return ret; + } + + gq->skbs[gq->cur] = skb; + desc = &gq->ring[gq->cur]; + rswitch_desc_set_dptr(&desc->desc, dma_addr); + desc->desc.info_ds = cpu_to_le16(skb->len); + + desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_FMT); + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + rdev->ts_tag++; + desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); + } + skb_tx_timestamp(skb); + + dma_wmb(); + + desc->desc.die_dt = DT_FSINGLE | DIE; + wmb(); /* gq->cur must be incremented after die_dt was set */ + + gq->cur = rswitch_next_queue_index(gq, true, 1); + rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32)); + + return ret; +} + +static struct net_device_stats *rswitch_get_stats(struct net_device *ndev) +{ + return &ndev->stats; +} + +static int rswitch_hwstamp_get(struct net_device *ndev, struct ifreq *req) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + struct rcar_gen4_ptp_private *ptp_priv; + struct hwtstamp_config config; + + ptp_priv = rdev->priv->ptp_priv; + + config.flags = 0; + config.tx_type = ptp_priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : + HWTSTAMP_TX_OFF; + switch (ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE) { + case RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT: + config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + break; + case RCAR_GEN4_RXTSTAMP_TYPE_ALL: + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + config.rx_filter = HWTSTAMP_FILTER_NONE; + break; + } + + return copy_to_user(req->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; +} + +static int rswitch_hwstamp_set(struct net_device *ndev, struct ifreq *req) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + u32 tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED; + struct hwtstamp_config config; + u32 tstamp_tx_ctrl; + + if (copy_from_user(&config, req->ifr_data, sizeof(config))) + return -EFAULT; + + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + tstamp_tx_ctrl = 0; + break; + case HWTSTAMP_TX_ON: + tstamp_tx_ctrl = RCAR_GEN4_TXTSTAMP_ENABLED; + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + tstamp_rx_ctrl = 0; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + tstamp_rx_ctrl |= RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + break; + default: + config.rx_filter = HWTSTAMP_FILTER_ALL; + tstamp_rx_ctrl |= RCAR_GEN4_RXTSTAMP_TYPE_ALL; + break; + } + + rdev->priv->ptp_priv->tstamp_tx_ctrl = tstamp_tx_ctrl; + rdev->priv->ptp_priv->tstamp_rx_ctrl = tstamp_rx_ctrl; + + return copy_to_user(req->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; +} + +static int rswitch_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + if (!netif_running(ndev)) + return -EINVAL; + + switch (cmd) { + case SIOCGHWTSTAMP: + return rswitch_hwstamp_get(ndev, req); + case SIOCSHWTSTAMP: + return rswitch_hwstamp_set(ndev, req); + default: + return phylink_mii_ioctl(rdev->phylink, req, cmd); + } +} + +static const struct net_device_ops rswitch_netdev_ops = { + .ndo_open = rswitch_open, + .ndo_stop = rswitch_stop, + .ndo_start_xmit = rswitch_start_xmit, + .ndo_get_stats = rswitch_get_stats, + .ndo_eth_ioctl = rswitch_eth_ioctl, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = eth_mac_addr, +}; + +static int rswitch_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info) +{ + struct rswitch_device *rdev = netdev_priv(ndev); + + info->phc_index = ptp_clock_index(rdev->priv->ptp_priv->clock); + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + +static const struct ethtool_ops rswitch_ethtool_ops = { + .get_ts_info = rswitch_get_ts_info, +}; + +static const struct of_device_id renesas_eth_sw_of_table[] = { + { .compatible = "renesas,r8a779f0-ether-switch", }, + { } +}; +MODULE_DEVICE_TABLE(of, renesas_eth_sw_of_table); + +static void rswitch_etha_init(struct rswitch_private *priv, int index) +{ + struct rswitch_etha *etha = &priv->etha[index]; + + memset(etha, 0, sizeof(*etha)); + etha->index = index; + etha->addr = priv->addr + RSWITCH_ETHA_OFFSET + index * RSWITCH_ETHA_SIZE; + etha->coma_addr = priv->addr; +} + +static int rswitch_device_alloc(struct rswitch_private *priv, int index) +{ + struct platform_device *pdev = priv->pdev; + struct rswitch_device *rdev; + struct net_device *ndev; + int err; + + if (index >= RSWITCH_NUM_PORTS) + return -EINVAL; + + ndev = alloc_etherdev_mqs(sizeof(struct rswitch_device), 1, 1); + if (!ndev) + return -ENOMEM; + + SET_NETDEV_DEV(ndev, &pdev->dev); + ether_setup(ndev); + + rdev = netdev_priv(ndev); + rdev->ndev = ndev; + rdev->priv = priv; + priv->rdev[index] = rdev; + rdev->port = index; + rdev->etha = &priv->etha[index]; + rdev->addr = priv->addr; + + ndev->base_addr = (unsigned long)rdev->addr; + snprintf(ndev->name, IFNAMSIZ, "tsn%d", index); + ndev->netdev_ops = &rswitch_netdev_ops; + ndev->ethtool_ops = &rswitch_ethtool_ops; + + netif_napi_add(ndev, &rdev->napi, rswitch_poll); + + err = of_get_ethdev_address(pdev->dev.of_node, ndev); + if (err) { + if (is_valid_ether_addr(rdev->etha->mac_addr)) + eth_hw_addr_set(ndev, rdev->etha->mac_addr); + else + eth_hw_addr_random(ndev); + } + + err = rswitch_etha_get_params(rdev); + if (err < 0) + goto out_get_params; + + if (rdev->priv->gwca.speed < rdev->etha->speed) + rdev->priv->gwca.speed = rdev->etha->speed; + + err = rswitch_rxdmac_alloc(ndev); + if (err < 0) + goto out_rxdmac; + + err = rswitch_txdmac_alloc(ndev); + if (err < 0) + goto out_txdmac; + + return 0; + +out_txdmac: + rswitch_rxdmac_free(ndev); + +out_rxdmac: +out_get_params: + netif_napi_del(&rdev->napi); + free_netdev(ndev); + + return err; +} + +static void rswitch_device_free(struct rswitch_private *priv, int index) +{ + struct rswitch_device *rdev = priv->rdev[index]; + struct net_device *ndev = rdev->ndev; + + rswitch_txdmac_free(ndev); + rswitch_rxdmac_free(ndev); + netif_napi_del(&rdev->napi); + free_netdev(ndev); +} + +static int rswitch_init(struct rswitch_private *priv) +{ + int i, err; + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) + rswitch_etha_init(priv, i); + + rswitch_clock_enable(priv); + for (i = 0; i < RSWITCH_NUM_PORTS; i++) + rswitch_etha_read_mac_address(&priv->etha[i]); + + rswitch_reset(priv); + + rswitch_clock_enable(priv); + rswitch_top_init(priv); + err = rswitch_bpool_config(priv); + if (err < 0) + return err; + + err = rswitch_gwca_desc_alloc(priv); + if (err < 0) + return -ENOMEM; + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + err = rswitch_device_alloc(priv, i); + if (err < 0) { + for (i--; i >= 0; i--) + rswitch_device_free(priv, i); + goto err_device_alloc; + } + } + + rswitch_fwd_init(priv); + + err = rcar_gen4_ptp_register(priv->ptp_priv, RCAR_GEN4_PTP_REG_LAYOUT_S4, + RCAR_GEN4_PTP_CLOCK_S4); + if (err < 0) + goto err_ptp_register; + + err = rswitch_gwca_request_irqs(priv); + if (err < 0) + goto err_gwca_request_irq; + + err = rswitch_gwca_hw_init(priv); + if (err < 0) + goto err_gwca_hw_init; + + err = rswitch_ether_port_init_all(priv); + if (err) + goto err_ether_port_init_all; + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + err = register_netdev(priv->rdev[i]->ndev); + if (err) { + for (i--; i >= 0; i--) + unregister_netdev(priv->rdev[i]->ndev); + goto err_register_netdev; + } + } + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) + netdev_info(priv->rdev[i]->ndev, "MAC address %pM\n", + priv->rdev[i]->ndev->dev_addr); + + return 0; + +err_register_netdev: + rswitch_ether_port_deinit_all(priv); + +err_ether_port_init_all: + rswitch_gwca_hw_deinit(priv); + +err_gwca_hw_init: +err_gwca_request_irq: + rcar_gen4_ptp_unregister(priv->ptp_priv); + +err_ptp_register: + for (i = 0; i < RSWITCH_NUM_PORTS; i++) + rswitch_device_free(priv, i); + +err_device_alloc: + rswitch_gwca_desc_free(priv); + + return err; +} + +static int renesas_eth_sw_probe(struct platform_device *pdev) +{ + struct rswitch_private *priv; + struct resource *res; + int ret; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "secure_base"); + if (!res) { + dev_err(&pdev->dev, "invalid resource\n"); + return -EINVAL; + } + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->ptp_priv = rcar_gen4_ptp_alloc(pdev); + if (!priv->ptp_priv) + return -ENOMEM; + + platform_set_drvdata(pdev, priv); + priv->pdev = pdev; + priv->addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->addr)) + return PTR_ERR(priv->addr); + + priv->ptp_priv->addr = priv->addr + RCAR_GEN4_GPTP_OFFSET_S4; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)); + if (ret < 0) { + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret < 0) + return ret; + } + + priv->gwca.index = AGENT_INDEX_GWCA; + priv->gwca.num_queues = min(RSWITCH_NUM_PORTS * NUM_QUEUES_PER_NDEV, + RSWITCH_MAX_NUM_QUEUES); + priv->gwca.queues = devm_kcalloc(&pdev->dev, priv->gwca.num_queues, + sizeof(*priv->gwca.queues), GFP_KERNEL); + if (!priv->gwca.queues) + return -ENOMEM; + + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + + ret = rswitch_init(priv); + + device_set_wakeup_capable(&pdev->dev, 1); + + return ret; +} + +static void rswitch_deinit(struct rswitch_private *priv) +{ + int i; + + rswitch_gwca_hw_deinit(priv); + rcar_gen4_ptp_unregister(priv->ptp_priv); + + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + struct rswitch_device *rdev = priv->rdev[i]; + + rswitch_serdes_deinit(rdev); + rswitch_ether_port_deinit_one(rdev); + unregister_netdev(rdev->ndev); + rswitch_device_free(priv, i); + } + + rswitch_gwca_desc_free(priv); + + rswitch_clock_disable(priv); +} + +static int renesas_eth_sw_remove(struct platform_device *pdev) +{ + struct rswitch_private *priv = platform_get_drvdata(pdev); + + rswitch_deinit(priv); + + pm_runtime_put(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver renesas_eth_sw_driver_platform = { + .probe = renesas_eth_sw_probe, + .remove = renesas_eth_sw_remove, + .driver = { + .name = "renesas_eth_sw", + .of_match_table = renesas_eth_sw_of_table, + } +}; +module_platform_driver(renesas_eth_sw_driver_platform); +MODULE_AUTHOR("Yoshihiro Shimoda"); +MODULE_DESCRIPTION("Renesas Ethernet Switch device driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h new file mode 100644 index 000000000000..edbdd1b98d3d --- /dev/null +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -0,0 +1,973 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Renesas Ethernet Switch device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#ifndef __RSWITCH_H__ +#define __RSWITCH_H__ + +#include <linux/platform_device.h> +#include "rcar_gen4_ptp.h" + +#define RSWITCH_MAX_NUM_QUEUES 128 + +#define RSWITCH_NUM_PORTS 3 + +#define TX_RING_SIZE 1024 +#define RX_RING_SIZE 1024 + +#define PKT_BUF_SZ 1584 +#define RSWITCH_ALIGN 128 +#define RSWITCH_MAX_CTAG_PCP 7 + +#define RSWITCH_TIMEOUT_US 100000 + +#define RSWITCH_TOP_OFFSET 0x00008000 +#define RSWITCH_COMA_OFFSET 0x00009000 +#define RSWITCH_ETHA_OFFSET 0x0000a000 /* with RMAC */ +#define RSWITCH_ETHA_SIZE 0x00002000 /* with RMAC */ +#define RSWITCH_GWCA0_OFFSET 0x00010000 +#define RSWITCH_GWCA1_OFFSET 0x00012000 + +/* TODO: hardcoded ETHA/GWCA settings for now */ +#define GWCA_IRQ_RESOURCE_NAME "gwca0_rxtx%d" +#define GWCA_IRQ_NAME "rswitch: gwca0_rxtx%d" +#define GWCA_NUM_IRQS 8 +#define GWCA_INDEX 0 +#define AGENT_INDEX_GWCA 3 +#define GWRO RSWITCH_GWCA0_OFFSET + +#define FWRO 0 +#define TPRO RSWITCH_TOP_OFFSET +#define CARO RSWITCH_COMA_OFFSET +#define TARO 0 +#define RMRO 0x1000 +enum rswitch_reg { + FWGC = FWRO + 0x0000, + FWTTC0 = FWRO + 0x0010, + FWTTC1 = FWRO + 0x0014, + FWLBMC = FWRO + 0x0018, + FWCEPTC = FWRO + 0x0020, + FWCEPRC0 = FWRO + 0x0024, + FWCEPRC1 = FWRO + 0x0028, + FWCEPRC2 = FWRO + 0x002c, + FWCLPTC = FWRO + 0x0030, + FWCLPRC = FWRO + 0x0034, + FWCMPTC = FWRO + 0x0040, + FWEMPTC = FWRO + 0x0044, + FWSDMPTC = FWRO + 0x0050, + FWSDMPVC = FWRO + 0x0054, + FWLBWMC0 = FWRO + 0x0080, + FWPC00 = FWRO + 0x0100, + FWPC10 = FWRO + 0x0104, + FWPC20 = FWRO + 0x0108, + FWCTGC00 = FWRO + 0x0400, + FWCTGC10 = FWRO + 0x0404, + FWCTTC00 = FWRO + 0x0408, + FWCTTC10 = FWRO + 0x040c, + FWCTTC200 = FWRO + 0x0410, + FWCTSC00 = FWRO + 0x0420, + FWCTSC10 = FWRO + 0x0424, + FWCTSC20 = FWRO + 0x0428, + FWCTSC30 = FWRO + 0x042c, + FWCTSC40 = FWRO + 0x0430, + FWTWBFC0 = FWRO + 0x1000, + FWTWBFVC0 = FWRO + 0x1004, + FWTHBFC0 = FWRO + 0x1400, + FWTHBFV0C0 = FWRO + 0x1404, + FWTHBFV1C0 = FWRO + 0x1408, + FWFOBFC0 = FWRO + 0x1800, + FWFOBFV0C0 = FWRO + 0x1804, + FWFOBFV1C0 = FWRO + 0x1808, + FWRFC0 = FWRO + 0x1c00, + FWRFVC0 = FWRO + 0x1c04, + FWCFC0 = FWRO + 0x2000, + FWCFMC00 = FWRO + 0x2004, + FWIP4SC = FWRO + 0x4008, + FWIP6SC = FWRO + 0x4018, + FWIP6OC = FWRO + 0x401c, + FWL2SC = FWRO + 0x4020, + FWSFHEC = FWRO + 0x4030, + FWSHCR0 = FWRO + 0x4040, + FWSHCR1 = FWRO + 0x4044, + FWSHCR2 = FWRO + 0x4048, + FWSHCR3 = FWRO + 0x404c, + FWSHCR4 = FWRO + 0x4050, + FWSHCR5 = FWRO + 0x4054, + FWSHCR6 = FWRO + 0x4058, + FWSHCR7 = FWRO + 0x405c, + FWSHCR8 = FWRO + 0x4060, + FWSHCR9 = FWRO + 0x4064, + FWSHCR10 = FWRO + 0x4068, + FWSHCR11 = FWRO + 0x406c, + FWSHCR12 = FWRO + 0x4070, + FWSHCR13 = FWRO + 0x4074, + FWSHCRR = FWRO + 0x4078, + FWLTHHEC = FWRO + 0x4090, + FWLTHHC = FWRO + 0x4094, + FWLTHTL0 = FWRO + 0x40a0, + FWLTHTL1 = FWRO + 0x40a4, + FWLTHTL2 = FWRO + 0x40a8, + FWLTHTL3 = FWRO + 0x40ac, + FWLTHTL4 = FWRO + 0x40b0, + FWLTHTL5 = FWRO + 0x40b4, + FWLTHTL6 = FWRO + 0x40b8, + FWLTHTL7 = FWRO + 0x40bc, + FWLTHTL80 = FWRO + 0x40c0, + FWLTHTL9 = FWRO + 0x40d0, + FWLTHTLR = FWRO + 0x40d4, + FWLTHTIM = FWRO + 0x40e0, + FWLTHTEM = FWRO + 0x40e4, + FWLTHTS0 = FWRO + 0x4100, + FWLTHTS1 = FWRO + 0x4104, + FWLTHTS2 = FWRO + 0x4108, + FWLTHTS3 = FWRO + 0x410c, + FWLTHTS4 = FWRO + 0x4110, + FWLTHTSR0 = FWRO + 0x4120, + FWLTHTSR1 = FWRO + 0x4124, + FWLTHTSR2 = FWRO + 0x4128, + FWLTHTSR3 = FWRO + 0x412c, + FWLTHTSR40 = FWRO + 0x4130, + FWLTHTSR5 = FWRO + 0x4140, + FWLTHTR = FWRO + 0x4150, + FWLTHTRR0 = FWRO + 0x4154, + FWLTHTRR1 = FWRO + 0x4158, + FWLTHTRR2 = FWRO + 0x415c, + FWLTHTRR3 = FWRO + 0x4160, + FWLTHTRR4 = FWRO + 0x4164, + FWLTHTRR5 = FWRO + 0x4168, + FWLTHTRR6 = FWRO + 0x416c, + FWLTHTRR7 = FWRO + 0x4170, + FWLTHTRR8 = FWRO + 0x4174, + FWLTHTRR9 = FWRO + 0x4180, + FWLTHTRR10 = FWRO + 0x4190, + FWIPHEC = FWRO + 0x4214, + FWIPHC = FWRO + 0x4218, + FWIPTL0 = FWRO + 0x4220, + FWIPTL1 = FWRO + 0x4224, + FWIPTL2 = FWRO + 0x4228, + FWIPTL3 = FWRO + 0x422c, + FWIPTL4 = FWRO + 0x4230, + FWIPTL5 = FWRO + 0x4234, + FWIPTL6 = FWRO + 0x4238, + FWIPTL7 = FWRO + 0x4240, + FWIPTL8 = FWRO + 0x4250, + FWIPTLR = FWRO + 0x4254, + FWIPTIM = FWRO + 0x4260, + FWIPTEM = FWRO + 0x4264, + FWIPTS0 = FWRO + 0x4270, + FWIPTS1 = FWRO + 0x4274, + FWIPTS2 = FWRO + 0x4278, + FWIPTS3 = FWRO + 0x427c, + FWIPTS4 = FWRO + 0x4280, + FWIPTSR0 = FWRO + 0x4284, + FWIPTSR1 = FWRO + 0x4288, + FWIPTSR2 = FWRO + 0x428c, + FWIPTSR3 = FWRO + 0x4290, + FWIPTSR4 = FWRO + 0x42a0, + FWIPTR = FWRO + 0x42b0, + FWIPTRR0 = FWRO + 0x42b4, + FWIPTRR1 = FWRO + 0x42b8, + FWIPTRR2 = FWRO + 0x42bc, + FWIPTRR3 = FWRO + 0x42c0, + FWIPTRR4 = FWRO + 0x42c4, + FWIPTRR5 = FWRO + 0x42c8, + FWIPTRR6 = FWRO + 0x42cc, + FWIPTRR7 = FWRO + 0x42d0, + FWIPTRR8 = FWRO + 0x42e0, + FWIPTRR9 = FWRO + 0x42f0, + FWIPHLEC = FWRO + 0x4300, + FWIPAGUSPC = FWRO + 0x4500, + FWIPAGC = FWRO + 0x4504, + FWIPAGM0 = FWRO + 0x4510, + FWIPAGM1 = FWRO + 0x4514, + FWIPAGM2 = FWRO + 0x4518, + FWIPAGM3 = FWRO + 0x451c, + FWIPAGM4 = FWRO + 0x4520, + FWMACHEC = FWRO + 0x4620, + FWMACHC = FWRO + 0x4624, + FWMACTL0 = FWRO + 0x4630, + FWMACTL1 = FWRO + 0x4634, + FWMACTL2 = FWRO + 0x4638, + FWMACTL3 = FWRO + 0x463c, + FWMACTL4 = FWRO + 0x4640, + FWMACTL5 = FWRO + 0x4650, + FWMACTLR = FWRO + 0x4654, + FWMACTIM = FWRO + 0x4660, + FWMACTEM = FWRO + 0x4664, + FWMACTS0 = FWRO + 0x4670, + FWMACTS1 = FWRO + 0x4674, + FWMACTSR0 = FWRO + 0x4678, + FWMACTSR1 = FWRO + 0x467c, + FWMACTSR2 = FWRO + 0x4680, + FWMACTSR3 = FWRO + 0x4690, + FWMACTR = FWRO + 0x46a0, + FWMACTRR0 = FWRO + 0x46a4, + FWMACTRR1 = FWRO + 0x46a8, + FWMACTRR2 = FWRO + 0x46ac, + FWMACTRR3 = FWRO + 0x46b0, + FWMACTRR4 = FWRO + 0x46b4, + FWMACTRR5 = FWRO + 0x46c0, + FWMACTRR6 = FWRO + 0x46d0, + FWMACHLEC = FWRO + 0x4700, + FWMACAGUSPC = FWRO + 0x4880, + FWMACAGC = FWRO + 0x4884, + FWMACAGM0 = FWRO + 0x4888, + FWMACAGM1 = FWRO + 0x488c, + FWVLANTEC = FWRO + 0x4900, + FWVLANTL0 = FWRO + 0x4910, + FWVLANTL1 = FWRO + 0x4914, + FWVLANTL2 = FWRO + 0x4918, + FWVLANTL3 = FWRO + 0x4920, + FWVLANTL4 = FWRO + 0x4930, + FWVLANTLR = FWRO + 0x4934, + FWVLANTIM = FWRO + 0x4940, + FWVLANTEM = FWRO + 0x4944, + FWVLANTS = FWRO + 0x4950, + FWVLANTSR0 = FWRO + 0x4954, + FWVLANTSR1 = FWRO + 0x4958, + FWVLANTSR2 = FWRO + 0x4960, + FWVLANTSR3 = FWRO + 0x4970, + FWPBFC0 = FWRO + 0x4a00, + FWPBFCSDC00 = FWRO + 0x4a04, + FWL23URL0 = FWRO + 0x4e00, + FWL23URL1 = FWRO + 0x4e04, + FWL23URL2 = FWRO + 0x4e08, + FWL23URL3 = FWRO + 0x4e0c, + FWL23URLR = FWRO + 0x4e10, + FWL23UTIM = FWRO + 0x4e20, + FWL23URR = FWRO + 0x4e30, + FWL23URRR0 = FWRO + 0x4e34, + FWL23URRR1 = FWRO + 0x4e38, + FWL23URRR2 = FWRO + 0x4e3c, + FWL23URRR3 = FWRO + 0x4e40, + FWL23URMC0 = FWRO + 0x4f00, + FWPMFGC0 = FWRO + 0x5000, + FWPGFC0 = FWRO + 0x5100, + FWPGFIGSC0 = FWRO + 0x5104, + FWPGFENC0 = FWRO + 0x5108, + FWPGFENM0 = FWRO + 0x510c, + FWPGFCSTC00 = FWRO + 0x5110, + FWPGFCSTC10 = FWRO + 0x5114, + FWPGFCSTM00 = FWRO + 0x5118, + FWPGFCSTM10 = FWRO + 0x511c, + FWPGFCTC0 = FWRO + 0x5120, + FWPGFCTM0 = FWRO + 0x5124, + FWPGFHCC0 = FWRO + 0x5128, + FWPGFSM0 = FWRO + 0x512c, + FWPGFGC0 = FWRO + 0x5130, + FWPGFGL0 = FWRO + 0x5500, + FWPGFGL1 = FWRO + 0x5504, + FWPGFGLR = FWRO + 0x5518, + FWPGFGR = FWRO + 0x5510, + FWPGFGRR0 = FWRO + 0x5514, + FWPGFGRR1 = FWRO + 0x5518, + FWPGFRIM = FWRO + 0x5520, + FWPMTRFC0 = FWRO + 0x5600, + FWPMTRCBSC0 = FWRO + 0x5604, + FWPMTRC0RC0 = FWRO + 0x5608, + FWPMTREBSC0 = FWRO + 0x560c, + FWPMTREIRC0 = FWRO + 0x5610, + FWPMTRFM0 = FWRO + 0x5614, + FWFTL0 = FWRO + 0x6000, + FWFTL1 = FWRO + 0x6004, + FWFTLR = FWRO + 0x6008, + FWFTOC = FWRO + 0x6010, + FWFTOPC = FWRO + 0x6014, + FWFTIM = FWRO + 0x6020, + FWFTR = FWRO + 0x6030, + FWFTRR0 = FWRO + 0x6034, + FWFTRR1 = FWRO + 0x6038, + FWFTRR2 = FWRO + 0x603c, + FWSEQNGC0 = FWRO + 0x6100, + FWSEQNGM0 = FWRO + 0x6104, + FWSEQNRC = FWRO + 0x6200, + FWCTFDCN0 = FWRO + 0x6300, + FWLTHFDCN0 = FWRO + 0x6304, + FWIPFDCN0 = FWRO + 0x6308, + FWLTWFDCN0 = FWRO + 0x630c, + FWPBFDCN0 = FWRO + 0x6310, + FWMHLCN0 = FWRO + 0x6314, + FWIHLCN0 = FWRO + 0x6318, + FWICRDCN0 = FWRO + 0x6500, + FWWMRDCN0 = FWRO + 0x6504, + FWCTRDCN0 = FWRO + 0x6508, + FWLTHRDCN0 = FWRO + 0x650c, + FWIPRDCN0 = FWRO + 0x6510, + FWLTWRDCN0 = FWRO + 0x6514, + FWPBRDCN0 = FWRO + 0x6518, + FWPMFDCN0 = FWRO + 0x6700, + FWPGFDCN0 = FWRO + 0x6780, + FWPMGDCN0 = FWRO + 0x6800, + FWPMYDCN0 = FWRO + 0x6804, + FWPMRDCN0 = FWRO + 0x6808, + FWFRPPCN0 = FWRO + 0x6a00, + FWFRDPCN0 = FWRO + 0x6a04, + FWEIS00 = FWRO + 0x7900, + FWEIE00 = FWRO + 0x7904, + FWEID00 = FWRO + 0x7908, + FWEIS1 = FWRO + 0x7a00, + FWEIE1 = FWRO + 0x7a04, + FWEID1 = FWRO + 0x7a08, + FWEIS2 = FWRO + 0x7a10, + FWEIE2 = FWRO + 0x7a14, + FWEID2 = FWRO + 0x7a18, + FWEIS3 = FWRO + 0x7a20, + FWEIE3 = FWRO + 0x7a24, + FWEID3 = FWRO + 0x7a28, + FWEIS4 = FWRO + 0x7a30, + FWEIE4 = FWRO + 0x7a34, + FWEID4 = FWRO + 0x7a38, + FWEIS5 = FWRO + 0x7a40, + FWEIE5 = FWRO + 0x7a44, + FWEID5 = FWRO + 0x7a48, + FWEIS60 = FWRO + 0x7a50, + FWEIE60 = FWRO + 0x7a54, + FWEID60 = FWRO + 0x7a58, + FWEIS61 = FWRO + 0x7a60, + FWEIE61 = FWRO + 0x7a64, + FWEID61 = FWRO + 0x7a68, + FWEIS62 = FWRO + 0x7a70, + FWEIE62 = FWRO + 0x7a74, + FWEID62 = FWRO + 0x7a78, + FWEIS63 = FWRO + 0x7a80, + FWEIE63 = FWRO + 0x7a84, + FWEID63 = FWRO + 0x7a88, + FWEIS70 = FWRO + 0x7a90, + FWEIE70 = FWRO + 0x7A94, + FWEID70 = FWRO + 0x7a98, + FWEIS71 = FWRO + 0x7aa0, + FWEIE71 = FWRO + 0x7aa4, + FWEID71 = FWRO + 0x7aa8, + FWEIS72 = FWRO + 0x7ab0, + FWEIE72 = FWRO + 0x7ab4, + FWEID72 = FWRO + 0x7ab8, + FWEIS73 = FWRO + 0x7ac0, + FWEIE73 = FWRO + 0x7ac4, + FWEID73 = FWRO + 0x7ac8, + FWEIS80 = FWRO + 0x7ad0, + FWEIE80 = FWRO + 0x7ad4, + FWEID80 = FWRO + 0x7ad8, + FWEIS81 = FWRO + 0x7ae0, + FWEIE81 = FWRO + 0x7ae4, + FWEID81 = FWRO + 0x7ae8, + FWEIS82 = FWRO + 0x7af0, + FWEIE82 = FWRO + 0x7af4, + FWEID82 = FWRO + 0x7af8, + FWEIS83 = FWRO + 0x7b00, + FWEIE83 = FWRO + 0x7b04, + FWEID83 = FWRO + 0x7b08, + FWMIS0 = FWRO + 0x7c00, + FWMIE0 = FWRO + 0x7c04, + FWMID0 = FWRO + 0x7c08, + FWSCR0 = FWRO + 0x7d00, + FWSCR1 = FWRO + 0x7d04, + FWSCR2 = FWRO + 0x7d08, + FWSCR3 = FWRO + 0x7d0c, + FWSCR4 = FWRO + 0x7d10, + FWSCR5 = FWRO + 0x7d14, + FWSCR6 = FWRO + 0x7d18, + FWSCR7 = FWRO + 0x7d1c, + FWSCR8 = FWRO + 0x7d20, + FWSCR9 = FWRO + 0x7d24, + FWSCR10 = FWRO + 0x7d28, + FWSCR11 = FWRO + 0x7d2c, + FWSCR12 = FWRO + 0x7d30, + FWSCR13 = FWRO + 0x7d34, + FWSCR14 = FWRO + 0x7d38, + FWSCR15 = FWRO + 0x7d3c, + FWSCR16 = FWRO + 0x7d40, + FWSCR17 = FWRO + 0x7d44, + FWSCR18 = FWRO + 0x7d48, + FWSCR19 = FWRO + 0x7d4c, + FWSCR20 = FWRO + 0x7d50, + FWSCR21 = FWRO + 0x7d54, + FWSCR22 = FWRO + 0x7d58, + FWSCR23 = FWRO + 0x7d5c, + FWSCR24 = FWRO + 0x7d60, + FWSCR25 = FWRO + 0x7d64, + FWSCR26 = FWRO + 0x7d68, + FWSCR27 = FWRO + 0x7d6c, + FWSCR28 = FWRO + 0x7d70, + FWSCR29 = FWRO + 0x7d74, + FWSCR30 = FWRO + 0x7d78, + FWSCR31 = FWRO + 0x7d7c, + FWSCR32 = FWRO + 0x7d80, + FWSCR33 = FWRO + 0x7d84, + FWSCR34 = FWRO + 0x7d88, + FWSCR35 = FWRO + 0x7d8c, + FWSCR36 = FWRO + 0x7d90, + FWSCR37 = FWRO + 0x7d94, + FWSCR38 = FWRO + 0x7d98, + FWSCR39 = FWRO + 0x7d9c, + FWSCR40 = FWRO + 0x7da0, + FWSCR41 = FWRO + 0x7da4, + FWSCR42 = FWRO + 0x7da8, + FWSCR43 = FWRO + 0x7dac, + FWSCR44 = FWRO + 0x7db0, + FWSCR45 = FWRO + 0x7db4, + FWSCR46 = FWRO + 0x7db8, + + TPEMIMC0 = TPRO + 0x0000, + TPEMIMC1 = TPRO + 0x0004, + TPEMIMC2 = TPRO + 0x0008, + TPEMIMC3 = TPRO + 0x000c, + TPEMIMC4 = TPRO + 0x0010, + TPEMIMC5 = TPRO + 0x0014, + TPEMIMC60 = TPRO + 0x0080, + TPEMIMC70 = TPRO + 0x0100, + TSIM = TPRO + 0x0700, + TFIM = TPRO + 0x0704, + TCIM = TPRO + 0x0708, + TGIM0 = TPRO + 0x0710, + TGIM1 = TPRO + 0x0714, + TEIM0 = TPRO + 0x0720, + TEIM1 = TPRO + 0x0724, + TEIM2 = TPRO + 0x0728, + + RIPV = CARO + 0x0000, + RRC = CARO + 0x0004, + RCEC = CARO + 0x0008, + RCDC = CARO + 0x000c, + RSSIS = CARO + 0x0010, + RSSIE = CARO + 0x0014, + RSSID = CARO + 0x0018, + CABPIBWMC = CARO + 0x0020, + CABPWMLC = CARO + 0x0040, + CABPPFLC0 = CARO + 0x0050, + CABPPWMLC0 = CARO + 0x0060, + CABPPPFLC00 = CARO + 0x00a0, + CABPULC = CARO + 0x0100, + CABPIRM = CARO + 0x0140, + CABPPCM = CARO + 0x0144, + CABPLCM = CARO + 0x0148, + CABPCPM = CARO + 0x0180, + CABPMCPM = CARO + 0x0200, + CARDNM = CARO + 0x0280, + CARDMNM = CARO + 0x0284, + CARDCN = CARO + 0x0290, + CAEIS0 = CARO + 0x0300, + CAEIE0 = CARO + 0x0304, + CAEID0 = CARO + 0x0308, + CAEIS1 = CARO + 0x0310, + CAEIE1 = CARO + 0x0314, + CAEID1 = CARO + 0x0318, + CAMIS0 = CARO + 0x0340, + CAMIE0 = CARO + 0x0344, + CAMID0 = CARO + 0x0348, + CAMIS1 = CARO + 0x0350, + CAMIE1 = CARO + 0x0354, + CAMID1 = CARO + 0x0358, + CASCR = CARO + 0x0380, + + EAMC = TARO + 0x0000, + EAMS = TARO + 0x0004, + EAIRC = TARO + 0x0010, + EATDQSC = TARO + 0x0014, + EATDQC = TARO + 0x0018, + EATDQAC = TARO + 0x001c, + EATPEC = TARO + 0x0020, + EATMFSC0 = TARO + 0x0040, + EATDQDC0 = TARO + 0x0060, + EATDQM0 = TARO + 0x0080, + EATDQMLM0 = TARO + 0x00a0, + EACTQC = TARO + 0x0100, + EACTDQDC = TARO + 0x0104, + EACTDQM = TARO + 0x0108, + EACTDQMLM = TARO + 0x010c, + EAVCC = TARO + 0x0130, + EAVTC = TARO + 0x0134, + EATTFC = TARO + 0x0138, + EACAEC = TARO + 0x0200, + EACC = TARO + 0x0204, + EACAIVC0 = TARO + 0x0220, + EACAULC0 = TARO + 0x0240, + EACOEM = TARO + 0x0260, + EACOIVM0 = TARO + 0x0280, + EACOULM0 = TARO + 0x02a0, + EACGSM = TARO + 0x02c0, + EATASC = TARO + 0x0300, + EATASENC0 = TARO + 0x0320, + EATASCTENC = TARO + 0x0340, + EATASENM0 = TARO + 0x0360, + EATASCTENM = TARO + 0x0380, + EATASCSTC0 = TARO + 0x03a0, + EATASCSTC1 = TARO + 0x03a4, + EATASCSTM0 = TARO + 0x03a8, + EATASCSTM1 = TARO + 0x03ac, + EATASCTC = TARO + 0x03b0, + EATASCTM = TARO + 0x03b4, + EATASGL0 = TARO + 0x03c0, + EATASGL1 = TARO + 0x03c4, + EATASGLR = TARO + 0x03c8, + EATASGR = TARO + 0x03d0, + EATASGRR = TARO + 0x03d4, + EATASHCC = TARO + 0x03e0, + EATASRIRM = TARO + 0x03e4, + EATASSM = TARO + 0x03e8, + EAUSMFSECN = TARO + 0x0400, + EATFECN = TARO + 0x0404, + EAFSECN = TARO + 0x0408, + EADQOECN = TARO + 0x040c, + EADQSECN = TARO + 0x0410, + EACKSECN = TARO + 0x0414, + EAEIS0 = TARO + 0x0500, + EAEIE0 = TARO + 0x0504, + EAEID0 = TARO + 0x0508, + EAEIS1 = TARO + 0x0510, + EAEIE1 = TARO + 0x0514, + EAEID1 = TARO + 0x0518, + EAEIS2 = TARO + 0x0520, + EAEIE2 = TARO + 0x0524, + EAEID2 = TARO + 0x0528, + EASCR = TARO + 0x0580, + + MPSM = RMRO + 0x0000, + MPIC = RMRO + 0x0004, + MPIM = RMRO + 0x0008, + MIOC = RMRO + 0x0010, + MIOM = RMRO + 0x0014, + MXMS = RMRO + 0x0018, + MTFFC = RMRO + 0x0020, + MTPFC = RMRO + 0x0024, + MTPFC2 = RMRO + 0x0028, + MTPFC30 = RMRO + 0x0030, + MTATC0 = RMRO + 0x0050, + MTIM = RMRO + 0x0060, + MRGC = RMRO + 0x0080, + MRMAC0 = RMRO + 0x0084, + MRMAC1 = RMRO + 0x0088, + MRAFC = RMRO + 0x008c, + MRSCE = RMRO + 0x0090, + MRSCP = RMRO + 0x0094, + MRSCC = RMRO + 0x0098, + MRFSCE = RMRO + 0x009c, + MRFSCP = RMRO + 0x00a0, + MTRC = RMRO + 0x00a4, + MRIM = RMRO + 0x00a8, + MRPFM = RMRO + 0x00ac, + MPFC0 = RMRO + 0x0100, + MLVC = RMRO + 0x0180, + MEEEC = RMRO + 0x0184, + MLBC = RMRO + 0x0188, + MXGMIIC = RMRO + 0x0190, + MPCH = RMRO + 0x0194, + MANC = RMRO + 0x0198, + MANM = RMRO + 0x019c, + MPLCA1 = RMRO + 0x01a0, + MPLCA2 = RMRO + 0x01a4, + MPLCA3 = RMRO + 0x01a8, + MPLCA4 = RMRO + 0x01ac, + MPLCAM = RMRO + 0x01b0, + MHDC1 = RMRO + 0x01c0, + MHDC2 = RMRO + 0x01c4, + MEIS = RMRO + 0x0200, + MEIE = RMRO + 0x0204, + MEID = RMRO + 0x0208, + MMIS0 = RMRO + 0x0210, + MMIE0 = RMRO + 0x0214, + MMID0 = RMRO + 0x0218, + MMIS1 = RMRO + 0x0220, + MMIE1 = RMRO + 0x0224, + MMID1 = RMRO + 0x0228, + MMIS2 = RMRO + 0x0230, + MMIE2 = RMRO + 0x0234, + MMID2 = RMRO + 0x0238, + MMPFTCT = RMRO + 0x0300, + MAPFTCT = RMRO + 0x0304, + MPFRCT = RMRO + 0x0308, + MFCICT = RMRO + 0x030c, + MEEECT = RMRO + 0x0310, + MMPCFTCT0 = RMRO + 0x0320, + MAPCFTCT0 = RMRO + 0x0330, + MPCFRCT0 = RMRO + 0x0340, + MHDCC = RMRO + 0x0350, + MROVFC = RMRO + 0x0354, + MRHCRCEC = RMRO + 0x0358, + MRXBCE = RMRO + 0x0400, + MRXBCP = RMRO + 0x0404, + MRGFCE = RMRO + 0x0408, + MRGFCP = RMRO + 0x040c, + MRBFC = RMRO + 0x0410, + MRMFC = RMRO + 0x0414, + MRUFC = RMRO + 0x0418, + MRPEFC = RMRO + 0x041c, + MRNEFC = RMRO + 0x0420, + MRFMEFC = RMRO + 0x0424, + MRFFMEFC = RMRO + 0x0428, + MRCFCEFC = RMRO + 0x042c, + MRFCEFC = RMRO + 0x0430, + MRRCFEFC = RMRO + 0x0434, + MRUEFC = RMRO + 0x043c, + MROEFC = RMRO + 0x0440, + MRBOEC = RMRO + 0x0444, + MTXBCE = RMRO + 0x0500, + MTXBCP = RMRO + 0x0504, + MTGFCE = RMRO + 0x0508, + MTGFCP = RMRO + 0x050c, + MTBFC = RMRO + 0x0510, + MTMFC = RMRO + 0x0514, + MTUFC = RMRO + 0x0518, + MTEFC = RMRO + 0x051c, + + GWMC = GWRO + 0x0000, + GWMS = GWRO + 0x0004, + GWIRC = GWRO + 0x0010, + GWRDQSC = GWRO + 0x0014, + GWRDQC = GWRO + 0x0018, + GWRDQAC = GWRO + 0x001c, + GWRGC = GWRO + 0x0020, + GWRMFSC0 = GWRO + 0x0040, + GWRDQDC0 = GWRO + 0x0060, + GWRDQM0 = GWRO + 0x0080, + GWRDQMLM0 = GWRO + 0x00a0, + GWMTIRM = GWRO + 0x0100, + GWMSTLS = GWRO + 0x0104, + GWMSTLR = GWRO + 0x0108, + GWMSTSS = GWRO + 0x010c, + GWMSTSR = GWRO + 0x0110, + GWMAC0 = GWRO + 0x0120, + GWMAC1 = GWRO + 0x0124, + GWVCC = GWRO + 0x0130, + GWVTC = GWRO + 0x0134, + GWTTFC = GWRO + 0x0138, + GWTDCAC00 = GWRO + 0x0140, + GWTDCAC10 = GWRO + 0x0144, + GWTSDCC0 = GWRO + 0x0160, + GWTNM = GWRO + 0x0180, + GWTMNM = GWRO + 0x0184, + GWAC = GWRO + 0x0190, + GWDCBAC0 = GWRO + 0x0194, + GWDCBAC1 = GWRO + 0x0198, + GWIICBSC = GWRO + 0x019c, + GWMDNC = GWRO + 0x01a0, + GWTRC0 = GWRO + 0x0200, + GWTPC0 = GWRO + 0x0300, + GWARIRM = GWRO + 0x0380, + GWDCC0 = GWRO + 0x0400, + GWAARSS = GWRO + 0x0800, + GWAARSR0 = GWRO + 0x0804, + GWAARSR1 = GWRO + 0x0808, + GWIDAUAS0 = GWRO + 0x0840, + GWIDASM0 = GWRO + 0x0880, + GWIDASAM00 = GWRO + 0x0900, + GWIDASAM10 = GWRO + 0x0904, + GWIDACAM00 = GWRO + 0x0980, + GWIDACAM10 = GWRO + 0x0984, + GWGRLC = GWRO + 0x0a00, + GWGRLULC = GWRO + 0x0a04, + GWRLIVC0 = GWRO + 0x0a80, + GWRLULC0 = GWRO + 0x0a84, + GWIDPC = GWRO + 0x0b00, + GWIDC0 = GWRO + 0x0c00, + GWDIS0 = GWRO + 0x1100, + GWDIE0 = GWRO + 0x1104, + GWDID0 = GWRO + 0x1108, + GWTSDIS = GWRO + 0x1180, + GWTSDIE = GWRO + 0x1184, + GWTSDID = GWRO + 0x1188, + GWEIS0 = GWRO + 0x1190, + GWEIE0 = GWRO + 0x1194, + GWEID0 = GWRO + 0x1198, + GWEIS1 = GWRO + 0x11a0, + GWEIE1 = GWRO + 0x11a4, + GWEID1 = GWRO + 0x11a8, + GWEIS20 = GWRO + 0x1200, + GWEIE20 = GWRO + 0x1204, + GWEID20 = GWRO + 0x1208, + GWEIS3 = GWRO + 0x1280, + GWEIE3 = GWRO + 0x1284, + GWEID3 = GWRO + 0x1288, + GWEIS4 = GWRO + 0x1290, + GWEIE4 = GWRO + 0x1294, + GWEID4 = GWRO + 0x1298, + GWEIS5 = GWRO + 0x12a0, + GWEIE5 = GWRO + 0x12a4, + GWEID5 = GWRO + 0x12a8, + GWSCR0 = GWRO + 0x1800, + GWSCR1 = GWRO + 0x1900, +}; + +/* ETHA/RMAC */ +enum rswitch_etha_mode { + EAMC_OPC_RESET, + EAMC_OPC_DISABLE, + EAMC_OPC_CONFIG, + EAMC_OPC_OPERATION, +}; + +#define EAMS_OPS_MASK EAMC_OPC_OPERATION + +#define EAVCC_VEM_SC_TAG (0x3 << 16) + +#define MPIC_PIS_MII 0x00 +#define MPIC_PIS_GMII 0x02 +#define MPIC_PIS_XGMII 0x04 +#define MPIC_LSC_SHIFT 3 +#define MPIC_LSC_100M (1 << MPIC_LSC_SHIFT) +#define MPIC_LSC_1G (2 << MPIC_LSC_SHIFT) +#define MPIC_LSC_2_5G (3 << MPIC_LSC_SHIFT) + +#define MDIO_READ_C45 0x03 +#define MDIO_WRITE_C45 0x01 + +#define MPSM_PSME BIT(0) +#define MPSM_MFF_C45 BIT(2) +#define MPSM_PRD_SHIFT 16 +#define MPSM_PRD_MASK GENMASK(31, MPSM_PRD_SHIFT) + +/* Completion flags */ +#define MMIS1_PAACS BIT(2) /* Address */ +#define MMIS1_PWACS BIT(1) /* Write */ +#define MMIS1_PRACS BIT(0) /* Read */ +#define MMIS1_CLEAR_FLAGS 0xf + +#define MPIC_PSMCS_SHIFT 16 +#define MPIC_PSMCS_MASK GENMASK(22, MPIC_PSMCS_SHIFT) +#define MPIC_PSMCS(val) ((val) << MPIC_PSMCS_SHIFT) + +#define MPIC_PSMHT_SHIFT 24 +#define MPIC_PSMHT_MASK GENMASK(26, MPIC_PSMHT_SHIFT) +#define MPIC_PSMHT(val) ((val) << MPIC_PSMHT_SHIFT) + +#define MLVC_PLV BIT(16) + +/* GWCA */ +enum rswitch_gwca_mode { + GWMC_OPC_RESET, + GWMC_OPC_DISABLE, + GWMC_OPC_CONFIG, + GWMC_OPC_OPERATION, +}; + +#define GWMS_OPS_MASK GWMC_OPC_OPERATION + +#define GWMTIRM_MTIOG BIT(0) +#define GWMTIRM_MTR BIT(1) + +#define GWVCC_VEM_SC_TAG (0x3 << 16) + +#define GWARIRM_ARIOG BIT(0) +#define GWARIRM_ARR BIT(1) + +#define GWDCC_BALR BIT(24) +#define GWDCC_DQT BIT(11) +#define GWDCC_ETS BIT(9) +#define GWDCC_EDE BIT(8) + +#define GWTRC(queue) (GWTRC0 + (queue) / 32 * 4) +#define GWDCC_OFFS(queue) (GWDCC0 + (queue) * 4) + +#define GWDIS(i) (GWDIS0 + (i) * 0x10) +#define GWDIE(i) (GWDIE0 + (i) * 0x10) +#define GWDID(i) (GWDID0 + (i) * 0x10) + +/* COMA */ +#define RRC_RR BIT(0) +#define RRC_RR_CLR 0 +#define RCEC_ACE_DEFAULT (BIT(0) | BIT(AGENT_INDEX_GWCA)) +#define RCEC_RCE BIT(16) +#define RCDC_RCD BIT(16) + +#define CABPIRM_BPIOG BIT(0) +#define CABPIRM_BPR BIT(1) + +/* MFWD */ +#define FWPC0_LTHTA BIT(0) +#define FWPC0_IP4UE BIT(3) +#define FWPC0_IP4TE BIT(4) +#define FWPC0_IP4OE BIT(5) +#define FWPC0_L2SE BIT(9) +#define FWPC0_IP4EA BIT(10) +#define FWPC0_IPDSA BIT(12) +#define FWPC0_IPHLA BIT(18) +#define FWPC0_MACSDA BIT(20) +#define FWPC0_MACHLA BIT(26) +#define FWPC0_MACHMA BIT(27) +#define FWPC0_VLANSA BIT(28) + +#define FWPC0(i) (FWPC00 + (i) * 0x10) +#define FWPC0_DEFAULT (FWPC0_LTHTA | FWPC0_IP4UE | FWPC0_IP4TE | \ + FWPC0_IP4OE | FWPC0_L2SE | FWPC0_IP4EA | \ + FWPC0_IPDSA | FWPC0_IPHLA | FWPC0_MACSDA | \ + FWPC0_MACHLA | FWPC0_MACHMA | FWPC0_VLANSA) +#define FWPC1(i) (FWPC10 + (i) * 0x10) +#define FWPC1_DDE BIT(0) + +#define FWPBFC(i) (FWPBFC0 + (i) * 0x10) + +#define FWPBFCSDC(j, i) (FWPBFCSDC00 + (i) * 0x10 + (j) * 0x04) + +/* TOP */ +#define TPEMIMC7(queue) (TPEMIMC70 + (queue) * 4) + +/* Descriptors */ +enum RX_DS_CC_BIT { + RX_DS = 0x0fff, /* Data size */ + RX_TR = 0x1000, /* Truncation indication */ + RX_EI = 0x2000, /* Error indication */ + RX_PS = 0xc000, /* Padding selection */ +}; + +enum TX_DS_TAGL_BIT { + TX_DS = 0x0fff, /* Data size */ + TX_TAGL = 0xf000, /* Frame tag LSBs */ +}; + +enum DIE_DT { + /* Frame data */ + DT_FSINGLE = 0x80, + DT_FSTART = 0x90, + DT_FMID = 0xa0, + DT_FEND = 0xb8, + + /* Chain control */ + DT_LEMPTY = 0xc0, + DT_EEMPTY = 0xd0, + DT_LINKFIX = 0x00, + DT_LINK = 0xe0, + DT_EOS = 0xf0, + /* HW/SW arbitration */ + DT_FEMPTY = 0x40, + DT_FEMPTY_IS = 0x10, + DT_FEMPTY_IC = 0x20, + DT_FEMPTY_ND = 0x38, + DT_FEMPTY_START = 0x50, + DT_FEMPTY_MID = 0x60, + DT_FEMPTY_END = 0x70, + + DT_MASK = 0xf0, + DIE = 0x08, /* Descriptor Interrupt Enable */ +}; + +/* Both transmission and reception */ +#define INFO1_FMT BIT(2) +#define INFO1_TXC BIT(3) + +/* For transmission */ +#define INFO1_TSUN(val) ((u64)(val) << 8ULL) +#define INFO1_CSD0(index) ((u64)(index) << 32ULL) +#define INFO1_CSD1(index) ((u64)(index) << 40ULL) +#define INFO1_DV(port_vector) ((u64)(port_vector) << 48ULL) + +/* For reception */ +#define INFO1_SPN(port) ((u64)(port) << 36ULL) + +struct rswitch_desc { + __le16 info_ds; /* Descriptor size */ + u8 die_dt; /* Descriptor interrupt enable and type */ + __u8 dptrh; /* Descriptor pointer MSB */ + __le32 dptrl; /* Descriptor pointer LSW */ +} __packed; + +struct rswitch_ts_desc { + struct rswitch_desc desc; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +struct rswitch_ext_desc { + struct rswitch_desc desc; + __le64 info1; +} __packed; + +struct rswitch_ext_ts_desc { + struct rswitch_desc desc; + __le64 info1; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +struct rswitch_etha { + int index; + void __iomem *addr; + void __iomem *coma_addr; + bool external_phy; + struct mii_bus *mii; + phy_interface_t phy_interface; + u8 mac_addr[MAX_ADDR_LEN]; + int link; + int speed; + + /* This hardware could not be initialized twice so that marked + * this flag to avoid multiple initialization. + */ + bool operated; +}; + +/* The datasheet said descriptor "chain" and/or "queue". For consistency of + * name, this driver calls "queue". + */ +struct rswitch_gwca_queue { + int index; + bool dir_tx; + bool gptp; + union { + struct rswitch_ext_desc *ring; + struct rswitch_ext_ts_desc *ts_ring; + }; + dma_addr_t ring_dma; + int ring_size; + int cur; + int dirty; + struct sk_buff **skbs; + + struct net_device *ndev; /* queue to ndev for irq */ +}; + +#define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) +struct rswitch_gwca { + int index; + struct rswitch_gwca_queue *queues; + int num_queues; + DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); + u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; + u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; + int speed; +}; + +#define NUM_QUEUES_PER_NDEV 2 +struct rswitch_device { + struct rswitch_private *priv; + struct net_device *ndev; + struct napi_struct napi; + struct phylink *phylink; + struct phylink_config phylink_config; + void __iomem *addr; + struct rswitch_gwca_queue *tx_queue; + struct rswitch_gwca_queue *rx_queue; + u8 ts_tag; + + int port; + struct rswitch_etha *etha; +}; + +struct rswitch_mfwd_mac_table_entry { + int queue_index; + unsigned char addr[MAX_ADDR_LEN]; +}; + +struct rswitch_mfwd { + struct rswitch_mac_table_entry *mac_table_entries; + int num_mac_table_entries; +}; + +struct rswitch_private { + struct platform_device *pdev; + void __iomem *addr; + struct rcar_gen4_ptp_private *ptp_priv; + struct rswitch_desc *linkfix_table; + dma_addr_t linkfix_table_dma; + u32 linkfix_table_size; + + struct rswitch_device *rdev[RSWITCH_NUM_PORTS]; + + struct rswitch_gwca gwca; + struct rswitch_etha etha[RSWITCH_NUM_PORTS]; + struct rswitch_mfwd mfwd; + + bool gwca_halt; +}; + +#endif /* #ifndef __RSWITCH_H__ */ diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 58cf7cc54f40..826990459fa4 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1821,19 +1821,17 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work) const struct ofdpa_fdb_learn_work *lw = container_of(work, struct ofdpa_fdb_learn_work, work); bool removing = (lw->flags & OFDPA_OP_FLAG_REMOVE); - bool learned = (lw->flags & OFDPA_OP_FLAG_LEARNED); struct switchdev_notifier_fdb_info info = {}; + enum switchdev_notifier_type event; info.addr = lw->addr; info.vid = lw->vid; + info.offloaded = !removing; + event = removing ? SWITCHDEV_FDB_DEL_TO_BRIDGE : + SWITCHDEV_FDB_ADD_TO_BRIDGE; rtnl_lock(); - if (learned && removing) - call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, - lw->ofdpa_port->dev, &info.info, NULL); - else if (learned && !removing) - call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, - lw->ofdpa_port->dev, &info.info, NULL); + call_switchdev_notifiers(event, lw->ofdpa_port->dev, &info.info, NULL); rtnl_unlock(); kfree(work); @@ -1865,6 +1863,9 @@ static int ofdpa_port_fdb_learn(struct ofdpa_port *ofdpa_port, if (!ofdpa_port_is_bridged(ofdpa_port)) return 0; + if (!(flags & OFDPA_OP_FLAG_LEARNED)) + return 0; + lw = kzalloc(sizeof(*lw), GFP_ATOMIC); if (!lw) return -ENOMEM; diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile index b5e45fc6337e..712a48d00069 100644 --- a/drivers/net/ethernet/sfc/Makefile +++ b/drivers/net/ethernet/sfc/Makefile @@ -9,7 +9,7 @@ sfc-y += efx.o efx_common.o efx_channels.o nic.o \ ef100_ethtool.o ef100_rx.o ef100_tx.o sfc-$(CONFIG_SFC_MTD) += mtd.o sfc-$(CONFIG_SFC_SRIOV) += sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \ - mae.o tc.o tc_bindings.o + mae.o tc.o tc_bindings.o tc_counters.o obj-$(CONFIG_SFC) += sfc.o diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 135ece2f1375..702abbe59b76 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -43,8 +43,6 @@ const struct ethtool_ops ef100_ethtool_ops = { .get_pauseparam = efx_ethtool_get_pauseparam, .set_pauseparam = efx_ethtool_set_pauseparam, .get_sset_count = efx_ethtool_get_sset_count, - .get_priv_flags = efx_ethtool_get_priv_flags, - .set_priv_flags = efx_ethtool_set_priv_flags, .self_test = efx_ethtool_self_test, .get_strings = efx_ethtool_get_strings, .get_link_ksettings = efx_ethtool_get_link_ksettings, diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c index 65bbe37753e6..83d9db71d7d7 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.c +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -21,7 +21,7 @@ /* Get the value of a field in the RX prefix */ #define PREFIX_OFFSET_W(_f) (ESF_GZ_RX_PREFIX_ ## _f ## _LBN / 32) #define PREFIX_OFFSET_B(_f) (ESF_GZ_RX_PREFIX_ ## _f ## _LBN % 32) -#define PREFIX_WIDTH_MASK(_f) ((1UL << ESF_GZ_RX_PREFIX_ ## _f ## _WIDTH) - 1) +#define PREFIX_WIDTH_MASK(_f) ((1ULL << ESF_GZ_RX_PREFIX_ ## _f ## _WIDTH) - 1) #define PREFIX_WORD(_p, _f) le32_to_cpu((__force __le32)(_p)[PREFIX_OFFSET_W(_f)]) #define PREFIX_FIELD(_p, _f) ((PREFIX_WORD(_p, _f) >> PREFIX_OFFSET_B(_f)) & \ PREFIX_WIDTH_MASK(_f)) @@ -67,6 +67,13 @@ void __ef100_rx_packet(struct efx_channel *channel) prefix = (u32 *)(eh - ESE_GZ_RX_PKT_PREFIX_LEN); + if (channel->type->receive_raw) { + u32 mark = PREFIX_FIELD(prefix, USER_MARK); + + if (channel->type->receive_raw(rx_queue, mark)) + return; /* packet was consumed */ + } + if (ef100_has_fcs_error(channel, prefix) && unlikely(!(efx->net_dev->features & NETIF_F_RXALL))) goto out; @@ -183,24 +190,32 @@ void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event) void ef100_rx_write(struct efx_rx_queue *rx_queue) { + unsigned int notified_count = rx_queue->notified_count; struct efx_rx_buffer *rx_buf; unsigned int idx; efx_qword_t *rxd; efx_dword_t rxdb; - while (rx_queue->notified_count != rx_queue->added_count) { - idx = rx_queue->notified_count & rx_queue->ptr_mask; + while (notified_count != rx_queue->added_count) { + idx = notified_count & rx_queue->ptr_mask; rx_buf = efx_rx_buffer(rx_queue, idx); rxd = efx_rx_desc(rx_queue, idx); EFX_POPULATE_QWORD_1(*rxd, ESF_GZ_RX_BUF_ADDR, rx_buf->dma_addr); - ++rx_queue->notified_count; + ++notified_count; } + if (notified_count == rx_queue->notified_count) + return; wmb(); EFX_POPULATE_DWORD_1(rxdb, ERF_GZ_RX_RING_PIDX, rx_queue->added_count & rx_queue->ptr_mask); efx_writed_page(rx_queue->efx, &rxdb, ER_GZ_RX_RING_DOORBELL, efx_rx_queue_index(rx_queue)); + if (rx_queue->grant_credits) + wmb(); + rx_queue->notified_count = notified_count; + if (rx_queue->grant_credits) + schedule_work(&rx_queue->grant_work); } diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index 102ddc7e206a..29ffaf35559d 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -367,7 +367,8 @@ void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) * Returns 0 on success, error code otherwise. In case of an error this * function will free the SKB. */ -int ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +netdev_tx_t ef100_enqueue_skb(struct efx_tx_queue *tx_queue, + struct sk_buff *skb) { return __ef100_enqueue_skb(tx_queue, skb, NULL); } diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index aaa381743bca..fcea3ea809d7 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -1119,6 +1119,8 @@ void efx_start_channels(struct efx_nic *efx) struct efx_channel *channel; efx_for_each_channel_rev(channel, efx) { + if (channel->type->start) + channel->type->start(channel); efx_for_each_channel_tx_queue(tx_queue, channel) { efx_init_tx_queue(tx_queue); atomic_inc(&efx->active_queues); @@ -1143,8 +1145,13 @@ void efx_stop_channels(struct efx_nic *efx) struct efx_channel *channel; int rc = 0; - /* Stop RX refill */ + /* Stop special channels and RX refill. + * The channel's stop has to be called first, since it might wait + * for a sentinel RX to indicate the channel has fully drained. + */ efx_for_each_channel(channel, efx) { + if (channel->type->stop) + channel->type->stop(channel); efx_for_each_channel_rx_queue(rx_queue, channel) rx_queue->refill_enabled = false; } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index c2224e41a694..cc30524c2fe4 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -1164,7 +1164,7 @@ static ssize_t mcdi_logging_show(struct device *dev, struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); - return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); + return sysfs_emit(buf, "%d\n", mcdi->logging_enabled); } static ssize_t mcdi_logging_store(struct device *dev, diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index 6649a2327d03..a8cbceeb301b 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -101,14 +101,6 @@ static const struct efx_sw_stat_desc efx_sw_stat_desc[] = { #define EFX_ETHTOOL_SW_STAT_COUNT ARRAY_SIZE(efx_sw_stat_desc) -static const char efx_ethtool_priv_flags_strings[][ETH_GSTRING_LEN] = { - "log-tc-errors", -}; - -#define EFX_ETHTOOL_PRIV_FLAGS_LOG_TC_ERRS BIT(0) - -#define EFX_ETHTOOL_PRIV_FLAGS_COUNT ARRAY_SIZE(efx_ethtool_priv_flags_strings) - void efx_ethtool_get_drvinfo(struct net_device *net_dev, struct ethtool_drvinfo *info) { @@ -460,8 +452,6 @@ int efx_ethtool_get_sset_count(struct net_device *net_dev, int string_set) efx_ptp_describe_stats(efx, NULL); case ETH_SS_TEST: return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL); - case ETH_SS_PRIV_FLAGS: - return EFX_ETHTOOL_PRIV_FLAGS_COUNT; default: return -EINVAL; } @@ -488,39 +478,12 @@ void efx_ethtool_get_strings(struct net_device *net_dev, case ETH_SS_TEST: efx_ethtool_fill_self_tests(efx, NULL, strings, NULL); break; - case ETH_SS_PRIV_FLAGS: - for (i = 0; i < EFX_ETHTOOL_PRIV_FLAGS_COUNT; i++) - strscpy(strings + i * ETH_GSTRING_LEN, - efx_ethtool_priv_flags_strings[i], - ETH_GSTRING_LEN); - break; default: /* No other string sets */ break; } } -u32 efx_ethtool_get_priv_flags(struct net_device *net_dev) -{ - struct efx_nic *efx = efx_netdev_priv(net_dev); - u32 ret_flags = 0; - - if (efx->log_tc_errs) - ret_flags |= EFX_ETHTOOL_PRIV_FLAGS_LOG_TC_ERRS; - - return ret_flags; -} - -int efx_ethtool_set_priv_flags(struct net_device *net_dev, u32 flags) -{ - struct efx_nic *efx = efx_netdev_priv(net_dev); - - efx->log_tc_errs = - !!(flags & EFX_ETHTOOL_PRIV_FLAGS_LOG_TC_ERRS); - - return 0; -} - void efx_ethtool_get_stats(struct net_device *net_dev, struct ethtool_stats *stats, u64 *data) diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h index 0afc74021a5e..659491932101 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.h +++ b/drivers/net/ethernet/sfc/ethtool_common.h @@ -27,8 +27,6 @@ int efx_ethtool_fill_self_tests(struct efx_nic *efx, int efx_ethtool_get_sset_count(struct net_device *net_dev, int string_set); void efx_ethtool_get_strings(struct net_device *net_dev, u32 string_set, u8 *strings); -u32 efx_ethtool_get_priv_flags(struct net_device *net_dev); -int efx_ethtool_set_priv_flags(struct net_device *net_dev, u32 flags); void efx_ethtool_get_stats(struct net_device *net_dev, struct ethtool_stats *stats __attribute__ ((unused)), u64 *data); diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c index 874c765b2465..583baf69981c 100644 --- a/drivers/net/ethernet/sfc/mae.c +++ b/drivers/net/ethernet/sfc/mae.c @@ -112,6 +112,117 @@ int efx_mae_lookup_mport(struct efx_nic *efx, u32 selector, u32 *id) return 0; } +int efx_mae_start_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_COUNTERS_STREAM_START_V2_IN_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_COUNTERS_STREAM_START_OUT_LEN); + u32 out_flags; + size_t outlen; + int rc; + + MCDI_SET_WORD(inbuf, MAE_COUNTERS_STREAM_START_V2_IN_QID, + efx_rx_queue_index(rx_queue)); + MCDI_SET_WORD(inbuf, MAE_COUNTERS_STREAM_START_V2_IN_PACKET_SIZE, + efx->net_dev->mtu); + MCDI_SET_DWORD(inbuf, MAE_COUNTERS_STREAM_START_V2_IN_COUNTER_TYPES_MASK, + BIT(MAE_COUNTER_TYPE_AR) | BIT(MAE_COUNTER_TYPE_CT) | + BIT(MAE_COUNTER_TYPE_OR)); + rc = efx_mcdi_rpc(efx, MC_CMD_MAE_COUNTERS_STREAM_START, + inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + if (outlen < sizeof(outbuf)) + return -EIO; + out_flags = MCDI_DWORD(outbuf, MAE_COUNTERS_STREAM_START_OUT_FLAGS); + if (out_flags & BIT(MC_CMD_MAE_COUNTERS_STREAM_START_OUT_USES_CREDITS_OFST)) { + netif_dbg(efx, drv, efx->net_dev, + "MAE counter stream uses credits\n"); + rx_queue->grant_credits = true; + out_flags &= ~BIT(MC_CMD_MAE_COUNTERS_STREAM_START_OUT_USES_CREDITS_OFST); + } + if (out_flags) { + netif_err(efx, drv, efx->net_dev, + "MAE counter stream start: unrecognised flags %x\n", + out_flags); + goto out_stop; + } + return 0; +out_stop: + efx_mae_stop_counters(efx, rx_queue); + return -EOPNOTSUPP; +} + +static bool efx_mae_counters_flushed(u32 *flush_gen, u32 *seen_gen) +{ + int i; + + for (i = 0; i < EFX_TC_COUNTER_TYPE_MAX; i++) + if ((s32)(flush_gen[i] - seen_gen[i]) > 0) + return false; + return true; +} + +int efx_mae_stop_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_COUNTERS_STREAM_STOP_V2_OUT_LENMAX); + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_COUNTERS_STREAM_STOP_IN_LEN); + size_t outlen; + int rc, i; + + MCDI_SET_WORD(inbuf, MAE_COUNTERS_STREAM_STOP_IN_QID, + efx_rx_queue_index(rx_queue)); + rc = efx_mcdi_rpc(efx, MC_CMD_MAE_COUNTERS_STREAM_STOP, + inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); + + if (rc) + return rc; + + netif_dbg(efx, drv, efx->net_dev, "Draining counters:\n"); + /* Only process received generation counts */ + for (i = 0; (i < (outlen / 4)) && (i < EFX_TC_COUNTER_TYPE_MAX); i++) { + efx->tc->flush_gen[i] = MCDI_ARRAY_DWORD(outbuf, + MAE_COUNTERS_STREAM_STOP_V2_OUT_GENERATION_COUNT, + i); + netif_dbg(efx, drv, efx->net_dev, + "\ttype %u, awaiting gen %u\n", i, + efx->tc->flush_gen[i]); + } + + efx->tc->flush_counters = true; + + /* Drain can take up to 2 seconds owing to FWRIVERHD-2884; whatever + * timeout we use, that delay is added to unload on nonresponsive + * hardware, so 2500ms seems like a reasonable compromise. + */ + if (!wait_event_timeout(efx->tc->flush_wq, + efx_mae_counters_flushed(efx->tc->flush_gen, + efx->tc->seen_gen), + msecs_to_jiffies(2500))) + netif_warn(efx, drv, efx->net_dev, + "Failed to drain counters RXQ, FW may be unhappy\n"); + + efx->tc->flush_counters = false; + + return rc; +} + +void efx_mae_counters_grant_credits(struct work_struct *work) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_COUNTERS_STREAM_GIVE_CREDITS_IN_LEN); + struct efx_rx_queue *rx_queue = container_of(work, struct efx_rx_queue, + grant_work); + struct efx_nic *efx = rx_queue->efx; + unsigned int credits; + + BUILD_BUG_ON(MC_CMD_MAE_COUNTERS_STREAM_GIVE_CREDITS_OUT_LEN); + credits = READ_ONCE(rx_queue->notified_count) - rx_queue->granted_count; + MCDI_SET_DWORD(inbuf, MAE_COUNTERS_STREAM_GIVE_CREDITS_IN_NUM_CREDITS, + credits); + if (!efx_mcdi_rpc(efx, MC_CMD_MAE_COUNTERS_STREAM_GIVE_CREDITS, + inbuf, sizeof(inbuf), NULL, 0, NULL)) + rx_queue->granted_count += credits; +} + static int efx_mae_get_basic_caps(struct efx_nic *efx, struct mae_caps *caps) { MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_GET_CAPS_OUT_LEN); @@ -250,6 +361,32 @@ static int efx_mae_match_check_cap_typ(u8 support, enum mask_type typ) } } +/* Validate field mask against hardware capabilities. Captures caller's 'rc' */ +#define CHECK(_mcdi, _field) ({ \ + enum mask_type typ = classify_mask((const u8 *)&mask->_field, \ + sizeof(mask->_field)); \ + \ + rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_ ## _mcdi],\ + typ); \ + if (rc) \ + NL_SET_ERR_MSG_FMT_MOD(extack, \ + "No support for %s mask in field %s", \ + mask_type_name(typ), #_field); \ + rc; \ +}) +/* Booleans need special handling */ +#define CHECK_BIT(_mcdi, _field) ({ \ + enum mask_type typ = mask->_field ? MASK_ONES : MASK_ZEROES; \ + \ + rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_ ## _mcdi],\ + typ); \ + if (rc) \ + NL_SET_ERR_MSG_FMT_MOD(extack, \ + "No support for %s mask in field %s", \ + mask_type_name(typ), #_field); \ + rc; \ +}) + int efx_mae_match_check_caps(struct efx_nic *efx, const struct efx_tc_match_fields *mask, struct netlink_ext_ack *extack) @@ -265,11 +402,86 @@ int efx_mae_match_check_caps(struct efx_nic *efx, rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_INGRESS_PORT], ingress_port_mask_type); if (rc) { - efx_tc_err(efx, "No support for %s mask in field ingress_port\n", - mask_type_name(ingress_port_mask_type)); - NL_SET_ERR_MSG_MOD(extack, "Unsupported mask type for ingress_port"); + NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field ingress_port", + mask_type_name(ingress_port_mask_type)); return rc; } + if (CHECK(ETHER_TYPE, eth_proto) || + CHECK(VLAN0_TCI, vlan_tci[0]) || + CHECK(VLAN0_PROTO, vlan_proto[0]) || + CHECK(VLAN1_TCI, vlan_tci[1]) || + CHECK(VLAN1_PROTO, vlan_proto[1]) || + CHECK(ETH_SADDR, eth_saddr) || + CHECK(ETH_DADDR, eth_daddr) || + CHECK(IP_PROTO, ip_proto) || + CHECK(IP_TOS, ip_tos) || + CHECK(IP_TTL, ip_ttl) || + CHECK(SRC_IP4, src_ip) || + CHECK(DST_IP4, dst_ip) || +#ifdef CONFIG_IPV6 + CHECK(SRC_IP6, src_ip6) || + CHECK(DST_IP6, dst_ip6) || +#endif + CHECK(L4_SPORT, l4_sport) || + CHECK(L4_DPORT, l4_dport) || + CHECK(TCP_FLAGS, tcp_flags) || + CHECK_BIT(IS_IP_FRAG, ip_frag) || + CHECK_BIT(IP_FIRST_FRAG, ip_firstfrag) || + CHECK(RECIRC_ID, recirc_id)) + return rc; + return 0; +} +#undef CHECK_BIT +#undef CHECK + +int efx_mae_allocate_counter(struct efx_nic *efx, struct efx_tc_counter *cnt) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_COUNTER_ALLOC_OUT_LEN(1)); + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_COUNTER_ALLOC_V2_IN_LEN); + size_t outlen; + int rc; + + if (!cnt) + return -EINVAL; + + MCDI_SET_DWORD(inbuf, MAE_COUNTER_ALLOC_V2_IN_REQUESTED_COUNT, 1); + MCDI_SET_DWORD(inbuf, MAE_COUNTER_ALLOC_V2_IN_COUNTER_TYPE, cnt->type); + rc = efx_mcdi_rpc(efx, MC_CMD_MAE_COUNTER_ALLOC, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + /* pcol says this can't happen, since count is 1 */ + if (outlen < sizeof(outbuf)) + return -EIO; + cnt->fw_id = MCDI_DWORD(outbuf, MAE_COUNTER_ALLOC_OUT_COUNTER_ID); + cnt->gen = MCDI_DWORD(outbuf, MAE_COUNTER_ALLOC_OUT_GENERATION_COUNT); + return 0; +} + +int efx_mae_free_counter(struct efx_nic *efx, struct efx_tc_counter *cnt) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_COUNTER_FREE_OUT_LEN(1)); + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_COUNTER_FREE_V2_IN_LEN); + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, MAE_COUNTER_FREE_V2_IN_COUNTER_ID_COUNT, 1); + MCDI_SET_DWORD(inbuf, MAE_COUNTER_FREE_V2_IN_FREE_COUNTER_ID, cnt->fw_id); + MCDI_SET_DWORD(inbuf, MAE_COUNTER_FREE_V2_IN_COUNTER_TYPE, cnt->type); + rc = efx_mcdi_rpc(efx, MC_CMD_MAE_COUNTER_FREE, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + /* pcol says this can't happen, since count is 1 */ + if (outlen < sizeof(outbuf)) + return -EIO; + /* FW freed a different ID than we asked for, should also never happen. + * Warn because it means we've now got a different idea to the FW of + * what counters exist, which could cause mayhem later. + */ + if (WARN_ON(MCDI_DWORD(outbuf, MAE_COUNTER_FREE_OUT_FREED_COUNTER_ID) != + cnt->fw_id)) + return -EIO; return 0; } @@ -289,8 +501,12 @@ int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act) MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL); MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_DST_MAC_ID, MC_CMD_MAE_MAC_ADDR_ALLOC_OUT_MAC_ID_NULL); - MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_COUNTER_ID, - MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_NULL); + if (act->count && !WARN_ON(!act->count->cnt)) + MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_COUNTER_ID, + act->count->cnt->fw_id); + else + MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_COUNTER_ID, + MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_NULL); MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_COUNTER_LIST_ID, MC_CMD_MAE_COUNTER_LIST_ALLOC_OUT_COUNTER_LIST_ID_NULL); MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_ENCAP_HEADER_ID, @@ -440,10 +656,90 @@ static int efx_mae_populate_match_criteria(MCDI_DECLARE_STRUCT_PTR(match_crit), } MCDI_STRUCT_SET_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_INGRESS_MPORT_SELECTOR_MASK, match->mask.ingress_port); + EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS), + MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG, + match->value.ip_frag, + MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG, + match->value.ip_firstfrag); + EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS_MASK), + MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG, + match->mask.ip_frag, + MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG, + match->mask.ip_firstfrag); MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID, match->value.recirc_id); MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID_MASK, match->mask.recirc_id); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE, + match->value.eth_proto); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE_MASK, + match->mask.eth_proto); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_TCI_BE, + match->value.vlan_tci[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_TCI_BE_MASK, + match->mask.vlan_tci[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_PROTO_BE, + match->value.vlan_proto[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_PROTO_BE_MASK, + match->mask.vlan_proto[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_TCI_BE, + match->value.vlan_tci[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_TCI_BE_MASK, + match->mask.vlan_tci[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_PROTO_BE, + match->value.vlan_proto[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_PROTO_BE_MASK, + match->mask.vlan_proto[1]); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_SADDR_BE), + match->value.eth_saddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_SADDR_BE_MASK), + match->mask.eth_saddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_DADDR_BE), + match->value.eth_daddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_DADDR_BE_MASK), + match->mask.eth_daddr, ETH_ALEN); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_PROTO, + match->value.ip_proto); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_PROTO_MASK, + match->mask.ip_proto); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TOS, + match->value.ip_tos); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TOS_MASK, + match->mask.ip_tos); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TTL, + match->value.ip_ttl); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TTL_MASK, + match->mask.ip_ttl); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP4_BE, + match->value.src_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP4_BE_MASK, + match->mask.src_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP4_BE, + match->value.dst_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP4_BE_MASK, + match->mask.dst_ip); +#ifdef CONFIG_IPV6 + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP6_BE), + &match->value.src_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP6_BE_MASK), + &match->mask.src_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP6_BE), + &match->value.dst_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP6_BE_MASK), + &match->mask.dst_ip6, sizeof(struct in6_addr)); +#endif + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_SPORT_BE, + match->value.l4_sport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_SPORT_BE_MASK, + match->mask.l4_sport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_DPORT_BE, + match->value.l4_dport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_DPORT_BE_MASK, + match->mask.l4_dport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_FLAGS_BE, + match->value.tcp_flags); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_FLAGS_BE_MASK, + match->mask.tcp_flags); return 0; } diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h index 3e0cd238d523..72343e90e222 100644 --- a/drivers/net/ethernet/sfc/mae.h +++ b/drivers/net/ethernet/sfc/mae.h @@ -27,6 +27,10 @@ void efx_mae_mport_mport(struct efx_nic *efx, u32 mport_id, u32 *out); int efx_mae_lookup_mport(struct efx_nic *efx, u32 selector, u32 *id); +int efx_mae_start_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue); +int efx_mae_stop_counters(struct efx_nic *efx, struct efx_rx_queue *rx_queue); +void efx_mae_counters_grant_credits(struct work_struct *work); + #define MAE_NUM_FIELDS (MAE_FIELD_ENC_VNET_ID + 1) struct mae_caps { @@ -41,6 +45,9 @@ int efx_mae_match_check_caps(struct efx_nic *efx, const struct efx_tc_match_fields *mask, struct netlink_ext_ack *extack); +int efx_mae_allocate_counter(struct efx_nic *efx, struct efx_tc_counter *cnt); +int efx_mae_free_counter(struct efx_nic *efx, struct efx_tc_counter *cnt); + int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act); int efx_mae_free_action_set(struct efx_nic *efx, u32 fw_id); diff --git a/drivers/net/ethernet/sfc/mae_counter_format.h b/drivers/net/ethernet/sfc/mae_counter_format.h new file mode 100644 index 000000000000..7e252e393fbe --- /dev/null +++ b/drivers/net/ethernet/sfc/mae_counter_format.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2020 Xilinx, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +/* Format of counter packets (version 2) from the ef100 Match-Action Engine */ + +#ifndef EFX_MAE_COUNTER_FORMAT_H +#define EFX_MAE_COUNTER_FORMAT_H + + +/*------------------------------------------------------------*/ +/* + * ER_RX_SL_PACKETISER_HEADER_WORD(160bit): + * + */ +#define ER_RX_SL_PACKETISER_HEADER_WORD_SIZE 20 +#define ER_RX_SL_PACKETISER_HEADER_WORD_WIDTH 160 + +#define ERF_SC_PACKETISER_HEADER_VERSION_LBN 0 +#define ERF_SC_PACKETISER_HEADER_VERSION_WIDTH 8 +#define ERF_SC_PACKETISER_HEADER_VERSION_VALUE 2 +#define ERF_SC_PACKETISER_HEADER_IDENTIFIER_LBN 8 +#define ERF_SC_PACKETISER_HEADER_IDENTIFIER_WIDTH 8 +#define ERF_SC_PACKETISER_HEADER_IDENTIFIER_AR 0 +#define ERF_SC_PACKETISER_HEADER_IDENTIFIER_CT 1 +#define ERF_SC_PACKETISER_HEADER_IDENTIFIER_OR 2 +#define ERF_SC_PACKETISER_HEADER_HEADER_OFFSET_LBN 16 +#define ERF_SC_PACKETISER_HEADER_HEADER_OFFSET_WIDTH 8 +#define ERF_SC_PACKETISER_HEADER_HEADER_OFFSET_DEFAULT 0x4 +#define ERF_SC_PACKETISER_HEADER_PAYLOAD_OFFSET_LBN 24 +#define ERF_SC_PACKETISER_HEADER_PAYLOAD_OFFSET_WIDTH 8 +#define ERF_SC_PACKETISER_HEADER_PAYLOAD_OFFSET_DEFAULT 0x14 +#define ERF_SC_PACKETISER_HEADER_INDEX_LBN 32 +#define ERF_SC_PACKETISER_HEADER_INDEX_WIDTH 16 +#define ERF_SC_PACKETISER_HEADER_COUNT_LBN 48 +#define ERF_SC_PACKETISER_HEADER_COUNT_WIDTH 16 +#define ERF_SC_PACKETISER_HEADER_RESERVED_0_LBN 64 +#define ERF_SC_PACKETISER_HEADER_RESERVED_0_WIDTH 32 +#define ERF_SC_PACKETISER_HEADER_RESERVED_1_LBN 96 +#define ERF_SC_PACKETISER_HEADER_RESERVED_1_WIDTH 32 +#define ERF_SC_PACKETISER_HEADER_RESERVED_2_LBN 128 +#define ERF_SC_PACKETISER_HEADER_RESERVED_2_WIDTH 32 + + +/*------------------------------------------------------------*/ +/* + * ER_RX_SL_PACKETISER_PAYLOAD_WORD(128bit): + * + */ +#define ER_RX_SL_PACKETISER_PAYLOAD_WORD_SIZE 16 +#define ER_RX_SL_PACKETISER_PAYLOAD_WORD_WIDTH 128 + +#define ERF_SC_PACKETISER_PAYLOAD_COUNTER_INDEX_LBN 0 +#define ERF_SC_PACKETISER_PAYLOAD_COUNTER_INDEX_WIDTH 24 +#define ERF_SC_PACKETISER_PAYLOAD_RESERVED_LBN 24 +#define ERF_SC_PACKETISER_PAYLOAD_RESERVED_WIDTH 8 +#define ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_OFST 4 +#define ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_SIZE 6 +#define ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_LBN 32 +#define ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_WIDTH 48 +#define ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_OFST 10 +#define ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_SIZE 6 +#define ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_LBN 80 +#define ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_WIDTH 48 + + +#endif /* EFX_MAE_COUNTER_FORMAT_H */ diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 1f18e9dc62e8..7e35fec9da35 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -221,15 +221,32 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); #define MCDI_BYTE(_buf, _field) \ ((void)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 1), \ *MCDI_PTR(_buf, _field)) +#define MCDI_SET_WORD(_buf, _field, _value) do { \ + BUILD_BUG_ON(MC_CMD_ ## _field ## _LEN != 2); \ + BUILD_BUG_ON(MC_CMD_ ## _field ## _OFST & 1); \ + *(__force __le16 *)MCDI_PTR(_buf, _field) = cpu_to_le16(_value);\ + } while (0) #define MCDI_WORD(_buf, _field) \ ((u16)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2) + \ le16_to_cpu(*(__force const __le16 *)MCDI_PTR(_buf, _field))) +/* Write a 16-bit field defined in the protocol as being big-endian. */ +#define MCDI_STRUCT_SET_WORD_BE(_buf, _field, _value) do { \ + BUILD_BUG_ON(_field ## _LEN != 2); \ + BUILD_BUG_ON(_field ## _OFST & 1); \ + *(__force __be16 *)MCDI_STRUCT_PTR(_buf, _field) = (_value); \ + } while (0) #define MCDI_SET_DWORD(_buf, _field, _value) \ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0, _value) #define MCDI_STRUCT_SET_DWORD(_buf, _field, _value) \ EFX_POPULATE_DWORD_1(*_MCDI_STRUCT_DWORD(_buf, _field), EFX_DWORD_0, _value) #define MCDI_DWORD(_buf, _field) \ EFX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0) +/* Write a 32-bit field defined in the protocol as being big-endian. */ +#define MCDI_STRUCT_SET_DWORD_BE(_buf, _field, _value) do { \ + BUILD_BUG_ON(_field ## _LEN != 4); \ + BUILD_BUG_ON(_field ## _OFST & 3); \ + *(__force __be32 *)MCDI_STRUCT_PTR(_buf, _field) = (_value); \ + } while (0) #define MCDI_POPULATE_DWORD_1(_buf, _field, _name1, _value1) \ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), \ MC_CMD_ ## _name1, _value1) diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 2e9ba0cfe848..3b49e216768b 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -56,7 +56,8 @@ #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS #define EFX_EXTRA_CHANNEL_IOV 0 #define EFX_EXTRA_CHANNEL_PTP 1 -#define EFX_MAX_EXTRA_CHANNELS 2U +#define EFX_EXTRA_CHANNEL_TC 2 +#define EFX_MAX_EXTRA_CHANNELS 3U /* Checksum generation is a per-queue option in hardware, so each * queue visible to the networking core is backed by two hardware TX @@ -363,8 +364,12 @@ struct efx_rx_page_state { * @refill_enabled: Enable refill whenever fill level is low * @flush_pending: Set when a RX flush is pending. Has the same lifetime as * @rxq_flush_pending. + * @grant_credits: Posted RX descriptors need to be granted to the MAE with + * %MC_CMD_MAE_COUNTERS_STREAM_GIVE_CREDITS. For %EFX_EXTRA_CHANNEL_TC, + * and only supported on EF100. * @added_count: Number of buffers added to the receive queue. * @notified_count: Number of buffers given to NIC (<= @added_count). + * @granted_count: Number of buffers granted to the MAE (<= @notified_count). * @removed_count: Number of buffers removed from the receive queue. * @scatter_n: Used by NIC specific receive code. * @scatter_len: Used by NIC specific receive code. @@ -385,6 +390,7 @@ struct efx_rx_page_state { * refill was triggered. * @recycle_count: RX buffer recycle counter. * @slow_fill: Timer used to defer efx_nic_generate_fill_event(). + * @grant_work: workitem used to grant credits to the MAE if @grant_credits * @xdp_rxq_info: XDP specific RX queue information. * @xdp_rxq_info_valid: Is xdp_rxq_info valid data?. */ @@ -396,9 +402,11 @@ struct efx_rx_queue { unsigned int ptr_mask; bool refill_enabled; bool flush_pending; + bool grant_credits; unsigned int added_count; unsigned int notified_count; + unsigned int granted_count; unsigned int removed_count; unsigned int scatter_n; unsigned int scatter_len; @@ -416,6 +424,7 @@ struct efx_rx_queue { unsigned int recycle_count; struct timer_list slow_fill; unsigned int slow_fill_count; + struct work_struct grant_work; /* Statistics to supplement MAC stats */ unsigned long rx_packets; struct xdp_rxq_info xdp_rxq_info; @@ -577,12 +586,15 @@ struct efx_msi_context { * struct efx_channel_type - distinguishes traffic and extra channels * @handle_no_channel: Handle failure to allocate an extra channel * @pre_probe: Set up extra state prior to initialisation + * @start: called early in efx_start_channels() + * @stop: called early in efx_stop_channels() * @post_remove: Tear down extra state after finalisation, if allocated. * May be called on channels that have not been probed. * @get_name: Generate the channel's name (used for its IRQ handler) * @copy: Copy the channel state prior to reallocation. May be %NULL if * reallocation is not supported. * @receive_skb: Handle an skb ready to be passed to netif_receive_skb() + * @receive_raw: Handle an RX buffer ready to be passed to __efx_rx_packet() * @want_txqs: Determine whether this channel should have TX queues * created. If %NULL, TX queues are not created. * @keep_eventq: Flag for whether event queue should be kept initialised @@ -593,10 +605,13 @@ struct efx_msi_context { struct efx_channel_type { void (*handle_no_channel)(struct efx_nic *); int (*pre_probe)(struct efx_channel *); + int (*start)(struct efx_channel *); + void (*stop)(struct efx_channel *); void (*post_remove)(struct efx_channel *); void (*get_name)(struct efx_channel *, char *buf, size_t len); struct efx_channel *(*copy)(const struct efx_channel *); bool (*receive_skb)(struct efx_channel *, struct sk_buff *); + bool (*receive_raw)(struct efx_rx_queue *, u32); bool (*want_txqs)(struct efx_channel *); bool keep_eventq; bool want_pio; @@ -855,7 +870,6 @@ enum efx_xdp_tx_queues_mode { * @timer_max_ns: Interrupt timer maximum value, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues * @irqs_hooked: Channel interrupts are hooked - * @log_tc_errs: Error logging for TC filter insertion is enabled * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues * @irq_rx_moderation_us: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags @@ -1018,7 +1032,6 @@ struct efx_nic { unsigned int timer_max_ns; bool irq_rx_adaptive; bool irqs_hooked; - bool log_tc_errs; unsigned int irq_mod_step_us; unsigned int irq_rx_moderation_us; u32 msg_enable; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index eaef4a15008a..9f07e1ba7780 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -351,7 +351,7 @@ struct efx_ptp_data { void (*xmit_skb)(struct efx_nic *efx, struct sk_buff *skb); }; -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); static int efx_phc_settime(struct ptp_clock_info *ptp, @@ -1508,7 +1508,7 @@ static const struct ptp_clock_info efx_phc_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 1, - .adjfreq = efx_phc_adjfreq, + .adjfine = efx_phc_adjfine, .adjtime = efx_phc_adjtime, .gettime64 = efx_phc_gettime, .settime64 = efx_phc_settime, @@ -2137,11 +2137,12 @@ void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, ptp->ts_corrections.general_rx); } -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); + s32 delta = scaled_ppm_to_ppb(scaled_ppm); struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN); s64 adjustment_ns; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 9220afeddee8..d2f35ee15eff 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -229,6 +229,7 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue) /* Initialise ptr fields */ rx_queue->added_count = 0; rx_queue->notified_count = 0; + rx_queue->granted_count = 0; rx_queue->removed_count = 0; rx_queue->min_fill = -1U; efx_init_rx_recycle_ring(rx_queue); @@ -281,6 +282,8 @@ void efx_fini_rx_queue(struct efx_rx_queue *rx_queue) "shutting down RX queue %d\n", efx_rx_queue_index(rx_queue)); del_timer_sync(&rx_queue->slow_fill); + if (rx_queue->grant_credits) + flush_work(&rx_queue->grant_work); /* Release RX buffers from the current read ptr to the write ptr */ if (rx_queue->buffer) { diff --git a/drivers/net/ethernet/sfc/siena/efx_common.c b/drivers/net/ethernet/sfc/siena/efx_common.c index 1fd396b00bfb..e4b294b8e9ac 100644 --- a/drivers/net/ethernet/sfc/siena/efx_common.c +++ b/drivers/net/ethernet/sfc/siena/efx_common.c @@ -1178,7 +1178,7 @@ static ssize_t mcdi_logging_show(struct device *dev, struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); - return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); + return sysfs_emit(buf, "%d\n", mcdi->logging_enabled); } static ssize_t mcdi_logging_store(struct device *dev, diff --git a/drivers/net/ethernet/sfc/siena/ptp.c b/drivers/net/ethernet/sfc/siena/ptp.c index 7c46752e6eae..38e666561bcd 100644 --- a/drivers/net/ethernet/sfc/siena/ptp.c +++ b/drivers/net/ethernet/sfc/siena/ptp.c @@ -347,7 +347,7 @@ struct efx_ptp_data { void (*xmit_skb)(struct efx_nic *efx, struct sk_buff *skb); }; -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); static int efx_phc_settime(struct ptp_clock_info *ptp, @@ -1429,7 +1429,7 @@ static const struct ptp_clock_info efx_phc_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 1, - .adjfreq = efx_phc_adjfreq, + .adjfine = efx_phc_adjfine, .adjtime = efx_phc_adjtime, .gettime64 = efx_phc_gettime, .settime64 = efx_phc_settime, @@ -2044,11 +2044,12 @@ void __efx_siena_rx_skb_attach_timestamp(struct efx_channel *channel, ptp->ts_corrections.general_rx); } -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); + s32 delta = scaled_ppm_to_ppb(scaled_ppm); struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN); s64 adjustment_ns; diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 3478860d4023..deeaab9ee761 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -77,6 +77,8 @@ static void efx_tc_free_action_set(struct efx_nic *efx, */ list_del(&act->list); } + if (act->count) + efx_tc_flower_put_counter_index(efx, act->count); kfree(act); } @@ -124,50 +126,187 @@ static void efx_tc_flow_free(void *ptr, void *arg) kfree(rule); } +/* Boilerplate for the simple 'copy a field' cases */ +#define _MAP_KEY_AND_MASK(_name, _type, _tcget, _tcfield, _field) \ +if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_##_name)) { \ + struct flow_match_##_type fm; \ + \ + flow_rule_match_##_tcget(rule, &fm); \ + match->value._field = fm.key->_tcfield; \ + match->mask._field = fm.mask->_tcfield; \ +} +#define MAP_KEY_AND_MASK(_name, _type, _tcfield, _field) \ + _MAP_KEY_AND_MASK(_name, _type, _type, _tcfield, _field) +#define MAP_ENC_KEY_AND_MASK(_name, _type, _tcget, _tcfield, _field) \ + _MAP_KEY_AND_MASK(ENC_##_name, _type, _tcget, _tcfield, _field) + static int efx_tc_flower_parse_match(struct efx_nic *efx, struct flow_rule *rule, struct efx_tc_match *match, struct netlink_ext_ack *extack) { struct flow_dissector *dissector = rule->match.dissector; + unsigned char ipv = 0; + /* Owing to internal TC infelicities, the IPV6_ADDRS key might be set + * even on IPv4 filters; so rather than relying on dissector->used_keys + * we check the addr_type in the CONTROL key. If we don't find it (or + * it's masked, which should never happen), we treat both IPV4_ADDRS + * and IPV6_ADDRS as absent. + */ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control fm; flow_rule_match_control(rule, &fm); + if (IS_ALL_ONES(fm.mask->addr_type)) + switch (fm.key->addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + ipv = 4; + break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + ipv = 6; + break; + default: + break; + } - if (fm.mask->flags) { - efx_tc_err(efx, "Unsupported match on control.flags %#x\n", - fm.mask->flags); - NL_SET_ERR_MSG_MOD(extack, "Unsupported match on control.flags"); + if (fm.mask->flags & FLOW_DIS_IS_FRAGMENT) { + match->value.ip_frag = fm.key->flags & FLOW_DIS_IS_FRAGMENT; + match->mask.ip_frag = true; + } + if (fm.mask->flags & FLOW_DIS_FIRST_FRAG) { + match->value.ip_firstfrag = fm.key->flags & FLOW_DIS_FIRST_FRAG; + match->mask.ip_firstfrag = true; + } + if (fm.mask->flags & ~(FLOW_DIS_IS_FRAGMENT | FLOW_DIS_FIRST_FRAG)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on control.flags %#x", + fm.mask->flags); return -EOPNOTSUPP; } } if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC))) { - efx_tc_err(efx, "Unsupported flower keys %#x\n", dissector->used_keys); - NL_SET_ERR_MSG_MOD(extack, "Unsupported flower keys encountered"); + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_CVLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_TCP) | + BIT(FLOW_DISSECTOR_KEY_IP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#x", + dissector->used_keys); return -EOPNOTSUPP; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_match_basic fm; + MAP_KEY_AND_MASK(BASIC, basic, n_proto, eth_proto); + /* Make sure we're IP if any L3/L4 keys used. */ + if (!IS_ALL_ONES(match->mask.eth_proto) || + !(match->value.eth_proto == htons(ETH_P_IP) || + match->value.eth_proto == htons(ETH_P_IPV6))) + if (dissector->used_keys & + (BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_IP) | + BIT(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "L3/L4 flower keys %#x require protocol ipv[46]", + dissector->used_keys); + return -EINVAL; + } - flow_rule_match_basic(rule, &fm); - if (fm.mask->n_proto) { - EFX_TC_ERR_MSG(efx, extack, "Unsupported eth_proto match\n"); - return -EOPNOTSUPP; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan fm; + + flow_rule_match_vlan(rule, &fm); + if (fm.mask->vlan_id || fm.mask->vlan_priority || fm.mask->vlan_tpid) { + match->value.vlan_proto[0] = fm.key->vlan_tpid; + match->mask.vlan_proto[0] = fm.mask->vlan_tpid; + match->value.vlan_tci[0] = cpu_to_be16(fm.key->vlan_priority << 13 | + fm.key->vlan_id); + match->mask.vlan_tci[0] = cpu_to_be16(fm.mask->vlan_priority << 13 | + fm.mask->vlan_id); } - if (fm.mask->ip_proto) { - EFX_TC_ERR_MSG(efx, extack, "Unsupported ip_proto match\n"); - return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan fm; + + flow_rule_match_cvlan(rule, &fm); + if (fm.mask->vlan_id || fm.mask->vlan_priority || fm.mask->vlan_tpid) { + match->value.vlan_proto[1] = fm.key->vlan_tpid; + match->mask.vlan_proto[1] = fm.mask->vlan_tpid; + match->value.vlan_tci[1] = cpu_to_be16(fm.key->vlan_priority << 13 | + fm.key->vlan_id); + match->mask.vlan_tci[1] = cpu_to_be16(fm.mask->vlan_priority << 13 | + fm.mask->vlan_id); } } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs fm; + + flow_rule_match_eth_addrs(rule, &fm); + ether_addr_copy(match->value.eth_saddr, fm.key->src); + ether_addr_copy(match->value.eth_daddr, fm.key->dst); + ether_addr_copy(match->mask.eth_saddr, fm.mask->src); + ether_addr_copy(match->mask.eth_daddr, fm.mask->dst); + } + + MAP_KEY_AND_MASK(BASIC, basic, ip_proto, ip_proto); + /* Make sure we're TCP/UDP if any L4 keys used. */ + if ((match->value.ip_proto != IPPROTO_UDP && + match->value.ip_proto != IPPROTO_TCP) || !IS_ALL_ONES(match->mask.ip_proto)) + if (dissector->used_keys & + (BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "L4 flower keys %#x require ipproto udp or tcp", + dissector->used_keys); + return -EINVAL; + } + MAP_KEY_AND_MASK(IP, ip, tos, ip_tos); + MAP_KEY_AND_MASK(IP, ip, ttl, ip_ttl); + if (ipv == 4) { + MAP_KEY_AND_MASK(IPV4_ADDRS, ipv4_addrs, src, src_ip); + MAP_KEY_AND_MASK(IPV4_ADDRS, ipv4_addrs, dst, dst_ip); + } +#ifdef CONFIG_IPV6 + else if (ipv == 6) { + MAP_KEY_AND_MASK(IPV6_ADDRS, ipv6_addrs, src, src_ip6); + MAP_KEY_AND_MASK(IPV6_ADDRS, ipv6_addrs, dst, dst_ip6); + } +#endif + MAP_KEY_AND_MASK(PORTS, ports, src, l4_sport); + MAP_KEY_AND_MASK(PORTS, ports, dst, l4_dport); + MAP_KEY_AND_MASK(TCP, tcp, flags, tcp_flags); + return 0; } +/* For details of action order constraints refer to SF-123102-TC-1§12.6.1 */ +enum efx_tc_action_order { + EFX_TC_AO_COUNT, + EFX_TC_AO_DELIVER +}; +/* Determine whether we can add @new action without violating order */ +static bool efx_tc_flower_action_order_ok(const struct efx_tc_action_set *act, + enum efx_tc_action_order new) +{ + switch (new) { + case EFX_TC_AO_COUNT: + if (act->count) + return false; + fallthrough; + case EFX_TC_AO_DELIVER: + return !act->deliver; + default: + /* Bad caller. Whatever they wanted to do, say they can't. */ + WARN_ON_ONCE(1); + return false; + } +} + static int efx_tc_flower_replace(struct efx_nic *efx, struct net_device *net_dev, struct flow_cls_offload *tc, @@ -200,13 +339,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (efv != from_efv) { /* can't happen */ - efx_tc_err(efx, "for %s efv is %snull but from_efv is %snull\n", - netdev_name(net_dev), efv ? "non-" : "", - from_efv ? "non-" : ""); - if (efv) - NL_SET_ERR_MSG_MOD(extack, "vfrep filter has PF net_dev (can't happen)"); - else - NL_SET_ERR_MSG_MOD(extack, "PF filter has vfrep net_dev (can't happen)"); + NL_SET_ERR_MSG_FMT_MOD(extack, "for %s efv is %snull but from_efv is %snull (can't happen)", + netdev_name(net_dev), efv ? "non-" : "", + from_efv ? "non-" : ""); return -EINVAL; } @@ -214,7 +349,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, memset(&match, 0, sizeof(match)); rc = efx_tc_flower_external_mport(efx, from_efv); if (rc < 0) { - EFX_TC_ERR_MSG(efx, extack, "Failed to identify ingress m-port"); + NL_SET_ERR_MSG_MOD(extack, "Failed to identify ingress m-port"); return rc; } match.value.ingress_port = rc; @@ -224,7 +359,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, return rc; if (tc->common.chain_index) { - EFX_TC_ERR_MSG(efx, extack, "No support for nonzero chain_index"); + NL_SET_ERR_MSG_MOD(extack, "No support for nonzero chain_index"); return -EOPNOTSUPP; } match.mask.recirc_id = 0xff; @@ -261,16 +396,57 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (!act) { /* more actions after a non-pipe action */ - EFX_TC_ERR_MSG(efx, extack, "Action follows non-pipe action"); + NL_SET_ERR_MSG_MOD(extack, "Action follows non-pipe action"); rc = -EINVAL; goto release; } + if ((fa->id == FLOW_ACTION_REDIRECT || + fa->id == FLOW_ACTION_MIRRED || + fa->id == FLOW_ACTION_DROP) && fa->hw_stats) { + struct efx_tc_counter_index *ctr; + + /* Currently the only actions that want stats are + * mirred and gact (ok, shot, trap, goto-chain), which + * means we want stats just before delivery. Also, + * note that tunnel_key set shouldn't change the length + * — it's only the subsequent mirred that does that, + * and the stats are taken _before_ the mirred action + * happens. + */ + if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_COUNT)) { + /* All supported actions that count either steal + * (gact shot, mirred redirect) or clone act + * (mirred mirror), so we should never get two + * count actions on one action_set. + */ + NL_SET_ERR_MSG_MOD(extack, "Count-action conflict (can't happen)"); + rc = -EOPNOTSUPP; + goto release; + } + + if (!(fa->hw_stats & FLOW_ACTION_HW_STATS_DELAYED)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "hw_stats_type %u not supported (only 'delayed')", + fa->hw_stats); + rc = -EOPNOTSUPP; + goto release; + } + + ctr = efx_tc_flower_get_counter_index(efx, tc->cookie, + EFX_TC_COUNTER_TYPE_AR); + if (IS_ERR(ctr)) { + rc = PTR_ERR(ctr); + NL_SET_ERR_MSG_MOD(extack, "Failed to obtain a counter"); + goto release; + } + act->count = ctr; + } + switch (fa->id) { case FLOW_ACTION_DROP: rc = efx_mae_alloc_action_set(efx, act); if (rc) { - EFX_TC_ERR_MSG(efx, extack, "Failed to write action set to hw (drop)"); + NL_SET_ERR_MSG_MOD(extack, "Failed to write action set to hw (drop)"); goto release; } list_add_tail(&act->list, &rule->acts.list); @@ -279,22 +455,30 @@ static int efx_tc_flower_replace(struct efx_nic *efx, case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: save = *act; + + if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_DELIVER)) { + /* can't happen */ + rc = -EOPNOTSUPP; + NL_SET_ERR_MSG_MOD(extack, "Deliver action violates action order (can't happen)"); + goto release; + } + to_efv = efx_tc_flower_lookup_efv(efx, fa->dev); if (IS_ERR(to_efv)) { - EFX_TC_ERR_MSG(efx, extack, "Mirred egress device not on switch"); + NL_SET_ERR_MSG_MOD(extack, "Mirred egress device not on switch"); rc = PTR_ERR(to_efv); goto release; } rc = efx_tc_flower_external_mport(efx, to_efv); if (rc < 0) { - EFX_TC_ERR_MSG(efx, extack, "Failed to identify egress m-port"); + NL_SET_ERR_MSG_MOD(extack, "Failed to identify egress m-port"); goto release; } act->dest_mport = rc; act->deliver = 1; rc = efx_mae_alloc_action_set(efx, act); if (rc) { - EFX_TC_ERR_MSG(efx, extack, "Failed to write action set to hw (mirred)"); + NL_SET_ERR_MSG_MOD(extack, "Failed to write action set to hw (mirred)"); goto release; } list_add_tail(&act->list, &rule->acts.list); @@ -302,6 +486,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (fa->id == FLOW_ACTION_REDIRECT) break; /* end of the line */ /* Mirror, so continue on with saved act */ + save.count = NULL; act = kzalloc(sizeof(*act), GFP_USER); if (!act) { rc = -ENOMEM; @@ -310,9 +495,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx, *act = save; break; default: - efx_tc_err(efx, "Unhandled action %u\n", fa->id); + NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u", + fa->id); rc = -EOPNOTSUPP; - NL_SET_ERR_MSG_MOD(extack, "Unsupported action"); goto release; } } @@ -334,7 +519,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, act->deliver = 1; rc = efx_mae_alloc_action_set(efx, act); if (rc) { - EFX_TC_ERR_MSG(efx, extack, "Failed to write action set to hw (deliver)"); + NL_SET_ERR_MSG_MOD(extack, "Failed to write action set to hw (deliver)"); goto release; } list_add_tail(&act->list, &rule->acts.list); @@ -349,13 +534,13 @@ static int efx_tc_flower_replace(struct efx_nic *efx, rc = efx_mae_alloc_action_set_list(efx, &rule->acts); if (rc) { - EFX_TC_ERR_MSG(efx, extack, "Failed to write action set list to hw"); + NL_SET_ERR_MSG_MOD(extack, "Failed to write action set list to hw"); goto release; } rc = efx_mae_insert_rule(efx, &rule->match, EFX_TC_PRIO_TC, rule->acts.fw_id, &rule->fw_id); if (rc) { - EFX_TC_ERR_MSG(efx, extack, "Failed to insert rule in hw"); + NL_SET_ERR_MSG_MOD(extack, "Failed to insert rule in hw"); goto release_acts; } return 0; @@ -410,6 +595,42 @@ static int efx_tc_flower_destroy(struct efx_nic *efx, return 0; } +static int efx_tc_flower_stats(struct efx_nic *efx, struct net_device *net_dev, + struct flow_cls_offload *tc) +{ + struct netlink_ext_ack *extack = tc->common.extack; + struct efx_tc_counter_index *ctr; + struct efx_tc_counter *cnt; + u64 packets, bytes; + + ctr = efx_tc_flower_find_counter_index(efx, tc->cookie); + if (!ctr) { + /* See comment in efx_tc_flower_destroy() */ + if (!IS_ERR(efx_tc_flower_lookup_efv(efx, net_dev))) + if (net_ratelimit()) + netif_warn(efx, drv, efx->net_dev, + "Filter %lx not found for stats\n", + tc->cookie); + NL_SET_ERR_MSG_MOD(extack, "Flow cookie not found in offloaded rules"); + return -ENOENT; + } + if (WARN_ON(!ctr->cnt)) /* can't happen */ + return -EIO; + cnt = ctr->cnt; + + spin_lock_bh(&cnt->lock); + /* Report only new pkts/bytes since last time TC asked */ + packets = cnt->packets; + bytes = cnt->bytes; + flow_stats_update(&tc->stats, bytes - cnt->old_bytes, + packets - cnt->old_packets, 0, cnt->touched, + FLOW_ACTION_HW_STATS_DELAYED); + cnt->old_packets = packets; + cnt->old_bytes = bytes; + spin_unlock_bh(&cnt->lock); + return 0; +} + int efx_tc_flower(struct efx_nic *efx, struct net_device *net_dev, struct flow_cls_offload *tc, struct efx_rep *efv) { @@ -426,6 +647,9 @@ int efx_tc_flower(struct efx_nic *efx, struct net_device *net_dev, case FLOW_CLS_DESTROY: rc = efx_tc_flower_destroy(efx, net_dev, tc); break; + case FLOW_CLS_STATS: + rc = efx_tc_flower_stats(efx, net_dev, tc); + break; default: rc = -EOPNOTSUPP; break; @@ -641,6 +865,10 @@ int efx_init_struct_tc(struct efx_nic *efx) INIT_LIST_HEAD(&efx->tc->block_list); mutex_init(&efx->tc->mutex); + init_waitqueue_head(&efx->tc->flush_wq); + rc = efx_tc_init_counters(efx); + if (rc < 0) + goto fail_counters; rc = rhashtable_init(&efx->tc->match_action_ht, &efx_tc_match_action_ht_params); if (rc < 0) goto fail_match_action_ht; @@ -650,8 +878,11 @@ int efx_init_struct_tc(struct efx_nic *efx) efx->tc->dflt.pf.fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL; INIT_LIST_HEAD(&efx->tc->dflt.wire.acts.list); efx->tc->dflt.wire.fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL; + efx->extra_channel_type[EFX_EXTRA_CHANNEL_TC] = &efx_tc_channel_type; return 0; fail_match_action_ht: + efx_tc_destroy_counters(efx); +fail_counters: mutex_destroy(&efx->tc->mutex); kfree(efx->tc->caps); fail_alloc_caps: @@ -672,6 +903,7 @@ void efx_fini_struct_tc(struct efx_nic *efx) MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL); rhashtable_free_and_destroy(&efx->tc->match_action_ht, efx_tc_flow_free, efx); + efx_tc_fini_counters(efx); mutex_unlock(&efx->tc->mutex); mutex_destroy(&efx->tc->mutex); kfree(efx->tc->caps); diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h index 196fd74ed973..418ce8c13a06 100644 --- a/drivers/net/ethernet/sfc/tc.h +++ b/drivers/net/ethernet/sfc/tc.h @@ -14,27 +14,13 @@ #include <net/flow_offload.h> #include <linux/rhashtable.h> #include "net_driver.h" +#include "tc_counters.h" -/* Error reporting: convenience macros. For indicating why a given filter - * insertion is not supported; errors in internal operation or in the - * hardware should be netif_err()s instead. - */ -/* Used when error message is constant. */ -#define EFX_TC_ERR_MSG(efx, extack, message) do { \ - NL_SET_ERR_MSG_MOD(extack, message); \ - if (efx->log_tc_errs) \ - netif_info(efx, drv, efx->net_dev, "%s\n", message); \ -} while (0) -/* Used when error message is not constant; caller should also supply a - * constant extack message with NL_SET_ERR_MSG_MOD(). - */ -#define efx_tc_err(efx, fmt, args...) do { \ -if (efx->log_tc_errs) \ - netif_info(efx, drv, efx->net_dev, fmt, ##args);\ -} while (0) +#define IS_ALL_ONES(v) (!(typeof (v))~(v)) struct efx_tc_action_set { u16 deliver:1; + struct efx_tc_counter_index *count; u32 dest_mport; u32 fw_id; /* index of this entry in firmware actions table */ struct list_head list; @@ -44,6 +30,20 @@ struct efx_tc_match_fields { /* L1 */ u32 ingress_port; u8 recirc_id; + /* L2 (inner when encap) */ + __be16 eth_proto; + __be16 vlan_tci[2], vlan_proto[2]; + u8 eth_saddr[ETH_ALEN], eth_daddr[ETH_ALEN]; + /* L3 (when IP) */ + u8 ip_proto, ip_tos, ip_ttl; + __be32 src_ip, dst_ip; +#ifdef CONFIG_IPV6 + struct in6_addr src_ip6, dst_ip6; +#endif + bool ip_frag, ip_firstfrag; + /* L4 */ + __be16 l4_sport, l4_dport; /* Ports (UDP, TCP) */ + __be16 tcp_flags; }; struct efx_tc_match { @@ -76,11 +76,19 @@ enum efx_tc_rule_prios { * @caps: MAE capabilities reported by MCDI * @block_list: List of &struct efx_tc_block_binding * @mutex: Used to serialise operations on TC hashtables + * @counter_ht: Hashtable of TC counters (FW IDs and counter values) + * @counter_id_ht: Hashtable mapping TC counter cookies to counters * @match_action_ht: Hashtable of TC match-action rules * @reps_mport_id: MAE port allocated for representor RX * @reps_filter_uc: VNIC filter for representor unicast RX (promisc) * @reps_filter_mc: VNIC filter for representor multicast RX (allmulti) * @reps_mport_vport_id: vport_id for representor RX filters + * @flush_counters: counters have been stopped, waiting for drain + * @flush_gen: final generation count per type array as reported by + * MC_CMD_MAE_COUNTERS_STREAM_STOP + * @seen_gen: most recent generation count per type as seen by efx_tc_rx() + * @flush_wq: wait queue used by efx_mae_stop_counters() to wait for + * MAE counters RXQ to finish draining * @dflt: Match-action rules for default switching; at priority * %EFX_TC_PRIO_DFLT. Named by *ingress* port * @dflt.pf: rule for traffic ingressing from PF (egresses to wire) @@ -91,9 +99,15 @@ struct efx_tc_state { struct mae_caps *caps; struct list_head block_list; struct mutex mutex; + struct rhashtable counter_ht; + struct rhashtable counter_id_ht; struct rhashtable match_action_ht; u32 reps_mport_id, reps_mport_vport_id; s32 reps_filter_uc, reps_filter_mc; + bool flush_counters; + u32 flush_gen[EFX_TC_COUNTER_TYPE_MAX]; + u32 seen_gen[EFX_TC_COUNTER_TYPE_MAX]; + wait_queue_head_t flush_wq; struct { struct efx_tc_flow_rule pf; struct efx_tc_flow_rule wire; diff --git a/drivers/net/ethernet/sfc/tc_counters.c b/drivers/net/ethernet/sfc/tc_counters.c new file mode 100644 index 000000000000..d1a91d54c6bb --- /dev/null +++ b/drivers/net/ethernet/sfc/tc_counters.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2022 Advanced Micro Devices, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include "tc_counters.h" +#include "mae_counter_format.h" +#include "mae.h" +#include "rx_common.h" + +/* Counter-management hashtables */ + +static const struct rhashtable_params efx_tc_counter_id_ht_params = { + .key_len = offsetof(struct efx_tc_counter_index, linkage), + .key_offset = 0, + .head_offset = offsetof(struct efx_tc_counter_index, linkage), +}; + +static const struct rhashtable_params efx_tc_counter_ht_params = { + .key_len = offsetof(struct efx_tc_counter, linkage), + .key_offset = 0, + .head_offset = offsetof(struct efx_tc_counter, linkage), +}; + +static void efx_tc_counter_free(void *ptr, void *__unused) +{ + struct efx_tc_counter *cnt = ptr; + + kfree(cnt); +} + +static void efx_tc_counter_id_free(void *ptr, void *__unused) +{ + struct efx_tc_counter_index *ctr = ptr; + + WARN_ON(refcount_read(&ctr->ref)); + kfree(ctr); +} + +int efx_tc_init_counters(struct efx_nic *efx) +{ + int rc; + + rc = rhashtable_init(&efx->tc->counter_id_ht, &efx_tc_counter_id_ht_params); + if (rc < 0) + goto fail_counter_id_ht; + rc = rhashtable_init(&efx->tc->counter_ht, &efx_tc_counter_ht_params); + if (rc < 0) + goto fail_counter_ht; + return 0; +fail_counter_ht: + rhashtable_destroy(&efx->tc->counter_id_ht); +fail_counter_id_ht: + return rc; +} + +/* Only call this in init failure teardown. + * Normal exit should fini instead as there may be entries in the table. + */ +void efx_tc_destroy_counters(struct efx_nic *efx) +{ + rhashtable_destroy(&efx->tc->counter_ht); + rhashtable_destroy(&efx->tc->counter_id_ht); +} + +void efx_tc_fini_counters(struct efx_nic *efx) +{ + rhashtable_free_and_destroy(&efx->tc->counter_id_ht, efx_tc_counter_id_free, NULL); + rhashtable_free_and_destroy(&efx->tc->counter_ht, efx_tc_counter_free, NULL); +} + +/* Counter allocation */ + +static struct efx_tc_counter *efx_tc_flower_allocate_counter(struct efx_nic *efx, + int type) +{ + struct efx_tc_counter *cnt; + int rc, rc2; + + cnt = kzalloc(sizeof(*cnt), GFP_USER); + if (!cnt) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&cnt->lock); + cnt->touched = jiffies; + cnt->type = type; + + rc = efx_mae_allocate_counter(efx, cnt); + if (rc) + goto fail1; + rc = rhashtable_insert_fast(&efx->tc->counter_ht, &cnt->linkage, + efx_tc_counter_ht_params); + if (rc) + goto fail2; + return cnt; +fail2: + /* If we get here, it implies that we couldn't insert into the table, + * which in turn probably means that the fw_id was already taken. + * In that case, it's unclear whether we really 'own' the fw_id; but + * the firmware seemed to think we did, so it's proper to free it. + */ + rc2 = efx_mae_free_counter(efx, cnt); + if (rc2) + netif_warn(efx, hw, efx->net_dev, + "Failed to free MAE counter %u, rc %d\n", + cnt->fw_id, rc2); +fail1: + kfree(cnt); + return ERR_PTR(rc > 0 ? -EIO : rc); +} + +static void efx_tc_flower_release_counter(struct efx_nic *efx, + struct efx_tc_counter *cnt) +{ + int rc; + + rhashtable_remove_fast(&efx->tc->counter_ht, &cnt->linkage, + efx_tc_counter_ht_params); + rc = efx_mae_free_counter(efx, cnt); + if (rc) + netif_warn(efx, hw, efx->net_dev, + "Failed to free MAE counter %u, rc %d\n", + cnt->fw_id, rc); + /* This doesn't protect counter updates coming in arbitrarily long + * after we deleted the counter. The RCU just ensures that we won't + * free the counter while another thread has a pointer to it. + * Ensuring we don't update the wrong counter if the ID gets re-used + * is handled by the generation count. + */ + synchronize_rcu(); + EFX_WARN_ON_PARANOID(spin_is_locked(&cnt->lock)); + kfree(cnt); +} + +static struct efx_tc_counter *efx_tc_flower_find_counter_by_fw_id( + struct efx_nic *efx, int type, u32 fw_id) +{ + struct efx_tc_counter key = {}; + + key.fw_id = fw_id; + key.type = type; + + return rhashtable_lookup_fast(&efx->tc->counter_ht, &key, + efx_tc_counter_ht_params); +} + +/* TC cookie to counter mapping */ + +void efx_tc_flower_put_counter_index(struct efx_nic *efx, + struct efx_tc_counter_index *ctr) +{ + if (!refcount_dec_and_test(&ctr->ref)) + return; /* still in use */ + rhashtable_remove_fast(&efx->tc->counter_id_ht, &ctr->linkage, + efx_tc_counter_id_ht_params); + efx_tc_flower_release_counter(efx, ctr->cnt); + kfree(ctr); +} + +struct efx_tc_counter_index *efx_tc_flower_get_counter_index( + struct efx_nic *efx, unsigned long cookie, + enum efx_tc_counter_type type) +{ + struct efx_tc_counter_index *ctr, *old; + struct efx_tc_counter *cnt; + + ctr = kzalloc(sizeof(*ctr), GFP_USER); + if (!ctr) + return ERR_PTR(-ENOMEM); + ctr->cookie = cookie; + old = rhashtable_lookup_get_insert_fast(&efx->tc->counter_id_ht, + &ctr->linkage, + efx_tc_counter_id_ht_params); + if (old) { + /* don't need our new entry */ + kfree(ctr); + if (!refcount_inc_not_zero(&old->ref)) + return ERR_PTR(-EAGAIN); + /* existing entry found */ + ctr = old; + } else { + cnt = efx_tc_flower_allocate_counter(efx, type); + if (IS_ERR(cnt)) { + rhashtable_remove_fast(&efx->tc->counter_id_ht, + &ctr->linkage, + efx_tc_counter_id_ht_params); + kfree(ctr); + return (void *)cnt; /* it's an ERR_PTR */ + } + ctr->cnt = cnt; + refcount_set(&ctr->ref, 1); + } + return ctr; +} + +struct efx_tc_counter_index *efx_tc_flower_find_counter_index( + struct efx_nic *efx, unsigned long cookie) +{ + struct efx_tc_counter_index key = {}; + + key.cookie = cookie; + return rhashtable_lookup_fast(&efx->tc->counter_id_ht, &key, + efx_tc_counter_id_ht_params); +} + +/* TC Channel. Counter updates are delivered on this channel's RXQ. */ + +static void efx_tc_handle_no_channel(struct efx_nic *efx) +{ + netif_warn(efx, drv, efx->net_dev, + "MAE counters require MSI-X and 1 additional interrupt vector.\n"); +} + +static int efx_tc_probe_channel(struct efx_channel *channel) +{ + struct efx_rx_queue *rx_queue = &channel->rx_queue; + + channel->irq_moderation_us = 0; + rx_queue->core_index = 0; + + INIT_WORK(&rx_queue->grant_work, efx_mae_counters_grant_credits); + + return 0; +} + +static int efx_tc_start_channel(struct efx_channel *channel) +{ + struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel); + struct efx_nic *efx = channel->efx; + + return efx_mae_start_counters(efx, rx_queue); +} + +static void efx_tc_stop_channel(struct efx_channel *channel) +{ + struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel); + struct efx_nic *efx = channel->efx; + int rc; + + rc = efx_mae_stop_counters(efx, rx_queue); + if (rc) + netif_warn(efx, drv, efx->net_dev, + "Failed to stop MAE counters streaming, rc=%d.\n", + rc); + rx_queue->grant_credits = false; + flush_work(&rx_queue->grant_work); +} + +static void efx_tc_remove_channel(struct efx_channel *channel) +{ +} + +static void efx_tc_get_channel_name(struct efx_channel *channel, + char *buf, size_t len) +{ + snprintf(buf, len, "%s-mae", channel->efx->name); +} + +static void efx_tc_counter_update(struct efx_nic *efx, + enum efx_tc_counter_type counter_type, + u32 counter_idx, u64 packets, u64 bytes, + u32 mark) +{ + struct efx_tc_counter *cnt; + + rcu_read_lock(); /* Protect against deletion of 'cnt' */ + cnt = efx_tc_flower_find_counter_by_fw_id(efx, counter_type, counter_idx); + if (!cnt) { + /* This can legitimately happen when a counter is removed, + * with updates for the counter still in-flight; however this + * should be an infrequent occurrence. + */ + if (net_ratelimit()) + netif_dbg(efx, drv, efx->net_dev, + "Got update for unwanted MAE counter %u type %u\n", + counter_idx, counter_type); + goto out; + } + + spin_lock_bh(&cnt->lock); + if ((s32)mark - (s32)cnt->gen < 0) { + /* This counter update packet is from before the counter was + * allocated; thus it must be for a previous counter with + * the same ID that has since been freed, and it should be + * ignored. + */ + } else { + /* Update latest seen generation count. This ensures that + * even a long-lived counter won't start getting ignored if + * the generation count wraps around, unless it somehow + * manages to go 1<<31 generations without an update. + */ + cnt->gen = mark; + /* update counter values */ + cnt->packets += packets; + cnt->bytes += bytes; + cnt->touched = jiffies; + } + spin_unlock_bh(&cnt->lock); +out: + rcu_read_unlock(); +} + +static void efx_tc_rx_version_1(struct efx_nic *efx, const u8 *data, u32 mark) +{ + u16 n_counters, i; + + /* Header format: + * + | 0 | 1 | 2 | 3 | + * 0 |version | reserved | + * 4 | seq_index | n_counters | + */ + + n_counters = le16_to_cpu(*(const __le16 *)(data + 6)); + + /* Counter update entry format: + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | a | b | c | d | e | f | + * | counter_idx | packet_count | byte_count | + */ + for (i = 0; i < n_counters; i++) { + const void *entry = data + 8 + 16 * i; + u64 packet_count, byte_count; + u32 counter_idx; + + counter_idx = le32_to_cpu(*(const __le32 *)entry); + packet_count = le32_to_cpu(*(const __le32 *)(entry + 4)) | + ((u64)le16_to_cpu(*(const __le16 *)(entry + 8)) << 32); + byte_count = le16_to_cpu(*(const __le16 *)(entry + 10)) | + ((u64)le32_to_cpu(*(const __le32 *)(entry + 12)) << 16); + efx_tc_counter_update(efx, EFX_TC_COUNTER_TYPE_AR, counter_idx, + packet_count, byte_count, mark); + } +} + +#define TCV2_HDR_PTR(pkt, field) \ + ((void)BUILD_BUG_ON_ZERO(ERF_SC_PACKETISER_HEADER_##field##_LBN & 7), \ + (pkt) + ERF_SC_PACKETISER_HEADER_##field##_LBN / 8) +#define TCV2_HDR_BYTE(pkt, field) \ + ((void)BUILD_BUG_ON_ZERO(ERF_SC_PACKETISER_HEADER_##field##_WIDTH != 8),\ + *TCV2_HDR_PTR(pkt, field)) +#define TCV2_HDR_WORD(pkt, field) \ + ((void)BUILD_BUG_ON_ZERO(ERF_SC_PACKETISER_HEADER_##field##_WIDTH != 16),\ + (void)BUILD_BUG_ON_ZERO(ERF_SC_PACKETISER_HEADER_##field##_LBN & 15), \ + *(__force const __le16 *)TCV2_HDR_PTR(pkt, field)) +#define TCV2_PKT_PTR(pkt, poff, i, field) \ + ((void)BUILD_BUG_ON_ZERO(ERF_SC_PACKETISER_PAYLOAD_##field##_LBN & 7), \ + (pkt) + ERF_SC_PACKETISER_PAYLOAD_##field##_LBN/8 + poff + \ + i * ER_RX_SL_PACKETISER_PAYLOAD_WORD_SIZE) + +/* Read a little-endian 48-bit field with 16-bit alignment */ +static u64 efx_tc_read48(const __le16 *field) +{ + u64 out = 0; + int i; + + for (i = 0; i < 3; i++) + out |= (u64)le16_to_cpu(field[i]) << (i * 16); + return out; +} + +static enum efx_tc_counter_type efx_tc_rx_version_2(struct efx_nic *efx, + const u8 *data, u32 mark) +{ + u8 payload_offset, header_offset, ident; + enum efx_tc_counter_type type; + u16 n_counters, i; + + ident = TCV2_HDR_BYTE(data, IDENTIFIER); + switch (ident) { + case ERF_SC_PACKETISER_HEADER_IDENTIFIER_AR: + type = EFX_TC_COUNTER_TYPE_AR; + break; + case ERF_SC_PACKETISER_HEADER_IDENTIFIER_CT: + type = EFX_TC_COUNTER_TYPE_CT; + break; + case ERF_SC_PACKETISER_HEADER_IDENTIFIER_OR: + type = EFX_TC_COUNTER_TYPE_OR; + break; + default: + if (net_ratelimit()) + netif_err(efx, drv, efx->net_dev, + "ignored v2 MAE counter packet (bad identifier %u" + "), counters may be inaccurate\n", ident); + return EFX_TC_COUNTER_TYPE_MAX; + } + header_offset = TCV2_HDR_BYTE(data, HEADER_OFFSET); + /* mae_counter_format.h implies that this offset is fixed, since it + * carries on with SOP-based LBNs for the fields in this header + */ + if (header_offset != ERF_SC_PACKETISER_HEADER_HEADER_OFFSET_DEFAULT) { + if (net_ratelimit()) + netif_err(efx, drv, efx->net_dev, + "choked on v2 MAE counter packet (bad header_offset %u" + "), counters may be inaccurate\n", header_offset); + return EFX_TC_COUNTER_TYPE_MAX; + } + payload_offset = TCV2_HDR_BYTE(data, PAYLOAD_OFFSET); + n_counters = le16_to_cpu(TCV2_HDR_WORD(data, COUNT)); + + for (i = 0; i < n_counters; i++) { + const void *counter_idx_p, *packet_count_p, *byte_count_p; + u64 packet_count, byte_count; + u32 counter_idx; + + /* 24-bit field with 32-bit alignment */ + counter_idx_p = TCV2_PKT_PTR(data, payload_offset, i, COUNTER_INDEX); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_COUNTER_INDEX_WIDTH != 24); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_COUNTER_INDEX_LBN & 31); + counter_idx = le32_to_cpu(*(const __le32 *)counter_idx_p) & 0xffffff; + /* 48-bit field with 16-bit alignment */ + packet_count_p = TCV2_PKT_PTR(data, payload_offset, i, PACKET_COUNT); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_WIDTH != 48); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_PACKET_COUNT_LBN & 15); + packet_count = efx_tc_read48((const __le16 *)packet_count_p); + /* 48-bit field with 16-bit alignment */ + byte_count_p = TCV2_PKT_PTR(data, payload_offset, i, BYTE_COUNT); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_WIDTH != 48); + BUILD_BUG_ON(ERF_SC_PACKETISER_PAYLOAD_BYTE_COUNT_LBN & 15); + byte_count = efx_tc_read48((const __le16 *)byte_count_p); + + if (type == EFX_TC_COUNTER_TYPE_CT) { + /* CT counters are 1-bit saturating counters to update + * the lastuse time in CT stats. A received CT counter + * should have packet counter to 0 and only LSB bit on + * in byte counter. + */ + if (packet_count || byte_count != 1) + netdev_warn_once(efx->net_dev, + "CT counter with inconsistent state (%llu, %llu)\n", + packet_count, byte_count); + /* Do not increment the driver's byte counter */ + byte_count = 0; + } + + efx_tc_counter_update(efx, type, counter_idx, packet_count, + byte_count, mark); + } + return type; +} + +/* We always swallow the packet, whether successful or not, since it's not + * a network packet and shouldn't ever be forwarded to the stack. + * @mark is the generation count for counter allocations. + */ +static bool efx_tc_rx(struct efx_rx_queue *rx_queue, u32 mark) +{ + struct efx_channel *channel = efx_rx_queue_channel(rx_queue); + struct efx_rx_buffer *rx_buf = efx_rx_buffer(rx_queue, + channel->rx_pkt_index); + const u8 *data = efx_rx_buf_va(rx_buf); + struct efx_nic *efx = rx_queue->efx; + enum efx_tc_counter_type type; + u8 version; + + /* version is always first byte of packet */ + version = *data; + switch (version) { + case 1: + type = EFX_TC_COUNTER_TYPE_AR; + efx_tc_rx_version_1(efx, data, mark); + break; + case ERF_SC_PACKETISER_HEADER_VERSION_VALUE: // 2 + type = efx_tc_rx_version_2(efx, data, mark); + break; + default: + if (net_ratelimit()) + netif_err(efx, drv, efx->net_dev, + "choked on MAE counter packet (bad version %u" + "); counters may be inaccurate\n", + version); + goto out; + } + + if (type < EFX_TC_COUNTER_TYPE_MAX) { + /* Update seen_gen unconditionally, to avoid a missed wakeup if + * we race with efx_mae_stop_counters(). + */ + efx->tc->seen_gen[type] = mark; + if (efx->tc->flush_counters && + (s32)(efx->tc->flush_gen[type] - mark) <= 0) + wake_up(&efx->tc->flush_wq); + } +out: + efx_free_rx_buffers(rx_queue, rx_buf, 1); + channel->rx_pkt_n_frags = 0; + return true; +} + +const struct efx_channel_type efx_tc_channel_type = { + .handle_no_channel = efx_tc_handle_no_channel, + .pre_probe = efx_tc_probe_channel, + .start = efx_tc_start_channel, + .stop = efx_tc_stop_channel, + .post_remove = efx_tc_remove_channel, + .get_name = efx_tc_get_channel_name, + .receive_raw = efx_tc_rx, + .keep_eventq = true, +}; diff --git a/drivers/net/ethernet/sfc/tc_counters.h b/drivers/net/ethernet/sfc/tc_counters.h new file mode 100644 index 000000000000..8fc7c4bbb29c --- /dev/null +++ b/drivers/net/ethernet/sfc/tc_counters.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2022 Advanced Micro Devices, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#ifndef EFX_TC_COUNTERS_H +#define EFX_TC_COUNTERS_H +#include <linux/refcount.h> +#include "net_driver.h" + +#include "mcdi_pcol.h" /* for MAE_COUNTER_TYPE_* */ + +enum efx_tc_counter_type { + EFX_TC_COUNTER_TYPE_AR = MAE_COUNTER_TYPE_AR, + EFX_TC_COUNTER_TYPE_CT = MAE_COUNTER_TYPE_CT, + EFX_TC_COUNTER_TYPE_OR = MAE_COUNTER_TYPE_OR, + EFX_TC_COUNTER_TYPE_MAX +}; + +struct efx_tc_counter { + u32 fw_id; /* index in firmware counter table */ + enum efx_tc_counter_type type; + struct rhash_head linkage; /* efx->tc->counter_ht */ + spinlock_t lock; /* Serialises updates to counter values */ + u32 gen; /* Generation count at which this counter is current */ + u64 packets, bytes; + u64 old_packets, old_bytes; /* Values last time passed to userspace */ + /* jiffies of the last time we saw packets increase */ + unsigned long touched; +}; + +struct efx_tc_counter_index { + unsigned long cookie; + struct rhash_head linkage; /* efx->tc->counter_id_ht */ + refcount_t ref; + struct efx_tc_counter *cnt; +}; + +/* create/uncreate/teardown hashtables */ +int efx_tc_init_counters(struct efx_nic *efx); +void efx_tc_destroy_counters(struct efx_nic *efx); +void efx_tc_fini_counters(struct efx_nic *efx); + +struct efx_tc_counter_index *efx_tc_flower_get_counter_index( + struct efx_nic *efx, unsigned long cookie, + enum efx_tc_counter_type type); +void efx_tc_flower_put_counter_index(struct efx_nic *efx, + struct efx_tc_counter_index *ctr); +struct efx_tc_counter_index *efx_tc_flower_find_counter_index( + struct efx_nic *efx, unsigned long cookie); + +extern const struct efx_channel_type efx_tc_channel_type; + +#endif /* EFX_TC_COUNTERS_H */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index c5f88f7a7a04..4ed4082836a9 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -207,11 +207,11 @@ static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb, skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u8 *vaddr; - vaddr = kmap_atomic(skb_frag_page(f)); + vaddr = kmap_local_page(skb_frag_page(f)); efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + skb_frag_off(f), skb_frag_size(f), copy_buf); - kunmap_atomic(vaddr); + kunmap_local(vaddr); } EFX_WARN_ON_ONCE_PARANOID(skb_shinfo(skb)->frag_list); diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig index 2524c907f386..5f22a8a4d27b 100644 --- a/drivers/net/ethernet/smsc/Kconfig +++ b/drivers/net/ethernet/smsc/Kconfig @@ -75,20 +75,6 @@ config EPIC100 More specific information and updates are available from <http://www.scyld.com/network/epic100.html>. -config SMC911X - tristate "SMSC LAN911[5678] support" - select CRC32 - select MII - depends on (ARM || SUPERH || COMPILE_TEST) - help - This is a driver for SMSC's LAN911x series of Ethernet chipsets - including the new LAN9115, LAN9116, LAN9117, and LAN9118. - Say Y here if you want it compiled into the kernel. - - This driver is also available as a module. The module will be - called smc911x. If you want to compile it as a module, say M - here and read <file:Documentation/kbuild/modules.rst> - config SMSC911X tristate "SMSC LAN911x/LAN921x families embedded ethernet support" depends on HAS_IOMEM diff --git a/drivers/net/ethernet/smsc/Makefile b/drivers/net/ethernet/smsc/Makefile index 4105912b1629..1501fa364c13 100644 --- a/drivers/net/ethernet/smsc/Makefile +++ b/drivers/net/ethernet/smsc/Makefile @@ -8,5 +8,4 @@ obj-$(CONFIG_SMC91X) += smc91x.o obj-$(CONFIG_PCMCIA_SMC91C92) += smc91c92_cs.o obj-$(CONFIG_EPIC100) += epic100.o obj-$(CONFIG_SMSC9420) += smsc9420.o -obj-$(CONFIG_SMC911X) += smc911x.o obj-$(CONFIG_SMSC911X) += smsc911x.o diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c deleted file mode 100644 index 52ecfb461c41..000000000000 --- a/drivers/net/ethernet/smsc/smc911x.c +++ /dev/null @@ -1,2198 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * smc911x.c - * This is a driver for SMSC's LAN911{5,6,7,8} single-chip Ethernet devices. - * - * Copyright (C) 2005 Sensoria Corp - * Derived from the unified SMC91x driver by Nicolas Pitre - * and the smsc911x.c reference driver by SMSC - * - * Arguments: - * watchdog = TX watchdog timeout - * tx_fifo_kb = Size of TX FIFO in KB - * - * History: - * 04/16/05 Dustin McIntire Initial version - */ -static const char version[] = - "smc911x.c: v1.0 04-16-2005 by Dustin McIntire <dustin@sensoria.com>\n"; - -/* Debugging options */ -#define ENABLE_SMC_DEBUG_RX 0 -#define ENABLE_SMC_DEBUG_TX 0 -#define ENABLE_SMC_DEBUG_DMA 0 -#define ENABLE_SMC_DEBUG_PKTS 0 -#define ENABLE_SMC_DEBUG_MISC 0 -#define ENABLE_SMC_DEBUG_FUNC 0 - -#define SMC_DEBUG_RX ((ENABLE_SMC_DEBUG_RX ? 1 : 0) << 0) -#define SMC_DEBUG_TX ((ENABLE_SMC_DEBUG_TX ? 1 : 0) << 1) -#define SMC_DEBUG_DMA ((ENABLE_SMC_DEBUG_DMA ? 1 : 0) << 2) -#define SMC_DEBUG_PKTS ((ENABLE_SMC_DEBUG_PKTS ? 1 : 0) << 3) -#define SMC_DEBUG_MISC ((ENABLE_SMC_DEBUG_MISC ? 1 : 0) << 4) -#define SMC_DEBUG_FUNC ((ENABLE_SMC_DEBUG_FUNC ? 1 : 0) << 5) - -#ifndef SMC_DEBUG -#define SMC_DEBUG ( SMC_DEBUG_RX | \ - SMC_DEBUG_TX | \ - SMC_DEBUG_DMA | \ - SMC_DEBUG_PKTS | \ - SMC_DEBUG_MISC | \ - SMC_DEBUG_FUNC \ - ) -#endif - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/errno.h> -#include <linux/ioport.h> -#include <linux/crc32.h> -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/spinlock.h> -#include <linux/ethtool.h> -#include <linux/mii.h> -#include <linux/workqueue.h> - -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> - -#include <linux/dmaengine.h> - -#include <asm/io.h> - -#include "smc911x.h" - -/* - * Transmit timeout, default 5 seconds. - */ -static int watchdog = 5000; -module_param(watchdog, int, 0400); -MODULE_PARM_DESC(watchdog, "transmit timeout in milliseconds"); - -static int tx_fifo_kb=8; -module_param(tx_fifo_kb, int, 0400); -MODULE_PARM_DESC(tx_fifo_kb,"transmit FIFO size in KB (1<x<15)(default=8)"); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:smc911x"); - -/* - * The internal workings of the driver. If you are changing anything - * here with the SMC stuff, you should have the datasheet and know - * what you are doing. - */ -#define CARDNAME "smc911x" - -/* - * Use power-down feature of the chip - */ -#define POWER_DOWN 1 - -#if SMC_DEBUG > 0 -#define DBG(n, dev, args...) \ - do { \ - if (SMC_DEBUG & (n)) \ - netdev_dbg(dev, args); \ - } while (0) - -#define PRINTK(dev, args...) netdev_info(dev, args) -#else -#define DBG(n, dev, args...) \ - while (0) { \ - netdev_dbg(dev, args); \ - } -#define PRINTK(dev, args...) netdev_dbg(dev, args) -#endif - -#if SMC_DEBUG_PKTS > 0 -static void PRINT_PKT(u_char *buf, int length) -{ - int i; - int remainder; - int lines; - - lines = length / 16; - remainder = length % 16; - - for (i = 0; i < lines ; i ++) { - int cur; - printk(KERN_DEBUG); - for (cur = 0; cur < 8; cur++) { - u_char a, b; - a = *buf++; - b = *buf++; - pr_cont("%02x%02x ", a, b); - } - pr_cont("\n"); - } - printk(KERN_DEBUG); - for (i = 0; i < remainder/2 ; i++) { - u_char a, b; - a = *buf++; - b = *buf++; - pr_cont("%02x%02x ", a, b); - } - pr_cont("\n"); -} -#else -static inline void PRINT_PKT(u_char *buf, int length) { } -#endif - - -/* this enables an interrupt in the interrupt mask register */ -#define SMC_ENABLE_INT(lp, x) do { \ - unsigned int __mask; \ - __mask = SMC_GET_INT_EN((lp)); \ - __mask |= (x); \ - SMC_SET_INT_EN((lp), __mask); \ -} while (0) - -/* this disables an interrupt from the interrupt mask register */ -#define SMC_DISABLE_INT(lp, x) do { \ - unsigned int __mask; \ - __mask = SMC_GET_INT_EN((lp)); \ - __mask &= ~(x); \ - SMC_SET_INT_EN((lp), __mask); \ -} while (0) - -/* - * this does a soft reset on the device - */ -static void smc911x_reset(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int reg, timeout=0, resets=1, irq_cfg; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* Take out of PM setting first */ - if ((SMC_GET_PMT_CTRL(lp) & PMT_CTRL_READY_) == 0) { - /* Write to the bytetest will take out of powerdown */ - SMC_SET_BYTE_TEST(lp, 0); - timeout=10; - do { - udelay(10); - reg = SMC_GET_PMT_CTRL(lp) & PMT_CTRL_READY_; - } while (--timeout && !reg); - if (timeout == 0) { - PRINTK(dev, "smc911x_reset timeout waiting for PM restore\n"); - return; - } - } - - /* Disable all interrupts */ - spin_lock_irqsave(&lp->lock, flags); - SMC_SET_INT_EN(lp, 0); - spin_unlock_irqrestore(&lp->lock, flags); - - while (resets--) { - SMC_SET_HW_CFG(lp, HW_CFG_SRST_); - timeout=10; - do { - udelay(10); - reg = SMC_GET_HW_CFG(lp); - /* If chip indicates reset timeout then try again */ - if (reg & HW_CFG_SRST_TO_) { - PRINTK(dev, "chip reset timeout, retrying...\n"); - resets++; - break; - } - } while (--timeout && (reg & HW_CFG_SRST_)); - } - if (timeout == 0) { - PRINTK(dev, "smc911x_reset timeout waiting for reset\n"); - return; - } - - /* make sure EEPROM has finished loading before setting GPIO_CFG */ - timeout=1000; - while (--timeout && (SMC_GET_E2P_CMD(lp) & E2P_CMD_EPC_BUSY_)) - udelay(10); - - if (timeout == 0){ - PRINTK(dev, "smc911x_reset timeout waiting for EEPROM busy\n"); - return; - } - - /* Initialize interrupts */ - SMC_SET_INT_EN(lp, 0); - SMC_ACK_INT(lp, -1); - - /* Reset the FIFO level and flow control settings */ - SMC_SET_HW_CFG(lp, (lp->tx_fifo_kb & 0xF) << 16); -//TODO: Figure out what appropriate pause time is - SMC_SET_FLOW(lp, FLOW_FCPT_ | FLOW_FCEN_); - SMC_SET_AFC_CFG(lp, lp->afc_cfg); - - - /* Set to LED outputs */ - SMC_SET_GPIO_CFG(lp, 0x70070000); - - /* - * Deassert IRQ for 1*10us for edge type interrupts - * and drive IRQ pin push-pull - */ - irq_cfg = (1 << 24) | INT_CFG_IRQ_EN_ | INT_CFG_IRQ_TYPE_; -#ifdef SMC_DYNAMIC_BUS_CONFIG - if (lp->cfg.irq_polarity) - irq_cfg |= INT_CFG_IRQ_POL_; -#endif - SMC_SET_IRQ_CFG(lp, irq_cfg); - - /* clear anything saved */ - if (lp->pending_tx_skb != NULL) { - dev_kfree_skb (lp->pending_tx_skb); - lp->pending_tx_skb = NULL; - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - } -} - -/* - * Enable Interrupts, Receive, and Transmit - */ -static void smc911x_enable(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned mask, cfg, cr; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - - SMC_SET_MAC_ADDR(lp, dev->dev_addr); - - /* Enable TX */ - cfg = SMC_GET_HW_CFG(lp); - cfg &= HW_CFG_TX_FIF_SZ_ | 0xFFF; - cfg |= HW_CFG_SF_; - SMC_SET_HW_CFG(lp, cfg); - SMC_SET_FIFO_TDA(lp, 0xFF); - /* Update TX stats on every 64 packets received or every 1 sec */ - SMC_SET_FIFO_TSL(lp, 64); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - - SMC_GET_MAC_CR(lp, cr); - cr |= MAC_CR_TXEN_ | MAC_CR_HBDIS_; - SMC_SET_MAC_CR(lp, cr); - SMC_SET_TX_CFG(lp, TX_CFG_TX_ON_); - - /* Add 2 byte padding to start of packets */ - SMC_SET_RX_CFG(lp, (2<<8) & RX_CFG_RXDOFF_); - - /* Turn on receiver and enable RX */ - if (cr & MAC_CR_RXEN_) - DBG(SMC_DEBUG_RX, dev, "Receiver already enabled\n"); - - SMC_SET_MAC_CR(lp, cr | MAC_CR_RXEN_); - - /* Interrupt on every received packet */ - SMC_SET_FIFO_RSA(lp, 0x01); - SMC_SET_FIFO_RSL(lp, 0x00); - - /* now, enable interrupts */ - mask = INT_EN_TDFA_EN_ | INT_EN_TSFL_EN_ | INT_EN_RSFL_EN_ | - INT_EN_GPT_INT_EN_ | INT_EN_RXDFH_INT_EN_ | INT_EN_RXE_EN_ | - INT_EN_PHY_INT_EN_; - if (IS_REV_A(lp->revision)) - mask|=INT_EN_RDFL_EN_; - else { - mask|=INT_EN_RDFO_EN_; - } - SMC_ENABLE_INT(lp, mask); - - spin_unlock_irqrestore(&lp->lock, flags); -} - -/* - * this puts the device in an inactive state - */ -static void smc911x_shutdown(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned cr; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "%s: --> %s\n", CARDNAME, __func__); - - /* Disable IRQ's */ - SMC_SET_INT_EN(lp, 0); - - /* Turn of Rx and TX */ - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CR(lp, cr); - cr &= ~(MAC_CR_TXEN_ | MAC_CR_RXEN_ | MAC_CR_HBDIS_); - SMC_SET_MAC_CR(lp, cr); - SMC_SET_TX_CFG(lp, TX_CFG_STOP_TX_); - spin_unlock_irqrestore(&lp->lock, flags); -} - -static inline void smc911x_drop_pkt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int fifo_count, timeout, reg; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_RX, dev, "%s: --> %s\n", - CARDNAME, __func__); - fifo_count = SMC_GET_RX_FIFO_INF(lp) & 0xFFFF; - if (fifo_count <= 4) { - /* Manually dump the packet data */ - while (fifo_count--) - SMC_GET_RX_FIFO(lp); - } else { - /* Fast forward through the bad packet */ - SMC_SET_RX_DP_CTRL(lp, RX_DP_CTRL_FFWD_BUSY_); - timeout=50; - do { - udelay(10); - reg = SMC_GET_RX_DP_CTRL(lp) & RX_DP_CTRL_FFWD_BUSY_; - } while (--timeout && reg); - if (timeout == 0) { - PRINTK(dev, "timeout waiting for RX fast forward\n"); - } - } -} - -/* - * This is the procedure to handle the receipt of a packet. - * It should be called after checking for packet presence in - * the RX status FIFO. It must be called with the spin lock - * already held. - */ -static inline void smc911x_rcv(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int pkt_len, status; - struct sk_buff *skb; - unsigned char *data; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_RX, dev, "--> %s\n", - __func__); - status = SMC_GET_RX_STS_FIFO(lp); - DBG(SMC_DEBUG_RX, dev, "Rx pkt len %d status 0x%08x\n", - (status & 0x3fff0000) >> 16, status & 0xc000ffff); - pkt_len = (status & RX_STS_PKT_LEN_) >> 16; - if (status & RX_STS_ES_) { - /* Deal with a bad packet */ - dev->stats.rx_errors++; - if (status & RX_STS_CRC_ERR_) - dev->stats.rx_crc_errors++; - else { - if (status & RX_STS_LEN_ERR_) - dev->stats.rx_length_errors++; - if (status & RX_STS_MCAST_) - dev->stats.multicast++; - } - /* Remove the bad packet data from the RX FIFO */ - smc911x_drop_pkt(dev); - } else { - /* Receive a valid packet */ - /* Alloc a buffer with extra room for DMA alignment */ - skb = netdev_alloc_skb(dev, pkt_len+32); - if (unlikely(skb == NULL)) { - PRINTK(dev, "Low memory, rcvd packet dropped.\n"); - dev->stats.rx_dropped++; - smc911x_drop_pkt(dev); - return; - } - /* Align IP header to 32 bits - * Note that the device is configured to add a 2 - * byte padding to the packet start, so we really - * want to write to the orignal data pointer */ - data = skb->data; - skb_reserve(skb, 2); - skb_put(skb,pkt_len-4); -#ifdef SMC_USE_DMA - { - unsigned int fifo; - /* Lower the FIFO threshold if possible */ - fifo = SMC_GET_FIFO_INT(lp); - if (fifo & 0xFF) fifo--; - DBG(SMC_DEBUG_RX, dev, "Setting RX stat FIFO threshold to %d\n", - fifo & 0xff); - SMC_SET_FIFO_INT(lp, fifo); - /* Setup RX DMA */ - SMC_SET_RX_CFG(lp, RX_CFG_RX_END_ALGN16_ | ((2<<8) & RX_CFG_RXDOFF_)); - lp->rxdma_active = 1; - lp->current_rx_skb = skb; - SMC_PULL_DATA(lp, data, (pkt_len+2+15) & ~15); - /* Packet processing deferred to DMA RX interrupt */ - } -#else - SMC_SET_RX_CFG(lp, RX_CFG_RX_END_ALGN4_ | ((2<<8) & RX_CFG_RXDOFF_)); - SMC_PULL_DATA(lp, data, pkt_len+2+3); - - DBG(SMC_DEBUG_PKTS, dev, "Received packet\n"); - PRINT_PKT(data, min(pkt_len - 4, 64U)); - skb->protocol = eth_type_trans(skb, dev); - netif_rx(skb); - dev->stats.rx_packets++; - dev->stats.rx_bytes += pkt_len-4; -#endif - } -} - -/* - * This is called to actually send a packet to the chip. - */ -static void smc911x_hardware_send_pkt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - struct sk_buff *skb; - unsigned int cmdA, cmdB, len; - unsigned char *buf; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", __func__); - BUG_ON(lp->pending_tx_skb == NULL); - - skb = lp->pending_tx_skb; - lp->pending_tx_skb = NULL; - - /* cmdA {25:24] data alignment [20:16] start offset [10:0] buffer length */ - /* cmdB {31:16] pkt tag [10:0] length */ -#ifdef SMC_USE_DMA - /* 16 byte buffer alignment mode */ - buf = (char*)((u32)(skb->data) & ~0xF); - len = (skb->len + 0xF + ((u32)skb->data & 0xF)) & ~0xF; - cmdA = (1<<24) | (((u32)skb->data & 0xF)<<16) | - TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ | - skb->len; -#else - buf = (char *)((uintptr_t)skb->data & ~0x3); - len = (skb->len + 3 + ((uintptr_t)skb->data & 3)) & ~0x3; - cmdA = (((uintptr_t)skb->data & 0x3) << 16) | - TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ | - skb->len; -#endif - /* tag is packet length so we can use this in stats update later */ - cmdB = (skb->len << 16) | (skb->len & 0x7FF); - - DBG(SMC_DEBUG_TX, dev, "TX PKT LENGTH 0x%04x (%d) BUF 0x%p CMDA 0x%08x CMDB 0x%08x\n", - len, len, buf, cmdA, cmdB); - SMC_SET_TX_FIFO(lp, cmdA); - SMC_SET_TX_FIFO(lp, cmdB); - - DBG(SMC_DEBUG_PKTS, dev, "Transmitted packet\n"); - PRINT_PKT(buf, min(len, 64U)); - - /* Send pkt via PIO or DMA */ -#ifdef SMC_USE_DMA - lp->current_tx_skb = skb; - SMC_PUSH_DATA(lp, buf, len); - /* DMA complete IRQ will free buffer and set jiffies */ -#else - SMC_PUSH_DATA(lp, buf, len); - netif_trans_update(dev); - dev_kfree_skb_irq(skb); -#endif - if (!lp->tx_throttle) { - netif_wake_queue(dev); - } - SMC_ENABLE_INT(lp, INT_EN_TDFA_EN_ | INT_EN_TSFL_EN_); -} - -/* - * Since I am not sure if I will have enough room in the chip's ram - * to store the packet, I call this routine which either sends it - * now, or set the card to generates an interrupt when ready - * for the packet. - */ -static netdev_tx_t -smc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int free; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", - __func__); - - spin_lock_irqsave(&lp->lock, flags); - - BUG_ON(lp->pending_tx_skb != NULL); - - free = SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TDFREE_; - DBG(SMC_DEBUG_TX, dev, "TX free space %d\n", free); - - /* Turn off the flow when running out of space in FIFO */ - if (free <= SMC911X_TX_FIFO_LOW_THRESHOLD) { - DBG(SMC_DEBUG_TX, dev, "Disabling data flow due to low FIFO space (%d)\n", - free); - /* Reenable when at least 1 packet of size MTU present */ - SMC_SET_FIFO_TDA(lp, (SMC911X_TX_FIFO_LOW_THRESHOLD)/64); - lp->tx_throttle = 1; - netif_stop_queue(dev); - } - - /* Drop packets when we run out of space in TX FIFO - * Account for overhead required for: - * - * Tx command words 8 bytes - * Start offset 15 bytes - * End padding 15 bytes - */ - if (unlikely(free < (skb->len + 8 + 15 + 15))) { - netdev_warn(dev, "No Tx free space %d < %d\n", - free, skb->len); - lp->pending_tx_skb = NULL; - dev->stats.tx_errors++; - dev->stats.tx_dropped++; - spin_unlock_irqrestore(&lp->lock, flags); - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - -#ifdef SMC_USE_DMA - { - /* If the DMA is already running then defer this packet Tx until - * the DMA IRQ starts it - */ - if (lp->txdma_active) { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "Tx DMA running, deferring packet\n"); - lp->pending_tx_skb = skb; - netif_stop_queue(dev); - spin_unlock_irqrestore(&lp->lock, flags); - return NETDEV_TX_OK; - } else { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "Activating Tx DMA\n"); - lp->txdma_active = 1; - } - } -#endif - lp->pending_tx_skb = skb; - smc911x_hardware_send_pkt(dev); - spin_unlock_irqrestore(&lp->lock, flags); - - return NETDEV_TX_OK; -} - -/* - * This handles a TX status interrupt, which is only called when: - * - a TX error occurred, or - * - TX of a packet completed. - */ -static void smc911x_tx(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int tx_status; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", - __func__); - - /* Collect the TX status */ - while (((SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TSUSED_) >> 16) != 0) { - DBG(SMC_DEBUG_TX, dev, "Tx stat FIFO used 0x%04x\n", - (SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TSUSED_) >> 16); - tx_status = SMC_GET_TX_STS_FIFO(lp); - dev->stats.tx_packets++; - dev->stats.tx_bytes+=tx_status>>16; - DBG(SMC_DEBUG_TX, dev, "Tx FIFO tag 0x%04x status 0x%04x\n", - (tx_status & 0xffff0000) >> 16, - tx_status & 0x0000ffff); - /* count Tx errors, but ignore lost carrier errors when in - * full-duplex mode */ - if ((tx_status & TX_STS_ES_) && !(lp->ctl_rfduplx && - !(tx_status & 0x00000306))) { - dev->stats.tx_errors++; - } - if (tx_status & TX_STS_MANY_COLL_) { - dev->stats.collisions+=16; - dev->stats.tx_aborted_errors++; - } else { - dev->stats.collisions+=(tx_status & TX_STS_COLL_CNT_) >> 3; - } - /* carrier error only has meaning for half-duplex communication */ - if ((tx_status & (TX_STS_LOC_ | TX_STS_NO_CARR_)) && - !lp->ctl_rfduplx) { - dev->stats.tx_carrier_errors++; - } - if (tx_status & TX_STS_LATE_COLL_) { - dev->stats.collisions++; - dev->stats.tx_aborted_errors++; - } - } -} - - -/*---PHY CONTROL AND CONFIGURATION-----------------------------------------*/ -/* - * Reads a register from the MII Management serial interface - */ - -static int smc911x_phy_read(struct net_device *dev, int phyaddr, int phyreg) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int phydata; - - SMC_GET_MII(lp, phyreg, phyaddr, phydata); - - DBG(SMC_DEBUG_MISC, dev, "%s: phyaddr=0x%x, phyreg=0x%02x, phydata=0x%04x\n", - __func__, phyaddr, phyreg, phydata); - return phydata; -} - - -/* - * Writes a register to the MII Management serial interface - */ -static void smc911x_phy_write(struct net_device *dev, int phyaddr, int phyreg, - int phydata) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_MISC, dev, "%s: phyaddr=0x%x, phyreg=0x%x, phydata=0x%x\n", - __func__, phyaddr, phyreg, phydata); - - SMC_SET_MII(lp, phyreg, phyaddr, phydata); -} - -/* - * Finds and reports the PHY address (115 and 117 have external - * PHY interface 118 has internal only - */ -static void smc911x_phy_detect(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr; - unsigned int cfg, id1, id2; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - lp->phy_type = 0; - - /* - * Scan all 32 PHY addresses if necessary, starting at - * PHY#1 to PHY#31, and then PHY#0 last. - */ - switch(lp->version) { - case CHIP_9115: - case CHIP_9117: - case CHIP_9215: - case CHIP_9217: - cfg = SMC_GET_HW_CFG(lp); - if (cfg & HW_CFG_EXT_PHY_DET_) { - cfg &= ~HW_CFG_PHY_CLK_SEL_; - cfg |= HW_CFG_PHY_CLK_SEL_CLK_DIS_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg |= HW_CFG_EXT_PHY_EN_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg &= ~HW_CFG_PHY_CLK_SEL_; - cfg |= HW_CFG_PHY_CLK_SEL_EXT_PHY_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg |= HW_CFG_SMI_SEL_; - SMC_SET_HW_CFG(lp, cfg); - - for (phyaddr = 1; phyaddr < 32; ++phyaddr) { - - /* Read the PHY identifiers */ - SMC_GET_PHY_ID1(lp, phyaddr & 31, id1); - SMC_GET_PHY_ID2(lp, phyaddr & 31, id2); - - /* Make sure it is a valid identifier */ - if (id1 != 0x0000 && id1 != 0xffff && - id1 != 0x8000 && id2 != 0x0000 && - id2 != 0xffff && id2 != 0x8000) { - /* Save the PHY's address */ - lp->mii.phy_id = phyaddr & 31; - lp->phy_type = id1 << 16 | id2; - break; - } - } - if (phyaddr < 32) - /* Found an external PHY */ - break; - } - fallthrough; - default: - /* Internal media only */ - SMC_GET_PHY_ID1(lp, 1, id1); - SMC_GET_PHY_ID2(lp, 1, id2); - /* Save the PHY's address */ - lp->mii.phy_id = 1; - lp->phy_type = id1 << 16 | id2; - } - - DBG(SMC_DEBUG_MISC, dev, "phy_id1=0x%x, phy_id2=0x%x phyaddr=0x%x\n", - id1, id2, lp->mii.phy_id); -} - -/* - * Sets the PHY to a configuration as determined by the user. - * Called with spin_lock held. - */ -static int smc911x_phy_fixed(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - int bmcr; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* Enter Link Disable state */ - SMC_GET_PHY_BMCR(lp, phyaddr, bmcr); - bmcr |= BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - /* - * Set our fixed capabilities - * Disable auto-negotiation - */ - bmcr &= ~BMCR_ANENABLE; - if (lp->ctl_rfduplx) - bmcr |= BMCR_FULLDPLX; - - if (lp->ctl_rspeed == 100) - bmcr |= BMCR_SPEED100; - - /* Write our capabilities to the phy control register */ - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - /* Re-Configure the Receive/Phy Control register */ - bmcr &= ~BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - return 1; -} - -/** - * smc911x_phy_reset - reset the phy - * @dev: net device - * @phy: phy address - * - * Issue a software reset for the specified PHY and - * wait up to 100ms for the reset to complete. We should - * not access the PHY for 50ms after issuing the reset. - * - * The time to wait appears to be dependent on the PHY. - * - */ -static int smc911x_phy_reset(struct net_device *dev, int phy) -{ - struct smc911x_local *lp = netdev_priv(dev); - int timeout; - unsigned long flags; - unsigned int reg; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s()\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - reg = SMC_GET_PMT_CTRL(lp); - reg &= ~0xfffff030; - reg |= PMT_CTRL_PHY_RST_; - SMC_SET_PMT_CTRL(lp, reg); - spin_unlock_irqrestore(&lp->lock, flags); - for (timeout = 2; timeout; timeout--) { - msleep(50); - spin_lock_irqsave(&lp->lock, flags); - reg = SMC_GET_PMT_CTRL(lp); - spin_unlock_irqrestore(&lp->lock, flags); - if (!(reg & PMT_CTRL_PHY_RST_)) { - /* extra delay required because the phy may - * not be completed with its reset - * when PHY_BCR_RESET_ is cleared. 256us - * should suffice, but use 500us to be safe - */ - udelay(500); - break; - } - } - - return reg & PMT_CTRL_PHY_RST_; -} - -/** - * smc911x_phy_powerdown - powerdown phy - * @dev: net device - * @phy: phy address - * - * Power down the specified PHY - */ -static void smc911x_phy_powerdown(struct net_device *dev, int phy) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int bmcr; - - /* Enter Link Disable state */ - SMC_GET_PHY_BMCR(lp, phy, bmcr); - bmcr |= BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phy, bmcr); -} - -/** - * smc911x_phy_check_media - check the media status and adjust BMCR - * @dev: net device - * @init: set true for initialisation - * - * Select duplex mode depending on negotiation state. This - * also updates our carrier state. - */ -static void smc911x_phy_check_media(struct net_device *dev, int init) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - unsigned int bmcr, cr; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (mii_check_media(&lp->mii, netif_msg_link(lp), init)) { - /* duplex state has changed */ - SMC_GET_PHY_BMCR(lp, phyaddr, bmcr); - SMC_GET_MAC_CR(lp, cr); - if (lp->mii.full_duplex) { - DBG(SMC_DEBUG_MISC, dev, "Configuring for full-duplex mode\n"); - bmcr |= BMCR_FULLDPLX; - cr |= MAC_CR_RCVOWN_; - } else { - DBG(SMC_DEBUG_MISC, dev, "Configuring for half-duplex mode\n"); - bmcr &= ~BMCR_FULLDPLX; - cr &= ~MAC_CR_RCVOWN_; - } - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - SMC_SET_MAC_CR(lp, cr); - } -} - -/* - * Configures the specified PHY through the MII management interface - * using Autonegotiation. - * Calls smc911x_phy_fixed() if the user has requested a certain config. - * If RPC ANEG bit is set, the media selection is dependent purely on - * the selection by the MII (either in the MII BMCR reg or the result - * of autonegotiation.) If the RPC ANEG bit is cleared, the selection - * is controlled by the RPC SPEED and RPC DPLX bits. - */ -static void smc911x_phy_configure(struct work_struct *work) -{ - struct smc911x_local *lp = container_of(work, struct smc911x_local, - phy_configure); - struct net_device *dev = lp->netdev; - int phyaddr = lp->mii.phy_id; - int my_phy_caps; /* My PHY capabilities */ - int my_ad_caps; /* My Advertised capabilities */ - int status __always_unused; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s()\n", __func__); - - /* - * We should not be called if phy_type is zero. - */ - if (lp->phy_type == 0) - return; - - if (smc911x_phy_reset(dev, phyaddr)) { - netdev_info(dev, "PHY reset timed out\n"); - return; - } - spin_lock_irqsave(&lp->lock, flags); - - /* - * Enable PHY Interrupts (for register 18) - * Interrupts listed here are enabled - */ - SMC_SET_PHY_INT_MASK(lp, phyaddr, PHY_INT_MASK_ENERGY_ON_ | - PHY_INT_MASK_ANEG_COMP_ | PHY_INT_MASK_REMOTE_FAULT_ | - PHY_INT_MASK_LINK_DOWN_); - - /* If the user requested no auto neg, then go set his request */ - if (lp->mii.force_media) { - smc911x_phy_fixed(dev); - goto smc911x_phy_configure_exit; - } - - /* Copy our capabilities from MII_BMSR to MII_ADVERTISE */ - SMC_GET_PHY_BMSR(lp, phyaddr, my_phy_caps); - if (!(my_phy_caps & BMSR_ANEGCAPABLE)) { - netdev_info(dev, "Auto negotiation NOT supported\n"); - smc911x_phy_fixed(dev); - goto smc911x_phy_configure_exit; - } - - /* CSMA capable w/ both pauses */ - my_ad_caps = ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM; - - if (my_phy_caps & BMSR_100BASE4) - my_ad_caps |= ADVERTISE_100BASE4; - if (my_phy_caps & BMSR_100FULL) - my_ad_caps |= ADVERTISE_100FULL; - if (my_phy_caps & BMSR_100HALF) - my_ad_caps |= ADVERTISE_100HALF; - if (my_phy_caps & BMSR_10FULL) - my_ad_caps |= ADVERTISE_10FULL; - if (my_phy_caps & BMSR_10HALF) - my_ad_caps |= ADVERTISE_10HALF; - - /* Disable capabilities not selected by our user */ - if (lp->ctl_rspeed != 100) - my_ad_caps &= ~(ADVERTISE_100BASE4|ADVERTISE_100FULL|ADVERTISE_100HALF); - - if (!lp->ctl_rfduplx) - my_ad_caps &= ~(ADVERTISE_100FULL|ADVERTISE_10FULL); - - /* Update our Auto-Neg Advertisement Register */ - SMC_SET_PHY_MII_ADV(lp, phyaddr, my_ad_caps); - lp->mii.advertising = my_ad_caps; - - /* - * Read the register back. Without this, it appears that when - * auto-negotiation is restarted, sometimes it isn't ready and - * the link does not come up. - */ - udelay(10); - SMC_GET_PHY_MII_ADV(lp, phyaddr, status); - - DBG(SMC_DEBUG_MISC, dev, "phy caps=0x%04x\n", my_phy_caps); - DBG(SMC_DEBUG_MISC, dev, "phy advertised caps=0x%04x\n", my_ad_caps); - - /* Restart auto-negotiation process in order to advertise my caps */ - SMC_SET_PHY_BMCR(lp, phyaddr, BMCR_ANENABLE | BMCR_ANRESTART); - - smc911x_phy_check_media(dev, 1); - -smc911x_phy_configure_exit: - spin_unlock_irqrestore(&lp->lock, flags); -} - -/* - * smc911x_phy_interrupt - * - * Purpose: Handle interrupts relating to PHY register 18. This is - * called from the "hard" interrupt handler under our private spinlock. - */ -static void smc911x_phy_interrupt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - int status __always_unused; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (lp->phy_type == 0) - return; - - smc911x_phy_check_media(dev, 0); - /* read to clear status bits */ - SMC_GET_PHY_INT_SRC(lp, phyaddr,status); - DBG(SMC_DEBUG_MISC, dev, "PHY interrupt status 0x%04x\n", - status & 0xffff); - DBG(SMC_DEBUG_MISC, dev, "AFC_CFG 0x%08x\n", - SMC_GET_AFC_CFG(lp)); -} - -/*--- END PHY CONTROL AND CONFIGURATION-------------------------------------*/ - -/* - * This is the main routine of the driver, to handle the device when - * it needs some attention. - */ -static irqreturn_t smc911x_interrupt(int irq, void *dev_id) -{ - struct net_device *dev = dev_id; - struct smc911x_local *lp = netdev_priv(dev); - unsigned int status, mask, timeout; - unsigned int rx_overrun=0, cr, pkts; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - - /* Spurious interrupt check */ - if ((SMC_GET_IRQ_CFG(lp) & (INT_CFG_IRQ_INT_ | INT_CFG_IRQ_EN_)) != - (INT_CFG_IRQ_INT_ | INT_CFG_IRQ_EN_)) { - spin_unlock_irqrestore(&lp->lock, flags); - return IRQ_NONE; - } - - mask = SMC_GET_INT_EN(lp); - SMC_SET_INT_EN(lp, 0); - - /* set a timeout value, so I don't stay here forever */ - timeout = 8; - - - do { - status = SMC_GET_INT(lp); - - DBG(SMC_DEBUG_MISC, dev, "INT 0x%08x MASK 0x%08x OUTSIDE MASK 0x%08x\n", - status, mask, status & ~mask); - - status &= mask; - if (!status) - break; - - /* Handle SW interrupt condition */ - if (status & INT_STS_SW_INT_) { - SMC_ACK_INT(lp, INT_STS_SW_INT_); - mask &= ~INT_EN_SW_INT_EN_; - } - /* Handle various error conditions */ - if (status & INT_STS_RXE_) { - SMC_ACK_INT(lp, INT_STS_RXE_); - dev->stats.rx_errors++; - } - if (status & INT_STS_RXDFH_INT_) { - SMC_ACK_INT(lp, INT_STS_RXDFH_INT_); - dev->stats.rx_dropped+=SMC_GET_RX_DROP(lp); - } - /* Undocumented interrupt-what is the right thing to do here? */ - if (status & INT_STS_RXDF_INT_) { - SMC_ACK_INT(lp, INT_STS_RXDF_INT_); - } - - /* Rx Data FIFO exceeds set level */ - if (status & INT_STS_RDFL_) { - if (IS_REV_A(lp->revision)) { - rx_overrun=1; - SMC_GET_MAC_CR(lp, cr); - cr &= ~MAC_CR_RXEN_; - SMC_SET_MAC_CR(lp, cr); - DBG(SMC_DEBUG_RX, dev, "RX overrun\n"); - dev->stats.rx_errors++; - dev->stats.rx_fifo_errors++; - } - SMC_ACK_INT(lp, INT_STS_RDFL_); - } - if (status & INT_STS_RDFO_) { - if (!IS_REV_A(lp->revision)) { - SMC_GET_MAC_CR(lp, cr); - cr &= ~MAC_CR_RXEN_; - SMC_SET_MAC_CR(lp, cr); - rx_overrun=1; - DBG(SMC_DEBUG_RX, dev, "RX overrun\n"); - dev->stats.rx_errors++; - dev->stats.rx_fifo_errors++; - } - SMC_ACK_INT(lp, INT_STS_RDFO_); - } - /* Handle receive condition */ - if ((status & INT_STS_RSFL_) || rx_overrun) { - unsigned int fifo; - DBG(SMC_DEBUG_RX, dev, "RX irq\n"); - fifo = SMC_GET_RX_FIFO_INF(lp); - pkts = (fifo & RX_FIFO_INF_RXSUSED_) >> 16; - DBG(SMC_DEBUG_RX, dev, "Rx FIFO pkts %d, bytes %d\n", - pkts, fifo & 0xFFFF); - if (pkts != 0) { -#ifdef SMC_USE_DMA - unsigned int fifo; - if (lp->rxdma_active){ - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, - "RX DMA active\n"); - /* The DMA is already running so up the IRQ threshold */ - fifo = SMC_GET_FIFO_INT(lp) & ~0xFF; - fifo |= pkts & 0xFF; - DBG(SMC_DEBUG_RX, dev, - "Setting RX stat FIFO threshold to %d\n", - fifo & 0xff); - SMC_SET_FIFO_INT(lp, fifo); - } else -#endif - smc911x_rcv(dev); - } - SMC_ACK_INT(lp, INT_STS_RSFL_); - } - /* Handle transmit FIFO available */ - if (status & INT_STS_TDFA_) { - DBG(SMC_DEBUG_TX, dev, "TX data FIFO space available irq\n"); - SMC_SET_FIFO_TDA(lp, 0xFF); - lp->tx_throttle = 0; -#ifdef SMC_USE_DMA - if (!lp->txdma_active) -#endif - netif_wake_queue(dev); - SMC_ACK_INT(lp, INT_STS_TDFA_); - } - /* Handle transmit done condition */ -#if 1 - if (status & (INT_STS_TSFL_ | INT_STS_GPT_INT_)) { - DBG(SMC_DEBUG_TX | SMC_DEBUG_MISC, dev, - "Tx stat FIFO limit (%d) /GPT irq\n", - (SMC_GET_FIFO_INT(lp) & 0x00ff0000) >> 16); - smc911x_tx(dev); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - SMC_ACK_INT(lp, INT_STS_TSFL_); - SMC_ACK_INT(lp, INT_STS_TSFL_ | INT_STS_GPT_INT_); - } -#else - if (status & INT_STS_TSFL_) { - DBG(SMC_DEBUG_TX, dev, "TX status FIFO limit (%d) irq\n", ?); - smc911x_tx(dev); - SMC_ACK_INT(lp, INT_STS_TSFL_); - } - - if (status & INT_STS_GPT_INT_) { - DBG(SMC_DEBUG_RX, dev, "IRQ_CFG 0x%08x FIFO_INT 0x%08x RX_CFG 0x%08x\n", - SMC_GET_IRQ_CFG(lp), - SMC_GET_FIFO_INT(lp), - SMC_GET_RX_CFG(lp)); - DBG(SMC_DEBUG_RX, dev, "Rx Stat FIFO Used 0x%02x Data FIFO Used 0x%04x Stat FIFO 0x%08x\n", - (SMC_GET_RX_FIFO_INF(lp) & 0x00ff0000) >> 16, - SMC_GET_RX_FIFO_INF(lp) & 0xffff, - SMC_GET_RX_STS_FIFO_PEEK(lp)); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - SMC_ACK_INT(lp, INT_STS_GPT_INT_); - } -#endif - - /* Handle PHY interrupt condition */ - if (status & INT_STS_PHY_INT_) { - DBG(SMC_DEBUG_MISC, dev, "PHY irq\n"); - smc911x_phy_interrupt(dev); - SMC_ACK_INT(lp, INT_STS_PHY_INT_); - } - } while (--timeout); - - /* restore mask state */ - SMC_SET_INT_EN(lp, mask); - - DBG(SMC_DEBUG_MISC, dev, "Interrupt done (%d loops)\n", - 8-timeout); - - spin_unlock_irqrestore(&lp->lock, flags); - - return IRQ_HANDLED; -} - -#ifdef SMC_USE_DMA -static void -smc911x_tx_dma_irq(void *data) -{ - struct smc911x_local *lp = data; - struct net_device *dev = lp->netdev; - struct sk_buff *skb = lp->current_tx_skb; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n"); - BUG_ON(skb == NULL); - dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); - netif_trans_update(dev); - dev_kfree_skb_irq(skb); - lp->current_tx_skb = NULL; - if (lp->pending_tx_skb != NULL) - smc911x_hardware_send_pkt(dev); - else { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, - "No pending Tx packets. DMA disabled\n"); - spin_lock_irqsave(&lp->lock, flags); - lp->txdma_active = 0; - if (!lp->tx_throttle) { - netif_wake_queue(dev); - } - spin_unlock_irqrestore(&lp->lock, flags); - } - - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, - "TX DMA irq completed\n"); -} -static void -smc911x_rx_dma_irq(void *data) -{ - struct smc911x_local *lp = data; - struct net_device *dev = lp->netdev; - struct sk_buff *skb = lp->current_rx_skb; - unsigned long flags; - unsigned int pkts; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n"); - dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); - BUG_ON(skb == NULL); - lp->current_rx_skb = NULL; - PRINT_PKT(skb->data, skb->len); - skb->protocol = eth_type_trans(skb, dev); - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; - netif_rx(skb); - - spin_lock_irqsave(&lp->lock, flags); - pkts = (SMC_GET_RX_FIFO_INF(lp) & RX_FIFO_INF_RXSUSED_) >> 16; - if (pkts != 0) { - smc911x_rcv(dev); - }else { - lp->rxdma_active = 0; - } - spin_unlock_irqrestore(&lp->lock, flags); - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, - "RX DMA irq completed. DMA RX FIFO PKTS %d\n", - pkts); -} -#endif /* SMC_USE_DMA */ - -#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling receive - used by netconsole and other diagnostic tools - * to allow network i/o with interrupts disabled. - */ -static void smc911x_poll_controller(struct net_device *dev) -{ - disable_irq(dev->irq); - smc911x_interrupt(dev->irq, dev); - enable_irq(dev->irq); -} -#endif - -/* Our watchdog timed out. Called by the networking layer */ -static void smc911x_timeout(struct net_device *dev, unsigned int txqueue) -{ - struct smc911x_local *lp = netdev_priv(dev); - int status, mask; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - status = SMC_GET_INT(lp); - mask = SMC_GET_INT_EN(lp); - spin_unlock_irqrestore(&lp->lock, flags); - DBG(SMC_DEBUG_MISC, dev, "INT 0x%02x MASK 0x%02x\n", - status, mask); - - /* Dump the current TX FIFO contents and restart */ - mask = SMC_GET_TX_CFG(lp); - SMC_SET_TX_CFG(lp, mask | TX_CFG_TXS_DUMP_ | TX_CFG_TXD_DUMP_); - /* - * Reconfiguring the PHY doesn't seem like a bad idea here, but - * smc911x_phy_configure() calls msleep() which calls schedule_timeout() - * which calls schedule(). Hence we use a work queue. - */ - if (lp->phy_type != 0) - schedule_work(&lp->phy_configure); - - /* We can accept TX packets again */ - netif_trans_update(dev); /* prevent tx timeout */ - netif_wake_queue(dev); -} - -/* - * This routine will, depending on the values passed to it, - * either make it accept multicast packets, go into - * promiscuous mode (for TCPDUMP and cousins) or accept - * a select set of multicast packets - */ -static void smc911x_set_multicast_list(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int multicast_table[2]; - unsigned int mcr, update_multicast = 0; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CR(lp, mcr); - spin_unlock_irqrestore(&lp->lock, flags); - - if (dev->flags & IFF_PROMISC) { - - DBG(SMC_DEBUG_MISC, dev, "RCR_PRMS\n"); - mcr |= MAC_CR_PRMS_; - } - /* - * Here, I am setting this to accept all multicast packets. - * I don't need to zero the multicast table, because the flag is - * checked before the table is - */ - else if (dev->flags & IFF_ALLMULTI || netdev_mc_count(dev) > 16) { - DBG(SMC_DEBUG_MISC, dev, "RCR_ALMUL\n"); - mcr |= MAC_CR_MCPAS_; - } - - /* - * This sets the internal hardware table to filter out unwanted - * multicast packets before they take up memory. - * - * The SMC chip uses a hash table where the high 6 bits of the CRC of - * address are the offset into the table. If that bit is 1, then the - * multicast packet is accepted. Otherwise, it's dropped silently. - * - * To use the 6 bits as an offset into the table, the high 1 bit is - * the number of the 32 bit register, while the low 5 bits are the bit - * within that register. - */ - else if (!netdev_mc_empty(dev)) { - struct netdev_hw_addr *ha; - - /* Set the Hash perfec mode */ - mcr |= MAC_CR_HPFILT_; - - /* start with a table of all zeros: reject all */ - memset(multicast_table, 0, sizeof(multicast_table)); - - netdev_for_each_mc_addr(ha, dev) { - u32 position; - - /* upper 6 bits are used as hash index */ - position = ether_crc(ETH_ALEN, ha->addr)>>26; - - multicast_table[position>>5] |= 1 << (position&0x1f); - } - - /* be sure I get rid of flags I might have set */ - mcr &= ~(MAC_CR_PRMS_ | MAC_CR_MCPAS_); - - /* now, the table can be loaded into the chipset */ - update_multicast = 1; - } else { - DBG(SMC_DEBUG_MISC, dev, "~(MAC_CR_PRMS_|MAC_CR_MCPAS_)\n"); - mcr &= ~(MAC_CR_PRMS_ | MAC_CR_MCPAS_); - - /* - * since I'm disabling all multicast entirely, I need to - * clear the multicast list - */ - memset(multicast_table, 0, sizeof(multicast_table)); - update_multicast = 1; - } - - spin_lock_irqsave(&lp->lock, flags); - SMC_SET_MAC_CR(lp, mcr); - if (update_multicast) { - DBG(SMC_DEBUG_MISC, dev, - "update mcast hash table 0x%08x 0x%08x\n", - multicast_table[0], multicast_table[1]); - SMC_SET_HASHL(lp, multicast_table[0]); - SMC_SET_HASHH(lp, multicast_table[1]); - } - spin_unlock_irqrestore(&lp->lock, flags); -} - - -/* - * Open and Initialize the board - * - * Set up everything, reset the card, etc.. - */ -static int -smc911x_open(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* reset the hardware */ - smc911x_reset(dev); - - /* Configure the PHY, initialize the link state */ - smc911x_phy_configure(&lp->phy_configure); - - /* Turn on Tx + Rx */ - smc911x_enable(dev); - - netif_start_queue(dev); - - return 0; -} - -/* - * smc911x_close - * - * this makes the board clean up everything that it can - * and not talk to the outside world. Caused by - * an 'ifconfig ethX down' - */ -static int smc911x_close(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - netif_stop_queue(dev); - netif_carrier_off(dev); - - /* clear everything */ - smc911x_shutdown(dev); - - if (lp->phy_type != 0) { - /* We need to ensure that no calls to - * smc911x_phy_configure are pending. - */ - cancel_work_sync(&lp->phy_configure); - smc911x_phy_powerdown(dev, lp->mii.phy_id); - } - - if (lp->pending_tx_skb) { - dev_kfree_skb(lp->pending_tx_skb); - lp->pending_tx_skb = NULL; - } - - return 0; -} - -/* - * Ethtool support - */ -static int -smc911x_ethtool_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct smc911x_local *lp = netdev_priv(dev); - int status; - unsigned long flags; - u32 supported; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - mii_ethtool_get_link_ksettings(&lp->mii, cmd); - spin_unlock_irqrestore(&lp->lock, flags); - } else { - supported = SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_TP | SUPPORTED_AUI; - - if (lp->ctl_rspeed == 10) - cmd->base.speed = SPEED_10; - else if (lp->ctl_rspeed == 100) - cmd->base.speed = SPEED_100; - - cmd->base.autoneg = AUTONEG_DISABLE; - cmd->base.port = 0; - SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status); - cmd->base.duplex = - (status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ? - DUPLEX_FULL : DUPLEX_HALF; - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.supported, supported); - - } - - return 0; -} - -static int -smc911x_ethtool_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - unsigned long flags; - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); - spin_unlock_irqrestore(&lp->lock, flags); - } else { - if (cmd->base.autoneg != AUTONEG_DISABLE || - cmd->base.speed != SPEED_10 || - (cmd->base.duplex != DUPLEX_HALF && - cmd->base.duplex != DUPLEX_FULL) || - (cmd->base.port != PORT_TP && - cmd->base.port != PORT_AUI)) - return -EINVAL; - - lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; - - ret = 0; - } - - return ret; -} - -static void -smc911x_ethtool_getdrvinfo(struct net_device *dev, struct ethtool_drvinfo *info) -{ - strscpy(info->driver, CARDNAME, sizeof(info->driver)); - strscpy(info->version, version, sizeof(info->version)); - strscpy(info->bus_info, dev_name(dev->dev.parent), - sizeof(info->bus_info)); -} - -static int smc911x_ethtool_nwayreset(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret = -EINVAL; - unsigned long flags; - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - ret = mii_nway_restart(&lp->mii); - spin_unlock_irqrestore(&lp->lock, flags); - } - - return ret; -} - -static u32 smc911x_ethtool_getmsglevel(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - return lp->msg_enable; -} - -static void smc911x_ethtool_setmsglevel(struct net_device *dev, u32 level) -{ - struct smc911x_local *lp = netdev_priv(dev); - lp->msg_enable = level; -} - -static int smc911x_ethtool_getregslen(struct net_device *dev) -{ - /* System regs + MAC regs + PHY regs */ - return (((E2P_CMD - ID_REV)/4 + 1) + - (WUCSR - MAC_CR)+1 + 32) * sizeof(u32); -} - -static void smc911x_ethtool_getregs(struct net_device *dev, - struct ethtool_regs *regs, void *buf) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned long flags; - u32 reg,i,j=0; - u32 *data = (u32*)buf; - - regs->version = lp->version; - for(i=ID_REV;i<=E2P_CMD;i+=4) { - data[j++] = SMC_inl(lp, i); - } - for(i=MAC_CR;i<=WUCSR;i++) { - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CSR(lp, i, reg); - spin_unlock_irqrestore(&lp->lock, flags); - data[j++] = reg; - } - for(i=0;i<=31;i++) { - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MII(lp, i, lp->mii.phy_id, reg); - spin_unlock_irqrestore(&lp->lock, flags); - data[j++] = reg & 0xFFFF; - } -} - -static int smc911x_ethtool_wait_eeprom_ready(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int timeout; - int e2p_cmd; - - e2p_cmd = SMC_GET_E2P_CMD(lp); - for(timeout=10;(e2p_cmd & E2P_CMD_EPC_BUSY_) && timeout; timeout--) { - if (e2p_cmd & E2P_CMD_EPC_TIMEOUT_) { - PRINTK(dev, "%s timeout waiting for EEPROM to respond\n", - __func__); - return -EFAULT; - } - mdelay(1); - e2p_cmd = SMC_GET_E2P_CMD(lp); - } - if (timeout == 0) { - PRINTK(dev, "%s timeout waiting for EEPROM CMD not busy\n", - __func__); - return -ETIMEDOUT; - } - return 0; -} - -static inline int smc911x_ethtool_write_eeprom_cmd(struct net_device *dev, - int cmd, int addr) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - SMC_SET_E2P_CMD(lp, E2P_CMD_EPC_BUSY_ | - ((cmd) & (0x7<<28)) | - ((addr) & 0xFF)); - return 0; -} - -static inline int smc911x_ethtool_read_eeprom_byte(struct net_device *dev, - u8 *data) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - *data = SMC_GET_E2P_DATA(lp); - return 0; -} - -static inline int smc911x_ethtool_write_eeprom_byte(struct net_device *dev, - u8 data) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - SMC_SET_E2P_DATA(lp, data); - return 0; -} - -static int smc911x_ethtool_geteeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - u8 eebuf[SMC911X_EEPROM_LEN]; - int i, ret; - - for(i=0;i<SMC911X_EEPROM_LEN;i++) { - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_READ_, i ))!=0) - return ret; - if ((ret=smc911x_ethtool_read_eeprom_byte(dev, &eebuf[i]))!=0) - return ret; - } - memcpy(data, eebuf+eeprom->offset, eeprom->len); - return 0; -} - -static int smc911x_ethtool_seteeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - int i, ret; - - /* Enable erase */ - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_EWEN_, 0 ))!=0) - return ret; - for(i=eeprom->offset;i<(eeprom->offset+eeprom->len);i++) { - /* erase byte */ - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_ERASE_, i ))!=0) - return ret; - /* write byte */ - if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0) - return ret; - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0) - return ret; - } - return 0; -} - -static int smc911x_ethtool_geteeprom_len(struct net_device *dev) -{ - return SMC911X_EEPROM_LEN; -} - -static const struct ethtool_ops smc911x_ethtool_ops = { - .get_drvinfo = smc911x_ethtool_getdrvinfo, - .get_msglevel = smc911x_ethtool_getmsglevel, - .set_msglevel = smc911x_ethtool_setmsglevel, - .nway_reset = smc911x_ethtool_nwayreset, - .get_link = ethtool_op_get_link, - .get_regs_len = smc911x_ethtool_getregslen, - .get_regs = smc911x_ethtool_getregs, - .get_eeprom_len = smc911x_ethtool_geteeprom_len, - .get_eeprom = smc911x_ethtool_geteeprom, - .set_eeprom = smc911x_ethtool_seteeprom, - .get_link_ksettings = smc911x_ethtool_get_link_ksettings, - .set_link_ksettings = smc911x_ethtool_set_link_ksettings, -}; - -/* - * smc911x_findirq - * - * This routine has a simple purpose -- make the SMC chip generate an - * interrupt, so an auto-detect routine can detect it, and find the IRQ, - */ -static int smc911x_findirq(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int timeout = 20; - unsigned long cookie; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - cookie = probe_irq_on(); - - /* - * Force a SW interrupt - */ - - SMC_SET_INT_EN(lp, INT_EN_SW_INT_EN_); - - /* - * Wait until positive that the interrupt has been generated - */ - do { - int int_status; - udelay(10); - int_status = SMC_GET_INT_EN(lp); - if (int_status & INT_EN_SW_INT_EN_) - break; /* got the interrupt */ - } while (--timeout); - - /* - * there is really nothing that I can do here if timeout fails, - * as autoirq_report will return a 0 anyway, which is what I - * want in this case. Plus, the clean up is needed in both - * cases. - */ - - /* and disable all interrupts again */ - SMC_SET_INT_EN(lp, 0); - - /* and return what I found */ - return probe_irq_off(cookie); -} - -static const struct net_device_ops smc911x_netdev_ops = { - .ndo_open = smc911x_open, - .ndo_stop = smc911x_close, - .ndo_start_xmit = smc911x_hard_start_xmit, - .ndo_tx_timeout = smc911x_timeout, - .ndo_set_rx_mode = smc911x_set_multicast_list, - .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = eth_mac_addr, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = smc911x_poll_controller, -#endif -}; - -/* - * Function: smc911x_probe(unsigned long ioaddr) - * - * Purpose: - * Tests to see if a given ioaddr points to an SMC911x chip. - * Returns a 0 on success - * - * Algorithm: - * (1) see if the endian word is OK - * (1) see if I recognize the chip ID in the appropriate register - * - * Here I do typical initialization tasks. - * - * o Initialize the structure if needed - * o print out my vanity message if not done so already - * o print out what type of hardware is detected - * o print out the ethernet address - * o find the IRQ - * o set up my private data - * o configure the dev structure with my subroutines - * o actually GRAB the irq. - * o GRAB the region - */ -static int smc911x_probe(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int i, retval; - unsigned int val, chip_id, revision; - const char *version_string; - unsigned long irq_flags; -#ifdef SMC_USE_DMA - struct dma_slave_config config; - dma_cap_mask_t mask; -#endif - u8 addr[ETH_ALEN]; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* First, see if the endian word is recognized */ - val = SMC_GET_BYTE_TEST(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: endian probe returned 0x%04x\n", - CARDNAME, val); - if (val != 0x87654321) { - netdev_err(dev, "Invalid chip endian 0x%08x\n", val); - retval = -ENODEV; - goto err_out; - } - - /* - * check if the revision register is something that I - * recognize. These might need to be added to later, - * as future revisions could be added. - */ - chip_id = SMC_GET_PN(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: id probe returned 0x%04x\n", - CARDNAME, chip_id); - for(i=0;chip_ids[i].id != 0; i++) { - if (chip_ids[i].id == chip_id) break; - } - if (!chip_ids[i].id) { - netdev_err(dev, "Unknown chip ID %04x\n", chip_id); - retval = -ENODEV; - goto err_out; - } - version_string = chip_ids[i].name; - - revision = SMC_GET_REV(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: revision = 0x%04x\n", CARDNAME, revision); - - /* At this point I'll assume that the chip is an SMC911x. */ - DBG(SMC_DEBUG_MISC, dev, "%s: Found a %s\n", - CARDNAME, chip_ids[i].name); - - /* Validate the TX FIFO size requested */ - if ((tx_fifo_kb < 2) || (tx_fifo_kb > 14)) { - netdev_err(dev, "Invalid TX FIFO size requested %d\n", - tx_fifo_kb); - retval = -EINVAL; - goto err_out; - } - - /* fill in some of the fields */ - lp->version = chip_ids[i].id; - lp->revision = revision; - lp->tx_fifo_kb = tx_fifo_kb; - /* Reverse calculate the RX FIFO size from the TX */ - lp->tx_fifo_size=(lp->tx_fifo_kb<<10) - 512; - lp->rx_fifo_size= ((0x4000 - 512 - lp->tx_fifo_size) / 16) * 15; - - /* Set the automatic flow control values */ - switch(lp->tx_fifo_kb) { - /* - * AFC_HI is about ((Rx Data Fifo Size)*2/3)/64 - * AFC_LO is AFC_HI/2 - * BACK_DUR is about 5uS*(AFC_LO) rounded down - */ - case 2:/* 13440 Rx Data Fifo Size */ - lp->afc_cfg=0x008C46AF;break; - case 3:/* 12480 Rx Data Fifo Size */ - lp->afc_cfg=0x0082419F;break; - case 4:/* 11520 Rx Data Fifo Size */ - lp->afc_cfg=0x00783C9F;break; - case 5:/* 10560 Rx Data Fifo Size */ - lp->afc_cfg=0x006E374F;break; - case 6:/* 9600 Rx Data Fifo Size */ - lp->afc_cfg=0x0064328F;break; - case 7:/* 8640 Rx Data Fifo Size */ - lp->afc_cfg=0x005A2D7F;break; - case 8:/* 7680 Rx Data Fifo Size */ - lp->afc_cfg=0x0050287F;break; - case 9:/* 6720 Rx Data Fifo Size */ - lp->afc_cfg=0x0046236F;break; - case 10:/* 5760 Rx Data Fifo Size */ - lp->afc_cfg=0x003C1E6F;break; - case 11:/* 4800 Rx Data Fifo Size */ - lp->afc_cfg=0x0032195F;break; - /* - * AFC_HI is ~1520 bytes less than RX Data Fifo Size - * AFC_LO is AFC_HI/2 - * BACK_DUR is about 5uS*(AFC_LO) rounded down - */ - case 12:/* 3840 Rx Data Fifo Size */ - lp->afc_cfg=0x0024124F;break; - case 13:/* 2880 Rx Data Fifo Size */ - lp->afc_cfg=0x0015073F;break; - case 14:/* 1920 Rx Data Fifo Size */ - lp->afc_cfg=0x0006032F;break; - default: - PRINTK(dev, "ERROR -- no AFC_CFG setting found"); - break; - } - - DBG(SMC_DEBUG_MISC | SMC_DEBUG_TX | SMC_DEBUG_RX, dev, - "%s: tx_fifo %d rx_fifo %d afc_cfg 0x%08x\n", CARDNAME, - lp->tx_fifo_size, lp->rx_fifo_size, lp->afc_cfg); - - spin_lock_init(&lp->lock); - - /* Get the MAC address */ - SMC_GET_MAC_ADDR(lp, addr); - eth_hw_addr_set(dev, addr); - - /* now, reset the chip, and put it into a known state */ - smc911x_reset(dev); - - /* - * If dev->irq is 0, then the device has to be banged on to see - * what the IRQ is. - * - * Specifying an IRQ is done with the assumption that the user knows - * what (s)he is doing. No checking is done!!!! - */ - if (dev->irq < 1) { - int trials; - - trials = 3; - while (trials--) { - dev->irq = smc911x_findirq(dev); - if (dev->irq) - break; - /* kick the card and try again */ - smc911x_reset(dev); - } - } - if (dev->irq == 0) { - netdev_warn(dev, "Couldn't autodetect your IRQ. Use irq=xx.\n"); - retval = -ENODEV; - goto err_out; - } - dev->irq = irq_canonicalize(dev->irq); - - dev->netdev_ops = &smc911x_netdev_ops; - dev->watchdog_timeo = msecs_to_jiffies(watchdog); - dev->ethtool_ops = &smc911x_ethtool_ops; - - INIT_WORK(&lp->phy_configure, smc911x_phy_configure); - lp->mii.phy_id_mask = 0x1f; - lp->mii.reg_num_mask = 0x1f; - lp->mii.force_media = 0; - lp->mii.full_duplex = 0; - lp->mii.dev = dev; - lp->mii.mdio_read = smc911x_phy_read; - lp->mii.mdio_write = smc911x_phy_write; - - /* - * Locate the phy, if any. - */ - smc911x_phy_detect(dev); - - /* Set default parameters */ - lp->msg_enable = NETIF_MSG_LINK; - lp->ctl_rfduplx = 1; - lp->ctl_rspeed = 100; - -#ifdef SMC_DYNAMIC_BUS_CONFIG - irq_flags = lp->cfg.irq_flags; -#else - irq_flags = IRQF_SHARED | SMC_IRQ_SENSE; -#endif - - /* Grab the IRQ */ - retval = request_irq(dev->irq, smc911x_interrupt, - irq_flags, dev->name, dev); - if (retval) - goto err_out; - -#ifdef SMC_USE_DMA - - dma_cap_zero(mask); - dma_cap_set(DMA_SLAVE, mask); - lp->rxdma = dma_request_channel(mask, NULL, NULL); - lp->txdma = dma_request_channel(mask, NULL, NULL); - lp->rxdma_active = 0; - lp->txdma_active = 0; - - memset(&config, 0, sizeof(config)); - config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - config.src_addr = lp->physaddr + RX_DATA_FIFO; - config.dst_addr = lp->physaddr + TX_DATA_FIFO; - config.src_maxburst = 32; - config.dst_maxburst = 32; - retval = dmaengine_slave_config(lp->rxdma, &config); - if (retval) { - dev_err(lp->dev, "dma rx channel configuration failed: %d\n", - retval); - goto err_out; - } - retval = dmaengine_slave_config(lp->txdma, &config); - if (retval) { - dev_err(lp->dev, "dma tx channel configuration failed: %d\n", - retval); - goto err_out; - } -#endif - - retval = register_netdev(dev); - if (retval == 0) { - /* now, print out the card info, in a short format.. */ - netdev_info(dev, "%s (rev %d) at %#lx IRQ %d", - version_string, lp->revision, - dev->base_addr, dev->irq); - -#ifdef SMC_USE_DMA - if (lp->rxdma) - pr_cont(" RXDMA %p", lp->rxdma); - - if (lp->txdma) - pr_cont(" TXDMA %p", lp->txdma); -#endif - pr_cont("\n"); - if (!is_valid_ether_addr(dev->dev_addr)) { - netdev_warn(dev, "Invalid ethernet MAC address. Please set using ifconfig\n"); - } else { - /* Print the Ethernet address */ - netdev_info(dev, "Ethernet addr: %pM\n", - dev->dev_addr); - } - - if (lp->phy_type == 0) { - PRINTK(dev, "No PHY found\n"); - } else if ((lp->phy_type & ~0xff) == LAN911X_INTERNAL_PHY_ID) { - PRINTK(dev, "LAN911x Internal PHY\n"); - } else { - PRINTK(dev, "External PHY 0x%08x\n", lp->phy_type); - } - } - -err_out: -#ifdef SMC_USE_DMA - if (retval) { - if (lp->rxdma) - dma_release_channel(lp->rxdma); - if (lp->txdma) - dma_release_channel(lp->txdma); - } -#endif - return retval; -} - -/* - * smc911x_drv_probe(void) - * - * Output: - * 0 --> there is a device - * anything else, error - */ -static int smc911x_drv_probe(struct platform_device *pdev) -{ - struct net_device *ndev; - struct resource *res; - struct smc911x_local *lp; - void __iomem *addr; - int ret; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - ret = -ENODEV; - goto out; - } - - /* - * Request the regions. - */ - if (!request_mem_region(res->start, SMC911X_IO_EXTENT, CARDNAME)) { - ret = -EBUSY; - goto out; - } - - ndev = alloc_etherdev(sizeof(struct smc911x_local)); - if (!ndev) { - ret = -ENOMEM; - goto release_1; - } - SET_NETDEV_DEV(ndev, &pdev->dev); - - ndev->dma = (unsigned char)-1; - ndev->irq = platform_get_irq(pdev, 0); - if (ndev->irq < 0) { - ret = ndev->irq; - goto release_both; - } - - lp = netdev_priv(ndev); - lp->netdev = ndev; -#ifdef SMC_DYNAMIC_BUS_CONFIG - { - struct smc911x_platdata *pd = dev_get_platdata(&pdev->dev); - if (!pd) { - ret = -EINVAL; - goto release_both; - } - memcpy(&lp->cfg, pd, sizeof(lp->cfg)); - } -#endif - - addr = ioremap(res->start, SMC911X_IO_EXTENT); - if (!addr) { - ret = -ENOMEM; - goto release_both; - } - - platform_set_drvdata(pdev, ndev); - lp->base = addr; - ndev->base_addr = res->start; - ret = smc911x_probe(ndev); - if (ret != 0) { - iounmap(addr); -release_both: - free_netdev(ndev); -release_1: - release_mem_region(res->start, SMC911X_IO_EXTENT); -out: - pr_info("%s: not found (%d).\n", CARDNAME, ret); - } -#ifdef SMC_USE_DMA - else { - lp->physaddr = res->start; - lp->dev = &pdev->dev; - } -#endif - - return ret; -} - -static int smc911x_drv_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - struct smc911x_local *lp = netdev_priv(ndev); - struct resource *res; - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - - unregister_netdev(ndev); - - free_irq(ndev->irq, ndev); - -#ifdef SMC_USE_DMA - { - if (lp->rxdma) - dma_release_channel(lp->rxdma); - if (lp->txdma) - dma_release_channel(lp->txdma); - } -#endif - iounmap(lp->base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, SMC911X_IO_EXTENT); - - free_netdev(ndev); - return 0; -} - -static int smc911x_drv_suspend(struct platform_device *dev, pm_message_t state) -{ - struct net_device *ndev = platform_get_drvdata(dev); - struct smc911x_local *lp = netdev_priv(ndev); - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - if (ndev) { - if (netif_running(ndev)) { - netif_device_detach(ndev); - smc911x_shutdown(ndev); -#if POWER_DOWN - /* Set D2 - Energy detect only setting */ - SMC_SET_PMT_CTRL(lp, 2<<12); -#endif - } - } - return 0; -} - -static int smc911x_drv_resume(struct platform_device *dev) -{ - struct net_device *ndev = platform_get_drvdata(dev); - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - if (ndev) { - struct smc911x_local *lp = netdev_priv(ndev); - - if (netif_running(ndev)) { - smc911x_reset(ndev); - if (lp->phy_type != 0) - smc911x_phy_configure(&lp->phy_configure); - smc911x_enable(ndev); - netif_device_attach(ndev); - } - } - return 0; -} - -static struct platform_driver smc911x_driver = { - .probe = smc911x_drv_probe, - .remove = smc911x_drv_remove, - .suspend = smc911x_drv_suspend, - .resume = smc911x_drv_resume, - .driver = { - .name = CARDNAME, - }, -}; - -module_platform_driver(smc911x_driver); diff --git a/drivers/net/ethernet/smsc/smc911x.h b/drivers/net/ethernet/smsc/smc911x.h deleted file mode 100644 index d4edcc0da87c..000000000000 --- a/drivers/net/ethernet/smsc/smc911x.h +++ /dev/null @@ -1,901 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/*------------------------------------------------------------------------ - . smc911x.h - macros for SMSC's LAN911{5,6,7,8} single-chip Ethernet device. - . - . Copyright (C) 2005 Sensoria Corp. - . Derived from the unified SMC91x driver by Nicolas Pitre - . - . - . Information contained in this file was obtained from the LAN9118 - . manual from SMC. To get a copy, if you really want one, you can find - . information under www.smsc.com. - . - . Authors - . Dustin McIntire <dustin@sensoria.com> - . - ---------------------------------------------------------------------------*/ -#ifndef _SMC911X_H_ -#define _SMC911X_H_ - -#include <linux/smc911x.h> -/* - * Use the DMA feature on PXA chips - */ -#ifdef CONFIG_ARCH_PXA - #define SMC_USE_PXA_DMA 1 - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_FALLING -#elif defined(CONFIG_SH_MAGIC_PANEL_R2) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW -#elif defined(CONFIG_ARCH_OMAP3) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW - #define SMC_MEM_RESERVED 1 -#elif defined(CONFIG_ARCH_OMAP2) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW - #define SMC_MEM_RESERVED 1 -#else -/* - * Default configuration - */ - -#define SMC_DYNAMIC_BUS_CONFIG -#endif - -#ifdef SMC_USE_PXA_DMA -#define SMC_USE_DMA -#endif - -/* store this information for the driver.. */ -struct smc911x_local { - /* - * If I have to wait until the DMA is finished and ready to reload a - * packet, I will store the skbuff here. Then, the DMA will send it - * out and free it. - */ - struct sk_buff *pending_tx_skb; - - /* version/revision of the SMC911x chip */ - u16 version; - u16 revision; - - /* FIFO sizes */ - int tx_fifo_kb; - int tx_fifo_size; - int rx_fifo_size; - int afc_cfg; - - /* Contains the current active receive/phy mode */ - int ctl_rfduplx; - int ctl_rspeed; - - u32 msg_enable; - u32 phy_type; - struct mii_if_info mii; - - /* work queue */ - struct work_struct phy_configure; - - int tx_throttle; - spinlock_t lock; - - struct net_device *netdev; - -#ifdef SMC_USE_DMA - /* DMA needs the physical address of the chip */ - u_long physaddr; - struct dma_chan *rxdma; - struct dma_chan *txdma; - int rxdma_active; - int txdma_active; - struct sk_buff *current_rx_skb; - struct sk_buff *current_tx_skb; - struct device *dev; -#endif - void __iomem *base; -#ifdef SMC_DYNAMIC_BUS_CONFIG - struct smc911x_platdata cfg; -#endif -}; - -/* - * Define the bus width specific IO macros - */ - -#ifdef SMC_DYNAMIC_BUS_CONFIG -static inline unsigned int SMC_inl(struct smc911x_local *lp, int reg) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) - return readl(ioaddr); - - if (lp->cfg.flags & SMC911X_USE_16BIT) - return readw(ioaddr) | (readw(ioaddr + 2) << 16); - - BUG(); -} - -static inline void SMC_outl(unsigned int value, struct smc911x_local *lp, - int reg) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - writel(value, ioaddr); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - writew(value & 0xffff, ioaddr); - writew(value >> 16, ioaddr + 2); - return; - } - - BUG(); -} - -static inline void SMC_insl(struct smc911x_local *lp, int reg, - void *addr, unsigned int count) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - ioread32_rep(ioaddr, addr, count); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - ioread16_rep(ioaddr, addr, count * 2); - return; - } - - BUG(); -} - -static inline void SMC_outsl(struct smc911x_local *lp, int reg, - void *addr, unsigned int count) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - iowrite32_rep(ioaddr, addr, count); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - iowrite16_rep(ioaddr, addr, count * 2); - return; - } - - BUG(); -} -#else -#if SMC_USE_16BIT -#define SMC_inl(lp, r) ((readw((lp)->base + (r)) & 0xFFFF) + (readw((lp)->base + (r) + 2) << 16)) -#define SMC_outl(v, lp, r) \ - do{ \ - writew(v & 0xFFFF, (lp)->base + (r)); \ - writew(v >> 16, (lp)->base + (r) + 2); \ - } while (0) -#define SMC_insl(lp, r, p, l) ioread16_rep((short*)((lp)->base + (r)), p, l*2) -#define SMC_outsl(lp, r, p, l) iowrite16_rep((short*)((lp)->base + (r)), p, l*2) - -#elif SMC_USE_32BIT -#define SMC_inl(lp, r) readl((lp)->base + (r)) -#define SMC_outl(v, lp, r) writel(v, (lp)->base + (r)) -#define SMC_insl(lp, r, p, l) ioread32_rep((int*)((lp)->base + (r)), p, l) -#define SMC_outsl(lp, r, p, l) iowrite32_rep((int*)((lp)->base + (r)), p, l) - -#endif /* SMC_USE_16BIT */ -#endif /* SMC_DYNAMIC_BUS_CONFIG */ - - -#ifdef SMC_USE_PXA_DMA - -/* - * Use a DMA for RX and TX packets. - */ -#include <linux/dma-mapping.h> - -static dma_addr_t rx_dmabuf, tx_dmabuf; -static int rx_dmalen, tx_dmalen; -static void smc911x_rx_dma_irq(void *data); -static void smc911x_tx_dma_irq(void *data); - -#ifdef SMC_insl -#undef SMC_insl -#define SMC_insl(lp, r, p, l) \ - smc_pxa_dma_insl(lp, lp->physaddr, r, lp->rxdma, p, l) - -static inline void -smc_pxa_dma_insl(struct smc911x_local *lp, u_long physaddr, - int reg, struct dma_chan *dma, u_char *buf, int len) -{ - struct dma_async_tx_descriptor *tx; - - /* 64 bit alignment is required for memory to memory DMA */ - if ((long)buf & 4) { - *((u32 *)buf) = SMC_inl(lp, reg); - buf += 4; - len--; - } - - len *= 4; - rx_dmabuf = dma_map_single(lp->dev, buf, len, DMA_FROM_DEVICE); - rx_dmalen = len; - tx = dmaengine_prep_slave_single(dma, rx_dmabuf, rx_dmalen, - DMA_DEV_TO_MEM, 0); - if (tx) { - tx->callback = smc911x_rx_dma_irq; - tx->callback_param = lp; - dmaengine_submit(tx); - dma_async_issue_pending(dma); - } -} -#endif - -#ifdef SMC_outsl -#undef SMC_outsl -#define SMC_outsl(lp, r, p, l) \ - smc_pxa_dma_outsl(lp, lp->physaddr, r, lp->txdma, p, l) - -static inline void -smc_pxa_dma_outsl(struct smc911x_local *lp, u_long physaddr, - int reg, struct dma_chan *dma, u_char *buf, int len) -{ - struct dma_async_tx_descriptor *tx; - - /* 64 bit alignment is required for memory to memory DMA */ - if ((long)buf & 4) { - SMC_outl(*((u32 *)buf), lp, reg); - buf += 4; - len--; - } - - len *= 4; - tx_dmabuf = dma_map_single(lp->dev, buf, len, DMA_TO_DEVICE); - tx_dmalen = len; - tx = dmaengine_prep_slave_single(dma, tx_dmabuf, tx_dmalen, - DMA_DEV_TO_MEM, 0); - if (tx) { - tx->callback = smc911x_tx_dma_irq; - tx->callback_param = lp; - dmaengine_submit(tx); - dma_async_issue_pending(dma); - } -} -#endif -#endif /* SMC_USE_PXA_DMA */ - - -/* Chip Parameters and Register Definitions */ - -#define SMC911X_TX_FIFO_LOW_THRESHOLD (1536*2) - -#define SMC911X_IO_EXTENT 0x100 - -#define SMC911X_EEPROM_LEN 7 - -/* Below are the register offsets and bit definitions - * of the Lan911x memory space - */ -#define RX_DATA_FIFO (0x00) - -#define TX_DATA_FIFO (0x20) -#define TX_CMD_A_INT_ON_COMP_ (0x80000000) -#define TX_CMD_A_INT_BUF_END_ALGN_ (0x03000000) -#define TX_CMD_A_INT_4_BYTE_ALGN_ (0x00000000) -#define TX_CMD_A_INT_16_BYTE_ALGN_ (0x01000000) -#define TX_CMD_A_INT_32_BYTE_ALGN_ (0x02000000) -#define TX_CMD_A_INT_DATA_OFFSET_ (0x001F0000) -#define TX_CMD_A_INT_FIRST_SEG_ (0x00002000) -#define TX_CMD_A_INT_LAST_SEG_ (0x00001000) -#define TX_CMD_A_BUF_SIZE_ (0x000007FF) -#define TX_CMD_B_PKT_TAG_ (0xFFFF0000) -#define TX_CMD_B_ADD_CRC_DISABLE_ (0x00002000) -#define TX_CMD_B_DISABLE_PADDING_ (0x00001000) -#define TX_CMD_B_PKT_BYTE_LENGTH_ (0x000007FF) - -#define RX_STATUS_FIFO (0x40) -#define RX_STS_PKT_LEN_ (0x3FFF0000) -#define RX_STS_ES_ (0x00008000) -#define RX_STS_BCST_ (0x00002000) -#define RX_STS_LEN_ERR_ (0x00001000) -#define RX_STS_RUNT_ERR_ (0x00000800) -#define RX_STS_MCAST_ (0x00000400) -#define RX_STS_TOO_LONG_ (0x00000080) -#define RX_STS_COLL_ (0x00000040) -#define RX_STS_ETH_TYPE_ (0x00000020) -#define RX_STS_WDOG_TMT_ (0x00000010) -#define RX_STS_MII_ERR_ (0x00000008) -#define RX_STS_DRIBBLING_ (0x00000004) -#define RX_STS_CRC_ERR_ (0x00000002) -#define RX_STATUS_FIFO_PEEK (0x44) -#define TX_STATUS_FIFO (0x48) -#define TX_STS_TAG_ (0xFFFF0000) -#define TX_STS_ES_ (0x00008000) -#define TX_STS_LOC_ (0x00000800) -#define TX_STS_NO_CARR_ (0x00000400) -#define TX_STS_LATE_COLL_ (0x00000200) -#define TX_STS_MANY_COLL_ (0x00000100) -#define TX_STS_COLL_CNT_ (0x00000078) -#define TX_STS_MANY_DEFER_ (0x00000004) -#define TX_STS_UNDERRUN_ (0x00000002) -#define TX_STS_DEFERRED_ (0x00000001) -#define TX_STATUS_FIFO_PEEK (0x4C) -#define ID_REV (0x50) -#define ID_REV_CHIP_ID_ (0xFFFF0000) /* RO */ -#define ID_REV_REV_ID_ (0x0000FFFF) /* RO */ - -#define INT_CFG (0x54) -#define INT_CFG_INT_DEAS_ (0xFF000000) /* R/W */ -#define INT_CFG_INT_DEAS_CLR_ (0x00004000) -#define INT_CFG_INT_DEAS_STS_ (0x00002000) -#define INT_CFG_IRQ_INT_ (0x00001000) /* RO */ -#define INT_CFG_IRQ_EN_ (0x00000100) /* R/W */ -#define INT_CFG_IRQ_POL_ (0x00000010) /* R/W Not Affected by SW Reset */ -#define INT_CFG_IRQ_TYPE_ (0x00000001) /* R/W Not Affected by SW Reset */ - -#define INT_STS (0x58) -#define INT_STS_SW_INT_ (0x80000000) /* R/WC */ -#define INT_STS_TXSTOP_INT_ (0x02000000) /* R/WC */ -#define INT_STS_RXSTOP_INT_ (0x01000000) /* R/WC */ -#define INT_STS_RXDFH_INT_ (0x00800000) /* R/WC */ -#define INT_STS_RXDF_INT_ (0x00400000) /* R/WC */ -#define INT_STS_TX_IOC_ (0x00200000) /* R/WC */ -#define INT_STS_RXD_INT_ (0x00100000) /* R/WC */ -#define INT_STS_GPT_INT_ (0x00080000) /* R/WC */ -#define INT_STS_PHY_INT_ (0x00040000) /* RO */ -#define INT_STS_PME_INT_ (0x00020000) /* R/WC */ -#define INT_STS_TXSO_ (0x00010000) /* R/WC */ -#define INT_STS_RWT_ (0x00008000) /* R/WC */ -#define INT_STS_RXE_ (0x00004000) /* R/WC */ -#define INT_STS_TXE_ (0x00002000) /* R/WC */ -//#define INT_STS_ERX_ (0x00001000) /* R/WC */ -#define INT_STS_TDFU_ (0x00000800) /* R/WC */ -#define INT_STS_TDFO_ (0x00000400) /* R/WC */ -#define INT_STS_TDFA_ (0x00000200) /* R/WC */ -#define INT_STS_TSFF_ (0x00000100) /* R/WC */ -#define INT_STS_TSFL_ (0x00000080) /* R/WC */ -//#define INT_STS_RXDF_ (0x00000040) /* R/WC */ -#define INT_STS_RDFO_ (0x00000040) /* R/WC */ -#define INT_STS_RDFL_ (0x00000020) /* R/WC */ -#define INT_STS_RSFF_ (0x00000010) /* R/WC */ -#define INT_STS_RSFL_ (0x00000008) /* R/WC */ -#define INT_STS_GPIO2_INT_ (0x00000004) /* R/WC */ -#define INT_STS_GPIO1_INT_ (0x00000002) /* R/WC */ -#define INT_STS_GPIO0_INT_ (0x00000001) /* R/WC */ - -#define INT_EN (0x5C) -#define INT_EN_SW_INT_EN_ (0x80000000) /* R/W */ -#define INT_EN_TXSTOP_INT_EN_ (0x02000000) /* R/W */ -#define INT_EN_RXSTOP_INT_EN_ (0x01000000) /* R/W */ -#define INT_EN_RXDFH_INT_EN_ (0x00800000) /* R/W */ -//#define INT_EN_RXDF_INT_EN_ (0x00400000) /* R/W */ -#define INT_EN_TIOC_INT_EN_ (0x00200000) /* R/W */ -#define INT_EN_RXD_INT_EN_ (0x00100000) /* R/W */ -#define INT_EN_GPT_INT_EN_ (0x00080000) /* R/W */ -#define INT_EN_PHY_INT_EN_ (0x00040000) /* R/W */ -#define INT_EN_PME_INT_EN_ (0x00020000) /* R/W */ -#define INT_EN_TXSO_EN_ (0x00010000) /* R/W */ -#define INT_EN_RWT_EN_ (0x00008000) /* R/W */ -#define INT_EN_RXE_EN_ (0x00004000) /* R/W */ -#define INT_EN_TXE_EN_ (0x00002000) /* R/W */ -//#define INT_EN_ERX_EN_ (0x00001000) /* R/W */ -#define INT_EN_TDFU_EN_ (0x00000800) /* R/W */ -#define INT_EN_TDFO_EN_ (0x00000400) /* R/W */ -#define INT_EN_TDFA_EN_ (0x00000200) /* R/W */ -#define INT_EN_TSFF_EN_ (0x00000100) /* R/W */ -#define INT_EN_TSFL_EN_ (0x00000080) /* R/W */ -//#define INT_EN_RXDF_EN_ (0x00000040) /* R/W */ -#define INT_EN_RDFO_EN_ (0x00000040) /* R/W */ -#define INT_EN_RDFL_EN_ (0x00000020) /* R/W */ -#define INT_EN_RSFF_EN_ (0x00000010) /* R/W */ -#define INT_EN_RSFL_EN_ (0x00000008) /* R/W */ -#define INT_EN_GPIO2_INT_ (0x00000004) /* R/W */ -#define INT_EN_GPIO1_INT_ (0x00000002) /* R/W */ -#define INT_EN_GPIO0_INT_ (0x00000001) /* R/W */ - -#define BYTE_TEST (0x64) -#define FIFO_INT (0x68) -#define FIFO_INT_TX_AVAIL_LEVEL_ (0xFF000000) /* R/W */ -#define FIFO_INT_TX_STS_LEVEL_ (0x00FF0000) /* R/W */ -#define FIFO_INT_RX_AVAIL_LEVEL_ (0x0000FF00) /* R/W */ -#define FIFO_INT_RX_STS_LEVEL_ (0x000000FF) /* R/W */ - -#define RX_CFG (0x6C) -#define RX_CFG_RX_END_ALGN_ (0xC0000000) /* R/W */ -#define RX_CFG_RX_END_ALGN4_ (0x00000000) /* R/W */ -#define RX_CFG_RX_END_ALGN16_ (0x40000000) /* R/W */ -#define RX_CFG_RX_END_ALGN32_ (0x80000000) /* R/W */ -#define RX_CFG_RX_DMA_CNT_ (0x0FFF0000) /* R/W */ -#define RX_CFG_RX_DUMP_ (0x00008000) /* R/W */ -#define RX_CFG_RXDOFF_ (0x00001F00) /* R/W */ -//#define RX_CFG_RXBAD_ (0x00000001) /* R/W */ - -#define TX_CFG (0x70) -//#define TX_CFG_TX_DMA_LVL_ (0xE0000000) /* R/W */ -//#define TX_CFG_TX_DMA_CNT_ (0x0FFF0000) /* R/W Self Clearing */ -#define TX_CFG_TXS_DUMP_ (0x00008000) /* Self Clearing */ -#define TX_CFG_TXD_DUMP_ (0x00004000) /* Self Clearing */ -#define TX_CFG_TXSAO_ (0x00000004) /* R/W */ -#define TX_CFG_TX_ON_ (0x00000002) /* R/W */ -#define TX_CFG_STOP_TX_ (0x00000001) /* Self Clearing */ - -#define HW_CFG (0x74) -#define HW_CFG_TTM_ (0x00200000) /* R/W */ -#define HW_CFG_SF_ (0x00100000) /* R/W */ -#define HW_CFG_TX_FIF_SZ_ (0x000F0000) /* R/W */ -#define HW_CFG_TR_ (0x00003000) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_ (0x00000060) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_INT_PHY_ (0x00000000) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_EXT_PHY_ (0x00000020) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_CLK_DIS_ (0x00000040) /* R/W */ -#define HW_CFG_SMI_SEL_ (0x00000010) /* R/W */ -#define HW_CFG_EXT_PHY_DET_ (0x00000008) /* RO */ -#define HW_CFG_EXT_PHY_EN_ (0x00000004) /* R/W */ -#define HW_CFG_32_16_BIT_MODE_ (0x00000004) /* RO */ -#define HW_CFG_SRST_TO_ (0x00000002) /* RO */ -#define HW_CFG_SRST_ (0x00000001) /* Self Clearing */ - -#define RX_DP_CTRL (0x78) -#define RX_DP_CTRL_RX_FFWD_ (0x80000000) /* R/W */ -#define RX_DP_CTRL_FFWD_BUSY_ (0x80000000) /* RO */ - -#define RX_FIFO_INF (0x7C) -#define RX_FIFO_INF_RXSUSED_ (0x00FF0000) /* RO */ -#define RX_FIFO_INF_RXDUSED_ (0x0000FFFF) /* RO */ - -#define TX_FIFO_INF (0x80) -#define TX_FIFO_INF_TSUSED_ (0x00FF0000) /* RO */ -#define TX_FIFO_INF_TDFREE_ (0x0000FFFF) /* RO */ - -#define PMT_CTRL (0x84) -#define PMT_CTRL_PM_MODE_ (0x00003000) /* Self Clearing */ -#define PMT_CTRL_PHY_RST_ (0x00000400) /* Self Clearing */ -#define PMT_CTRL_WOL_EN_ (0x00000200) /* R/W */ -#define PMT_CTRL_ED_EN_ (0x00000100) /* R/W */ -#define PMT_CTRL_PME_TYPE_ (0x00000040) /* R/W Not Affected by SW Reset */ -#define PMT_CTRL_WUPS_ (0x00000030) /* R/WC */ -#define PMT_CTRL_WUPS_NOWAKE_ (0x00000000) /* R/WC */ -#define PMT_CTRL_WUPS_ED_ (0x00000010) /* R/WC */ -#define PMT_CTRL_WUPS_WOL_ (0x00000020) /* R/WC */ -#define PMT_CTRL_WUPS_MULTI_ (0x00000030) /* R/WC */ -#define PMT_CTRL_PME_IND_ (0x00000008) /* R/W */ -#define PMT_CTRL_PME_POL_ (0x00000004) /* R/W */ -#define PMT_CTRL_PME_EN_ (0x00000002) /* R/W Not Affected by SW Reset */ -#define PMT_CTRL_READY_ (0x00000001) /* RO */ - -#define GPIO_CFG (0x88) -#define GPIO_CFG_LED3_EN_ (0x40000000) /* R/W */ -#define GPIO_CFG_LED2_EN_ (0x20000000) /* R/W */ -#define GPIO_CFG_LED1_EN_ (0x10000000) /* R/W */ -#define GPIO_CFG_GPIO2_INT_POL_ (0x04000000) /* R/W */ -#define GPIO_CFG_GPIO1_INT_POL_ (0x02000000) /* R/W */ -#define GPIO_CFG_GPIO0_INT_POL_ (0x01000000) /* R/W */ -#define GPIO_CFG_EEPR_EN_ (0x00700000) /* R/W */ -#define GPIO_CFG_GPIOBUF2_ (0x00040000) /* R/W */ -#define GPIO_CFG_GPIOBUF1_ (0x00020000) /* R/W */ -#define GPIO_CFG_GPIOBUF0_ (0x00010000) /* R/W */ -#define GPIO_CFG_GPIODIR2_ (0x00000400) /* R/W */ -#define GPIO_CFG_GPIODIR1_ (0x00000200) /* R/W */ -#define GPIO_CFG_GPIODIR0_ (0x00000100) /* R/W */ -#define GPIO_CFG_GPIOD4_ (0x00000010) /* R/W */ -#define GPIO_CFG_GPIOD3_ (0x00000008) /* R/W */ -#define GPIO_CFG_GPIOD2_ (0x00000004) /* R/W */ -#define GPIO_CFG_GPIOD1_ (0x00000002) /* R/W */ -#define GPIO_CFG_GPIOD0_ (0x00000001) /* R/W */ - -#define GPT_CFG (0x8C) -#define GPT_CFG_TIMER_EN_ (0x20000000) /* R/W */ -#define GPT_CFG_GPT_LOAD_ (0x0000FFFF) /* R/W */ - -#define GPT_CNT (0x90) -#define GPT_CNT_GPT_CNT_ (0x0000FFFF) /* RO */ - -#define ENDIAN (0x98) -#define FREE_RUN (0x9C) -#define RX_DROP (0xA0) -#define MAC_CSR_CMD (0xA4) -#define MAC_CSR_CMD_CSR_BUSY_ (0x80000000) /* Self Clearing */ -#define MAC_CSR_CMD_R_NOT_W_ (0x40000000) /* R/W */ -#define MAC_CSR_CMD_CSR_ADDR_ (0x000000FF) /* R/W */ - -#define MAC_CSR_DATA (0xA8) -#define AFC_CFG (0xAC) -#define AFC_CFG_AFC_HI_ (0x00FF0000) /* R/W */ -#define AFC_CFG_AFC_LO_ (0x0000FF00) /* R/W */ -#define AFC_CFG_BACK_DUR_ (0x000000F0) /* R/W */ -#define AFC_CFG_FCMULT_ (0x00000008) /* R/W */ -#define AFC_CFG_FCBRD_ (0x00000004) /* R/W */ -#define AFC_CFG_FCADD_ (0x00000002) /* R/W */ -#define AFC_CFG_FCANY_ (0x00000001) /* R/W */ - -#define E2P_CMD (0xB0) -#define E2P_CMD_EPC_BUSY_ (0x80000000) /* Self Clearing */ -#define E2P_CMD_EPC_CMD_ (0x70000000) /* R/W */ -#define E2P_CMD_EPC_CMD_READ_ (0x00000000) /* R/W */ -#define E2P_CMD_EPC_CMD_EWDS_ (0x10000000) /* R/W */ -#define E2P_CMD_EPC_CMD_EWEN_ (0x20000000) /* R/W */ -#define E2P_CMD_EPC_CMD_WRITE_ (0x30000000) /* R/W */ -#define E2P_CMD_EPC_CMD_WRAL_ (0x40000000) /* R/W */ -#define E2P_CMD_EPC_CMD_ERASE_ (0x50000000) /* R/W */ -#define E2P_CMD_EPC_CMD_ERAL_ (0x60000000) /* R/W */ -#define E2P_CMD_EPC_CMD_RELOAD_ (0x70000000) /* R/W */ -#define E2P_CMD_EPC_TIMEOUT_ (0x00000200) /* RO */ -#define E2P_CMD_MAC_ADDR_LOADED_ (0x00000100) /* RO */ -#define E2P_CMD_EPC_ADDR_ (0x000000FF) /* R/W */ - -#define E2P_DATA (0xB4) -#define E2P_DATA_EEPROM_DATA_ (0x000000FF) /* R/W */ -/* end of LAN register offsets and bit definitions */ - -/* - **************************************************************************** - **************************************************************************** - * MAC Control and Status Register (Indirect Address) - * Offset (through the MAC_CSR CMD and DATA port) - **************************************************************************** - **************************************************************************** - * - */ -#define MAC_CR (0x01) /* R/W */ - -/* MAC_CR - MAC Control Register */ -#define MAC_CR_RXALL_ (0x80000000) -// TODO: delete this bit? It is not described in the data sheet. -#define MAC_CR_HBDIS_ (0x10000000) -#define MAC_CR_RCVOWN_ (0x00800000) -#define MAC_CR_LOOPBK_ (0x00200000) -#define MAC_CR_FDPX_ (0x00100000) -#define MAC_CR_MCPAS_ (0x00080000) -#define MAC_CR_PRMS_ (0x00040000) -#define MAC_CR_INVFILT_ (0x00020000) -#define MAC_CR_PASSBAD_ (0x00010000) -#define MAC_CR_HFILT_ (0x00008000) -#define MAC_CR_HPFILT_ (0x00002000) -#define MAC_CR_LCOLL_ (0x00001000) -#define MAC_CR_BCAST_ (0x00000800) -#define MAC_CR_DISRTY_ (0x00000400) -#define MAC_CR_PADSTR_ (0x00000100) -#define MAC_CR_BOLMT_MASK_ (0x000000C0) -#define MAC_CR_DFCHK_ (0x00000020) -#define MAC_CR_TXEN_ (0x00000008) -#define MAC_CR_RXEN_ (0x00000004) - -#define ADDRH (0x02) /* R/W mask 0x0000FFFFUL */ -#define ADDRL (0x03) /* R/W mask 0xFFFFFFFFUL */ -#define HASHH (0x04) /* R/W */ -#define HASHL (0x05) /* R/W */ - -#define MII_ACC (0x06) /* R/W */ -#define MII_ACC_PHY_ADDR_ (0x0000F800) -#define MII_ACC_MIIRINDA_ (0x000007C0) -#define MII_ACC_MII_WRITE_ (0x00000002) -#define MII_ACC_MII_BUSY_ (0x00000001) - -#define MII_DATA (0x07) /* R/W mask 0x0000FFFFUL */ - -#define FLOW (0x08) /* R/W */ -#define FLOW_FCPT_ (0xFFFF0000) -#define FLOW_FCPASS_ (0x00000004) -#define FLOW_FCEN_ (0x00000002) -#define FLOW_FCBSY_ (0x00000001) - -#define VLAN1 (0x09) /* R/W mask 0x0000FFFFUL */ -#define VLAN1_VTI1_ (0x0000ffff) - -#define VLAN2 (0x0A) /* R/W mask 0x0000FFFFUL */ -#define VLAN2_VTI2_ (0x0000ffff) - -#define WUFF (0x0B) /* WO */ - -#define WUCSR (0x0C) /* R/W */ -#define WUCSR_GUE_ (0x00000200) -#define WUCSR_WUFR_ (0x00000040) -#define WUCSR_MPR_ (0x00000020) -#define WUCSR_WAKE_EN_ (0x00000004) -#define WUCSR_MPEN_ (0x00000002) - -/* - **************************************************************************** - * Chip Specific MII Defines - **************************************************************************** - * - * Phy register offsets and bit definitions - * - */ - -#define PHY_MODE_CTRL_STS ((u32)17) /* Mode Control/Status Register */ -//#define MODE_CTRL_STS_FASTRIP_ ((u16)0x4000) -#define MODE_CTRL_STS_EDPWRDOWN_ ((u16)0x2000) -//#define MODE_CTRL_STS_LOWSQEN_ ((u16)0x0800) -//#define MODE_CTRL_STS_MDPREBP_ ((u16)0x0400) -//#define MODE_CTRL_STS_FARLOOPBACK_ ((u16)0x0200) -//#define MODE_CTRL_STS_FASTEST_ ((u16)0x0100) -//#define MODE_CTRL_STS_REFCLKEN_ ((u16)0x0010) -//#define MODE_CTRL_STS_PHYADBP_ ((u16)0x0008) -//#define MODE_CTRL_STS_FORCE_G_LINK_ ((u16)0x0004) -#define MODE_CTRL_STS_ENERGYON_ ((u16)0x0002) - -#define PHY_INT_SRC ((u32)29) -#define PHY_INT_SRC_ENERGY_ON_ ((u16)0x0080) -#define PHY_INT_SRC_ANEG_COMP_ ((u16)0x0040) -#define PHY_INT_SRC_REMOTE_FAULT_ ((u16)0x0020) -#define PHY_INT_SRC_LINK_DOWN_ ((u16)0x0010) -#define PHY_INT_SRC_ANEG_LP_ACK_ ((u16)0x0008) -#define PHY_INT_SRC_PAR_DET_FAULT_ ((u16)0x0004) -#define PHY_INT_SRC_ANEG_PGRX_ ((u16)0x0002) - -#define PHY_INT_MASK ((u32)30) -#define PHY_INT_MASK_ENERGY_ON_ ((u16)0x0080) -#define PHY_INT_MASK_ANEG_COMP_ ((u16)0x0040) -#define PHY_INT_MASK_REMOTE_FAULT_ ((u16)0x0020) -#define PHY_INT_MASK_LINK_DOWN_ ((u16)0x0010) -#define PHY_INT_MASK_ANEG_LP_ACK_ ((u16)0x0008) -#define PHY_INT_MASK_PAR_DET_FAULT_ ((u16)0x0004) -#define PHY_INT_MASK_ANEG_PGRX_ ((u16)0x0002) - -#define PHY_SPECIAL ((u32)31) -#define PHY_SPECIAL_ANEG_DONE_ ((u16)0x1000) -#define PHY_SPECIAL_RES_ ((u16)0x0040) -#define PHY_SPECIAL_RES_MASK_ ((u16)0x0FE1) -#define PHY_SPECIAL_SPD_ ((u16)0x001C) -#define PHY_SPECIAL_SPD_10HALF_ ((u16)0x0004) -#define PHY_SPECIAL_SPD_10FULL_ ((u16)0x0014) -#define PHY_SPECIAL_SPD_100HALF_ ((u16)0x0008) -#define PHY_SPECIAL_SPD_100FULL_ ((u16)0x0018) - -#define LAN911X_INTERNAL_PHY_ID (0x0007C000) - -/* Chip ID values */ -#define CHIP_9115 0x0115 -#define CHIP_9116 0x0116 -#define CHIP_9117 0x0117 -#define CHIP_9118 0x0118 -#define CHIP_9211 0x9211 -#define CHIP_9215 0x115A -#define CHIP_9217 0x117A -#define CHIP_9218 0x118A - -struct chip_id { - u16 id; - char *name; -}; - -static const struct chip_id chip_ids[] = { - { CHIP_9115, "LAN9115" }, - { CHIP_9116, "LAN9116" }, - { CHIP_9117, "LAN9117" }, - { CHIP_9118, "LAN9118" }, - { CHIP_9211, "LAN9211" }, - { CHIP_9215, "LAN9215" }, - { CHIP_9217, "LAN9217" }, - { CHIP_9218, "LAN9218" }, - { 0, NULL }, -}; - -#define IS_REV_A(x) ((x & 0xFFFF)==0) - -/* - * Macros to abstract register access according to the data bus - * capabilities. Please use those and not the in/out primitives. - */ -/* FIFO read/write macros */ -#define SMC_PUSH_DATA(lp, p, l) SMC_outsl( lp, TX_DATA_FIFO, p, (l) >> 2 ) -#define SMC_PULL_DATA(lp, p, l) SMC_insl ( lp, RX_DATA_FIFO, p, (l) >> 2 ) -#define SMC_SET_TX_FIFO(lp, x) SMC_outl( x, lp, TX_DATA_FIFO ) -#define SMC_GET_RX_FIFO(lp) SMC_inl( lp, RX_DATA_FIFO ) - - -/* I/O mapped register read/write macros */ -#define SMC_GET_TX_STS_FIFO(lp) SMC_inl( lp, TX_STATUS_FIFO ) -#define SMC_GET_RX_STS_FIFO(lp) SMC_inl( lp, RX_STATUS_FIFO ) -#define SMC_GET_RX_STS_FIFO_PEEK(lp) SMC_inl( lp, RX_STATUS_FIFO_PEEK ) -#define SMC_GET_PN(lp) (SMC_inl( lp, ID_REV ) >> 16) -#define SMC_GET_REV(lp) (SMC_inl( lp, ID_REV ) & 0xFFFF) -#define SMC_GET_IRQ_CFG(lp) SMC_inl( lp, INT_CFG ) -#define SMC_SET_IRQ_CFG(lp, x) SMC_outl( x, lp, INT_CFG ) -#define SMC_GET_INT(lp) SMC_inl( lp, INT_STS ) -#define SMC_ACK_INT(lp, x) SMC_outl( x, lp, INT_STS ) -#define SMC_GET_INT_EN(lp) SMC_inl( lp, INT_EN ) -#define SMC_SET_INT_EN(lp, x) SMC_outl( x, lp, INT_EN ) -#define SMC_GET_BYTE_TEST(lp) SMC_inl( lp, BYTE_TEST ) -#define SMC_SET_BYTE_TEST(lp, x) SMC_outl( x, lp, BYTE_TEST ) -#define SMC_GET_FIFO_INT(lp) SMC_inl( lp, FIFO_INT ) -#define SMC_SET_FIFO_INT(lp, x) SMC_outl( x, lp, FIFO_INT ) -#define SMC_SET_FIFO_TDA(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<24); \ - SMC_SET_FIFO_INT( (lp), __mask | (x)<<24 ); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_TSL(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<16); \ - SMC_SET_FIFO_INT( (lp), __mask | (((x) & 0xFF)<<16)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_RSA(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<8); \ - SMC_SET_FIFO_INT( (lp), __mask | (((x) & 0xFF)<<8)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_RSL(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~0xFF; \ - SMC_SET_FIFO_INT( (lp),__mask | ((x) & 0xFF)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_GET_RX_CFG(lp) SMC_inl( lp, RX_CFG ) -#define SMC_SET_RX_CFG(lp, x) SMC_outl( x, lp, RX_CFG ) -#define SMC_GET_TX_CFG(lp) SMC_inl( lp, TX_CFG ) -#define SMC_SET_TX_CFG(lp, x) SMC_outl( x, lp, TX_CFG ) -#define SMC_GET_HW_CFG(lp) SMC_inl( lp, HW_CFG ) -#define SMC_SET_HW_CFG(lp, x) SMC_outl( x, lp, HW_CFG ) -#define SMC_GET_RX_DP_CTRL(lp) SMC_inl( lp, RX_DP_CTRL ) -#define SMC_SET_RX_DP_CTRL(lp, x) SMC_outl( x, lp, RX_DP_CTRL ) -#define SMC_GET_PMT_CTRL(lp) SMC_inl( lp, PMT_CTRL ) -#define SMC_SET_PMT_CTRL(lp, x) SMC_outl( x, lp, PMT_CTRL ) -#define SMC_GET_GPIO_CFG(lp) SMC_inl( lp, GPIO_CFG ) -#define SMC_SET_GPIO_CFG(lp, x) SMC_outl( x, lp, GPIO_CFG ) -#define SMC_GET_RX_FIFO_INF(lp) SMC_inl( lp, RX_FIFO_INF ) -#define SMC_SET_RX_FIFO_INF(lp, x) SMC_outl( x, lp, RX_FIFO_INF ) -#define SMC_GET_TX_FIFO_INF(lp) SMC_inl( lp, TX_FIFO_INF ) -#define SMC_SET_TX_FIFO_INF(lp, x) SMC_outl( x, lp, TX_FIFO_INF ) -#define SMC_GET_GPT_CFG(lp) SMC_inl( lp, GPT_CFG ) -#define SMC_SET_GPT_CFG(lp, x) SMC_outl( x, lp, GPT_CFG ) -#define SMC_GET_RX_DROP(lp) SMC_inl( lp, RX_DROP ) -#define SMC_SET_RX_DROP(lp, x) SMC_outl( x, lp, RX_DROP ) -#define SMC_GET_MAC_CMD(lp) SMC_inl( lp, MAC_CSR_CMD ) -#define SMC_SET_MAC_CMD(lp, x) SMC_outl( x, lp, MAC_CSR_CMD ) -#define SMC_GET_MAC_DATA(lp) SMC_inl( lp, MAC_CSR_DATA ) -#define SMC_SET_MAC_DATA(lp, x) SMC_outl( x, lp, MAC_CSR_DATA ) -#define SMC_GET_AFC_CFG(lp) SMC_inl( lp, AFC_CFG ) -#define SMC_SET_AFC_CFG(lp, x) SMC_outl( x, lp, AFC_CFG ) -#define SMC_GET_E2P_CMD(lp) SMC_inl( lp, E2P_CMD ) -#define SMC_SET_E2P_CMD(lp, x) SMC_outl( x, lp, E2P_CMD ) -#define SMC_GET_E2P_DATA(lp) SMC_inl( lp, E2P_DATA ) -#define SMC_SET_E2P_DATA(lp, x) SMC_outl( x, lp, E2P_DATA ) - -/* MAC register read/write macros */ -#define SMC_GET_MAC_CSR(lp,a,v) \ - do { \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_CMD((lp),MAC_CSR_CMD_CSR_BUSY_ | \ - MAC_CSR_CMD_R_NOT_W_ | (a) ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - v = SMC_GET_MAC_DATA((lp)); \ - } while (0) -#define SMC_SET_MAC_CSR(lp,a,v) \ - do { \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_DATA((lp), v); \ - SMC_SET_MAC_CMD((lp), MAC_CSR_CMD_CSR_BUSY_ | (a) ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - } while (0) -#define SMC_GET_MAC_CR(lp, x) SMC_GET_MAC_CSR( (lp), MAC_CR, x ) -#define SMC_SET_MAC_CR(lp, x) SMC_SET_MAC_CSR( (lp), MAC_CR, x ) -#define SMC_GET_ADDRH(lp, x) SMC_GET_MAC_CSR( (lp), ADDRH, x ) -#define SMC_SET_ADDRH(lp, x) SMC_SET_MAC_CSR( (lp), ADDRH, x ) -#define SMC_GET_ADDRL(lp, x) SMC_GET_MAC_CSR( (lp), ADDRL, x ) -#define SMC_SET_ADDRL(lp, x) SMC_SET_MAC_CSR( (lp), ADDRL, x ) -#define SMC_GET_HASHH(lp, x) SMC_GET_MAC_CSR( (lp), HASHH, x ) -#define SMC_SET_HASHH(lp, x) SMC_SET_MAC_CSR( (lp), HASHH, x ) -#define SMC_GET_HASHL(lp, x) SMC_GET_MAC_CSR( (lp), HASHL, x ) -#define SMC_SET_HASHL(lp, x) SMC_SET_MAC_CSR( (lp), HASHL, x ) -#define SMC_GET_MII_ACC(lp, x) SMC_GET_MAC_CSR( (lp), MII_ACC, x ) -#define SMC_SET_MII_ACC(lp, x) SMC_SET_MAC_CSR( (lp), MII_ACC, x ) -#define SMC_GET_MII_DATA(lp, x) SMC_GET_MAC_CSR( (lp), MII_DATA, x ) -#define SMC_SET_MII_DATA(lp, x) SMC_SET_MAC_CSR( (lp), MII_DATA, x ) -#define SMC_GET_FLOW(lp, x) SMC_GET_MAC_CSR( (lp), FLOW, x ) -#define SMC_SET_FLOW(lp, x) SMC_SET_MAC_CSR( (lp), FLOW, x ) -#define SMC_GET_VLAN1(lp, x) SMC_GET_MAC_CSR( (lp), VLAN1, x ) -#define SMC_SET_VLAN1(lp, x) SMC_SET_MAC_CSR( (lp), VLAN1, x ) -#define SMC_GET_VLAN2(lp, x) SMC_GET_MAC_CSR( (lp), VLAN2, x ) -#define SMC_SET_VLAN2(lp, x) SMC_SET_MAC_CSR( (lp), VLAN2, x ) -#define SMC_SET_WUFF(lp, x) SMC_SET_MAC_CSR( (lp), WUFF, x ) -#define SMC_GET_WUCSR(lp, x) SMC_GET_MAC_CSR( (lp), WUCSR, x ) -#define SMC_SET_WUCSR(lp, x) SMC_SET_MAC_CSR( (lp), WUCSR, x ) - -/* PHY register read/write macros */ -#define SMC_GET_MII(lp,a,phy,v) \ - do { \ - u32 __v; \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_SET_MII_ACC( (lp), ((phy)<<11) | ((a)<<6) | \ - MII_ACC_MII_BUSY_); \ - do { \ - SMC_GET_MII_ACC( (lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_GET_MII_DATA((lp), v); \ - } while (0) -#define SMC_SET_MII(lp,a,phy,v) \ - do { \ - u32 __v; \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_SET_MII_DATA((lp), v); \ - SMC_SET_MII_ACC( (lp), ((phy)<<11) | ((a)<<6) | \ - MII_ACC_MII_BUSY_ | \ - MII_ACC_MII_WRITE_ ); \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - } while (0) -#define SMC_GET_PHY_BMCR(lp,phy,x) SMC_GET_MII( (lp), MII_BMCR, phy, x ) -#define SMC_SET_PHY_BMCR(lp,phy,x) SMC_SET_MII( (lp), MII_BMCR, phy, x ) -#define SMC_GET_PHY_BMSR(lp,phy,x) SMC_GET_MII( (lp), MII_BMSR, phy, x ) -#define SMC_GET_PHY_ID1(lp,phy,x) SMC_GET_MII( (lp), MII_PHYSID1, phy, x ) -#define SMC_GET_PHY_ID2(lp,phy,x) SMC_GET_MII( (lp), MII_PHYSID2, phy, x ) -#define SMC_GET_PHY_MII_ADV(lp,phy,x) SMC_GET_MII( (lp), MII_ADVERTISE, phy, x ) -#define SMC_SET_PHY_MII_ADV(lp,phy,x) SMC_SET_MII( (lp), MII_ADVERTISE, phy, x ) -#define SMC_GET_PHY_MII_LPA(lp,phy,x) SMC_GET_MII( (lp), MII_LPA, phy, x ) -#define SMC_SET_PHY_MII_LPA(lp,phy,x) SMC_SET_MII( (lp), MII_LPA, phy, x ) -#define SMC_GET_PHY_CTRL_STS(lp,phy,x) SMC_GET_MII( (lp), PHY_MODE_CTRL_STS, phy, x ) -#define SMC_SET_PHY_CTRL_STS(lp,phy,x) SMC_SET_MII( (lp), PHY_MODE_CTRL_STS, phy, x ) -#define SMC_GET_PHY_INT_SRC(lp,phy,x) SMC_GET_MII( (lp), PHY_INT_SRC, phy, x ) -#define SMC_SET_PHY_INT_SRC(lp,phy,x) SMC_SET_MII( (lp), PHY_INT_SRC, phy, x ) -#define SMC_GET_PHY_INT_MASK(lp,phy,x) SMC_GET_MII( (lp), PHY_INT_MASK, phy, x ) -#define SMC_SET_PHY_INT_MASK(lp,phy,x) SMC_SET_MII( (lp), PHY_INT_MASK, phy, x ) -#define SMC_GET_PHY_SPECIAL(lp,phy,x) SMC_GET_MII( (lp), PHY_SPECIAL, phy, x ) - - - -/* Misc read/write macros */ - -#ifndef SMC_GET_MAC_ADDR -#define SMC_GET_MAC_ADDR(lp, addr) \ - do { \ - unsigned int __v; \ - \ - SMC_GET_MAC_CSR((lp), ADDRL, __v); \ - addr[0] = __v; addr[1] = __v >> 8; \ - addr[2] = __v >> 16; addr[3] = __v >> 24; \ - SMC_GET_MAC_CSR((lp), ADDRH, __v); \ - addr[4] = __v; addr[5] = __v >> 8; \ - } while (0) -#endif - -#define SMC_SET_MAC_ADDR(lp, addr) \ - do { \ - SMC_SET_MAC_CSR((lp), ADDRL, \ - addr[0] | \ - (addr[1] << 8) | \ - (addr[2] << 16) | \ - (addr[3] << 24)); \ - SMC_SET_MAC_CSR((lp), ADDRH, addr[4]|(addr[5] << 8));\ - } while (0) - - -#define SMC_WRITE_EEPROM_CMD(lp, cmd, addr) \ - do { \ - while (SMC_GET_E2P_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_CMD((lp), MAC_CSR_CMD_R_NOT_W_ | a ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - } while (0) - -#endif /* _SMC911X_H_ */ diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index d2c6a5dfdc0e..492c39c08af1 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1508,16 +1508,16 @@ static void ave_get_stats64(struct net_device *ndev, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&priv->stats_rx.syncp); + start = u64_stats_fetch_begin(&priv->stats_rx.syncp); stats->rx_packets = priv->stats_rx.packets; stats->rx_bytes = priv->stats_rx.bytes; - } while (u64_stats_fetch_retry_irq(&priv->stats_rx.syncp, start)); + } while (u64_stats_fetch_retry(&priv->stats_rx.syncp, start)); do { - start = u64_stats_fetch_begin_irq(&priv->stats_tx.syncp); + start = u64_stats_fetch_begin(&priv->stats_tx.syncp); stats->tx_packets = priv->stats_tx.packets; stats->tx_bytes = priv->stats_tx.bytes; - } while (u64_stats_fetch_retry_irq(&priv->stats_tx.syncp, start)); + } while (u64_stats_fetch_retry(&priv->stats_tx.syncp, start)); stats->rx_errors = priv->stats_rx.errors; stats->tx_errors = priv->stats_tx.errors; @@ -1766,12 +1766,6 @@ static int ave_resume(struct device *dev) wol.wolopts = priv->wolopts; __ave_ethtool_set_wol(ndev, &wol); - if (ndev->phydev) { - ret = phy_resume(ndev->phydev); - if (ret) - return ret; - } - if (netif_running(ndev)) { ret = ave_open(ndev); netif_device_attach(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 31ff35174034..f77511fe4e87 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -235,6 +235,15 @@ config DWMAC_INTEL_PLAT the stmmac device driver. This driver is used for the Intel Keem Bay SoC. +config DWMAC_TEGRA + tristate "NVIDIA Tegra MGBE support" + depends on ARCH_TEGRA || COMPILE_TEST + help + This selects the Multi-GigaBit Ethernet (MGBE) Controller that is + found on the NVIDIA Tegra SoC devices. This driver provides the glue + layer on top of the stmmac driver required for these NVIDIA Tegra SoC + devices. + config DWMAC_VISCONTI tristate "Toshiba Visconti DWMAC support" default ARCH_VISCONTI diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index d4e12e9ace4f..057e4bab5c08 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_DWMAC_DWC_QOS_ETH) += dwmac-dwc-qos-eth.o obj-$(CONFIG_DWMAC_INTEL_PLAT) += dwmac-intel-plat.o obj-$(CONFIG_DWMAC_GENERIC) += dwmac-generic.o obj-$(CONFIG_DWMAC_IMX8) += dwmac-imx.o +obj-$(CONFIG_DWMAC_TEGRA) += dwmac-tegra.o obj-$(CONFIG_DWMAC_VISCONTI) += dwmac-visconti.o stmmac-platform-objs:= stmmac_platform.o dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c new file mode 100644 index 000000000000..bdf990cf2f31 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/platform_device.h> +#include <linux/of_device.h> +#include <linux/module.h> +#include <linux/stmmac.h> +#include <linux/clk.h> + +#include "stmmac_platform.h" + +static const char *const mgbe_clks[] = { + "rx-pcs", "tx", "tx-pcs", "mac-divider", "mac", "mgbe", "ptp-ref", "mac" +}; + +struct tegra_mgbe { + struct device *dev; + + struct clk_bulk_data *clks; + + struct reset_control *rst_mac; + struct reset_control *rst_pcs; + + void __iomem *hv; + void __iomem *regs; + void __iomem *xpcs; + + struct mii_bus *mii; +}; + +#define XPCS_WRAP_UPHY_RX_CONTROL 0x801c +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_SW_OVRD BIT(31) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_PCS_PHY_RDY BIT(10) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET BIT(9) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_CAL_EN BIT(8) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_SLEEP (BIT(7) | BIT(6)) +#define XPCS_WRAP_UPHY_RX_CONTROL_AUX_RX_IDDQ BIT(5) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_IDDQ BIT(4) +#define XPCS_WRAP_UPHY_RX_CONTROL_RX_DATA_EN BIT(0) +#define XPCS_WRAP_UPHY_HW_INIT_CTRL 0x8020 +#define XPCS_WRAP_UPHY_HW_INIT_CTRL_TX_EN BIT(0) +#define XPCS_WRAP_UPHY_HW_INIT_CTRL_RX_EN BIT(2) +#define XPCS_WRAP_UPHY_STATUS 0x8044 +#define XPCS_WRAP_UPHY_STATUS_TX_P_UP BIT(0) +#define XPCS_WRAP_IRQ_STATUS 0x8050 +#define XPCS_WRAP_IRQ_STATUS_PCS_LINK_STS BIT(6) + +#define XPCS_REG_ADDR_SHIFT 10 +#define XPCS_REG_ADDR_MASK 0x1fff +#define XPCS_ADDR 0x3fc + +#define MGBE_WRAP_COMMON_INTR_ENABLE 0x8704 +#define MAC_SBD_INTR BIT(2) +#define MGBE_WRAP_AXI_ASID0_CTRL 0x8400 +#define MGBE_SID 0x6 + +static int __maybe_unused tegra_mgbe_suspend(struct device *dev) +{ + struct tegra_mgbe *mgbe = get_stmmac_bsp_priv(dev); + int err; + + err = stmmac_suspend(dev); + if (err) + return err; + + clk_bulk_disable_unprepare(ARRAY_SIZE(mgbe_clks), mgbe->clks); + + return reset_control_assert(mgbe->rst_mac); +} + +static int __maybe_unused tegra_mgbe_resume(struct device *dev) +{ + struct tegra_mgbe *mgbe = get_stmmac_bsp_priv(dev); + u32 value; + int err; + + err = clk_bulk_prepare_enable(ARRAY_SIZE(mgbe_clks), mgbe->clks); + if (err < 0) + return err; + + err = reset_control_deassert(mgbe->rst_mac); + if (err < 0) + return err; + + /* Enable common interrupt at wrapper level */ + writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); + + /* Program SID */ + writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_STATUS); + if ((value & XPCS_WRAP_UPHY_STATUS_TX_P_UP) == 0) { + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL); + value |= XPCS_WRAP_UPHY_HW_INIT_CTRL_TX_EN; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL); + } + + err = readl_poll_timeout(mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL, value, + (value & XPCS_WRAP_UPHY_HW_INIT_CTRL_TX_EN) == 0, + 500, 500 * 2000); + if (err < 0) { + dev_err(mgbe->dev, "timeout waiting for TX lane to become enabled\n"); + clk_bulk_disable_unprepare(ARRAY_SIZE(mgbe_clks), mgbe->clks); + return err; + } + + err = stmmac_resume(dev); + if (err < 0) + clk_bulk_disable_unprepare(ARRAY_SIZE(mgbe_clks), mgbe->clks); + + return err; +} + +static int mgbe_uphy_lane_bringup_serdes_up(struct net_device *ndev, void *mgbe_data) +{ + struct tegra_mgbe *mgbe = (struct tegra_mgbe *)mgbe_data; + u32 value; + int err; + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_SW_OVRD; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_IDDQ; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_AUX_RX_IDDQ; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_SLEEP; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_CAL_EN; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + err = readl_poll_timeout(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL, value, + (value & XPCS_WRAP_UPHY_RX_CONTROL_RX_CAL_EN) == 0, + 1000, 1000 * 2000); + if (err < 0) { + dev_err(mgbe->dev, "timeout waiting for RX calibration to become enabled\n"); + return err; + } + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_DATA_EN; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_PCS_PHY_RDY; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + err = readl_poll_timeout(mgbe->xpcs + XPCS_WRAP_IRQ_STATUS, value, + value & XPCS_WRAP_IRQ_STATUS_PCS_LINK_STS, + 500, 500 * 2000); + if (err < 0) { + dev_err(mgbe->dev, "timeout waiting for link to become ready\n"); + return err; + } + + /* clear status */ + writel(value, mgbe->xpcs + XPCS_WRAP_IRQ_STATUS); + + return 0; +} + +static void mgbe_uphy_lane_bringup_serdes_down(struct net_device *ndev, void *mgbe_data) +{ + struct tegra_mgbe *mgbe = (struct tegra_mgbe *)mgbe_data; + u32 value; + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_SW_OVRD; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_DATA_EN; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_SLEEP; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_AUX_RX_IDDQ; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_IDDQ; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); +} + +static int tegra_mgbe_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat; + struct stmmac_resources res; + struct tegra_mgbe *mgbe; + int irq, err, i; + u32 value; + + mgbe = devm_kzalloc(&pdev->dev, sizeof(*mgbe), GFP_KERNEL); + if (!mgbe) + return -ENOMEM; + + mgbe->dev = &pdev->dev; + + memset(&res, 0, sizeof(res)); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + mgbe->hv = devm_platform_ioremap_resource_byname(pdev, "hypervisor"); + if (IS_ERR(mgbe->hv)) + return PTR_ERR(mgbe->hv); + + mgbe->regs = devm_platform_ioremap_resource_byname(pdev, "mac"); + if (IS_ERR(mgbe->regs)) + return PTR_ERR(mgbe->regs); + + mgbe->xpcs = devm_platform_ioremap_resource_byname(pdev, "xpcs"); + if (IS_ERR(mgbe->xpcs)) + return PTR_ERR(mgbe->xpcs); + + res.addr = mgbe->regs; + res.irq = irq; + + mgbe->clks = devm_kzalloc(&pdev->dev, sizeof(*mgbe->clks), GFP_KERNEL); + if (!mgbe->clks) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(mgbe_clks); i++) + mgbe->clks[i].id = mgbe_clks[i]; + + err = devm_clk_bulk_get(mgbe->dev, ARRAY_SIZE(mgbe_clks), mgbe->clks); + if (err < 0) + return err; + + err = clk_bulk_prepare_enable(ARRAY_SIZE(mgbe_clks), mgbe->clks); + if (err < 0) + return err; + + /* Perform MAC reset */ + mgbe->rst_mac = devm_reset_control_get(&pdev->dev, "mac"); + if (IS_ERR(mgbe->rst_mac)) { + err = PTR_ERR(mgbe->rst_mac); + goto disable_clks; + } + + err = reset_control_assert(mgbe->rst_mac); + if (err < 0) + goto disable_clks; + + usleep_range(2000, 4000); + + err = reset_control_deassert(mgbe->rst_mac); + if (err < 0) + goto disable_clks; + + /* Perform PCS reset */ + mgbe->rst_pcs = devm_reset_control_get(&pdev->dev, "pcs"); + if (IS_ERR(mgbe->rst_pcs)) { + err = PTR_ERR(mgbe->rst_pcs); + goto disable_clks; + } + + err = reset_control_assert(mgbe->rst_pcs); + if (err < 0) + goto disable_clks; + + usleep_range(2000, 4000); + + err = reset_control_deassert(mgbe->rst_pcs); + if (err < 0) + goto disable_clks; + + plat = stmmac_probe_config_dt(pdev, res.mac); + if (IS_ERR(plat)) { + err = PTR_ERR(plat); + goto disable_clks; + } + + plat->has_xgmac = 1; + plat->tso_en = 1; + plat->pmt = 1; + plat->bsp_priv = mgbe; + + if (!plat->mdio_node) + plat->mdio_node = of_get_child_by_name(pdev->dev.of_node, "mdio"); + + if (!plat->mdio_bus_data) { + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(*plat->mdio_bus_data), + GFP_KERNEL); + if (!plat->mdio_bus_data) { + err = -ENOMEM; + goto remove; + } + } + + plat->mdio_bus_data->needs_reset = true; + + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_STATUS); + if ((value & XPCS_WRAP_UPHY_STATUS_TX_P_UP) == 0) { + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL); + value |= XPCS_WRAP_UPHY_HW_INIT_CTRL_TX_EN; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL); + } + + err = readl_poll_timeout(mgbe->xpcs + XPCS_WRAP_UPHY_HW_INIT_CTRL, value, + (value & XPCS_WRAP_UPHY_HW_INIT_CTRL_TX_EN) == 0, + 500, 500 * 2000); + if (err < 0) { + dev_err(mgbe->dev, "timeout waiting for TX lane to become enabled\n"); + goto remove; + } + + plat->serdes_powerup = mgbe_uphy_lane_bringup_serdes_up; + plat->serdes_powerdown = mgbe_uphy_lane_bringup_serdes_down; + + /* Tx FIFO Size - 128KB */ + plat->tx_fifo_size = 131072; + /* Rx FIFO Size - 192KB */ + plat->rx_fifo_size = 196608; + + /* Enable common interrupt at wrapper level */ + writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); + + /* Program SID */ + writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + + plat->serdes_up_after_phy_linkup = 1; + + err = stmmac_dvr_probe(&pdev->dev, plat, &res); + if (err < 0) + goto remove; + + return 0; + +remove: + stmmac_remove_config_dt(pdev, plat); +disable_clks: + clk_bulk_disable_unprepare(ARRAY_SIZE(mgbe_clks), mgbe->clks); + + return err; +} + +static int tegra_mgbe_remove(struct platform_device *pdev) +{ + struct tegra_mgbe *mgbe = get_stmmac_bsp_priv(&pdev->dev); + + clk_bulk_disable_unprepare(ARRAY_SIZE(mgbe_clks), mgbe->clks); + + stmmac_pltfr_remove(pdev); + + return 0; +} + +static const struct of_device_id tegra_mgbe_match[] = { + { .compatible = "nvidia,tegra234-mgbe", }, + { } +}; +MODULE_DEVICE_TABLE(of, tegra_mgbe_match); + +static SIMPLE_DEV_PM_OPS(tegra_mgbe_pm_ops, tegra_mgbe_suspend, tegra_mgbe_resume); + +static struct platform_driver tegra_mgbe_driver = { + .probe = tegra_mgbe_probe, + .remove = tegra_mgbe_remove, + .driver = { + .name = "tegra-mgbe", + .pm = &tegra_mgbe_pm_ops, + .of_match_table = tegra_mgbe_match, + }, +}; +module_platform_driver(tegra_mgbe_driver); + +MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA Tegra MGBE driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 71dad409f78b..ccd49346d3b3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -331,9 +331,7 @@ enum power_event { #define MTL_RXQ_DMA_MAP0 0x00000c30 /* queue 0 to 3 */ #define MTL_RXQ_DMA_MAP1 0x00000c34 /* queue 4 to 7 */ -#define MTL_RXQ_DMA_Q04MDMACH_MASK GENMASK(3, 0) -#define MTL_RXQ_DMA_Q04MDMACH(x) ((x) << 0) -#define MTL_RXQ_DMA_QXMDMACH_MASK(x) GENMASK(11 + (8 * ((x) - 1)), 8 * (x)) +#define MTL_RXQ_DMA_QXMDMACH_MASK(x) (0xf << 8 * (x)) #define MTL_RXQ_DMA_QXMDMACH(chan, q) ((chan) << (8 * (q))) #define MTL_CHAN_BASE_ADDR 0x00000d00 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index e5cfde1cbd5c..8c7a0b7c9952 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -214,26 +214,17 @@ static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) void __iomem *ioaddr = hw->pcsr; u32 value; - if (queue < 4) + if (queue < 4) { value = readl(ioaddr + MTL_RXQ_DMA_MAP0); - else - value = readl(ioaddr + MTL_RXQ_DMA_MAP1); - - if (queue == 0 || queue == 4) { - value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK; - value |= MTL_RXQ_DMA_Q04MDMACH(chan); - } else if (queue > 4) { - value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue - 4); - value |= MTL_RXQ_DMA_QXMDMACH(chan, queue - 4); - } else { value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue); value |= MTL_RXQ_DMA_QXMDMACH(chan, queue); - } - - if (queue < 4) writel(value, ioaddr + MTL_RXQ_DMA_MAP0); - else + } else { + value = readl(ioaddr + MTL_RXQ_DMA_MAP1); + value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue - 4); + value |= MTL_RXQ_DMA_QXMDMACH(chan, queue - 4); writel(value, ioaddr + MTL_RXQ_DMA_MAP1); + } } static void dwmac4_config_cbs(struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b978d057c5f4..ec64b65dee34 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -988,6 +988,9 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 old_ctrl, ctrl; + if (priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) + priv->plat->serdes_powerup(priv->dev, priv->plat->bsp_priv); + old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl = old_ctrl & ~priv->hw->link.speed_mask; @@ -1088,7 +1091,6 @@ static void stmmac_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, @@ -3810,7 +3812,7 @@ static int __stmmac_open(struct net_device *dev, stmmac_reset_queues_param(priv); - if (priv->plat->serdes_powerup) { + if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv); if (ret < 0) { netdev_err(priv->dev, "%s: Serdes powerup failed\n", @@ -7520,7 +7522,7 @@ int stmmac_resume(struct device *dev) stmmac_mdio_reset(priv->mii); } - if (priv->plat->serdes_powerup) { + if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(ndev, priv->plat->bsp_priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 4d11980dcd64..fc06ddeac0d5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -15,29 +15,20 @@ * stmmac_adjust_freq * * @ptp: pointer to ptp_clock_info structure - * @ppb: desired period change in parts ber billion + * @scaled_ppm: desired period change in scaled parts per million * * Description: this function will adjust the frequency of hardware clock. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) +static int stmmac_adjust_freq(struct ptp_clock_info *ptp, long scaled_ppm) { struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); unsigned long flags; - u32 diff, addend; - int neg_adj = 0; - u64 adj; - - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } + u32 addend; - addend = priv->default_addend; - adj = addend; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); - addend = neg_adj ? (addend - diff) : (addend + diff); + addend = adjust_by_scaled_ppm(priv->default_addend, scaled_ppm); write_lock_irqsave(&priv->ptp_lock, flags); stmmac_config_addend(priv, priv->ptpaddr, addend); @@ -269,7 +260,7 @@ static struct ptp_clock_info stmmac_ptp_clock_ops = { .n_per_out = 0, /* will be overwritten in stmmac_ptp_register */ .n_pins = 0, .pps = 0, - .adjfreq = stmmac_adjust_freq, + .adjfine = stmmac_adjust_freq, .adjtime = stmmac_adjust_time, .gettime64 = stmmac_get_time, .settime64 = stmmac_set_time, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 773e415cc2de..2cfb18cef1d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -926,6 +926,9 @@ static int tc_setup_taprio(struct stmmac_priv *priv, int i, ret = 0; u64 ctr; + if (qopt->base_time < 0) + return -ERANGE; + if (!priv->dma_cap.estsel) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 0aca193d9550..4ef05bad4613 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -90,8 +90,6 @@ #include <linux/uaccess.h> #include <linux/jiffies.h> -#define cas_page_map(x) kmap_atomic((x)) -#define cas_page_unmap(x) kunmap_atomic((x)) #define CAS_NCPUS num_online_cpus() #define cas_skb_release(x) netif_rx(x) @@ -1915,7 +1913,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, int off, swivel = RX_SWIVEL_OFF_VAL; struct cas_page *page; struct sk_buff *skb; - void *addr, *crcaddr; + void *crcaddr; __sum16 csum; char *p; @@ -1936,7 +1934,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, skb_reserve(skb, swivel); p = skb->data; - addr = crcaddr = NULL; + crcaddr = NULL; if (hlen) { /* always copy header pages */ i = CAS_VAL(RX_COMP2_HDR_INDEX, words[1]); page = cp->rx_pages[CAS_VAL(RX_INDEX_RING, i)][CAS_VAL(RX_INDEX_NUM, i)]; @@ -1948,12 +1946,10 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, i += cp->crc_size; dma_sync_single_for_cpu(&cp->pdev->dev, page->dma_addr + off, i, DMA_FROM_DEVICE); - addr = cas_page_map(page->buffer); - memcpy(p, addr + off, i); + memcpy(p, page_address(page->buffer) + off, i); dma_sync_single_for_device(&cp->pdev->dev, page->dma_addr + off, i, DMA_FROM_DEVICE); - cas_page_unmap(addr); RX_USED_ADD(page, 0x100); p += hlen; swivel = 0; @@ -1984,12 +1980,11 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, /* make sure we always copy a header */ swivel = 0; if (p == (char *) skb->data) { /* not split */ - addr = cas_page_map(page->buffer); - memcpy(p, addr + off, RX_COPY_MIN); + memcpy(p, page_address(page->buffer) + off, + RX_COPY_MIN); dma_sync_single_for_device(&cp->pdev->dev, page->dma_addr + off, i, DMA_FROM_DEVICE); - cas_page_unmap(addr); off += RX_COPY_MIN; swivel = RX_COPY_MIN; RX_USED_ADD(page, cp->mtu_stride); @@ -2036,10 +2031,8 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, RX_USED_ADD(page, hlen + cp->crc_size); } - if (cp->crc_size) { - addr = cas_page_map(page->buffer); - crcaddr = addr + off + hlen; - } + if (cp->crc_size) + crcaddr = page_address(page->buffer) + off + hlen; } else { /* copying packet */ @@ -2061,12 +2054,10 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, i += cp->crc_size; dma_sync_single_for_cpu(&cp->pdev->dev, page->dma_addr + off, i, DMA_FROM_DEVICE); - addr = cas_page_map(page->buffer); - memcpy(p, addr + off, i); + memcpy(p, page_address(page->buffer) + off, i); dma_sync_single_for_device(&cp->pdev->dev, page->dma_addr + off, i, DMA_FROM_DEVICE); - cas_page_unmap(addr); if (p == (char *) skb->data) /* not split */ RX_USED_ADD(page, cp->mtu_stride); else @@ -2081,20 +2072,17 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, page->dma_addr, dlen + cp->crc_size, DMA_FROM_DEVICE); - addr = cas_page_map(page->buffer); - memcpy(p, addr, dlen + cp->crc_size); + memcpy(p, page_address(page->buffer), dlen + cp->crc_size); dma_sync_single_for_device(&cp->pdev->dev, page->dma_addr, dlen + cp->crc_size, DMA_FROM_DEVICE); - cas_page_unmap(addr); RX_USED_ADD(page, dlen + cp->crc_size); } end_copy_pkt: - if (cp->crc_size) { - addr = NULL; + if (cp->crc_size) crcaddr = skb->data + alloclen; - } + skb_put(skb, alloclen); } @@ -2103,8 +2091,6 @@ end_copy_pkt: /* checksum includes FCS. strip it out. */ csum = csum_fold(csum_partial(crcaddr, cp->crc_size, csum_unfold(csum))); - if (addr) - cas_page_unmap(addr); } skb->protocol = eth_type_trans(skb, cp->dev); if (skb->protocol == htons(ETH_P_IP)) { @@ -2793,18 +2779,14 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, tabort = cas_calc_tabort(cp, skb_frag_off(fragp), len); if (unlikely(tabort)) { - void *addr; - /* NOTE: len is always > tabort */ cas_write_txd(cp, ring, entry, mapping, len - tabort, ctrl, 0); entry = TX_DESC_NEXT(ring, entry); - - addr = cas_page_map(skb_frag_page(fragp)); - memcpy(tx_tiny_buf(cp, ring, entry), - addr + skb_frag_off(fragp) + len - tabort, - tabort); - cas_page_unmap(addr); + memcpy_from_page(tx_tiny_buf(cp, ring, entry), + skb_frag_page(fragp), + skb_frag_off(fragp) + len - tabort, + tabort); mapping = tx_tiny_map(cp, ring, entry, tentry); len = tabort; } diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index 80fde5f06fce..a6211b95ed17 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1085,13 +1085,13 @@ static inline int vnet_skb_map(struct ldc_channel *lp, struct sk_buff *skb, u8 *vaddr; if (nc < ncookies) { - vaddr = kmap_atomic(skb_frag_page(f)); + vaddr = kmap_local_page(skb_frag_page(f)); blen = skb_frag_size(f); blen += 8 - (blen & 7); err = ldc_map_single(lp, vaddr + skb_frag_off(f), blen, cookies + nc, ncookies - nc, map_perm); - kunmap_atomic(vaddr); + kunmap_local(vaddr); } else { err = -EMSGSIZE; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index b3b0ba842541..9decb0c7961b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -24,6 +24,7 @@ #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> +#include <linux/rtnetlink.h> #include <linux/mfd/syscon.h> #include <linux/sys_soc.h> #include <linux/dma/ti-cppi5.h> @@ -555,22 +556,38 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_port *port = am65_ndev_to_port(ndev); int ret, i; + u32 reg; ret = pm_runtime_resume_and_get(common->dev); if (ret < 0) return ret; + /* Idle MAC port */ + cpsw_sl_ctl_set(port->slave.mac_sl, CPSW_SL_CTL_CMD_IDLE); + cpsw_sl_wait_for_idle(port->slave.mac_sl, 100); + cpsw_sl_ctl_reset(port->slave.mac_sl); + + /* soft reset MAC */ + cpsw_sl_reg_write(port->slave.mac_sl, CPSW_SL_SOFT_RESET, 1); + mdelay(1); + reg = cpsw_sl_reg_read(port->slave.mac_sl, CPSW_SL_SOFT_RESET); + if (reg) { + dev_err(common->dev, "soft RESET didn't complete\n"); + ret = -ETIMEDOUT; + goto runtime_put; + } + /* Notify the stack of the actual queue counts. */ ret = netif_set_real_num_tx_queues(ndev, common->tx_ch_num); if (ret) { dev_err(common->dev, "cannot set real number of tx queues\n"); - return ret; + goto runtime_put; } ret = netif_set_real_num_rx_queues(ndev, AM65_CPSW_MAX_RX_QUEUES); if (ret) { dev_err(common->dev, "cannot set real number of rx queues\n"); - return ret; + goto runtime_put; } for (i = 0; i < common->tx_ch_num; i++) @@ -578,7 +595,7 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) ret = am65_cpsw_nuss_common_open(common); if (ret) - return ret; + goto runtime_put; common->usage_count++; @@ -606,6 +623,10 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) error_cleanup: am65_cpsw_nuss_ndo_slave_stop(ndev); return ret; + +runtime_put: + pm_runtime_put(common->dev); + return ret; } static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma) @@ -1362,12 +1383,12 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, cpu_stats = per_cpu_ptr(ndev_priv->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); rx_packets = cpu_stats->rx_packets; rx_bytes = cpu_stats->rx_bytes; tx_packets = cpu_stats->tx_packets; tx_bytes = cpu_stats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -1380,13 +1401,6 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } -static struct devlink_port *am65_cpsw_ndo_get_devlink_port(struct net_device *ndev) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - - return &port->devlink_port; -} - static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, @@ -1400,7 +1414,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, .ndo_eth_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, - .ndo_get_devlink_port = am65_cpsw_ndo_get_devlink_port, }; static void am65_cpsw_nuss_mac_config(struct phylink_config *config, unsigned int mode, @@ -1479,7 +1492,6 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy } static const struct phylink_mac_ops am65_cpsw_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = am65_cpsw_nuss_mac_config, .mac_link_down = am65_cpsw_nuss_mac_link_down, .mac_link_up = am65_cpsw_nuss_mac_link_up, @@ -1542,6 +1554,32 @@ void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common) } } +static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) +{ + struct device *dev = common->dev; + int i, ret = 0; + + for (i = 0; i < common->tx_ch_num; i++) { + struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; + + netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, + am65_cpsw_nuss_tx_poll); + + ret = devm_request_irq(dev, tx_chn->irq, + am65_cpsw_nuss_tx_irq, + IRQF_TRIGGER_HIGH, + tx_chn->tx_chn_name, tx_chn); + if (ret) { + dev_err(dev, "failure requesting tx%u irq %u, %d\n", + tx_chn->id, tx_chn->irq, ret); + goto err; + } + } + +err: + return ret; +} + static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) { u32 max_desc_num = ALIGN(AM65_CPSW_MAX_TX_DESC, MAX_SKB_FRAGS); @@ -1608,6 +1646,12 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) dev_name(dev), tx_chn->id); } + ret = am65_cpsw_nuss_ndev_add_tx_napi(common); + if (ret) { + dev_err(dev, "Failed to add tx NAPI %d\n", ret); + goto err; + } + err: i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common); if (i) { @@ -1632,6 +1676,29 @@ static void am65_cpsw_nuss_free_rx_chns(void *data) k3_udma_glue_release_rx_chn(rx_chn->rx_chn); } +static void am65_cpsw_nuss_remove_rx_chns(void *data) +{ + struct am65_cpsw_common *common = data; + struct am65_cpsw_rx_chn *rx_chn; + struct device *dev = common->dev; + + rx_chn = &common->rx_chns; + devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common); + + if (!(rx_chn->irq < 0)) + devm_free_irq(dev, rx_chn->irq, common); + + netif_napi_del(&common->napi_rx); + + if (!IS_ERR_OR_NULL(rx_chn->desc_pool)) + k3_cppi_desc_pool_destroy(rx_chn->desc_pool); + + if (!IS_ERR_OR_NULL(rx_chn->rx_chn)) + k3_udma_glue_release_rx_chn(rx_chn->rx_chn); + + common->rx_flow_id_base = -1; +} + static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; @@ -1719,6 +1786,18 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) } } + netif_napi_add(common->dma_ndev, &common->napi_rx, + am65_cpsw_nuss_rx_poll); + + ret = devm_request_irq(dev, rx_chn->irq, + am65_cpsw_nuss_rx_irq, + IRQF_TRIGGER_HIGH, dev_name(dev), common); + if (ret) { + dev_err(dev, "failure requesting rx irq %u, %d\n", + rx_chn->irq, ret); + goto err; + } + err: i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common); if (i) { @@ -1990,6 +2069,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) port->slave.phylink_config.dev = &port->ndev->dev; port->slave.phylink_config.type = PHYLINK_NETDEV; port->slave.phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + port->slave.phylink_config.mac_managed_pm = true; /* MAC does PM */ if (phy_interface_mode_is_rgmii(port->slave.phy_if)) { phy_interface_set_rgmii(port->slave.phylink_config.supported_interfaces); @@ -2043,35 +2123,6 @@ static int am65_cpsw_nuss_init_ndevs(struct am65_cpsw_common *common) return ret; } - netif_napi_add(common->dma_ndev, &common->napi_rx, - am65_cpsw_nuss_rx_poll); - - return ret; -} - -static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) -{ - struct device *dev = common->dev; - int i, ret = 0; - - for (i = 0; i < common->tx_ch_num; i++) { - struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - - netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, - am65_cpsw_nuss_tx_poll); - - ret = devm_request_irq(dev, tx_chn->irq, - am65_cpsw_nuss_tx_irq, - IRQF_TRIGGER_HIGH, - tx_chn->tx_chn_name, tx_chn); - if (ret) { - dev_err(dev, "failure requesting tx%u irq %u, %d\n", - tx_chn->id, tx_chn->irq, ret); - goto err; - } - } - -err: return ret; } @@ -2534,22 +2585,16 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { struct device *dev = common->dev; - struct devlink_port *dl_port; struct am65_cpsw_port *port; int ret = 0, i; - ret = am65_cpsw_nuss_ndev_add_tx_napi(common); + /* init tx channels */ + ret = am65_cpsw_nuss_init_tx_chns(common); if (ret) return ret; - - ret = devm_request_irq(dev, common->rx_chns.irq, - am65_cpsw_nuss_rx_irq, - IRQF_TRIGGER_HIGH, dev_name(dev), common); - if (ret) { - dev_err(dev, "failure requesting rx irq %u, %d\n", - common->rx_chns.irq, ret); + ret = am65_cpsw_nuss_init_rx_chns(common); + if (ret) return ret; - } ret = am65_cpsw_nuss_register_devlink(common); if (ret) @@ -2561,15 +2606,14 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (!port->ndev) continue; + SET_NETDEV_DEVLINK_PORT(port->ndev, &port->devlink_port); + ret = register_netdev(port->ndev); if (ret) { dev_err(dev, "error registering slave net device%i %d\n", i, ret); goto err_cleanup_ndev; } - - dl_port = &port->devlink_port; - devlink_port_type_eth_set(dl_port, port->ndev); } ret = am65_cpsw_register_notifiers(common); @@ -2595,10 +2639,8 @@ int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx) common->tx_ch_num = num_tx; ret = am65_cpsw_nuss_init_tx_chns(common); - if (ret) - return ret; - return am65_cpsw_nuss_ndev_add_tx_napi(common); + return ret; } struct am65_cpsw_soc_pdata { @@ -2675,6 +2717,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) struct clk *clk; u64 id_temp; int ret, i; + int ale_entries; common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL); if (!common) @@ -2747,14 +2790,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) am65_cpsw_nuss_get_ver(common); - /* init tx channels */ - ret = am65_cpsw_nuss_init_tx_chns(common); - if (ret) - goto err_of_clear; - ret = am65_cpsw_nuss_init_rx_chns(common); - if (ret) - goto err_of_clear; - ret = am65_cpsw_nuss_init_host_p(common); if (ret) goto err_of_clear; @@ -2778,6 +2813,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) goto err_of_clear; } + ale_entries = common->ale->params.ale_entries; + common->ale_context = devm_kzalloc(dev, + ale_entries * ALE_ENTRY_WORDS * sizeof(u32), + GFP_KERNEL); ret = am65_cpsw_init_cpts(common); if (ret) goto err_of_clear; @@ -2839,10 +2878,103 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int am65_cpsw_nuss_suspend(struct device *dev) +{ + struct am65_cpsw_common *common = dev_get_drvdata(dev); + struct am65_cpsw_host *host_p = am65_common_get_host(common); + struct am65_cpsw_port *port; + struct net_device *ndev; + int i, ret; + + cpsw_ale_dump(common->ale, common->ale_context); + host_p->vid_context = readl(host_p->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + ndev = port->ndev; + + if (!ndev) + continue; + + port->vid_context = readl(port->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + netif_device_detach(ndev); + if (netif_running(ndev)) { + rtnl_lock(); + ret = am65_cpsw_nuss_ndo_slave_stop(ndev); + rtnl_unlock(); + if (ret < 0) { + netdev_err(ndev, "failed to stop: %d", ret); + return ret; + } + } + } + + am65_cpts_suspend(common->cpts); + + am65_cpsw_nuss_remove_rx_chns(common); + am65_cpsw_nuss_remove_tx_chns(common); + + return 0; +} + +static int am65_cpsw_nuss_resume(struct device *dev) +{ + struct am65_cpsw_common *common = dev_get_drvdata(dev); + struct am65_cpsw_port *port; + struct net_device *ndev; + int i, ret; + struct am65_cpsw_host *host_p = am65_common_get_host(common); + + ret = am65_cpsw_nuss_init_tx_chns(common); + if (ret) + return ret; + ret = am65_cpsw_nuss_init_rx_chns(common); + if (ret) + return ret; + + /* If RX IRQ was disabled before suspend, keep it disabled */ + if (common->rx_irq_disabled) + disable_irq(common->rx_chns.irq); + + am65_cpts_resume(common->cpts); + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + ndev = port->ndev; + + if (!ndev) + continue; + + if (netif_running(ndev)) { + rtnl_lock(); + ret = am65_cpsw_nuss_ndo_slave_open(ndev); + rtnl_unlock(); + if (ret < 0) { + netdev_err(ndev, "failed to start: %d", ret); + return ret; + } + } + + netif_device_attach(ndev); + writel(port->vid_context, port->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + } + + writel(host_p->vid_context, host_p->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + cpsw_ale_restore(common->ale, common->ale_context); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +static const struct dev_pm_ops am65_cpsw_nuss_dev_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(am65_cpsw_nuss_suspend, am65_cpsw_nuss_resume) +}; + static struct platform_driver am65_cpsw_nuss_driver = { .driver = { .name = AM65_CPSW_DRV_NAME, .of_match_table = am65_cpsw_nuss_of_mtable, + .pm = &am65_cpsw_nuss_dev_pm_ops, }, .probe = am65_cpsw_nuss_probe, .remove = am65_cpsw_nuss_remove, diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 2c9850fdfcb6..4b75620f8d28 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -55,12 +55,16 @@ struct am65_cpsw_port { bool rx_ts_enabled; struct am65_cpsw_qos qos; struct devlink_port devlink_port; + /* Only for suspend resume context */ + u32 vid_context; }; struct am65_cpsw_host { struct am65_cpsw_common *common; void __iomem *port_base; void __iomem *stat_base; + /* Only for suspend resume context */ + u32 vid_context; }; struct am65_cpsw_tx_chn { @@ -145,6 +149,8 @@ struct am65_cpsw_common { struct net_device *hw_bridge_dev; struct notifier_block am65_cpsw_netdevice_nb; unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN]; + /* only for suspend/resume context restore */ + u32 *ale_context; }; struct am65_cpsw_ndev_stats { diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index e2f0fb286143..9535396b28cd 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -176,6 +176,16 @@ struct am65_cpts { u32 genf_enable; u32 hw_ts_enable; struct sk_buff_head txq; + /* context save/restore */ + u64 sr_cpts_ns; + u64 sr_ktime_ns; + u32 sr_control; + u32 sr_int_enable; + u32 sr_rftclk_sel; + u32 sr_ts_ppm_hi; + u32 sr_ts_ppm_low; + struct am65_genf_regs sr_genf[AM65_CPTS_GENF_MAX_NUM]; + struct am65_genf_regs sr_estf[AM65_CPTS_ESTF_MAX_NUM]; }; struct am65_cpts_skb_cb_data { @@ -381,9 +391,10 @@ static irqreturn_t am65_cpts_interrupt(int irq, void *dev_id) } /* PTP clock operations */ -static int am65_cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int am65_cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); int neg_adj = 0; u64 adj_period; u32 val; @@ -615,7 +626,7 @@ static long am65_cpts_ts_work(struct ptp_clock_info *ptp); static struct ptp_clock_info am65_ptp_info = { .owner = THIS_MODULE, .name = "CTPS timer", - .adjfreq = am65_cpts_ptp_adjfreq, + .adjfine = am65_cpts_ptp_adjfine, .adjtime = am65_cpts_ptp_adjtime, .gettimex64 = am65_cpts_ptp_gettimex, .settime64 = am65_cpts_ptp_settime, @@ -1029,6 +1040,72 @@ refclk_disable: } EXPORT_SYMBOL_GPL(am65_cpts_create); +void am65_cpts_suspend(struct am65_cpts *cpts) +{ + /* save state and disable CPTS */ + cpts->sr_control = am65_cpts_read32(cpts, control); + cpts->sr_int_enable = am65_cpts_read32(cpts, int_enable); + cpts->sr_rftclk_sel = am65_cpts_read32(cpts, rftclk_sel); + cpts->sr_ts_ppm_hi = am65_cpts_read32(cpts, ts_ppm_hi); + cpts->sr_ts_ppm_low = am65_cpts_read32(cpts, ts_ppm_low); + cpts->sr_cpts_ns = am65_cpts_gettime(cpts, NULL); + cpts->sr_ktime_ns = ktime_to_ns(ktime_get_real()); + am65_cpts_disable(cpts); + clk_disable(cpts->refclk); + + /* Save GENF state */ + memcpy_fromio(&cpts->sr_genf, &cpts->reg->genf, sizeof(cpts->sr_genf)); + + /* Save ESTF state */ + memcpy_fromio(&cpts->sr_estf, &cpts->reg->estf, sizeof(cpts->sr_estf)); +} +EXPORT_SYMBOL_GPL(am65_cpts_suspend); + +void am65_cpts_resume(struct am65_cpts *cpts) +{ + int i; + s64 ktime_ns; + + /* restore state and enable CPTS */ + clk_enable(cpts->refclk); + am65_cpts_write32(cpts, cpts->sr_rftclk_sel, rftclk_sel); + am65_cpts_set_add_val(cpts); + am65_cpts_write32(cpts, cpts->sr_control, control); + am65_cpts_write32(cpts, cpts->sr_int_enable, int_enable); + + /* Restore time to saved CPTS time + time in suspend/resume */ + ktime_ns = ktime_to_ns(ktime_get_real()); + ktime_ns -= cpts->sr_ktime_ns; + am65_cpts_settime(cpts, cpts->sr_cpts_ns + ktime_ns); + + /* Restore compensation (PPM) */ + am65_cpts_write32(cpts, cpts->sr_ts_ppm_hi, ts_ppm_hi); + am65_cpts_write32(cpts, cpts->sr_ts_ppm_low, ts_ppm_low); + + /* Restore GENF state */ + for (i = 0; i < AM65_CPTS_GENF_MAX_NUM; i++) { + am65_cpts_write32(cpts, 0, genf[i].length); /* TRM sequence */ + am65_cpts_write32(cpts, cpts->sr_genf[i].comp_hi, genf[i].comp_hi); + am65_cpts_write32(cpts, cpts->sr_genf[i].comp_lo, genf[i].comp_lo); + am65_cpts_write32(cpts, cpts->sr_genf[i].length, genf[i].length); + am65_cpts_write32(cpts, cpts->sr_genf[i].control, genf[i].control); + am65_cpts_write32(cpts, cpts->sr_genf[i].ppm_hi, genf[i].ppm_hi); + am65_cpts_write32(cpts, cpts->sr_genf[i].ppm_low, genf[i].ppm_low); + } + + /* Restore ESTTF state */ + for (i = 0; i < AM65_CPTS_ESTF_MAX_NUM; i++) { + am65_cpts_write32(cpts, 0, estf[i].length); /* TRM sequence */ + am65_cpts_write32(cpts, cpts->sr_estf[i].comp_hi, estf[i].comp_hi); + am65_cpts_write32(cpts, cpts->sr_estf[i].comp_lo, estf[i].comp_lo); + am65_cpts_write32(cpts, cpts->sr_estf[i].length, estf[i].length); + am65_cpts_write32(cpts, cpts->sr_estf[i].control, estf[i].control); + am65_cpts_write32(cpts, cpts->sr_estf[i].ppm_hi, estf[i].ppm_hi); + am65_cpts_write32(cpts, cpts->sr_estf[i].ppm_low, estf[i].ppm_low); + } +} +EXPORT_SYMBOL_GPL(am65_cpts_resume); + static int am65_cpts_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h index cf9fbc28fd03..bd08f4b2edd2 100644 --- a/drivers/net/ethernet/ti/am65-cpts.h +++ b/drivers/net/ethernet/ti/am65-cpts.h @@ -28,6 +28,8 @@ u64 am65_cpts_ns_gettime(struct am65_cpts *cpts); int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx, struct am65_cpts_estf_cfg *cfg); void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx); +void am65_cpts_suspend(struct am65_cpts *cpts); +void am65_cpts_resume(struct am65_cpts *cpts); #else static inline struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, @@ -69,6 +71,14 @@ static inline int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx, static inline void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx) { } + +static inline void am65_cpts_suspend(struct am65_cpts *cpts) +{ +} + +static inline void am65_cpts_resume(struct am65_cpts *cpts) +{ +} #endif #endif /* K3_CPTS_H_ */ diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 231370e9a801..0c5e783e574c 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -1452,6 +1452,16 @@ void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) } } +void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data) +{ + int i; + + for (i = 0; i < ale->params.ale_entries; i++) { + cpsw_ale_write(ale, i, data); + data += ALE_ENTRY_WORDS; + } +} + u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale) { return ale ? ale->params.ale_entries : 0; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index aba4572cfa3b..6779ee111d57 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -127,6 +127,7 @@ int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control); int cpsw_ale_control_set(struct cpsw_ale *ale, int port, int control, int value); void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data); +void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data); u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale); static inline int cpsw_ale_get_vlan_p0_untag(struct cpsw_ale *ale, u16 vid) diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 92ca739fac01..bcccf43d368b 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -213,25 +213,13 @@ static void cpts_update_cur_time(struct cpts *cpts, int match, /* PTP clock operations */ -static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct cpts *cpts = container_of(ptp, struct cpts, info); - int neg_adj = 0; - u32 diff, mult; - u64 adj; - - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - mult = cpts->cc_mult; - adj = mult; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); mutex_lock(&cpts->ptp_clk_mutex); - cpts->mult_new = neg_adj ? mult - diff : mult + diff; + cpts->mult_new = adjust_by_scaled_ppm(cpts->cc_mult, scaled_ppm); cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL); @@ -435,7 +423,7 @@ static const struct ptp_clock_info cpts_info = { .n_ext_ts = 0, .n_pins = 0, .pps = 0, - .adjfreq = cpts_ptp_adjfreq, + .adjfine = cpts_ptp_adjfine, .adjtime = cpts_ptp_adjtime, .gettimex64 = cpts_ptp_gettimeex, .settime64 = cpts_ptp_settime, @@ -794,7 +782,7 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts_calc_mult_shift(cpts); /* save cc.mult original value as it can be modified - * by cpts_ptp_adjfreq(). + * by cpts_ptp_adjfine(). */ cpts->cc_mult = cpts->cc.mult; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index aba70bef4894..1bb596a9d8a2 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1261,7 +1261,7 @@ out: } /* Submit the packet */ -static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct netcp_intf *netcp = netdev_priv(ndev); struct netcp_stats *tx_stats = &netcp->stats; @@ -1916,16 +1916,16 @@ netcp_get_stats(struct net_device *ndev, struct rtnl_link_stats64 *stats) unsigned int start; do { - start = u64_stats_fetch_begin_irq(&p->syncp_rx); + start = u64_stats_fetch_begin(&p->syncp_rx); rxpackets = p->rx_packets; rxbytes = p->rx_bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp_rx, start)); + } while (u64_stats_fetch_retry(&p->syncp_rx, start)); do { - start = u64_stats_fetch_begin_irq(&p->syncp_tx); + start = u64_stats_fetch_begin(&p->syncp_tx); txpackets = p->tx_packets; txbytes = p->tx_bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp_tx, start)); + } while (u64_stats_fetch_retry(&p->syncp_tx, start)); stats->rx_packets = rxpackets; stats->rx_bytes = rxbytes; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 0fb15a17b547..d716e6fe26e1 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2217,16 +2217,16 @@ rhine_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) netdev_stats_to_stats64(stats, &dev->stats); do { - start = u64_stats_fetch_begin_irq(&rp->rx_stats.syncp); + start = u64_stats_fetch_begin(&rp->rx_stats.syncp); stats->rx_packets = rp->rx_stats.packets; stats->rx_bytes = rp->rx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&rp->rx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&rp->rx_stats.syncp, start)); do { - start = u64_stats_fetch_begin_irq(&rp->tx_stats.syncp); + start = u64_stats_fetch_begin(&rp->tx_stats.syncp); stats->tx_packets = rp->tx_stats.packets; stats->tx_bytes = rp->tx_stats.bytes; - } while (u64_stats_fetch_retry_irq(&rp->tx_stats.syncp, start)); + } while (u64_stats_fetch_retry(&rp->tx_stats.syncp, start)); } static void rhine_set_rx_mode(struct net_device *dev) diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index f5d43d8c9629..86310588c6c1 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -16,9 +16,15 @@ config NET_VENDOR_WANGXUN if NET_VENDOR_WANGXUN +config LIBWX + tristate + help + Common library for Wangxun(R) Ethernet drivers. + config NGBE tristate "Wangxun(R) GbE PCI Express adapters support" depends on PCI + select LIBWX help This driver supports Wangxun(R) GbE PCI Express family of adapters. @@ -32,6 +38,7 @@ config NGBE config TXGBE tristate "Wangxun(R) 10GbE PCI Express adapters support" depends on PCI + select LIBWX help This driver supports Wangxun(R) 10GbE PCI Express family of adapters. diff --git a/drivers/net/ethernet/wangxun/Makefile b/drivers/net/ethernet/wangxun/Makefile index ac3fb06b233c..ca19311dbe38 100644 --- a/drivers/net/ethernet/wangxun/Makefile +++ b/drivers/net/ethernet/wangxun/Makefile @@ -3,5 +3,6 @@ # Makefile for the Wangxun network device drivers. # +obj-$(CONFIG_LIBWX) += libwx/ obj-$(CONFIG_TXGBE) += txgbe/ obj-$(CONFIG_NGBE) += ngbe/ diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile new file mode 100644 index 000000000000..1ed5e23af944 --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. +# + +obj-$(CONFIG_LIBWX) += libwx.o + +libwx-objs := wx_hw.o diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c new file mode 100644 index 000000000000..c57dc3238b3f --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -0,0 +1,936 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <linux/iopoll.h> +#include <linux/pci.h> + +#include "wx_type.h" +#include "wx_hw.h" + +static void wx_intr_disable(struct wx_hw *wxhw, u64 qmask) +{ + u32 mask; + + mask = (qmask & 0xFFFFFFFF); + if (mask) + wr32(wxhw, WX_PX_IMS(0), mask); + + if (wxhw->mac.type == wx_mac_sp) { + mask = (qmask >> 32); + if (mask) + wr32(wxhw, WX_PX_IMS(1), mask); + } +} + +/* cmd_addr is used for some special command: + * 1. to be sector address, when implemented erase sector command + * 2. to be flash address when implemented read, write flash address + */ +static int wx_fmgr_cmd_op(struct wx_hw *wxhw, u32 cmd, u32 cmd_addr) +{ + u32 cmd_val = 0, val = 0; + + cmd_val = WX_SPI_CMD_CMD(cmd) | + WX_SPI_CMD_CLK(WX_SPI_CLK_DIV) | + cmd_addr; + wr32(wxhw, WX_SPI_CMD, cmd_val); + + return read_poll_timeout(rd32, val, (val & 0x1), 10, 100000, + false, wxhw, WX_SPI_STATUS); +} + +static int wx_flash_read_dword(struct wx_hw *wxhw, u32 addr, u32 *data) +{ + int ret = 0; + + ret = wx_fmgr_cmd_op(wxhw, WX_SPI_CMD_READ_DWORD, addr); + if (ret < 0) + return ret; + + *data = rd32(wxhw, WX_SPI_DATA); + + return ret; +} + +int wx_check_flash_load(struct wx_hw *hw, u32 check_bit) +{ + u32 reg = 0; + int err = 0; + + /* if there's flash existing */ + if (!(rd32(hw, WX_SPI_STATUS) & + WX_SPI_STATUS_FLASH_BYPASS)) { + /* wait hw load flash done */ + err = read_poll_timeout(rd32, reg, !(reg & check_bit), 20000, 2000000, + false, hw, WX_SPI_ILDR_STATUS); + if (err < 0) + wx_err(hw, "Check flash load timeout.\n"); + } + + return err; +} +EXPORT_SYMBOL(wx_check_flash_load); + +void wx_control_hw(struct wx_hw *wxhw, bool drv) +{ + if (drv) { + /* Let firmware know the driver has taken over */ + wr32m(wxhw, WX_CFG_PORT_CTL, + WX_CFG_PORT_CTL_DRV_LOAD, WX_CFG_PORT_CTL_DRV_LOAD); + } else { + /* Let firmware take over control of hw */ + wr32m(wxhw, WX_CFG_PORT_CTL, + WX_CFG_PORT_CTL_DRV_LOAD, 0); + } +} +EXPORT_SYMBOL(wx_control_hw); + +/** + * wx_mng_present - returns 0 when management capability is present + * @wxhw: pointer to hardware structure + */ +int wx_mng_present(struct wx_hw *wxhw) +{ + u32 fwsm; + + fwsm = rd32(wxhw, WX_MIS_ST); + if (fwsm & WX_MIS_ST_MNG_INIT_DN) + return 0; + else + return -EACCES; +} +EXPORT_SYMBOL(wx_mng_present); + +/* Software lock to be held while software semaphore is being accessed. */ +static DEFINE_MUTEX(wx_sw_sync_lock); + +/** + * wx_release_sw_sync - Release SW semaphore + * @wxhw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Releases the SW semaphore for the specified + * function (CSR, PHY0, PHY1, EEPROM, Flash) + **/ +static void wx_release_sw_sync(struct wx_hw *wxhw, u32 mask) +{ + mutex_lock(&wx_sw_sync_lock); + wr32m(wxhw, WX_MNG_SWFW_SYNC, mask, 0); + mutex_unlock(&wx_sw_sync_lock); +} + +/** + * wx_acquire_sw_sync - Acquire SW semaphore + * @wxhw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SW semaphore for the specified + * function (CSR, PHY0, PHY1, EEPROM, Flash) + **/ +static int wx_acquire_sw_sync(struct wx_hw *wxhw, u32 mask) +{ + u32 sem = 0; + int ret = 0; + + mutex_lock(&wx_sw_sync_lock); + ret = read_poll_timeout(rd32, sem, !(sem & mask), + 5000, 2000000, false, wxhw, WX_MNG_SWFW_SYNC); + if (!ret) { + sem |= mask; + wr32(wxhw, WX_MNG_SWFW_SYNC, sem); + } else { + wx_err(wxhw, "SW Semaphore not granted: 0x%x.\n", sem); + } + mutex_unlock(&wx_sw_sync_lock); + + return ret; +} + +/** + * wx_host_interface_command - Issue command to manageability block + * @wxhw: pointer to the HW structure + * @buffer: contains the command to write and where the return status will + * be placed + * @length: length of buffer, must be multiple of 4 bytes + * @timeout: time in ms to wait for command completion + * @return_data: read and return data from the buffer (true) or not (false) + * Needed because FW structures are big endian and decoding of + * these fields can be 8 bit or 16 bit based on command. Decoding + * is not easily understood without making a table of commands. + * So we will leave this up to the caller to read back the data + * in these cases. + **/ +int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, + u32 length, u32 timeout, bool return_data) +{ + u32 hdr_size = sizeof(struct wx_hic_hdr); + u32 hicr, i, bi, buf[64] = {}; + int status = 0; + u32 dword_len; + u16 buf_len; + + if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) { + wx_err(wxhw, "Buffer length failure buffersize=%d.\n", length); + return -EINVAL; + } + + status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_MB); + if (status != 0) + return status; + + /* Calculate length in DWORDs. We must be DWORD aligned */ + if ((length % (sizeof(u32))) != 0) { + wx_err(wxhw, "Buffer length failure, not aligned to dword"); + status = -EINVAL; + goto rel_out; + } + + dword_len = length >> 2; + + /* The device driver writes the relevant command block + * into the ram area. + */ + for (i = 0; i < dword_len; i++) { + wr32a(wxhw, WX_MNG_MBOX, i, (__force u32)cpu_to_le32(buffer[i])); + /* write flush */ + buf[i] = rd32a(wxhw, WX_MNG_MBOX, i); + } + /* Setting this bit tells the ARC that a new command is pending. */ + wr32m(wxhw, WX_MNG_MBOX_CTL, + WX_MNG_MBOX_CTL_SWRDY, WX_MNG_MBOX_CTL_SWRDY); + + status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000, + timeout * 1000, false, wxhw, WX_MNG_MBOX_CTL); + + /* Check command completion */ + if (status) { + wx_dbg(wxhw, "Command has failed with no status valid.\n"); + + buf[0] = rd32(wxhw, WX_MNG_MBOX); + if ((buffer[0] & 0xff) != (~buf[0] >> 24)) { + status = -EINVAL; + goto rel_out; + } + if ((buf[0] & 0xff0000) >> 16 == 0x80) { + wx_dbg(wxhw, "It's unknown cmd.\n"); + status = -EINVAL; + goto rel_out; + } + + wx_dbg(wxhw, "write value:\n"); + for (i = 0; i < dword_len; i++) + wx_dbg(wxhw, "%x ", buffer[i]); + wx_dbg(wxhw, "read value:\n"); + for (i = 0; i < dword_len; i++) + wx_dbg(wxhw, "%x ", buf[i]); + } + + if (!return_data) + goto rel_out; + + /* Calculate length in DWORDs */ + dword_len = hdr_size >> 2; + + /* first pull in the header so we know the buffer length */ + for (bi = 0; bi < dword_len; bi++) { + buffer[bi] = rd32a(wxhw, WX_MNG_MBOX, bi); + le32_to_cpus(&buffer[bi]); + } + + /* If there is any thing in data position pull it in */ + buf_len = ((struct wx_hic_hdr *)buffer)->buf_len; + if (buf_len == 0) + goto rel_out; + + if (length < buf_len + hdr_size) { + wx_err(wxhw, "Buffer not large enough for reply message.\n"); + status = -EFAULT; + goto rel_out; + } + + /* Calculate length in DWORDs, add 3 for odd lengths */ + dword_len = (buf_len + 3) >> 2; + + /* Pull in the rest of the buffer (bi is where we left off) */ + for (; bi <= dword_len; bi++) { + buffer[bi] = rd32a(wxhw, WX_MNG_MBOX, bi); + le32_to_cpus(&buffer[bi]); + } + +rel_out: + wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_MB); + return status; +} +EXPORT_SYMBOL(wx_host_interface_command); + +/** + * wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd + * assuming that the semaphore is already obtained. + * @wxhw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the hostif. + **/ +static int wx_read_ee_hostif_data(struct wx_hw *wxhw, u16 offset, u16 *data) +{ + struct wx_hic_read_shadow_ram buffer; + int status; + + buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* convert offset from words to bytes */ + buffer.address = (__force u32)cpu_to_be32(offset * 2); + /* one word */ + buffer.length = (__force u16)cpu_to_be16(sizeof(u16)); + + status = wx_host_interface_command(wxhw, (u32 *)&buffer, sizeof(buffer), + WX_HI_COMMAND_TIMEOUT, false); + + if (status != 0) + return status; + + *data = (u16)rd32a(wxhw, WX_MNG_MBOX, FW_NVM_DATA_OFFSET); + + return status; +} + +/** + * wx_read_ee_hostif - Read EEPROM word using a host interface cmd + * @wxhw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the hostif. + **/ +int wx_read_ee_hostif(struct wx_hw *wxhw, u16 offset, u16 *data) +{ + int status = 0; + + status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + if (status == 0) { + status = wx_read_ee_hostif_data(wxhw, offset, data); + wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + } + + return status; +} +EXPORT_SYMBOL(wx_read_ee_hostif); + +/** + * wx_read_ee_hostif_buffer- Read EEPROM word(s) using hostif + * @wxhw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @words: number of words + * @data: word(s) read from the EEPROM + * + * Reads a 16 bit word(s) from the EEPROM using the hostif. + **/ +int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, + u16 offset, u16 words, u16 *data) +{ + struct wx_hic_read_shadow_ram buffer; + u32 current_word = 0; + u16 words_to_read; + u32 value = 0; + int status; + u32 i; + + /* Take semaphore for the entire operation. */ + status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + if (status != 0) + return status; + + while (words) { + if (words > FW_MAX_READ_BUFFER_SIZE / 2) + words_to_read = FW_MAX_READ_BUFFER_SIZE / 2; + else + words_to_read = words; + + buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* convert offset from words to bytes */ + buffer.address = (__force u32)cpu_to_be32((offset + current_word) * 2); + buffer.length = (__force u16)cpu_to_be16(words_to_read * 2); + + status = wx_host_interface_command(wxhw, (u32 *)&buffer, + sizeof(buffer), + WX_HI_COMMAND_TIMEOUT, + false); + + if (status != 0) { + wx_err(wxhw, "Host interface command failed\n"); + goto out; + } + + for (i = 0; i < words_to_read; i++) { + u32 reg = WX_MNG_MBOX + (FW_NVM_DATA_OFFSET << 2) + 2 * i; + + value = rd32(wxhw, reg); + data[current_word] = (u16)(value & 0xffff); + current_word++; + i++; + if (i < words_to_read) { + value >>= 16; + data[current_word] = (u16)(value & 0xffff); + current_word++; + } + } + words -= words_to_read; + } + +out: + wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + return status; +} +EXPORT_SYMBOL(wx_read_ee_hostif_buffer); + +/** + * wx_calculate_checksum - Calculate checksum for buffer + * @buffer: pointer to EEPROM + * @length: size of EEPROM to calculate a checksum for + * Calculates the checksum for some buffer on a specified length. The + * checksum calculated is returned. + **/ +static u8 wx_calculate_checksum(u8 *buffer, u32 length) +{ + u8 sum = 0; + u32 i; + + if (!buffer) + return 0; + + for (i = 0; i < length; i++) + sum += buffer[i]; + + return (u8)(0 - sum); +} + +/** + * wx_reset_hostif - send reset cmd to fw + * @wxhw: pointer to hardware structure + * + * Sends reset cmd to firmware through the manageability + * block. + **/ +int wx_reset_hostif(struct wx_hw *wxhw) +{ + struct wx_hic_reset reset_cmd; + int ret_val = 0; + int i; + + reset_cmd.hdr.cmd = FW_RESET_CMD; + reset_cmd.hdr.buf_len = FW_RESET_LEN; + reset_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + reset_cmd.lan_id = wxhw->bus.func; + reset_cmd.reset_type = (u16)wxhw->reset_type; + reset_cmd.hdr.checksum = 0; + reset_cmd.hdr.checksum = wx_calculate_checksum((u8 *)&reset_cmd, + (FW_CEM_HDR_LEN + + reset_cmd.hdr.buf_len)); + + for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { + ret_val = wx_host_interface_command(wxhw, (u32 *)&reset_cmd, + sizeof(reset_cmd), + WX_HI_COMMAND_TIMEOUT, + true); + if (ret_val != 0) + continue; + + if (reset_cmd.hdr.cmd_or_resp.ret_status == + FW_CEM_RESP_STATUS_SUCCESS) + ret_val = 0; + else + ret_val = -EFAULT; + + break; + } + + return ret_val; +} +EXPORT_SYMBOL(wx_reset_hostif); + +/** + * wx_init_eeprom_params - Initialize EEPROM params + * @wxhw: pointer to hardware structure + * + * Initializes the EEPROM parameters wx_eeprom_info within the + * wx_hw struct in order to set up EEPROM access. + **/ +void wx_init_eeprom_params(struct wx_hw *wxhw) +{ + struct wx_eeprom_info *eeprom = &wxhw->eeprom; + u16 eeprom_size; + u16 data = 0x80; + + if (eeprom->type == wx_eeprom_uninitialized) { + eeprom->semaphore_delay = 10; + eeprom->type = wx_eeprom_none; + + if (!(rd32(wxhw, WX_SPI_STATUS) & + WX_SPI_STATUS_FLASH_BYPASS)) { + eeprom->type = wx_flash; + + eeprom_size = 4096; + eeprom->word_size = eeprom_size >> 1; + + wx_dbg(wxhw, "Eeprom params: type = %d, size = %d\n", + eeprom->type, eeprom->word_size); + } + } + + if (wxhw->mac.type == wx_mac_sp) { + if (wx_read_ee_hostif(wxhw, WX_SW_REGION_PTR, &data)) { + wx_err(wxhw, "NVM Read Error\n"); + return; + } + data = data >> 1; + } + + eeprom->sw_region_offset = data; +} +EXPORT_SYMBOL(wx_init_eeprom_params); + +/** + * wx_get_mac_addr - Generic get MAC address + * @wxhw: pointer to hardware structure + * @mac_addr: Adapter MAC address + * + * Reads the adapter's MAC address from first Receive Address Register (RAR0) + * A reset of the adapter must be performed prior to calling this function + * in order for the MAC address to have been loaded from the EEPROM into RAR0 + **/ +void wx_get_mac_addr(struct wx_hw *wxhw, u8 *mac_addr) +{ + u32 rar_high; + u32 rar_low; + u16 i; + + wr32(wxhw, WX_PSR_MAC_SWC_IDX, 0); + rar_high = rd32(wxhw, WX_PSR_MAC_SWC_AD_H); + rar_low = rd32(wxhw, WX_PSR_MAC_SWC_AD_L); + + for (i = 0; i < 2; i++) + mac_addr[i] = (u8)(rar_high >> (1 - i) * 8); + + for (i = 0; i < 4; i++) + mac_addr[i + 2] = (u8)(rar_low >> (3 - i) * 8); +} +EXPORT_SYMBOL(wx_get_mac_addr); + +/** + * wx_set_rar - Set Rx address register + * @wxhw: pointer to hardware structure + * @index: Receive address register to write + * @addr: Address to put into receive address register + * @pools: VMDq "set" or "pool" index + * @enable_addr: set flag that address is active + * + * Puts an ethernet address into a receive address register. + **/ +int wx_set_rar(struct wx_hw *wxhw, u32 index, u8 *addr, u64 pools, + u32 enable_addr) +{ + u32 rar_entries = wxhw->mac.num_rar_entries; + u32 rar_low, rar_high; + + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + wx_err(wxhw, "RAR index %d is out of range.\n", index); + return -EINVAL; + } + + /* select the MAC address */ + wr32(wxhw, WX_PSR_MAC_SWC_IDX, index); + + /* setup VMDq pool mapping */ + wr32(wxhw, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF); + if (wxhw->mac.type == wx_mac_sp) + wr32(wxhw, WX_PSR_MAC_SWC_VM_H, pools >> 32); + + /* HW expects these in little endian so we reverse the byte + * order from network order (big endian) to little endian + * + * Some parts put the VMDq setting in the extra RAH bits, + * so save everything except the lower 16 bits that hold part + * of the address and the address valid bit. + */ + rar_low = ((u32)addr[5] | + ((u32)addr[4] << 8) | + ((u32)addr[3] << 16) | + ((u32)addr[2] << 24)); + rar_high = ((u32)addr[1] | + ((u32)addr[0] << 8)); + if (enable_addr != 0) + rar_high |= WX_PSR_MAC_SWC_AD_H_AV; + + wr32(wxhw, WX_PSR_MAC_SWC_AD_L, rar_low); + wr32m(wxhw, WX_PSR_MAC_SWC_AD_H, + (WX_PSR_MAC_SWC_AD_H_AD(~0) | + WX_PSR_MAC_SWC_AD_H_ADTYPE(~0) | + WX_PSR_MAC_SWC_AD_H_AV), + rar_high); + + return 0; +} +EXPORT_SYMBOL(wx_set_rar); + +/** + * wx_clear_rar - Remove Rx address register + * @wxhw: pointer to hardware structure + * @index: Receive address register to write + * + * Clears an ethernet address from a receive address register. + **/ +int wx_clear_rar(struct wx_hw *wxhw, u32 index) +{ + u32 rar_entries = wxhw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + wx_err(wxhw, "RAR index %d is out of range.\n", index); + return -EINVAL; + } + + /* Some parts put the VMDq setting in the extra RAH bits, + * so save everything except the lower 16 bits that hold part + * of the address and the address valid bit. + */ + wr32(wxhw, WX_PSR_MAC_SWC_IDX, index); + + wr32(wxhw, WX_PSR_MAC_SWC_VM_L, 0); + wr32(wxhw, WX_PSR_MAC_SWC_VM_H, 0); + + wr32(wxhw, WX_PSR_MAC_SWC_AD_L, 0); + wr32m(wxhw, WX_PSR_MAC_SWC_AD_H, + (WX_PSR_MAC_SWC_AD_H_AD(~0) | + WX_PSR_MAC_SWC_AD_H_ADTYPE(~0) | + WX_PSR_MAC_SWC_AD_H_AV), + 0); + + return 0; +} +EXPORT_SYMBOL(wx_clear_rar); + +/** + * wx_clear_vmdq - Disassociate a VMDq pool index from a rx address + * @wxhw: pointer to hardware struct + * @rar: receive address register index to disassociate + * @vmdq: VMDq pool index to remove from the rar + **/ +static int wx_clear_vmdq(struct wx_hw *wxhw, u32 rar, u32 __maybe_unused vmdq) +{ + u32 rar_entries = wxhw->mac.num_rar_entries; + u32 mpsar_lo, mpsar_hi; + + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + wx_err(wxhw, "RAR index %d is out of range.\n", rar); + return -EINVAL; + } + + wr32(wxhw, WX_PSR_MAC_SWC_IDX, rar); + mpsar_lo = rd32(wxhw, WX_PSR_MAC_SWC_VM_L); + mpsar_hi = rd32(wxhw, WX_PSR_MAC_SWC_VM_H); + + if (!mpsar_lo && !mpsar_hi) + return 0; + + /* was that the last pool using this rar? */ + if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0) + wx_clear_rar(wxhw, rar); + + return 0; +} + +/** + * wx_init_uta_tables - Initialize the Unicast Table Array + * @wxhw: pointer to hardware structure + **/ +static void wx_init_uta_tables(struct wx_hw *wxhw) +{ + int i; + + wx_dbg(wxhw, " Clearing UTA\n"); + + for (i = 0; i < 128; i++) + wr32(wxhw, WX_PSR_UC_TBL(i), 0); +} + +/** + * wx_init_rx_addrs - Initializes receive address filters. + * @wxhw: pointer to hardware structure + * + * Places the MAC address in receive address register 0 and clears the rest + * of the receive address registers. Clears the multicast table. Assumes + * the receiver is in reset when the routine is called. + **/ +void wx_init_rx_addrs(struct wx_hw *wxhw) +{ + u32 rar_entries = wxhw->mac.num_rar_entries; + u32 psrctl; + int i; + + /* If the current mac address is valid, assume it is a software override + * to the permanent address. + * Otherwise, use the permanent address from the eeprom. + */ + if (!is_valid_ether_addr(wxhw->mac.addr)) { + /* Get the MAC address from the RAR0 for later reference */ + wx_get_mac_addr(wxhw, wxhw->mac.addr); + wx_dbg(wxhw, "Keeping Current RAR0 Addr = %pM\n", wxhw->mac.addr); + } else { + /* Setup the receive address. */ + wx_dbg(wxhw, "Overriding MAC Address in RAR[0]\n"); + wx_dbg(wxhw, "New MAC Addr = %pM\n", wxhw->mac.addr); + + wx_set_rar(wxhw, 0, wxhw->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV); + + if (wxhw->mac.type == wx_mac_sp) { + /* clear VMDq pool/queue selection for RAR 0 */ + wx_clear_vmdq(wxhw, 0, WX_CLEAR_VMDQ_ALL); + } + } + + /* Zero out the other receive addresses. */ + wx_dbg(wxhw, "Clearing RAR[1-%d]\n", rar_entries - 1); + for (i = 1; i < rar_entries; i++) { + wr32(wxhw, WX_PSR_MAC_SWC_IDX, i); + wr32(wxhw, WX_PSR_MAC_SWC_AD_L, 0); + wr32(wxhw, WX_PSR_MAC_SWC_AD_H, 0); + } + + /* Clear the MTA */ + wxhw->addr_ctrl.mta_in_use = 0; + psrctl = rd32(wxhw, WX_PSR_CTL); + psrctl &= ~(WX_PSR_CTL_MO | WX_PSR_CTL_MFE); + psrctl |= wxhw->mac.mc_filter_type << WX_PSR_CTL_MO_SHIFT; + wr32(wxhw, WX_PSR_CTL, psrctl); + wx_dbg(wxhw, " Clearing MTA\n"); + for (i = 0; i < wxhw->mac.mcft_size; i++) + wr32(wxhw, WX_PSR_MC_TBL(i), 0); + + wx_init_uta_tables(wxhw); +} +EXPORT_SYMBOL(wx_init_rx_addrs); + +void wx_disable_rx(struct wx_hw *wxhw) +{ + u32 pfdtxgswc; + u32 rxctrl; + + rxctrl = rd32(wxhw, WX_RDB_PB_CTL); + if (rxctrl & WX_RDB_PB_CTL_RXEN) { + pfdtxgswc = rd32(wxhw, WX_PSR_CTL); + if (pfdtxgswc & WX_PSR_CTL_SW_EN) { + pfdtxgswc &= ~WX_PSR_CTL_SW_EN; + wr32(wxhw, WX_PSR_CTL, pfdtxgswc); + wxhw->mac.set_lben = true; + } else { + wxhw->mac.set_lben = false; + } + rxctrl &= ~WX_RDB_PB_CTL_RXEN; + wr32(wxhw, WX_RDB_PB_CTL, rxctrl); + + if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { + /* disable mac receiver */ + wr32m(wxhw, WX_MAC_RX_CFG, + WX_MAC_RX_CFG_RE, 0); + } + } +} +EXPORT_SYMBOL(wx_disable_rx); + +/** + * wx_disable_pcie_master - Disable PCI-express master access + * @wxhw: pointer to hardware structure + * + * Disables PCI-Express master access and verifies there are no pending + * requests. + **/ +int wx_disable_pcie_master(struct wx_hw *wxhw) +{ + int status = 0; + u32 val; + + /* Always set this bit to ensure any future transactions are blocked */ + pci_clear_master(wxhw->pdev); + + /* Exit if master requests are blocked */ + if (!(rd32(wxhw, WX_PX_TRANSACTION_PENDING))) + return 0; + + /* Poll for master request bit to clear */ + status = read_poll_timeout(rd32, val, !val, 100, WX_PCI_MASTER_DISABLE_TIMEOUT, + false, wxhw, WX_PX_TRANSACTION_PENDING); + if (status < 0) + wx_err(wxhw, "PCIe transaction pending bit did not clear.\n"); + + return status; +} +EXPORT_SYMBOL(wx_disable_pcie_master); + +/** + * wx_stop_adapter - Generic stop Tx/Rx units + * @wxhw: pointer to hardware structure + * + * Sets the adapter_stopped flag within wx_hw struct. Clears interrupts, + * disables transmit and receive units. The adapter_stopped flag is used by + * the shared code and drivers to determine if the adapter is in a stopped + * state and should not touch the hardware. + **/ +int wx_stop_adapter(struct wx_hw *wxhw) +{ + u16 i; + + /* Set the adapter_stopped flag so other driver functions stop touching + * the hardware + */ + wxhw->adapter_stopped = true; + + /* Disable the receive unit */ + wx_disable_rx(wxhw); + + /* Set interrupt mask to stop interrupts from being generated */ + wx_intr_disable(wxhw, WX_INTR_ALL); + + /* Clear any pending interrupts, flush previous writes */ + wr32(wxhw, WX_PX_MISC_IC, 0xffffffff); + wr32(wxhw, WX_BME_CTL, 0x3); + + /* Disable the transmit unit. Each queue must be disabled. */ + for (i = 0; i < wxhw->mac.max_tx_queues; i++) { + wr32m(wxhw, WX_PX_TR_CFG(i), + WX_PX_TR_CFG_SWFLSH | WX_PX_TR_CFG_ENABLE, + WX_PX_TR_CFG_SWFLSH); + } + + /* Disable the receive unit by stopping each queue */ + for (i = 0; i < wxhw->mac.max_rx_queues; i++) { + wr32m(wxhw, WX_PX_RR_CFG(i), + WX_PX_RR_CFG_RR_EN, 0); + } + + /* flush all queues disables */ + WX_WRITE_FLUSH(wxhw); + + /* Prevent the PCI-E bus from hanging by disabling PCI-E master + * access and verify no pending requests + */ + return wx_disable_pcie_master(wxhw); +} +EXPORT_SYMBOL(wx_stop_adapter); + +void wx_reset_misc(struct wx_hw *wxhw) +{ + int i; + + /* receive packets that size > 2048 */ + wr32m(wxhw, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE); + + /* clear counters on read */ + wr32m(wxhw, WX_MMC_CONTROL, + WX_MMC_CONTROL_RSTONRD, WX_MMC_CONTROL_RSTONRD); + + wr32m(wxhw, WX_MAC_RX_FLOW_CTRL, + WX_MAC_RX_FLOW_CTRL_RFE, WX_MAC_RX_FLOW_CTRL_RFE); + + wr32(wxhw, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + + wr32m(wxhw, WX_MIS_RST_ST, + WX_MIS_RST_ST_RST_INIT, 0x1E00); + + /* errata 4: initialize mng flex tbl and wakeup flex tbl*/ + wr32(wxhw, WX_PSR_MNG_FLEX_SEL, 0); + for (i = 0; i < 16; i++) { + wr32(wxhw, WX_PSR_MNG_FLEX_DW_L(i), 0); + wr32(wxhw, WX_PSR_MNG_FLEX_DW_H(i), 0); + wr32(wxhw, WX_PSR_MNG_FLEX_MSK(i), 0); + } + wr32(wxhw, WX_PSR_LAN_FLEX_SEL, 0); + for (i = 0; i < 16; i++) { + wr32(wxhw, WX_PSR_LAN_FLEX_DW_L(i), 0); + wr32(wxhw, WX_PSR_LAN_FLEX_DW_H(i), 0); + wr32(wxhw, WX_PSR_LAN_FLEX_MSK(i), 0); + } + + /* set pause frame dst mac addr */ + wr32(wxhw, WX_RDB_PFCMACDAL, 0xC2000001); + wr32(wxhw, WX_RDB_PFCMACDAH, 0x0180); +} +EXPORT_SYMBOL(wx_reset_misc); + +/** + * wx_get_pcie_msix_counts - Gets MSI-X vector count + * @wxhw: pointer to hardware structure + * @msix_count: number of MSI interrupts that can be obtained + * @max_msix_count: number of MSI interrupts that mac need + * + * Read PCIe configuration space, and get the MSI-X vector count from + * the capabilities table. + **/ +int wx_get_pcie_msix_counts(struct wx_hw *wxhw, u16 *msix_count, u16 max_msix_count) +{ + struct pci_dev *pdev = wxhw->pdev; + struct device *dev = &pdev->dev; + int pos; + + *msix_count = 1; + pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX); + if (!pos) { + dev_err(dev, "Unable to find MSI-X Capabilities\n"); + return -EINVAL; + } + pci_read_config_word(pdev, + pos + PCI_MSIX_FLAGS, + msix_count); + *msix_count &= WX_PCIE_MSIX_TBL_SZ_MASK; + /* MSI-X count is zero-based in HW */ + *msix_count += 1; + + if (*msix_count > max_msix_count) + *msix_count = max_msix_count; + + return 0; +} +EXPORT_SYMBOL(wx_get_pcie_msix_counts); + +int wx_sw_init(struct wx_hw *wxhw) +{ + struct pci_dev *pdev = wxhw->pdev; + u32 ssid = 0; + int err = 0; + + wxhw->vendor_id = pdev->vendor; + wxhw->device_id = pdev->device; + wxhw->revision_id = pdev->revision; + wxhw->oem_svid = pdev->subsystem_vendor; + wxhw->oem_ssid = pdev->subsystem_device; + wxhw->bus.device = PCI_SLOT(pdev->devfn); + wxhw->bus.func = PCI_FUNC(pdev->devfn); + + if (wxhw->oem_svid == PCI_VENDOR_ID_WANGXUN) { + wxhw->subsystem_vendor_id = pdev->subsystem_vendor; + wxhw->subsystem_device_id = pdev->subsystem_device; + } else { + err = wx_flash_read_dword(wxhw, 0xfffdc, &ssid); + if (!err) + wxhw->subsystem_device_id = swab16((u16)ssid); + + return err; + } + + return 0; +} +EXPORT_SYMBOL(wx_sw_init); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h new file mode 100644 index 000000000000..a0652f5e9939 --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _WX_HW_H_ +#define _WX_HW_H_ + +int wx_check_flash_load(struct wx_hw *hw, u32 check_bit); +void wx_control_hw(struct wx_hw *wxhw, bool drv); +int wx_mng_present(struct wx_hw *wxhw); +int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, + u32 length, u32 timeout, bool return_data); +int wx_read_ee_hostif(struct wx_hw *wxhw, u16 offset, u16 *data); +int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, + u16 offset, u16 words, u16 *data); +int wx_reset_hostif(struct wx_hw *wxhw); +void wx_init_eeprom_params(struct wx_hw *wxhw); +void wx_get_mac_addr(struct wx_hw *wxhw, u8 *mac_addr); +int wx_set_rar(struct wx_hw *wxhw, u32 index, u8 *addr, u64 pools, u32 enable_addr); +int wx_clear_rar(struct wx_hw *wxhw, u32 index); +void wx_init_rx_addrs(struct wx_hw *wxhw); +void wx_disable_rx(struct wx_hw *wxhw); +int wx_disable_pcie_master(struct wx_hw *wxhw); +int wx_stop_adapter(struct wx_hw *wxhw); +void wx_reset_misc(struct wx_hw *wxhw); +int wx_get_pcie_msix_counts(struct wx_hw *wxhw, u16 *msix_count, u16 max_msix_count); +int wx_sw_init(struct wx_hw *wxhw); + +#endif /* _WX_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h new file mode 100644 index 000000000000..1cbeef8230bf --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -0,0 +1,352 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _WX_TYPE_H_ +#define _WX_TYPE_H_ + +/* Vendor ID */ +#ifndef PCI_VENDOR_ID_WANGXUN +#define PCI_VENDOR_ID_WANGXUN 0x8088 +#endif + +#define WX_NCSI_SUP 0x8000 +#define WX_NCSI_MASK 0x8000 +#define WX_WOL_SUP 0x4000 +#define WX_WOL_MASK 0x4000 + +/* MSI-X capability fields masks */ +#define WX_PCIE_MSIX_TBL_SZ_MASK 0x7FF +#define WX_PCI_LINK_STATUS 0xB2 + +/**************** Global Registers ****************************/ +/* chip control Registers */ +#define WX_MIS_PWR 0x10000 +#define WX_MIS_RST 0x1000C +#define WX_MIS_RST_LAN_RST(_i) BIT((_i) + 1) +#define WX_MIS_RST_SW_RST BIT(0) +#define WX_MIS_ST 0x10028 +#define WX_MIS_ST_MNG_INIT_DN BIT(0) +#define WX_MIS_SWSM 0x1002C +#define WX_MIS_SWSM_SMBI BIT(0) +#define WX_MIS_RST_ST 0x10030 +#define WX_MIS_RST_ST_RST_INI_SHIFT 8 +#define WX_MIS_RST_ST_RST_INIT (0xFF << WX_MIS_RST_ST_RST_INI_SHIFT) + +/* FMGR Registers */ +#define WX_SPI_CMD 0x10104 +#define WX_SPI_CMD_READ_DWORD 0x1 +#define WX_SPI_CLK_DIV 0x3 +#define WX_SPI_CMD_CMD(_v) (((_v) & 0x7) << 28) +#define WX_SPI_CMD_CLK(_v) (((_v) & 0x7) << 25) +#define WX_SPI_CMD_ADDR(_v) (((_v) & 0xFFFFFF)) +#define WX_SPI_DATA 0x10108 +#define WX_SPI_DATA_BYPASS BIT(31) +#define WX_SPI_DATA_STATUS(_v) (((_v) & 0xFF) << 16) +#define WX_SPI_DATA_OP_DONE BIT(0) +#define WX_SPI_STATUS 0x1010C +#define WX_SPI_STATUS_OPDONE BIT(0) +#define WX_SPI_STATUS_FLASH_BYPASS BIT(31) +#define WX_SPI_ILDR_STATUS 0x10120 + +/* Sensors for PVT(Process Voltage Temperature) */ +#define WX_TS_EN 0x10304 +#define WX_TS_EN_ENA BIT(0) +#define WX_TS_ALARM_THRE 0x1030C +#define WX_TS_DALARM_THRE 0x10310 +#define WX_TS_INT_EN 0x10314 +#define WX_TS_INT_EN_DALARM_INT_EN BIT(1) +#define WX_TS_INT_EN_ALARM_INT_EN BIT(0) +#define WX_TS_ALARM_ST 0x10318 +#define WX_TS_ALARM_ST_DALARM BIT(1) +#define WX_TS_ALARM_ST_ALARM BIT(0) + +/************************* Port Registers ************************************/ +/* port cfg Registers */ +#define WX_CFG_PORT_CTL 0x14400 +#define WX_CFG_PORT_CTL_DRV_LOAD BIT(3) + +/*********************** Transmit DMA registers **************************/ +/* transmit global control */ +#define WX_TDM_CTL 0x18000 +/* TDM CTL BIT */ +#define WX_TDM_CTL_TE BIT(0) /* Transmit Enable */ + +/***************************** RDB registers *********************************/ +/* receive packet buffer */ +#define WX_RDB_PB_CTL 0x19000 +#define WX_RDB_PB_CTL_RXEN BIT(31) /* Enable Receiver */ +#define WX_RDB_PB_CTL_DISABLED BIT(0) +/* statistic */ +#define WX_RDB_PFCMACDAL 0x19210 +#define WX_RDB_PFCMACDAH 0x19214 + +/******************************* PSR Registers *******************************/ +/* psr control */ +#define WX_PSR_CTL 0x15000 +/* Header split receive */ +#define WX_PSR_CTL_SW_EN BIT(18) +#define WX_PSR_CTL_RSC_ACK BIT(17) +#define WX_PSR_CTL_RSC_DIS BIT(16) +#define WX_PSR_CTL_PCSD BIT(13) +#define WX_PSR_CTL_IPPCSE BIT(12) +#define WX_PSR_CTL_BAM BIT(10) +#define WX_PSR_CTL_UPE BIT(9) +#define WX_PSR_CTL_MPE BIT(8) +#define WX_PSR_CTL_MFE BIT(7) +#define WX_PSR_CTL_MO_SHIFT 5 +#define WX_PSR_CTL_MO (0x3 << WX_PSR_CTL_MO_SHIFT) +#define WX_PSR_CTL_TPE BIT(4) +/* mcasst/ucast overflow tbl */ +#define WX_PSR_MC_TBL(_i) (0x15200 + ((_i) * 4)) +#define WX_PSR_UC_TBL(_i) (0x15400 + ((_i) * 4)) + +/* Management */ +#define WX_PSR_MNG_FLEX_SEL 0x1582C +#define WX_PSR_MNG_FLEX_DW_L(_i) (0x15A00 + ((_i) * 16)) +#define WX_PSR_MNG_FLEX_DW_H(_i) (0x15A04 + ((_i) * 16)) +#define WX_PSR_MNG_FLEX_MSK(_i) (0x15A08 + ((_i) * 16)) +#define WX_PSR_LAN_FLEX_SEL 0x15B8C +#define WX_PSR_LAN_FLEX_DW_L(_i) (0x15C00 + ((_i) * 16)) +#define WX_PSR_LAN_FLEX_DW_H(_i) (0x15C04 + ((_i) * 16)) +#define WX_PSR_LAN_FLEX_MSK(_i) (0x15C08 + ((_i) * 16)) + +/* mac switcher */ +#define WX_PSR_MAC_SWC_AD_L 0x16200 +#define WX_PSR_MAC_SWC_AD_H 0x16204 +#define WX_PSR_MAC_SWC_AD_H_AD(v) (((v) & 0xFFFF)) +#define WX_PSR_MAC_SWC_AD_H_ADTYPE(v) (((v) & 0x1) << 30) +#define WX_PSR_MAC_SWC_AD_H_AV BIT(31) +#define WX_PSR_MAC_SWC_VM_L 0x16208 +#define WX_PSR_MAC_SWC_VM_H 0x1620C +#define WX_PSR_MAC_SWC_IDX 0x16210 +#define WX_CLEAR_VMDQ_ALL 0xFFFFFFFFU + +/************************************** MNG ********************************/ +#define WX_MNG_SWFW_SYNC 0x1E008 +#define WX_MNG_SWFW_SYNC_SW_MB BIT(2) +#define WX_MNG_SWFW_SYNC_SW_FLASH BIT(3) +#define WX_MNG_MBOX 0x1E100 +#define WX_MNG_MBOX_CTL 0x1E044 +#define WX_MNG_MBOX_CTL_SWRDY BIT(0) +#define WX_MNG_MBOX_CTL_FWRDY BIT(2) + +/************************************* ETH MAC *****************************/ +#define WX_MAC_TX_CFG 0x11000 +#define WX_MAC_TX_CFG_TE BIT(0) +#define WX_MAC_RX_CFG 0x11004 +#define WX_MAC_RX_CFG_RE BIT(0) +#define WX_MAC_RX_CFG_JE BIT(8) +#define WX_MAC_PKT_FLT 0x11008 +#define WX_MAC_PKT_FLT_PR BIT(0) /* promiscuous mode */ +#define WX_MAC_RX_FLOW_CTRL 0x11090 +#define WX_MAC_RX_FLOW_CTRL_RFE BIT(0) /* receive fc enable */ +#define WX_MMC_CONTROL 0x11800 +#define WX_MMC_CONTROL_RSTONRD BIT(2) /* reset on read */ + +/********************************* BAR registers ***************************/ +/* Interrupt Registers */ +#define WX_BME_CTL 0x12020 +#define WX_PX_MISC_IC 0x100 +#define WX_PX_IMS(_i) (0x140 + (_i) * 4) +#define WX_PX_TRANSACTION_PENDING 0x168 + +/* transmit DMA Registers */ +#define WX_PX_TR_CFG(_i) (0x03010 + ((_i) * 0x40)) +/* Transmit Config masks */ +#define WX_PX_TR_CFG_ENABLE BIT(0) /* Ena specific Tx Queue */ +#define WX_PX_TR_CFG_TR_SIZE_SHIFT 1 /* tx desc number per ring */ +#define WX_PX_TR_CFG_SWFLSH BIT(26) /* Tx Desc. wr-bk flushing */ +#define WX_PX_TR_CFG_WTHRESH_SHIFT 16 /* shift to WTHRESH bits */ +#define WX_PX_TR_CFG_THRE_SHIFT 8 + +/* Receive DMA Registers */ +#define WX_PX_RR_CFG(_i) (0x01010 + ((_i) * 0x40)) +/* PX_RR_CFG bit definitions */ +#define WX_PX_RR_CFG_RR_EN BIT(0) + +/* Number of 80 microseconds we wait for PCI Express master disable */ +#define WX_PCI_MASTER_DISABLE_TIMEOUT 80000 + +/****************** Manageablility Host Interface defines ********************/ +#define WX_HI_MAX_BLOCK_BYTE_LENGTH 256 /* Num of bytes in range */ +#define WX_HI_COMMAND_TIMEOUT 1000 /* Process HI command limit */ + +#define FW_READ_SHADOW_RAM_CMD 0x31 +#define FW_READ_SHADOW_RAM_LEN 0x6 +#define FW_DEFAULT_CHECKSUM 0xFF /* checksum always 0xFF */ +#define FW_NVM_DATA_OFFSET 3 +#define FW_MAX_READ_BUFFER_SIZE 244 +#define FW_RESET_CMD 0xDF +#define FW_RESET_LEN 0x2 +#define FW_CEM_HDR_LEN 0x4 +#define FW_CEM_CMD_RESERVED 0X0 +#define FW_CEM_MAX_RETRIES 3 +#define FW_CEM_RESP_STATUS_SUCCESS 0x1 + +#define WX_SW_REGION_PTR 0x1C + +/* Host Interface Command Structures */ +struct wx_hic_hdr { + u8 cmd; + u8 buf_len; + union { + u8 cmd_resv; + u8 ret_status; + } cmd_or_resp; + u8 checksum; +}; + +struct wx_hic_hdr2_req { + u8 cmd; + u8 buf_lenh; + u8 buf_lenl; + u8 checksum; +}; + +struct wx_hic_hdr2_rsp { + u8 cmd; + u8 buf_lenl; + u8 buf_lenh_status; /* 7-5: high bits of buf_len, 4-0: status */ + u8 checksum; +}; + +union wx_hic_hdr2 { + struct wx_hic_hdr2_req req; + struct wx_hic_hdr2_rsp rsp; +}; + +/* These need to be dword aligned */ +struct wx_hic_read_shadow_ram { + union wx_hic_hdr2 hdr; + u32 address; + u16 length; + u16 pad2; + u16 data; + u16 pad3; +}; + +struct wx_hic_reset { + struct wx_hic_hdr hdr; + u16 lan_id; + u16 reset_type; +}; + +/* Bus parameters */ +struct wx_bus_info { + u8 func; + u16 device; +}; + +struct wx_thermal_sensor_data { + s16 temp; + s16 alarm_thresh; + s16 dalarm_thresh; +}; + +enum wx_mac_type { + wx_mac_unknown = 0, + wx_mac_sp, + wx_mac_em +}; + +struct wx_mac_info { + enum wx_mac_type type; + bool set_lben; + u8 addr[ETH_ALEN]; + u8 perm_addr[ETH_ALEN]; + s32 mc_filter_type; + u32 mcft_size; + u32 num_rar_entries; + u32 max_tx_queues; + u32 max_rx_queues; + + u16 max_msix_vectors; + struct wx_thermal_sensor_data sensor; +}; + +enum wx_eeprom_type { + wx_eeprom_uninitialized = 0, + wx_eeprom_spi, + wx_flash, + wx_eeprom_none /* No NVM support */ +}; + +struct wx_eeprom_info { + enum wx_eeprom_type type; + u32 semaphore_delay; + u16 word_size; + u16 sw_region_offset; +}; + +struct wx_addr_filter_info { + u32 num_mc_addrs; + u32 mta_in_use; + bool user_set_promisc; +}; + +enum wx_reset_type { + WX_LAN_RESET = 0, + WX_SW_RESET, + WX_GLOBAL_RESET +}; + +struct wx_hw { + u8 __iomem *hw_addr; + struct pci_dev *pdev; + struct wx_bus_info bus; + struct wx_mac_info mac; + struct wx_eeprom_info eeprom; + struct wx_addr_filter_info addr_ctrl; + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + u16 oem_ssid; + u16 oem_svid; + bool adapter_stopped; + enum wx_reset_type reset_type; +}; + +#define WX_INTR_ALL (~0ULL) + +/* register operations */ +#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) +#define rd32(a, reg) readl((a)->hw_addr + (reg)) +#define rd32a(a, reg, offset) ( \ + rd32((a), (reg) + ((offset) << 2))) +#define wr32a(a, reg, off, val) \ + wr32((a), (reg) + ((off) << 2), (val)) + +static inline u32 +rd32m(struct wx_hw *wxhw, u32 reg, u32 mask) +{ + u32 val; + + val = rd32(wxhw, reg); + return val & mask; +} + +static inline void +wr32m(struct wx_hw *wxhw, u32 reg, u32 mask, u32 field) +{ + u32 val; + + val = rd32(wxhw, reg); + val = ((val & ~mask) | (field & mask)); + + wr32(wxhw, reg, val); +} + +/* On some domestic CPU platforms, sometimes IO is not synchronized with + * flushing memory, here use readl() to flush PCI read and write. + */ +#define WX_WRITE_FLUSH(H) rd32(H, WX_MIS_PWR) + +#define wx_err(wxhw, fmt, arg...) \ + dev_err(&(wxhw)->pdev->dev, fmt, ##arg) + +#define wx_dbg(wxhw, fmt, arg...) \ + dev_dbg(&(wxhw)->pdev->dev, fmt, ##arg) + +#endif /* _WX_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/Makefile b/drivers/net/ethernet/wangxun/ngbe/Makefile index 0baf75907496..391c2cbc1bb4 100644 --- a/drivers/net/ethernet/wangxun/ngbe/Makefile +++ b/drivers/net/ethernet/wangxun/ngbe/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_NGBE) += ngbe.o -ngbe-objs := ngbe_main.o +ngbe-objs := ngbe_main.o ngbe_hw.o diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe.h b/drivers/net/ethernet/wangxun/ngbe/ngbe.h index f5fa6e5238cc..af147ca8605c 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe.h @@ -11,12 +11,67 @@ #define NGBE_MAX_RX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) #define NGBE_MAX_TX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) +#define NGBE_ETH_LENGTH_OF_ADDRESS 6 +#define NGBE_MAX_MSIX_VECTORS 0x09 +#define NGBE_RAR_ENTRIES 32 + +/* TX/RX descriptor defines */ +#define NGBE_DEFAULT_TXD 512 /* default ring size */ +#define NGBE_DEFAULT_TX_WORK 256 +#define NGBE_MAX_TXD 8192 +#define NGBE_MIN_TXD 128 + +#define NGBE_DEFAULT_RXD 512 /* default ring size */ +#define NGBE_DEFAULT_RX_WORK 256 +#define NGBE_MAX_RXD 8192 +#define NGBE_MIN_RXD 128 + +#define NGBE_MAC_STATE_DEFAULT 0x1 +#define NGBE_MAC_STATE_MODIFIED 0x2 +#define NGBE_MAC_STATE_IN_USE 0x4 + +struct ngbe_mac_addr { + u8 addr[ETH_ALEN]; + u16 state; /* bitmask */ + u64 pools; +}; + /* board specific private data structure */ struct ngbe_adapter { u8 __iomem *io_addr; /* Mainly for iounmap use */ /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; + + /* structs defined in ngbe_hw.h */ + struct ngbe_hw hw; + struct ngbe_mac_addr *mac_table; + u16 msg_enable; + + /* Tx fast path data */ + int num_tx_queues; + u16 tx_itr_setting; + u16 tx_work_limit; + + /* Rx fast path data */ + int num_rx_queues; + u16 rx_itr_setting; + u16 rx_work_limit; + + int num_q_vectors; /* current number of q_vectors for device */ + int max_q_vectors; /* upper limit of q_vectors for device */ + + u32 tx_ring_count; + u32 rx_ring_count; + +#define NGBE_MAX_RETA_ENTRIES 128 + u8 rss_indir_tbl[NGBE_MAX_RETA_ENTRIES]; + +#define NGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ + u32 *rss_key; + u32 wol; + + u16 bd_number; }; extern char ngbe_driver_name[]; diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c new file mode 100644 index 000000000000..0e3923b3737e --- /dev/null +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/etherdevice.h> +#include <linux/iopoll.h> +#include <linux/pci.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_hw.h" +#include "ngbe_type.h" +#include "ngbe_hw.h" +#include "ngbe.h" + +int ngbe_eeprom_chksum_hostif(struct ngbe_hw *hw) +{ + struct wx_hic_read_shadow_ram buffer; + struct wx_hw *wxhw = &hw->wxhw; + int status; + int tmp; + + buffer.hdr.req.cmd = NGBE_FW_EEPROM_CHECKSUM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = 0; + buffer.hdr.req.checksum = NGBE_FW_CMD_DEFAULT_CHECKSUM; + /* convert offset from words to bytes */ + buffer.address = 0; + /* one word */ + buffer.length = 0; + + status = wx_host_interface_command(wxhw, (u32 *)&buffer, sizeof(buffer), + WX_HI_COMMAND_TIMEOUT, false); + + if (status < 0) + return status; + tmp = rd32a(wxhw, WX_MNG_MBOX, 1); + if (tmp == NGBE_FW_CMD_ST_PASS) + return 0; + return -EIO; +} + +static int ngbe_reset_misc(struct ngbe_hw *hw) +{ + struct wx_hw *wxhw = &hw->wxhw; + + wx_reset_misc(wxhw); + if (hw->mac_type == ngbe_mac_type_rgmii) + wr32(wxhw, NGBE_MDIO_CLAUSE_SELECT, 0xF); + if (hw->gpio_ctrl) { + /* gpio0 is used to power on/off control*/ + wr32(wxhw, NGBE_GPIO_DDR, 0x1); + wr32(wxhw, NGBE_GPIO_DR, NGBE_GPIO_DR_0); + } + return 0; +} + +/** + * ngbe_reset_hw - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, perform a PHY reset, and perform a link (MAC) + * reset. + **/ +int ngbe_reset_hw(struct ngbe_hw *hw) +{ + struct wx_hw *wxhw = &hw->wxhw; + int status = 0; + u32 reset = 0; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + status = wx_stop_adapter(wxhw); + if (status != 0) + return status; + reset = WX_MIS_RST_LAN_RST(wxhw->bus.func); + wr32(wxhw, WX_MIS_RST, reset | rd32(wxhw, WX_MIS_RST)); + ngbe_reset_misc(hw); + + /* Store the permanent mac address */ + wx_get_mac_addr(wxhw, wxhw->mac.perm_addr); + + /* reset num_rar_entries to 128 */ + wxhw->mac.num_rar_entries = NGBE_RAR_ENTRIES; + wx_init_rx_addrs(wxhw); + pci_set_master(wxhw->pdev); + + return 0; +} diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h new file mode 100644 index 000000000000..42476a3fe57c --- /dev/null +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * WangXun Gigabit PCI Express Linux driver + * Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. + */ + +#ifndef _NGBE_HW_H_ +#define _NGBE_HW_H_ + +int ngbe_eeprom_chksum_hostif(struct ngbe_hw *hw); +int ngbe_reset_hw(struct ngbe_hw *hw); +#endif /* _NGBE_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index 7674cb6e5700..f0b24366da18 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -8,7 +8,12 @@ #include <linux/string.h> #include <linux/aer.h> #include <linux/etherdevice.h> +#include <net/ip.h> +#include "../libwx/wx_type.h" +#include "../libwx/wx_hw.h" +#include "ngbe_type.h" +#include "ngbe_hw.h" #include "ngbe.h" char ngbe_driver_name[] = "ngbe"; @@ -34,6 +39,247 @@ static const struct pci_device_id ngbe_pci_tbl[] = { { .device = 0 } }; +static void ngbe_mac_set_default_filter(struct ngbe_adapter *adapter, u8 *addr) +{ + struct ngbe_hw *hw = &adapter->hw; + + memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); + adapter->mac_table[0].pools = 1ULL; + adapter->mac_table[0].state = (NGBE_MAC_STATE_DEFAULT | + NGBE_MAC_STATE_IN_USE); + wx_set_rar(&hw->wxhw, 0, adapter->mac_table[0].addr, + adapter->mac_table[0].pools, + WX_PSR_MAC_SWC_AD_H_AV); +} + +/** + * ngbe_init_type_code - Initialize the shared code + * @hw: pointer to hardware structure + **/ +static void ngbe_init_type_code(struct ngbe_hw *hw) +{ + int wol_mask = 0, ncsi_mask = 0; + struct wx_hw *wxhw = &hw->wxhw; + u16 type_mask = 0; + + wxhw->mac.type = wx_mac_em; + type_mask = (u16)(wxhw->subsystem_device_id & NGBE_OEM_MASK); + ncsi_mask = wxhw->subsystem_device_id & NGBE_NCSI_MASK; + wol_mask = wxhw->subsystem_device_id & NGBE_WOL_MASK; + + switch (type_mask) { + case NGBE_SUBID_M88E1512_SFP: + case NGBE_SUBID_LY_M88E1512_SFP: + hw->phy.type = ngbe_phy_m88e1512_sfi; + break; + case NGBE_SUBID_M88E1512_RJ45: + hw->phy.type = ngbe_phy_m88e1512; + break; + case NGBE_SUBID_M88E1512_MIX: + hw->phy.type = ngbe_phy_m88e1512_unknown; + break; + case NGBE_SUBID_YT8521S_SFP: + case NGBE_SUBID_YT8521S_SFP_GPIO: + case NGBE_SUBID_LY_YT8521S_SFP: + hw->phy.type = ngbe_phy_yt8521s_sfi; + break; + case NGBE_SUBID_INTERNAL_YT8521S_SFP: + case NGBE_SUBID_INTERNAL_YT8521S_SFP_GPIO: + hw->phy.type = ngbe_phy_internal_yt8521s_sfi; + break; + case NGBE_SUBID_RGMII_FPGA: + case NGBE_SUBID_OCP_CARD: + fallthrough; + default: + hw->phy.type = ngbe_phy_internal; + break; + } + + if (hw->phy.type == ngbe_phy_internal || + hw->phy.type == ngbe_phy_internal_yt8521s_sfi) + hw->mac_type = ngbe_mac_type_mdi; + else + hw->mac_type = ngbe_mac_type_rgmii; + + hw->wol_enabled = (wol_mask == NGBE_WOL_SUP) ? 1 : 0; + hw->ncsi_enabled = (ncsi_mask == NGBE_NCSI_MASK || + type_mask == NGBE_SUBID_OCP_CARD) ? 1 : 0; + + switch (type_mask) { + case NGBE_SUBID_LY_YT8521S_SFP: + case NGBE_SUBID_LY_M88E1512_SFP: + case NGBE_SUBID_YT8521S_SFP_GPIO: + case NGBE_SUBID_INTERNAL_YT8521S_SFP_GPIO: + hw->gpio_ctrl = 1; + break; + default: + hw->gpio_ctrl = 0; + break; + } +} + +/** + * ngbe_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ngbe_init_rss_key(struct ngbe_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(NGBE_RSS_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, NGBE_RSS_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + +/** + * ngbe_sw_init - Initialize general software structures + * @adapter: board private structure to initialize + **/ +static int ngbe_sw_init(struct ngbe_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ngbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; + u16 msix_count = 0; + int err = 0; + + wxhw->hw_addr = adapter->io_addr; + wxhw->pdev = pdev; + + /* PCI config space info */ + err = wx_sw_init(wxhw); + if (err < 0) { + netif_err(adapter, probe, adapter->netdev, + "Read of internal subsystem device id failed\n"); + return err; + } + + /* mac type, phy type , oem type */ + ngbe_init_type_code(hw); + + wxhw->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; + wxhw->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; + wxhw->mac.num_rar_entries = NGBE_RAR_ENTRIES; + /* Set common capability flags and settings */ + adapter->max_q_vectors = NGBE_MAX_MSIX_VECTORS; + + err = wx_get_pcie_msix_counts(wxhw, &msix_count, NGBE_MAX_MSIX_VECTORS); + if (err) + dev_err(&pdev->dev, "Do not support MSI-X\n"); + wxhw->mac.max_msix_vectors = msix_count; + + adapter->mac_table = kcalloc(wxhw->mac.num_rar_entries, + sizeof(struct ngbe_mac_addr), + GFP_KERNEL); + if (!adapter->mac_table) { + dev_err(&pdev->dev, "mac_table allocation failed: %d\n", err); + return -ENOMEM; + } + + if (ngbe_init_rss_key(adapter)) + return -ENOMEM; + + /* enable itr by default in dynamic mode */ + adapter->rx_itr_setting = 1; + adapter->tx_itr_setting = 1; + + /* set default ring sizes */ + adapter->tx_ring_count = NGBE_DEFAULT_TXD; + adapter->rx_ring_count = NGBE_DEFAULT_RXD; + + /* set default work limits */ + adapter->tx_work_limit = NGBE_DEFAULT_TX_WORK; + adapter->rx_work_limit = NGBE_DEFAULT_RX_WORK; + + return 0; +} + +static void ngbe_down(struct ngbe_adapter *adapter) +{ + netif_carrier_off(adapter->netdev); + netif_tx_disable(adapter->netdev); +}; + +/** + * ngbe_open - Called when a network interface is made active + * @netdev: network interface device structure + * + * Returns 0 on success, negative value on failure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). + **/ +static int ngbe_open(struct net_device *netdev) +{ + struct ngbe_adapter *adapter = netdev_priv(netdev); + struct ngbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; + + wx_control_hw(wxhw, true); + + return 0; +} + +/** + * ngbe_close - Disables a network interface + * @netdev: network interface device structure + * + * Returns 0, this is not allowed to fail + * + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the drivers control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. + **/ +static int ngbe_close(struct net_device *netdev) +{ + struct ngbe_adapter *adapter = netdev_priv(netdev); + + ngbe_down(adapter); + wx_control_hw(&adapter->hw.wxhw, false); + + return 0; +} + +static netdev_tx_t ngbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + return NETDEV_TX_OK; +} + +/** + * ngbe_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int ngbe_set_mac(struct net_device *netdev, void *p) +{ + struct ngbe_adapter *adapter = netdev_priv(netdev); + struct wx_hw *wxhw = &adapter->hw.wxhw; + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + eth_hw_addr_set(netdev, addr->sa_data); + memcpy(wxhw->mac.addr, addr->sa_data, netdev->addr_len); + + ngbe_mac_set_default_filter(adapter, wxhw->mac.addr); + + return 0; +} + static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { struct ngbe_adapter *adapter = pci_get_drvdata(pdev); @@ -41,13 +287,22 @@ static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) netif_device_detach(netdev); + rtnl_lock(); + if (netif_running(netdev)) + ngbe_down(adapter); + rtnl_unlock(); + wx_control_hw(&adapter->hw.wxhw, false); + pci_disable_device(pdev); } static void ngbe_shutdown(struct pci_dev *pdev) { + struct ngbe_adapter *adapter = pci_get_drvdata(pdev); bool wake; + wake = !!adapter->wol; + ngbe_dev_shutdown(pdev, &wake); if (system_state == SYSTEM_POWER_OFF) { @@ -56,6 +311,14 @@ static void ngbe_shutdown(struct pci_dev *pdev) } } +static const struct net_device_ops ngbe_netdev_ops = { + .ndo_open = ngbe_open, + .ndo_stop = ngbe_close, + .ndo_start_xmit = ngbe_xmit_frame, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = ngbe_set_mac, +}; + /** * ngbe_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -71,7 +334,14 @@ static int ngbe_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct ngbe_adapter *adapter = NULL; + struct ngbe_hw *hw = NULL; + struct wx_hw *wxhw = NULL; struct net_device *netdev; + u32 e2rom_cksum_cap = 0; + static int func_nums; + u16 e2rom_ver = 0; + u32 etrack_id = 0; + u32 saved_ver = 0; int err; err = pci_enable_device_mem(pdev); @@ -111,6 +381,9 @@ static int ngbe_probe(struct pci_dev *pdev, adapter = netdev_priv(netdev); adapter->netdev = netdev; adapter->pdev = pdev; + hw = &adapter->hw; + wxhw = &hw->wxhw; + adapter->msg_enable = BIT(3) - 1; adapter->io_addr = devm_ioremap(&pdev->dev, pci_resource_start(pdev, 0), @@ -120,12 +393,101 @@ static int ngbe_probe(struct pci_dev *pdev, goto err_pci_release_regions; } + netdev->netdev_ops = &ngbe_netdev_ops; + netdev->features |= NETIF_F_HIGHDMA; + adapter->bd_number = func_nums; + /* setup the private structure */ + err = ngbe_sw_init(adapter); + if (err) + goto err_free_mac_table; + + /* check if flash load is done after hw power up */ + err = wx_check_flash_load(wxhw, NGBE_SPI_ILDR_STATUS_PERST); + if (err) + goto err_free_mac_table; + err = wx_check_flash_load(wxhw, NGBE_SPI_ILDR_STATUS_PWRRST); + if (err) + goto err_free_mac_table; + + err = wx_mng_present(wxhw); + if (err) { + dev_err(&pdev->dev, "Management capability is not present\n"); + goto err_free_mac_table; + } + + err = ngbe_reset_hw(hw); + if (err) { + dev_err(&pdev->dev, "HW Init failed: %d\n", err); + goto err_free_mac_table; + } + + if (wxhw->bus.func == 0) { + wr32(wxhw, NGBE_CALSUM_CAP_STATUS, 0x0); + wr32(wxhw, NGBE_EEPROM_VERSION_STORE_REG, 0x0); + } else { + e2rom_cksum_cap = rd32(wxhw, NGBE_CALSUM_CAP_STATUS); + saved_ver = rd32(wxhw, NGBE_EEPROM_VERSION_STORE_REG); + } + + wx_init_eeprom_params(wxhw); + if (wxhw->bus.func == 0 || e2rom_cksum_cap == 0) { + /* make sure the EEPROM is ready */ + err = ngbe_eeprom_chksum_hostif(hw); + if (err) { + dev_err(&pdev->dev, "The EEPROM Checksum Is Not Valid\n"); + err = -EIO; + goto err_free_mac_table; + } + } + + adapter->wol = 0; + if (hw->wol_enabled) + adapter->wol = NGBE_PSR_WKUP_CTL_MAG; + + hw->wol_enabled = !!(adapter->wol); + wr32(wxhw, NGBE_PSR_WKUP_CTL, adapter->wol); + + device_set_wakeup_enable(&pdev->dev, adapter->wol); + + /* Save off EEPROM version number and Option Rom version which + * together make a unique identify for the eeprom + */ + if (saved_ver) { + etrack_id = saved_ver; + } else { + wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_H, + &e2rom_ver); + etrack_id = e2rom_ver << 16; + wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_L, + &e2rom_ver); + etrack_id |= e2rom_ver; + wr32(wxhw, NGBE_EEPROM_VERSION_STORE_REG, etrack_id); + } + + eth_hw_addr_set(netdev, wxhw->mac.perm_addr); + ngbe_mac_set_default_filter(adapter, wxhw->mac.perm_addr); + + err = register_netdev(netdev); + if (err) + goto err_register; + pci_set_drvdata(pdev, adapter); + netif_info(adapter, probe, netdev, + "PHY: %s, PBA No: Wang Xun GbE Family Controller\n", + hw->phy.type == ngbe_phy_internal ? "Internal" : "External"); + netif_info(adapter, probe, netdev, "%pM\n", netdev->dev_addr); + return 0; +err_register: + wx_control_hw(wxhw, false); +err_free_mac_table: + kfree(adapter->mac_table); err_pci_release_regions: pci_disable_pcie_error_reporting(pdev); pci_release_selected_regions(pdev, @@ -146,9 +508,15 @@ err_pci_disable_dev: **/ static void ngbe_remove(struct pci_dev *pdev) { + struct ngbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev; + + netdev = adapter->netdev; + unregister_netdev(netdev); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); + kfree(adapter->mac_table); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index 26e776c3539a..39f6c03f1a54 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -8,11 +8,6 @@ #include <linux/netdevice.h> /************ NGBE_register.h ************/ -/* Vendor ID */ -#ifndef PCI_VENDOR_ID_WANGXUN -#define PCI_VENDOR_ID_WANGXUN 0x8088 -#endif - /* Device IDs */ #define NGBE_DEV_ID_EM_WX1860AL_W 0x0100 #define NGBE_DEV_ID_EM_WX1860A2 0x0101 @@ -47,4 +42,98 @@ #define NGBE_WOL_SUP 0x4000 #define NGBE_WOL_MASK 0x4000 +/**************** EM Registers ****************************/ +/* chip control Registers */ +#define NGBE_MIS_PRB_CTL 0x10010 +/* FMGR Registers */ +#define NGBE_SPI_ILDR_STATUS 0x10120 +#define NGBE_SPI_ILDR_STATUS_PERST BIT(0) /* PCIE_PERST is done */ +#define NGBE_SPI_ILDR_STATUS_PWRRST BIT(1) /* Power on reset is done */ +#define NGBE_SPI_ILDR_STATUS_LAN_SW_RST(_i) BIT((_i) + 9) /* lan soft reset done */ + +/* Checksum and EEPROM pointers */ +#define NGBE_CALSUM_COMMAND 0xE9 +#define NGBE_CALSUM_CAP_STATUS 0x10224 +#define NGBE_EEPROM_VERSION_STORE_REG 0x1022C +#define NGBE_SAN_MAC_ADDR_PTR 0x18 +#define NGBE_DEVICE_CAPS 0x1C +#define NGBE_EEPROM_VERSION_L 0x1D +#define NGBE_EEPROM_VERSION_H 0x1E + +/* Media-dependent registers. */ +#define NGBE_MDIO_CLAUSE_SELECT 0x11220 + +/* GPIO Registers */ +#define NGBE_GPIO_DR 0x14800 +#define NGBE_GPIO_DDR 0x14804 +/*GPIO bit */ +#define NGBE_GPIO_DR_0 BIT(0) /* SDP0 Data Value */ +#define NGBE_GPIO_DR_1 BIT(1) /* SDP1 Data Value */ +#define NGBE_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ +#define NGBE_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ + +/* Wake up registers */ +#define NGBE_PSR_WKUP_CTL 0x15B80 +/* Wake Up Filter Control Bit */ +#define NGBE_PSR_WKUP_CTL_LNKC BIT(0) /* Link Status Change Wakeup Enable*/ +#define NGBE_PSR_WKUP_CTL_MAG BIT(1) /* Magic Packet Wakeup Enable */ +#define NGBE_PSR_WKUP_CTL_EX BIT(2) /* Directed Exact Wakeup Enable */ +#define NGBE_PSR_WKUP_CTL_MC BIT(3) /* Directed Multicast Wakeup Enable*/ +#define NGBE_PSR_WKUP_CTL_BC BIT(4) /* Broadcast Wakeup Enable */ +#define NGBE_PSR_WKUP_CTL_ARP BIT(5) /* ARP Request Packet Wakeup Enable*/ +#define NGBE_PSR_WKUP_CTL_IPV4 BIT(6) /* Directed IPv4 Pkt Wakeup Enable */ +#define NGBE_PSR_WKUP_CTL_IPV6 BIT(7) /* Directed IPv6 Pkt Wakeup Enable */ + +#define NGBE_FW_EEPROM_CHECKSUM_CMD 0xE9 +#define NGBE_FW_NVM_DATA_OFFSET 3 +#define NGBE_FW_CMD_DEFAULT_CHECKSUM 0xFF /* checksum always 0xFF */ +#define NGBE_FW_CMD_ST_PASS 0x80658383 +#define NGBE_FW_CMD_ST_FAIL 0x70657376 + +enum ngbe_phy_type { + ngbe_phy_unknown = 0, + ngbe_phy_none, + ngbe_phy_internal, + ngbe_phy_m88e1512, + ngbe_phy_m88e1512_sfi, + ngbe_phy_m88e1512_unknown, + ngbe_phy_yt8521s, + ngbe_phy_yt8521s_sfi, + ngbe_phy_internal_yt8521s_sfi, + ngbe_phy_generic +}; + +enum ngbe_media_type { + ngbe_media_type_unknown = 0, + ngbe_media_type_fiber, + ngbe_media_type_copper, + ngbe_media_type_backplane, +}; + +enum ngbe_mac_type { + ngbe_mac_type_unknown = 0, + ngbe_mac_type_mdi, + ngbe_mac_type_rgmii +}; + +struct ngbe_phy_info { + enum ngbe_phy_type type; + enum ngbe_media_type media_type; + + u32 addr; + u32 id; + + bool reset_if_overtemp; + +}; + +struct ngbe_hw { + struct wx_hw wxhw; + struct ngbe_phy_info phy; + enum ngbe_mac_type mac_type; + + bool wol_enabled; + bool ncsi_enabled; + bool gpio_ctrl; +}; #endif /* _NGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile index 431303ca75b4..78484c58b78b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/Makefile +++ b/drivers/net/ethernet/wangxun/txgbe/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_TXGBE) += txgbe.o -txgbe-objs := txgbe_main.o +txgbe-objs := txgbe_main.o \ + txgbe_hw.o diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe.h b/drivers/net/ethernet/wangxun/txgbe/txgbe.h index 38ddbde0ed0f..19e61377bd00 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe.h @@ -4,19 +4,38 @@ #ifndef _TXGBE_H_ #define _TXGBE_H_ -#include "txgbe_type.h" - #define TXGBE_MAX_FDIR_INDICES 63 #define TXGBE_MAX_RX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) #define TXGBE_MAX_TX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) +#define TXGBE_SP_MAX_TX_QUEUES 128 +#define TXGBE_SP_MAX_RX_QUEUES 128 +#define TXGBE_SP_RAR_ENTRIES 128 +#define TXGBE_SP_MC_TBL_SIZE 128 + +struct txgbe_mac_addr { + u8 addr[ETH_ALEN]; + u16 state; /* bitmask */ + u64 pools; +}; + +#define TXGBE_MAC_STATE_DEFAULT 0x1 +#define TXGBE_MAC_STATE_MODIFIED 0x2 +#define TXGBE_MAC_STATE_IN_USE 0x4 + /* board specific private data structure */ struct txgbe_adapter { u8 __iomem *io_addr; /* Mainly for iounmap use */ /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; + + /* structs defined in txgbe_type.h */ + struct txgbe_hw hw; + u16 msg_enable; + struct txgbe_mac_addr *mac_table; + char eeprom_id[32]; }; extern char txgbe_driver_name[]; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c new file mode 100644 index 000000000000..167f7ff73192 --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <linux/string.h> +#include <linux/iopoll.h> +#include <linux/types.h> +#include <linux/pci.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_hw.h" +#include "txgbe.h" + +/** + * txgbe_init_thermal_sensor_thresh - Inits thermal sensor thresholds + * @hw: pointer to hardware structure + * + * Inits the thermal sensor thresholds according to the NVM map + * and save off the threshold and location values into mac.thermal_sensor_data + **/ +static void txgbe_init_thermal_sensor_thresh(struct txgbe_hw *hw) +{ + struct wx_hw *wxhw = &hw->wxhw; + struct wx_thermal_sensor_data *data = &wxhw->mac.sensor; + + memset(data, 0, sizeof(struct wx_thermal_sensor_data)); + + /* Only support thermal sensors attached to SP physical port 0 */ + if (wxhw->bus.func) + return; + + wr32(wxhw, TXGBE_TS_CTL, TXGBE_TS_CTL_EVAL_MD); + + wr32(wxhw, WX_TS_INT_EN, + WX_TS_INT_EN_ALARM_INT_EN | WX_TS_INT_EN_DALARM_INT_EN); + wr32(wxhw, WX_TS_EN, WX_TS_EN_ENA); + + data->alarm_thresh = 100; + wr32(wxhw, WX_TS_ALARM_THRE, 677); + data->dalarm_thresh = 90; + wr32(wxhw, WX_TS_DALARM_THRE, 614); +} + +/** + * txgbe_read_pba_string - Reads part number string from EEPROM + * @hw: pointer to hardware structure + * @pba_num: stores the part number string from the EEPROM + * @pba_num_size: part number string buffer length + * + * Reads the part number string from the EEPROM. + **/ +int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) +{ + u16 pba_ptr, offset, length, data; + struct wx_hw *wxhw = &hw->wxhw; + int ret_val; + + if (!pba_num) { + wx_err(wxhw, "PBA string buffer was null\n"); + return -EINVAL; + } + + ret_val = wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + TXGBE_PBANUM0_PTR, + &data); + if (ret_val != 0) { + wx_err(wxhw, "NVM Read Error\n"); + return ret_val; + } + + ret_val = wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + TXGBE_PBANUM1_PTR, + &pba_ptr); + if (ret_val != 0) { + wx_err(wxhw, "NVM Read Error\n"); + return ret_val; + } + + /* if data is not ptr guard the PBA must be in legacy format which + * means pba_ptr is actually our second data word for the PBA number + * and we can decode it into an ascii string + */ + if (data != TXGBE_PBANUM_PTR_GUARD) { + wx_err(wxhw, "NVM PBA number is not stored as string\n"); + + /* we will need 11 characters to store the PBA */ + if (pba_num_size < 11) { + wx_err(wxhw, "PBA string buffer too small\n"); + return -ENOMEM; + } + + /* extract hex string from data and pba_ptr */ + pba_num[0] = (data >> 12) & 0xF; + pba_num[1] = (data >> 8) & 0xF; + pba_num[2] = (data >> 4) & 0xF; + pba_num[3] = data & 0xF; + pba_num[4] = (pba_ptr >> 12) & 0xF; + pba_num[5] = (pba_ptr >> 8) & 0xF; + pba_num[6] = '-'; + pba_num[7] = 0; + pba_num[8] = (pba_ptr >> 4) & 0xF; + pba_num[9] = pba_ptr & 0xF; + + /* put a null character on the end of our string */ + pba_num[10] = '\0'; + + /* switch all the data but the '-' to hex char */ + for (offset = 0; offset < 10; offset++) { + if (pba_num[offset] < 0xA) + pba_num[offset] += '0'; + else if (pba_num[offset] < 0x10) + pba_num[offset] += 'A' - 0xA; + } + + return 0; + } + + ret_val = wx_read_ee_hostif(wxhw, pba_ptr, &length); + if (ret_val != 0) { + wx_err(wxhw, "NVM Read Error\n"); + return ret_val; + } + + if (length == 0xFFFF || length == 0) { + wx_err(wxhw, "NVM PBA number section invalid length\n"); + return -EINVAL; + } + + /* check if pba_num buffer is big enough */ + if (pba_num_size < (((u32)length * 2) - 1)) { + wx_err(wxhw, "PBA string buffer too small\n"); + return -ENOMEM; + } + + /* trim pba length from start of string */ + pba_ptr++; + length--; + + for (offset = 0; offset < length; offset++) { + ret_val = wx_read_ee_hostif(wxhw, pba_ptr + offset, &data); + if (ret_val != 0) { + wx_err(wxhw, "NVM Read Error\n"); + return ret_val; + } + pba_num[offset * 2] = (u8)(data >> 8); + pba_num[(offset * 2) + 1] = (u8)(data & 0xFF); + } + pba_num[offset * 2] = '\0'; + + return 0; +} + +/** + * txgbe_calc_eeprom_checksum - Calculates and returns the checksum + * @hw: pointer to hardware structure + * @checksum: pointer to cheksum + * + * Returns a negative error code on error + **/ +static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) +{ + struct wx_hw *wxhw = &hw->wxhw; + u16 *eeprom_ptrs = NULL; + u32 buffer_size = 0; + u16 *buffer = NULL; + u16 *local_buffer; + int status; + u16 i; + + wx_init_eeprom_params(wxhw); + + if (!buffer) { + eeprom_ptrs = kvmalloc_array(TXGBE_EEPROM_LAST_WORD, sizeof(u16), + GFP_KERNEL); + if (!eeprom_ptrs) + return -ENOMEM; + /* Read pointer area */ + status = wx_read_ee_hostif_buffer(wxhw, 0, + TXGBE_EEPROM_LAST_WORD, + eeprom_ptrs); + if (status != 0) { + wx_err(wxhw, "Failed to read EEPROM image\n"); + kvfree(eeprom_ptrs); + return status; + } + local_buffer = eeprom_ptrs; + } else { + if (buffer_size < TXGBE_EEPROM_LAST_WORD) + return -EFAULT; + local_buffer = buffer; + } + + for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) + if (i != wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) + *checksum += local_buffer[i]; + + if (eeprom_ptrs) + kvfree(eeprom_ptrs); + + if (*checksum > TXGBE_EEPROM_SUM) + return -EINVAL; + + *checksum = TXGBE_EEPROM_SUM - *checksum; + + return 0; +} + +/** + * txgbe_validate_eeprom_checksum - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + **/ +int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val) +{ + struct wx_hw *wxhw = &hw->wxhw; + u16 read_checksum = 0; + u16 checksum; + int status; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = wx_read_ee_hostif(wxhw, 0, &checksum); + if (status) { + wx_err(wxhw, "EEPROM read failed\n"); + return status; + } + + checksum = 0; + status = txgbe_calc_eeprom_checksum(hw, &checksum); + if (status != 0) + return status; + + status = wx_read_ee_hostif(wxhw, wxhw->eeprom.sw_region_offset + + TXGBE_EEPROM_CHECKSUM, &read_checksum); + if (status != 0) + return status; + + /* Verify read checksum from EEPROM is the same as + * calculated checksum + */ + if (read_checksum != checksum) { + status = -EIO; + wx_err(wxhw, "Invalid EEPROM checksum\n"); + } + + /* If the user cares, return the calculated checksum */ + if (checksum_val) + *checksum_val = checksum; + + return status; +} + +static void txgbe_reset_misc(struct txgbe_hw *hw) +{ + struct wx_hw *wxhw = &hw->wxhw; + + wx_reset_misc(wxhw); + txgbe_init_thermal_sensor_thresh(hw); +} + +/** + * txgbe_reset_hw - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, perform a PHY reset, and perform a link (MAC) + * reset. + **/ +int txgbe_reset_hw(struct txgbe_hw *hw) +{ + struct wx_hw *wxhw = &hw->wxhw; + int status; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + status = wx_stop_adapter(wxhw); + if (status != 0) + return status; + + if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) + wx_reset_hostif(wxhw); + + usleep_range(10, 100); + + status = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(wxhw->bus.func)); + if (status != 0) + return status; + + txgbe_reset_misc(hw); + + /* Store the permanent mac address */ + wx_get_mac_addr(wxhw, wxhw->mac.perm_addr); + + /* Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to 128, + * since we modify this value when programming the SAN MAC address. + */ + wxhw->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; + wx_init_rx_addrs(wxhw); + + pci_set_master(wxhw->pdev); + + return 0; +} diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h new file mode 100644 index 000000000000..6a751a69177b --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _TXGBE_HW_H_ +#define _TXGBE_HW_H_ + +int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size); +int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val); +int txgbe_reset_hw(struct txgbe_hw *hw); + +#endif /* _TXGBE_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index d3b9f73ecba4..36780e7f05b7 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -8,7 +8,12 @@ #include <linux/string.h> #include <linux/aer.h> #include <linux/etherdevice.h> +#include <net/ip.h> +#include "../libwx/wx_type.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_hw.h" #include "txgbe.h" char txgbe_driver_name[] = "txgbe"; @@ -30,13 +35,305 @@ static const struct pci_device_id txgbe_pci_tbl[] = { #define DEFAULT_DEBUG_LEVEL_SHIFT 3 +static void txgbe_check_minimum_link(struct txgbe_adapter *adapter) +{ + struct pci_dev *pdev; + + pdev = adapter->pdev; + pcie_print_link_status(pdev); +} + +/** + * txgbe_enumerate_functions - Get the number of ports this device has + * @adapter: adapter structure + * + * This function enumerates the phsyical functions co-located on a single slot, + * in order to determine how many ports a device has. This is most useful in + * determining the required GT/s of PCIe bandwidth necessary for optimal + * performance. + **/ +static int txgbe_enumerate_functions(struct txgbe_adapter *adapter) +{ + struct pci_dev *entry, *pdev = adapter->pdev; + int physfns = 0; + + list_for_each_entry(entry, &pdev->bus->devices, bus_list) { + /* When the devices on the bus don't all match our device ID, + * we can't reliably determine the correct number of + * functions. This can occur if a function has been direct + * attached to a virtual machine using VT-d. + */ + if (entry->vendor != pdev->vendor || + entry->device != pdev->device) + return -EINVAL; + + physfns++; + } + + return physfns; +} + +static void txgbe_sync_mac_table(struct txgbe_adapter *adapter) +{ + struct txgbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; + int i; + + for (i = 0; i < wxhw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & TXGBE_MAC_STATE_MODIFIED) { + if (adapter->mac_table[i].state & TXGBE_MAC_STATE_IN_USE) { + wx_set_rar(wxhw, i, + adapter->mac_table[i].addr, + adapter->mac_table[i].pools, + WX_PSR_MAC_SWC_AD_H_AV); + } else { + wx_clear_rar(wxhw, i); + } + adapter->mac_table[i].state &= ~(TXGBE_MAC_STATE_MODIFIED); + } + } +} + +/* this function destroys the first RAR entry */ +static void txgbe_mac_set_default_filter(struct txgbe_adapter *adapter, + u8 *addr) +{ + struct wx_hw *wxhw = &adapter->hw.wxhw; + + memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); + adapter->mac_table[0].pools = 1ULL; + adapter->mac_table[0].state = (TXGBE_MAC_STATE_DEFAULT | + TXGBE_MAC_STATE_IN_USE); + wx_set_rar(wxhw, 0, adapter->mac_table[0].addr, + adapter->mac_table[0].pools, + WX_PSR_MAC_SWC_AD_H_AV); +} + +static void txgbe_flush_sw_mac_table(struct txgbe_adapter *adapter) +{ + struct wx_hw *wxhw = &adapter->hw.wxhw; + u32 i; + + for (i = 0; i < wxhw->mac.num_rar_entries; i++) { + adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].pools = 0; + } + txgbe_sync_mac_table(adapter); +} + +static int txgbe_del_mac_filter(struct txgbe_adapter *adapter, u8 *addr, u16 pool) +{ + struct wx_hw *wxhw = &adapter->hw.wxhw; + u32 i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* search table for addr, if found, set to 0 and sync */ + for (i = 0; i < wxhw->mac.num_rar_entries; i++) { + if (ether_addr_equal(addr, adapter->mac_table[i].addr)) { + if (adapter->mac_table[i].pools & (1ULL << pool)) { + adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; + adapter->mac_table[i].pools &= ~(1ULL << pool); + txgbe_sync_mac_table(adapter); + } + return 0; + } + + if (adapter->mac_table[i].pools != (1 << pool)) + continue; + if (!ether_addr_equal(addr, adapter->mac_table[i].addr)) + continue; + + adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].pools = 0; + txgbe_sync_mac_table(adapter); + return 0; + } + return -ENOMEM; +} + +static void txgbe_up_complete(struct txgbe_adapter *adapter) +{ + struct txgbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; + + wx_control_hw(wxhw, true); +} + +static void txgbe_reset(struct txgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct txgbe_hw *hw = &adapter->hw; + u8 old_addr[ETH_ALEN]; + int err; + + err = txgbe_reset_hw(hw); + if (err != 0) + dev_err(&adapter->pdev->dev, "Hardware Error: %d\n", err); + + /* do not flush user set addresses */ + memcpy(old_addr, &adapter->mac_table[0].addr, netdev->addr_len); + txgbe_flush_sw_mac_table(adapter); + txgbe_mac_set_default_filter(adapter, old_addr); +} + +static void txgbe_disable_device(struct txgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct wx_hw *wxhw = &adapter->hw.wxhw; + + wx_disable_pcie_master(wxhw); + /* disable receives */ + wx_disable_rx(wxhw); + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + + if (wxhw->bus.func < 2) + wr32m(wxhw, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wxhw->bus.func), 0); + else + dev_err(&adapter->pdev->dev, + "%s: invalid bus lan id %d\n", + __func__, wxhw->bus.func); + + if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { + /* disable mac transmiter */ + wr32m(wxhw, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); + } + + /* Disable the Tx DMA engine */ + wr32m(wxhw, WX_TDM_CTL, WX_TDM_CTL_TE, 0); +} + +static void txgbe_down(struct txgbe_adapter *adapter) +{ + txgbe_disable_device(adapter); + txgbe_reset(adapter); +} + +/** + * txgbe_sw_init - Initialize general software structures (struct txgbe_adapter) + * @adapter: board private structure to initialize + **/ +static int txgbe_sw_init(struct txgbe_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct txgbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; + int err; + + wxhw->hw_addr = adapter->io_addr; + wxhw->pdev = pdev; + + /* PCI config space info */ + err = wx_sw_init(wxhw); + if (err < 0) { + netif_err(adapter, probe, adapter->netdev, + "read of internal subsystem device id failed\n"); + return err; + } + + switch (wxhw->device_id) { + case TXGBE_DEV_ID_SP1000: + case TXGBE_DEV_ID_WX1820: + wxhw->mac.type = wx_mac_sp; + break; + default: + wxhw->mac.type = wx_mac_unknown; + break; + } + + wxhw->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; + wxhw->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; + wxhw->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; + wxhw->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; + + adapter->mac_table = kcalloc(wxhw->mac.num_rar_entries, + sizeof(struct txgbe_mac_addr), + GFP_KERNEL); + if (!adapter->mac_table) { + netif_err(adapter, probe, adapter->netdev, + "mac_table allocation failed\n"); + return -ENOMEM; + } + + return 0; +} + +/** + * txgbe_open - Called when a network interface is made active + * @netdev: network interface device structure + * + * Returns 0 on success, negative value on failure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). + **/ +static int txgbe_open(struct net_device *netdev) +{ + struct txgbe_adapter *adapter = netdev_priv(netdev); + + txgbe_up_complete(adapter); + + return 0; +} + +/** + * txgbe_close_suspend - actions necessary to both suspend and close flows + * @adapter: the private adapter struct + * + * This function should contain the necessary work common to both suspending + * and closing of the device. + */ +static void txgbe_close_suspend(struct txgbe_adapter *adapter) +{ + txgbe_disable_device(adapter); +} + +/** + * txgbe_close - Disables a network interface + * @netdev: network interface device structure + * + * Returns 0, this is not allowed to fail + * + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the drivers control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. + **/ +static int txgbe_close(struct net_device *netdev) +{ + struct txgbe_adapter *adapter = netdev_priv(netdev); + + txgbe_down(adapter); + wx_control_hw(&adapter->hw.wxhw, false); + + return 0; +} + static void txgbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { struct txgbe_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; + struct txgbe_hw *hw = &adapter->hw; + struct wx_hw *wxhw = &hw->wxhw; netif_device_detach(netdev); + rtnl_lock(); + if (netif_running(netdev)) + txgbe_close_suspend(adapter); + rtnl_unlock(); + + wx_control_hw(wxhw, false); + pci_disable_device(pdev); } @@ -52,6 +349,47 @@ static void txgbe_shutdown(struct pci_dev *pdev) } } +static netdev_tx_t txgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + return NETDEV_TX_OK; +} + +/** + * txgbe_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int txgbe_set_mac(struct net_device *netdev, void *p) +{ + struct txgbe_adapter *adapter = netdev_priv(netdev); + struct wx_hw *wxhw = &adapter->hw.wxhw; + struct sockaddr *addr = p; + int retval; + + retval = eth_prepare_mac_addr_change(netdev, addr); + if (retval) + return retval; + + txgbe_del_mac_filter(adapter, wxhw->mac.addr, 0); + eth_hw_addr_set(netdev, addr->sa_data); + memcpy(wxhw->mac.addr, addr->sa_data, netdev->addr_len); + + txgbe_mac_set_default_filter(adapter, wxhw->mac.addr); + + return 0; +} + +static const struct net_device_ops txgbe_netdev_ops = { + .ndo_open = txgbe_open, + .ndo_stop = txgbe_close, + .ndo_start_xmit = txgbe_xmit_frame, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = txgbe_set_mac, +}; + /** * txgbe_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -67,8 +405,16 @@ static int txgbe_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct txgbe_adapter *adapter = NULL; + struct txgbe_hw *hw = NULL; + struct wx_hw *wxhw = NULL; struct net_device *netdev; - int err; + int err, expected_gts; + + u16 eeprom_verh = 0, eeprom_verl = 0, offset = 0; + u16 eeprom_cfg_blkh = 0, eeprom_cfg_blkl = 0; + u16 build = 0, major = 0, patch = 0; + u8 part_str[TXGBE_PBANUM_LENGTH]; + u32 etrack_id = 0; err = pci_enable_device_mem(pdev); if (err) @@ -107,6 +453,9 @@ static int txgbe_probe(struct pci_dev *pdev, adapter = netdev_priv(netdev); adapter->netdev = netdev; adapter->pdev = pdev; + hw = &adapter->hw; + wxhw = &hw->wxhw; + adapter->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1; adapter->io_addr = devm_ioremap(&pdev->dev, pci_resource_start(pdev, 0), @@ -116,12 +465,118 @@ static int txgbe_probe(struct pci_dev *pdev, goto err_pci_release_regions; } + netdev->netdev_ops = &txgbe_netdev_ops; + + /* setup the private structure */ + err = txgbe_sw_init(adapter); + if (err) + goto err_free_mac_table; + + /* check if flash load is done after hw power up */ + err = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_PERST); + if (err) + goto err_free_mac_table; + err = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_PWRRST); + if (err) + goto err_free_mac_table; + + err = wx_mng_present(wxhw); + if (err) { + dev_err(&pdev->dev, "Management capability is not present\n"); + goto err_free_mac_table; + } + + err = txgbe_reset_hw(hw); + if (err) { + dev_err(&pdev->dev, "HW Init failed: %d\n", err); + goto err_free_mac_table; + } + netdev->features |= NETIF_F_HIGHDMA; + /* make sure the EEPROM is good */ + err = txgbe_validate_eeprom_checksum(hw, NULL); + if (err != 0) { + dev_err(&pdev->dev, "The EEPROM Checksum Is Not Valid\n"); + wr32(wxhw, WX_MIS_RST, WX_MIS_RST_SW_RST); + err = -EIO; + goto err_free_mac_table; + } + + eth_hw_addr_set(netdev, wxhw->mac.perm_addr); + txgbe_mac_set_default_filter(adapter, wxhw->mac.perm_addr); + + /* Save off EEPROM version number and Option Rom version which + * together make a unique identify for the eeprom + */ + wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_H, + &eeprom_verh); + wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_L, + &eeprom_verl); + etrack_id = (eeprom_verh << 16) | eeprom_verl; + + wx_read_ee_hostif(wxhw, + wxhw->eeprom.sw_region_offset + TXGBE_ISCSI_BOOT_CONFIG, + &offset); + + /* Make sure offset to SCSI block is valid */ + if (!(offset == 0x0) && !(offset == 0xffff)) { + wx_read_ee_hostif(wxhw, offset + 0x84, &eeprom_cfg_blkh); + wx_read_ee_hostif(wxhw, offset + 0x83, &eeprom_cfg_blkl); + + /* Only display Option Rom if exist */ + if (eeprom_cfg_blkl && eeprom_cfg_blkh) { + major = eeprom_cfg_blkl >> 8; + build = (eeprom_cfg_blkl << 8) | (eeprom_cfg_blkh >> 8); + patch = eeprom_cfg_blkh & 0x00ff; + + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "0x%08x, %d.%d.%d", etrack_id, major, build, + patch); + } else { + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "0x%08x", etrack_id); + } + } else { + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "0x%08x", etrack_id); + } + + err = register_netdev(netdev); + if (err) + goto err_release_hw; + pci_set_drvdata(pdev, adapter); + /* calculate the expected PCIe bandwidth required for optimal + * performance. Note that some older parts will never have enough + * bandwidth due to being older generation PCIe parts. We clamp these + * parts to ensure that no warning is displayed, as this could confuse + * users otherwise. + */ + expected_gts = txgbe_enumerate_functions(adapter) * 10; + + /* don't check link if we failed to enumerate functions */ + if (expected_gts > 0) + txgbe_check_minimum_link(adapter); + else + dev_warn(&pdev->dev, "Failed to enumerate PF devices.\n"); + + /* First try to read PBA as a string */ + err = txgbe_read_pba_string(hw, part_str, TXGBE_PBANUM_LENGTH); + if (err) + strncpy(part_str, "Unknown", TXGBE_PBANUM_LENGTH); + + netif_info(adapter, probe, netdev, "%pM\n", netdev->dev_addr); + return 0; +err_release_hw: + wx_control_hw(wxhw, false); +err_free_mac_table: + kfree(adapter->mac_table); err_pci_release_regions: pci_disable_pcie_error_reporting(pdev); pci_release_selected_regions(pdev, @@ -142,9 +597,17 @@ err_pci_disable_dev: **/ static void txgbe_remove(struct pci_dev *pdev) { + struct txgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev; + + netdev = adapter->netdev; + unregister_netdev(netdev); + pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); + kfree(adapter->mac_table); + pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index b2e329f50bae..740a1c447e20 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -4,15 +4,6 @@ #ifndef _TXGBE_TYPE_H_ #define _TXGBE_TYPE_H_ -#include <linux/types.h> -#include <linux/netdevice.h> - -/************ txgbe_register.h ************/ -/* Vendor ID */ -#ifndef PCI_VENDOR_ID_WANGXUN -#define PCI_VENDOR_ID_WANGXUN 0x8088 -#endif - /* Device IDs */ #define TXGBE_DEV_ID_SP1000 0x1001 #define TXGBE_DEV_ID_WX1820 0x2001 @@ -42,16 +33,42 @@ #define TXGBE_ID_WX1820_MAC_SGMII 0x2060 #define TXGBE_ID_MAC_SGMII 0x60 -#define TXGBE_NCSI_SUP 0x8000 -#define TXGBE_NCSI_MASK 0x8000 -#define TXGBE_WOL_SUP 0x4000 -#define TXGBE_WOL_MASK 0x4000 -#define TXGBE_DEV_MASK 0xf0 - /* Combined interface*/ #define TXGBE_ID_SFI_XAUI 0x50 /* Revision ID */ #define TXGBE_SP_MPW 1 +/**************** SP Registers ****************************/ +/* chip control Registers */ +#define TXGBE_MIS_PRB_CTL 0x10010 +#define TXGBE_MIS_PRB_CTL_LAN_UP(_i) BIT(1 - (_i)) +/* FMGR Registers */ +#define TXGBE_SPI_ILDR_STATUS 0x10120 +#define TXGBE_SPI_ILDR_STATUS_PERST BIT(0) /* PCIE_PERST is done */ +#define TXGBE_SPI_ILDR_STATUS_PWRRST BIT(1) /* Power on reset is done */ +#define TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(_i) BIT((_i) + 9) /* lan soft reset done */ + +/* Sensors for PVT(Process Voltage Temperature) */ +#define TXGBE_TS_CTL 0x10300 +#define TXGBE_TS_CTL_EVAL_MD BIT(31) + +/* Part Number String Length */ +#define TXGBE_PBANUM_LENGTH 32 + +/* Checksum and EEPROM pointers */ +#define TXGBE_EEPROM_LAST_WORD 0x800 +#define TXGBE_EEPROM_CHECKSUM 0x2F +#define TXGBE_EEPROM_SUM 0xBABA +#define TXGBE_EEPROM_VERSION_L 0x1D +#define TXGBE_EEPROM_VERSION_H 0x1E +#define TXGBE_ISCSI_BOOT_CONFIG 0x07 +#define TXGBE_PBANUM0_PTR 0x05 +#define TXGBE_PBANUM1_PTR 0x06 +#define TXGBE_PBANUM_PTR_GUARD 0xFAFA + +struct txgbe_hw { + struct wx_hw wxhw; +}; + #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 6370c447ac5c..575ff9de8985 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -611,8 +611,6 @@ static inline void axienet_dma_out_addr(struct axienet_local *lp, off_t reg, #endif /* CONFIG_64BIT */ /* Function prototypes visible in xilinx_axienet_mdio.c for other files */ -int axienet_mdio_enable(struct axienet_local *lp); -void axienet_mdio_disable(struct axienet_local *lp); int axienet_mdio_setup(struct axienet_local *lp); void axienet_mdio_teardown(struct axienet_local *lp); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index d1d772580da9..3e310b55bce2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1305,16 +1305,16 @@ axienet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) netdev_stats_to_stats64(stats, &dev->stats); do { - start = u64_stats_fetch_begin_irq(&lp->rx_stat_sync); + start = u64_stats_fetch_begin(&lp->rx_stat_sync); stats->rx_packets = u64_stats_read(&lp->rx_packets); stats->rx_bytes = u64_stats_read(&lp->rx_bytes); - } while (u64_stats_fetch_retry_irq(&lp->rx_stat_sync, start)); + } while (u64_stats_fetch_retry(&lp->rx_stat_sync, start)); do { - start = u64_stats_fetch_begin_irq(&lp->tx_stat_sync); + start = u64_stats_fetch_begin(&lp->tx_stat_sync); stats->tx_packets = u64_stats_read(&lp->tx_packets); stats->tx_bytes = u64_stats_read(&lp->tx_bytes); - } while (u64_stats_fetch_retry_irq(&lp->tx_stat_sync, start)); + } while (u64_stats_fetch_retry(&lp->tx_stat_sync, start)); } static const struct net_device_ops axienet_netdev_ops = { @@ -1736,7 +1736,6 @@ static void axienet_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops axienet_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = axienet_mac_select_pcs, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, @@ -2217,12 +2216,48 @@ static void axienet_shutdown(struct platform_device *pdev) rtnl_unlock(); } +static int axienet_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + + if (!netif_running(ndev)) + return 0; + + netif_device_detach(ndev); + + rtnl_lock(); + axienet_stop(ndev); + rtnl_unlock(); + + return 0; +} + +static int axienet_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + + if (!netif_running(ndev)) + return 0; + + rtnl_lock(); + axienet_open(ndev); + rtnl_unlock(); + + netif_device_attach(ndev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(axienet_pm_ops, + axienet_suspend, axienet_resume); + static struct platform_driver axienet_driver = { .probe = axienet_probe, .remove = axienet_remove, .shutdown = axienet_shutdown, .driver = { .name = "xilinx_axienet", + .pm = &axienet_pm_ops, .of_match_table = axienet_of_match, }, }; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 0b3b6935c558..2f07fde361aa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -17,7 +17,7 @@ #include "xilinx_axienet.h" -#define MAX_MDIO_FREQ 2500000 /* 2.5 MHz */ +#define DEFAULT_MDIO_FREQ 2500000 /* 2.5 MHz */ #define DEFAULT_HOST_CLOCK 150000000 /* 150 MHz */ /* Wait till MDIO interface is ready to accept a new transaction.*/ @@ -147,15 +147,20 @@ static int axienet_mdio_write(struct mii_bus *bus, int phy_id, int reg, /** * axienet_mdio_enable - MDIO hardware setup function * @lp: Pointer to axienet local data structure. + * @np: Pointer to mdio device tree node. * - * Return: 0 on success, -ETIMEDOUT on a timeout. + * Return: 0 on success, -ETIMEDOUT on a timeout, -EOVERFLOW on a clock + * divisor overflow. * * Sets up the MDIO interface by initializing the MDIO clock and enabling the * MDIO interface in hardware. **/ -int axienet_mdio_enable(struct axienet_local *lp) +static int axienet_mdio_enable(struct axienet_local *lp, struct device_node *np) { + u32 mdio_freq = DEFAULT_MDIO_FREQ; u32 host_clock; + u32 clk_div; + int ret; lp->mii_clk_div = 0; @@ -184,6 +189,12 @@ int axienet_mdio_enable(struct axienet_local *lp) host_clock); } + if (np) + of_property_read_u32(np, "clock-frequency", &mdio_freq); + if (mdio_freq != DEFAULT_MDIO_FREQ) + netdev_info(lp->ndev, "Setting non-standard mdio bus frequency to %u Hz\n", + mdio_freq); + /* clk_div can be calculated by deriving it from the equation: * fMDIO = fHOST / ((1 + clk_div) * 2) * @@ -209,40 +220,42 @@ int axienet_mdio_enable(struct axienet_local *lp) * "clock-frequency" from the CPU */ - lp->mii_clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1; + clk_div = (host_clock / (mdio_freq * 2)) - 1; /* If there is any remainder from the division of - * fHOST / (MAX_MDIO_FREQ * 2), then we need to add - * 1 to the clock divisor or we will surely be above 2.5 MHz + * fHOST / (mdio_freq * 2), then we need to add + * 1 to the clock divisor or we will surely be + * above the requested frequency */ - if (host_clock % (MAX_MDIO_FREQ * 2)) - lp->mii_clk_div++; + if (host_clock % (mdio_freq * 2)) + clk_div++; + + /* Check for overflow of mii_clk_div */ + if (clk_div & ~XAE_MDIO_MC_CLOCK_DIVIDE_MAX) { + netdev_warn(lp->ndev, "MDIO clock divisor overflow\n"); + return -EOVERFLOW; + } + lp->mii_clk_div = (u8)clk_div; netdev_dbg(lp->ndev, "Setting MDIO clock divisor to %u/%u Hz host clock.\n", lp->mii_clk_div, host_clock); - axienet_iow(lp, XAE_MDIO_MC_OFFSET, lp->mii_clk_div | XAE_MDIO_MC_MDIOEN_MASK); + axienet_mdio_mdc_enable(lp); - return axienet_mdio_wait_until_ready(lp); -} + ret = axienet_mdio_wait_until_ready(lp); + if (ret) + axienet_mdio_mdc_disable(lp); -/** - * axienet_mdio_disable - MDIO hardware disable function - * @lp: Pointer to axienet local data structure. - * - * Disable the MDIO interface in hardware. - **/ -void axienet_mdio_disable(struct axienet_local *lp) -{ - axienet_iow(lp, XAE_MDIO_MC_OFFSET, 0); + return ret; } /** * axienet_mdio_setup - MDIO setup function * @lp: Pointer to axienet local data structure. * - * Return: 0 on success, -ETIMEDOUT on a timeout, -ENOMEM when - * mdiobus_alloc (to allocate memory for mii bus structure) fails. + * Return: 0 on success, -ETIMEDOUT on a timeout, -EOVERFLOW on a clock + * divisor overflow, -ENOMEM when mdiobus_alloc (to allocate + * memory for mii bus structure) fails. * * Sets up the MDIO interface by initializing the MDIO clock. * Register the MDIO interface. @@ -253,10 +266,6 @@ int axienet_mdio_setup(struct axienet_local *lp) struct mii_bus *bus; int ret; - ret = axienet_mdio_enable(lp); - if (ret < 0) - return ret; - bus = mdiobus_alloc(); if (!bus) return -ENOMEM; @@ -272,15 +281,23 @@ int axienet_mdio_setup(struct axienet_local *lp) lp->mii_bus = bus; mdio_node = of_get_child_by_name(lp->dev->of_node, "mdio"); + ret = axienet_mdio_enable(lp, mdio_node); + if (ret < 0) + goto unregister; ret = of_mdiobus_register(bus, mdio_node); + if (ret) + goto unregister_mdio_enabled; of_node_put(mdio_node); - if (ret) { - mdiobus_free(bus); - lp->mii_bus = NULL; - return ret; - } axienet_mdio_mdc_disable(lp); return 0; + +unregister_mdio_enabled: + axienet_mdio_mdc_disable(lp); +unregister: + of_node_put(mdio_node); + mdiobus_free(bus); + lp->mii_bus = NULL; + return ret; } /** diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c index 9abbdb71e629..94203eb46e6b 100644 --- a/drivers/net/ethernet/xscale/ptp_ixp46x.c +++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c @@ -120,24 +120,13 @@ static irqreturn_t isr(int irq, void *priv) * PTP clock operations */ -static int ptp_ixp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int ptp_ixp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { - u64 adj; - u32 diff, addend; - int neg_adj = 0; + u32 addend; struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - addend = DEFAULT_ADDEND; - adj = addend; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); - - addend = neg_adj ? addend - diff : addend + diff; + addend = adjust_by_scaled_ppm(DEFAULT_ADDEND, scaled_ppm); __raw_writel(addend, ®s->addend); @@ -230,7 +219,7 @@ static const struct ptp_clock_info ptp_ixp_caps = { .n_ext_ts = N_EXT_TS, .n_pins = 0, .pps = 0, - .adjfreq = ptp_ixp_adjfreq, + .adjfine = ptp_ixp_adjfine, .adjtime = ptp_ixp_adjtime, .gettime64 = ptp_ixp_gettime, .settime64 = ptp_ixp_settime, |