diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-07-31 17:10:56 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-07-31 17:10:56 -0700 |
| commit | 7c764cec3703583247c4ab837c652975a3d41f4b (patch) | |
| tree | bd7149e43ee1d3465f7f3db5ed1df53c06eae62c | |
| parent | acea568fa9eaeffbf949d15b2f7c9c346e16aae3 (diff) | |
| parent | ea111545843e657504193e4f726e1116b96b8141 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Must teardown SR-IOV before unregistering netdev in igb driver, from
Alex Williamson.
2) Fix ipv6 route unreachable crash in IPVS, from Alex Gartrell.
3) Default route selection in ipv4 should take the prefix length, table
ID, and TOS into account, from Julian Anastasov.
4) sch_plug must have a reset method in order to purge all buffered
packets when the qdisc is reset, likewise for sch_choke, from WANG
Cong.
5) Fix deadlock and races in slave_changelink/br_setport in bridging.
From Nikolay Aleksandrov.
6) mlx4 bug fixes (wrong index in port even propagation to VFs,
overzealous BUG_ON assertion, etc.) from Ido Shamay, Jack
Morgenstein, and Or Gerlitz.
7) Turn off klog message about SCTP userspace interface compat that
makes no sense at all, from Daniel Borkmann.
8) Fix unbounded restarts of inet frag eviction process, causing NMI
watchdog soft lockup messages, from Florian Westphal.
9) Suspend/resume fixes for r8152 from Hayes Wang.
10) Fix busy loop when MSG_WAITALL|MSG_PEEK is used in TCP recv, from
Sabrina Dubroca.
11) Fix performance regression when removing a lot of routes from the
ipv4 routing tables, from Alexander Duyck.
12) Fix device leak in AF_PACKET, from Lars Westerhoff.
13) AF_PACKET also has a header length comparison bug due to signedness,
from Alexander Drozdov.
14) Fix bug in EBPF tail call generation on x86, from Daniel Borkmann.
15) Memory leaks, TSO stats, watchdog timeout and other fixes to
thunderx driver from Sunil Goutham and Thanneeru Srinivasulu.
16) act_bpf can leak memory when replacing programs, from Daniel
Borkmann.
17) WOL packet fixes in gianfar driver, from Claudiu Manoil.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
stmmac: fix missing MODULE_LICENSE in stmmac_platform
gianfar: Enable device wakeup when appropriate
gianfar: Fix suspend/resume for wol magic packet
gianfar: Fix warning when CONFIG_PM off
act_pedit: check binding before calling tcf_hash_release()
net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket
net: sched: fix refcount imbalance in actions
r8152: reset device when tx timeout
r8152: add pre_reset and post_reset
qlcnic: Fix corruption while copying
act_bpf: fix memory leaks when replacing bpf programs
net: thunderx: Fix for crash while BGX teardown
net: thunderx: Add PCI driver shutdown routine
net: thunderx: Fix crash when changing rss with mutliple traffic flows
net: thunderx: Set watchdog timeout value
net: thunderx: Wakeup TXQ only if CQE_TX are processed
net: thunderx: Suppress alloc_pages() failure warnings
net: thunderx: Fix TSO packet statistic
net: thunderx: Fix memory leak when changing queue count
net: thunderx: Fix RQ_DROP miscalculation
...
78 files changed, 1000 insertions, 539 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 579a8fd74be0..be2e7a2b10d7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ offsetof(struct bpf_array, map.max_entries)); EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 44 /* number of bytes to jump */ +#define OFFSET1 47 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 33 +#define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ /* prog = array->prog[index]; */ - EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */ - EMIT1(offsetof(struct bpf_array, prog)); + EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + offsetof(struct bpf_array, prog)); EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index caeb39561567..bf9eb2ecf960 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -104,6 +104,57 @@ static void *macb_rx_buffer(struct macb *bp, unsigned int index) return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index); } +/* I/O accessors */ +static u32 hw_readl_native(struct macb *bp, int offset) +{ + return __raw_readl(bp->regs + offset); +} + +static void hw_writel_native(struct macb *bp, int offset, u32 value) +{ + __raw_writel(value, bp->regs + offset); +} + +static u32 hw_readl(struct macb *bp, int offset) +{ + return readl_relaxed(bp->regs + offset); +} + +static void hw_writel(struct macb *bp, int offset, u32 value) +{ + writel_relaxed(value, bp->regs + offset); +} + +/* + * Find the CPU endianness by using the loopback bit of NCR register. When the + * CPU is in big endian we need to program swaped mode for management + * descriptor access. + */ +static bool hw_is_native_io(void __iomem *addr) +{ + u32 value = MACB_BIT(LLB); + + __raw_writel(value, addr + MACB_NCR); + value = __raw_readl(addr + MACB_NCR); + + /* Write 0 back to disable everything */ + __raw_writel(0, addr + MACB_NCR); + + return value == MACB_BIT(LLB); +} + +static bool hw_is_gem(void __iomem *addr, bool native_io) +{ + u32 id; + + if (native_io) + id = __raw_readl(addr + MACB_MID); + else + id = readl_relaxed(addr + MACB_MID); + + return MACB_BFEXT(IDNUM, id) >= 0x2; +} + static void macb_set_hwaddr(struct macb *bp) { u32 bottom; @@ -160,7 +211,7 @@ static void macb_get_hwaddr(struct macb *bp) } } - netdev_info(bp->dev, "invalid hw address, using random\n"); + dev_info(&bp->pdev->dev, "invalid hw address, using random\n"); eth_hw_addr_random(bp->dev); } @@ -252,7 +303,6 @@ static void macb_handle_link_change(struct net_device *dev) struct macb *bp = netdev_priv(dev); struct phy_device *phydev = bp->phy_dev; unsigned long flags; - int status_change = 0; spin_lock_irqsave(&bp->lock, flags); @@ -449,14 +499,14 @@ err_out: static void macb_update_stats(struct macb *bp) { - u32 __iomem *reg = bp->regs + MACB_PFR; u32 *p = &bp->hw_stats.macb.rx_pause_frames; u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1; + int offset = MACB_PFR; WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4); - for(; p < end; p++, reg++) - *p += readl_relaxed(reg); + for(; p < end; p++, offset += 4) + *p += bp->macb_reg_readl(bp, offset); } static int macb_halt_tx(struct macb *bp) @@ -1107,12 +1157,6 @@ static void macb_poll_controller(struct net_device *dev) } #endif -static inline unsigned int macb_count_tx_descriptors(struct macb *bp, - unsigned int len) -{ - return (len + bp->max_tx_length - 1) / bp->max_tx_length; -} - static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb) @@ -1263,11 +1307,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev) * socket buffer: skb fragments of jumbo frames may need to be * splitted into many buffer descriptors. */ - count = macb_count_tx_descriptors(bp, skb_headlen(skb)); + count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length); nr_frags = skb_shinfo(skb)->nr_frags; for (f = 0; f < nr_frags; f++) { frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]); - count += macb_count_tx_descriptors(bp, frag_size); + count += DIV_ROUND_UP(frag_size, bp->max_tx_length); } spin_lock_irqsave(&bp->lock, flags); @@ -1603,7 +1647,6 @@ static u32 macb_dbw(struct macb *bp) static void macb_configure_dma(struct macb *bp) { u32 dmacfg; - u32 tmp, ncr; if (macb_is_gem(bp)) { dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L); @@ -1613,22 +1656,11 @@ static void macb_configure_dma(struct macb *bp) dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L); dmacfg &= ~GEM_BIT(ENDIA_PKT); - /* Find the CPU endianness by using the loopback bit of net_ctrl - * register. save it first. When the CPU is in big endian we - * need to program swaped mode for management descriptor access. - */ - ncr = macb_readl(bp, NCR); - __raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR); - tmp = __raw_readl(bp->regs + MACB_NCR); - - if (tmp == MACB_BIT(LLB)) + if (bp->native_io) dmacfg &= ~GEM_BIT(ENDIA_DESC); else dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */ - /* Restore net_ctrl */ - macb_writel(bp, NCR, ncr); - if (bp->dev->features & NETIF_F_HW_CSUM) dmacfg |= GEM_BIT(TXCOEN); else @@ -1897,19 +1929,19 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu) static void gem_update_stats(struct macb *bp) { - int i; + unsigned int i; u32 *p = &bp->hw_stats.gem.tx_octets_31_0; for (i = 0; i < GEM_STATS_LEN; ++i, ++p) { u32 offset = gem_statistics[i].offset; - u64 val = readl_relaxed(bp->regs + offset); + u64 val = bp->macb_reg_readl(bp, offset); bp->ethtool_stats[i] += val; *p += val; if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) { /* Add GEM_OCTTXH, GEM_OCTRXH */ - val = readl_relaxed(bp->regs + offset + 4); + val = bp->macb_reg_readl(bp, offset + 4); bp->ethtool_stats[i] += ((u64)val) << 32; *(++p) += val; } @@ -1976,7 +2008,7 @@ static int gem_get_sset_count(struct net_device *dev, int sset) static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) { - int i; + unsigned int i; switch (sset) { case ETH_SS_STATS: @@ -2190,7 +2222,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co if (dt_conf) bp->caps = dt_conf->caps; - if (macb_is_gem_hw(bp->regs)) { + if (hw_is_gem(bp->regs, bp->native_io)) { bp->caps |= MACB_CAPS_MACB_IS_GEM; dcfg = gem_readl(bp, DCFG1); @@ -2201,10 +2233,11 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co bp->caps |= MACB_CAPS_FIFO_MODE; } - netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps); + dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps); } static void macb_probe_queues(void __iomem *mem, + bool native_io, unsigned int *queue_mask, unsigned int *num_queues) { @@ -2219,7 +2252,7 @@ static void macb_probe_queues(void __iomem *mem, * we are early in the probe process and don't have the * MACB_CAPS_MACB_IS_GEM flag positioned */ - if (!macb_is_gem_hw(mem)) + if (!hw_is_gem(mem, native_io)) return; /* bit 0 is never set but queue 0 always exists */ @@ -2786,6 +2819,7 @@ static int macb_probe(struct platform_device *pdev) struct clk *pclk, *hclk, *tx_clk; unsigned int queue_mask, num_queues; struct macb_platform_data *pdata; + bool native_io; struct phy_device *phydev; struct net_device *dev; struct resource *regs; @@ -2794,6 +2828,11 @@ static int macb_probe(struct platform_device *pdev) struct macb *bp; int err; + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + mem = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(mem)) + return PTR_ERR(mem); + if (np) { const struct of_device_id *match; @@ -2809,14 +2848,9 @@ static int macb_probe(struct platform_device *pdev) if (err) return err; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mem = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(mem)) { - err = PTR_ERR(mem); - goto err_disable_clocks; - } + native_io = hw_is_native_io(mem); - macb_probe_queues(mem, &queue_mask, &num_queues); + macb_probe_queues(mem, native_io, &queue_mask, &num_queues); dev = alloc_etherdev_mq(sizeof(*bp), num_queues); if (!dev) { err = -ENOMEM; @@ -2831,6 +2865,14 @@ static int macb_probe(struct platform_device *pdev) bp->pdev = pdev; bp->dev = dev; bp->regs = mem; + bp->native_io = native_io; + if (native_io) { + bp->macb_reg_readl = hw_readl_native; + bp->macb_reg_writel = hw_writel_native; + } else { + bp->macb_reg_readl = hw_readl; + bp->macb_reg_writel = hw_writel; + } bp->num_queues = num_queues; bp->queue_mask = queue_mask; if (macb_config) @@ -2838,9 +2880,8 @@ static int macb_probe(struct platform_device *pdev) bp->pclk = pclk; bp->hclk = hclk; bp->tx_clk = tx_clk; - if (macb_config->jumbo_max_len) { + if (macb_config) bp->jumbo_max_len = macb_config->jumbo_max_len; - } spin_lock_init(&bp->lock); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d74655993d4b..1895b6b2addd 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -429,18 +429,12 @@ | GEM_BF(name, value)) /* Register access macros */ -#define macb_readl(port,reg) \ - readl_relaxed((port)->regs + MACB_##reg) -#define macb_writel(port,reg,value) \ - writel_relaxed((value), (port)->regs + MACB_##reg) -#define gem_readl(port, reg) \ - readl_relaxed((port)->regs + GEM_##reg) -#define gem_writel(port, reg, value) \ - writel_relaxed((value), (port)->regs + GEM_##reg) -#define queue_readl(queue, reg) \ - readl_relaxed((queue)->bp->regs + (queue)->reg) -#define queue_writel(queue, reg, value) \ - writel_relaxed((value), (queue)->bp->regs + (queue)->reg) +#define macb_readl(port, reg) (port)->macb_reg_readl((port), MACB_##reg) +#define macb_writel(port, reg, value) (port)->macb_reg_writel((port), MACB_##reg, (value)) +#define gem_readl(port, reg) (port)->macb_reg_readl((port), GEM_##reg) +#define gem_writel(port, reg, value) (port)->macb_reg_writel((port), GEM_##reg, (value)) +#define queue_readl(queue, reg) (queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg) +#define queue_writel(queue, reg, value) (queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value)) /* Conditional GEM/MACB macros. These perform the operation to the correct * register dependent on whether the device is a GEM or a MACB. For registers @@ -785,6 +779,11 @@ struct macb_queue { struct macb { void __iomem *regs; + bool native_io; + + /* hardware IO accessors */ + u32 (*macb_reg_readl)(struct macb *bp, int offset); + void (*macb_reg_writel)(struct macb *bp, int offset, u32 value); unsigned int rx_tail; unsigned int rx_prepared_head; @@ -817,9 +816,9 @@ struct macb { struct mii_bus *mii_bus; struct phy_device *phy_dev; - unsigned int link; - unsigned int speed; - unsigned int duplex; + int link; + int speed; + int duplex; u32 caps; unsigned int dma_burst_length; @@ -843,9 +842,4 @@ static inline bool macb_is_gem(struct macb *bp) return !!(bp->caps & MACB_CAPS_MACB_IS_GEM); } -static inline bool macb_is_gem_hw(void __iomem *addr) -{ - return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2); -} - #endif /* _MACB_H */ diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index dda8a02b7322..8aee250904ec 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -125,6 +125,15 @@ */ #define NICPF_CLK_PER_INT_TICK 2 +/* Time to wait before we decide that a SQ is stuck. + * + * Since both pkt rx and tx notifications are done with same CQ, + * when packets are being received at very high rate (eg: L2 forwarding) + * then freeing transmitted skbs will be delayed and watchdog + * will kick in, resetting interface. Hence keeping this value high. + */ +#define NICVF_TX_TIMEOUT (50 * HZ) + struct nicvf_cq_poll { u8 cq_idx; /* Completion queue index */ struct napi_struct napi; @@ -216,8 +225,9 @@ struct nicvf_drv_stats { /* Tx */ u64 tx_frames_ok; u64 tx_drops; - u64 tx_busy; u64 tx_tso; + u64 txq_stop; + u64 txq_wake; }; struct nicvf { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index 16bd2d772db9..a4228e664567 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -66,9 +66,10 @@ static const struct nicvf_stat nicvf_drv_stats[] = { NICVF_DRV_STAT(rx_frames_jumbo), NICVF_DRV_STAT(rx_drops), NICVF_DRV_STAT(tx_frames_ok), - NICVF_DRV_STAT(tx_busy), NICVF_DRV_STAT(tx_tso), NICVF_DRV_STAT(tx_drops), + NICVF_DRV_STAT(txq_stop), + NICVF_DRV_STAT(txq_wake), }; static const struct nicvf_stat nicvf_queue_stats[] = { @@ -126,6 +127,7 @@ static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl) static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) { + struct nicvf *nic = netdev_priv(netdev); int stats, qidx; if (sset != ETH_SS_STATS) @@ -141,7 +143,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) data += ETH_GSTRING_LEN; } - for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) { for (stats = 0; stats < nicvf_n_queue_stats; stats++) { sprintf(data, "rxq%d: %s", qidx, nicvf_queue_stats[stats].name); @@ -149,7 +151,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) } } - for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) { for (stats = 0; stats < nicvf_n_queue_stats; stats++) { sprintf(data, "txq%d: %s", qidx, nicvf_queue_stats[stats].name); @@ -170,12 +172,14 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) static int nicvf_get_sset_count(struct net_device *netdev, int sset) { + struct nicvf *nic = netdev_priv(netdev); + if (sset != ETH_SS_STATS) return -EINVAL; return nicvf_n_hw_stats + nicvf_n_drv_stats + (nicvf_n_queue_stats * - (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) + + (nic->qs->rq_cnt + nic->qs->sq_cnt)) + BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT; } @@ -197,13 +201,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, *(data++) = ((u64 *)&nic->drv_stats) [nicvf_drv_stats[stat].index]; - for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) { for (stat = 0; stat < nicvf_n_queue_stats; stat++) *(data++) = ((u64 *)&nic->qs->rq[qidx].stats) [nicvf_queue_stats[stat].index]; } - for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) { for (stat = 0; stat < nicvf_n_queue_stats; stat++) *(data++) = ((u64 *)&nic->qs->sq[qidx].stats) [nicvf_queue_stats[stat].index]; @@ -543,6 +547,7 @@ static int nicvf_set_channels(struct net_device *dev, { struct nicvf *nic = netdev_priv(dev); int err = 0; + bool if_up = netif_running(dev); if (!channel->rx_count || !channel->tx_count) return -EINVAL; @@ -551,6 +556,9 @@ static int nicvf_set_channels(struct net_device *dev, if (channel->tx_count > MAX_SND_QUEUES_PER_QS) return -EINVAL; + if (if_up) + nicvf_stop(dev); + nic->qs->rq_cnt = channel->rx_count; nic->qs->sq_cnt = channel->tx_count; nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt); @@ -559,11 +567,9 @@ static int nicvf_set_channels(struct net_device *dev, if (err) return err; - if (!netif_running(dev)) - return err; + if (if_up) + nicvf_open(dev); - nicvf_stop(dev); - nicvf_open(dev); netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n", nic->qs->sq_cnt, nic->qs->rq_cnt); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 8b119a035b7e..3b90afb8c293 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -234,7 +234,7 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) nic->duplex == DUPLEX_FULL ? "Full duplex" : "Half duplex"); netif_carrier_on(nic->netdev); - netif_tx_wake_all_queues(nic->netdev); + netif_tx_start_all_queues(nic->netdev); } else { netdev_info(nic->netdev, "%s: Link is Down\n", nic->netdev->name); @@ -425,6 +425,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, if (skb) { prefetch(skb); dev_consume_skb_any(skb); + sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL; } } @@ -476,12 +477,13 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx, struct napi_struct *napi, int budget) { - int processed_cqe, work_done = 0; + int processed_cqe, work_done = 0, tx_done = 0; int cqe_count, cqe_head; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct cmp_queue *cq = &qs->cq[cq_idx]; struct cqe_rx_t *cq_desc; + struct netdev_queue *txq; spin_lock_bh(&cq->lock); loop: @@ -496,8 +498,8 @@ loop: cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9; cqe_head &= 0xFFFF; - netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n", - __func__, cqe_count, cqe_head); + netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n", + __func__, cq_idx, cqe_count, cqe_head); while (processed_cqe < cqe_count) { /* Get the CQ descriptor */ cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head); @@ -511,8 +513,8 @@ loop: break; } - netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n", - cq_desc->cqe_type); + netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n", + cq_idx, cq_desc->cqe_type); switch (cq_desc->cqe_type) { case CQE_TYPE_RX: nicvf_rcv_pkt_handler(netdev, napi, cq, @@ -522,6 +524,7 @@ loop: case CQE_TYPE_SEND: nicvf_snd_pkt_handler(netdev, cq, (void *)cq_desc, CQE_TYPE_SEND); + tx_done++; break; case CQE_TYPE_INVALID: case CQE_TYPE_RX_SPLIT: @@ -532,8 +535,9 @@ loop: } processed_cqe++; } - netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n", - __func__, processed_cqe, work_done, budget); + netdev_dbg(nic->netdev, + "%s CQ%d processed_cqe %d work_done %d budget %d\n", + __func__, cq_idx, processed_cqe, work_done, budget); /* Ring doorbell to inform H/W to reuse processed CQEs */ nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR, @@ -543,6 +547,19 @@ loop: goto loop; done: + /* Wakeup TXQ if its stopped earlier due to SQ full */ + if (tx_done) { + txq = netdev_get_tx_queue(netdev, cq_idx); + if (netif_tx_queue_stopped(txq)) { + netif_tx_start_queue(txq); + nic->drv_stats.txq_wake++; + if (netif_msg_tx_err(nic)) + netdev_warn(netdev, + "%s: Transmit queue wakeup SQ%d\n", + netdev->name, cq_idx); + } + } + spin_unlock_bh(&cq->lock); return work_done; } @@ -554,15 +571,10 @@ static int nicvf_poll(struct napi_struct *napi, int budget) struct net_device *netdev = napi->dev; struct nicvf *nic = netdev_priv(netdev); struct nicvf_cq_poll *cq; - struct netdev_queue *txq; cq = container_of(napi, struct nicvf_cq_poll, napi); work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget); - txq = netdev_get_tx_queue(netdev, cq->cq_idx); - if (netif_tx_queue_stopped(txq)) - netif_tx_wake_queue(txq); - if (work_done < budget) { /* Slow packet rate, exit polling */ napi_complete(napi); @@ -833,9 +845,9 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) { + if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) { netif_tx_stop_queue(txq); - nic->drv_stats.tx_busy++; + nic->drv_stats.txq_stop++; if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit ring full, stopping SQ%d\n", @@ -859,7 +871,6 @@ int nicvf_stop(struct net_device *netdev) nicvf_send_msg_to_pf(nic, &mbx); netif_carrier_off(netdev); - netif_tx_disable(netdev); /* Disable RBDR & QS error interrupts */ for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) { @@ -894,6 +905,8 @@ int nicvf_stop(struct net_device *netdev) kfree(cq_poll); } + netif_tx_disable(netdev); + /* Free resources */ nicvf_config_data_transfer(nic, false); @@ -988,6 +1001,9 @@ int nicvf_open(struct net_device *netdev) for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); + nic->drv_stats.txq_stop = 0; + nic->drv_stats.txq_wake = 0; + netif_carrier_on(netdev); netif_tx_start_all_queues(netdev); @@ -1278,6 +1294,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features = netdev->features; netdev->netdev_ops = &nicvf_netdev_ops; + netdev->watchdog_timeo = NICVF_TX_TIMEOUT; INIT_WORK(&nic->reset_task, nicvf_reset_task); @@ -1318,11 +1335,17 @@ static void nicvf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static void nicvf_shutdown(struct pci_dev *pdev) +{ + nicvf_remove(pdev); +} + static struct pci_driver nicvf_driver = { .name = DRV_NAME, .id_table = nicvf_id_table, .probe = nicvf_probe, .remove = nicvf_remove, + .shutdown = nicvf_shutdown, }; static int __init nicvf_init_module(void) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index d69d228d11a0..ca4240aa6d15 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -103,9 +103,11 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, /* Allocate a new page */ if (!nic->rb_page) { - nic->rb_page = alloc_pages(gfp | __GFP_COMP, order); + nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, + order); if (!nic->rb_page) { - netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n"); + netdev_err(nic->netdev, + "Failed to allocate new rcv buffer\n"); return -ENOMEM; } nic->rb_page_offset = 0; @@ -382,7 +384,8 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) return; if (sq->tso_hdrs) - dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len, + dma_free_coherent(&nic->pdev->dev, + sq->dmem.q_len * TSO_HEADER_SIZE, sq->tso_hdrs, sq->tso_hdrs_phys); kfree(sq->skbuff); @@ -863,10 +866,11 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq, continue; } skb = (struct sk_buff *)sq->skbuff[sq->head]; + if (skb) + dev_kfree_skb_any(skb); atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets); atomic64_add(hdr->tot_len, (atomic64_t *)&netdev->stats.tx_bytes); - dev_kfree_skb_any(skb); nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); } } @@ -992,7 +996,7 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry, memset(gather, 0, SND_QUEUE_DESC_SIZE); gather->subdesc_type = SQ_DESC_TYPE_GATHER; - gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB; + gather->ld_type = NIC_SEND_LD_TYPE_E_LDD; gather->size = size; gather->addr = data; } @@ -1048,7 +1052,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, } nicvf_sq_add_hdr_subdesc(sq, hdr_qentry, seg_subdescs - 1, skb, seg_len); - sq->skbuff[hdr_qentry] = 0; + sq->skbuff[hdr_qentry] = (u64)NULL; qentry = nicvf_get_nxt_sqentry(sq, qentry); desc_cnt += seg_subdescs; @@ -1062,6 +1066,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, /* Inform HW to xmit all TSO segments */ nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, skb_get_queue_mapping(skb), desc_cnt); + nic->drv_stats.tx_tso++; return 1; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 8341bdf755d1..f0937b7bfe9f 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -62,7 +62,7 @@ #define SND_QUEUE_CNT 8 #define CMP_QUEUE_CNT 8 /* Max of RCV and SND qcount */ -#define SND_QSIZE SND_QUEUE_SIZE4 +#define SND_QSIZE SND_QUEUE_SIZE2 #define SND_QUEUE_LEN (1ULL << (SND_QSIZE + 10)) #define MAX_SND_QUEUE_LEN (1ULL << (SND_QUEUE_SIZE6 + 10)) #define SND_QUEUE_THRESH 2ULL @@ -70,7 +70,10 @@ /* Since timestamp not enabled, otherwise 2 */ #define MAX_CQE_PER_PKT_XMIT 1 -#define CMP_QSIZE CMP_QUEUE_SIZE4 +/* Keep CQ and SQ sizes same, if timestamping + * is enabled this equation will change. + */ +#define CMP_QSIZE CMP_QUEUE_SIZE2 #define CMP_QUEUE_LEN (1ULL << (CMP_QSIZE + 10)) #define CMP_QUEUE_CQE_THRESH 0 #define CMP_QUEUE_TIMER_THRESH 220 /* 10usec */ @@ -87,7 +90,12 @@ #define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \ MAX_CQE_PER_PKT_XMIT) -#define RQ_CQ_DROP ((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256) +/* Calculate number of CQEs to reserve for all SQEs. + * Its 1/256th level of CQ size. + * '+ 1' to account for pipelining + */ +#define RQ_CQ_DROP ((256 / (CMP_QUEUE_LEN / \ + (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1) /* Descriptor size in bytes */ #define SND_QUEUE_DESC_SIZE 16 diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 633ec05dfe05..b961a89dc626 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -673,7 +673,10 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg); bgx_flush_dmac_addrs(bgx, lmacid); - if (lmac->phydev) + if ((bgx->lmac_type != BGX_MODE_XFI) && + (bgx->lmac_type != BGX_MODE_XLAUI) && + (bgx->lmac_type != BGX_MODE_40G_KR) && + (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev) phy_disconnect(lmac->phydev); lmac->phydev = NULL; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 1eee73cccdf5..99d33e2d35e6 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -562,6 +562,7 @@ struct fec_enet_private { }; void fec_ptp_init(struct platform_device *pdev); +void fec_ptp_stop(struct platform_device *pdev); void fec_ptp_start_cyclecounter(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1f89c59b4353..32e3807c650e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> +#include <linux/pm_runtime.h> #include <linux/ptrace.h> #include <linux/errno.h> #include <linux/ioport.h> @@ -77,6 +78,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev); #define FEC_ENET_RAEM_V 0x8 #define FEC_ENET_RAFL_V 0x8 #define FEC_ENET_OPD_V 0xFFF0 +#define FEC_MDIO_PM_TIMEOUT 100 /* ms */ static struct platform_device_id fec_devtype[] = { { @@ -1767,7 +1769,13 @@ static void fec_enet_adjust_link(struct net_device *ndev) static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; unsigned long time_left; + int ret = 0; + + ret = pm_runtime_get_sync(dev); + if (IS_ERR_VALUE(ret)) + return ret; fep->mii_timeout = 0; init_completion(&fep->mdio_done); @@ -1783,18 +1791,30 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) if (time_left == 0) { fep->mii_timeout = 1; netdev_err(fep->netdev, "MDIO read timeout\n"); - return -ETIMEDOUT; + ret = -ETIMEDOUT; + goto out; } - /* return value */ - return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); + ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); + +out: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; } static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value) { struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; unsigned long time_left; + int ret = 0; + + ret = pm_runtime_get_sync(dev); + if (IS_ERR_VALUE(ret)) + return ret; fep->mii_timeout = 0; init_completion(&fep->mdio_done); @@ -1811,10 +1831,13 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, if (time_left == 0) { fep->mii_timeout = 1; netdev_err(fep->netdev, "MDIO write timeout\n"); - return -ETIMEDOUT; + ret = -ETIMEDOUT; } - return 0; + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; } static int fec_enet_clk_enable(struct net_device *ndev, bool enable) @@ -1826,9 +1849,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) ret = clk_prepare_enable(fep->clk_ahb); if (ret) return ret; - ret = clk_prepare_enable(fep->clk_ipg); - if (ret) - goto failed_clk_ipg; if (fep->clk_enet_out) { ret = clk_prepare_enable(fep->clk_enet_out); if (ret) @@ -1852,7 +1872,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) } } else { clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { @@ -1874,8 +1893,6 @@ failed_clk_ptp: if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); failed_clk_enet_out: - clk_disable_unprepare(fep->clk_ipg); -failed_clk_ipg: clk_disable_unprepare(fep->clk_ahb); return ret; @@ -2847,10 +2864,14 @@ fec_enet_open(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); int ret; + ret = pm_runtime_get_sync(&fep->pdev->dev); + if (IS_ERR_VALUE(ret)) + return ret; + pinctrl_pm_select_default_state(&fep->pdev->dev); ret = fec_enet_clk_enable(ndev, true); if (ret) - return ret; + goto clk_enable; /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. @@ -2881,6 +2902,9 @@ err_enet_mii_probe: fec_enet_free_buffers(ndev); err_enet_alloc: fec_enet_clk_enable(ndev, false); +clk_enable: + pm_runtime_mark_last_busy(&fep->pdev->dev); + pm_runtime_put_autosuspend(&fep->pdev->dev); pinctrl_pm_select_sleep_state(&fep->pdev->dev); return ret; } @@ -2903,6 +2927,9 @@ fec_enet_close(struct net_device *ndev) fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&fep->pdev->dev); + pm_runtime_mark_last_busy(&fep->pdev->dev); + pm_runtime_put_autosuspend(&fep->pdev->dev); + fec_enet_free_buffers(ndev); return 0; @@ -3115,8 +3142,8 @@ static int fec_enet_init(struct net_device *ndev) fep->bufdesc_size; /* Allocate memory for buffer descriptors. */ - cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma, - GFP_KERNEL); + cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma, + GFP_KERNEL); if (!cbd_base) { return -ENOMEM; } @@ -3388,6 +3415,10 @@ fec_probe(struct platform_device *pdev) if (ret) goto failed_clk; + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + fep->reg_phy = devm_regulator_get(&pdev->dev, "phy"); if (!IS_ERR(fep->reg_phy)) { ret = regulator_enable(fep->reg_phy); @@ -3400,6 +3431,11 @@ fec_probe(struct platform_device *pdev) fep->reg_phy = NULL; } + pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + fec_reset_phy(pdev); if (fep->bufdesc_ex) @@ -3447,6 +3483,10 @@ fec_probe(struct platform_device *pdev) fep->rx_copybreak = COPYBREAK_DEFAULT; INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work); + + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); + return 0; failed_register: @@ -3454,9 +3494,12 @@ failed_register: failed_mii_init: failed_irq: failed_init: + fec_ptp_stop(pdev); if (fep->reg_phy) regulator_disable(fep->reg_phy); failed_regulator: + clk_disable_unprepare(fep->clk_ipg); +failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: failed_phy: @@ -3473,14 +3516,12 @@ fec_drv_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - cancel_delayed_work_sync(&fep->time_keep); cancel_work_sync(&fep->tx_timeout_work); + fec_ptp_stop(pdev); unregister_netdev(ndev); fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); - if (fep->ptp_clock) - ptp_clock_unregister(fep->ptp_clock); of_node_put(fep->phy_node); free_netdev(ndev); @@ -3568,7 +3609,28 @@ failed_clk: return ret; } -static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume); +static int __maybe_unused fec_runtime_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct fec_enet_private *fep = netdev_priv(ndev); + + clk_disable_unprepare(fep->clk_ipg); + + return 0; +} + +static int __maybe_unused fec_runtime_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct fec_enet_private *fep = netdev_priv(ndev); + + return clk_prepare_enable(fep->clk_ipg); +} + +static const struct dev_pm_ops fec_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) + SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) +}; static struct platform_driver fec_driver = { .driver = { diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index a15663ad7f5e..f457a23d0bfb 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -604,6 +604,16 @@ void fec_ptp_init(struct platform_device *pdev) schedule_delayed_work(&fep->time_keep, HZ); } +void fec_ptp_stop(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct fec_enet_private *fep = netdev_priv(ndev); + + cancel_delayed_work_sync(&fep->time_keep); + if (fep->ptp_clock) + ptp_clock_unregister(fep->ptp_clock); +} + /** * fec_ptp_check_pps_event * @fep: the fec_enet_private structure handle diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index ff875028fdff..2b7610f341b0 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -565,22 +565,6 @@ static void gfar_ints_enable(struct gfar_private *priv) } } -static void lock_tx_qs(struct gfar_private *priv) -{ - int i; - - for (i = 0; i < priv->num_tx_queues; i++) - spin_lock(&priv->tx_queue[i]->txlock); -} - -static void unlock_tx_qs(struct gfar_private *priv) -{ - int i; - - for (i = 0; i < priv->num_tx_queues; i++) - spin_unlock(&priv->tx_queue[i]->txlock); -} - static int gfar_alloc_tx_queues(struct gfar_private *priv) { int i; @@ -1376,7 +1360,6 @@ static int gfar_probe(struct platform_device *ofdev) priv->dev = &ofdev->dev; SET_NETDEV_DEV(dev, &ofdev->dev); - spin_lock_init(&priv->bflock); INIT_WORK(&priv->reset_task, gfar_reset_task); platform_set_drvdata(ofdev, priv); @@ -1470,9 +1453,8 @@ static int gfar_probe(struct platform_device *ofdev) goto register_fail; } - device_init_wakeup(&dev->dev, - priv->device_flags & - FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + device_set_wakeup_capable(&dev->dev, priv->device_flags & + FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); /* fill out IRQ number and name fields */ for (i = 0; i < priv->num_grps; i++) { @@ -1540,48 +1522,37 @@ static int gfar_suspend(struct device *dev) struct gfar_private *priv = dev_get_drvdata(dev); struct net_device *ndev = priv->ndev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned long flags; u32 tempval; - int magic_packet = priv->wol_en && (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + if (!netif_running(ndev)) + return 0; + + disable_napi(priv); + netif_tx_lock(ndev); netif_device_detach(ndev); + netif_tx_unlock(ndev); - if (netif_running(ndev)) { + gfar_halt(priv); - local_irq_save(flags); - lock_tx_qs(priv); + if (magic_packet) { + /* Enable interrupt on Magic Packet */ + gfar_write(®s->imask, IMASK_MAG); - gfar_halt_nodisable(priv); + /* Enable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval |= MACCFG2_MPEN; + gfar_write(®s->maccfg2, tempval); - /* Disable Tx, and Rx if wake-on-LAN is disabled. */ + /* re-enable the Rx block */ tempval = gfar_read(®s->maccfg1); - - tempval &= ~MACCFG1_TX_EN; - - if (!magic_packet) - tempval &= ~MACCFG1_RX_EN; - + tempval |= MACCFG1_RX_EN; gfar_write(®s->maccfg1, tempval); - unlock_tx_qs(priv); - local_irq_restore(flags); - - disable_napi(priv); - - if (magic_packet) { - /* Enable interrupt on Magic Packet */ - gfar_write(®s->imask, IMASK_MAG); - - /* Enable Magic Packet mode */ - tempval = gfar_read(®s->maccfg2); - tempval |= MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); - } else { - phy_stop(priv->phydev); - } + } else { + phy_stop(priv->phydev); } return 0; @@ -1592,37 +1563,26 @@ static int gfar_resume(struct device *dev) struct gfar_private *priv = dev_get_drvdata(dev); struct net_device *ndev = priv->ndev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned long flags; u32 tempval; int magic_packet = priv->wol_en && (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); - if (!netif_running(ndev)) { - netif_device_attach(ndev); + if (!netif_running(ndev)) return 0; - } - if (!magic_packet && priv->phydev) + if (magic_packet) { + /* Disable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval &= ~MACCFG2_MPEN; + gfar_write(®s->maccfg2, tempval); + } else { phy_start(priv->phydev); - - /* Disable Magic Packet mode, in case something - * else woke us up. - */ - local_irq_save(flags); - lock_tx_qs(priv); - - tempval = gfar_read(®s->maccfg2); - tempval &= ~MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); + } gfar_start(priv); - unlock_tx_qs(priv); - local_irq_restore(flags); - netif_device_attach(ndev); - enable_napi(priv); return 0; @@ -2045,7 +2005,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) /* Install our interrupt handlers for Error, * Transmit, and Receive */ - err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0, + err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, + IRQF_NO_SUSPEND, gfar_irq(grp, ER)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", @@ -2068,7 +2029,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) goto rx_irq_fail; } } else { - err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0, + err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, + IRQF_NO_SUSPEND, gfar_irq(grp, TX)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", @@ -2169,8 +2131,6 @@ static int gfar_enet_open(struct net_device *dev) if (err) return err; - device_set_wakeup_enable(&dev->dev, priv->wol_en); - return err; } diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index daa1d37de642..5545e4103368 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -1145,9 +1145,6 @@ struct gfar_private { int oldduplex; int oldlink; - /* Bitfield update lock */ - spinlock_t bflock; - uint32_t msg_enable; struct work_struct reset_task; diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index fda12fb32ec7..3c0a8f825b63 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -653,7 +653,6 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct gfar_private *priv = netdev_priv(dev); - unsigned long flags; if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && wol->wolopts != 0) @@ -664,9 +663,7 @@ static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC); - spin_lock_irqsave(&priv->bflock, flags); - priv->wol_en = !!device_may_wakeup(&dev->dev); - spin_unlock_irqrestore(&priv->bflock, flags); + priv->wol_en = !!device_may_wakeup(&dev->dev); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 82040137d7d9..0a3202047569 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -686,6 +686,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, { struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd; struct mlx4_cmd_context *context; + long ret_wait; int err = 0; down(&cmd->event_sem); @@ -711,8 +712,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, if (err) goto out_reset; - if (!wait_for_completion_timeout(&context->done, - msecs_to_jiffies(timeout))) { + if (op == MLX4_CMD_SENSE_PORT) { + ret_wait = + wait_for_completion_interruptible_timeout(&context->done, + msecs_to_jiffies(timeout)); + if (ret_wait < 0) { + context->fw_status = 0; + context->out_param = 0; + context->result = 0; + } + } else { + ret_wait = (long)wait_for_completion_timeout(&context->done, + msecs_to_jiffies(timeout)); + } + if (!ret_wait) { mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n", op); if (op == MLX4_CMD_NOP) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7a4f20bb7fcb..9c145dddd717 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -246,7 +246,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) { - BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size); return ring->prod == ring->cons; } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index aae13adfb492..8e81e53c370e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -601,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n", __func__, i, port); - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( @@ -640,7 +640,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; if (i == mlx4_master_func_num(dev)) continue; - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 12fbfcb44d8a..29c2a017a450 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2273,6 +2273,11 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) } else if (err == -ENOENT) { err = 0; continue; + } else if (mlx4_is_slave(dev) && err == -EINVAL) { + priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev); + mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n", + MLX4_SINK_COUNTER_INDEX(dev)); + err = 0; } else { mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n", __func__, port + 1, err); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 33669c29b341..753ea8bad953 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1415,7 +1415,7 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter) if (fw->size & 0xF) { addr = dest + size; for (i = 0; i < (fw->size & 0xF); i++) - data[i] = temp[size + i]; + data[i] = ((u8 *)temp)[size + i]; for (; i < 16; i++) data[i] = 0; ret = qlcnic_ms_mem_write128(adapter, addr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index f3918c7e7eeb..bcdc8955c719 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -413,3 +413,7 @@ static int stmmac_pltfr_resume(struct device *dev) SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend, stmmac_pltfr_resume); EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops); + +MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support"); +MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 0c5842aeb807..ab6051a43134 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6658,10 +6658,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, struct sk_buff *skb_new; skb_new = skb_realloc_headroom(skb, len); - if (!skb_new) { - rp->tx_errors++; + if (!skb_new) goto out_drop; - } kfree_skb(skb); skb = skb_new; } else diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index bbacf5cccec2..a8a730641bbb 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -223,6 +223,7 @@ void *netcp_device_find_module(struct netcp_device *netcp_device, /* SGMII functions */ int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port); +bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set); int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port); int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index ec8ed30196f3..9749dfd78c43 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2112,6 +2112,7 @@ probe_quit: static int netcp_remove(struct platform_device *pdev) { struct netcp_device *netcp_device = platform_get_drvdata(pdev); + struct netcp_intf *netcp_intf, *netcp_tmp; struct netcp_inst_modpriv *inst_modpriv, *tmp; struct netcp_module *module; @@ -2123,10 +2124,17 @@ static int netcp_remove(struct platform_device *pdev) list_del(&inst_modpriv->inst_list); kfree(inst_modpriv); } - WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n", - pdev->name); - devm_kfree(&pdev->dev, netcp_device); + /* now that all modules are removed, clean up the interfaces */ + list_for_each_entry_safe(netcp_intf, netcp_tmp, + &netcp_device->interface_head, + interface_list) { + netcp_delete_interface(netcp_device, netcp_intf->ndev); + } + + WARN(!list_empty(&netcp_device->interface_head), + "%s interface list not empty!\n", pdev->name); + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 9b7e0a34c98b..1974a8ae764a 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -1901,11 +1901,28 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control)); } +static void gbe_sgmii_rtreset(struct gbe_priv *priv, + struct gbe_slave *slave, bool set) +{ + void __iomem *sgmii_port_regs; + + if (SLAVE_LINK_IS_XGMII(slave)) + return; + + if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2)) + sgmii_port_regs = priv->sgmii_port34_regs; + else + sgmii_port_regs = priv->sgmii_port_regs; + + netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set); +} + static void gbe_slave_stop(struct gbe_intf *intf) { struct gbe_priv *gbe_dev = intf->gbe_dev; struct gbe_slave *slave = intf->slave; + gbe_sgmii_rtreset(gbe_dev, slave, true); gbe_port_reset(slave); /* Disable forwarding */ cpsw_ale_control_set(gbe_dev->ale, slave->port_num, @@ -1947,6 +1964,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) gbe_sgmii_config(priv, slave); gbe_port_reset(slave); + gbe_sgmii_rtreset(priv, slave, false); gbe_port_config(priv, slave, priv->rx_packet_max); gbe_set_slave_mac(slave, gbe_intf); /* enable forwarding */ @@ -2490,10 +2508,9 @@ static void free_secondary_ports(struct gbe_priv *gbe_dev) { struct gbe_slave *slave; - for (;;) { + while (!list_empty(&gbe_dev->secondary_slaves)) { slave = first_sec_slave(gbe_dev); - if (!slave) - break; + if (slave->phy) phy_disconnect(slave->phy); list_del(&slave->slave_list); @@ -2839,14 +2856,13 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, &gbe_dev->dma_chan_name); if (ret < 0) { dev_err(dev, "missing \"tx-channel\" parameter\n"); - ret = -ENODEV; - goto quit; + return -EINVAL; } if (!strcmp(node->name, "gbe")) { ret = get_gbe_resource_version(gbe_dev, node); if (ret) - goto quit; + return ret; dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version); @@ -2857,22 +2873,20 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, else ret = -ENODEV; - if (ret) - goto quit; } else if (!strcmp(node->name, "xgbe")) { ret = set_xgbe_ethss10_priv(gbe_dev, node); if (ret) - goto quit; + return ret; ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs, gbe_dev->ss_regs); - if (ret) - goto quit; } else { dev_err(dev, "unknown GBE node(%s)\n", node->name); ret = -ENODEV; - goto quit; } + if (ret) + return ret; + interfaces = of_get_child_by_name(node, "interfaces"); if (!interfaces) dev_err(dev, "could not find interfaces\n"); @@ -2880,11 +2894,11 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device, gbe_dev->dma_chan_name, gbe_dev->tx_queue_id); if (ret) - goto quit; + return ret; ret = netcp_txpipe_open(&gbe_dev->tx_pipe); if (ret) - goto quit; + return ret; /* Create network interfaces */ INIT_LIST_HEAD(&gbe_dev->gbe_intf_head); @@ -2899,6 +2913,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) break; } + of_node_put(interfaces); if (!gbe_dev->num_slaves) dev_warn(dev, "No network interface configured\n"); @@ -2911,9 +2926,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, of_node_put(secondary_ports); if (!gbe_dev->num_slaves) { - dev_err(dev, "No network interface or secondary ports configured\n"); + dev_err(dev, + "No network interface or secondary ports configured\n"); ret = -ENODEV; - goto quit; + goto free_sec_ports; } memset(&ale_params, 0, sizeof(ale_params)); @@ -2927,7 +2943,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (!gbe_dev->ale) { dev_err(gbe_dev->dev, "error initializing ale engine\n"); ret = -ENODEV; - goto quit; + goto free_sec_ports; } else { dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n"); } @@ -2943,14 +2959,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, *inst_priv = gbe_dev; return 0; -quit: - if (gbe_dev->hw_stats) - devm_kfree(dev, gbe_dev->hw_stats); - cpsw_ale_destroy(gbe_dev->ale); - if (gbe_dev->ss_regs) - devm_iounmap(dev, gbe_dev->ss_regs); - of_node_put(interfaces); - devm_kfree(dev, gbe_dev); +free_sec_ports: + free_secondary_ports(gbe_dev); return ret; } @@ -3023,12 +3033,9 @@ static int gbe_remove(struct netcp_device *netcp_device, void *inst_priv) free_secondary_ports(gbe_dev); if (!list_empty(&gbe_dev->gbe_intf_head)) - dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n"); + dev_alert(gbe_dev->dev, + "unreleased ethss interfaces present\n"); - devm_kfree(gbe_dev->dev, gbe_dev->hw_stats); - devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs); - memset(gbe_dev, 0x00, sizeof(*gbe_dev)); - devm_kfree(gbe_dev->dev, gbe_dev); return 0; } diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c index dbeb14266e2f..5d8419f658d0 100644 --- a/drivers/net/ethernet/ti/netcp_sgmii.c +++ b/drivers/net/ethernet/ti/netcp_sgmii.c @@ -18,6 +18,9 @@ #include "netcp.h" +#define SGMII_SRESET_RESET BIT(0) +#define SGMII_SRESET_RTRESET BIT(1) + #define SGMII_REG_STATUS_LOCK BIT(4) #define SGMII_REG_STATUS_LINK BIT(0) #define SGMII_REG_STATUS_AUTONEG BIT(2) @@ -51,12 +54,35 @@ static void sgmii_write_reg_bit(void __iomem *base, int reg, u32 val) int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port) { /* Soft reset */ - sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1); - while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0) + sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), + SGMII_SRESET_RESET); + + while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) & + SGMII_SRESET_RESET) != 0x0) ; + return 0; } +/* port is 0 based */ +bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set) +{ + u32 reg; + bool oldval; + + /* Initiate a soft reset */ + reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)); + oldval = (reg & SGMII_SRESET_RTRESET) != 0x0; + if (set) + reg |= SGMII_SRESET_RTRESET; + else + reg &= ~SGMII_SRESET_RTRESET; + sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg); + wmb(); + + return oldval; +} + int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port) { u32 status = 0, link = 0; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 3b933bb5a8d5..edd77342773a 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -719,6 +719,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, struct virtio_net_hdr vnet_hdr = { 0 }; int vnet_hdr_len = 0; int copylen = 0; + int depth; bool zerocopy = false; size_t linear; ssize_t n; @@ -804,6 +805,12 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_probe_transport_header(skb, ETH_HLEN); + /* Move network header to the right position for VLAN tagged packets */ + if ((skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); + rcu_read_lock(); vlan = rcu_dereference(q->vlan); /* copy skb_ubuf_info for callback when skb has no error */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7f6419ebb5e1..ad8cbc6c9ee7 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -27,7 +27,7 @@ #include <linux/usb/cdc.h> /* Version Information */ -#define DRIVER_VERSION "v1.08.0 (2015/01/13)" +#define DRIVER_VERSION "v1.08.1 (2015/07/28)" #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>" #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters" #define MODULENAME "r8152" @@ -1902,11 +1902,10 @@ static void rtl_drop_queued_tx(struct r8152 *tp) static void rtl8152_tx_timeout(struct net_device *netdev) { struct r8152 *tp = netdev_priv(netdev); - int i; netif_warn(tp, tx_err, netdev, "Tx timeout\n"); - for (i = 0; i < RTL8152_MAX_TX; i++) - usb_unlink_urb(tp->tx_info[i].urb); + + usb_queue_reset_device(tp->intf); } static void rtl8152_set_rx_mode(struct net_device *netdev) @@ -2075,7 +2074,6 @@ static int rtl_start_rx(struct r8152 *tp) { int i, ret = 0; - napi_disable(&tp->napi); INIT_LIST_HEAD(&tp->rx_done); for (i = 0; i < RTL8152_MAX_RX; i++) { INIT_LIST_HEAD(&tp->rx_info[i].list); @@ -2083,7 +2081,6 @@ static int rtl_start_rx(struct r8152 *tp) if (ret) break; } - napi_enable(&tp->napi); if (ret && ++i < RTL8152_MAX_RX) { struct list_head rx_queue; @@ -2166,6 +2163,7 @@ static int rtl8153_enable(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return -ENODEV; + usb_disable_lpm(tp->udev); set_tx_qlen(tp); rtl_set_eee_plus(tp); r8153_set_rx_early_timeout(tp); @@ -2337,11 +2335,61 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) device_set_wakeup_enable(&tp->udev->dev, false); } +static void r8153_u1u2en(struct r8152 *tp, bool enable) +{ + u8 u1u2[8]; + + if (enable) + memset(u1u2, 0xff, sizeof(u1u2)); + else + memset(u1u2, 0x00, sizeof(u1u2)); + + usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2); +} + +static void r8153_u2p3en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL); + if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04) + ocp_data |= U2P3_ENABLE; + else + ocp_data &= ~U2P3_ENABLE; + ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data); +} + +static void r8153_power_cut_en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT); + if (enable) + ocp_data |= PWR_EN | PHASE2_EN; + else + ocp_data &= ~(PWR_EN | PHASE2_EN); + ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data); + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); + ocp_data &= ~PCUT_STATUS; + ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); +} + +static bool rtl_can_wakeup(struct r8152 *tp) +{ + struct usb_device *udev = tp->udev; + + return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP); +} + static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) { if (enable) { u32 ocp_data; + r8153_u1u2en(tp, false); + r8153_u2p3en(tp, false); + __rtl_set_wol(tp, WAKE_ANY); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); @@ -2353,6 +2401,8 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); } else { __rtl_set_wol(tp, tp->saved_wolopts); + r8153_u2p3en(tp, true); + r8153_u1u2en(tp, true); } } @@ -2599,46 +2649,6 @@ static void r8153_hw_phy_cfg(struct r8152 *tp) set_bit(PHY_RESET, &tp->flags); } -static void r8153_u1u2en(struct r8152 *tp, bool enable) -{ - u8 u1u2[8]; - - if (enable) - memset(u1u2, 0xff, sizeof(u1u2)); - else - memset(u1u2, 0x00, sizeof(u1u2)); - - usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2); -} - -static void r8153_u2p3en(struct r8152 *tp, bool enable) -{ - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL); - if (enable) - ocp_data |= U2P3_ENABLE; - else - ocp_data &= ~U2P3_ENABLE; - ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data); -} - -static void r8153_power_cut_en(struct r8152 *tp, bool enable) -{ - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT); - if (enable) - ocp_data |= PWR_EN | PHASE2_EN; - else - ocp_data &= ~(PWR_EN | PHASE2_EN); - ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data); - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); - ocp_data &= ~PCUT_STATUS; - ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); -} - static void r8153_first_init(struct r8152 *tp) { u32 ocp_data; @@ -2781,6 +2791,7 @@ static void rtl8153_disable(struct r8152 *tp) r8153_disable_aldps(tp); rtl_disable(tp); r8153_enable_aldps(tp); + usb_enable_lpm(tp->udev); } static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) @@ -2901,9 +2912,13 @@ static void rtl8153_up(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; + r8153_u1u2en(tp, false); r8153_disable_aldps(tp); r8153_first_init(tp); r8153_enable_aldps(tp); + r8153_u2p3en(tp, true); + r8153_u1u2en(tp, true); + usb_enable_lpm(tp->udev); } static void rtl8153_down(struct r8152 *tp) @@ -2914,6 +2929,7 @@ static void rtl8153_down(struct r8152 *tp) } r8153_u1u2en(tp, false); + r8153_u2p3en(tp, false); r8153_power_cut_en(tp, false); r8153_disable_aldps(tp); r8153_enter_oob(tp); @@ -2932,8 +2948,10 @@ static void set_carrier(struct r8152 *tp) if (!netif_carrier_ok(netdev)) { tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); + napi_disable(&tp->napi); netif_carrier_on(netdev); rtl_start_rx(tp); + napi_enable(&tp->napi); } } else { if (netif_carrier_ok(netdev)) { @@ -3252,6 +3270,7 @@ static void r8153_init(struct r8152 *tp) msleep(20); } + usb_disable_lpm(tp->udev); r8153_u2p3en(tp, false); if (tp->version == RTL_VER_04) { @@ -3319,6 +3338,59 @@ static void r8153_init(struct r8152 *tp) r8153_enable_aldps(tp); r8152b_enable_fc(tp); rtl_tally_reset(tp); + r8153_u2p3en(tp, true); +} + +static int rtl8152_pre_reset(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev; + + if (!tp) + return 0; + + netdev = tp->netdev; + if (!netif_running(netdev)) + return 0; + + napi_disable(&tp->napi); + clear_bit(WORK_ENABLE, &tp->flags); + usb_kill_urb(tp->intr_urb); + cancel_delayed_work_sync(&tp->schedule); + if (netif_carrier_ok(netdev)) { + netif_stop_queue(netdev); + mutex_lock(&tp->control); + tp->rtl_ops.disable(tp); + mutex_unlock(&tp->control); + } + + return 0; +} + +static int rtl8152_post_reset(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev; + + if (!tp) + return 0; + + netdev = tp->netdev; + if (!netif_running(netdev)) + return 0; + + set_bit(WORK_ENABLE, &tp->flags); + if (netif_carrier_ok(netdev)) { + mutex_lock(&tp->control); + tp->rtl_ops.enable(tp); + rtl8152_set_rx_mode(netdev); + mutex_unlock(&tp->control); + netif_wake_queue(netdev); + } + + napi_enable(&tp->napi); + + return 0; } static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) @@ -3374,9 +3446,11 @@ static int rtl8152_resume(struct usb_interface *intf) if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); + napi_disable(&tp->napi); set_bit(WORK_ENABLE, &tp->flags); if (netif_carrier_ok(tp->netdev)) rtl_start_rx(tp); + napi_enable(&tp->napi); } else { tp->rtl_ops.up(tp); rtl8152_set_speed(tp, AUTONEG_ENABLE, @@ -3403,12 +3477,15 @@ static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (usb_autopm_get_interface(tp->intf) < 0) return; - mutex_lock(&tp->control); - - wol->supported = WAKE_ANY; - wol->wolopts = __rtl_get_wol(tp); - - mutex_unlock(&tp->control); + if (!rtl_can_wakeup(tp)) { + wol->supported = 0; + wol->wolopts = 0; + } else { + mutex_lock(&tp->control); + wol->supported = WAKE_ANY; + wol->wolopts = __rtl_get_wol(tp); + mutex_unlock(&tp->control); + } usb_autopm_put_interface(tp->intf); } @@ -3418,6 +3495,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct r8152 *tp = netdev_priv(dev); int ret; + if (!rtl_can_wakeup(tp)) + return -EOPNOTSUPP; + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out_set_wol; @@ -4059,6 +4139,9 @@ static int rtl8152_probe(struct usb_interface *intf, goto out1; } + if (!rtl_can_wakeup(tp)) + __rtl_set_wol(tp, 0); + tp->saved_wolopts = __rtl_get_wol(tp); if (tp->saved_wolopts) device_set_wakeup_enable(&udev->dev, true); @@ -4132,6 +4215,8 @@ static struct usb_driver rtl8152_driver = { .suspend = rtl8152_suspend, .resume = rtl8152_resume, .reset_resume = rtl8152_resume, + .pre_reset = rtl8152_pre_reset, + .post_reset = rtl8152_post_reset, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 044a124bfbbc..21b15f6fee25 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,11 +8,19 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +/** + * struct macb_platform_data - platform data for MACB Ethernet + * @phy_mask: phy mask passed when register the MDIO bus + * within the driver + * @phy_irq_pin: PHY IRQ + * @is_rmii: using RMII interface? + * @rev_eth_addr: reverse Ethernet address byte order + */ struct macb_platform_data { u32 phy_mask; - int phy_irq_pin; /* PHY IRQ */ - u8 is_rmii; /* using RMII interface? */ - u8 rev_eth_addr; /* reverse Ethernet address byte order */ + int phy_irq_pin; + u8 is_rmii; + u8 rev_eth_addr; }; #endif /* __MACB_PDATA_H__ */ diff --git a/include/net/act_api.h b/include/net/act_api.h index 3ee4c92afd1b..931738bc5bba 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -99,7 +99,6 @@ struct tc_action_ops { int tcf_hash_search(struct tc_action *a, u32 index); void tcf_hash_destroy(struct tc_action *a); -int tcf_hash_release(struct tc_action *a, int bind); u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); int tcf_hash_check(u32 index, struct tc_action *a, int bind); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, @@ -107,6 +106,13 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); void tcf_hash_insert(struct tc_action *a); +int __tcf_hash_release(struct tc_action *a, bool bind, bool strict); + +static inline int tcf_hash_release(struct tc_action *a, bool bind) +{ + return __tcf_hash_release(a, bind, false); +} + int tcf_register_action(struct tc_action_ops *a, unsigned int mask); int tcf_unregister_action(struct tc_action_ops *a); int tcf_action_destroy(struct list_head *actions, int bind); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index e1300b3dd597..53eead2da743 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -21,13 +21,11 @@ struct netns_frags { * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction - * @INET_FRAG_EVICTED: frag queue is being evicted */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), - INET_FRAG_EVICTED = BIT(3) }; /** @@ -45,6 +43,7 @@ enum { * @flags: fragment queue flags * @max_size: maximum received fragment size * @net: namespace that this frag belongs to + * @list_evictor: list of queues to forcefully evict (e.g. due to low memory) */ struct inet_frag_queue { spinlock_t lock; @@ -59,6 +58,7 @@ struct inet_frag_queue { __u8 flags; u16 max_size; struct netns_frags *net; + struct hlist_node list_evictor; }; #define INETFRAGS_HASHSZ 1024 @@ -125,6 +125,11 @@ static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f inet_frag_destroy(q, f); } +static inline bool inet_frag_evicting(struct inet_frag_queue *q) +{ + return !hlist_unhashed(&q->list_evictor); +} + /* Memory Tracking Functions. */ /* The default percpu_counter batch size is not big enough to scale to @@ -139,14 +144,14 @@ static inline int frag_mem_limit(struct netns_frags *nf) return percpu_counter_read(&nf->mem); } -static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i) +static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch); + __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch); } -static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i) +static inline void add_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch); + __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch); } static inline void init_frag_mem_limit(struct netns_frags *nf) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 49c142bdf01e..5fa643b4e891 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -183,7 +183,6 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; - int tb_default; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; @@ -290,7 +289,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); -void fib_select_default(struct fib_result *res); +void fib_select_default(const struct flowi4 *flp, struct fib_result *res); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 095433b8a8b0..37cd3911d5c5 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -291,7 +291,7 @@ extern unsigned int nf_conntrack_max; extern unsigned int nf_conntrack_hash_rnd; void init_nf_conntrack_hash_rnd(void); -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl); +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags); #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 29d6a94db54d..723b61c82b3f 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -68,7 +68,6 @@ struct ct_pcpu { spinlock_t lock; struct hlist_nulls_head unconfirmed; struct hlist_nulls_head dying; - struct hlist_nulls_head tmpl; }; struct netns_ct { diff --git a/include/net/sock.h b/include/net/sock.h index 05a8c1aea251..f21f0708ec59 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -902,7 +902,7 @@ void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); -int sk_wait_data(struct sock *sk, long *timeo); +int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 3d0f7d2a0616..ad82324f710f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2312,6 +2312,10 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) return 1; chan = conn->smp; + if (!chan) { + BT_ERR("SMP security requested but not available"); + return 1; + } if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 0ff6e1bbca91..fa7bfced888e 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -37,15 +37,30 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) { - if (!is_skb_forwardable(skb->dev, skb)) { - kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); - br_drop_fake_rtable(skb); - skb_sender_cpu_clear(skb); - dev_queue_xmit(skb); + if (!is_skb_forwardable(skb->dev, skb)) + goto drop; + + skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); + skb_sender_cpu_clear(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD))) { + int depth; + + if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + goto drop; + + skb_set_network_header(skb, depth); } + dev_queue_xmit(skb); + + return 0; + +drop: + kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1198a3dbad95..c94321955db7 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -445,6 +445,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (p->port->state == BR_STATE_DISABLED) goto unlock; + entry->state = p->state; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 79db489cdade..0b39dcc65b94 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1416,8 +1416,7 @@ br_multicast_leave_group(struct net_bridge *br, spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED) || - timer_pending(&other_query->timer)) + (port && port->state == BR_STATE_DISABLED)) goto out; mdb = mlock_dereference(br->mdb, br); @@ -1425,6 +1424,31 @@ br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + + if (timer_pending(&other_query->timer)) + goto out; + if (br->multicast_querier) { __br_multicast_send_query(br, port, &mp->addr); @@ -1450,28 +1474,6 @@ br_multicast_leave_group(struct net_bridge *br, } } - if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { - struct net_bridge_port_group __rcu **pp; - - for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; - pp = &p->next) { - if (p->port != port) - continue; - - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); - - if (!mp->ports && !mp->mglist && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); - } - goto out; - } - now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 364bdc98bd9b..3da5525eb8a2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -693,9 +693,17 @@ static int br_port_slave_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[]) { + struct net_bridge *br = netdev_priv(brdev); + int ret; + if (!data) return 0; - return br_setport(br_port_get_rtnl(dev), data); + + spin_lock_bh(&br->lock); + ret = br_setport(br_port_get_rtnl(dev), data); + spin_unlock_bh(&br->lock); + + return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index b4b6dab9c285..ed74ffaa851f 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,8 +209,9 @@ void br_transmit_config(struct net_bridge_port *p) br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; - mod_timer(&p->hold_timer, - round_jiffies(jiffies + BR_HOLD_TIME)); + if (p->br->stp_enabled == BR_KERNEL_STP) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); } } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index a2730e7196cd..4ca449a16132 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -48,7 +48,8 @@ void br_stp_enable_bridge(struct net_bridge *br) struct net_bridge_port *p; spin_lock_bh(&br->lock); - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->stp_enabled == BR_KERNEL_STP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); mod_timer(&br->gc_timer, jiffies + HZ/10); br_config_bpdu_generation(br); @@ -127,6 +128,7 @@ static void br_stp_start(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); @@ -140,6 +142,10 @@ static void br_stp_start(struct net_bridge *br) if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); + /* Stop hello and hold timers */ + del_timer(&br->hello_timer); + list_for_each_entry(p, &br->port_list, list) + del_timer(&p->hold_timer); } else { br->stp_enabled = BR_KERNEL_STP; br_debug(br, "using kernel STP\n"); @@ -156,12 +162,17 @@ static void br_stp_stop(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; if (br->stp_enabled == BR_USER_STP) { r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); br_info(br, "userspace STP stopped, return code %d\n", r); /* To start timers on any ports left in blocking */ + mod_timer(&br->hello_timer, jiffies + br->hello_time); + list_for_each_entry(p, &br->port_list, list) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); spin_lock_bh(&br->lock); br_port_state_selection(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 7caf7fae2d5b..5f0f5af0ec35 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -40,7 +40,9 @@ static void br_hello_timer_expired(unsigned long arg) if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); - mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); + if (br->stp_enabled != BR_USER_STP) + mod_timer(&br->hello_timer, + round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 1f2a126f4ffa..6441f47b1a8f 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -23,7 +23,8 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return css_cls_state(task_css(p, net_cls_cgrp_id)); + return css_cls_state(task_css_check(p, net_cls_cgrp_id, + rcu_read_lock_bh_held())); } EXPORT_SYMBOL_GPL(task_cls_state); diff --git a/net/core/sock.c b/net/core/sock.c index 08f16db46070..193901d09757 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1497,7 +1497,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); /* SANITY */ - get_net(sock_net(newsk)); + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); @@ -1967,20 +1968,21 @@ static void __release_sock(struct sock *sk) * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long + * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ -int sk_wait_data(struct sock *sk, long *timeo) +int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { int rc; DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); + rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); finish_wait(sk_sleep(sk), &wait); return rc; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 52a94016526d..b5cf13a28009 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -886,7 +886,7 @@ verify_sock_status: break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f46e4d1306f2..214d44aef35b 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -207,7 +207,7 @@ found: } else { fq->q.meat += skb->len; } - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { @@ -287,7 +287,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, clone->data_len = clone->len; head->data_len -= clone->len; head->len -= clone->len; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } WARN_ON(head == NULL); @@ -310,7 +310,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 933a92820d26..6c8b1fbafce8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1017,14 +1017,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) neigh = neigh_lookup(&arp_tbl, &ip, dev); if (neigh) { - read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); - r->arp_flags = arp_state_to_flags(neigh); - read_unlock_bh(&neigh->lock); - r->arp_ha.sa_family = dev->type; - strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + if (!(neigh->nud_state & NUD_NOARP)) { + read_lock_bh(&neigh->lock); + memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + r->arp_flags = arp_state_to_flags(neigh); + read_unlock_bh(&neigh->lock); + r->arp_ha.sa_family = dev->type; + strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + err = 0; + } neigh_release(neigh); - err = 0; } return err; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e813196c91c7..2d9cb1748f81 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); - blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } return 0; } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index c6211ed60b03..9c02920725db 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -13,6 +13,7 @@ struct fib_alias { u8 fa_state; u8 fa_slen; u32 tb_id; + s16 fa_default; struct rcu_head rcu; }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7358ea4ae93..3a06586b170c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1202,23 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) } /* Must be invoked inside of an RCU protected region. */ -void fib_select_default(struct fib_result *res) +void fib_select_default(const struct flowi4 *flp, struct fib_result *res) { struct fib_info *fi = NULL, *last_resort = NULL; struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; + u8 slen = 32 - res->prefixlen; int order = -1, last_idx = -1; - struct fib_alias *fa; + struct fib_alias *fa, *fa1 = NULL; + u32 last_prio = res->fi->fib_priority; + u8 last_tos = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; + if (fa->fa_slen != slen) + continue; + if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + continue; + if (fa->tb_id != tb->tb_id) + continue; + if (next_fi->fib_priority > last_prio && + fa->fa_tos == last_tos) { + if (last_tos) + continue; + break; + } + if (next_fi->fib_flags & RTNH_F_DEAD) + continue; + last_tos = fa->fa_tos; + last_prio = next_fi->fib_priority; + if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; @@ -1228,10 +1245,11 @@ void fib_select_default(struct fib_result *res) if (!fi) { if (next_fi != res->fi) break; + fa1 = fa; } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { + &last_idx, fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } fi = next_fi; @@ -1239,20 +1257,21 @@ void fib_select_default(struct fib_result *res) } if (order <= 0 || !fi) { - tb->tb_default = -1; + if (fa1) + fa1->fa_default = -1; goto out; } if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { + fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } if (last_idx >= 0) fib_result_assign(res, last_resort); - tb->tb_default = last_idx; + fa1->fa_default = last_idx; out: return; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 15d32612e3c6..37c4bb89a708 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; err = switchdev_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; /* (Optionally) offload fib entry to switch hardware. */ err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type, @@ -1791,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } } @@ -1862,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } @@ -1990,7 +1988,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) return NULL; tb->tb_id = id; - tb->tb_default = -1; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5e346a082e5f..d0a7c0319e3d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -131,34 +131,22 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) unsigned int evicted = 0; HLIST_HEAD(expired); -evict_again: spin_lock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &hb->chain, list) { if (!inet_fragq_should_evict(fq)) continue; - if (!del_timer(&fq->timer)) { - /* q expiring right now thus increment its refcount so - * it won't be freed under us and wait until the timer - * has finished executing then destroy it - */ - atomic_inc(&fq->refcnt); - spin_unlock(&hb->chain_lock); - del_timer_sync(&fq->timer); - inet_frag_put(fq, f); - goto evict_again; - } + if (!del_timer(&fq->timer)) + continue; - fq->flags |= INET_FRAG_EVICTED; - hlist_del(&fq->list); - hlist_add_head(&fq->list, &expired); + hlist_add_head(&fq->list_evictor, &expired); ++evicted; } spin_unlock(&hb->chain_lock); - hlist_for_each_entry_safe(fq, n, &expired, list) + hlist_for_each_entry_safe(fq, n, &expired, list_evictor) f->frag_expire((unsigned long) fq); return evicted; @@ -240,18 +228,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) int i; nf->low_thresh = 0; - local_bh_disable(); evict_again: + local_bh_disable(); seq = read_seqbegin(&f->rnd_seqlock); for (i = 0; i < INETFRAGS_HASHSZ ; i++) inet_evict_bucket(f, &f->hash[i]); - if (read_seqretry(&f->rnd_seqlock, seq)) - goto evict_again; - local_bh_enable(); + cond_resched(); + + if (read_seqretry(&f->rnd_seqlock, seq) || + percpu_counter_sum(&nf->mem)) + goto evict_again; percpu_counter_destroy(&nf->mem); } @@ -284,8 +274,8 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) struct inet_frag_bucket *hb; hb = get_frag_bucket_locked(fq, f); - if (!(fq->flags & INET_FRAG_EVICTED)) - hlist_del(&fq->list); + hlist_del(&fq->list); + fq->flags |= INET_FRAG_COMPLETE; spin_unlock(&hb->chain_lock); } @@ -297,7 +287,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); atomic_dec(&fq->refcnt); - fq->flags |= INET_FRAG_COMPLETE; } } EXPORT_SYMBOL(inet_frag_kill); @@ -330,11 +319,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) fp = xp; } sum = sum_truesize + f->qsize; - sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); + + sub_frag_mem_limit(nf, sum); } EXPORT_SYMBOL(inet_frag_destroy); @@ -390,7 +380,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - add_frag_mem_limit(q, f->qsize); + add_frag_mem_limit(nf, f->qsize); setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 31f71b15cfba..921138f6c97c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg) ipq_kill(qp); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if (!(qp->q.flags & INET_FRAG_EVICTED)) { + if (!inet_frag_evicting(&qp->q)) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; @@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp) kfree_skb(fp); fp = xp; } while (fp); - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); qp->q.flags = 0; qp->q.len = 0; @@ -455,7 +455,7 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - sub_frag_mem_limit(&qp->q, free_it->truesize); + sub_frag_mem_limit(qp->q.net, free_it->truesize); kfree_skb(free_it); } } @@ -479,7 +479,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - add_frag_mem_limit(&qp->q, skb->truesize); + add_frag_mem_limit(qp->q.net, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; @@ -587,7 +587,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&qp->q, clone->truesize); + add_frag_mem_limit(qp->q.net, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -615,7 +615,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d0362a2de3d3..e681b852ced1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (!res.prefixlen && res.table->tb_num_default > 1 && res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(&res); + fib_select_default(fl4, &res); if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7f4056785acc..45534a5ab430 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - struct sk_buff *skb; + struct sk_buff *skb, *last; u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) @@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Next get a buffer. */ + last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { + last = skb; /* Now that we have two receive queues this * shouldn't happen. */ @@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); - } else - sk_wait_data(sk, &timeo); + } else { + sk_wait_data(sk, &timeo, last); + } if (user_recv) { int chunk; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0a05b35a90fc..c53331cfed95 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1650,6 +1650,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; @@ -1664,6 +1665,11 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, ndisc_send_unsol_na(dev); in6_dev_put(idev); break; + case NETDEV_CHANGE: + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + neigh_changeaddr(&nd_tbl, dev); + break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f187c8d8a1b..6d02498172c1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,7 @@ found: fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -430,7 +430,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -454,7 +454,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - sub_frag_mem_limit(&fq->q, head->truesize); + sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; head->next = NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 8ffa2c8cce77..f1159bb76e0a 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -144,7 +144,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - if (fq->q.flags & INET_FRAG_EVICTED) + if (inet_frag_evicting(&fq->q)) goto out_rcu_unlock; IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); @@ -330,7 +330,7 @@ found: fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -443,7 +443,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -481,7 +481,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8fd9febaa5ba..8dab4e569571 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -613,7 +613,7 @@ static int llc_wait_data(struct sock *sk, long timeo) if (signal_pending(current)) break; rc = 0; - if (sk_wait_data(sk, &timeo)) + if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; @@ -802,7 +802,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(sk); lock_sock(sk); } else - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5d2b806a862e..38fbc194b9cb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -319,7 +319,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); @@ -467,7 +473,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 285eae3a1454..24c554201a76 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -842,15 +842,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, __ip_vs_dst_cache_reset(dest); spin_unlock_bh(&dest->dst_lock); - sched = rcu_dereference_protected(svc->scheduler, 1); if (add) { ip_vs_start_estimator(svc->net, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; - if (sched->add_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->add_dest) sched->add_dest(svc, dest); } else { - if (sched->upd_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->upd_dest) sched->upd_dest(svc, dest); } } @@ -1084,7 +1085,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_scheduler *sched; sched = rcu_dereference_protected(svc->scheduler, 1); - if (sched->del_dest) + if (sched && sched->del_dest) sched->del_dest(svc, dest); } } @@ -1175,11 +1176,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, ip_vs_use_count_inc(); /* Lookup the scheduler by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - ret = -ENOENT; - goto out_err; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + ret = -ENOENT; + goto out_err; + } } if (u->pe_name && *u->pe_name) { @@ -1240,10 +1244,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) - goto out_err; - sched = NULL; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) + goto out_err; + sched = NULL; + } /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); @@ -1291,17 +1297,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { - struct ip_vs_scheduler *sched, *old_sched; + struct ip_vs_scheduler *sched = NULL, *old_sched; struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; /* * Lookup the scheduler, by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - return -ENOENT; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + return -ENOENT; + } } old_sched = sched; @@ -1329,14 +1338,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { + if (old_sched) { + ip_vs_unbind_scheduler(svc, old_sched); + RCU_INIT_POINTER(svc->scheduler, NULL); + /* Wait all svc->sched_data users */ + synchronize_rcu(); + } /* Bind the new scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) { - old_sched = sched; - goto out; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) { + ip_vs_scheduler_put(sched); + goto out; + } } - /* Unbind the old scheduler on success */ - ip_vs_unbind_scheduler(svc, old_sched); } /* @@ -1982,6 +1997,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 @@ -1990,18 +2006,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), - sched->name); + sched_name); else #endif seq_printf(seq, "%s %08X:%04X %s %s ", ip_vs_proto_name(svc->protocol), ntohl(svc->addr.ip), ntohs(svc->port), - sched->name, + sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } else { seq_printf(seq, "FWM %08X %s %s", - svc->fwmark, sched->name, + svc->fwmark, sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } @@ -2427,13 +2443,15 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; struct ip_vs_kstats kstats; + char *sched_name; sched = rcu_dereference_protected(src->scheduler, 1); + sched_name = sched ? sched->name : "none"; dst->protocol = src->protocol; dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; - strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name)); + strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name)); dst->flags = src->flags; dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; @@ -2892,6 +2910,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; struct ip_vs_kstats kstats; + char *sched_name; nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) @@ -2910,8 +2929,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, } sched = rcu_dereference_protected(svc->scheduler, 1); + sched_name = sched ? sched->name : "none"; pe = rcu_dereference_protected(svc->pe, 1); - if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) || + if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) || (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) || nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 199760c71f39..7e8141647943 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc, if (sched->done_service) sched->done_service(svc); - /* svc->scheduler can not be set to NULL */ + /* svc->scheduler can be set to NULL only by caller */ } @@ -147,21 +147,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg) { - struct ip_vs_scheduler *sched; + struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; - sched = rcu_dereference(svc->scheduler); if (svc->fwmark) { IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n", - sched->name, svc->fwmark, svc->fwmark, msg); + sched_name, svc->fwmark, svc->fwmark, msg); #ifdef CONFIG_IP_VS_IPV6 } else if (svc->af == AF_INET6) { IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), msg); #endif } else { IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.ip, ntohs(svc->port), msg); } } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index b08ba9538d12..d99ad93eb855 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(net, cp->control, pkts); + ip_vs_sync_conn(net, cp, pkts); } } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index bf66a8657a5f..258a0b0e82a2 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; - fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? FLOWI_FLAG_KNOWN_NH : 0; @@ -505,6 +504,13 @@ err_put: return -1; err_unreach: + /* The ip6_link_failure function requires the dev field to be set + * in order to get the net (further for the sake of fwmark + * reflection). + */ + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } @@ -523,10 +529,27 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); } return ret; } +/* In the event of a remote destination, it's possible that we would have + * matches against an old socket (particularly a TIME-WAIT socket). This + * causes havoc down the line (ip_local_out et. al. expect regular sockets + * and invalid memory accesses will happen) so simply drop the association + * in this case. +*/ +static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb) +{ + /* If dev is set, the packet came from the LOCAL_IN callback and + * not from a local TCP socket. + */ + if (skb->dev) + skb_orphan(skb); +} + /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, struct ip_vs_conn *cp, int local) @@ -538,12 +561,23 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 1); + + /* Remove the early_demux association unless it's bound for the + * exact same port and address on this host after translation. + */ + if (!local || cp->vport != cp->dport || + !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr)) + ip_vs_drop_early_demux_sk(skb); + if (!local) { skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; + return ret; } @@ -557,7 +591,10 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (likely(!(cp->flags & IP_VS_CONN_F_NFCT))) ip_vs_notrack(skb); if (!local) { + ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else @@ -845,6 +882,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, struct ipv6hdr *old_ipv6h = NULL; #endif + ip_vs_drop_early_demux_sk(skb); + if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) { new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 13fad8668f83..651039ad1681 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -287,6 +287,46 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) spin_unlock(&pcpu->lock); } +/* Released via destroy_conntrack() */ +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) +{ + struct nf_conn *tmpl; + + tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL); + if (tmpl == NULL) + return NULL; + + tmpl->status = IPS_TEMPLATE; + write_pnet(&tmpl->ct_net, net); + +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (zone) { + struct nf_conntrack_zone *nf_ct_zone; + + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC); + if (!nf_ct_zone) + goto out_free; + nf_ct_zone->id = zone; + } +#endif + atomic_set(&tmpl->ct_general.use, 0); + + return tmpl; +#ifdef CONFIG_NF_CONNTRACK_ZONES +out_free: + kfree(tmpl); + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); + +static void nf_ct_tmpl_free(struct nf_conn *tmpl) +{ + nf_ct_ext_destroy(tmpl); + nf_ct_ext_free(tmpl); + kfree(tmpl); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -298,6 +338,10 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); + if (unlikely(nf_ct_is_template(ct))) { + nf_ct_tmpl_free(ct); + return; + } rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -540,28 +584,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); -/* deletion from this larval template list happens via nf_ct_put() */ -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) -{ - struct ct_pcpu *pcpu; - - __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); - - /* add this conntrack to the (per cpu) tmpl list */ - local_bh_disable(); - tmpl->cpu = smp_processor_id(); - pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); - - spin_lock(&pcpu->lock); - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &pcpu->tmpl); - spin_unlock_bh(&pcpu->lock); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); - /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -1751,7 +1773,6 @@ int nf_conntrack_init_net(struct net *net) spin_lock_init(&pcpu->lock); INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } net->ct.stat = alloc_percpu(struct ip_conntrack_stat); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 7a17070c5dab..b45a4223cb05 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } - return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask); + return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } static inline int expect_matches(const struct nf_conntrack_expect *a, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d1c23940a86a..6b8b0abbfab4 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2995,11 +2995,6 @@ ctnetlink_create_expect(struct net *net, u16 zone, } err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) - goto err_exp; - - return 0; -err_exp: nf_ct_expect_put(exp); err_ct: nf_ct_put(ct); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 789feeae6c44..71f1e9fdfa18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -349,12 +349,10 @@ static void __net_exit synproxy_proc_exit(struct net *net) static int __net_init synproxy_net_init(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - struct nf_conntrack_tuple t; struct nf_conn *ct; int err = -ENOMEM; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); if (IS_ERR(ct)) { err = PTR_ERR(ct); goto err1; @@ -365,7 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) if (!nfct_synproxy_ext_add(ct)) goto err2; - nf_conntrack_tmpl_insert(net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 75747aecdebe..c6630030c912 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -184,7 +184,6 @@ out: static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { - struct nf_conntrack_tuple t; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -202,8 +201,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err1; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); ret = PTR_ERR(ct); if (IS_ERR(ct)) goto err2; @@ -227,8 +225,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err3; } - - nf_conntrack_tmpl_insert(par->net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f407ebc13481..29d2c31f406c 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -126,6 +126,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9e8741226c6..ed458b315ef4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2403,7 +2403,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); - if (tp_len > dev->mtu + dev->hard_header_len) { + if (likely(tp_len >= 0) && + tp_len > dev->mtu + dev->hard_header_len) { struct ethhdr *ehdr; /* Earlier code assumed this would be a VLAN pkt, * double-check this now that we have the actual @@ -2784,7 +2785,7 @@ static int packet_release(struct socket *sock) static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) { struct packet_sock *po = pkt_sk(sk); - const struct net_device *dev_curr; + struct net_device *dev_curr; __be16 proto_curr; bool need_rehook; @@ -2808,15 +2809,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) po->num = proto; po->prot_hook.type = proto; - - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; packet_cached_dev_assign(po, dev); } + if (dev_curr) + dev_put(dev_curr); if (proto == 0 || !need_rehook) goto out_unlock; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index af427a3dbcba..43ec92680ae8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a) } EXPORT_SYMBOL(tcf_hash_destroy); -int tcf_hash_release(struct tc_action *a, int bind) +int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) { struct tcf_common *p = a->priv; int ret = 0; @@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind) if (p) { if (bind) p->tcfc_bindcnt--; - else if (p->tcfc_bindcnt > 0) + else if (strict && p->tcfc_bindcnt > 0) return -EPERM; p->tcfc_refcnt--; @@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind) ret = 1; } } + return ret; } -EXPORT_SYMBOL(tcf_hash_release); +EXPORT_SYMBOL(__tcf_hash_release); static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a) @@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { a->priv = p; - ret = tcf_hash_release(a, 0); + ret = __tcf_hash_release(a, false, true); if (ret == ACT_P_DELETED) { module_put(a->ops->owner); n_i++; @@ -408,7 +409,7 @@ int tcf_action_destroy(struct list_head *actions, int bind) int ret = 0; list_for_each_entry_safe(a, tmp, actions, list) { - ret = tcf_hash_release(a, bind); + ret = __tcf_hash_release(a, bind, true); if (ret == ACT_P_DELETED) module_put(a->ops->owner); else if (ret < 0) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1df78289e248..d0edeb7a1950 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -27,9 +27,10 @@ struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; - char *bpf_name; + const char *bpf_name; u32 bpf_fd; u16 bpf_num_ops; + bool is_ebpf; }; static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, @@ -207,6 +208,7 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; + cfg->is_ebpf = false; return 0; } @@ -241,18 +243,40 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_fd = bpf_fd; cfg->bpf_name = name; cfg->filter = fp; + cfg->is_ebpf = true; return 0; } +static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) +{ + if (cfg->is_ebpf) + bpf_prog_put(cfg->filter); + else + bpf_prog_destroy(cfg->filter); + + kfree(cfg->bpf_ops); + kfree(cfg->bpf_name); +} + +static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, + struct tcf_bpf_cfg *cfg) +{ + cfg->is_ebpf = tcf_bpf_is_ebpf(prog); + cfg->filter = prog->filter; + + cfg->bpf_ops = prog->bpf_ops; + cfg->bpf_name = prog->bpf_name; +} + static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int replace, int bind) { struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; - struct tcf_bpf_cfg cfg; bool is_bpf, is_ebpf; int ret; @@ -301,6 +325,9 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog = to_bpf(act); spin_lock_bh(&prog->tcf_lock); + if (ret != ACT_P_CREATED) + tcf_bpf_prog_fill_cfg(prog, &old); + prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; @@ -316,32 +343,22 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (ret == ACT_P_CREATED) tcf_hash_insert(act); + else + tcf_bpf_cfg_cleanup(&old); return ret; destroy_fp: - if (is_ebpf) - bpf_prog_put(cfg.filter); - else - bpf_prog_destroy(cfg.filter); - - kfree(cfg.bpf_ops); - kfree(cfg.bpf_name); - + tcf_bpf_cfg_cleanup(&cfg); return ret; } static void tcf_bpf_cleanup(struct tc_action *act, int bind) { - const struct tcf_bpf *prog = act->priv; - - if (tcf_bpf_is_ebpf(prog)) - bpf_prog_put(prog->filter); - else - bpf_prog_destroy(prog->filter); + struct tcf_bpf_cfg tmp; - kfree(prog->bpf_ops); - kfree(prog->bpf_name); + tcf_bpf_prog_fill_cfg(act->priv, &tmp); + tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17e6d6669c7f..ff8b466a73f6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -68,13 +68,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; } else { - p = to_pedit(a); - tcf_hash_release(a, bind); if (bind) return 0; + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; - + p = to_pedit(a); if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 93d5742dc7e0..6a783afe4960 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -385,6 +385,19 @@ static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); + while (q->head != q->tail) { + struct sk_buff *skb = q->tab[q->head]; + + q->head = (q->head + 1) & q->tab_mask; + if (!skb) + continue; + qdisc_qstats_backlog_dec(sch, skb); + --sch->q.qlen; + qdisc_drop(skb, sch); + } + + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 89f8fcf73f18..ade9445a55ab 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -216,6 +216,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .peek = qdisc_peek_head, .init = plug_init, .change = plug_change, + .reset = qdisc_reset_queue, .owner = THIS_MODULE, }; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1425ec2bbd5a..17bef01b9aa3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,12 +2200,6 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; - if (sctp_sk(sk)->subscribe.sctp_data_io_event) - pr_warn_ratelimited(DEPRECATED "%s (pid %d) " - "Requested SCTP_SNDRCVINFO event.\n" - "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n", - current->comm, task_pid_nr(current)); - /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. |