Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster

Pull networking updates from Jakub Kicinski:
 "Not much excitement - a handful of large patchsets (devmem among them)
  did not make it in time.

  Core & protocols:

   - Use local_lock in addition to local_bh_disable() to protect per-CPU
     resources in networking, a step closer for local_bh_disable() not
     to act as a big lock on PREEMPT_RT

   - Use flex array for netdevice priv area, ensure its cache alignment

   - Add a sysctl knob to allow user to specify a default rto_min at
     socket init time. Bit of a big hammer but multiple companies were
     independently carrying such patch downstream so clearly it's useful

   - Support scheduling transmission of packets based on CLOCK_TAI

   - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned
     off using cpusets

   - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address

   - Allow configuration of multipath hash seed, to both allow
     synchronizing hashing of two routers, and preventing partial
     accidental sync

   - Improve TCP compliance with RFC 9293 for simultaneous connect()

   - Support sending NAT keepalives in IPsec ESP in UDP states.
     Userspace IKE daemon had to do this before, but the kernel can
     better keep track of it

   - Support sending supervision HSR frames with MAC addresses stored in
     ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled

   - Introduce IPPROTO_SMC for selecting SMC when socket is created

   - Allow UDP GSO transmit from devices with no checksum offload

   - openvswitch: add packet sampling via psample, separating the
     sampled traffic from "upcall" packets sent to user space for
     forwarding

   - nf_tables: shrink memory consumption for transaction objects

  Things we sprinkled into general kernel code:

   - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for
     QCA6390)           [ Already merged separately - Linus ]

   - Add IRQ information in sysfs for auxiliary bus

   - Introduce guard definition for local_lock

   - Add aligned flavor of __cacheline_group_{begin, end}() markings for
     grouping fields in structures

  BPF:

   - Notify user space (via epoll) when a struct_ops object is getting
     detached/unregistered

   - Add new kfuncs for a generic, open-coded bits iterator

   - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and
     bpf_list_head

   - Support resilient split BTF which cuts down on duplication and
     makes BTF as compact as possible WRT BTF from modules

   - Add support for dumping kfunc prototypes from BTF which enables
     both detecting as well as dumping compilable prototypes for kfuncs

   - riscv64 BPF JIT improvements in particular to add 12-argument
     support for BPF trampolines and to utilize bpf_prog_pack for the
     latter

   - Add the capability to offload the netfilter flowtable in XDP layer
     through kfuncs

  Driver API:

   - Allow users to configure IRQ tresholds between which automatic IRQ
     moderation can choose

   - Expand Power Sourcing (PoE) status with power, class and failure
     reason. Support setting power limits

   - Track additional RSS contexts in the core, make sure configuration
     changes don't break them

   - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated
     ESP data paths

   - Support updating firmware on SFP modules

  Tests and tooling:

   - mptcp: use net/lib.sh to manage netns

   - TCP-AO and TCP-MD5: replace debug prints used by tests with
     tracepoints

   - openvswitch: make test self-contained (don't depend on OvS CLI
     tools)

  Drivers:

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - increase the max total outstanding PTP TX packets to 4
         - add timestamping statistics support
         - implement netdev_queue_mgmt_ops
         - support new RSS context API
      - Intel (100G, ice, idpf):
         - implement FEC statistics and dumping signal quality indicators
         - support E825C products (with 56Gbps PHYs)
      - nVidia/Mellanox:
         - support HW-GRO
         - mlx4/mlx5: support per-queue statistics via netlink
         - obey the max number of EQs setting in sub-functions
      - AMD/Solarflare:
         - support new RSS context API
      - AMD/Pensando:
         - ionic: rework fix for doorbell miss to lower overhead and
           skip it on new HW
      - Wangxun:
         - txgbe: support Flow Director perfect filters

   - Ethernet NICs consumer, embedded and virtual:
      - Add driver for Tehuti Networks TN40xx chips
      - Add driver for Meta's internal NIC chips
      - Add driver for Ethernet MAC on Airoha EN7581 SoCs
      - Add driver for Renesas Ethernet-TSN devices
      - Google cloud vNIC:
         - flow steering support
      - Microsoft vNIC:
         - support page sizes other than 4KB on ARM64
      - vmware vNIC:
         - support latency measurement (update to version 9)
      - VirtIO net:
         - support for Byte Queue Limits
         - support configuring thresholds for automatic IRQ moderation
         - support for AF_XDP Rx zero-copy
      - Synopsys (stmmac):
         - support for STM32MP13 SoC
         - let platforms select the right PCS implementation
      - TI:
         - icssg-prueth: add multicast filtering support
         - icssg-prueth: enable PTP timestamping and PPS
      - Renesas:
         - ravb: improve Rx performance 30-400% by using page pool,
           theaded NAPI and timer-based IRQ coalescing
         - ravb: add MII support for R-Car V4M
      - Cadence (macb):
         - macb: add ARP support to Wake-On-LAN
      - Cortina:
         - use phylib for RX and TX pause configuration

   - Ethernet switches:
      - nVidia/Mellanox:
         - support configuration of multipath hash seed
         - report more accurate max MTU
         - use page_pool to improve Rx performance
      - MediaTek:
         - mt7530: add support for bridge port isolation
      - Qualcomm:
         - qca8k: add support for bridge port isolation
      - Microchip:
         - lan9371/2: add 100BaseTX PHY support
      - NXP:
         - vsc73xx: implement VLAN operations

   - Ethernet PHYs:
      - aquantia: enable support for aqr115c
      - aquantia: add support for PHY LEDs
      - realtek: add support for rtl8224 2.5Gbps PHY
      - xpcs: add memory-mapped device support
      - add BroadR-Reach link mode and support in Broadcom's PHY driver

   - CAN:
      - add document for ISO 15765-2 protocol support
      - mcp251xfd: workaround for erratum DS80000789E, use timestamps to
        catch when device returns incorrect FIFO status

   - WiFi:
      - mac80211/cfg80211:
         - parse Transmit Power Envelope (TPE) data in mac80211 instead
           of in drivers
         - improvements for 6 GHz regulatory flexibility
         - multi-link improvements
         - support multiple radios per wiphy
         - remove DEAUTH_NEED_MGD_TX_PREP flag
      - Intel (iwlwifi):
         - bump FW API to 91 for BZ/SC devices
         - report 64-bit radiotap timestamp
         - enable P2P low latency by default
         - handle Transmit Power Envelope (TPE) advertised by AP
         - remove support for older FW for new devices
         - fast resume (keeping the device configured)
         - mvm: re-enable Multi-Link Operation (MLO)
         - aggregation (A-MSDU) optimizations
      - MediaTek (mt76):
         - mt7925 Multi-Link Operation (MLO) support
      - Qualcomm (ath10k):
         - LED support for various chipsets
      - Qualcomm (ath12k):
         - remove unsupported Tx monitor handling
         - support channel 2 in 6 GHz band
         - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band
         - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID
           Advertisements (EMA)
         - support dynamic VLAN
         - add panic handler for resetting the firmware state
         - DebugFS support for datapath statistics
         - WCN7850: support for Wake on WLAN
      - Microchip (wilc1000):
         - read MAC address during probe to make it visible to user space
         - suspend/resume improvements
      - TI (wl18xx):
         - support newer firmware versions
      - RealTek (rtw89):
         - preparation for RTL8852BE-VT support
         - Wake on WLAN support for WiFi 6 chips
         - 36-bit PCI DMA support
      - RealTek (rtlwifi):
         - RTL8192DU support
      - Broadcom (brcmfmac):
         - Management Frame Protection support (to enable WPA3)

   - Bluetooth:
      - qualcomm: use the power sequencer for QCA6390
      - btusb: mediatek: add ISO data transmission functions
      - hci_bcm4377: add BCM4388 support
      - btintel: add support for BlazarU core
      - btintel: add support for Whale Peak2
      - btnxpuart: add support for AW693 A1 chipset
      - btnxpuart: add support for IW615 chipset
      - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"

* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits)
  eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering"
  tcp: Replace strncpy() with strscpy()
  wifi: ath12k: fix build vs old compiler
  tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child().
  eth: fbnic: Write the TCAM tables used for RSS control and Rx to host
  eth: fbnic: Add L2 address programming
  eth: fbnic: Add basic Rx handling
  eth: fbnic: Add basic Tx handling
  eth: fbnic: Add link detection
  eth: fbnic: Add initial messaging to notify FW of our presence
  eth: fbnic: Implement Rx queue alloc/start/stop/free
  eth: fbnic: Implement Tx queue alloc/start/stop/free
  eth: fbnic: Allocate a netdevice and napi vectors with queues
  eth: fbnic: Add FW communication mechanism
  eth: fbnic: Add message parsing for FW messages
  eth: fbnic: Add register init to set PCIe/Ethernet device config
  eth: fbnic: Allocate core device specific structures and devlink interface
  eth: fbnic: Add scaffolding for Meta's NIC driver
  PCI: Add Meta Platforms vendor ID
  net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK
  ...

1 files changed, 89 insertions, 41 deletions

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c84ce54a84a0..0cc2dd85652f 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -80,7 +80,9 @@ static const struct mtk_reg_map mtk_reg_map = {
 		.fq_blen	= 0x1b2c,
 	},
 	.gdm1_cnt		= 0x2400,
-	.gdma_to_ppe		= 0x4444,
+	.gdma_to_ppe	= {
+		[0]		= 0x4444,
+	},
 	.ppe_base		= 0x0c00,
 	.wdma_base = {
 		[0]		= 0x2800,
@@ -144,7 +146,10 @@ static const struct mtk_reg_map mt7986_reg_map = {
 		.tx_sch_rate	= 0x4798,
 	},
 	.gdm1_cnt		= 0x1c00,
-	.gdma_to_ppe		= 0x3333,
+	.gdma_to_ppe	= {
+		[0]		= 0x3333,
+		[1]		= 0x4444,
+	},
 	.ppe_base		= 0x2000,
 	.wdma_base = {
 		[0]		= 0x4800,
@@ -192,7 +197,11 @@ static const struct mtk_reg_map mt7988_reg_map = {
 		.tx_sch_rate	= 0x4798,
 	},
 	.gdm1_cnt		= 0x1c00,
-	.gdma_to_ppe		= 0x3333,
+	.gdma_to_ppe	= {
+		[0]		= 0x3333,
+		[1]		= 0x4444,
+		[2]		= 0xcccc,
+	},
 	.ppe_base		= 0x2000,
 	.wdma_base = {
 		[0]		= 0x4800,
@@ -2015,6 +2024,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 	struct mtk_rx_dma_v2 *rxd, trxd;
 	int done = 0, bytes = 0;
 	dma_addr_t dma_addr = DMA_MAPPING_ERROR;
+	int ppe_idx = 0;
 
 	while (done < budget) {
 		unsigned int pktlen, *rxdcsum;
@@ -2058,6 +2068,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			goto release_desc;
 
 		netdev = eth->netdev[mac];
+		ppe_idx = eth->mac[mac]->ppe_idx;
 
 		if (unlikely(test_bit(MTK_RESETTING, &eth->state)))
 			goto release_desc;
@@ -2181,7 +2192,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		}
 
 		if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
-			mtk_ppe_check_skb(eth->ppe[0], skb, hash);
+			mtk_ppe_check_skb(eth->ppe[ppe_idx], skb, hash);
 
 		skb_record_rx_queue(skb, 0);
 		napi_gro_receive(napi, skb);
@@ -3276,37 +3287,27 @@ static int mtk_start_dma(struct mtk_eth *eth)
 	return 0;
 }
 
-static void mtk_gdm_config(struct mtk_eth *eth, u32 config)
+static void mtk_gdm_config(struct mtk_eth *eth, u32 id, u32 config)
 {
-	int i;
+	u32 val;
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 		return;
 
-	for (i = 0; i < MTK_MAX_DEVS; i++) {
-		u32 val;
-
-		if (!eth->netdev[i])
-			continue;
-
-		val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i));
+	val = mtk_r32(eth, MTK_GDMA_FWD_CFG(id));
 
-		/* default setup the forward port to send frame to PDMA */
-		val &= ~0xffff;
+	/* default setup the forward port to send frame to PDMA */
+	val &= ~0xffff;
 
-		/* Enable RX checksum */
-		val |= MTK_GDMA_ICS_EN | MTK_GDMA_TCS_EN | MTK_GDMA_UCS_EN;
+	/* Enable RX checksum */
+	val |= MTK_GDMA_ICS_EN | MTK_GDMA_TCS_EN | MTK_GDMA_UCS_EN;
 
-		val |= config;
+	val |= config;
 
-		if (netdev_uses_dsa(eth->netdev[i]))
-			val |= MTK_GDMA_SPECIAL_TAG;
+	if (eth->netdev[id] && netdev_uses_dsa(eth->netdev[id]))
+		val |= MTK_GDMA_SPECIAL_TAG;
 
-		mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i));
-	}
-	/* Reset and enable PSE */
-	mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
-	mtk_w32(eth, 0, MTK_RST_GL);
+	mtk_w32(eth, val, MTK_GDMA_FWD_CFG(id));
 }
 
 
@@ -3366,7 +3367,10 @@ static int mtk_open(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
-	int i, err;
+	struct mtk_mac *target_mac;
+	int i, err, ppe_num;
+
+	ppe_num = eth->soc->ppe_num;
 
 	err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0);
 	if (err) {
@@ -3390,18 +3394,38 @@ static int mtk_open(struct net_device *dev)
 		for (i = 0; i < ARRAY_SIZE(eth->ppe); i++)
 			mtk_ppe_start(eth->ppe[i]);
 
-		gdm_config = soc->offload_version ? soc->reg_map->gdma_to_ppe
-						  : MTK_GDMA_TO_PDMA;
-		mtk_gdm_config(eth, gdm_config);
+		for (i = 0; i < MTK_MAX_DEVS; i++) {
+			if (!eth->netdev[i])
+				continue;
+
+			target_mac = netdev_priv(eth->netdev[i]);
+			if (!soc->offload_version) {
+				target_mac->ppe_idx = 0;
+				gdm_config = MTK_GDMA_TO_PDMA;
+			} else if (ppe_num >= 3 && target_mac->id == 2) {
+				target_mac->ppe_idx = 2;
+				gdm_config = soc->reg_map->gdma_to_ppe[2];
+			} else if (ppe_num >= 2 && target_mac->id == 1) {
+				target_mac->ppe_idx = 1;
+				gdm_config = soc->reg_map->gdma_to_ppe[1];
+			} else {
+				target_mac->ppe_idx = 0;
+				gdm_config = soc->reg_map->gdma_to_ppe[0];
+			}
+			mtk_gdm_config(eth, target_mac->id, gdm_config);
+		}
+		/* Reset and enable PSE */
+		mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
+		mtk_w32(eth, 0, MTK_RST_GL);
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
 		mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
 		mtk_rx_irq_enable(eth, soc->rx.irq_done_mask);
 		refcount_set(&eth->dma_refcnt, 1);
-	}
-	else
+	} else {
 		refcount_inc(&eth->dma_refcnt);
+	}
 
 	phylink_start(mac->phylink);
 	netif_tx_start_all_queues(dev);
@@ -3478,7 +3502,8 @@ static int mtk_stop(struct net_device *dev)
 	if (!refcount_dec_and_test(&eth->dma_refcnt))
 		return 0;
 
-	mtk_gdm_config(eth, MTK_GDMA_DROP_ALL);
+	for (i = 0; i < MTK_MAX_DEVS; i++)
+		mtk_gdm_config(eth, i, MTK_GDMA_DROP_ALL);
 
 	mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
 	mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask);
@@ -4439,6 +4464,20 @@ static int mtk_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return ret;
 }
 
+static void mtk_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	phylink_ethtool_get_pauseparam(mac->phylink, pause);
+}
+
+static int mtk_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_set_pauseparam(mac->phylink, pause);
+}
+
 static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb,
 			    struct net_device *sb_dev)
 {
@@ -4467,8 +4506,10 @@ static const struct ethtool_ops mtk_ethtool_ops = {
 	.get_strings		= mtk_get_strings,
 	.get_sset_count		= mtk_get_sset_count,
 	.get_ethtool_stats	= mtk_get_ethtool_stats,
+	.get_pauseparam		= mtk_get_pauseparam,
+	.set_pauseparam		= mtk_set_pauseparam,
 	.get_rxnfc		= mtk_get_rxnfc,
-	.set_rxnfc              = mtk_set_rxnfc,
+	.set_rxnfc		= mtk_set_rxnfc,
 };
 
 static const struct net_device_ops mtk_netdev_ops = {
@@ -4959,23 +5000,24 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (eth->soc->offload_version) {
-		u32 num_ppe = mtk_is_netsys_v2_or_greater(eth) ? 2 : 1;
+		u8 ppe_num = eth->soc->ppe_num;
 
-		num_ppe = min_t(u32, ARRAY_SIZE(eth->ppe), num_ppe);
-		for (i = 0; i < num_ppe; i++) {
-			u32 ppe_addr = eth->soc->reg_map->ppe_base + i * 0x400;
+		ppe_num = min_t(u8, ARRAY_SIZE(eth->ppe), ppe_num);
+		for (i = 0; i < ppe_num; i++) {
+			u32 ppe_addr = eth->soc->reg_map->ppe_base;
 
+			ppe_addr += (i == 2 ? 0xc00 : i * 0x400);
 			eth->ppe[i] = mtk_ppe_init(eth, eth->base + ppe_addr, i);
 
 			if (!eth->ppe[i]) {
 				err = -ENOMEM;
 				goto err_deinit_ppe;
 			}
-		}
+			err = mtk_eth_offload_init(eth, i);
 
-		err = mtk_eth_offload_init(eth);
-		if (err)
-			goto err_deinit_ppe;
+			if (err)
+				goto err_deinit_ppe;
+		}
 	}
 
 	for (i = 0; i < MTK_MAX_DEVS; i++) {
@@ -5083,6 +5125,7 @@ static const struct mtk_soc_data mt7621_data = {
 	.required_pctl = false,
 	.version = 1,
 	.offload_version = 1,
+	.ppe_num = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.tx = {
@@ -5111,6 +5154,7 @@ static const struct mtk_soc_data mt7622_data = {
 	.required_pctl = false,
 	.version = 1,
 	.offload_version = 2,
+	.ppe_num = 1,
 	.hash_offset = 2,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
@@ -5139,6 +5183,7 @@ static const struct mtk_soc_data mt7623_data = {
 	.required_pctl = true,
 	.version = 1,
 	.offload_version = 1,
+	.ppe_num = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.disable_pll_modes = true,
@@ -5194,6 +5239,7 @@ static const struct mtk_soc_data mt7981_data = {
 	.required_pctl = false,
 	.version = 2,
 	.offload_version = 2,
+	.ppe_num = 2,
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
@@ -5223,6 +5269,7 @@ static const struct mtk_soc_data mt7986_data = {
 	.required_pctl = false,
 	.version = 2,
 	.offload_version = 2,
+	.ppe_num = 2,
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
@@ -5252,6 +5299,7 @@ static const struct mtk_soc_data mt7988_data = {
 	.required_pctl = false,
 	.version = 3,
 	.offload_version = 2,
+	.ppe_num = 3,
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V3_SIZE,