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, 160 insertions, 32 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 2b4819b610b8..6ea1d20676fb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -229,7 +229,7 @@ static inline void backlog_lock_irq_save(struct softnet_data *sd,
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_save(*flags);
 }
 
@@ -237,7 +237,7 @@ static inline void backlog_lock_irq_disable(struct softnet_data *sd)
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_lock_irq(&sd->input_pkt_queue.lock);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_disable();
 }
 
@@ -246,7 +246,7 @@ static inline void backlog_unlock_irq_restore(struct softnet_data *sd,
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_restore(*flags);
 }
 
@@ -254,7 +254,7 @@ static inline void backlog_unlock_irq_enable(struct softnet_data *sd)
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_unlock_irq(&sd->input_pkt_queue.lock);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_enable();
 }
 
@@ -449,7 +449,9 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
  *	queue in the local softnet handler.
  */
 
-DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
+DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = {
+	.process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock),
+};
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
 /* Page_pool has a lockless array/stack to alloc/recycle pages.
@@ -2160,7 +2162,7 @@ EXPORT_SYMBOL(net_disable_timestamp);
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp = 0;
-	skb->mono_delivery_time = 0;
+	skb->tstamp_type = SKB_CLOCK_REALTIME;
 	if (static_branch_unlikely(&netstamp_needed_key))
 		skb->tstamp = ktime_get_real();
 }
@@ -3940,6 +3942,7 @@ netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
 	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
 }
 
+#ifndef CONFIG_PREEMPT_RT
 static bool netdev_xmit_txqueue_skipped(void)
 {
 	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
@@ -3950,6 +3953,19 @@ void netdev_xmit_skip_txqueue(bool skip)
 	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
 }
 EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+
+#else
+static bool netdev_xmit_txqueue_skipped(void)
+{
+	return current->net_xmit.skip_txqueue;
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	current->net_xmit.skip_txqueue = skip;
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+#endif
 #endif /* CONFIG_NET_EGRESS */
 
 #ifdef CONFIG_NET_XGRESS
@@ -4029,10 +4045,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 {
 	struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS;
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int sch_ret;
 
 	if (!entry)
 		return skb;
+
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
 		*pt_prev = NULL;
@@ -4061,10 +4080,12 @@ ingress_verdict:
 			break;
 		}
 		*ret = NET_RX_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	case TC_ACT_SHOT:
 		kfree_skb_reason(skb, drop_reason);
 		*ret = NET_RX_DROP;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	/* used by tc_run */
 	case TC_ACT_STOLEN:
@@ -4074,8 +4095,10 @@ ingress_verdict:
 		fallthrough;
 	case TC_ACT_CONSUMED:
 		*ret = NET_RX_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	}
+	bpf_net_ctx_clear(bpf_net_ctx);
 
 	return skb;
 }
@@ -4085,11 +4108,14 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
 	struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS;
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int sch_ret;
 
 	if (!entry)
 		return skb;
 
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
 	/* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was
 	 * already set by the caller.
 	 */
@@ -4105,10 +4131,12 @@ egress_verdict:
 		/* No need to push/pop skb's mac_header here on egress! */
 		skb_do_redirect(skb);
 		*ret = NET_XMIT_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	case TC_ACT_SHOT:
 		kfree_skb_reason(skb, drop_reason);
 		*ret = NET_XMIT_DROP;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	/* used by tc_run */
 	case TC_ACT_STOLEN:
@@ -4118,8 +4146,10 @@ egress_verdict:
 		fallthrough;
 	case TC_ACT_CONSUMED:
 		*ret = NET_XMIT_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	}
+	bpf_net_ctx_clear(bpf_net_ctx);
 
 	return skb;
 }
@@ -5096,11 +5126,14 @@ static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
 
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
+
 	if (xdp_prog) {
 		struct xdp_buff xdp;
 		u32 act;
 		int err;
 
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 		act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog);
 		if (act != XDP_PASS) {
 			switch (act) {
@@ -5114,11 +5147,13 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb)
 				generic_xdp_tx(*pskb, xdp_prog);
 				break;
 			}
+			bpf_net_ctx_clear(bpf_net_ctx);
 			return XDP_DROP;
 		}
 	}
 	return XDP_PASS;
 out_redir:
+	bpf_net_ctx_clear(bpf_net_ctx);
 	kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP);
 	return XDP_DROP;
 }
@@ -5234,7 +5269,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 				trace_consume_skb(skb, net_tx_action);
 			else
 				trace_kfree_skb(skb, net_tx_action,
-						get_kfree_skb_cb(skb)->reason);
+						get_kfree_skb_cb(skb)->reason, NULL);
 
 			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
 				__kfree_skb(skb);
@@ -5935,6 +5970,7 @@ static void flush_backlog(struct work_struct *work)
 	}
 	backlog_unlock_irq_enable(sd);
 
+	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
@@ -5942,6 +5978,7 @@ static void flush_backlog(struct work_struct *work)
 			rps_input_queue_head_incr(sd);
 		}
 	}
+	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
 }
 
@@ -6063,7 +6100,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 	while (again) {
 		struct sk_buff *skb;
 
+		local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 			rcu_read_lock();
 			__netif_receive_skb(skb);
 			rcu_read_unlock();
@@ -6072,7 +6111,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 				return work;
 			}
 
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
+		local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 
 		backlog_lock_irq_disable(sd);
 		if (skb_queue_empty(&sd->input_pkt_queue)) {
@@ -6087,8 +6128,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			napi->state &= NAPIF_STATE_THREADED;
 			again = false;
 		} else {
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 			skb_queue_splice_tail_init(&sd->input_pkt_queue,
 						   &sd->process_queue);
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
 		backlog_unlock_irq_enable(sd);
 	}
@@ -6301,6 +6344,7 @@ enum {
 static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 			   unsigned flags, u16 budget)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	bool skip_schedule = false;
 	unsigned long timeout;
 	int rc;
@@ -6318,6 +6362,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
 
 	local_bh_disable();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
@@ -6340,6 +6385,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	netpoll_poll_unlock(have_poll_lock);
 	if (rc == budget)
 		__busy_poll_stop(napi, skip_schedule);
+	bpf_net_ctx_clear(bpf_net_ctx);
 	local_bh_enable();
 }
 
@@ -6349,6 +6395,7 @@ static void __napi_busy_loop(unsigned int napi_id,
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
@@ -6367,6 +6414,7 @@ restart:
 		int work = 0;
 
 		local_bh_disable();
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 		if (!napi_poll) {
 			unsigned long val = READ_ONCE(napi->state);
 
@@ -6397,6 +6445,7 @@ count:
 			__NET_ADD_STATS(dev_net(napi->dev),
 					LINUX_MIB_BUSYPOLLRXPACKETS, work);
 		skb_defer_free_flush(this_cpu_ptr(&softnet_data));
+		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
 		if (!loop_end || loop_end(loop_end_arg, start_time))
@@ -6824,6 +6873,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 
 static void napi_threaded_poll_loop(struct napi_struct *napi)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
 	unsigned long last_qs = jiffies;
 
@@ -6832,6 +6882,8 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 		void *have;
 
 		local_bh_disable();
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
 		sd = this_cpu_ptr(&softnet_data);
 		sd->in_napi_threaded_poll = true;
 
@@ -6847,6 +6899,7 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 			net_rps_action_and_irq_enable(sd);
 		}
 		skb_defer_free_flush(sd);
+		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
 		if (!repoll)
@@ -6872,10 +6925,12 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies +
 		usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs));
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int budget = READ_ONCE(net_hotdata.netdev_budget);
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 start:
 	sd->in_net_rx_action = true;
 	local_irq_disable();
@@ -6928,7 +6983,8 @@ start:
 		sd->in_net_rx_action = false;
 
 	net_rps_action_and_irq_enable(sd);
-end:;
+end:
+	bpf_net_ctx_clear(bpf_net_ctx);
 }
 
 struct netdev_adjacent {
@@ -10285,6 +10341,10 @@ int register_netdevice(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	/* rss ctx ID 0 is reserved for the default context, start from 1 */
+	xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1);
+	mutex_init(&dev->ethtool->rss_lock);
+
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 
@@ -10703,6 +10763,54 @@ void netdev_run_todo(void)
 		wake_up(&netdev_unregistering_wq);
 }
 
+/* Collate per-cpu network dstats statistics
+ *
+ * Read per-cpu network statistics from dev->dstats and populate the related
+ * fields in @s.
+ */
+static void dev_fetch_dstats(struct rtnl_link_stats64 *s,
+			     const struct pcpu_dstats __percpu *dstats)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		u64 rx_packets, rx_bytes, rx_drops;
+		u64 tx_packets, tx_bytes, tx_drops;
+		const struct pcpu_dstats *stats;
+		unsigned int start;
+
+		stats = per_cpu_ptr(dstats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			rx_packets = u64_stats_read(&stats->rx_packets);
+			rx_bytes   = u64_stats_read(&stats->rx_bytes);
+			rx_drops   = u64_stats_read(&stats->rx_drops);
+			tx_packets = u64_stats_read(&stats->tx_packets);
+			tx_bytes   = u64_stats_read(&stats->tx_bytes);
+			tx_drops   = u64_stats_read(&stats->tx_drops);
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		s->rx_packets += rx_packets;
+		s->rx_bytes   += rx_bytes;
+		s->rx_dropped += rx_drops;
+		s->tx_packets += tx_packets;
+		s->tx_bytes   += tx_bytes;
+		s->tx_dropped += tx_drops;
+	}
+}
+
+/* ndo_get_stats64 implementation for dtstats-based accounting.
+ *
+ * Populate @s from dev->stats and dev->dstats. This is used internally by the
+ * core for NETDEV_PCPU_STAT_DSTAT-type stats collection.
+ */
+static void dev_get_dstats64(const struct net_device *dev,
+			     struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_dstats(s, dev->dstats);
+}
+
 /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has
  * all the same fields in the same order as net_device_stats, with only
  * the type differing, but rtnl_link_stats64 may have additional fields
@@ -10779,6 +10887,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 		netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
 	} else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) {
 		dev_get_tstats64(dev, storage);
+	} else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) {
+		dev_get_dstats64(dev, storage);
 	} else {
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
@@ -10896,13 +11006,6 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on);
 
-void netdev_freemem(struct net_device *dev)
-{
-	char *addr = (char *)dev - dev->padded;
-
-	kvfree(addr);
-}
-
 /**
  * alloc_netdev_mqs - allocate network device
  * @sizeof_priv: size of private data to allocate space for
@@ -10922,8 +11025,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *dev;
-	unsigned int alloc_size;
-	struct net_device *p;
 
 	BUG_ON(strlen(name) >= sizeof(dev->name));
 
@@ -10937,21 +11038,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-	alloc_size = sizeof(struct net_device);
-	if (sizeof_priv) {
-		/* ensure 32-byte alignment of private area */
-		alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);
-		alloc_size += sizeof_priv;
-	}
-	/* ensure 32-byte alignment of whole construct */
-	alloc_size += NETDEV_ALIGN - 1;
-
-	p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
-	if (!p)
+	dev = kvzalloc(struct_size(dev, priv, sizeof_priv),
+		       GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
+	if (!dev)
 		return NULL;
 
-	dev = PTR_ALIGN(p, NETDEV_ALIGN);
-	dev->padded = (char *)dev - (char *)p;
+	dev->priv_len = sizeof_priv;
 
 	ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
 #ifdef CONFIG_PCPU_DEV_REFCNT
@@ -11015,6 +11107,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
 		goto free_all;
+	dev->ethtool = kzalloc(sizeof(*dev->ethtool), GFP_KERNEL_ACCOUNT);
+	if (!dev->ethtool)
+		goto free_all;
 
 	strcpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
@@ -11035,7 +11130,7 @@ free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
 free_dev:
 #endif
-	netdev_freemem(dev);
+	kvfree(dev);
 	return NULL;
 }
 EXPORT_SYMBOL(alloc_netdev_mqs);
@@ -11065,6 +11160,7 @@ void free_netdev(struct net_device *dev)
 		return;
 	}
 
+	kfree(dev->ethtool);
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
@@ -11089,7 +11185,7 @@ void free_netdev(struct net_device *dev)
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED ||
 	    dev->reg_state == NETREG_DUMMY) {
-		netdev_freemem(dev);
+		kvfree(dev);
 		return;
 	}
 
@@ -11130,6 +11226,34 @@ void synchronize_net(void)
 }
 EXPORT_SYMBOL(synchronize_net);
 
+static void netdev_rss_contexts_free(struct net_device *dev)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+
+	mutex_lock(&dev->ethtool->rss_lock);
+	xa_for_each(&dev->ethtool->rss_ctx, context, ctx) {
+		struct ethtool_rxfh_param rxfh;
+
+		rxfh.indir = ethtool_rxfh_context_indir(ctx);
+		rxfh.key = ethtool_rxfh_context_key(ctx);
+		rxfh.hfunc = ctx->hfunc;
+		rxfh.input_xfrm = ctx->input_xfrm;
+		rxfh.rss_context = context;
+		rxfh.rss_delete = true;
+
+		xa_erase(&dev->ethtool->rss_ctx, context);
+		if (dev->ethtool_ops->create_rxfh_context)
+			dev->ethtool_ops->remove_rxfh_context(dev, ctx,
+							      context, NULL);
+		else
+			dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
+		kfree(ctx);
+	}
+	xa_destroy(&dev->ethtool->rss_ctx);
+	mutex_unlock(&dev->ethtool->rss_lock);
+}
+
 /**
  *	unregister_netdevice_queue - remove device from the kernel
  *	@dev: device
@@ -11233,11 +11357,15 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		netdev_name_node_alt_flush(dev);
 		netdev_name_node_free(dev->name_node);
 
+		netdev_rss_contexts_free(dev);
+
 		call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
 
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
+		mutex_destroy(&dev->ethtool->rss_lock);
+
 		if (skb)
 			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh);