Merge tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Introduce a config option to tweak MAX_SKB_FRAGS. Increasing the
     default value allows for better BIG TCP performances

   - Reduce compound page head access for zero-copy data transfers

   - RPS/RFS improvements, avoiding unneeded NET_RX_SOFTIRQ when
     possible

   - Threaded NAPI improvements, adding defer skb free support and
     unneeded softirq avoidance

   - Address dst_entry reference count scalability issues, via false
     sharing avoidance and optimize refcount tracking

   - Add lockless accesses annotation to sk_err[_soft]

   - Optimize again the skb struct layout

   - Extends the skb drop reasons to make it usable by multiple
     subsystems

   - Better const qualifier awareness for socket casts

  BPF:

   - Add skb and XDP typed dynptrs which allow BPF programs for more
     ergonomic and less brittle iteration through data and
     variable-sized accesses

   - Add a new BPF netfilter program type and minimal support to hook
     BPF programs to netfilter hooks such as prerouting or forward

   - Add more precise memory usage reporting for all BPF map types

   - Adds support for using {FOU,GUE} encap with an ipip device
     operating in collect_md mode and add a set of BPF kfuncs for
     controlling encap params

   - Allow BPF programs to detect at load time whether a particular
     kfunc exists or not, and also add support for this in light
     skeleton

   - Bigger batch of BPF verifier improvements to prepare for upcoming
     BPF open-coded iterators allowing for less restrictive looping
     capabilities

   - Rework RCU enforcement in the verifier, add kptr_rcu and enforce
     BPF programs to NULL-check before passing such pointers into kfunc

   - Add support for kptrs in percpu hashmaps, percpu LRU hashmaps and
     in local storage maps

   - Enable RCU semantics for task BPF kptrs and allow referenced kptr
     tasks to be stored in BPF maps

   - Add support for refcounted local kptrs to the verifier for allowing
     shared ownership, useful for adding a node to both the BPF list and
     rbtree

   - Add BPF verifier support for ST instructions in
     convert_ctx_access() which will help new -mcpu=v4 clang flag to
     start emitting them

   - Add ARM32 USDT support to libbpf

   - Improve bpftool's visual program dump which produces the control
     flow graph in a DOT format by adding C source inline annotations

  Protocols:

   - IPv4: Allow adding to IPv4 address a 'protocol' tag. Such value
     indicates the provenance of the IP address

   - IPv6: optimize route lookup, dropping unneeded R/W lock acquisition

   - Add the handshake upcall mechanism, allowing the user-space to
     implement generic TLS handshake on kernel's behalf

   - Bridge: support per-{Port, VLAN} neighbor suppression, increasing
     resilience to nodes failures

   - SCTP: add support for Fair Capacity and Weighted Fair Queueing
     schedulers

   - MPTCP: delay first subflow allocation up to its first usage. This
     will allow for later better LSM interaction

   - xfrm: Remove inner/outer modes from input/output path. These are
     not needed anymore

   - WiFi:
      - reduced neighbor report (RNR) handling for AP mode
      - HW timestamping support
      - support for randomized auth/deauth TA for PASN privacy
      - per-link debugfs for multi-link
      - TC offload support for mac80211 drivers
      - mac80211 mesh fast-xmit and fast-rx support
      - enable Wi-Fi 7 (EHT) mesh support

  Netfilter:

   - Add nf_tables 'brouting' support, to force a packet to be routed
     instead of being bridged

   - Update bridge netfilter and ovs conntrack helpers to handle IPv6
     Jumbo packets properly, i.e. fetch the packet length from
     hop-by-hop extension header. This is needed for BIT TCP support

   - The iptables 32bit compat interface isn't compiled in by default
     anymore

   - Move ip(6)tables builtin icmp matches to the udptcp one. This has
     the advantage that icmp/icmpv6 match doesn't load the
     iptables/ip6tables modules anymore when iptables-nft is used

   - Extended netlink error report for netdevice in flowtables and
     netdev/chains. Allow for incrementally add/delete devices to netdev
     basechain. Allow to create netdev chain without device

  Driver API:

   - Remove redundant Device Control Error Reporting Enable, as PCI core
     has already error reporting enabled at enumeration time

   - Move Multicast DB netlink handlers to core, allowing devices other
     then bridge to use them

   - Allow the page_pool to directly recycle the pages from safely
     localized NAPI

   - Implement lockless TX queue stop/wake combo macros, allowing for
     further code de-duplication and sanitization

   - Add YNL support for user headers and struct attrs

   - Add partial YNL specification for devlink

   - Add partial YNL specification for ethtool

   - Add tc-mqprio and tc-taprio support for preemptible traffic classes

   - Add tx push buf len param to ethtool, specifies the maximum number
     of bytes of a transmitted packet a driver can push directly to the
     underlying device

   - Add basic LED support for switch/phy

   - Add NAPI documentation, stop relaying on external links

   - Convert dsa_master_ioctl() to netdev notifier. This is a
     preparatory work to make the hardware timestamping layer selectable
     by user space

   - Add transceiver support and improve the error messages for CAN-FD
     controllers

  New hardware / drivers:

   - Ethernet:
      - AMD/Pensando core device support
      - MediaTek MT7981 SoC
      - MediaTek MT7988 SoC
      - Broadcom BCM53134 embedded switch
      - Texas Instruments CPSW9G ethernet switch
      - Qualcomm EMAC3 DWMAC ethernet
      - StarFive JH7110 SoC
      - NXP CBTX ethernet PHY

   - WiFi:
      - Apple M1 Pro/Max devices
      - RealTek rtl8710bu/rtl8188gu
      - RealTek rtl8822bs, rtl8822cs and rtl8821cs SDIO chipset

   - Bluetooth:
      - Realtek RTL8821CS, RTL8851B, RTL8852BS
      - Mediatek MT7663, MT7922
      - NXP w8997
      - Actions Semi ATS2851
      - QTI WCN6855
      - Marvell 88W8997

   - Can:
      - STMicroelectronics bxcan stm32f429

  Drivers:

   - Ethernet NICs:
      - Intel (1G, icg):
         - add tracking and reporting of QBV config errors
         - add support for configuring max SDU for each Tx queue
      - Intel (100G, ice):
         - refactor mailbox overflow detection to support Scalable IOV
         - GNSS interface optimization
      - Intel (i40e):
         - support XDP multi-buffer
      - nVidia/Mellanox:
         - add the support for linux bridge multicast offload
         - enable TC offload for egress and engress MACVLAN over bond
         - add support for VxLAN GBP encap/decap flows offload
         - extend packet offload to fully support libreswan
         - support tunnel mode in mlx5 IPsec packet offload
         - extend XDP multi-buffer support
         - support MACsec VLAN offload
         - add support for dynamic msix vectors allocation
         - drop RX page_cache and fully use page_pool
         - implement thermal zone to report NIC temperature
      - Netronome/Corigine:
         - add support for multi-zone conntrack offload
      - Solarflare/Xilinx:
         - support offloading TC VLAN push/pop actions to the MAE
         - support TC decap rules
         - support unicast PTP

   - Other NICs:
      - Broadcom (bnxt): enforce software based freq adjustments only on
        shared PHC NIC
      - RealTek (r8169): refactor to addess ASPM issues during NAPI poll
      - Micrel (lan8841): add support for PTP_PF_PEROUT
      - Cadence (macb): enable PTP unicast
      - Engleder (tsnep): add XDP socket zero-copy support
      - virtio-net: implement exact header length guest feature
      - veth: add page_pool support for page recycling
      - vxlan: add MDB data path support
      - gve: add XDP support for GQI-QPL format
      - geneve: accept every ethertype
      - macvlan: allow some packets to bypass broadcast queue
      - mana: add support for jumbo frame

   - Ethernet high-speed switches:
      - Microchip (sparx5): Add support for TC flower templates

   - Ethernet embedded switches:
      - Broadcom (b54):
         - configure 6318 and 63268 RGMII ports
      - Marvell (mv88e6xxx):
         - faster C45 bus scan
      - Microchip:
         - lan966x:
            - add support for IS1 VCAP
            - better TX/RX from/to CPU performances
         - ksz9477: add ETS Qdisc support
         - ksz8: enhance static MAC table operations and error handling
         - sama7g5: add PTP capability
      - NXP (ocelot):
         - add support for external ports
         - add support for preemptible traffic classes
      - Texas Instruments:
         - add CPSWxG SGMII support for J7200 and J721E

   - Intel WiFi (iwlwifi):
      - preparation for Wi-Fi 7 EHT and multi-link support
      - EHT (Wi-Fi 7) sniffer support
      - hardware timestamping support for some devices/firwmares
      - TX beacon protection on newer hardware

   - Qualcomm 802.11ax WiFi (ath11k):
      - MU-MIMO parameters support
      - ack signal support for management packets

   - RealTek WiFi (rtw88):
      - SDIO bus support
      - better support for some SDIO devices (e.g. MAC address from
        efuse)

   - RealTek WiFi (rtw89):
      - HW scan support for 8852b
      - better support for 6 GHz scanning
      - support for various newer firmware APIs
      - framework firmware backwards compatibility

   - MediaTek WiFi (mt76):
      - P2P support
      - mesh A-MSDU support
      - EHT (Wi-Fi 7) support
      - coredump support"

* tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2078 commits)
  net: phy: hide the PHYLIB_LEDS knob
  net: phy: marvell-88x2222: remove unnecessary (void*) conversions
  tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp.
  net: amd: Fix link leak when verifying config failed
  net: phy: marvell: Fix inconsistent indenting in led_blink_set
  lan966x: Don't use xdp_frame when action is XDP_TX
  tsnep: Add XDP socket zero-copy TX support
  tsnep: Add XDP socket zero-copy RX support
  tsnep: Move skb receive action to separate function
  tsnep: Add functions for queue enable/disable
  tsnep: Rework TX/RX queue initialization
  tsnep: Replace modulo operation with mask
  net: phy: dp83867: Add led_brightness_set support
  net: phy: Fix reading LED reg property
  drivers: nfc: nfcsim: remove return value check of `dev_dir`
  net: phy: dp83867: Remove unnecessary (void*) conversions
  net: ethtool: coalesce: try to make user settings stick twice
  net: mana: Check if netdev/napi_alloc_frag returns single page
  net: mana: Rename mana_refill_rxoob and remove some empty lines
  net: veth: add page_pool stats
  ...

1 files changed, 91 insertions, 53 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1488f700bf819..735096d42c1d1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -160,8 +160,6 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
 
 static int netif_rx_internal(struct sk_buff *skb);
-static int call_netdevice_notifiers_info(unsigned long val,
-					 struct netdev_notifier_info *info);
 static int call_netdevice_notifiers_extack(unsigned long val,
 					   struct net_device *dev,
 					   struct netlink_ext_ack *extack);
@@ -1919,8 +1917,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev,
  *	are as for raw_notifier_call_chain().
  */
 
-static int call_netdevice_notifiers_info(unsigned long val,
-					 struct netdev_notifier_info *info)
+int call_netdevice_notifiers_info(unsigned long val,
+				  struct netdev_notifier_info *info)
 {
 	struct net *net = dev_net(info->dev);
 	int ret;
@@ -2535,6 +2533,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	struct xps_map *map, *new_map;
 	unsigned int nr_ids;
 
+	WARN_ON_ONCE(index >= dev->num_tx_queues);
+
 	if (dev->num_tc) {
 		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
@@ -3075,7 +3075,7 @@ void __netif_schedule(struct Qdisc *q)
 EXPORT_SYMBOL(__netif_schedule);
 
 struct dev_kfree_skb_cb {
-	enum skb_free_reason reason;
+	enum skb_drop_reason reason;
 };
 
 static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
@@ -3108,7 +3108,7 @@ void netif_tx_wake_queue(struct netdev_queue *dev_queue)
 }
 EXPORT_SYMBOL(netif_tx_wake_queue);
 
-void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
+void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	unsigned long flags;
 
@@ -3128,18 +3128,16 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL(__dev_kfree_skb_irq);
+EXPORT_SYMBOL(dev_kfree_skb_irq_reason);
 
-void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
+void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	if (in_hardirq() || irqs_disabled())
-		__dev_kfree_skb_irq(skb, reason);
-	else if (unlikely(reason == SKB_REASON_DROPPED))
-		kfree_skb(skb);
+		dev_kfree_skb_irq_reason(skb, reason);
 	else
-		consume_skb(skb);
+		kfree_skb_reason(skb, reason);
 }
-EXPORT_SYMBOL(__dev_kfree_skb_any);
+EXPORT_SYMBOL(dev_kfree_skb_any_reason);
 
 
 /**
@@ -3317,8 +3315,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
 						  skb->len - start, ~(__u32)0,
 						  crc32c_csum_stub));
 	*(__le32 *)(skb->data + offset) = crc32c_csum;
-	skb->ip_summed = CHECKSUM_NONE;
-	skb->csum_not_inet = 0;
+	skb_reset_csum_not_inet(skb);
 out:
 	return ret;
 }
@@ -3736,25 +3733,25 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 	 * we add to pkt_len the headers size of all segments
 	 */
 	if (shinfo->gso_size && skb_transport_header_was_set(skb)) {
-		unsigned int hdr_len;
 		u16 gso_segs = shinfo->gso_segs;
+		unsigned int hdr_len;
 
 		/* mac layer + network layer */
-		hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+		hdr_len = skb_transport_offset(skb);
 
 		/* + transport layer */
 		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
 			const struct tcphdr *th;
 			struct tcphdr _tcphdr;
 
-			th = skb_header_pointer(skb, skb_transport_offset(skb),
+			th = skb_header_pointer(skb, hdr_len,
 						sizeof(_tcphdr), &_tcphdr);
 			if (likely(th))
 				hdr_len += __tcp_hdrlen(th);
 		} else {
 			struct udphdr _udphdr;
 
-			if (skb_header_pointer(skb, skb_transport_offset(skb),
+			if (skb_header_pointer(skb, hdr_len,
 					       sizeof(_udphdr), &_udphdr))
 				hdr_len += sizeof(struct udphdr);
 		}
@@ -4361,7 +4358,12 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	}
 
 	list_add_tail(&napi->poll_list, &sd->poll_list);
-	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	WRITE_ONCE(napi->list_owner, smp_processor_id());
+	/* If not called from net_rx_action()
+	 * we have to raise NET_RX_SOFTIRQ.
+	 */
+	if (!sd->in_net_rx_action)
+		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS
@@ -4583,11 +4585,16 @@ static void trigger_rx_softirq(void *data)
 }
 
 /*
- * Check if this softnet_data structure is another cpu one
- * If yes, queue it to our IPI list and return 1
- * If no, return 0
+ * After we queued a packet into sd->input_pkt_queue,
+ * we need to make sure this queue is serviced soon.
+ *
+ * - If this is another cpu queue, link it to our rps_ipi_list,
+ *   and make sure we will process rps_ipi_list from net_rx_action().
+ *
+ * - If this is our own queue, NAPI schedule our backlog.
+ *   Note that this also raises NET_RX_SOFTIRQ.
  */
-static int napi_schedule_rps(struct softnet_data *sd)
+static void napi_schedule_rps(struct softnet_data *sd)
 {
 	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
@@ -4596,12 +4603,15 @@ static int napi_schedule_rps(struct softnet_data *sd)
 		sd->rps_ipi_next = mysd->rps_ipi_list;
 		mysd->rps_ipi_list = sd;
 
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-		return 1;
+		/* If not called from net_rx_action() or napi_threaded_poll()
+		 * we have to raise NET_RX_SOFTIRQ.
+		 */
+		if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll)
+			__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		return;
 	}
 #endif /* CONFIG_RPS */
 	__napi_schedule_irqoff(&mysd->backlog);
-	return 0;
 }
 
 #ifdef CONFIG_NET_FLOW_LIMIT
@@ -5021,16 +5031,17 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 			clist = clist->next;
 
 			WARN_ON(refcount_read(&skb->users));
-			if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
+			if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED))
 				trace_consume_skb(skb, net_tx_action);
 			else
 				trace_kfree_skb(skb, net_tx_action,
-						SKB_DROP_REASON_NOT_SPECIFIED);
+						get_kfree_skb_cb(skb)->reason);
 
 			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
 				__kfree_skb(skb);
 			else
-				__kfree_skb_defer(skb);
+				__napi_kfree_skb(skb,
+						 get_kfree_skb_cb(skb)->reason);
 		}
 	}
 
@@ -6059,6 +6070,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		list_del_init(&n->poll_list);
 		local_irq_restore(flags);
 	}
+	WRITE_ONCE(n->list_owner, -1);
 
 	val = READ_ONCE(n->state);
 	do {
@@ -6374,6 +6386,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
+	napi->list_owner = -1;
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	set_bit(NAPI_STATE_NPSVC, &napi->state);
 	list_add_rcu(&napi->dev_list, &dev->napi_list);
@@ -6585,9 +6598,31 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
+static void skb_defer_free_flush(struct softnet_data *sd)
+{
+	struct sk_buff *skb, *next;
+
+	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
+	if (!READ_ONCE(sd->defer_list))
+		return;
+
+	spin_lock(&sd->defer_lock);
+	skb = sd->defer_list;
+	sd->defer_list = NULL;
+	sd->defer_count = 0;
+	spin_unlock(&sd->defer_lock);
+
+	while (skb != NULL) {
+		next = skb->next;
+		napi_consume_skb(skb, 1);
+		skb = next;
+	}
+}
+
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	struct softnet_data *sd;
 	void *have;
 
 	while (!napi_thread_wait(napi)) {
@@ -6595,11 +6630,21 @@ static int napi_threaded_poll(void *data)
 			bool repoll = false;
 
 			local_bh_disable();
+			sd = this_cpu_ptr(&softnet_data);
+			sd->in_napi_threaded_poll = true;
 
 			have = netpoll_poll_lock(napi);
 			__napi_poll(napi, &repoll);
 			netpoll_poll_unlock(have);
 
+			sd->in_napi_threaded_poll = false;
+			barrier();
+
+			if (sd_has_rps_ipi_waiting(sd)) {
+				local_irq_disable();
+				net_rps_action_and_irq_enable(sd);
+			}
+			skb_defer_free_flush(sd);
 			local_bh_enable();
 
 			if (!repoll)
@@ -6611,27 +6656,6 @@ static int napi_threaded_poll(void *data)
 	return 0;
 }
 
-static void skb_defer_free_flush(struct softnet_data *sd)
-{
-	struct sk_buff *skb, *next;
-
-	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
-	if (!READ_ONCE(sd->defer_list))
-		return;
-
-	spin_lock_irq(&sd->defer_lock);
-	skb = sd->defer_list;
-	sd->defer_list = NULL;
-	sd->defer_count = 0;
-	spin_unlock_irq(&sd->defer_lock);
-
-	while (skb != NULL) {
-		next = skb->next;
-		napi_consume_skb(skb, 1);
-		skb = next;
-	}
-}
-
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -6641,6 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
+start:
+	sd->in_net_rx_action = true;
 	local_irq_disable();
 	list_splice_init(&sd->poll_list, &list);
 	local_irq_enable();
@@ -6651,8 +6677,18 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 		skb_defer_free_flush(sd);
 
 		if (list_empty(&list)) {
-			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
-				goto end;
+			if (list_empty(&repoll)) {
+				sd->in_net_rx_action = false;
+				barrier();
+				/* We need to check if ____napi_schedule()
+				 * had refilled poll_list while
+				 * sd->in_net_rx_action was true.
+				 */
+				if (!list_empty(&sd->poll_list))
+					goto start;
+				if (!sd_has_rps_ipi_waiting(sd))
+					goto end;
+			}
 			break;
 		}
 
@@ -6677,6 +6713,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	list_splice(&list, &sd->poll_list);
 	if (!list_empty(&sd->poll_list))
 		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	else
+		sd->in_net_rx_action = false;
 
 	net_rps_action_and_irq_enable(sd);
 end:;