Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

net/core/bpf_sk_storage.c

@@ -524,8 +524,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 			nr_maps++;
 	}
 
-	diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps,
-		       GFP_KERNEL);
+	diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL);
 	if (!diag)
 		return ERR_PTR(-ENOMEM);
 

net/core/dev.c

@@ -148,6 +148,7 @@
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
 #include <linux/prandom.h>
+#include <linux/once_lite.h>
 
 #include "net-sysfs.h"
 
@@ -3487,13 +3488,16 @@ EXPORT_SYMBOL(__skb_gso_segment);
 
 /* Take action when hardware reception checksum errors are detected. */
 #ifdef CONFIG_BUG
+static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
+{
+	pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
+	skb_dump(KERN_ERR, skb, true);
+	dump_stack();
+}
+
 void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
 {
-	if (net_ratelimit()) {
-		pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
-		skb_dump(KERN_ERR, skb, true);
-		dump_stack();
-	}
+	DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb);
 }
 EXPORT_SYMBOL(netdev_rx_csum_fault);
 #endif
@@ -3852,10 +3856,33 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-		if (likely(!netif_xmit_frozen_or_stopped(txq)))
-			qdisc_run(q);
+		if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
+		    qdisc_run_begin(q)) {
+			/* Retest nolock_qdisc_is_empty() within the protection
+			 * of q->seqlock to protect from racing with requeuing.
+			 */
+			if (unlikely(!nolock_qdisc_is_empty(q))) {
+				rc = q->enqueue(skb, q, &to_free) &
+					NET_XMIT_MASK;
+				__qdisc_run(q);
+				qdisc_run_end(q);
 
+				goto no_lock_out;
+			}
+
+			qdisc_bstats_cpu_update(q, skb);
+			if (sch_direct_xmit(skb, q, dev, txq, NULL, true) &&
+			    !nolock_qdisc_is_empty(q))
+				__qdisc_run(q);
+
+			qdisc_run_end(q);
+			return NET_XMIT_SUCCESS;
+		}
+
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
+
+no_lock_out:
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
 		return rc;
@@ -5277,9 +5304,9 @@ another_round:
 	if (static_branch_unlikely(&generic_xdp_needed_key)) {
 		int ret2;
 
-		preempt_disable();
+		migrate_disable();
 		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
-		preempt_enable();
+		migrate_enable();
 
 		if (ret2 != XDP_PASS) {
 			ret = NET_RX_DROP;
@@ -6520,11 +6547,18 @@ EXPORT_SYMBOL(napi_schedule_prep);
  * __napi_schedule_irqoff - schedule for receive
  * @n: entry to schedule
  *
- * Variant of __napi_schedule() assuming hard irqs are masked
+ * Variant of __napi_schedule() assuming hard irqs are masked.
+ *
+ * On PREEMPT_RT enabled kernels this maps to __napi_schedule()
+ * because the interrupt disabled assumption might not be true
+ * due to force-threaded interrupts and spinlock substitution.
  */
 void __napi_schedule_irqoff(struct napi_struct *n)
 {
-	____napi_schedule(this_cpu_ptr(&softnet_data), n);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		____napi_schedule(this_cpu_ptr(&softnet_data), n);
+	else
+		__napi_schedule(n);
 }
 EXPORT_SYMBOL(__napi_schedule_irqoff);
 

net/core/devlink.c

@@ -190,6 +190,80 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
 	return devlink_port_get_from_attrs(devlink, info->attrs);
 }
 
+static inline bool
+devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
+}
+
+static inline bool
+devlink_rate_is_node(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
+}
+
+static struct devlink_rate *
+devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink_port *devlink_port;
+
+	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
+	if (IS_ERR(devlink_port))
+		return ERR_CAST(devlink_port);
+	devlink_rate = devlink_port->devlink_rate;
+	return devlink_rate ?: ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
+{
+	static struct devlink_rate *devlink_rate;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate) &&
+		    !strcmp(node_name, devlink_rate->name))
+			return devlink_rate;
+	}
+	return ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+	const char *rate_node_name;
+	size_t len;
+
+	if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return ERR_PTR(-EINVAL);
+	rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
+	len = strlen(rate_node_name);
+	/* Name cannot be empty or decimal number */
+	if (!len || strspn(rate_node_name, "0123456789") == len)
+		return ERR_PTR(-EINVAL);
+
+	return devlink_rate_node_get_by_name(devlink, rate_node_name);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
+}
+
+static struct devlink_rate *
+devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX])
+		return devlink_rate_leaf_get_from_info(devlink, info);
+	else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return devlink_rate_node_get_from_info(devlink, info);
+	else
+		return ERR_PTR(-EINVAL);
+}
+
 struct devlink_sb {
 	struct list_head list;
 	unsigned int index;
@@ -408,12 +482,14 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 
 #define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
+#define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
 
 /* The per devlink instance lock is taken by default in the pre-doit
  * operation, yet several commands do not require this. The global
  * devlink lock is taken and protects from disruption by user-calls.
  */
-#define DEVLINK_NL_FLAG_NO_LOCK			BIT(2)
+#define DEVLINK_NL_FLAG_NO_LOCK			BIT(4)
 
 static int devlink_nl_pre_doit(const struct genl_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info)
@@ -442,6 +518,24 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (!IS_ERR(devlink_port))
 			info->user_ptr[1] = devlink_port;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
+		struct devlink_rate *devlink_rate;
+
+		devlink_rate = devlink_rate_get_from_info(devlink, info);
+		if (IS_ERR(devlink_rate)) {
+			err = PTR_ERR(devlink_rate);
+			goto unlock;
+		}
+		info->user_ptr[1] = devlink_rate;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
+		struct devlink_rate *rate_node;
+
+		rate_node = devlink_rate_node_get_from_info(devlink, info);
+		if (IS_ERR(rate_node)) {
+			err = PTR_ERR(rate_node);
+			goto unlock;
+		}
+		info->user_ptr[1] = rate_node;
 	}
 	return 0;
 
@@ -748,6 +842,56 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *
 	return 0;
 }
 
+static int devlink_nl_rate_fill(struct sk_buff *msg,
+				struct devlink *devlink,
+				struct devlink_rate *devlink_rate,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags,
+				struct netlink_ext_ack *extack)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
+		goto nla_put_failure;
+
+	if (devlink_rate_is_leaf(devlink_rate)) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				devlink_rate->devlink_port->index))
+			goto nla_put_failure;
+	} else if (devlink_rate_is_node(devlink_rate)) {
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
+				   devlink_rate->name))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
+			      devlink_rate->tx_share, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
+			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (devlink_rate->parent)
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+				   devlink_rate->parent->name))
+			goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
 static bool
 devlink_port_fn_state_valid(enum devlink_port_fn_state state)
 {
@@ -919,6 +1063,111 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_rate_notify(struct devlink_rate *devlink_rate,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW &&
+		cmd != DEVLINK_CMD_RATE_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   cmd, 0, 0, 0, NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg,
+					  struct netlink_callback *cb)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err = 0;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		mutex_lock(&devlink->lock);
+		list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+			enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
+			u32 id = NETLINK_CB(cb->skb).portid;
+
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_rate_fill(msg, devlink,
+						   devlink_rate,
+						   cmd, id,
+						   cb->nlh->nlmsg_seq,
+						   NLM_F_MULTI, NULL);
+			if (err) {
+				mutex_unlock(&devlink->lock);
+				goto out;
+			}
+			idx++;
+		}
+		mutex_unlock(&devlink->lock);
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+	if (err != -EMSGSIZE)
+		return err;
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   DEVLINK_CMD_RATE_NEW,
+				   info->snd_portid, info->snd_seq, 0,
+				   info->extack);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static bool
+devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
+			    struct devlink_rate *parent)
+{
+	while (parent) {
+		if (parent == devlink_rate)
+			return true;
+		parent = parent->parent;
+	}
+	return false;
+}
+
 static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
@@ -1339,6 +1588,255 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
 	return devlink->ops->port_del(devlink, port_index, extack);
 }
 
+static int
+devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
+				struct genl_info *info,
+				struct nlattr *nla_parent)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	const char *parent_name = nla_data(nla_parent);
+	const struct devlink_ops *ops = devlink->ops;
+	size_t len = strlen(parent_name);
+	struct devlink_rate *parent;
+	int err = -EOPNOTSUPP;
+
+	parent = devlink_rate->parent;
+	if (parent && len) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent.");
+		return -EBUSY;
+	} else if (parent && !len) {
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		if (err)
+			return err;
+
+		refcount_dec(&parent->refcnt);
+		devlink_rate->parent = NULL;
+	} else if (!parent && len) {
+		parent = devlink_rate_node_get_by_name(devlink, parent_name);
+		if (IS_ERR(parent))
+			return -ENODEV;
+
+		if (parent == devlink_rate) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed");
+			return -EINVAL;
+		}
+
+		if (devlink_rate_is_node(devlink_rate) &&
+		    devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node.");
+			return -EEXIST;
+		}
+
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		if (err)
+			return err;
+
+		refcount_inc(&parent->refcnt);
+		devlink_rate->parent = parent;
+	}
+
+	return 0;
+}
+
+static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
+			       const struct devlink_ops *ops,
+			       struct genl_info *info)
+{
+	struct nlattr *nla_parent, **attrs = info->attrs;
+	int err = -EOPNOTSUPP;
+	u64 rate;
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_share = rate;
+	}
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_max = rate;
+	}
+
+	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
+	if (nla_parent) {
+		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
+						      nla_parent);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
+					   struct genl_info *info,
+					   enum devlink_rate_type type)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (type == DEVLINK_RATE_TYPE_LEAF) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_leaf_parent_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs");
+			return false;
+		}
+	} else if (type == DEVLINK_RATE_TYPE_NODE) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_node_parent_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes");
+			return false;
+		}
+	} else {
+		WARN(1, "Unknown type of rate object");
+		return false;
+	}
+
+	return true;
+}
+
+static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = devlink_rate->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	int err;
+
+	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
+		return -EOPNOTSUPP;
+
+	err = devlink_nl_rate_set(devlink_rate, ops, info);
+
+	if (!err)
+		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	return err;
+}
+
+static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *rate_node;
+	const struct devlink_ops *ops;
+	int err;
+
+	ops = devlink->ops;
+	if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
+		return -EOPNOTSUPP;
+
+	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
+	if (!IS_ERR(rate_node))
+		return -EEXIST;
+	else if (rate_node == ERR_PTR(-EINVAL))
+		return -EINVAL;
+
+	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+	if (!rate_node)
+		return -ENOMEM;
+
+	rate_node->devlink = devlink;
+	rate_node->type = DEVLINK_RATE_TYPE_NODE;
+	rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
+	if (!rate_node->name) {
+		err = -ENOMEM;
+		goto err_strdup;
+	}
+
+	err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
+	if (err)
+		goto err_node_new;
+
+	err = devlink_nl_rate_set(rate_node, ops, info);
+	if (err)
+		goto err_rate_set;
+
+	refcount_set(&rate_node->refcnt, 1);
+	list_add(&rate_node->list, &devlink->rate_list);
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	return 0;
+
+err_rate_set:
+	ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+err_node_new:
+	kfree(rate_node->name);
+err_strdup:
+	kfree(rate_node);
+	return err;
+}
+
+static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *rate_node = info->user_ptr[1];
+	struct devlink *devlink = rate_node->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	int err;
+
+	if (refcount_read(&rate_node->refcnt) > 1) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node.");
+		return -EBUSY;
+	}
+
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+	err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+	if (rate_node->parent)
+		refcount_dec(&rate_node->parent->refcnt);
+	list_del(&rate_node->list);
+	kfree(rate_node->name);
+	kfree(rate_node);
+	return err;
+}
+
 static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
 			      struct devlink_sb *devlink_sb,
 			      enum devlink_command cmd, u32 portid,
@@ -2207,6 +2705,23 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
+static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
+				    struct netlink_ext_ack *extack)
+{
+	struct devlink_rate *devlink_rate;
+
+	/* Take the lock to sync with devlink_rate_nodes_destroy() */
+	mutex_lock(&devlink->lock);
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
+		if (devlink_rate_is_node(devlink_rate)) {
+			mutex_unlock(&devlink->lock);
+			NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists.");
+			return -EBUSY;
+		}
+	mutex_unlock(&devlink->lock);
+	return 0;
+}
+
 static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 					   struct genl_info *info)
 {
@@ -2221,6 +2736,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 		if (!ops->eswitch_mode_set)
 			return -EOPNOTSUPP;
 		mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+		err = devlink_rate_nodes_check(devlink, mode, info->extack);
+		if (err)
+			return err;
 		err = ops->eswitch_mode_set(devlink, mode, info->extack);
 		if (err)
 			return err;
@@ -6994,8 +7512,9 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats,
 	}
 }
 
-static int devlink_trap_stats_put(struct sk_buff *msg,
-				  struct devlink_stats __percpu *trap_stats)
+static int
+devlink_trap_group_stats_put(struct sk_buff *msg,
+			     struct devlink_stats __percpu *trap_stats)
 {
 	struct devlink_stats stats;
 	struct nlattr *attr;
@@ -7023,6 +7542,50 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink,
+				  const struct devlink_trap_item *trap_item)
+{
+	struct devlink_stats stats;
+	struct nlattr *attr;
+	u64 drops = 0;
+	int err;
+
+	if (devlink->ops->trap_drop_counter_get) {
+		err = devlink->ops->trap_drop_counter_get(devlink,
+							  trap_item->trap,
+							  &drops);
+		if (err)
+			return err;
+	}
+
+	devlink_trap_stats_read(trap_item->stats, &stats);
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if (devlink->ops->trap_drop_counter_get &&
+	    nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
+			      stats.rx_packets, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
+			      stats.rx_bytes, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
 static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
 				const struct devlink_trap_item *trap_item,
 				enum devlink_command cmd, u32 portid, u32 seq,
@@ -7060,7 +7623,7 @@ static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
-	err = devlink_trap_stats_put(msg, trap_item->stats);
+	err = devlink_trap_stats_put(msg, devlink, trap_item);
 	if (err)
 		goto nla_put_failure;
 
@@ -7277,7 +7840,7 @@ devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink,
 			group_item->policer_item->policer->id))
 		goto nla_put_failure;
 
-	err = devlink_trap_stats_put(msg, group_item->stats);
+	err = devlink_trap_group_stats_put(msg, group_item->stats);
 	if (err)
 		goto nla_put_failure;
 
@@ -7801,6 +8364,11 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING },
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7826,6 +8394,30 @@ static const struct genl_small_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
+	{
+		.cmd = DEVLINK_CMD_RATE_GET,
+		.doit = devlink_nl_cmd_rate_get_doit,
+		.dumpit = devlink_nl_cmd_rate_get_dumpit,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_SET,
+		.doit = devlink_nl_cmd_rate_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_NEW,
+		.doit = devlink_nl_cmd_rate_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_DEL,
+		.doit = devlink_nl_cmd_rate_del_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE,
+	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -8201,6 +8793,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
 	__devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
+	INIT_LIST_HEAD(&devlink->rate_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
 	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	INIT_LIST_HEAD(&devlink->resource_list);
@@ -8303,6 +8896,7 @@ void devlink_free(struct devlink *devlink)
 	WARN_ON(!list_empty(&devlink->resource_list));
 	WARN_ON(!list_empty(&devlink->dpipe_table_list));
 	WARN_ON(!list_empty(&devlink->sb_list));
+	WARN_ON(!list_empty(&devlink->rate_list));
 	WARN_ON(!list_empty(&devlink->port_list));
 
 	xa_destroy(&devlink->snapshot_ids);
@@ -8619,6 +9213,110 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
 
+/**
+ * devlink_rate_leaf_create - create devlink rate leaf
+ *
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ *
+ * Create devlink rate object of type leaf on provided @devlink_port.
+ * Throws call trace if @devlink_port already has a devlink rate object.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: -ENOMEM if failed to allocate rate object, 0 otherwise.
+ */
+int
+devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_rate *devlink_rate;
+
+	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+	if (!devlink_rate)
+		return -ENOMEM;
+
+	mutex_lock(&devlink->lock);
+	WARN_ON(devlink_port->devlink_rate);
+	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+	devlink_rate->devlink = devlink;
+	devlink_rate->devlink_port = devlink_port;
+	devlink_rate->priv = priv;
+	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	devlink_port->devlink_rate = devlink_rate;
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	mutex_unlock(&devlink->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_create);
+
+/**
+ * devlink_rate_leaf_destroy - destroy devlink rate leaf
+ *
+ * @devlink_port: devlink port linked to the rate object
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
+{
+	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+	struct devlink *devlink = devlink_port->devlink;
+
+	if (!devlink_rate)
+		return;
+
+	mutex_lock(&devlink->lock);
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+	if (devlink_rate->parent)
+		refcount_dec(&devlink_rate->parent->refcnt);
+	list_del(&devlink_rate->list);
+	devlink_port->devlink_rate = NULL;
+	mutex_unlock(&devlink->lock);
+	kfree(devlink_rate);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy);
+
+/**
+ * devlink_rate_nodes_destroy - destroy all devlink rate nodes on device
+ *
+ * @devlink: devlink instance
+ *
+ * Unset parent for all rate objects and destroy all rate nodes
+ * on specified device.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_nodes_destroy(struct devlink *devlink)
+{
+	static struct devlink_rate *devlink_rate, *tmp;
+	const struct devlink_ops *ops = devlink->ops;
+
+	mutex_lock(&devlink->lock);
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (!devlink_rate->parent)
+			continue;
+
+		refcount_dec(&devlink_rate->parent->refcnt);
+		if (devlink_rate_is_leaf(devlink_rate))
+			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+		else if (devlink_rate_is_node(devlink_rate))
+			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+	}
+	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate)) {
+			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
+			list_del(&devlink_rate->list);
+			kfree(devlink_rate->name);
+			kfree(devlink_rate);
+		}
+	}
+	mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy);
+
 static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 					     char *name, size_t len)
 {
@@ -8630,12 +9328,18 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 
 	switch (attrs->flavour) {
 	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+		n = snprintf(name, len, "p%u", attrs->phys.port_number);
+		if (n < len && attrs->split)
+			n += snprintf(name + n, len - n, "s%u",
+				      attrs->phys.split_subport_number);
 		if (!attrs->split)
 			n = snprintf(name, len, "p%u", attrs->phys.port_number);
 		else
 			n = snprintf(name, len, "p%us%u",
 				     attrs->phys.port_number,
 				     attrs->phys.split_subport_number);
+
 		break;
 	case DEVLINK_PORT_FLAVOUR_CPU:
 	case DEVLINK_PORT_FLAVOUR_DSA:
@@ -8677,8 +9381,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 		n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
 			     attrs->pci_sf.sf);
 		break;
-	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
-		return -EOPNOTSUPP;
 	}
 
 	if (n >= len)

net/core/filter.c

@@ -3241,9 +3241,6 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
-		return -ENOTSUPP;
-
 	ret = skb_cow(skb, len_diff);
 	if (unlikely(ret < 0))
 		return ret;
@@ -3255,19 +3252,11 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		/* SKB_GSO_TCPV4 needs to be changed into
-		 * SKB_GSO_TCPV6.
-		 */
+		/* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */
 		if (shinfo->gso_type & SKB_GSO_TCPV4) {
 			shinfo->gso_type &= ~SKB_GSO_TCPV4;
 			shinfo->gso_type |=  SKB_GSO_TCPV6;
 		}
-
-		/* Due to IPv6 header, MSS needs to be downgraded. */
-		skb_decrease_gso_size(shinfo, len_diff);
-		/* Header must be checked, and gso_segs recomputed. */
-		shinfo->gso_type |= SKB_GSO_DODGY;
-		shinfo->gso_segs = 0;
 	}
 
 	skb->protocol = htons(ETH_P_IPV6);
@@ -3282,9 +3271,6 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
-		return -ENOTSUPP;
-
 	ret = skb_unclone(skb, GFP_ATOMIC);
 	if (unlikely(ret < 0))
 		return ret;
@@ -3296,19 +3282,11 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		/* SKB_GSO_TCPV6 needs to be changed into
-		 * SKB_GSO_TCPV4.
-		 */
+		/* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */
 		if (shinfo->gso_type & SKB_GSO_TCPV6) {
 			shinfo->gso_type &= ~SKB_GSO_TCPV6;
 			shinfo->gso_type |=  SKB_GSO_TCPV4;
 		}
-
-		/* Due to IPv4 header, MSS can be upgraded. */
-		skb_increase_gso_size(shinfo, len_diff);
-		/* Header must be checked, and gso_segs recomputed. */
-		shinfo->gso_type |= SKB_GSO_DODGY;
-		shinfo->gso_segs = 0;
 	}
 
 	skb->protocol = htons(ETH_P_IP);
@@ -3919,6 +3897,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+/* XDP_REDIRECT works by a three-step process, implemented in the functions
+ * below:
+ *
+ * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target
+ *    of the redirect and store it (along with some other metadata) in a per-CPU
+ *    struct bpf_redirect_info.
+ *
+ * 2. When the program returns the XDP_REDIRECT return code, the driver will
+ *    call xdp_do_redirect() which will use the information in struct
+ *    bpf_redirect_info to actually enqueue the frame into a map type-specific
+ *    bulk queue structure.
+ *
+ * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(),
+ *    which will flush all the different bulk queues, thus completing the
+ *    redirect.
+ *
+ * Pointers to the map entries will be kept around for this whole sequence of
+ * steps, protected by RCU. However, there is no top-level rcu_read_lock() in
+ * the core code; instead, the RCU protection relies on everything happening
+ * inside a single NAPI poll sequence, which means it's between a pair of calls
+ * to local_bh_disable()/local_bh_enable().
+ *
+ * The map entries are marked as __rcu and the map code makes sure to
+ * dereference those pointers with rcu_dereference_check() in a way that works
+ * for both sections that to hold an rcu_read_lock() and sections that are
+ * called from NAPI without a separate rcu_read_lock(). The code below does not
+ * use RCU annotations, but relies on those in the map code.
+ */
 void xdp_do_flush(void)
 {
 	__dev_flush();
@@ -3927,6 +3933,23 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
+void bpf_clear_redirect_map(struct bpf_map *map)
+{
+	struct bpf_redirect_info *ri;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
+		/* Avoid polluting remote cacheline due to writes if
+		 * not needed. Once we pass this test, we need the
+		 * cmpxchg() to make sure it hasn't been changed in
+		 * the meantime by remote CPU.
+		 */
+		if (unlikely(READ_ONCE(ri->map) == map))
+			cmpxchg(&ri->map, map, NULL);
+	}
+}
+
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
@@ -3934,6 +3957,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	enum bpf_map_type map_type = ri->map_type;
 	void *fwd = ri->tgt_value;
 	u32 map_id = ri->map_id;
+	struct bpf_map *map;
 	int err;
 
 	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
@@ -3943,7 +3967,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_enqueue(fwd, xdp, dev);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_enqueue_multi(xdp, dev, map,
+						    ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_enqueue(fwd, xdp, dev);
+		}
 		break;
 	case BPF_MAP_TYPE_CPUMAP:
 		err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3985,13 +4016,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       enum bpf_map_type map_type, u32 map_id)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map;
 	int err;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+						     ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		}
 		if (unlikely(err))
 			goto err;
 		break;
@@ -10008,11 +10047,13 @@ out:
 static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 				    struct sock_reuseport *reuse,
 				    struct sock *sk, struct sk_buff *skb,
+				    struct sock *migrating_sk,
 				    u32 hash)
 {
 	reuse_kern->skb = skb;
 	reuse_kern->sk = sk;
 	reuse_kern->selected_sk = NULL;
+	reuse_kern->migrating_sk = migrating_sk;
 	reuse_kern->data_end = skb->data + skb_headlen(skb);
 	reuse_kern->hash = hash;
 	reuse_kern->reuseport_id = reuse->reuseport_id;
@@ -10021,12 +10062,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
+				  struct sock *migrating_sk,
 				  u32 hash)
 {
 	struct sk_reuseport_kern reuse_kern;
 	enum sk_action action;
 
-	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash);
 	action = BPF_PROG_RUN(prog, &reuse_kern);
 
 	if (action == SK_PASS)
@@ -10136,6 +10178,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 		return &sk_reuseport_load_bytes_proto;
 	case BPF_FUNC_skb_load_bytes_relative:
 		return &sk_reuseport_load_bytes_relative_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_ptr_cookie_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -10165,6 +10209,14 @@ sk_reuseport_is_valid_access(int off, int size,
 	case offsetof(struct sk_reuseport_md, hash):
 		return size == size_default;
 
+	case offsetof(struct sk_reuseport_md, sk):
+		info->reg_type = PTR_TO_SOCKET;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL;
+		return size == sizeof(__u64);
+
 	/* Fields that allow narrowing */
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
@@ -10237,6 +10289,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct sk_reuseport_md, bind_inany):
 		SK_REUSEPORT_LOAD_FIELD(bind_inany);
 		break;
+
+	case offsetof(struct sk_reuseport_md, sk):
+		SK_REUSEPORT_LOAD_FIELD(sk);
+		break;
+
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		SK_REUSEPORT_LOAD_FIELD(migrating_sk);
+		break;
 	}
 
 	return insn - insn_buf;

net/core/flow_dissector.c

@@ -943,8 +943,8 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			/* Tail taggers don't break flow dissection */
-			if (!ops->tail_tag) {
+			/* Only DSA header taggers break flow dissection */
+			if (ops->needed_headroom) {
 				if (ops->flow_dissect)
 					ops->flow_dissect(skb, &proto, &offset);
 				else

net/core/neighbour.c

@@ -3142,7 +3142,7 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq)
 	struct net *net = seq_file_net(seq);
 	struct neigh_table *tbl = state->tbl;
 	struct pneigh_entry *pn = NULL;
-	int bucket = state->bucket;
+	int bucket;
 
 	state->flags |= NEIGH_SEQ_IS_PNEIGH;
 	for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) {

net/core/net-traces.c

@@ -60,3 +60,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
 EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum);

net/core/netpoll.c

@@ -36,6 +36,7 @@
 #include <net/ip6_checksum.h>
 #include <asm/unaligned.h>
 #include <trace/events/napi.h>
+#include <linux/kconfig.h>
 
 /*
  * We maintain a small pool of fully-sized skbs, to make sure the
@@ -389,7 +390,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 	static atomic_t ip_ident;
 	struct ipv6hdr *ip6h;
 
-	WARN_ON_ONCE(!irqs_disabled());
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		WARN_ON_ONCE(!irqs_disabled());
 
 	udp_len = len + sizeof(*udph);
 	if (np->ipv6)

net/core/page_pool.c

@@ -17,6 +17,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/page-flags.h>
 #include <linux/mm.h> /* for __put_page() */
+#include <linux/poison.h>
 
 #include <trace/events/page_pool.h>
 
@@ -221,6 +222,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 		return NULL;
 	}
 
+	page->pp_magic |= PP_SIGNATURE;
+
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
@@ -263,6 +266,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 			put_page(page);
 			continue;
 		}
+		page->pp_magic |= PP_SIGNATURE;
 		pool->alloc.cache[pool->alloc.count++] = page;
 		/* Track how many pages are held 'in-flight' */
 		pool->pages_state_hold_cnt++;
@@ -341,6 +345,8 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page_pool_set_dma_addr(page, 0);
 skip_dma_unmap:
+	page->pp_magic = 0;
+
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.
 	 */
@@ -622,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
+
+bool page_pool_return_skb_page(struct page *page)
+{
+	struct page_pool *pp;
+
+	page = compound_head(page);
+	if (unlikely(page->pp_magic != PP_SIGNATURE))
+		return false;
+
+	pp = page->pp;
+
+	/* Driver set this to memory recycling info. Reset it on recycle.
+	 * This will *not* work for NIC using a split-page memory model.
+	 * The page will be returned to the pool here regardless of the
+	 * 'flipped' fragment being in use or not.
+	 */
+	page->pp = NULL;
+	page_pool_put_full_page(pp, page, false);
+
+	return true;
+}
+EXPORT_SYMBOL(page_pool_return_skb_page);

net/core/pktgen.c

@@ -467,7 +467,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
 static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
 static void pktgen_run_all_threads(struct pktgen_net *pn);
 static void pktgen_reset_all_threads(struct pktgen_net *pn);
-static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn);
+static void pktgen_stop_all_threads(struct pktgen_net *pn);
 
 static void pktgen_stop(struct pktgen_thread *t);
 static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
@@ -516,14 +516,11 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
 	data[count - 1] = 0;	/* Strip trailing '\n' and terminate string */
 
 	if (!strcmp(data, "stop"))
-		pktgen_stop_all_threads_ifs(pn);
-
+		pktgen_stop_all_threads(pn);
 	else if (!strcmp(data, "start"))
 		pktgen_run_all_threads(pn);
-
 	else if (!strcmp(data, "reset"))
 		pktgen_reset_all_threads(pn);
-
 	else
 		return -EINVAL;
 
@@ -3027,20 +3024,25 @@ static void pktgen_run(struct pktgen_thread *t)
 		t->control &= ~(T_STOP);
 }
 
-static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn)
+static void pktgen_handle_all_threads(struct pktgen_net *pn, u32 flags)
 {
 	struct pktgen_thread *t;
 
-	func_enter();
-
 	mutex_lock(&pktgen_thread_lock);
 
 	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= T_STOP;
+		t->control |= (flags);
 
 	mutex_unlock(&pktgen_thread_lock);
 }
 
+static void pktgen_stop_all_threads(struct pktgen_net *pn)
+{
+	func_enter();
+
+	pktgen_handle_all_threads(pn, T_STOP);
+}
+
 static int thread_is_running(const struct pktgen_thread *t)
 {
 	const struct pktgen_dev *pkt_dev;
@@ -3103,16 +3105,9 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 
 static void pktgen_run_all_threads(struct pktgen_net *pn)
 {
-	struct pktgen_thread *t;
-
 	func_enter();
 
-	mutex_lock(&pktgen_thread_lock);
-
-	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= (T_RUN);
-
-	mutex_unlock(&pktgen_thread_lock);
+	pktgen_handle_all_threads(pn, T_RUN);
 
 	/* Propagate thread->control  */
 	schedule_timeout_interruptible(msecs_to_jiffies(125));
@@ -3122,16 +3117,9 @@ static void pktgen_run_all_threads(struct pktgen_net *pn)
 
 static void pktgen_reset_all_threads(struct pktgen_net *pn)
 {
-	struct pktgen_thread *t;
-
 	func_enter();
 
-	mutex_lock(&pktgen_thread_lock);
-
-	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= (T_REMDEVALL);
-
-	mutex_unlock(&pktgen_thread_lock);
+	pktgen_handle_all_threads(pn, T_REMDEVALL);
 
 	/* Propagate thread->control  */
 	schedule_timeout_interruptible(msecs_to_jiffies(125));

net/core/rtnetlink.c

@@ -9,7 +9,7 @@
  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
  *
  *	Fixes:
- *	Vitaly E. Lavrov		RTA_OK arithmetics was wrong.
+ *	Vitaly E. Lavrov		RTA_OK arithmetic was wrong.
  */
 
 #include <linux/bitops.h>
@@ -234,7 +234,7 @@ unlock:
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
- * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
+ * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions
  *
  * Like rtnl_register, but for use by removable modules.
  */
@@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(rtnl_register_module);
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
- * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
+ * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions
  *
  * Registers the specified function pointers (at least one of them has
  * to be non-NULL) to be called whenever a request message for the
@@ -376,12 +376,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops)
 	if (rtnl_link_ops_get(ops->kind))
 		return -EEXIST;
 
-	/* The check for setup is here because if ops
+	/* The check for alloc/setup is here because if ops
 	 * does not have that filled up, it is not possible
 	 * to use the ops for creating device. So do not
 	 * fill up dellink as well. That disables rtnl_dellink.
 	 */
-	if (ops->setup && !ops->dellink)
+	if ((ops->alloc || ops->setup) && !ops->dellink)
 		ops->dellink = unregister_netdevice_queue;
 
 	list_add_tail(&ops->list, &link_ops);
@@ -543,7 +543,9 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
 {
 	const struct rtnl_af_ops *ops;
 
-	list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
+	ASSERT_RTNL();
+
+	list_for_each_entry(ops, &rtnl_af_ops, list) {
 		if (ops->family == family)
 			return ops;
 	}
@@ -1819,6 +1821,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	if (rtnl_fill_prop_list(skb, dev))
 		goto nla_put_failure;
 
+	if (dev->dev.parent &&
+	    nla_put_string(skb, IFLA_PARENT_DEV_NAME,
+			   dev_name(dev->dev.parent)))
+		goto nla_put_failure;
+
+	if (dev->dev.parent && dev->dev.parent->bus &&
+	    nla_put_string(skb, IFLA_PARENT_DEV_BUS_NAME,
+			   dev->dev.parent->bus->name))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1878,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PERM_ADDRESS]	= { .type = NLA_REJECT },
 	[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
 	[IFLA_NEW_IFINDEX]	= NLA_POLICY_MIN(NLA_S32, 1),
+	[IFLA_PARENT_DEV_NAME]	= { .type = NLA_NUL_STRING },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2274,27 +2287,18 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 		nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
 			const struct rtnl_af_ops *af_ops;
 
-			rcu_read_lock();
 			af_ops = rtnl_af_lookup(nla_type(af));
-			if (!af_ops) {
-				rcu_read_unlock();
+			if (!af_ops)
 				return -EAFNOSUPPORT;
-			}
 
-			if (!af_ops->set_link_af) {
-				rcu_read_unlock();
+			if (!af_ops->set_link_af)
 				return -EOPNOTSUPP;
-			}
 
 			if (af_ops->validate_link_af) {
 				err = af_ops->validate_link_af(dev, af);
-				if (err < 0) {
-					rcu_read_unlock();
+				if (err < 0)
 					return err;
-				}
 			}
-
-			rcu_read_unlock();
 		}
 	}
 
@@ -2574,7 +2578,7 @@ static int do_set_proto_down(struct net_device *dev,
 	if (nl_proto_down) {
 		proto_down = nla_get_u8(nl_proto_down);
 
-		/* Dont turn off protodown if there are active reasons */
+		/* Don't turn off protodown if there are active reasons */
 		if (!proto_down && dev->proto_down_reason) {
 			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
 			return -EBUSY;
@@ -2868,17 +2872,12 @@ static int do_setlink(const struct sk_buff *skb,
 		nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
 			const struct rtnl_af_ops *af_ops;
 
-			rcu_read_lock();
-
 			BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
 
 			err = af_ops->set_link_af(dev, af, extack);
-			if (err < 0) {
-				rcu_read_unlock();
+			if (err < 0)
 				goto errout;
-			}
 
-			rcu_read_unlock();
 			status |= DO_SETLINK_NOTIFY;
 		}
 	}
@@ -3177,8 +3176,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		return ERR_PTR(-EINVAL);
 	}
 
-	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
-			       ops->setup, num_tx_queues, num_rx_queues);
+	if (ops->alloc) {
+		dev = ops->alloc(tb, ifname, name_assign_type,
+				 num_tx_queues, num_rx_queues);
+		if (IS_ERR(dev))
+			return dev;
+	} else {
+		dev = alloc_netdev_mqs(ops->priv_size, ifname,
+				       name_assign_type, ops->setup,
+				       num_tx_queues, num_rx_queues);
+	}
+
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -3411,7 +3419,7 @@ replay:
 		return -EOPNOTSUPP;
 	}
 
-	if (!ops->setup)
+	if (!ops->alloc && !ops->setup)
 		return -EOPNOTSUPP;
 
 	if (!ifname[0]) {
@@ -3939,12 +3947,12 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 	 * implement its own handler for this.
 	 */
 	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
-		pr_info("%s: FDB only supports static addresses\n", dev->name);
+		netdev_info(dev, "default FDB implementation only supports local addresses\n");
 		return err;
 	}
 
 	if (vid) {
-		pr_info("%s: vlans aren't supported yet for dev_uc|mc_add()\n", dev->name);
+		netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n");
 		return err;
 	}
 
@@ -4078,7 +4086,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 	 * implement its own handler for this.
 	 */
 	if (!(ndm->ndm_state & NUD_PERMANENT)) {
-		pr_info("%s: FDB only supports static addresses\n", dev->name);
+		netdev_info(dev, "default FDB implementation only supports local addresses\n");
 		return err;
 	}
 

net/core/skbuff.c

@@ -70,6 +70,7 @@
 #include <net/xfrm.h>
 #include <net/mpls.h>
 #include <net/mptcp.h>
+#include <net/page_pool.h>
 
 #include <linux/uaccess.h>
 #include <trace/events/skb.h>
@@ -645,10 +646,13 @@ static void skb_free_head(struct sk_buff *skb)
 {
 	unsigned char *head = skb->head;
 
-	if (skb->head_frag)
+	if (skb->head_frag) {
+		if (skb_pp_recycle(skb, head))
+			return;
 		skb_free_frag(head);
-	else
+	} else {
 		kfree(head);
+	}
 }
 
 static void skb_release_data(struct sk_buff *skb)
@@ -664,7 +668,7 @@ static void skb_release_data(struct sk_buff *skb)
 	skb_zcopy_clear(skb, true);
 
 	for (i = 0; i < shinfo->nr_frags; i++)
-		__skb_frag_unref(&shinfo->frags[i]);
+		__skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
 
 	if (shinfo->frag_list)
 		kfree_skb_list(shinfo->frag_list);
@@ -1046,6 +1050,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->nohdr = 0;
 	n->peeked = 0;
 	C(pfmemalloc);
+	C(pp_recycle);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
@@ -1289,7 +1294,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg)
 	}
 	spin_unlock_irqrestore(&q->lock, flags);
 
-	sk->sk_error_report(sk);
+	sk_error_report(sk);
 
 release:
 	consume_skb(skb);
@@ -3497,7 +3502,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 		fragto = &skb_shinfo(tgt)->frags[merge];
 
 		skb_frag_size_add(fragto, skb_frag_size(fragfrom));
-		__skb_frag_unref(fragfrom);
+		__skb_frag_unref(fragfrom, skb->pp_recycle);
 	}
 
 	/* Reposition in the original skb */
@@ -4680,7 +4685,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_error_report(sk);
+		sk_error_report(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
@@ -4711,7 +4716,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 		sk->sk_err = 0;
 
 	if (skb_next)
-		sk->sk_error_report(sk);
+		sk_error_report(sk);
 
 	return skb;
 }
@@ -5287,6 +5292,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (skb_cloned(to))
 		return false;
 
+	/* The page pool signature of struct page will eventually figure out
+	 * which pages can be recycled or not but for now let's prohibit slab
+	 * allocated and page_pool allocated SKBs from being coalesced.
+	 */
+	if (to->pp_recycle != from->pp_recycle)
+		return false;
+
 	if (len <= skb_tailroom(to)) {
 		if (len)
 			BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));

net/core/skmsg.c

@@ -399,29 +399,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
-		     long timeo, int *err)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	int ret = 0;
-
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
-		return 1;
-
-	if (!timeo)
-		return ret;
-
-	add_wait_queue(sk_sleep(sk), &wait);
-	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	ret = sk_wait_event(sk, &timeo,
-			    !list_empty(&psock->ingress_msg) ||
-			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
-	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	remove_wait_queue(sk_sleep(sk), &wait);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(sk_msg_wait_data);
-
 /* Receive sk_msg from psock->ingress_msg to @msg. */
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags)
@@ -601,6 +578,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 	return sk_psock_skb_ingress(psock, skb);
 }
 
+static void sock_drop(struct sock *sk, struct sk_buff *skb)
+{
+	sk_drops_add(sk, skb);
+	kfree_skb(skb);
+}
+
 static void sk_psock_backlog(struct work_struct *work)
 {
 	struct sk_psock *psock = container_of(work, struct sk_psock, work);
@@ -640,7 +623,7 @@ start:
 				/* Hard errors break pipe and stop xmit. */
 				sk_psock_report_error(psock, ret ? -ret : EPIPE);
 				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
-				kfree_skb(skb);
+				sock_drop(psock->sk, skb);
 				goto end;
 			}
 			off += ret;
@@ -731,7 +714,7 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
 
 	while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
 		skb_bpf_redirect_clear(skb);
-		kfree_skb(skb);
+		sock_drop(psock->sk, skb);
 	}
 	__sk_psock_purge_ingress_msg(psock);
 }
@@ -847,7 +830,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
 
-static void sk_psock_skb_redirect(struct sk_buff *skb)
+static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
@@ -857,8 +840,8 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 	 * return code, but then didn't set a redirect interface.
 	 */
 	if (unlikely(!sk_other)) {
-		kfree_skb(skb);
-		return;
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 	psock_other = sk_psock(sk_other);
 	/* This error indicates the socket is being torn down or had another
@@ -866,26 +849,30 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 	 * a socket that is in this state so we drop the skb.
 	 */
 	if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
-		kfree_skb(skb);
-		return;
+		skb_bpf_redirect_clear(skb);
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 	spin_lock_bh(&psock_other->ingress_lock);
 	if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
 		spin_unlock_bh(&psock_other->ingress_lock);
-		kfree_skb(skb);
-		return;
+		skb_bpf_redirect_clear(skb);
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 
 	skb_queue_tail(&psock_other->ingress_skb, skb);
 	schedule_work(&psock_other->work);
 	spin_unlock_bh(&psock_other->ingress_lock);
+	return 0;
 }
 
-static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb,
+				       struct sk_psock *from, int verdict)
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(skb);
+		sk_psock_skb_redirect(from, skb);
 		break;
 	case __SK_PASS:
 	case __SK_DROP:
@@ -909,20 +896,21 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
-	sk_psock_tls_verdict_apply(skb, psock->sk, ret);
+	sk_psock_tls_verdict_apply(skb, psock, ret);
 	rcu_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
 
-static void sk_psock_verdict_apply(struct sk_psock *psock,
-				   struct sk_buff *skb, int verdict)
+static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
+				  int verdict)
 {
 	struct sock *sk_other;
-	int err = -EIO;
+	int err = 0;
 
 	switch (verdict) {
 	case __SK_PASS:
+		err = -EIO;
 		sk_other = psock->sk;
 		if (sock_flag(sk_other, SOCK_DEAD) ||
 		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
@@ -945,18 +933,25 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 			if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 				skb_queue_tail(&psock->ingress_skb, skb);
 				schedule_work(&psock->work);
+				err = 0;
 			}
 			spin_unlock_bh(&psock->ingress_lock);
+			if (err < 0) {
+				skb_bpf_redirect_clear(skb);
+				goto out_free;
+			}
 		}
 		break;
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(skb);
+		err = sk_psock_skb_redirect(psock, skb);
 		break;
 	case __SK_DROP:
 	default:
 out_free:
-		kfree_skb(skb);
+		sock_drop(psock->sk, skb);
 	}
+
+	return err;
 }
 
 static void sk_psock_write_space(struct sock *sk)
@@ -988,7 +983,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 	sk = strp->sk;
 	psock = sk_psock(sk);
 	if (unlikely(!psock)) {
-		kfree_skb(skb);
+		sock_drop(sk, skb);
 		goto out;
 	}
 	prog = READ_ONCE(psock->progs.stream_verdict);
@@ -1109,7 +1104,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 	psock = sk_psock(sk);
 	if (unlikely(!psock)) {
 		len = 0;
-		kfree_skb(skb);
+		sock_drop(sk, skb);
 		goto out;
 	}
 	prog = READ_ONCE(psock->progs.stream_verdict);
@@ -1123,7 +1118,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
-	sk_psock_verdict_apply(psock, skb, ret);
+	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
+		len = 0;
 out:
 	rcu_read_unlock();
 	return len;

net/core/sock.c

@@ -331,6 +331,22 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(__sk_backlog_rcv);
 
+void sk_error_report(struct sock *sk)
+{
+	sk->sk_error_report(sk);
+
+	switch (sk->sk_family) {
+	case AF_INET:
+		fallthrough;
+	case AF_INET6:
+		trace_inet_sk_error_report(sk);
+		break;
+	default:
+		break;
+	}
+}
+EXPORT_SYMBOL(sk_error_report);
+
 static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
 {
 	struct __kernel_sock_timeval tv;
@@ -776,6 +792,58 @@ void sock_enable_timestamps(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_enable_timestamps);
 
+void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
+{
+	switch (optname) {
+	case SO_TIMESTAMP_OLD:
+		__sock_set_timestamps(sk, valbool, false, false);
+		break;
+	case SO_TIMESTAMP_NEW:
+		__sock_set_timestamps(sk, valbool, true, false);
+		break;
+	case SO_TIMESTAMPNS_OLD:
+		__sock_set_timestamps(sk, valbool, false, true);
+		break;
+	case SO_TIMESTAMPNS_NEW:
+		__sock_set_timestamps(sk, valbool, true, true);
+		break;
+	}
+}
+
+int sock_set_timestamping(struct sock *sk, int optname, int val)
+{
+	if (val & ~SOF_TIMESTAMPING_MASK)
+		return -EINVAL;
+
+	if (val & SOF_TIMESTAMPING_OPT_ID &&
+	    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
+		if (sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM) {
+			if ((1 << sk->sk_state) &
+			    (TCPF_CLOSE | TCPF_LISTEN))
+				return -EINVAL;
+			sk->sk_tskey = tcp_sk(sk)->snd_una;
+		} else {
+			sk->sk_tskey = 0;
+		}
+	}
+
+	if (val & SOF_TIMESTAMPING_OPT_STATS &&
+	    !(val & SOF_TIMESTAMPING_OPT_TSONLY))
+		return -EINVAL;
+
+	sk->sk_tsflags = val;
+	sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+
+	if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
+		sock_enable_timestamp(sk,
+				      SOCK_TIMESTAMPING_RX_SOFTWARE);
+	else
+		sock_disable_timestamp(sk,
+				       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
+	return 0;
+}
+
 void sock_set_keepalive(struct sock *sk)
 {
 	lock_sock(sk);
@@ -997,54 +1065,15 @@ set_sndbuf:
 		break;
 
 	case SO_TIMESTAMP_OLD:
-		__sock_set_timestamps(sk, valbool, false, false);
-		break;
 	case SO_TIMESTAMP_NEW:
-		__sock_set_timestamps(sk, valbool, true, false);
-		break;
 	case SO_TIMESTAMPNS_OLD:
-		__sock_set_timestamps(sk, valbool, false, true);
-		break;
 	case SO_TIMESTAMPNS_NEW:
-		__sock_set_timestamps(sk, valbool, true, true);
+		sock_set_timestamp(sk, valbool, optname);
 		break;
+
 	case SO_TIMESTAMPING_NEW:
 	case SO_TIMESTAMPING_OLD:
-		if (val & ~SOF_TIMESTAMPING_MASK) {
-			ret = -EINVAL;
-			break;
-		}
-
-		if (val & SOF_TIMESTAMPING_OPT_ID &&
-		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-			if (sk->sk_protocol == IPPROTO_TCP &&
-			    sk->sk_type == SOCK_STREAM) {
-				if ((1 << sk->sk_state) &
-				    (TCPF_CLOSE | TCPF_LISTEN)) {
-					ret = -EINVAL;
-					break;
-				}
-				sk->sk_tskey = tcp_sk(sk)->snd_una;
-			} else {
-				sk->sk_tskey = 0;
-			}
-		}
-
-		if (val & SOF_TIMESTAMPING_OPT_STATS &&
-		    !(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
-			ret = -EINVAL;
-			break;
-		}
-
-		sk->sk_tsflags = val;
-		sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
-
-		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
-			sock_enable_timestamp(sk,
-					      SOCK_TIMESTAMPING_RX_SOFTWARE);
-		else
-			sock_disable_timestamp(sk,
-					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
+		ret = sock_set_timestamping(sk, optname, val);
 		break;
 
 	case SO_RCVLOWAT:
@@ -1622,6 +1651,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_bound_dev_if;
 		break;
 
+	case SO_NETNS_COOKIE:
+		lv = sizeof(u64);
+		if (len != lv)
+			return -EINVAL;
+		v.val64 = sock_net(sk)->net_cookie;
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).

net/core/sock_map.c

@@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	bpf_map_init_from_attr(&stab->map, attr);
 	raw_spin_lock_init(&stab->lock);
 
-	stab->sks = bpf_map_area_alloc(stab->map.max_entries *
+	stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries *
 				       sizeof(struct sock *),
 				       stab->map.numa_node);
 	if (!stab->sks) {

net/core/sock_reuseport.c

@@ -6,6 +6,7 @@
  * selecting the socket index from the array of available sockets.
  */
 
+#include <net/ip.h>
 #include <net/sock_reuseport.h>
 #include <linux/bpf.h>
 #include <linux/idr.h>
@@ -17,6 +18,74 @@
 DEFINE_SPINLOCK(reuseport_lock);
 
 static DEFINE_IDA(reuseport_ida);
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany);
+
+static int reuseport_sock_index(struct sock *sk,
+				const struct sock_reuseport *reuse,
+				bool closed)
+{
+	int left, right;
+
+	if (!closed) {
+		left = 0;
+		right = reuse->num_socks;
+	} else {
+		left = reuse->max_socks - reuse->num_closed_socks;
+		right = reuse->max_socks;
+	}
+
+	for (; left < right; left++)
+		if (reuse->socks[left] == sk)
+			return left;
+	return -1;
+}
+
+static void __reuseport_add_sock(struct sock *sk,
+				 struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->num_socks] = sk;
+	/* paired with smp_rmb() in reuseport_(select|migrate)_sock() */
+	smp_wmb();
+	reuse->num_socks++;
+}
+
+static bool __reuseport_detach_sock(struct sock *sk,
+				    struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, false);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
+	reuse->num_socks--;
+
+	return true;
+}
+
+static void __reuseport_add_closed_sock(struct sock *sk,
+					struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk;
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1);
+}
+
+static bool __reuseport_detach_closed_sock(struct sock *sk,
+					   struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, true);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1);
+
+	return true;
+}
 
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
@@ -49,6 +118,12 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 	if (reuse) {
+		if (reuse->num_closed_socks) {
+			/* sk was shutdown()ed before */
+			ret = reuseport_resurrect(sk, reuse, NULL, bind_inany);
+			goto out;
+		}
+
 		/* Only set reuse->bind_inany if the bind_inany is true.
 		 * Otherwise, it will overwrite the reuse->bind_inany
 		 * which was set by the bind/hash path.
@@ -72,9 +147,9 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
 	}
 
 	reuse->reuseport_id = id;
+	reuse->bind_inany = bind_inany;
 	reuse->socks[0] = sk;
 	reuse->num_socks = 1;
-	reuse->bind_inany = bind_inany;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 out:
@@ -90,14 +165,30 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	u32 more_socks_size, i;
 
 	more_socks_size = reuse->max_socks * 2U;
-	if (more_socks_size > U16_MAX)
+	if (more_socks_size > U16_MAX) {
+		if (reuse->num_closed_socks) {
+			/* Make room by removing a closed sk.
+			 * The child has already been migrated.
+			 * Only reqsk left at this point.
+			 */
+			struct sock *sk;
+
+			sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+			RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL);
+			__reuseport_detach_closed_sock(sk, reuse);
+
+			return reuse;
+		}
+
 		return NULL;
+	}
 
 	more_reuse = __reuseport_alloc(more_socks_size);
 	if (!more_reuse)
 		return NULL;
 
 	more_reuse->num_socks = reuse->num_socks;
+	more_reuse->num_closed_socks = reuse->num_closed_socks;
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
@@ -105,9 +196,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
+	memcpy(more_reuse->socks +
+	       (more_reuse->max_socks - more_reuse->num_closed_socks),
+	       reuse->socks + (reuse->max_socks - reuse->num_closed_socks),
+	       reuse->num_closed_socks * sizeof(struct sock *));
 	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
 
-	for (i = 0; i < reuse->num_socks; ++i)
+	for (i = 0; i < reuse->max_socks; ++i)
 		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
 				   more_reuse);
 
@@ -152,13 +247,21 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
-					     lockdep_is_held(&reuseport_lock));
+					      lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_closed_socks) {
+		/* sk was shutdown()ed before */
+		int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany);
+
+		spin_unlock_bh(&reuseport_lock);
+		return err;
+	}
+
 	if (old_reuse && old_reuse->num_socks != 1) {
 		spin_unlock_bh(&reuseport_lock);
 		return -EBUSY;
 	}
 
-	if (reuse->num_socks == reuse->max_socks) {
+	if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
 		if (!reuse) {
 			spin_unlock_bh(&reuseport_lock);
@@ -166,10 +269,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 		}
 	}
 
-	reuse->socks[reuse->num_socks] = sk;
-	/* paired with smp_rmb() in reuseport_select_sock() */
-	smp_wmb();
-	reuse->num_socks++;
+	__reuseport_add_sock(sk, reuse);
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 	spin_unlock_bh(&reuseport_lock);
@@ -180,15 +280,77 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 }
 EXPORT_SYMBOL(reuseport_add_sock);
 
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany)
+{
+	if (old_reuse == reuse) {
+		/* If sk was in the same reuseport group, just pop sk out of
+		 * the closed section and push sk into the listening section.
+		 */
+		__reuseport_detach_closed_sock(sk, old_reuse);
+		__reuseport_add_sock(sk, old_reuse);
+		return 0;
+	}
+
+	if (!reuse) {
+		/* In bind()/listen() path, we cannot carry over the eBPF prog
+		 * for the shutdown()ed socket. In setsockopt() path, we should
+		 * not change the eBPF prog of listening sockets by attaching a
+		 * prog to the shutdown()ed socket. Thus, we will allocate a new
+		 * reuseport group and detach sk from the old group.
+		 */
+		int id;
+
+		reuse = __reuseport_alloc(INIT_SOCKS);
+		if (!reuse)
+			return -ENOMEM;
+
+		id = ida_alloc(&reuseport_ida, GFP_ATOMIC);
+		if (id < 0) {
+			kfree(reuse);
+			return id;
+		}
+
+		reuse->reuseport_id = id;
+		reuse->bind_inany = bind_inany;
+	} else {
+		/* Move sk from the old group to the new one if
+		 * - all the other listeners in the old group were close()d or
+		 *   shutdown()ed, and then sk2 has listen()ed on the same port
+		 * OR
+		 * - sk listen()ed without bind() (or with autobind), was
+		 *   shutdown()ed, and then listen()s on another port which
+		 *   sk2 listen()s on.
+		 */
+		if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
+			reuse = reuseport_grow(reuse);
+			if (!reuse)
+				return -ENOMEM;
+		}
+	}
+
+	__reuseport_detach_closed_sock(sk, old_reuse);
+	__reuseport_add_sock(sk, reuse);
+	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+
+	if (old_reuse->num_socks + old_reuse->num_closed_socks == 0)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
+
+	return 0;
+}
+
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-	int i;
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 
+	/* reuseport_grow() has detached a closed sk */
+	if (!reuse)
+		goto out;
+
 	/* Notify the bpf side. The sk may be added to a sockarray
 	 * map. If so, sockarray logic will remove it from the map.
 	 *
@@ -201,19 +363,52 @@ void reuseport_detach_sock(struct sock *sk)
 
 	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
 
-	for (i = 0; i < reuse->num_socks; i++) {
-		if (reuse->socks[i] == sk) {
-			reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
-			reuse->num_socks--;
-			if (reuse->num_socks == 0)
-				call_rcu(&reuse->rcu, reuseport_free_rcu);
-			break;
-		}
-	}
+	if (!__reuseport_detach_closed_sock(sk, reuse))
+		__reuseport_detach_sock(sk, reuse);
+
+	if (reuse->num_socks + reuse->num_closed_socks == 0)
+		call_rcu(&reuse->rcu, reuseport_free_rcu);
+
+out:
 	spin_unlock_bh(&reuseport_lock);
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
 
+void reuseport_stop_listen_sock(struct sock *sk)
+{
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		struct sock_reuseport *reuse;
+		struct bpf_prog *prog;
+
+		spin_lock_bh(&reuseport_lock);
+
+		reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+						  lockdep_is_held(&reuseport_lock));
+		prog = rcu_dereference_protected(reuse->prog,
+						 lockdep_is_held(&reuseport_lock));
+
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
+			/* Migration capable, move sk from the listening section
+			 * to the closed section.
+			 */
+			bpf_sk_reuseport_detach(sk);
+
+			__reuseport_detach_sock(sk, reuse);
+			__reuseport_add_closed_sock(sk, reuse);
+
+			spin_unlock_bh(&reuseport_lock);
+			return;
+		}
+
+		spin_unlock_bh(&reuseport_lock);
+	}
+
+	/* Not capable to do migration, detach immediately */
+	reuseport_detach_sock(sk);
+}
+EXPORT_SYMBOL(reuseport_stop_listen_sock);
+
 static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
 				   struct bpf_prog *prog, struct sk_buff *skb,
 				   int hdr_len)
@@ -244,6 +439,23 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
 	return reuse->socks[index];
 }
 
+static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse,
+						  u32 hash, u16 num_socks)
+{
+	int i, j;
+
+	i = j = reciprocal_scale(hash, num_socks);
+	while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
+		i++;
+		if (i >= num_socks)
+			i = 0;
+		if (i == j)
+			return NULL;
+	}
+
+	return reuse->socks[i];
+}
+
 /**
  *  reuseport_select_sock - Select a socket from an SO_REUSEPORT group.
  *  @sk: First socket in the group.
@@ -274,32 +486,21 @@ struct sock *reuseport_select_sock(struct sock *sk,
 	prog = rcu_dereference(reuse->prog);
 	socks = READ_ONCE(reuse->num_socks);
 	if (likely(socks)) {
-		/* paired with smp_wmb() in reuseport_add_sock() */
+		/* paired with smp_wmb() in __reuseport_add_sock() */
 		smp_rmb();
 
 		if (!prog || !skb)
 			goto select_by_hash;
 
 		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
-			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash);
 		else
 			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
 select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
-		if (!sk2) {
-			int i, j;
-
-			i = j = reciprocal_scale(hash, socks);
-			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
-				i++;
-				if (i >= socks)
-					i = 0;
-				if (i == j)
-					goto out;
-			}
-			sk2 = reuse->socks[i];
-		}
+		if (!sk2)
+			sk2 = reuseport_select_sock_by_hash(reuse, hash, socks);
 	}
 
 out:
@@ -308,14 +509,90 @@ out:
 }
 EXPORT_SYMBOL(reuseport_select_sock);
 
+/**
+ *  reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group.
+ *  @sk: close()ed or shutdown()ed socket in the group.
+ *  @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or
+ *    NEW_SYN_RECV request socket during 3WHS.
+ *  @skb: skb to run through BPF filter.
+ *  Returns a socket (with sk_refcnt +1) that should accept the child socket
+ *  (or NULL on error).
+ */
+struct sock *reuseport_migrate_sock(struct sock *sk,
+				    struct sock *migrating_sk,
+				    struct sk_buff *skb)
+{
+	struct sock_reuseport *reuse;
+	struct sock *nsk = NULL;
+	bool allocated = false;
+	struct bpf_prog *prog;
+	u16 socks;
+	u32 hash;
+
+	rcu_read_lock();
+
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (!reuse)
+		goto out;
+
+	socks = READ_ONCE(reuse->num_socks);
+	if (unlikely(!socks))
+		goto failure;
+
+	/* paired with smp_wmb() in __reuseport_add_sock() */
+	smp_rmb();
+
+	hash = migrating_sk->sk_hash;
+	prog = rcu_dereference(reuse->prog);
+	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+			goto select_by_hash;
+		goto failure;
+	}
+
+	if (!skb) {
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			goto failure;
+		allocated = true;
+	}
+
+	nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash);
+
+	if (allocated)
+		kfree_skb(skb);
+
+select_by_hash:
+	if (!nsk)
+		nsk = reuseport_select_sock_by_hash(reuse, hash, socks);
+
+	if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) {
+		nsk = NULL;
+		goto failure;
+	}
+
+out:
+	rcu_read_unlock();
+	return nsk;
+
+failure:
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
+	goto out;
+}
+EXPORT_SYMBOL(reuseport_migrate_sock);
+
 int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 {
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
-	if (sk_unhashed(sk) && sk->sk_reuseport) {
-		int err = reuseport_alloc(sk, false);
+	if (sk_unhashed(sk)) {
+		int err;
 
+		if (!sk->sk_reuseport)
+			return -EINVAL;
+
+		err = reuseport_alloc(sk, false);
 		if (err)
 			return err;
 	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -341,13 +618,24 @@ int reuseport_detach_prog(struct sock *sk)
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return sk->sk_reuseport ? -ENOENT : -EINVAL;
-
 	old_prog = NULL;
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
+
+	/* reuse must be checked after acquiring the reuseport_lock
+	 * because reuseport_grow() can detach a closed sk.
+	 */
+	if (!reuse) {
+		spin_unlock_bh(&reuseport_lock);
+		return sk->sk_reuseport ? -ENOENT : -EINVAL;
+	}
+
+	if (sk_unhashed(sk) && reuse->num_closed_socks) {
+		spin_unlock_bh(&reuseport_lock);
+		return -ENOENT;
+	}
+
 	old_prog = rcu_replace_pointer(reuse->prog, old_prog,
 				       lockdep_is_held(&reuseport_lock));
 	spin_unlock_bh(&reuseport_lock);

net/core/xdp.c

@@ -113,8 +113,13 @@ static void mem_allocator_disconnect(void *allocator)
 void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
 {
 	struct xdp_mem_allocator *xa;
+	int type = xdp_rxq->mem.type;
 	int id = xdp_rxq->mem.id;
 
+	/* Reset mem info to defaults */
+	xdp_rxq->mem.id = 0;
+	xdp_rxq->mem.type = 0;
+
 	if (xdp_rxq->reg_state != REG_STATE_REGISTERED) {
 		WARN(1, "Missing register, driver bug");
 		return;
@@ -123,7 +128,7 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
 	if (id == 0)
 		return;
 
-	if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) {
+	if (type == MEM_TYPE_PAGE_POOL) {
 		rcu_read_lock();
 		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
 		page_pool_destroy(xa->page_pool);
@@ -144,10 +149,6 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
 
 	xdp_rxq->reg_state = REG_STATE_UNREGISTERED;
 	xdp_rxq->dev = NULL;
-
-	/* Reset mem info to defaults */
-	xdp_rxq->mem.id = 0;
-	xdp_rxq->mem.type = 0;
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg);
 
@@ -584,3 +585,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	return __xdp_build_skb_from_frame(xdpf, skb, dev);
 }
 EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+	unsigned int headroom, totalsize;
+	struct xdp_frame *nxdpf;
+	struct page *page;
+	void *addr;
+
+	headroom = xdpf->headroom + sizeof(*xdpf);
+	totalsize = headroom + xdpf->len;
+
+	if (unlikely(totalsize > PAGE_SIZE))
+		return NULL;
+	page = dev_alloc_page();
+	if (!page)
+		return NULL;
+	addr = page_to_virt(page);
+
+	memcpy(addr, xdpf, totalsize);
+
+	nxdpf = addr;
+	nxdpf->data = addr + headroom;
+	nxdpf->frame_sz = PAGE_SIZE;
+	nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+	nxdpf->mem.id = 0;
+
+	return nxdpf;
+}