12 files changed, 300 insertions, 69 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index c907f0dc7f87..359908a7d3c1 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/bpf_local_storage.h>
 #include <net/bpf_sk_storage.h>
@@ -15,20 +16,8 @@
 
 DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
-static int omem_charge(struct sock *sk, unsigned int size)
-{
-	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
-		atomic_add(size, &sk->sk_omem_alloc);
-		return 0;
-	}
-
-	return -ENOMEM;
-}
-
 static struct bpf_local_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 {
 	struct bpf_local_storage *sk_storage;
 	struct bpf_local_storage_map *smap;
@@ -41,11 +30,11 @@ sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 	return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
 }
 
-static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
 {
 	struct bpf_local_storage_data *sdata;
 
-	sdata = sk_storage_lookup(sk, map, false);
+	sdata = bpf_sk_storage_lookup(sk, map, false);
 	if (!sdata)
 		return -ENOENT;
 
@@ -94,7 +83,7 @@ void bpf_sk_storage_free(struct sock *sk)
 		kfree_rcu(sk_storage, rcu);
 }
 
-static void sk_storage_map_free(struct bpf_map *map)
+static void bpf_sk_storage_map_free(struct bpf_map *map)
 {
 	struct bpf_local_storage_map *smap;
 
@@ -103,7 +92,7 @@ static void sk_storage_map_free(struct bpf_map *map)
 	bpf_local_storage_map_free(smap);
 }
 
-static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_local_storage_map *smap;
 
@@ -130,7 +119,7 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		sdata = sk_storage_lookup(sock->sk, map, true);
+		sdata = bpf_sk_storage_lookup(sock->sk, map, true);
 		sockfd_put(sock);
 		return sdata ? sdata->data : NULL;
 	}
@@ -166,7 +155,7 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		err = sk_storage_delete(sock->sk, map);
+		err = bpf_sk_storage_del(sock->sk, map);
 		sockfd_put(sock);
 		return err;
 	}
@@ -272,7 +261,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
 		return (unsigned long)NULL;
 
-	sdata = sk_storage_lookup(sk, map, true);
+	sdata = bpf_sk_storage_lookup(sk, map, true);
 	if (sdata)
 		return (unsigned long)sdata->data;
 
@@ -305,7 +294,7 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
 		int err;
 
-		err = sk_storage_delete(sk, map);
+		err = bpf_sk_storage_del(sk, map);
 		sock_put(sk);
 		return err;
 	}
@@ -313,14 +302,23 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 	return -ENOENT;
 }
 
-static int sk_storage_charge(struct bpf_local_storage_map *smap,
-			     void *owner, u32 size)
+static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
+				 void *owner, u32 size)
 {
-	return omem_charge(owner, size);
+	struct sock *sk = (struct sock *)owner;
+
+	/* same check as in sock_kmalloc() */
+	if (size <= sysctl_optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+		atomic_add(size, &sk->sk_omem_alloc);
+		return 0;
+	}
+
+	return -ENOMEM;
 }
 
-static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
-				void *owner, u32 size)
+static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
+				    void *owner, u32 size)
 {
 	struct sock *sk = owner;
 
@@ -328,7 +326,7 @@ static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
 }
 
 static struct bpf_local_storage __rcu **
-sk_storage_ptr(void *owner)
+bpf_sk_storage_ptr(void *owner)
 {
 	struct sock *sk = owner;
 
@@ -339,8 +337,8 @@ static int sk_storage_map_btf_id;
 const struct bpf_map_ops sk_storage_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
-	.map_alloc = sk_storage_map_alloc,
-	.map_free = sk_storage_map_free,
+	.map_alloc = bpf_sk_storage_map_alloc,
+	.map_free = bpf_sk_storage_map_free,
 	.map_get_next_key = notsupp_get_next_key,
 	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
@@ -348,9 +346,9 @@ const struct bpf_map_ops sk_storage_map_ops = {
 	.map_check_btf = bpf_local_storage_map_check_btf,
 	.map_btf_name = "bpf_local_storage_map",
 	.map_btf_id = &sk_storage_map_btf_id,
-	.map_local_storage_charge = sk_storage_charge,
-	.map_local_storage_uncharge = sk_storage_uncharge,
-	.map_owner_storage_ptr = sk_storage_ptr,
+	.map_local_storage_charge = bpf_sk_storage_charge,
+	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
+	.map_owner_storage_ptr = bpf_sk_storage_ptr,
 };
 
 const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -381,6 +379,79 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
+static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
+{
+	const struct btf *btf_vmlinux;
+	const struct btf_type *t;
+	const char *tname;
+	u32 btf_id;
+
+	if (prog->aux->dst_prog)
+		return false;
+
+	/* Ensure the tracing program is not tracing
+	 * any bpf_sk_storage*() function and also
+	 * use the bpf_sk_storage_(get|delete) helper.
+	 */
+	switch (prog->expected_attach_type) {
+	case BPF_TRACE_RAW_TP:
+		/* bpf_sk_storage has no trace point */
+		return true;
+	case BPF_TRACE_FENTRY:
+	case BPF_TRACE_FEXIT:
+		btf_vmlinux = bpf_get_btf_vmlinux();
+		btf_id = prog->aux->attach_btf_id;
+		t = btf_type_by_id(btf_vmlinux, btf_id);
+		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+		return !!strncmp(tname, "bpf_sk_storage",
+				 strlen("bpf_sk_storage"));
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
+	   void *, value, u64, flags)
+{
+	if (!in_serving_softirq() && !in_task())
+		return (unsigned long)NULL;
+
+	return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
+}
+
+BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
+	   struct sock *, sk)
+{
+	if (!in_serving_softirq() && !in_task())
+		return -EPERM;
+
+	return ____bpf_sk_storage_delete(map, sk);
+}
+
+const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
+	.func		= bpf_sk_storage_get_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+	.allowed	= bpf_sk_storage_tracing_allowed,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
+	.func		= bpf_sk_storage_delete_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.allowed	= bpf_sk_storage_tracing_allowed,
+};
+
 struct bpf_sk_storage_diag {
 	u32 nr_maps;
 	struct bpf_map *maps[];
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9fcaa544f11a..81809fa735a7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -709,7 +709,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
 /**
- *	skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ *	skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
  *          and update a checksum.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying from
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..51b263076124 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3206,7 +3206,7 @@ int skb_checksum_help(struct sk_buff *skb)
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		goto out_set_summed;
 
-	if (unlikely(skb_shinfo(skb)->gso_size)) {
+	if (unlikely(skb_is_gso(skb))) {
 		skb_warn_bad_offload(skb);
 		return -EINVAL;
 	}
@@ -3495,6 +3495,11 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > dev->gso_max_segs)
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (!skb_shinfo(skb)->gso_type) {
+		skb_warn_bad_offload(skb);
+		return features & ~NETIF_F_GSO_MASK;
+	}
+
 	/* Support for GSO partial features requires software
 	 * intervention before we can actually process the packets
 	 * so we need to strip support for any partial features now
@@ -3867,6 +3872,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+	qdisc_skb_cb(skb)->mru = 0;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
@@ -4954,6 +4960,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	}
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	qdisc_skb_cb(skb)->mru = 0;
 	skb->tc_at_ingress = 1;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
@@ -6919,7 +6926,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
 EXPORT_SYMBOL(netdev_has_upper_dev);
 
 /**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
  * @dev: device
  * @upper_dev: upper device to check
  *
@@ -8157,7 +8164,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
 
 /**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
  * @lower_dev: device
  * @lower_state_info: state to dispatch
  *
@@ -8902,7 +8909,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 		return dev->netdev_ops->ndo_bpf;
 	default:
 		return NULL;
-	};
+	}
 }
 
 static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
@@ -10366,6 +10373,21 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 }
 EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
 
+/**
+ *	dev_get_tstats64 - ndo_get_stats64 implementation
+ *	@dev: device to get statistics from
+ *	@s: place to store stats
+ *
+ *	Populate @s from dev->stats and dev->tstats. Can be used as
+ *	ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 205e92e604ef..db8a0ff86f36 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -230,7 +230,7 @@ static int dev_do_ioctl(struct net_device *dev,
 			struct ifreq *ifr, unsigned int cmd)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	int err = -EOPNOTSUPP;
+	int err;
 
 	err = dsa_ndo_do_ioctl(dev, ifr, cmd);
 	if (err == 0 || err != -EOPNOTSUPP)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8c5ddffd707d..88c0ac8ed444 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3394,7 +3394,7 @@ out_free_msg:
 	nlmsg_free(msg);
 }
 
-void devlink_flash_update_begin_notify(struct devlink *devlink)
+static void devlink_flash_update_begin_notify(struct devlink *devlink)
 {
 	struct devlink_flash_notify params = { 0 };
 
@@ -3402,9 +3402,8 @@ void devlink_flash_update_begin_notify(struct devlink *devlink)
 				      DEVLINK_CMD_FLASH_UPDATE,
 				      &params);
 }
-EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
 
-void devlink_flash_update_end_notify(struct devlink *devlink)
+static void devlink_flash_update_end_notify(struct devlink *devlink)
 {
 	struct devlink_flash_notify params = { 0 };
 
@@ -3412,7 +3411,6 @@ void devlink_flash_update_end_notify(struct devlink *devlink)
 				      DEVLINK_CMD_FLASH_UPDATE_END,
 				      &params);
 }
-EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
 
 void devlink_flash_update_status_notify(struct devlink *devlink,
 					const char *status_msg,
@@ -3453,10 +3451,12 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
-	struct nlattr *nla_component, *nla_overwrite_mask;
+	struct nlattr *nla_component, *nla_overwrite_mask, *nla_file_name;
 	struct devlink_flash_update_params params = {};
 	struct devlink *devlink = info->user_ptr[0];
+	const char *file_name;
 	u32 supported_params;
+	int ret;
 
 	if (!devlink->ops->flash_update)
 		return -EOPNOTSUPP;
@@ -3466,8 +3466,6 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 
 	supported_params = devlink->ops->supported_flash_update_params;
 
-	params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
-
 	nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
 	if (nla_component) {
 		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
@@ -3491,7 +3489,21 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 		params.overwrite_mask = sections.value & sections.selector;
 	}
 
-	return devlink->ops->flash_update(devlink, &params, info->extack);
+	nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME];
+	file_name = nla_data(nla_file_name);
+	ret = request_firmware(&params.fw, file_name, devlink->dev);
+	if (ret) {
+		NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file");
+		return ret;
+	}
+
+	devlink_flash_update_begin_notify(devlink);
+	ret = devlink->ops->flash_update(devlink, &params, info->extack);
+	devlink_flash_update_end_notify(devlink);
+
+	release_firmware(params.fw);
+
+	return ret;
 }
 
 static const struct devlink_param devlink_param_generic[] = {
@@ -9500,6 +9512,7 @@ static const struct devlink_trap devlink_trap_generic[] = {
 	DEVLINK_TRAP(DCCP_PARSING, DROP),
 	DEVLINK_TRAP(GTP_PARSING, DROP),
 	DEVLINK_TRAP(ESP_PARSING, DROP),
+	DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
 };
 
 #define DEVLINK_TRAP_GROUP(_id)						      \
@@ -10249,12 +10262,18 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 		goto out;
 	}
 
-	params.file_name = file_name;
+	ret = request_firmware(&params.fw, file_name, devlink->dev);
+	if (ret)
+		goto out;
 
 	mutex_lock(&devlink->lock);
+	devlink_flash_update_begin_notify(devlink);
 	ret = devlink->ops->flash_update(devlink, &params, NULL);
+	devlink_flash_update_end_notify(devlink);
 	mutex_unlock(&devlink->lock);
 
+	release_firmware(params.fw);
+
 out:
 	rtnl_lock();
 	dev_put(dev);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 7bcfb16854cb..cd80ffed6d26 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -563,7 +563,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->iifindex = -1;
-		nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->iifname);
 		if (dev)
 			nlrule->iifindex = dev->ifindex;
@@ -573,7 +573,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->oifindex = -1;
-		nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->oifname);
 		if (dev)
 			nlrule->oifindex = dev->ifindex;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e21950a2c897..6f1adba6695f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -48,7 +48,7 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 	memset(flow_dissector, 0, sizeof(*flow_dissector));
 
 	for (i = 0; i < key_count; i++, key++) {
-		/* User should make sure that every key target offset is withing
+		/* User should make sure that every key target offset is within
 		 * boundaries of unsigned short.
 		 */
 		BUG_ON(key->offset > USHRT_MAX);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ef98372facf6..f3c690b8c8e3 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -11,6 +11,8 @@
 #include <linux/device.h>
 
 #include <net/page_pool.h>
+#include <net/xdp.h>
+
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
 #include <linux/page-flags.h>
@@ -362,8 +364,9 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
  * If the page refcnt != 1, then the page will be returned to memory
  * subsystem.
  */
-void page_pool_put_page(struct page_pool *pool, struct page *page,
-			unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+		     unsigned int dma_sync_size, bool allow_direct)
 {
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
@@ -379,15 +382,12 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 			page_pool_dma_sync_for_device(pool, page,
 						      dma_sync_size);
 
-		if (allow_direct && in_serving_softirq())
-			if (page_pool_recycle_in_cache(page, pool))
-				return;
+		if (allow_direct && in_serving_softirq() &&
+		    page_pool_recycle_in_cache(page, pool))
+			return NULL;
 
-		if (!page_pool_recycle_in_ring(pool, page)) {
-			/* Cache full, fallback to free pages */
-			page_pool_return_page(pool, page);
-		}
-		return;
+		/* Page found as candidate for recycling */
+		return page;
 	}
 	/* Fallback/non-XDP mode: API user have elevated refcnt.
 	 *
@@ -405,9 +405,59 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 	/* Do not replace this with page_pool_return_page() */
 	page_pool_release_page(pool, page);
 	put_page(page);
+
+	return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+			unsigned int dma_sync_size, bool allow_direct)
+{
+	page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+	if (page && !page_pool_recycle_in_ring(pool, page)) {
+		/* Cache full, fallback to free pages */
+		page_pool_return_page(pool, page);
+	}
 }
 EXPORT_SYMBOL(page_pool_put_page);
 
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count)
+{
+	int i, bulk_len = 0;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = virt_to_head_page(data[i]);
+
+		page = __page_pool_put_page(pool, page, -1, false);
+		/* Approved for bulk recycling in ptr_ring cache */
+		if (page)
+			data[bulk_len++] = page;
+	}
+
+	if (unlikely(!bulk_len))
+		return;
+
+	/* Bulk producer into ptr_ring page_pool cache */
+	page_pool_ring_lock(pool);
+	for (i = 0; i < bulk_len; i++) {
+		if (__ptr_ring_produce(&pool->ring, data[i]))
+			break; /* ring full */
+	}
+	page_pool_ring_unlock(pool);
+
+	/* Hopefully all pages was return into ptr_ring */
+	if (likely(i == bulk_len))
+		return;
+
+	/* ptr_ring cache full, free remaining pages outside producer lock
+	 * since put_page() with refcnt == 1 can be an expensive operation
+	 */
+	for (; i < bulk_len; i++)
+		page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
 static void page_pool_empty_ring(struct page_pool *pool)
 {
 	struct page *page;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7d7223691783..60917ff4a00b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1939,7 +1939,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	if (linfo[IFLA_INFO_KIND]) {
 		char kind[MODULE_NAME_LEN];
 
-		nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	}
 
@@ -2953,9 +2953,9 @@ static struct net_device *rtnl_dev_get(struct net *net,
 	if (!ifname) {
 		ifname = buffer;
 		if (ifname_attr)
-			nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+			nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
 		else if (altifname_attr)
-			nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+			nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
 		else
 			return NULL;
 	}
@@ -2983,7 +2983,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3264,7 +3264,7 @@ replay:
 		return err;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3296,7 +3296,7 @@ replay:
 		memset(linkinfo, 0, sizeof(linkinfo));
 
 	if (linkinfo[IFLA_INFO_KIND]) {
-		nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	} else {
 		kind[0] = '\0';
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06c526e0d810..ad98265f1dd1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 
 		fclones->skb2.fclone = SKB_FCLONE_CLONE;
 	}
+
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 out:
 	return skb;
 nodata:
@@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb,
 	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
 	atomic_set(&shinfo->dataref, 1);
 
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 	return skb;
 }
 
@@ -837,7 +842,7 @@ EXPORT_SYMBOL(consume_skb);
 #endif
 
 /**
- *	consume_stateless_skb - free an skbuff, assuming it is stateless
+ *	__consume_stateless_skb - free an skbuff, assuming it is stateless
  *	@skb: buffer to free
  *
  *	Alike consume_skb(), but this variant assumes that this is the last
@@ -897,6 +902,8 @@ void napi_consume_skb(struct sk_buff *skb, int budget)
 		return;
 	}
 
+	lockdep_assert_in_softirq();
+
 	if (!skb_unref(skb))
 		return;
 
@@ -4203,6 +4210,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MPTCP)
 	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
 #endif
+#if IS_ENABLED(CONFIG_KCOV)
+	[SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4220,6 +4230,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #if IS_ENABLED(CONFIG_MPTCP)
 		skb_ext_type_len[SKB_EXT_MPTCP] +
 #endif
+#if IS_ENABLED(CONFIG_KCOV)
+		skb_ext_type_len[SKB_EXT_KCOV_HANDLE] +
+#endif
 		0;
 }
 
@@ -5430,7 +5443,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 		goto err_free;
 
 	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
+	if (!skb_transport_header_was_set(skb))
+		skb_reset_transport_header(skb);
 	skb_reset_mac_len(skb);
 
 	return skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index 727ea1cc633c..9badbe7bb4e4 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3078,7 +3078,7 @@ EXPORT_SYMBOL(release_sock);
  *
  *   sk_lock.slock unlocked, owned = 1, BH enabled
  */
-bool lock_sock_fast(struct sock *sk)
+bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
 {
 	might_sleep();
 	spin_lock_bh(&sk->sk_lock.slock);
@@ -3096,6 +3096,7 @@ bool lock_sock_fast(struct sock *sk)
 	 * The sk_lock has mutex_lock() semantics here:
 	 */
 	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+	__acquire(&sk->sk_lock.slock);
 	local_bh_enable();
 	return true;
 }
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 48aba933a5a8..3d330ebda893 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -380,6 +380,60 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_allocator *xa = bq->xa;
+
+	if (unlikely(!xa || !bq->count))
+		return;
+
+	page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+	/* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_info *mem = &xdpf->mem;
+	struct xdp_mem_allocator *xa;
+
+	if (mem->type != MEM_TYPE_PAGE_POOL) {
+		__xdp_return(xdpf->data, &xdpf->mem, false);
+		return;
+	}
+
+	xa = bq->xa;
+	if (unlikely(!xa)) {
+		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+		bq->count = 0;
+		bq->xa = xa;
+	}
+
+	if (bq->count == XDP_BULK_QUEUE_SIZE)
+		xdp_flush_frame_bulk(bq);
+
+	if (unlikely(mem->id != xa->mem.id)) {
+		xdp_flush_frame_bulk(bq);
+		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+	}
+
+	bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);