Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

9 files changed, 511 insertions, 88 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 29d781061cd5..e1d9adb212f9 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o
 ifeq ($(CONFIG_INET),y)
 obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
 endif
+ifeq ($(CONFIG_SYSFS),y)
+obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
+endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5fcc7a17eb5a..adb3adcebe3c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -195,8 +195,8 @@
 	     i < btf_type_vlen(struct_type);					\
 	     i++, member++)
 
-static DEFINE_IDR(btf_idr);
-static DEFINE_SPINLOCK(btf_idr_lock);
+DEFINE_IDR(btf_idr);
+DEFINE_SPINLOCK(btf_idr_lock);
 
 struct btf {
 	void *data;
@@ -3376,6 +3376,15 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 	btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
 }
 
+#ifdef CONFIG_PROC_FS
+static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+	const struct btf *btf = filp->private_data;
+
+	seq_printf(m, "btf_id:\t%u\n", btf->id);
+}
+#endif
+
 static int btf_release(struct inode *inode, struct file *filp)
 {
 	btf_put(filp->private_data);
@@ -3383,6 +3392,9 @@ static int btf_release(struct inode *inode, struct file *filp)
 }
 
 const struct file_operations btf_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= bpf_btf_show_fdinfo,
+#endif
 	.release	= btf_release,
 };
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 0a00eaca6fae..ddd8addcdb5c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -964,7 +964,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 		return -ENOMEM;
 
 	ctx->optval_end = ctx->optval + max_optlen;
-	ctx->optlen = max_optlen;
 
 	return 0;
 }
@@ -984,7 +983,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		.level = *level,
 		.optname = *optname,
 	};
-	int ret;
+	int ret, max_optlen;
 
 	/* Opportunistic check to see whether we have any BPF program
 	 * attached to the hook so we don't waste time allocating
@@ -994,10 +993,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
 		return 0;
 
-	ret = sockopt_alloc_buf(&ctx, *optlen);
+	/* Allocate a bit more than the initial user buffer for
+	 * BPF program. The canonical use case is overriding
+	 * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic).
+	 */
+	max_optlen = max_t(int, 16, *optlen);
+
+	ret = sockopt_alloc_buf(&ctx, max_optlen);
 	if (ret)
 		return ret;
 
+	ctx.optlen = *optlen;
+
 	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
 		ret = -EFAULT;
 		goto out;
@@ -1016,7 +1023,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	if (ctx.optlen == -1) {
 		/* optlen set to -1, bypass kernel */
 		ret = 1;
-	} else if (ctx.optlen > *optlen || ctx.optlen < -1) {
+	} else if (ctx.optlen > max_optlen || ctx.optlen < -1) {
 		/* optlen is out of bounds */
 		ret = -EFAULT;
 	} else {
@@ -1063,6 +1070,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	if (ret)
 		return ret;
 
+	ctx.optlen = max_optlen;
+
 	if (!retval) {
 		/* If kernel getsockopt finished successfully,
 		 * copy whatever was returned to the user back
@@ -1325,6 +1334,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
 				     struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
+	u32 read_size;
 
 	switch (si->off) {
 	case offsetof(struct bpf_sysctl, write):
@@ -1356,7 +1366,9 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
 				treg, si->dst_reg,
 				offsetof(struct bpf_sysctl_kern, ppos));
 			*insn++ = BPF_STX_MEM(
-				BPF_SIZEOF(u32), treg, si->src_reg, 0);
+				BPF_SIZEOF(u32), treg, si->src_reg,
+				bpf_ctx_narrow_access_offset(
+					0, sizeof(u32), sizeof(loff_t)));
 			*insn++ = BPF_LDX_MEM(
 				BPF_DW, treg, si->dst_reg,
 				offsetof(struct bpf_sysctl_kern, tmp_reg));
@@ -1365,8 +1377,11 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
 				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
 				si->dst_reg, si->src_reg,
 				offsetof(struct bpf_sysctl_kern, ppos));
+			read_size = bpf_size_to_bytes(BPF_SIZE(si->code));
 			*insn++ = BPF_LDX_MEM(
-				BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0);
+				BPF_SIZE(si->code), si->dst_reg, si->dst_reg,
+				bpf_ctx_narrow_access_offset(
+					0, read_size, sizeof(loff_t)));
 		}
 		*target_size = sizeof(u32);
 		break;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d83cf8ccc872..d27f3b60ff6d 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -37,6 +37,12 @@
  * notifier hook walks the map we know that new dev references can not be
  * added by the user because core infrastructure ensures dev_get_by_index()
  * calls will fail at this point.
+ *
+ * The devmap_hash type is a map type which interprets keys as ifindexes and
+ * indexes these using a hashmap. This allows maps that use ifindex as key to be
+ * densely packed instead of having holes in the lookup array for unused
+ * ifindexes. The setup and packet enqueue/send code is shared between the two
+ * types of devmap; only the lookup and insertion is different.
  */
 #include <linux/bpf.h>
 #include <net/xdp.h>
@@ -59,10 +65,11 @@ struct xdp_bulk_queue {
 
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
+	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
-	unsigned int bit;
 	struct xdp_bulk_queue __percpu *bulkq;
 	struct rcu_head rcu;
+	unsigned int idx; /* keep track of map index for tracepoint */
 };
 
 struct bpf_dtab {
@@ -70,33 +77,45 @@ struct bpf_dtab {
 	struct bpf_dtab_netdev **netdev_map;
 	struct list_head __percpu *flush_list;
 	struct list_head list;
+
+	/* these are only used for DEVMAP_HASH type maps */
+	struct hlist_head *dev_index_head;
+	spinlock_t index_lock;
+	unsigned int items;
+	u32 n_buckets;
 };
 
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
-static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+static struct hlist_head *dev_map_create_hash(unsigned int entries)
+{
+	int i;
+	struct hlist_head *hash;
+
+	hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL);
+	if (hash != NULL)
+		for (i = 0; i < entries; i++)
+			INIT_HLIST_HEAD(&hash[i]);
+
+	return hash;
+}
+
+static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 {
-	struct bpf_dtab *dtab;
 	int err, cpu;
 	u64 cost;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
 	 * verifier prevents writes from the BPF side
 	 */
 	attr->map_flags |= BPF_F_RDONLY_PROG;
 
-	dtab = kzalloc(sizeof(*dtab), GFP_USER);
-	if (!dtab)
-		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&dtab->map, attr);
 
@@ -104,12 +123,18 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
 	cost += sizeof(struct list_head) * num_possible_cpus();
 
+	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
+
+		if (!dtab->n_buckets) /* Overflow check */
+			return -EINVAL;
+		cost += sizeof(struct hlist_head) * dtab->n_buckets;
+	}
+
 	/* if map size is larger than memlock limit, reject it */
 	err = bpf_map_charge_init(&dtab->map.memory, cost);
 	if (err)
-		goto free_dtab;
-
-	err = -ENOMEM;
+		return -EINVAL;
 
 	dtab->flush_list = alloc_percpu(struct list_head);
 	if (!dtab->flush_list)
@@ -124,19 +149,48 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	if (!dtab->netdev_map)
 		goto free_percpu;
 
-	spin_lock(&dev_map_lock);
-	list_add_tail_rcu(&dtab->list, &dev_map_list);
-	spin_unlock(&dev_map_lock);
+	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
+		if (!dtab->dev_index_head)
+			goto free_map_area;
 
-	return &dtab->map;
+		spin_lock_init(&dtab->index_lock);
+	}
 
+	return 0;
+
+free_map_area:
+	bpf_map_area_free(dtab->netdev_map);
 free_percpu:
 	free_percpu(dtab->flush_list);
 free_charge:
 	bpf_map_charge_finish(&dtab->map.memory);
-free_dtab:
-	kfree(dtab);
-	return ERR_PTR(err);
+	return -ENOMEM;
+}
+
+static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_dtab *dtab;
+	int err;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	dtab = kzalloc(sizeof(*dtab), GFP_USER);
+	if (!dtab)
+		return ERR_PTR(-ENOMEM);
+
+	err = dev_map_init_map(dtab, attr);
+	if (err) {
+		kfree(dtab);
+		return ERR_PTR(err);
+	}
+
+	spin_lock(&dev_map_lock);
+	list_add_tail_rcu(&dtab->list, &dev_map_list);
+	spin_unlock(&dev_map_lock);
+
+	return &dtab->map;
 }
 
 static void dev_map_free(struct bpf_map *map)
@@ -188,6 +242,7 @@ static void dev_map_free(struct bpf_map *map)
 
 	free_percpu(dtab->flush_list);
 	bpf_map_area_free(dtab->netdev_map);
+	kfree(dtab->dev_index_head);
 	kfree(dtab);
 }
 
@@ -208,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
+						    int idx)
+{
+	return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
+}
+
+struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct hlist_head *head = dev_map_index_hash(dtab, key);
+	struct bpf_dtab_netdev *dev;
+
+	hlist_for_each_entry_rcu(dev, head, index_hlist)
+		if (dev->idx == key)
+			return dev;
+
+	return NULL;
+}
+
+static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
+				    void *next_key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	u32 idx, *next = next_key;
+	struct bpf_dtab_netdev *dev, *next_dev;
+	struct hlist_head *head;
+	int i = 0;
+
+	if (!key)
+		goto find_first;
+
+	idx = *(u32 *)key;
+
+	dev = __dev_map_hash_lookup_elem(map, idx);
+	if (!dev)
+		goto find_first;
+
+	next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)),
+				    struct bpf_dtab_netdev, index_hlist);
+
+	if (next_dev) {
+		*next = next_dev->idx;
+		return 0;
+	}
+
+	i = idx & (dtab->n_buckets - 1);
+	i++;
+
+ find_first:
+	for (; i < dtab->n_buckets; i++) {
+		head = dev_map_index_hash(dtab, i);
+
+		next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+					    struct bpf_dtab_netdev,
+					    index_hlist);
+		if (next_dev) {
+			*next = next_dev->idx;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
 static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags,
 		       bool in_napi_ctx)
 {
@@ -235,7 +354,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags,
 out:
 	bq->count = 0;
 
-	trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
+	trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
 			      sent, drops, bq->dev_rx, dev, err);
 	bq->dev_rx = NULL;
 	__list_del_clearprev(&bq->flush_node);
@@ -363,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 	return dev ? &dev->ifindex : NULL;
 }
 
+static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
+								*(u32 *)key);
+	struct net_device *dev = obj ? obj->dev : NULL;
+
+	return dev ? &dev->ifindex : NULL;
+}
+
 static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 {
 	if (dev->dev->netdev_ops->ndo_xdp_xmit) {
@@ -412,17 +540,74 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
 	return 0;
 }
 
-static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
-				u64 map_flags)
+static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	struct net *net = current->nsproxy->net_ns;
+	struct bpf_dtab_netdev *old_dev;
+	int k = *(u32 *)key;
+	unsigned long flags;
+	int ret = -ENOENT;
+
+	spin_lock_irqsave(&dtab->index_lock, flags);
+
+	old_dev = __dev_map_hash_lookup_elem(map, k);
+	if (old_dev) {
+		dtab->items--;
+		hlist_del_init_rcu(&old_dev->index_hlist);
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+
+	return ret;
+}
+
+static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
+						    struct bpf_dtab *dtab,
+						    u32 ifindex,
+						    unsigned int idx)
+{
 	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+	struct bpf_dtab_netdev *dev;
+	struct xdp_bulk_queue *bq;
+	int cpu;
+
+	dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
+					sizeof(void *), gfp);
+	if (!dev->bulkq) {
+		kfree(dev);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for_each_possible_cpu(cpu) {
+		bq = per_cpu_ptr(dev->bulkq, cpu);
+		bq->obj = dev;
+	}
+
+	dev->dev = dev_get_by_index(net, ifindex);
+	if (!dev->dev) {
+		free_percpu(dev->bulkq);
+		kfree(dev);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev->idx = idx;
+	dev->dtab = dtab;
+
+	return dev;
+}
+
+static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
+				 void *key, void *value, u64 map_flags)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
 	u32 ifindex = *(u32 *)value;
-	struct xdp_bulk_queue *bq;
 	u32 i = *(u32 *)key;
-	int cpu;
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -434,31 +619,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 	if (!ifindex) {
 		dev = NULL;
 	} else {
-		dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node);
-		if (!dev)
-			return -ENOMEM;
-
-		dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
-						sizeof(void *), gfp);
-		if (!dev->bulkq) {
-			kfree(dev);
-			return -ENOMEM;
-		}
-
-		for_each_possible_cpu(cpu) {
-			bq = per_cpu_ptr(dev->bulkq, cpu);
-			bq->obj = dev;
-		}
-
-		dev->dev = dev_get_by_index(net, ifindex);
-		if (!dev->dev) {
-			free_percpu(dev->bulkq);
-			kfree(dev);
-			return -EINVAL;
-		}
-
-		dev->bit = i;
-		dev->dtab = dtab;
+		dev = __dev_map_alloc_node(net, dtab, ifindex, i);
+		if (IS_ERR(dev))
+			return PTR_ERR(dev);
 	}
 
 	/* Use call_rcu() here to ensure rcu critical sections have completed
@@ -472,6 +635,70 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 	return 0;
 }
 
+static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	return __dev_map_update_elem(current->nsproxy->net_ns,
+				     map, key, value, map_flags);
+}
+
+static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
+				     void *key, void *value, u64 map_flags)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *dev, *old_dev;
+	u32 ifindex = *(u32 *)value;
+	u32 idx = *(u32 *)key;
+	unsigned long flags;
+	int err = -EEXIST;
+
+	if (unlikely(map_flags > BPF_EXIST || !ifindex))
+		return -EINVAL;
+
+	spin_lock_irqsave(&dtab->index_lock, flags);
+
+	old_dev = __dev_map_hash_lookup_elem(map, idx);
+	if (old_dev && (map_flags & BPF_NOEXIST))
+		goto out_err;
+
+	dev = __dev_map_alloc_node(net, dtab, ifindex, idx);
+	if (IS_ERR(dev)) {
+		err = PTR_ERR(dev);
+		goto out_err;
+	}
+
+	if (old_dev) {
+		hlist_del_rcu(&old_dev->index_hlist);
+	} else {
+		if (dtab->items >= dtab->map.max_entries) {
+			spin_unlock_irqrestore(&dtab->index_lock, flags);
+			call_rcu(&dev->rcu, __dev_map_entry_free);
+			return -E2BIG;
+		}
+		dtab->items++;
+	}
+
+	hlist_add_head_rcu(&dev->index_hlist,
+			   dev_map_index_hash(dtab, idx));
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+
+	if (old_dev)
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+
+	return 0;
+
+out_err:
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+	return err;
+}
+
+static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
+				   u64 map_flags)
+{
+	return __dev_map_hash_update_elem(current->nsproxy->net_ns,
+					 map, key, value, map_flags);
+}
+
 const struct bpf_map_ops dev_map_ops = {
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
@@ -482,6 +709,16 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_check_btf = map_check_no_btf,
 };
 
+const struct bpf_map_ops dev_map_hash_ops = {
+	.map_alloc = dev_map_alloc,
+	.map_free = dev_map_free,
+	.map_get_next_key = dev_map_hash_get_next_key,
+	.map_lookup_elem = dev_map_hash_lookup_elem,
+	.map_update_elem = dev_map_hash_update_elem,
+	.map_delete_elem = dev_map_hash_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};
+
 static int dev_map_notification(struct notifier_block *notifier,
 				ulong event, void *ptr)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 272071e9112f..82eabd4e38ad 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -683,8 +683,8 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 }
 
 /* map_idr_lock should have been held */
-static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
-					    bool uref)
+static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map,
+					      bool uref)
 {
 	int refold;
 
@@ -704,6 +704,16 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
 	return map;
 }
 
+struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
+{
+	spin_lock_bh(&map_idr_lock);
+	map = __bpf_map_inc_not_zero(map, uref);
+	spin_unlock_bh(&map_idr_lock);
+
+	return map;
+}
+EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero);
+
 int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 {
 	return -ENOTSUPP;
@@ -1619,6 +1629,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT |
 				 BPF_F_ANY_ALIGNMENT |
+				 BPF_F_TEST_STATE_FREQ |
 				 BPF_F_TEST_RND_HI32))
 		return -EINVAL;
 
@@ -2183,7 +2194,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 	spin_lock_bh(&map_idr_lock);
 	map = idr_find(&map_idr, id);
 	if (map)
-		map = bpf_map_inc_not_zero(map, true);
+		map = __bpf_map_inc_not_zero(map, true);
 	else
 		map = ERR_PTR(-ENOENT);
 	spin_unlock_bh(&map_idr_lock);
@@ -2880,6 +2891,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_obj_get_next_id(&attr, uattr,
 					  &map_idr, &map_idr_lock);
 		break;
+	case BPF_BTF_GET_NEXT_ID:
+		err = bpf_obj_get_next_id(&attr, uattr,
+					  &btf_idr, &btf_idr_lock);
+		break;
 	case BPF_PROG_GET_FD_BY_ID:
 		err = bpf_prog_get_fd_by_id(&attr);
 		break;
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
new file mode 100644
index 000000000000..7ae5dddd1fe6
--- /dev/null
+++ b/kernel/bpf/sysfs_btf.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Provide kernel BTF information for introspection and use by eBPF tools.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/init.h>
+#include <linux/sysfs.h>
+
+/* See scripts/link-vmlinux.sh, gen_btf() func for details */
+extern char __weak _binary__btf_vmlinux_bin_start[];
+extern char __weak _binary__btf_vmlinux_bin_end[];
+
+static ssize_t
+btf_vmlinux_read(struct file *file, struct kobject *kobj,
+		 struct bin_attribute *bin_attr,
+		 char *buf, loff_t off, size_t len)
+{
+	memcpy(buf, _binary__btf_vmlinux_bin_start + off, len);
+	return len;
+}
+
+static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
+	.attr = { .name = "vmlinux", .mode = 0444, },
+	.read = btf_vmlinux_read,
+};
+
+static struct kobject *btf_kobj;
+
+static int __init btf_vmlinux_init(void)
+{
+	if (!_binary__btf_vmlinux_bin_start)
+		return 0;
+
+	btf_kobj = kobject_create_and_add("btf", kernel_kobj);
+	if (!btf_kobj)
+		return -ENOMEM;
+
+	bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end -
+				    _binary__btf_vmlinux_bin_start;
+
+	return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
+}
+
+subsys_initcall(btf_vmlinux_init);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c36a719fee6d..ffc3e53f5300 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3463,6 +3463,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 			goto error;
 		break;
 	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
 		if (func_id != BPF_FUNC_redirect_map &&
 		    func_id != BPF_FUNC_map_lookup_elem)
 			goto error;
@@ -3545,6 +3546,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		break;
 	case BPF_FUNC_redirect_map:
 		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+		    map->map_type != BPF_MAP_TYPE_DEVMAP_HASH &&
 		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
 		    map->map_type != BPF_MAP_TYPE_XSKMAP)
 			goto error;
@@ -7226,7 +7228,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	struct bpf_verifier_state_list *sl, **pprev;
 	struct bpf_verifier_state *cur = env->cur_state, *new;
 	int i, j, err, states_cnt = 0;
-	bool add_new_state = false;
+	bool add_new_state = env->test_state_freq ? true : false;
 
 	cur->last_insn_idx = env->prev_insn_idx;
 	if (!env->insn_aux_data[insn_idx].prune_point)
@@ -8622,8 +8624,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 
 		if (is_narrower_load && size < target_size) {
-			u8 shift = bpf_ctx_narrow_load_shift(off, size,
-							     size_default);
+			u8 shift = bpf_ctx_narrow_access_offset(
+				off, size, size_default) * 8;
 			if (ctx_field_size <= 4) {
 				if (shift)
 					insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
@@ -9266,6 +9268,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 
 	env->allow_ptr_leaks = is_priv;
 
+	if (is_priv)
+		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
+
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 9bb96ace9fa1..942c662e2eed 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -13,8 +13,71 @@ struct xsk_map {
 	struct bpf_map map;
 	struct xdp_sock **xsk_map;
 	struct list_head __percpu *flush_list;
+	spinlock_t lock; /* Synchronize map updates */
 };
 
+int xsk_map_inc(struct xsk_map *map)
+{
+	struct bpf_map *m = &map->map;
+
+	m = bpf_map_inc(m, false);
+	return PTR_ERR_OR_ZERO(m);
+}
+
+void xsk_map_put(struct xsk_map *map)
+{
+	bpf_map_put(&map->map);
+}
+
+static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
+					       struct xdp_sock **map_entry)
+{
+	struct xsk_map_node *node;
+	int err;
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
+	if (!node)
+		return NULL;
+
+	err = xsk_map_inc(map);
+	if (err) {
+		kfree(node);
+		return ERR_PTR(err);
+	}
+
+	node->map = map;
+	node->map_entry = map_entry;
+	return node;
+}
+
+static void xsk_map_node_free(struct xsk_map_node *node)
+{
+	xsk_map_put(node->map);
+	kfree(node);
+}
+
+static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
+{
+	spin_lock_bh(&xs->map_list_lock);
+	list_add_tail(&node->node, &xs->map_list);
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
+static void xsk_map_sock_delete(struct xdp_sock *xs,
+				struct xdp_sock **map_entry)
+{
+	struct xsk_map_node *n, *tmp;
+
+	spin_lock_bh(&xs->map_list_lock);
+	list_for_each_entry_safe(n, tmp, &xs->map_list, node) {
+		if (map_entry == n->map_entry) {
+			list_del(&n->node);
+			xsk_map_node_free(n);
+		}
+	}
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
 	struct xsk_map *m;
@@ -34,6 +97,7 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&m->map, attr);
+	spin_lock_init(&m->lock);
 
 	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
 	cost += sizeof(struct list_head) * num_possible_cpus();
@@ -71,21 +135,9 @@ free_m:
 static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	int i;
 
 	bpf_clear_redirect_map(map);
 	synchronize_net();
-
-	for (i = 0; i < map->max_entries; i++) {
-		struct xdp_sock *xs;
-
-		xs = m->xsk_map[i];
-		if (!xs)
-			continue;
-
-		sock_put((struct sock *)xs);
-	}
-
 	free_percpu(m->flush_list);
 	bpf_map_area_free(m->xsk_map);
 	kfree(m);
@@ -164,8 +216,9 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *xs, *old_xs, **map_entry;
 	u32 i = *(u32 *)key, fd = *(u32 *)value;
-	struct xdp_sock *xs, *old_xs;
+	struct xsk_map_node *node;
 	struct socket *sock;
 	int err;
 
@@ -173,8 +226,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EINVAL;
 	if (unlikely(i >= m->map.max_entries))
 		return -E2BIG;
-	if (unlikely(map_flags == BPF_NOEXIST))
-		return -EEXIST;
 
 	sock = sockfd_lookup(fd, &err);
 	if (!sock)
@@ -192,32 +243,70 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EOPNOTSUPP;
 	}
 
-	sock_hold(sock->sk);
+	map_entry = &m->xsk_map[i];
+	node = xsk_map_node_alloc(m, map_entry);
+	if (IS_ERR(node)) {
+		sockfd_put(sock);
+		return PTR_ERR(node);
+	}
 
-	old_xs = xchg(&m->xsk_map[i], xs);
+	spin_lock_bh(&m->lock);
+	old_xs = READ_ONCE(*map_entry);
+	if (old_xs == xs) {
+		err = 0;
+		goto out;
+	} else if (old_xs && map_flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto out;
+	} else if (!old_xs && map_flags == BPF_EXIST) {
+		err = -ENOENT;
+		goto out;
+	}
+	xsk_map_sock_add(xs, node);
+	WRITE_ONCE(*map_entry, xs);
 	if (old_xs)
-		sock_put((struct sock *)old_xs);
-
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
 	sockfd_put(sock);
 	return 0;
+
+out:
+	spin_unlock_bh(&m->lock);
+	sockfd_put(sock);
+	xsk_map_node_free(node);
+	return err;
 }
 
 static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *old_xs;
+	struct xdp_sock *old_xs, **map_entry;
 	int k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;
 
-	old_xs = xchg(&m->xsk_map[k], NULL);
+	spin_lock_bh(&m->lock);
+	map_entry = &m->xsk_map[k];
+	old_xs = xchg(map_entry, NULL);
 	if (old_xs)
-		sock_put((struct sock *)old_xs);
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
 
 	return 0;
 }
 
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock **map_entry)
+{
+	spin_lock_bh(&map->lock);
+	if (READ_ONCE(*map_entry) == xs) {
+		WRITE_ONCE(*map_entry, NULL);
+		xsk_map_sock_delete(xs, map_entry);
+	}
+	spin_unlock_bh(&map->lock);
+}
+
 const struct bpf_map_ops xsk_map_ops = {
 	.map_alloc = xsk_map_alloc,
 	.map_free = xsk_map_free,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6a64d7772870..e08527f50d2a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -520,7 +520,8 @@ config BPF_EVENTS
 	bool
 	default y
 	help
-	  This allows the user to attach BPF programs to kprobe events.
+	  This allows the user to attach BPF programs to kprobe, uprobe, and
+	  tracepoint events.
 
 config DYNAMIC_EVENTS
 	def_bool n