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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-01-17

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add initial BPF map offloading for nfp driver. Currently only
   programs were supported so far w/o being able to access maps.
   Offloaded programs are right now only allowed to perform map
   lookups, and control path is responsible for populating the
   maps. BPF core infrastructure along with nfp implementation is
   provided, from Jakub.

2) Various follow-ups to Josef's BPF error injections. More
   specifically that includes: properly check whether the error
   injectable event is on function entry or not, remove the percpu
   bpf_kprobe_override and rather compare instruction pointer
   with original one, separate error-injection from kprobes since
   it's not limited to it, add injectable error types in order to
   specify what is the expected type of failure, and last but not
   least also support the kernel's fault injection framework, all
   from Masami.

3) Various misc improvements and cleanups to the libbpf Makefile.
   That is, fix permissions when installing BPF header files, remove
   unused variables and functions, and also install the libbpf.h
   header, from Jesper.

4) When offloading to nfp JIT and the BPF insn is unsupported in the
   JIT, then reject right at verification time. Also fix libbpf with
   regards to ELF section name matching by properly treating the
   program type as prefix. Both from Quentin.

5) Add -DPACKAGE to bpftool when including bfd.h for the disassembler.
   This is needed, for example, when building libfd from source as
   bpftool doesn't supply a config.h for bfd.h. Fix from Jiong.

6) xdp_convert_ctx_access() is simplified since it doesn't need to
   set target size during verification, from Jesper.

7) Let bpftool properly recognize BPF_PROG_TYPE_CGROUP_DEVICE
   program types, from Roman.

8) Various functions in BPF cpumap were not declared static, from Wei.

9) Fix a double semicolon in BPF samples, from Luis.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

18 files changed, 730 insertions, 318 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 172d151d429c..f85ae5dfa474 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_KCOV) += kcov.o
 obj-$(CONFIG_KPROBES) += kprobes.o
+obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index ce5b669003b2..fbfdada6caee 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -94,13 +94,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 	if (!cmap)
 		return ERR_PTR(-ENOMEM);
 
-	/* mandatory map attributes */
-	cmap->map.map_type = attr->map_type;
-	cmap->map.key_size = attr->key_size;
-	cmap->map.value_size = attr->value_size;
-	cmap->map.max_entries = attr->max_entries;
-	cmap->map.map_flags = attr->map_flags;
-	cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+	bpf_map_init_from_attr(&cmap->map, attr);
 
 	/* Pre-limit array size based on NR_CPUS, not final CPU check */
 	if (cmap->map.max_entries > NR_CPUS) {
@@ -143,7 +137,7 @@ free_cmap:
 	return ERR_PTR(err);
 }
 
-void __cpu_map_queue_destructor(void *ptr)
+static void __cpu_map_queue_destructor(void *ptr)
 {
 	/* The tear-down procedure should have made sure that queue is
 	 * empty.  See __cpu_map_entry_replace() and work-queue
@@ -222,8 +216,8 @@ static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
 	return xdp_pkt;
 }
 
-struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
-				  struct xdp_pkt *xdp_pkt)
+static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+					 struct xdp_pkt *xdp_pkt)
 {
 	unsigned int frame_size;
 	void *pkt_data_start;
@@ -337,7 +331,8 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
+						       int map_id)
 {
 	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
@@ -395,7 +390,7 @@ free_rcu:
 	return NULL;
 }
 
-void __cpu_map_entry_free(struct rcu_head *rcu)
+static void __cpu_map_entry_free(struct rcu_head *rcu)
 {
 	struct bpf_cpu_map_entry *rcpu;
 	int cpu;
@@ -438,8 +433,8 @@ void __cpu_map_entry_free(struct rcu_head *rcu)
  * cpu_map_kthread_stop, which waits for an RCU graze period before
  * stopping kthread, emptying the queue.
  */
-void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
-			     u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+				    u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
 {
 	struct bpf_cpu_map_entry *old_rcpu;
 
@@ -451,7 +446,7 @@ void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 	}
 }
 
-int cpu_map_delete_elem(struct bpf_map *map, void *key)
+static int cpu_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	u32 key_cpu = *(u32 *)key;
@@ -464,8 +459,8 @@ int cpu_map_delete_elem(struct bpf_map *map, void *key)
 	return 0;
 }
 
-int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
-				u64 map_flags)
+static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	struct bpf_cpu_map_entry *rcpu;
@@ -502,7 +497,7 @@ int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 	return 0;
 }
 
-void cpu_map_free(struct bpf_map *map)
+static void cpu_map_free(struct bpf_map *map)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	int cpu;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index ebdef54bf7df..565f9ece9115 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -93,13 +93,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	if (!dtab)
 		return ERR_PTR(-ENOMEM);
 
-	/* mandatory map attributes */
-	dtab->map.map_type = attr->map_type;
-	dtab->map.key_size = attr->key_size;
-	dtab->map.value_size = attr->value_size;
-	dtab->map.max_entries = attr->max_entries;
-	dtab->map.map_flags = attr->map_flags;
-	dtab->map.numa_node = bpf_map_attr_numa_node(attr);
+	bpf_map_init_from_attr(&dtab->map, attr);
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
index e0857d016f89..266fe8ee542b 100644
--- a/kernel/bpf/disasm.h
+++ b/kernel/bpf/disasm.h
@@ -29,8 +29,8 @@ extern const char *const bpf_class_string[8];
 
 const char *func_id_name(int id);
 
-typedef void (*bpf_insn_print_t)(struct bpf_verifier_env *env,
-				 const char *, ...);
+typedef __printf(2, 3) void (*bpf_insn_print_t)(struct bpf_verifier_env *env,
+						const char *, ...);
 typedef const char *(*bpf_insn_revmap_call_t)(void *private_data,
 					      const struct bpf_insn *insn);
 typedef const char *(*bpf_insn_print_imm_t)(void *private_data,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3905d4bc5b80..b76828f23b49 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -227,7 +227,7 @@ static int alloc_extra_elems(struct bpf_htab *htab)
 }
 
 /* Called from syscall */
-static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
+static int htab_map_alloc_check(union bpf_attr *attr)
 {
 	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 		       attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
@@ -241,9 +241,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
 	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
 	int numa_node = bpf_map_attr_numa_node(attr);
-	struct bpf_htab *htab;
-	int err, i;
-	u64 cost;
 
 	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
 		     offsetof(struct htab_elem, hash_node.pprev));
@@ -254,40 +251,68 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		/* LRU implementation is much complicated than other
 		 * maps.  Hence, limit to CAP_SYS_ADMIN for now.
 		 */
-		return ERR_PTR(-EPERM);
+		return -EPERM;
 
 	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
 		/* reserved bits should not be used */
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (!lru && percpu_lru)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (lru && !prealloc)
-		return ERR_PTR(-ENOTSUPP);
+		return -ENOTSUPP;
 
 	if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
+
+	/* check sanity of attributes.
+	 * value_size == 0 may be allowed in the future to use map as a set
+	 */
+	if (attr->max_entries == 0 || attr->key_size == 0 ||
+	    attr->value_size == 0)
+		return -EINVAL;
+
+	if (attr->key_size > MAX_BPF_STACK)
+		/* eBPF programs initialize keys on stack, so they cannot be
+		 * larger than max stack size
+		 */
+		return -E2BIG;
+
+	if (attr->value_size >= KMALLOC_MAX_SIZE -
+	    MAX_BPF_STACK - sizeof(struct htab_elem))
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements via bpf syscall. This check also makes
+		 * sure that the elem_size doesn't overflow and it's
+		 * kmalloc-able later in htab_map_update_elem()
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
+static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
+{
+	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+		       attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+	bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
+		    attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+	/* percpu_lru means each cpu has its own LRU list.
+	 * it is different from BPF_MAP_TYPE_PERCPU_HASH where
+	 * the map's value itself is percpu.  percpu_lru has
+	 * nothing to do with the map's value.
+	 */
+	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
+	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+	struct bpf_htab *htab;
+	int err, i;
+	u64 cost;
 
 	htab = kzalloc(sizeof(*htab), GFP_USER);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
-	/* mandatory map attributes */
-	htab->map.map_type = attr->map_type;
-	htab->map.key_size = attr->key_size;
-	htab->map.value_size = attr->value_size;
-	htab->map.max_entries = attr->max_entries;
-	htab->map.map_flags = attr->map_flags;
-	htab->map.numa_node = numa_node;
-
-	/* check sanity of attributes.
-	 * value_size == 0 may be allowed in the future to use map as a set
-	 */
-	err = -EINVAL;
-	if (htab->map.max_entries == 0 || htab->map.key_size == 0 ||
-	    htab->map.value_size == 0)
-		goto free_htab;
+	bpf_map_init_from_attr(&htab->map, attr);
 
 	if (percpu_lru) {
 		/* ensure each CPU's lru list has >=1 elements.
@@ -304,22 +329,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	/* hash table size must be power of 2 */
 	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
 
-	err = -E2BIG;
-	if (htab->map.key_size > MAX_BPF_STACK)
-		/* eBPF programs initialize keys on stack, so they cannot be
-		 * larger than max stack size
-		 */
-		goto free_htab;
-
-	if (htab->map.value_size >= KMALLOC_MAX_SIZE -
-	    MAX_BPF_STACK - sizeof(struct htab_elem))
-		/* if value_size is bigger, the user space won't be able to
-		 * access the elements via bpf syscall. This check also makes
-		 * sure that the elem_size doesn't overflow and it's
-		 * kmalloc-able later in htab_map_update_elem()
-		 */
-		goto free_htab;
-
 	htab->elem_size = sizeof(struct htab_elem) +
 			  round_up(htab->map.key_size, 8);
 	if (percpu)
@@ -327,6 +336,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	else
 		htab->elem_size += round_up(htab->map.value_size, 8);
 
+	err = -E2BIG;
 	/* prevent zero size kmalloc and check for u32 overflow */
 	if (htab->n_buckets == 0 ||
 	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
@@ -1143,6 +1153,7 @@ static void htab_map_free(struct bpf_map *map)
 }
 
 const struct bpf_map_ops htab_map_ops = {
+	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1153,6 +1164,7 @@ const struct bpf_map_ops htab_map_ops = {
 };
 
 const struct bpf_map_ops htab_lru_map_ops = {
+	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1236,6 +1248,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 }
 
 const struct bpf_map_ops htab_percpu_map_ops = {
+	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1245,6 +1258,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 };
 
 const struct bpf_map_ops htab_lru_percpu_map_ops = {
+	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1253,11 +1267,11 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 };
 
-static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
+static int fd_htab_map_alloc_check(union bpf_attr *attr)
 {
 	if (attr->value_size != sizeof(u32))
-		return ERR_PTR(-EINVAL);
-	return htab_map_alloc(attr);
+		return -EINVAL;
+	return htab_map_alloc_check(attr);
 }
 
 static void fd_htab_map_free(struct bpf_map *map)
@@ -1328,7 +1342,7 @@ static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr)
 	if (IS_ERR(inner_map_meta))
 		return inner_map_meta;
 
-	map = fd_htab_map_alloc(attr);
+	map = htab_map_alloc(attr);
 	if (IS_ERR(map)) {
 		bpf_map_meta_free(inner_map_meta);
 		return map;
@@ -1372,6 +1386,7 @@ static void htab_of_map_free(struct bpf_map *map)
 }
 
 const struct bpf_map_ops htab_of_maps_map_ops = {
+	.map_alloc_check = fd_htab_map_alloc_check,
 	.map_alloc = htab_of_map_alloc,
 	.map_free = htab_of_map_free,
 	.map_get_next_key = htab_map_get_next_key,
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 885e45479680..584e02227671 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -522,12 +522,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 
 	/* copy mandatory map attributes */
-	trie->map.map_type = attr->map_type;
-	trie->map.key_size = attr->key_size;
-	trie->map.value_size = attr->value_size;
-	trie->map.max_entries = attr->max_entries;
-	trie->map.map_flags = attr->map_flags;
-	trie->map.numa_node = bpf_map_attr_numa_node(attr);
+	bpf_map_init_from_attr(&trie->map, attr);
 	trie->data_size = attr->key_size -
 			  offsetof(struct bpf_lpm_trie_key, data);
 	trie->max_prefixlen = trie->data_size * 8;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 040d4e0edf3f..a88cebf368bf 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -24,15 +24,27 @@
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
 
-/* Protects bpf_prog_offload_devs and offload members of all progs.
+/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members
+ * of all progs.
  * RTNL lock cannot be taken when holding this lock.
  */
 static DECLARE_RWSEM(bpf_devs_lock);
 static LIST_HEAD(bpf_prog_offload_devs);
+static LIST_HEAD(bpf_map_offload_devs);
+
+static int bpf_dev_offload_check(struct net_device *netdev)
+{
+	if (!netdev)
+		return -EINVAL;
+	if (!netdev->netdev_ops->ndo_bpf)
+		return -EOPNOTSUPP;
+	return 0;
+}
 
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 {
-	struct bpf_dev_offload *offload;
+	struct bpf_prog_offload *offload;
+	int err;
 
 	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
 	    attr->prog_type != BPF_PROG_TYPE_XDP)
@@ -49,12 +61,15 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 
 	offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
 					   attr->prog_ifindex);
-	if (!offload->netdev)
-		goto err_free;
+	err = bpf_dev_offload_check(offload->netdev);
+	if (err)
+		goto err_maybe_put;
 
 	down_write(&bpf_devs_lock);
-	if (offload->netdev->reg_state != NETREG_REGISTERED)
+	if (offload->netdev->reg_state != NETREG_REGISTERED) {
+		err = -EINVAL;
 		goto err_unlock;
+	}
 	prog->aux->offload = offload;
 	list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
 	dev_put(offload->netdev);
@@ -63,16 +78,17 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 	return 0;
 err_unlock:
 	up_write(&bpf_devs_lock);
-	dev_put(offload->netdev);
-err_free:
+err_maybe_put:
+	if (offload->netdev)
+		dev_put(offload->netdev);
 	kfree(offload);
-	return -EINVAL;
+	return err;
 }
 
 static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
 			     struct netdev_bpf *data)
 {
-	struct bpf_dev_offload *offload = prog->aux->offload;
+	struct bpf_prog_offload *offload = prog->aux->offload;
 	struct net_device *netdev;
 
 	ASSERT_RTNL();
@@ -80,8 +96,6 @@ static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
 	if (!offload)
 		return -ENODEV;
 	netdev = offload->netdev;
-	if (!netdev->netdev_ops->ndo_bpf)
-		return -EOPNOTSUPP;
 
 	data->command = cmd;
 
@@ -110,7 +124,7 @@ exit_unlock:
 int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 				 int insn_idx, int prev_insn_idx)
 {
-	struct bpf_dev_offload *offload;
+	struct bpf_prog_offload *offload;
 	int ret = -ENODEV;
 
 	down_read(&bpf_devs_lock);
@@ -124,7 +138,7 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 
 static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 {
-	struct bpf_dev_offload *offload = prog->aux->offload;
+	struct bpf_prog_offload *offload = prog->aux->offload;
 	struct netdev_bpf data = {};
 
 	data.offload.prog = prog;
@@ -238,11 +252,184 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 const struct bpf_prog_ops bpf_offload_prog_ops = {
 };
 
+static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
+			       enum bpf_netdev_command cmd)
+{
+	struct netdev_bpf data = {};
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	data.command = cmd;
+	data.offmap = offmap;
+	/* Caller must make sure netdev is valid */
+	netdev = offmap->netdev;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, &data);
+}
+
+struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_offloaded_map *offmap;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+	if (attr->map_type != BPF_MAP_TYPE_HASH)
+		return ERR_PTR(-EINVAL);
+
+	offmap = kzalloc(sizeof(*offmap), GFP_USER);
+	if (!offmap)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&offmap->map, attr);
+
+	rtnl_lock();
+	down_write(&bpf_devs_lock);
+	offmap->netdev = __dev_get_by_index(net, attr->map_ifindex);
+	err = bpf_dev_offload_check(offmap->netdev);
+	if (err)
+		goto err_unlock;
+
+	err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
+	if (err)
+		goto err_unlock;
+
+	list_add_tail(&offmap->offloads, &bpf_map_offload_devs);
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+
+	return &offmap->map;
+
+err_unlock:
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+	kfree(offmap);
+	return ERR_PTR(err);
+}
+
+static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
+{
+	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
+	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
+	bpf_map_free_id(&offmap->map, true);
+	list_del_init(&offmap->offloads);
+	offmap->netdev = NULL;
+}
+
+void bpf_map_offload_map_free(struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+
+	rtnl_lock();
+	down_write(&bpf_devs_lock);
+	if (offmap->netdev)
+		__bpf_map_offload_destroy(offmap);
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+
+	kfree(offmap);
+}
+
+int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_lookup_elem(offmap, key, value);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_update_elem(struct bpf_map *map,
+				void *key, void *value, u64 flags)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	if (unlikely(flags > BPF_EXIST))
+		return -EINVAL;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_update_elem(offmap, key, value,
+						       flags);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_delete_elem(offmap, key);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_get_next_key(offmap, key, next_key);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap;
+	struct bpf_prog_offload *offload;
+	bool ret;
+
+	if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map))
+		return false;
+
+	down_read(&bpf_devs_lock);
+	offload = prog->aux->offload;
+	offmap = map_to_offmap(map);
+
+	ret = offload && offload->netdev == offmap->netdev;
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+static void bpf_offload_orphan_all_progs(struct net_device *netdev)
+{
+	struct bpf_prog_offload *offload, *tmp;
+
+	list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads)
+		if (offload->netdev == netdev)
+			__bpf_prog_offload_destroy(offload->prog);
+}
+
+static void bpf_offload_orphan_all_maps(struct net_device *netdev)
+{
+	struct bpf_offloaded_map *offmap, *tmp;
+
+	list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads)
+		if (offmap->netdev == netdev)
+			__bpf_map_offload_destroy(offmap);
+}
+
 static int bpf_offload_notification(struct notifier_block *notifier,
 				    ulong event, void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-	struct bpf_dev_offload *offload, *tmp;
 
 	ASSERT_RTNL();
 
@@ -253,11 +440,8 @@ static int bpf_offload_notification(struct notifier_block *notifier,
 			break;
 
 		down_write(&bpf_devs_lock);
-		list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs,
-					 offloads) {
-			if (offload->netdev == netdev)
-				__bpf_prog_offload_destroy(offload->prog);
-		}
+		bpf_offload_orphan_all_progs(netdev);
+		bpf_offload_orphan_all_maps(netdev);
 		up_write(&bpf_devs_lock);
 		break;
 	default:
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 079968680bc3..0314d1783d77 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -513,13 +513,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	if (!stab)
 		return ERR_PTR(-ENOMEM);
 
-	/* mandatory map attributes */
-	stab->map.map_type = attr->map_type;
-	stab->map.key_size = attr->key_size;
-	stab->map.value_size = attr->value_size;
-	stab->map.max_entries = attr->max_entries;
-	stab->map.map_flags = attr->map_flags;
-	stab->map.numa_node = bpf_map_attr_numa_node(attr);
+	bpf_map_init_from_attr(&stab->map, attr);
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 6c63c2222ea8..b0ecf43f5894 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -88,14 +88,10 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (cost >= U32_MAX - PAGE_SIZE)
 		goto free_smap;
 
-	smap->map.map_type = attr->map_type;
-	smap->map.key_size = attr->key_size;
+	bpf_map_init_from_attr(&smap->map, attr);
 	smap->map.value_size = value_size;
-	smap->map.max_entries = attr->max_entries;
-	smap->map.map_flags = attr->map_flags;
 	smap->n_buckets = n_buckets;
 	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
-	smap->map.numa_node = bpf_map_attr_numa_node(attr);
 
 	err = bpf_map_precharge_memlock(smap->map.pages);
 	if (err)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2bac0dc8baba..c691b9e972e3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -94,18 +94,34 @@ static int check_uarg_tail_zero(void __user *uaddr,
 	return 0;
 }
 
+const struct bpf_map_ops bpf_map_offload_ops = {
+	.map_alloc = bpf_map_offload_map_alloc,
+	.map_free = bpf_map_offload_map_free,
+};
+
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 {
+	const struct bpf_map_ops *ops;
 	struct bpf_map *map;
+	int err;
 
-	if (attr->map_type >= ARRAY_SIZE(bpf_map_types) ||
-	    !bpf_map_types[attr->map_type])
+	if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+		return ERR_PTR(-EINVAL);
+	ops = bpf_map_types[attr->map_type];
+	if (!ops)
 		return ERR_PTR(-EINVAL);
 
-	map = bpf_map_types[attr->map_type]->map_alloc(attr);
+	if (ops->map_alloc_check) {
+		err = ops->map_alloc_check(attr);
+		if (err)
+			return ERR_PTR(err);
+	}
+	if (attr->map_ifindex)
+		ops = &bpf_map_offload_ops;
+	map = ops->map_alloc(attr);
 	if (IS_ERR(map))
 		return map;
-	map->ops = bpf_map_types[attr->map_type];
+	map->ops = ops;
 	map->map_type = attr->map_type;
 	return map;
 }
@@ -134,6 +150,16 @@ void bpf_map_area_free(void *area)
 	kvfree(area);
 }
 
+void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
+{
+	map->map_type = attr->map_type;
+	map->key_size = attr->key_size;
+	map->value_size = attr->value_size;
+	map->max_entries = attr->max_entries;
+	map->map_flags = attr->map_flags;
+	map->numa_node = bpf_map_attr_numa_node(attr);
+}
+
 int bpf_map_precharge_memlock(u32 pages)
 {
 	struct user_struct *user = get_current_user();
@@ -189,16 +215,25 @@ static int bpf_map_alloc_id(struct bpf_map *map)
 	return id > 0 ? 0 : id;
 }
 
-static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
+void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
 {
 	unsigned long flags;
 
+	/* Offloaded maps are removed from the IDR store when their device
+	 * disappears - even if someone holds an fd to them they are unusable,
+	 * the memory is gone, all ops will fail; they are simply waiting for
+	 * refcnt to drop to be freed.
+	 */
+	if (!map->id)
+		return;
+
 	if (do_idr_lock)
 		spin_lock_irqsave(&map_idr_lock, flags);
 	else
 		__acquire(&map_idr_lock);
 
 	idr_remove(&map_idr, map->id);
+	map->id = 0;
 
 	if (do_idr_lock)
 		spin_unlock_irqrestore(&map_idr_lock, flags);
@@ -378,7 +413,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 	return 0;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_name
+#define BPF_MAP_CREATE_LAST_FIELD map_ifindex
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -566,8 +601,10 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!value)
 		goto free_key;
 
-	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
-	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+	if (bpf_map_is_dev_bound(map)) {
+		err = bpf_map_offload_lookup_elem(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value);
@@ -654,7 +691,10 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_value;
 
 	/* Need to create a kthread, thus must support schedule */
-	if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+	if (bpf_map_is_dev_bound(map)) {
+		err = bpf_map_offload_update_elem(map, key, value, attr->flags);
+		goto out;
+	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		goto out;
 	}
@@ -731,6 +771,11 @@ static int map_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
+	if (bpf_map_is_dev_bound(map)) {
+		err = bpf_map_offload_delete_elem(map, key);
+		goto out;
+	}
+
 	preempt_disable();
 	__this_cpu_inc(bpf_prog_active);
 	rcu_read_lock();
@@ -738,7 +783,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	rcu_read_unlock();
 	__this_cpu_dec(bpf_prog_active);
 	preempt_enable();
-
+out:
 	if (!err)
 		trace_bpf_map_delete_elem(map, ufd, key);
 	kfree(key);
@@ -788,9 +833,15 @@ static int map_get_next_key(union bpf_attr *attr)
 	if (!next_key)
 		goto free_key;
 
+	if (bpf_map_is_dev_bound(map)) {
+		err = bpf_map_offload_get_next_key(map, key, next_key);
+		goto out;
+	}
+
 	rcu_read_lock();
 	err = map->ops->map_get_next_key(map, key, next_key);
 	rcu_read_unlock();
+out:
 	if (err)
 		goto free_next_key;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48b61caa94cb..ceabb394d2dc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4816,6 +4816,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 	}
+
+	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
+	    !bpf_offload_dev_match(prog, map)) {
+		verbose(env, "offload device mismatch between prog and map\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
new file mode 100644
index 000000000000..21b0122cb39c
--- /dev/null
+++ b/kernel/fail_function.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fail_function.c: Function-based error injection
+ */
+#include <linux/error-injection.h>
+#include <linux/debugfs.h>
+#include <linux/fault-inject.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
+
+struct fei_attr {
+	struct list_head list;
+	struct kprobe kp;
+	unsigned long retval;
+};
+static DEFINE_MUTEX(fei_lock);
+static LIST_HEAD(fei_attr_list);
+static DECLARE_FAULT_ATTR(fei_fault_attr);
+static struct dentry *fei_debugfs_dir;
+
+static unsigned long adjust_error_retval(unsigned long addr, unsigned long retv)
+{
+	switch (get_injectable_error_type(addr)) {
+	case EI_ETYPE_NULL:
+		if (retv != 0)
+			return 0;
+		break;
+	case EI_ETYPE_ERRNO:
+		if (retv < (unsigned long)-MAX_ERRNO)
+			return (unsigned long)-EINVAL;
+		break;
+	case EI_ETYPE_ERRNO_NULL:
+		if (retv != 0 && retv < (unsigned long)-MAX_ERRNO)
+			return (unsigned long)-EINVAL;
+		break;
+	}
+
+	return retv;
+}
+
+static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
+{
+	struct fei_attr *attr;
+
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	if (attr) {
+		attr->kp.symbol_name = kstrdup(sym, GFP_KERNEL);
+		if (!attr->kp.symbol_name) {
+			kfree(attr);
+			return NULL;
+		}
+		attr->kp.pre_handler = fei_kprobe_handler;
+		attr->retval = adjust_error_retval(addr, 0);
+		INIT_LIST_HEAD(&attr->list);
+	}
+	return attr;
+}
+
+static void fei_attr_free(struct fei_attr *attr)
+{
+	if (attr) {
+		kfree(attr->kp.symbol_name);
+		kfree(attr);
+	}
+}
+
+static struct fei_attr *fei_attr_lookup(const char *sym)
+{
+	struct fei_attr *attr;
+
+	list_for_each_entry(attr, &fei_attr_list, list) {
+		if (!strcmp(attr->kp.symbol_name, sym))
+			return attr;
+	}
+
+	return NULL;
+}
+
+static bool fei_attr_is_valid(struct fei_attr *_attr)
+{
+	struct fei_attr *attr;
+
+	list_for_each_entry(attr, &fei_attr_list, list) {
+		if (attr == _attr)
+			return true;
+	}
+
+	return false;
+}
+
+static int fei_retval_set(void *data, u64 val)
+{
+	struct fei_attr *attr = data;
+	unsigned long retv = (unsigned long)val;
+	int err = 0;
+
+	mutex_lock(&fei_lock);
+	/*
+	 * Since this operation can be done after retval file is removed,
+	 * It is safer to check the attr is still valid before accessing
+	 * its member.
+	 */
+	if (!fei_attr_is_valid(attr)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (attr->kp.addr) {
+		if (adjust_error_retval((unsigned long)attr->kp.addr,
+					val) != retv)
+			err = -EINVAL;
+	}
+	if (!err)
+		attr->retval = val;
+out:
+	mutex_unlock(&fei_lock);
+
+	return err;
+}
+
+static int fei_retval_get(void *data, u64 *val)
+{
+	struct fei_attr *attr = data;
+	int err = 0;
+
+	mutex_lock(&fei_lock);
+	/* Here we also validate @attr to ensure it still exists. */
+	if (!fei_attr_is_valid(attr))
+		err = -ENOENT;
+	else
+		*val = attr->retval;
+	mutex_unlock(&fei_lock);
+
+	return err;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fei_retval_ops, fei_retval_get, fei_retval_set,
+			 "%llx\n");
+
+static int fei_debugfs_add_attr(struct fei_attr *attr)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir(attr->kp.symbol_name, fei_debugfs_dir);
+	if (!dir)
+		return -ENOMEM;
+
+	if (!debugfs_create_file("retval", 0600, dir, attr, &fei_retval_ops)) {
+		debugfs_remove_recursive(dir);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void fei_debugfs_remove_attr(struct fei_attr *attr)
+{
+	struct dentry *dir;
+
+	dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir);
+	if (dir)
+		debugfs_remove_recursive(dir);
+}
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
+{
+	struct fei_attr *attr = container_of(kp, struct fei_attr, kp);
+
+	if (should_fail(&fei_fault_attr, 1)) {
+		regs_set_return_value(regs, attr->retval);
+		override_function_with_return(regs);
+		/* Kprobe specific fixup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+
+	return 0;
+}
+NOKPROBE_SYMBOL(fei_kprobe_handler)
+
+static void *fei_seq_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&fei_lock);
+	return seq_list_start(&fei_attr_list, *pos);
+}
+
+static void fei_seq_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&fei_lock);
+}
+
+static void *fei_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &fei_attr_list, pos);
+}
+
+static int fei_seq_show(struct seq_file *m, void *v)
+{
+	struct fei_attr *attr = list_entry(v, struct fei_attr, list);
+
+	seq_printf(m, "%pf\n", attr->kp.addr);
+	return 0;
+}
+
+static const struct seq_operations fei_seq_ops = {
+	.start	= fei_seq_start,
+	.next	= fei_seq_next,
+	.stop	= fei_seq_stop,
+	.show	= fei_seq_show,
+};
+
+static int fei_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fei_seq_ops);
+}
+
+static void fei_attr_remove(struct fei_attr *attr)
+{
+	fei_debugfs_remove_attr(attr);
+	unregister_kprobe(&attr->kp);
+	list_del(&attr->list);
+	fei_attr_free(attr);
+}
+
+static void fei_attr_remove_all(void)
+{
+	struct fei_attr *attr, *n;
+
+	list_for_each_entry_safe(attr, n, &fei_attr_list, list) {
+		fei_attr_remove(attr);
+	}
+}
+
+static ssize_t fei_write(struct file *file, const char __user *buffer,
+			 size_t count, loff_t *ppos)
+{
+	struct fei_attr *attr;
+	unsigned long addr;
+	char *buf, *sym;
+	int ret;
+
+	/* cut off if it is too long */
+	if (count > KSYM_NAME_LEN)
+		count = KSYM_NAME_LEN;
+	buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, buffer, count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	buf[count] = '\0';
+	sym = strstrip(buf);
+
+	mutex_lock(&fei_lock);
+
+	/* Writing just spaces will remove all injection points */
+	if (sym[0] == '\0') {
+		fei_attr_remove_all();
+		ret = count;
+		goto out;
+	}
+	/* Writing !function will remove one injection point */
+	if (sym[0] == '!') {
+		attr = fei_attr_lookup(sym + 1);
+		if (!attr) {
+			ret = -ENOENT;
+			goto out;
+		}
+		fei_attr_remove(attr);
+		ret = count;
+		goto out;
+	}
+
+	addr = kallsyms_lookup_name(sym);
+	if (!addr) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (!within_error_injection_list(addr)) {
+		ret = -ERANGE;
+		goto out;
+	}
+	if (fei_attr_lookup(sym)) {
+		ret = -EBUSY;
+		goto out;
+	}
+	attr = fei_attr_new(sym, addr);
+	if (!attr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = register_kprobe(&attr->kp);
+	if (!ret)
+		ret = fei_debugfs_add_attr(attr);
+	if (ret < 0)
+		fei_attr_remove(attr);
+	else {
+		list_add_tail(&attr->list, &fei_attr_list);
+		ret = count;
+	}
+out:
+	kfree(buf);
+	mutex_unlock(&fei_lock);
+	return ret;
+}
+
+static const struct file_operations fei_ops = {
+	.open =		fei_open,
+	.read =		seq_read,
+	.write =	fei_write,
+	.llseek =	seq_lseek,
+	.release =	seq_release,
+};
+
+static int __init fei_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_function", NULL,
+					&fei_fault_attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	/* injectable attribute is just a symlink of error_inject/list */
+	if (!debugfs_create_symlink("injectable", dir,
+				    "../error_injection/list"))
+		goto error;
+
+	if (!debugfs_create_file("inject", 0600, dir, NULL, &fei_ops))
+		goto error;
+
+	fei_debugfs_dir = dir;
+
+	return 0;
+error:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
+}
+
+late_initcall(fei_debugfs_init);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index b4aab48ad258..da2ccf142358 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -83,16 +83,6 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
 	return &(kretprobe_table_locks[hash].lock);
 }
 
-/* List of symbols that can be overriden for error injection. */
-static LIST_HEAD(kprobe_error_injection_list);
-static DEFINE_MUTEX(kprobe_ei_mutex);
-struct kprobe_ei_entry {
-	struct list_head list;
-	unsigned long start_addr;
-	unsigned long end_addr;
-	void *priv;
-};
-
 /* Blacklist -- list of struct kprobe_blacklist_entry */
 static LIST_HEAD(kprobe_blacklist);
 
@@ -1404,17 +1394,6 @@ bool within_kprobe_blacklist(unsigned long addr)
 	return false;
 }
 
-bool within_kprobe_error_injection_list(unsigned long addr)
-{
-	struct kprobe_ei_entry *ent;
-
-	list_for_each_entry(ent, &kprobe_error_injection_list, list) {
-		if (addr >= ent->start_addr && addr < ent->end_addr)
-			return true;
-	}
-	return false;
-}
-
 /*
  * If we have a symbol_name argument, look it up and add the offset field
  * to it. This way, we can specify a relative address to a symbol.
@@ -2189,86 +2168,6 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 	return 0;
 }
 
-#ifdef CONFIG_BPF_KPROBE_OVERRIDE
-/* Markers of the _kprobe_error_inject_list section */
-extern unsigned long __start_kprobe_error_inject_list[];
-extern unsigned long __stop_kprobe_error_inject_list[];
-
-/*
- * Lookup and populate the kprobe_error_injection_list.
- *
- * For safety reasons we only allow certain functions to be overriden with
- * bpf_error_injection, so we need to populate the list of the symbols that have
- * been marked as safe for overriding.
- */
-static void populate_kprobe_error_injection_list(unsigned long *start,
-						 unsigned long *end,
-						 void *priv)
-{
-	unsigned long *iter;
-	struct kprobe_ei_entry *ent;
-	unsigned long entry, offset = 0, size = 0;
-
-	mutex_lock(&kprobe_ei_mutex);
-	for (iter = start; iter < end; iter++) {
-		entry = arch_deref_entry_point((void *)*iter);
-
-		if (!kernel_text_address(entry) ||
-		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
-			pr_err("Failed to find error inject entry at %p\n",
-				(void *)entry);
-			continue;
-		}
-
-		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
-		if (!ent)
-			break;
-		ent->start_addr = entry;
-		ent->end_addr = entry + size;
-		ent->priv = priv;
-		INIT_LIST_HEAD(&ent->list);
-		list_add_tail(&ent->list, &kprobe_error_injection_list);
-	}
-	mutex_unlock(&kprobe_ei_mutex);
-}
-
-static void __init populate_kernel_kprobe_ei_list(void)
-{
-	populate_kprobe_error_injection_list(__start_kprobe_error_inject_list,
-					     __stop_kprobe_error_inject_list,
-					     NULL);
-}
-
-static void module_load_kprobe_ei_list(struct module *mod)
-{
-	if (!mod->num_kprobe_ei_funcs)
-		return;
-	populate_kprobe_error_injection_list(mod->kprobe_ei_funcs,
-					     mod->kprobe_ei_funcs +
-					     mod->num_kprobe_ei_funcs, mod);
-}
-
-static void module_unload_kprobe_ei_list(struct module *mod)
-{
-	struct kprobe_ei_entry *ent, *n;
-	if (!mod->num_kprobe_ei_funcs)
-		return;
-
-	mutex_lock(&kprobe_ei_mutex);
-	list_for_each_entry_safe(ent, n, &kprobe_error_injection_list, list) {
-		if (ent->priv == mod) {
-			list_del_init(&ent->list);
-			kfree(ent);
-		}
-	}
-	mutex_unlock(&kprobe_ei_mutex);
-}
-#else
-static inline void __init populate_kernel_kprobe_ei_list(void) {}
-static inline void module_load_kprobe_ei_list(struct module *m) {}
-static inline void module_unload_kprobe_ei_list(struct module *m) {}
-#endif
-
 /* Module notifier call back, checking kprobes on the module */
 static int kprobes_module_callback(struct notifier_block *nb,
 				   unsigned long val, void *data)
@@ -2279,11 +2178,6 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	unsigned int i;
 	int checkcore = (val == MODULE_STATE_GOING);
 
-	if (val == MODULE_STATE_COMING)
-		module_load_kprobe_ei_list(mod);
-	else if (val == MODULE_STATE_GOING)
-		module_unload_kprobe_ei_list(mod);
-
 	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
 		return NOTIFY_DONE;
 
@@ -2346,8 +2240,6 @@ static int __init init_kprobes(void)
 		pr_err("Please take care of using kprobes.\n");
 	}
 
-	populate_kernel_kprobe_ei_list();
-
 	if (kretprobe_blacklist_size) {
 		/* lookup the function address from its name */
 		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
@@ -2515,56 +2407,6 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = {
 	.release        = seq_release,
 };
 
-/*
- * kprobes/error_injection_list -- shows which functions can be overriden for
- * error injection.
- * */
-static void *kprobe_ei_seq_start(struct seq_file *m, loff_t *pos)
-{
-	mutex_lock(&kprobe_ei_mutex);
-	return seq_list_start(&kprobe_error_injection_list, *pos);
-}
-
-static void kprobe_ei_seq_stop(struct seq_file *m, void *v)
-{
-	mutex_unlock(&kprobe_ei_mutex);
-}
-
-static void *kprobe_ei_seq_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	return seq_list_next(v, &kprobe_error_injection_list, pos);
-}
-
-static int kprobe_ei_seq_show(struct seq_file *m, void *v)
-{
-	char buffer[KSYM_SYMBOL_LEN];
-	struct kprobe_ei_entry *ent =
-		list_entry(v, struct kprobe_ei_entry, list);
-
-	sprint_symbol(buffer, ent->start_addr);
-	seq_printf(m, "%s\n", buffer);
-	return 0;
-}
-
-static const struct seq_operations kprobe_ei_seq_ops = {
-	.start = kprobe_ei_seq_start,
-	.next  = kprobe_ei_seq_next,
-	.stop  = kprobe_ei_seq_stop,
-	.show  = kprobe_ei_seq_show,
-};
-
-static int kprobe_ei_open(struct inode *inode, struct file *filp)
-{
-	return seq_open(filp, &kprobe_ei_seq_ops);
-}
-
-static const struct file_operations debugfs_kprobe_ei_ops = {
-	.open           = kprobe_ei_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
 static void arm_all_kprobes(void)
 {
 	struct hlist_head *head;
@@ -2706,11 +2548,6 @@ static int __init debugfs_kprobe_init(void)
 	if (!file)
 		goto error;
 
-	file = debugfs_create_file("error_injection_list", 0444, dir, NULL,
-				  &debugfs_kprobe_ei_ops);
-	if (!file)
-		goto error;
-
 	return 0;
 
 error:
diff --git a/kernel/module.c b/kernel/module.c
index bd695bfdc5c4..601494d4b7ea 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3118,10 +3118,10 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					     sizeof(*mod->ftrace_callsites),
 					     &mod->num_ftrace_callsites);
 #endif
-#ifdef CONFIG_BPF_KPROBE_OVERRIDE
-	mod->kprobe_ei_funcs = section_objs(info, "_kprobe_error_inject_list",
-					    sizeof(*mod->kprobe_ei_funcs),
-					    &mod->num_kprobe_ei_funcs);
+#ifdef CONFIG_FUNCTION_ERROR_INJECTION
+	mod->ei_funcs = section_objs(info, "_error_injection_whitelist",
+					    sizeof(*mod->ei_funcs),
+					    &mod->num_ei_funcs);
 #endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index ae3a2d519e50..7114c885a78a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -533,9 +533,7 @@ config FUNCTION_PROFILER
 config BPF_KPROBE_OVERRIDE
 	bool "Enable BPF programs to override a kprobed function"
 	depends on BPF_EVENTS
-	depends on KPROBES_ON_FTRACE
-	depends on HAVE_KPROBE_OVERRIDE
-	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on FUNCTION_ERROR_INJECTION
 	default n
 	help
 	 Allows BPF to override the execution of a probed function and
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f6d2327ecb59..f274468cbc45 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -14,7 +14,7 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/kprobes.h>
-#include <asm/kprobes.h>
+#include <linux/error-injection.h>
 
 #include "trace_probe.h"
 #include "trace.h"
@@ -83,9 +83,8 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
 {
-	__this_cpu_write(bpf_kprobe_override, 1);
 	regs_set_return_value(regs, rc);
-	arch_ftrace_kprobe_override_function(regs);
+	override_function_with_return(regs);
 	return 0;
 }
 
@@ -800,11 +799,11 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 	int ret = -EEXIST;
 
 	/*
-	 * Kprobe override only works for ftrace based kprobes, and only if they
-	 * are on the opt-in list.
+	 * Kprobe override only works if they are on the function entry,
+	 * and only if they are on the opt-in list.
 	 */
 	if (prog->kprobe_override &&
-	    (!trace_kprobe_ftrace(event->tp_event) ||
+	    (!trace_kprobe_on_func_entry(event->tp_event) ||
 	     !trace_kprobe_error_injectable(event->tp_event)))
 		return -EINVAL;
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 91f4b57dab82..1fad24acd444 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <linux/rculist.h>
+#include <linux/error-injection.h>
 
 #include "trace_probe.h"
 
@@ -42,8 +43,6 @@ struct trace_kprobe {
 	(offsetof(struct trace_kprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
-DEFINE_PER_CPU(int, bpf_kprobe_override);
-
 static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
 	return tk->rp.handler != NULL;
@@ -88,13 +87,16 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
 	return nhit;
 }
 
-int trace_kprobe_ftrace(struct trace_event_call *call)
+bool trace_kprobe_on_func_entry(struct trace_event_call *call)
 {
 	struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
-	return kprobe_ftrace(&tk->rp.kp);
+
+	return kprobe_on_func_entry(tk->rp.kp.addr,
+			tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
+			tk->rp.kp.addr ? 0 : tk->rp.kp.offset);
 }
 
-int trace_kprobe_error_injectable(struct trace_event_call *call)
+bool trace_kprobe_error_injectable(struct trace_event_call *call)
 {
 	struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
 	unsigned long addr;
@@ -106,7 +108,7 @@ int trace_kprobe_error_injectable(struct trace_event_call *call)
 	} else {
 		addr = (unsigned long)tk->rp.kp.addr;
 	}
-	return within_kprobe_error_injection_list(addr);
+	return within_error_injection_list(addr);
 }
 
 static int register_kprobe_event(struct trace_kprobe *tk);
@@ -1202,6 +1204,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	int rctx;
 
 	if (bpf_prog_array_valid(call)) {
+		unsigned long orig_ip = instruction_pointer(regs);
 		int ret;
 
 		ret = trace_call_bpf(call, regs);
@@ -1209,12 +1212,13 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 		/*
 		 * We need to check and see if we modified the pc of the
 		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the instruction skipping.  Also reset our state so
-		 * we are clean the next pass through.
+		 * don't do the single stepping.
+		 * The ftrace kprobe handler leaves it up to us to re-enable
+		 * preemption here before returning if we've modified the ip.
 		 */
-		if (__this_cpu_read(bpf_kprobe_override)) {
-			__this_cpu_write(bpf_kprobe_override, 0);
+		if (orig_ip != instruction_pointer(regs)) {
 			reset_current_kprobe();
+			preempt_enable_no_resched();
 			return 1;
 		}
 		if (!ret)
@@ -1322,15 +1326,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 	if (tk->tp.flags & TP_FLAG_TRACE)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (tk->tp.flags & TP_FLAG_PROFILE) {
+	if (tk->tp.flags & TP_FLAG_PROFILE)
 		ret = kprobe_perf_func(tk, regs);
-		/*
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
-		 */
-		if (ret)
-			preempt_enable_no_resched();
-	}
 #endif
 	return ret;
 }
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5e54d748c84c..e101c5bb9eda 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -252,8 +252,8 @@ struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
 struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
-int trace_kprobe_ftrace(struct trace_event_call *call);
-int trace_kprobe_error_injectable(struct trace_event_call *call);
+bool trace_kprobe_on_func_entry(struct trace_event_call *call);
+bool trace_kprobe_error_injectable(struct trace_event_call *call);
 #else
 /* uprobes do not support symbol fetch methods */
 #define fetch_symbol_u8			NULL
@@ -280,14 +280,14 @@ alloc_symbol_cache(const char *sym, long offset)
 	return NULL;
 }
 
-static inline int trace_kprobe_ftrace(struct trace_event_call *call)
+static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call)
 {
-	return 0;
+	return false;
 }
 
-static inline int trace_kprobe_error_injectable(struct trace_event_call *call)
+static inline bool trace_kprobe_error_injectable(struct trace_event_call *call)
 {
-	return 0;
+	return false;
 }
 #endif /* CONFIG_KPROBE_EVENTS */