Merge tag 'v5.17-rc4' into for-linus

Merge with mainline to get the Intel ASoC generic helpers header and
other changes.

34 files changed, 2487 insertions, 782 deletions

diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index a82d6de86522..d24d518ddd63 100644
--- a/kernel/bpf/Kconfig
+++ b/kernel/bpf/Kconfig
@@ -64,6 +64,7 @@ config BPF_JIT_DEFAULT_ON
 
 config BPF_UNPRIV_DEFAULT_OFF
 	bool "Disable unprivileged BPF by default"
+	default y
 	depends on BPF_SYSCALL
 	help
 	  Disables unprivileged BPF by default by setting the corresponding
@@ -72,6 +73,12 @@ config BPF_UNPRIV_DEFAULT_OFF
 	  disable it by setting it to 1 (from which no other transition to
 	  0 is possible anymore).
 
+	  Unprivileged BPF could be used to exploit certain potential
+	  speculative execution side-channel vulnerabilities on unmitigated
+	  affected hardware.
+
+	  If you are unsure how to answer this question, answer Y.
+
 source "kernel/bpf/preload/Kconfig"
 
 config BPF_LSM
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 7f33098ca63f..c1a9be6a4b9f 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -7,7 +7,7 @@ endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
@@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
 obj-${CONFIG_BPF_LSM} += bpf_lsm.o
 endif
 obj-$(CONFIG_BPF_PRELOAD) += preload/
+
+obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
+$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE
+	$(call if_changed_rule,cc_o_c)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 447def540544..c7a5be3bf8be 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -645,7 +645,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_array_map_info),
 };
 
-static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				   void *callback_ctx, u64 flags)
 {
 	u32 i, key, num_elems = 0;
@@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
 			val = array->value + array->elem_size * i;
 		num_elems++;
 		key = i;
-		ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)&key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+		ret = callback_fn((u64)(long)map, (u64)(long)&key,
+				  (u64)(long)val, (u64)(long)callback_ctx, 0);
 		/* return value: 0 - continue, 1 - stop and return */
 		if (ret)
 			break;
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
new file mode 100644
index 000000000000..b141a1346f72
--- /dev/null
+++ b/kernel/bpf/bloom_filter.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bitmap.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+
+#define BLOOM_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK)
+
+struct bpf_bloom_filter {
+	struct bpf_map map;
+	u32 bitset_mask;
+	u32 hash_seed;
+	/* If the size of the values in the bloom filter is u32 aligned,
+	 * then it is more performant to use jhash2 as the underlying hash
+	 * function, else we use jhash. This tracks the number of u32s
+	 * in an u32-aligned value size. If the value size is not u32 aligned,
+	 * this will be 0.
+	 */
+	u32 aligned_u32_count;
+	u32 nr_hash_funcs;
+	unsigned long bitset[];
+};
+
+static u32 hash(struct bpf_bloom_filter *bloom, void *value,
+		u32 value_size, u32 index)
+{
+	u32 h;
+
+	if (bloom->aligned_u32_count)
+		h = jhash2(value, bloom->aligned_u32_count,
+			   bloom->hash_seed + index);
+	else
+		h = jhash(value, value_size, bloom->hash_seed + index);
+
+	return h & bloom->bitset_mask;
+}
+
+static int bloom_map_peek_elem(struct bpf_map *map, void *value)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+	u32 i, h;
+
+	for (i = 0; i < bloom->nr_hash_funcs; i++) {
+		h = hash(bloom, value, map->value_size, i);
+		if (!test_bit(h, bloom->bitset))
+			return -ENOENT;
+	}
+
+	return 0;
+}
+
+static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+	u32 i, h;
+
+	if (flags != BPF_ANY)
+		return -EINVAL;
+
+	for (i = 0; i < bloom->nr_hash_funcs; i++) {
+		h = hash(bloom, value, map->value_size, i);
+		set_bit(h, bloom->bitset);
+	}
+
+	return 0;
+}
+
+static int bloom_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static int bloom_map_delete_elem(struct bpf_map *map, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
+{
+	u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
+	int numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_bloom_filter *bloom;
+
+	if (!bpf_capable())
+		return ERR_PTR(-EPERM);
+
+	if (attr->key_size != 0 || attr->value_size == 0 ||
+	    attr->max_entries == 0 ||
+	    attr->map_flags & ~BLOOM_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
+	    /* The lower 4 bits of map_extra (0xF) specify the number
+	     * of hash functions
+	     */
+	    (attr->map_extra & ~0xF))
+		return ERR_PTR(-EINVAL);
+
+	nr_hash_funcs = attr->map_extra;
+	if (nr_hash_funcs == 0)
+		/* Default to using 5 hash functions if unspecified */
+		nr_hash_funcs = 5;
+
+	/* For the bloom filter, the optimal bit array size that minimizes the
+	 * false positive probability is n * k / ln(2) where n is the number of
+	 * expected entries in the bloom filter and k is the number of hash
+	 * functions. We use 7 / 5 to approximate 1 / ln(2).
+	 *
+	 * We round this up to the nearest power of two to enable more efficient
+	 * hashing using bitmasks. The bitmask will be the bit array size - 1.
+	 *
+	 * If this overflows a u32, the bit array size will have 2^32 (4
+	 * GB) bits.
+	 */
+	if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) ||
+	    check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) ||
+	    nr_bits > (1UL << 31)) {
+		/* The bit array size is 2^32 bits but to avoid overflowing the
+		 * u32, we use U32_MAX, which will round up to the equivalent
+		 * number of bytes
+		 */
+		bitset_bytes = BITS_TO_BYTES(U32_MAX);
+		bitset_mask = U32_MAX;
+	} else {
+		if (nr_bits <= BITS_PER_LONG)
+			nr_bits = BITS_PER_LONG;
+		else
+			nr_bits = roundup_pow_of_two(nr_bits);
+		bitset_bytes = BITS_TO_BYTES(nr_bits);
+		bitset_mask = nr_bits - 1;
+	}
+
+	bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long));
+	bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node);
+
+	if (!bloom)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&bloom->map, attr);
+
+	bloom->nr_hash_funcs = nr_hash_funcs;
+	bloom->bitset_mask = bitset_mask;
+
+	/* Check whether the value size is u32-aligned */
+	if ((attr->value_size & (sizeof(u32) - 1)) == 0)
+		bloom->aligned_u32_count =
+			attr->value_size / sizeof(u32);
+
+	if (!(attr->map_flags & BPF_F_ZERO_SEED))
+		bloom->hash_seed = get_random_int();
+
+	return &bloom->map;
+}
+
+static void bloom_map_free(struct bpf_map *map)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+
+	bpf_map_area_free(bloom);
+}
+
+static void *bloom_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	/* The eBPF program should use map_peek_elem instead */
+	return ERR_PTR(-EINVAL);
+}
+
+static int bloom_map_update_elem(struct bpf_map *map, void *key,
+				 void *value, u64 flags)
+{
+	/* The eBPF program should use map_push_elem instead */
+	return -EINVAL;
+}
+
+static int bloom_map_check_btf(const struct bpf_map *map,
+			       const struct btf *btf,
+			       const struct btf_type *key_type,
+			       const struct btf_type *value_type)
+{
+	/* Bloom filter maps are keyless */
+	return btf_type_is_void(key_type) ? 0 : -EINVAL;
+}
+
+static int bpf_bloom_map_btf_id;
+const struct bpf_map_ops bloom_filter_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc = bloom_map_alloc,
+	.map_free = bloom_map_free,
+	.map_get_next_key = bloom_map_get_next_key,
+	.map_push_elem = bloom_map_push_elem,
+	.map_peek_elem = bloom_map_peek_elem,
+	.map_pop_elem = bloom_map_pop_elem,
+	.map_lookup_elem = bloom_map_lookup_elem,
+	.map_update_elem = bloom_map_update_elem,
+	.map_delete_elem = bloom_map_delete_elem,
+	.map_check_btf = bloom_map_check_btf,
+	.map_btf_name = "bpf_bloom_filter",
+	.map_btf_id = &bpf_bloom_map_btf_id,
+};
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 96ceed0e0fb5..e29d9e3d853e 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -17,6 +17,7 @@
 #include <linux/bpf_lsm.h>
 #include <linux/btf_ids.h>
 #include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
 
 DEFINE_BPF_STORAGE_CACHE(inode_cache);
 
@@ -44,7 +45,8 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
 	if (!bsb)
 		return NULL;
 
-	inode_storage = rcu_dereference(bsb->storage);
+	inode_storage =
+		rcu_dereference_check(bsb->storage, bpf_rcu_lock_held());
 	if (!inode_storage)
 		return NULL;
 
@@ -172,6 +174,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
 {
 	struct bpf_local_storage_data *sdata;
 
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
 	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
 		return (unsigned long)NULL;
 
@@ -204,6 +207,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
 BPF_CALL_2(bpf_inode_storage_delete,
 	   struct bpf_map *, map, struct inode *, inode)
 {
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
 	if (!inode)
 		return -EINVAL;
 
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index b2ee45064e06..b7aef5b3416d 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -714,3 +714,38 @@ const struct bpf_func_proto bpf_for_each_map_elem_proto = {
 	.arg3_type	= ARG_PTR_TO_STACK_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
 };
+
+/* maximum number of loops */
+#define MAX_LOOPS	BIT(23)
+
+BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx,
+	   u64, flags)
+{
+	bpf_callback_t callback = (bpf_callback_t)callback_fn;
+	u64 ret;
+	u32 i;
+
+	if (flags)
+		return -EINVAL;
+	if (nr_loops > MAX_LOOPS)
+		return -E2BIG;
+
+	for (i = 0; i < nr_loops; i++) {
+		ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0);
+		/* return value: 0 - continue, 1 - stop and return */
+		if (ret)
+			return i + 1;
+	}
+
+	return i;
+}
+
+const struct bpf_func_proto bpf_loop_proto = {
+	.func		= bpf_loop,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_PTR_TO_FUNC,
+	.arg3_type	= ARG_PTR_TO_STACK_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b305270b7a4b..71de2a89869c 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -11,6 +11,9 @@
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
 
 #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
 
@@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
 	return NULL;
 }
 
+void bpf_local_storage_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage *local_storage;
+
+	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
+	kfree_rcu(local_storage, rcu);
+}
+
+static void bpf_selem_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage_elem *selem;
+
+	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+	kfree_rcu(selem, rcu);
+}
+
 /* local_storage->lock must be held and selem->local_storage == local_storage.
  * The caller must ensure selem->smap is still valid to be
  * dereferenced for its smap->elem_size and smap->cache_idx.
@@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 	bool free_local_storage;
 	void *owner;
 
-	smap = rcu_dereference(SDATA(selem)->smap);
+	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
 	owner = local_storage->owner;
 
 	/* All uncharging on the owner must be done first.
@@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 		 *
 		 * Although the unlock will be done under
 		 * rcu_read_lock(),  it is more intutivie to
-		 * read if kfree_rcu(local_storage, rcu) is done
+		 * read if the freeing of the storage is done
 		 * after the raw_spin_unlock_bh(&local_storage->lock).
 		 *
 		 * Hence, a "bool free_local_storage" is returned
-		 * to the caller which then calls the kfree_rcu()
-		 * after unlock.
+		 * to the caller which then calls then frees the storage after
+		 * all the RCU grace periods have expired.
 		 */
 	}
 	hlist_del_init_rcu(&selem->snode);
@@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 	    SDATA(selem))
 		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
 
-	kfree_rcu(selem, rcu);
-
+	call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
 	return free_local_storage;
 }
 
@@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 		/* selem has already been unlinked from sk */
 		return;
 
-	local_storage = rcu_dereference(selem->local_storage);
+	local_storage = rcu_dereference_check(selem->local_storage,
+					      bpf_rcu_lock_held());
 	raw_spin_lock_irqsave(&local_storage->lock, flags);
 	if (likely(selem_linked_to_storage(selem)))
 		free_local_storage = bpf_selem_unlink_storage_nolock(
@@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 
 	if (free_local_storage)
-		kfree_rcu(local_storage, rcu);
+		call_rcu_tasks_trace(&local_storage->rcu,
+				     bpf_local_storage_free_rcu);
 }
 
 void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
@@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 		/* selem has already be unlinked from smap */
 		return;
 
-	smap = rcu_dereference(SDATA(selem)->smap);
+	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
 	b = select_bucket(smap, selem);
 	raw_spin_lock_irqsave(&b->lock, flags);
 	if (likely(selem_linked_to_map(selem)))
@@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
 	struct bpf_local_storage_elem *selem;
 
 	/* Fast path (cache hit) */
-	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+	sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
+				      bpf_rcu_lock_held());
 	if (sdata && rcu_access_pointer(sdata->smap) == smap)
 		return sdata;
 
 	/* Slow path (cache miss) */
-	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode,
+				  rcu_read_lock_trace_held())
 		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
 			break;
 
@@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner,
 		 * bucket->list, first_selem can be freed immediately
 		 * (instead of kfree_rcu) because
 		 * bpf_local_storage_map_free() does a
-		 * synchronize_rcu() before walking the bucket->list.
+		 * synchronize_rcu_mult (waiting for both sleepable and
+		 * normal programs) before walking the bucket->list.
 		 * Hence, no one is accessing selem from the
 		 * bucket->list under rcu_read_lock().
 		 */
@@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		     !map_value_has_spin_lock(&smap->map)))
 		return ERR_PTR(-EINVAL);
 
-	local_storage = rcu_dereference(*owner_storage(smap, owner));
+	local_storage = rcu_dereference_check(*owner_storage(smap, owner),
+					      bpf_rcu_lock_held());
 	if (!local_storage || hlist_empty(&local_storage->list)) {
 		/* Very first elem for the owner */
 		err = check_flags(NULL, map_flags);
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 06062370c3b8..9e4ecc990647 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -207,7 +207,7 @@ BTF_ID(func, bpf_lsm_socket_socketpair)
 
 BTF_ID(func, bpf_lsm_syslog)
 BTF_ID(func, bpf_lsm_task_alloc)
-BTF_ID(func, bpf_lsm_task_getsecid_subj)
+BTF_ID(func, bpf_lsm_current_getsecid_subj)
 BTF_ID(func, bpf_lsm_task_getsecid_obj)
 BTF_ID(func, bpf_lsm_task_prctl)
 BTF_ID(func, bpf_lsm_task_setscheduler)
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 9abcc33f02cf..21069dbe9138 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -93,6 +93,9 @@ const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = {
 };
 
 const struct bpf_prog_ops bpf_struct_ops_prog_ops = {
+#ifdef CONFIG_NET
+	.test_run = bpf_struct_ops_test_run,
+#endif
 };
 
 static const struct btf_type *module_type;
@@ -162,7 +165,7 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log)
 				break;
 			}
 
-			if (btf_member_bitfield_size(t, member)) {
+			if (__btf_member_bitfield_size(t, member)) {
 				pr_warn("bit field member %s in struct %s is not supported\n",
 					mname, st_ops->name);
 				break;
@@ -293,7 +296,7 @@ static int check_zero_holes(const struct btf_type *t, void *data)
 	const struct btf_type *mtype;
 
 	for_each_member(i, t, member) {
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		if (moff > prev_mend &&
 		    memchr_inv(data + prev_mend, 0, moff - prev_mend))
 			return -EINVAL;
@@ -312,6 +315,20 @@ static int check_zero_holes(const struct btf_type *t, void *data)
 	return 0;
 }
 
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs,
+				      struct bpf_prog *prog,
+				      const struct btf_func_model *model,
+				      void *image, void *image_end)
+{
+	u32 flags;
+
+	tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
+	tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
+	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+	return arch_prepare_bpf_trampoline(NULL, image, image_end,
+					   model, flags, tprogs, NULL);
+}
+
 static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 					  void *value, u64 flags)
 {
@@ -323,7 +340,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	struct bpf_tramp_progs *tprogs = NULL;
 	void *udata, *kdata;
 	int prog_fd, err = 0;
-	void *image;
+	void *image, *image_end;
 	u32 i;
 
 	if (flags)
@@ -363,14 +380,14 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	udata = &uvalue->data;
 	kdata = &kvalue->data;
 	image = st_map->image;
+	image_end = st_map->image + PAGE_SIZE;
 
 	for_each_member(i, t, member) {
 		const struct btf_type *mtype, *ptype;
 		struct bpf_prog *prog;
 		u32 moff;
-		u32 flags;
 
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
 		if (ptype == module_type) {
 			if (*(void **)(udata + moff))
@@ -430,14 +447,9 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			goto reset_unlock;
 		}
 
-		tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
-		tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
-		flags = st_ops->func_models[i].ret_size > 0 ?
-			BPF_TRAMP_F_RET_FENTRY_RET : 0;
-		err = arch_prepare_bpf_trampoline(NULL, image,
-						  st_map->image + PAGE_SIZE,
-						  &st_ops->func_models[i],
-						  flags, tprogs, NULL);
+		err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+							&st_ops->func_models[i],
+							image, image_end);
 		if (err < 0)
 			goto reset_unlock;
 
diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h
index 066d83ea1c99..5678a9ddf817 100644
--- a/kernel/bpf/bpf_struct_ops_types.h
+++ b/kernel/bpf/bpf_struct_ops_types.h
@@ -2,6 +2,9 @@
 /* internal file - do not include directly */
 
 #ifdef CONFIG_BPF_JIT
+#ifdef CONFIG_NET
+BPF_STRUCT_OPS_TYPE(bpf_dummy_ops)
+#endif
 #ifdef CONFIG_INET
 #include <net/tcp.h>
 BPF_STRUCT_OPS_TYPE(tcp_congestion_ops)
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index ebfa8bc90892..5da7bed0f5f6 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -17,6 +17,7 @@
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
 
 DEFINE_BPF_STORAGE_CACHE(task_cache);
 
@@ -59,7 +60,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map,
 	struct bpf_local_storage *task_storage;
 	struct bpf_local_storage_map *smap;
 
-	task_storage = rcu_dereference(task->bpf_storage);
+	task_storage =
+		rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held());
 	if (!task_storage)
 		return NULL;
 
@@ -229,6 +231,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
 {
 	struct bpf_local_storage_data *sdata;
 
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
 	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
 		return (unsigned long)NULL;
 
@@ -260,6 +263,7 @@ BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
 {
 	int ret;
 
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
 	if (!task)
 		return -EINVAL;
 
@@ -323,7 +327,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = {
 	.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_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type = ARG_ANYTHING,
 };
@@ -334,5 +338,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = {
 	.ret_type = RET_INTEGER,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id = &btf_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 };
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dfe61df4f974..e16dafeb2450 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -25,6 +25,7 @@
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <net/sock.h>
+#include "../tools/lib/bpf/relo_core.h"
 
 /* BTF (BPF Type Format) is the meta data format which describes
  * the data types of BPF program/map.  Hence, it basically focus
@@ -281,6 +282,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
+	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
+	[BTF_KIND_TYPE_TAG]	= "TYPE_TAG",
 };
 
 const char *btf_type_str(const struct btf_type *t)
@@ -417,6 +420,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return true;
 	}
 
@@ -459,6 +463,17 @@ static bool btf_type_is_datasec(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
 }
 
+static bool btf_type_is_decl_tag(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG;
+}
+
+static bool btf_type_is_decl_tag_target(const struct btf_type *t)
+{
+	return btf_type_is_func(t) || btf_type_is_struct(t) ||
+	       btf_type_is_var(t) || btf_type_is_typedef(t);
+}
+
 u32 btf_nr_types(const struct btf *btf)
 {
 	u32 total = 0;
@@ -537,6 +552,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
 static bool btf_type_is_resolve_source_only(const struct btf_type *t)
 {
 	return btf_type_is_var(t) ||
+	       btf_type_is_decl_tag(t) ||
 	       btf_type_is_datasec(t);
 }
 
@@ -563,6 +579,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t)
 	       btf_type_is_struct(t) ||
 	       btf_type_is_array(t) ||
 	       btf_type_is_var(t) ||
+	       btf_type_is_decl_tag(t) ||
 	       btf_type_is_datasec(t);
 }
 
@@ -616,6 +633,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t)
 	return (const struct btf_var *)(t + 1);
 }
 
+static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t)
+{
+	return (const struct btf_decl_tag *)(t + 1);
+}
+
 static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 {
 	return kind_ops[BTF_INFO_KIND(t->info)];
@@ -815,7 +837,7 @@ static const char *btf_show_name(struct btf_show *show)
 	const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)];
 	const char *name = NULL, *prefix = "", *parens = "";
 	const struct btf_member *m = show->state.member;
-	const struct btf_type *t = show->state.type;
+	const struct btf_type *t;
 	const struct btf_array *array;
 	u32 id = show->state.type_id;
 	const char *member = NULL;
@@ -1718,6 +1740,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
+		case BTF_KIND_TYPE_TAG:
 			id = type->type;
 			type = btf_type_by_id(btf, type->type);
 			break;
@@ -2326,6 +2349,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 				   const struct btf_type *t,
 				   u32 meta_left)
 {
+	const char *value;
+
 	if (btf_type_vlen(t)) {
 		btf_verifier_log_type(env, t, "vlen != 0");
 		return -EINVAL;
@@ -2341,7 +2366,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* typedef type must have a valid name, and other ref types,
+	/* typedef/type_tag type must have a valid name, and other ref types,
 	 * volatile, const, restrict, should have a null name.
 	 */
 	if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
@@ -2350,6 +2375,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 			btf_verifier_log_type(env, t, "Invalid name");
 			return -EINVAL;
 		}
+	} else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) {
+		value = btf_name_by_offset(env->btf, t->name_off);
+		if (!value || !value[0]) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
 	} else {
 		if (t->name_off) {
 			btf_verifier_log_type(env, t, "Invalid name");
@@ -2939,7 +2970,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		offset = btf_member_bit_offset(t, member);
+		offset = __btf_member_bit_offset(t, member);
 		if (is_union && offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
@@ -3064,7 +3095,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 		if (off != -ENOENT)
 			/* only one such field is allowed */
 			return -E2BIG;
-		off = btf_member_bit_offset(t, member);
+		off = __btf_member_bit_offset(t, member);
 		if (off % 8)
 			/* valid C code cannot generate such BTF */
 			return -EINVAL;
@@ -3154,8 +3185,8 @@ static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
 
 		btf_show_start_member(show, member);
 
-		member_offset = btf_member_bit_offset(t, member);
-		bitfield_size = btf_member_bitfield_size(t, member);
+		member_offset = __btf_member_bit_offset(t, member);
+		bitfield_size = __btf_member_bitfield_size(t, member);
 		bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
 		bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		if (bitfield_size) {
@@ -3801,6 +3832,110 @@ static const struct btf_kind_operations float_ops = {
 	.show = btf_df_show,
 };
 
+static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env,
+			      const struct btf_type *t,
+			      u32 meta_left)
+{
+	const struct btf_decl_tag *tag;
+	u32 meta_needed = sizeof(*tag);
+	s32 component_idx;
+	const char *value;
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	value = btf_name_by_offset(env->btf, t->name_off);
+	if (!value || !value[0]) {
+		btf_verifier_log_type(env, t, "Invalid value");
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
+	component_idx = btf_type_decl_tag(t)->component_idx;
+	if (component_idx < -1) {
+		btf_verifier_log_type(env, t, "Invalid component_idx");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static int btf_decl_tag_resolve(struct btf_verifier_env *env,
+			   const struct resolve_vertex *v)
+{
+	const struct btf_type *next_type;
+	const struct btf_type *t = v->t;
+	u32 next_type_id = t->type;
+	struct btf *btf = env->btf;
+	s32 component_idx;
+	u32 vlen;
+
+	next_type = btf_type_by_id(btf, next_type_id);
+	if (!next_type || !btf_type_is_decl_tag_target(next_type)) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	if (!env_type_is_resolve_sink(env, next_type) &&
+	    !env_type_is_resolved(env, next_type_id))
+		return env_stack_push(env, next_type, next_type_id);
+
+	component_idx = btf_type_decl_tag(t)->component_idx;
+	if (component_idx != -1) {
+		if (btf_type_is_var(next_type) || btf_type_is_typedef(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid component_idx");
+			return -EINVAL;
+		}
+
+		if (btf_type_is_struct(next_type)) {
+			vlen = btf_type_vlen(next_type);
+		} else {
+			/* next_type should be a function */
+			next_type = btf_type_by_id(btf, next_type->type);
+			vlen = btf_type_vlen(next_type);
+		}
+
+		if ((u32)component_idx >= vlen) {
+			btf_verifier_log_type(env, v->t, "Invalid component_idx");
+			return -EINVAL;
+		}
+	}
+
+	env_stack_pop_resolved(env, next_type_id, 0);
+
+	return 0;
+}
+
+static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t)
+{
+	btf_verifier_log(env, "type=%u component_idx=%d", t->type,
+			 btf_type_decl_tag(t)->component_idx);
+}
+
+static const struct btf_kind_operations decl_tag_ops = {
+	.check_meta = btf_decl_tag_check_meta,
+	.resolve = btf_decl_tag_resolve,
+	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
+	.log_details = btf_decl_tag_log,
+	.show = btf_df_show,
+};
+
 static int btf_func_proto_check(struct btf_verifier_env *env,
 				const struct btf_type *t)
 {
@@ -3935,6 +4070,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR] = &var_ops,
 	[BTF_KIND_DATASEC] = &datasec_ops,
 	[BTF_KIND_FLOAT] = &float_ops,
+	[BTF_KIND_DECL_TAG] = &decl_tag_ops,
+	[BTF_KIND_TYPE_TAG] = &modifier_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -4019,6 +4156,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
 		return !btf_resolved_type_id(btf, type_id) &&
 		       !btf_resolved_type_size(btf, type_id);
 
+	if (btf_type_is_decl_tag(t))
+		return btf_resolved_type_id(btf, type_id) &&
+		       !btf_resolved_type_size(btf, type_id);
+
 	if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
 	    btf_type_is_var(t)) {
 		t = btf_type_id_resolve(btf, &type_id);
@@ -4332,8 +4473,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 		log->len_total = log_size;
 
 		/* log attributes have to be sane */
-		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
-		    !log->level || !log->ubuf) {
+		if (!bpf_verifier_log_attr_valid(log)) {
 			err = -EINVAL;
 			goto errout;
 		}
@@ -4686,7 +4826,7 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 		return prog->aux->attach_btf;
 }
 
-static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
+static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
 {
 	/* t comes in already as a pointer */
 	t = btf_type_by_id(btf, t->type);
@@ -4695,8 +4835,7 @@ static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
 	if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST)
 		t = btf_type_by_id(btf, t->type);
 
-	/* char, signed char, unsigned char */
-	return btf_type_is_int(t) && t->size == 1;
+	return btf_type_is_int(t);
 }
 
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
@@ -4801,10 +4940,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
 	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
 		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+		u32 type, flag;
 
-		if (ctx_arg_info->offset == off &&
-		    (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
-		     ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+		type = base_type(ctx_arg_info->reg_type);
+		flag = type_flag(ctx_arg_info->reg_type);
+		if (ctx_arg_info->offset == off && type == PTR_TO_BUF &&
+		    (flag & PTR_MAYBE_NULL)) {
 			info->reg_type = ctx_arg_info->reg_type;
 			return true;
 		}
@@ -4817,7 +4958,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		 */
 		return true;
 
-	if (is_string_ptr(btf, t))
+	if (is_int_ptr(btf, t))
 		return true;
 
 	/* this is a pointer to another type */
@@ -4920,7 +5061,7 @@ again:
 		if (array_elem->nelems != 0)
 			goto error;
 
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		if (off < moff)
 			goto error;
 
@@ -4943,14 +5084,14 @@ error:
 
 	for_each_member(i, t, member) {
 		/* offset of the field in bytes */
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		if (off + size <= moff)
 			/* won't find anything, field is already too far */
 			break;
 
-		if (btf_member_bitfield_size(t, member)) {
-			u32 end_bit = btf_member_bit_offset(t, member) +
-				btf_member_bitfield_size(t, member);
+		if (__btf_member_bitfield_size(t, member)) {
+			u32 end_bit = __btf_member_bit_offset(t, member) +
+				__btf_member_bitfield_size(t, member);
 
 			/* off <= moff instead of off == moff because clang
 			 * does not generate a BTF member for anonymous
@@ -5435,12 +5576,53 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
 #endif
 };
 
+/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */
+static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log,
+					const struct btf *btf,
+					const struct btf_type *t, int rec)
+{
+	const struct btf_type *member_type;
+	const struct btf_member *member;
+	u32 i;
+
+	if (!btf_type_is_struct(t))
+		return false;
+
+	for_each_member(i, t, member) {
+		const struct btf_array *array;
+
+		member_type = btf_type_skip_modifiers(btf, member->type, NULL);
+		if (btf_type_is_struct(member_type)) {
+			if (rec >= 3) {
+				bpf_log(log, "max struct nesting depth exceeded\n");
+				return false;
+			}
+			if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1))
+				return false;
+			continue;
+		}
+		if (btf_type_is_array(member_type)) {
+			array = btf_type_array(member_type);
+			if (!array->nelems)
+				return false;
+			member_type = btf_type_skip_modifiers(btf, array->type, NULL);
+			if (!btf_type_is_scalar(member_type))
+				return false;
+			continue;
+		}
+		if (!btf_type_is_scalar(member_type))
+			return false;
+	}
+	return true;
+}
+
 static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				    const struct btf *btf, u32 func_id,
 				    struct bpf_reg_state *regs,
 				    bool ptr_to_mem_ok)
 {
 	struct bpf_verifier_log *log = &env->log;
+	bool is_kfunc = btf_is_kernel(btf);
 	const char *func_name, *ref_tname;
 	const struct btf_type *t, *ref_t;
 	const struct btf_param *args;
@@ -5493,7 +5675,20 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 
 		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
 		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
-		if (btf_is_kernel(btf)) {
+		if (btf_get_prog_ctx_type(log, btf, t,
+					  env->prog->type, i)) {
+			/* If function expects ctx type in BTF check that caller
+			 * is passing PTR_TO_CTX.
+			 */
+			if (reg->type != PTR_TO_CTX) {
+				bpf_log(log,
+					"arg#%d expected pointer to ctx, but got %s\n",
+					i, btf_type_str(t));
+				return -EINVAL;
+			}
+			if (check_ptr_off_reg(env, reg, regno))
+				return -EINVAL;
+		} else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) {
 			const struct btf_type *reg_ref_t;
 			const struct btf *reg_btf;
 			const char *reg_ref_tname;
@@ -5509,14 +5704,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			if (reg->type == PTR_TO_BTF_ID) {
 				reg_btf = reg->btf;
 				reg_ref_id = reg->btf_id;
-			} else if (reg2btf_ids[reg->type]) {
+			} else {
 				reg_btf = btf_vmlinux;
 				reg_ref_id = *reg2btf_ids[reg->type];
-			} else {
-				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
-					func_name, i,
-					btf_type_str(ref_t), ref_tname, regno);
-				return -EINVAL;
 			}
 
 			reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id,
@@ -5532,23 +5722,24 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 					reg_ref_tname);
 				return -EINVAL;
 			}
-		} else if (btf_get_prog_ctx_type(log, btf, t,
-						 env->prog->type, i)) {
-			/* If function expects ctx type in BTF check that caller
-			 * is passing PTR_TO_CTX.
-			 */
-			if (reg->type != PTR_TO_CTX) {
-				bpf_log(log,
-					"arg#%d expected pointer to ctx, but got %s\n",
-					i, btf_type_str(t));
-				return -EINVAL;
-			}
-			if (check_ctx_reg(env, reg, regno))
-				return -EINVAL;
 		} else if (ptr_to_mem_ok) {
 			const struct btf_type *resolve_ret;
 			u32 type_size;
 
+			if (is_kfunc) {
+				/* Permit pointer to mem, but only when argument
+				 * type is pointer to scalar, or struct composed
+				 * (recursively) of scalars.
+				 */
+				if (!btf_type_is_scalar(ref_t) &&
+				    !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) {
+					bpf_log(log,
+						"arg#%d pointer type %s %s must point to scalar or struct with scalar\n",
+						i, btf_type_str(ref_t), ref_tname);
+					return -EINVAL;
+				}
+			}
+
 			resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
 			if (IS_ERR(resolve_ret)) {
 				bpf_log(log,
@@ -5561,6 +5752,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			if (check_mem_reg(env, reg, regno, type_size))
 				return -EINVAL;
 		} else {
+			bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i,
+				is_kfunc ? "kernel " : "", func_name, func_id);
 			return -EINVAL;
 		}
 	}
@@ -5610,7 +5803,7 @@ int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
 			      const struct btf *btf, u32 func_id,
 			      struct bpf_reg_state *regs)
 {
-	return btf_check_func_arg_match(env, btf, func_id, regs, false);
+	return btf_check_func_arg_match(env, btf, func_id, regs, true);
 }
 
 /* Convert BTF of a function into bpf_reg_state if possible
@@ -5718,7 +5911,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 
-			reg->type = PTR_TO_MEM_OR_NULL;
+			reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
 			reg->id = ++env->id_gen;
 
 			continue;
@@ -6029,6 +6222,8 @@ btf_module_read(struct file *file, struct kobject *kobj,
 	return len;
 }
 
+static void purge_cand_cache(struct btf *btf);
+
 static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			     void *module)
 {
@@ -6063,6 +6258,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			goto out;
 		}
 
+		purge_cand_cache(NULL);
 		mutex_lock(&btf_module_mutex);
 		btf_mod->module = module;
 		btf_mod->btf = btf;
@@ -6105,6 +6301,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			list_del(&btf_mod->list);
 			if (btf_mod->sysfs_attr)
 				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
+			purge_cand_cache(btf_mod->btf);
 			btf_put(btf_mod->btf);
 			kfree(btf_mod->sysfs_attr);
 			kfree(btf_mod);
@@ -6208,10 +6405,442 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
 	.func		= bpf_btf_find_by_name_kind,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_ANYTHING,
 };
 
-BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
+BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE)
+#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type)
+BTF_TRACING_TYPE_xxx
+#undef BTF_TRACING_TYPE
+
+/* BTF ID set registration API for modules */
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+
+void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
+			       struct kfunc_btf_id_set *s)
+{
+	mutex_lock(&l->mutex);
+	list_add(&s->list, &l->list);
+	mutex_unlock(&l->mutex);
+}
+EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set);
+
+void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
+				 struct kfunc_btf_id_set *s)
+{
+	mutex_lock(&l->mutex);
+	list_del_init(&s->list);
+	mutex_unlock(&l->mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set);
+
+bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
+			      struct module *owner)
+{
+	struct kfunc_btf_id_set *s;
+
+	mutex_lock(&klist->mutex);
+	list_for_each_entry(s, &klist->list, list) {
+		if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
+			mutex_unlock(&klist->mutex);
+			return true;
+		}
+	}
+	mutex_unlock(&klist->mutex);
+	return false;
+}
+
+#define DEFINE_KFUNC_BTF_ID_LIST(name)                                         \
+	struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list),           \
+					  __MUTEX_INITIALIZER(name.mutex) };   \
+	EXPORT_SYMBOL_GPL(name)
+
+DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
+DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+
+#endif
+
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+			      const struct btf *targ_btf, __u32 targ_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+	/* check X___Y name pattern, where X and Y are not underscores */
+	return s[0] != '_' &&				      /* X */
+	       s[1] == '_' && s[2] == '_' && s[3] == '_' &&   /* ___ */
+	       s[4] != '_';				      /* Y */
+}
+
+size_t bpf_core_essential_name_len(const char *name)
+{
+	size_t n = strlen(name);
+	int i;
+
+	for (i = n - 5; i >= 0; i--) {
+		if (bpf_core_is_flavor_sep(name + i))
+			return i + 1;
+	}
+	return n;
+}
+
+struct bpf_cand_cache {
+	const char *name;
+	u32 name_len;
+	u16 kind;
+	u16 cnt;
+	struct {
+		const struct btf *btf;
+		u32 id;
+	} cands[];
+};
+
+static void bpf_free_cands(struct bpf_cand_cache *cands)
+{
+	if (!cands->cnt)
+		/* empty candidate array was allocated on stack */
+		return;
+	kfree(cands);
+}
+
+static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands)
+{
+	kfree(cands->name);
+	kfree(cands);
+}
+
+#define VMLINUX_CAND_CACHE_SIZE 31
+static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE];
+
+#define MODULE_CAND_CACHE_SIZE 31
+static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE];
+
+static DEFINE_MUTEX(cand_cache_mutex);
+
+static void __print_cand_cache(struct bpf_verifier_log *log,
+			       struct bpf_cand_cache **cache,
+			       int cache_size)
+{
+	struct bpf_cand_cache *cc;
+	int i, j;
+
+	for (i = 0; i < cache_size; i++) {
+		cc = cache[i];
+		if (!cc)
+			continue;
+		bpf_log(log, "[%d]%s(", i, cc->name);
+		for (j = 0; j < cc->cnt; j++) {
+			bpf_log(log, "%d", cc->cands[j].id);
+			if (j < cc->cnt - 1)
+				bpf_log(log, " ");
+		}
+		bpf_log(log, "), ");
+	}
+}
+
+static void print_cand_cache(struct bpf_verifier_log *log)
+{
+	mutex_lock(&cand_cache_mutex);
+	bpf_log(log, "vmlinux_cand_cache:");
+	__print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	bpf_log(log, "\nmodule_cand_cache:");
+	__print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	bpf_log(log, "\n");
+	mutex_unlock(&cand_cache_mutex);
+}
+
+static u32 hash_cands(struct bpf_cand_cache *cands)
+{
+	return jhash(cands->name, cands->name_len, 0);
+}
+
+static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands,
+					       struct bpf_cand_cache **cache,
+					       int cache_size)
+{
+	struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size];
+
+	if (cc && cc->name_len == cands->name_len &&
+	    !strncmp(cc->name, cands->name, cands->name_len))
+		return cc;
+	return NULL;
+}
+
+static size_t sizeof_cands(int cnt)
+{
+	return offsetof(struct bpf_cand_cache, cands[cnt]);
+}
+
+static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
+						  struct bpf_cand_cache **cache,
+						  int cache_size)
+{
+	struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands;
+
+	if (*cc) {
+		bpf_free_cands_from_cache(*cc);
+		*cc = NULL;
+	}
+	new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
+	if (!new_cands) {
+		bpf_free_cands(cands);
+		return ERR_PTR(-ENOMEM);
+	}
+	/* strdup the name, since it will stay in cache.
+	 * the cands->name points to strings in prog's BTF and the prog can be unloaded.
+	 */
+	new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL);
+	bpf_free_cands(cands);
+	if (!new_cands->name) {
+		kfree(new_cands);
+		return ERR_PTR(-ENOMEM);
+	}
+	*cc = new_cands;
+	return new_cands;
+}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache,
+			       int cache_size)
+{
+	struct bpf_cand_cache *cc;
+	int i, j;
+
+	for (i = 0; i < cache_size; i++) {
+		cc = cache[i];
+		if (!cc)
+			continue;
+		if (!btf) {
+			/* when new module is loaded purge all of module_cand_cache,
+			 * since new module might have candidates with the name
+			 * that matches cached cands.
+			 */
+			bpf_free_cands_from_cache(cc);
+			cache[i] = NULL;
+			continue;
+		}
+		/* when module is unloaded purge cache entries
+		 * that match module's btf
+		 */
+		for (j = 0; j < cc->cnt; j++)
+			if (cc->cands[j].btf == btf) {
+				bpf_free_cands_from_cache(cc);
+				cache[i] = NULL;
+				break;
+			}
+	}
+
+}
+
+static void purge_cand_cache(struct btf *btf)
+{
+	mutex_lock(&cand_cache_mutex);
+	__purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	mutex_unlock(&cand_cache_mutex);
+}
+#endif
+
+static struct bpf_cand_cache *
+bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf,
+		   int targ_start_id)
+{
+	struct bpf_cand_cache *new_cands;
+	const struct btf_type *t;
+	const char *targ_name;
+	size_t targ_essent_len;
+	int n, i;
+
+	n = btf_nr_types(targ_btf);
+	for (i = targ_start_id; i < n; i++) {
+		t = btf_type_by_id(targ_btf, i);
+		if (btf_kind(t) != cands->kind)
+			continue;
+
+		targ_name = btf_name_by_offset(targ_btf, t->name_off);
+		if (!targ_name)
+			continue;
+
+		/* the resched point is before strncmp to make sure that search
+		 * for non-existing name will have a chance to schedule().
+		 */
+		cond_resched();
+
+		if (strncmp(cands->name, targ_name, cands->name_len) != 0)
+			continue;
+
+		targ_essent_len = bpf_core_essential_name_len(targ_name);
+		if (targ_essent_len != cands->name_len)
+			continue;
+
+		/* most of the time there is only one candidate for a given kind+name pair */
+		new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL);
+		if (!new_cands) {
+			bpf_free_cands(cands);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		memcpy(new_cands, cands, sizeof_cands(cands->cnt));
+		bpf_free_cands(cands);
+		cands = new_cands;
+		cands->cands[cands->cnt].btf = targ_btf;
+		cands->cands[cands->cnt].id = i;
+		cands->cnt++;
+	}
+	return cands;
+}
+
+static struct bpf_cand_cache *
+bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
+{
+	struct bpf_cand_cache *cands, *cc, local_cand = {};
+	const struct btf *local_btf = ctx->btf;
+	const struct btf_type *local_type;
+	const struct btf *main_btf;
+	size_t local_essent_len;
+	struct btf *mod_btf;
+	const char *name;
+	int id;
+
+	main_btf = bpf_get_btf_vmlinux();
+	if (IS_ERR(main_btf))
+		return ERR_CAST(main_btf);
+
+	local_type = btf_type_by_id(local_btf, local_type_id);
+	if (!local_type)
+		return ERR_PTR(-EINVAL);
+
+	name = btf_name_by_offset(local_btf, local_type->name_off);
+	if (str_is_empty(name))
+		return ERR_PTR(-EINVAL);
+	local_essent_len = bpf_core_essential_name_len(name);
+
+	cands = &local_cand;
+	cands->name = name;
+	cands->kind = btf_kind(local_type);
+	cands->name_len = local_essent_len;
+
+	cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	/* cands is a pointer to stack here */
+	if (cc) {
+		if (cc->cnt)
+			return cc;
+		goto check_modules;
+	}
+
+	/* Attempt to find target candidates in vmlinux BTF first */
+	cands = bpf_core_add_cands(cands, main_btf, 1);
+	if (IS_ERR(cands))
+		return ERR_CAST(cands);
+
+	/* cands is a pointer to kmalloced memory here if cands->cnt > 0 */
+
+	/* populate cache even when cands->cnt == 0 */
+	cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	if (IS_ERR(cc))
+		return ERR_CAST(cc);
+
+	/* if vmlinux BTF has any candidate, don't go for module BTFs */
+	if (cc->cnt)
+		return cc;
+
+check_modules:
+	/* cands is a pointer to stack here and cands->cnt == 0 */
+	cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	if (cc)
+		/* if cache has it return it even if cc->cnt == 0 */
+		return cc;
+
+	/* If candidate is not found in vmlinux's BTF then search in module's BTFs */
+	spin_lock_bh(&btf_idr_lock);
+	idr_for_each_entry(&btf_idr, mod_btf, id) {
+		if (!btf_is_module(mod_btf))
+			continue;
+		/* linear search could be slow hence unlock/lock
+		 * the IDR to avoiding holding it for too long
+		 */
+		btf_get(mod_btf);
+		spin_unlock_bh(&btf_idr_lock);
+		cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf));
+		if (IS_ERR(cands)) {
+			btf_put(mod_btf);
+			return ERR_CAST(cands);
+		}
+		spin_lock_bh(&btf_idr_lock);
+		btf_put(mod_btf);
+	}
+	spin_unlock_bh(&btf_idr_lock);
+	/* cands is a pointer to kmalloced memory here if cands->cnt > 0
+	 * or pointer to stack if cands->cnd == 0.
+	 * Copy it into the cache even when cands->cnt == 0 and
+	 * return the result.
+	 */
+	return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+}
+
+int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+		   int relo_idx, void *insn)
+{
+	bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL;
+	struct bpf_core_cand_list cands = {};
+	struct bpf_core_spec *specs;
+	int err;
+
+	/* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
+	 * into arrays of btf_ids of struct fields and array indices.
+	 */
+	specs = kcalloc(3, sizeof(*specs), GFP_KERNEL);
+	if (!specs)
+		return -ENOMEM;
+
+	if (need_cands) {
+		struct bpf_cand_cache *cc;
+		int i;
+
+		mutex_lock(&cand_cache_mutex);
+		cc = bpf_core_find_cands(ctx, relo->type_id);
+		if (IS_ERR(cc)) {
+			bpf_log(ctx->log, "target candidate search failed for %d\n",
+				relo->type_id);
+			err = PTR_ERR(cc);
+			goto out;
+		}
+		if (cc->cnt) {
+			cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL);
+			if (!cands.cands) {
+				err = -ENOMEM;
+				goto out;
+			}
+		}
+		for (i = 0; i < cc->cnt; i++) {
+			bpf_log(ctx->log,
+				"CO-RE relocating %s %s: found target candidate [%d]\n",
+				btf_kind_str[cc->kind], cc->name, cc->cands[i].id);
+			cands.cands[i].btf = cc->cands[i].btf;
+			cands.cands[i].id = cc->cands[i].id;
+		}
+		cands.len = cc->cnt;
+		/* cand_cache_mutex needs to span the cache lookup and
+		 * copy of btf pointer into bpf_core_cand_list,
+		 * since module can be unloaded while bpf_core_apply_relo_insn
+		 * is working with module's btf.
+		 */
+	}
+
+	err = bpf_core_apply_relo_insn((void *)ctx->log, insn, relo->insn_off / 8,
+				       relo, relo_idx, ctx->btf, &cands, specs);
+out:
+	kfree(specs);
+	if (need_cands) {
+		kfree(cands.cands);
+		mutex_unlock(&cand_cache_mutex);
+		if (ctx->log->level & BPF_LOG_LEVEL2)
+			print_cand_cache(ctx->log);
+	}
+	return err;
+}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 03145d45e3d5..514b4681a90a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -430,10 +430,10 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs,
  * Exactly one of @prog or @link can be non-null.
  * Must be called with cgroup_mutex held.
  */
-int __cgroup_bpf_attach(struct cgroup *cgrp,
-			struct bpf_prog *prog, struct bpf_prog *replace_prog,
-			struct bpf_cgroup_link *link,
-			enum bpf_attach_type type, u32 flags)
+static int __cgroup_bpf_attach(struct cgroup *cgrp,
+			       struct bpf_prog *prog, struct bpf_prog *replace_prog,
+			       struct bpf_cgroup_link *link,
+			       enum bpf_attach_type type, u32 flags)
 {
 	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
 	struct bpf_prog *old_prog = NULL;
@@ -523,6 +523,20 @@ cleanup:
 	return err;
 }
 
+static int cgroup_bpf_attach(struct cgroup *cgrp,
+			     struct bpf_prog *prog, struct bpf_prog *replace_prog,
+			     struct bpf_cgroup_link *link,
+			     enum bpf_attach_type type,
+			     u32 flags)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
 /* Swap updated BPF program for given link in effective program arrays across
  * all descendant cgroups. This function is guaranteed to succeed.
  */
@@ -672,14 +686,14 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to detach or NULL
- * @prog: A link to detach or NULL
+ * @link: A link to detach or NULL
  * @type: Type of detach operation
  *
  * At most one of @prog or @link can be non-NULL.
  * Must be called with cgroup_mutex held.
  */
-int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-			struct bpf_cgroup_link *link, enum bpf_attach_type type)
+static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			       struct bpf_cgroup_link *link, enum bpf_attach_type type)
 {
 	enum cgroup_bpf_attach_type atype;
 	struct bpf_prog *old_prog;
@@ -730,9 +744,20 @@ cleanup:
 	return err;
 }
 
+static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			     enum bpf_attach_type type)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_detach(cgrp, prog, NULL, type);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
 /* Must be called with cgroup_mutex held to avoid races. */
-int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
-		       union bpf_attr __user *uattr)
+static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+			      union bpf_attr __user *uattr)
 {
 	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
 	enum bpf_attach_type type = attr->query.attach_type;
@@ -789,6 +814,17 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	return ret;
 }
 
+static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+			    union bpf_attr __user *uattr)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_query(cgrp, attr, uattr);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog)
 {
@@ -1753,7 +1789,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
@@ -1773,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_get_new_value_proto;
 	case BPF_FUNC_sysctl_set_new_value:
 		return &bpf_sysctl_set_new_value_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6e3ae90ad107..de3e5bc6781f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -32,6 +32,7 @@
 #include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/log2.h>
+#include <linux/bpf_verifier.h>
 
 #include <asm/barrier.h>
 #include <asm/unaligned.h>
@@ -389,6 +390,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
 			i = end_new;
 			insn = prog->insnsi + end_old;
 		}
+		if (bpf_pseudo_func(insn)) {
+			ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+						   end_new, i, probe_pass);
+			if (ret)
+				return ret;
+			continue;
+		}
 		code = insn->code;
 		if ((BPF_CLASS(code) != BPF_JMP &&
 		     BPF_CLASS(code) != BPF_JMP32) ||
@@ -1566,7 +1574,8 @@ select_insn:
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
+
+		if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT))
 			goto out;
 
 		tail_call_cnt++;
@@ -1883,7 +1892,7 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 
 /**
  *	bpf_prog_select_runtime - select exec runtime for BPF program
- *	@fp: bpf_prog populated with internal BPF program
+ *	@fp: bpf_prog populated with BPF program
  *	@err: pointer to error variable
  *
  * Try to JIT eBPF program, if JIT is not available, use interpreter.
@@ -2263,6 +2272,9 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	int i;
 
 	aux = container_of(work, struct bpf_prog_aux, work);
+#ifdef CONFIG_BPF_SYSCALL
+	bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab);
+#endif
 	bpf_free_used_maps(aux);
 	bpf_free_used_btfs(aux);
 	if (bpf_prog_is_dev_bound(aux))
@@ -2289,7 +2301,6 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	}
 }
 
-/* Free internal BPF program */
 void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
@@ -2365,6 +2376,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
+{
+	return NULL;
+}
+
 u64 __weak
 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		 void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 585b2b77ccc4..b3e6b9422238 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -195,7 +195,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 			}
 			return;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
 			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(skb->dev, rcpu->prog, act);
@@ -254,7 +254,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 			}
 			break;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
 			fallthrough;
 		case XDP_DROP:
 			xdp_return_frame(xdpf);
@@ -746,15 +746,9 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 		list_add(&bq->flush_node, flush_list);
 }
 
-int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
-	struct xdp_frame *xdpf;
-
-	xdpf = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	/* Info needed when constructing SKB on remote CPU */
 	xdpf->dev_rx = dev_rx;
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index f02d04540c0c..fe019dbdb3f0 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -348,7 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
 				frames[nframes++] = xdpf;
 			break;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
 			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(dev, xdp_prog, act);
@@ -467,24 +467,19 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 	bq->q[bq->count++] = xdpf;
 }
 
-static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 				struct net_device *dev_rx,
 				struct bpf_prog *xdp_prog)
 {
-	struct xdp_frame *xdpf;
 	int err;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit)
 		return -EOPNOTSUPP;
 
-	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	err = xdp_ok_fwd_dev(dev, xdpf->len);
 	if (unlikely(err))
 		return err;
 
-	xdpf = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
 	return 0;
 }
@@ -507,7 +502,7 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev
 		__skb_push(skb, skb->mac_len);
 		break;
 	default:
-		bpf_warn_invalid_xdp_action(act);
+		bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(dst->dev, dst->xdp_prog, act);
@@ -520,27 +515,27 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev
 	return act;
 }
 
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
-	return __xdp_enqueue(dev, xdp, dev_rx, NULL);
+	return __xdp_enqueue(dev, xdpf, dev_rx, NULL);
 }
 
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
 	struct net_device *dev = dst->dev;
 
-	return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
+	return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog);
 }
 
-static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp)
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf)
 {
 	if (!obj ||
 	    !obj->dev->netdev_ops->ndo_xdp_xmit)
 		return false;
 
-	if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
+	if (xdp_ok_fwd_dev(obj->dev, xdpf->len))
 		return false;
 
 	return true;
@@ -586,14 +581,13 @@ static int get_upper_ifindexes(struct net_device *dev, int *indexes)
 	return n;
 }
 
-int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 			  struct bpf_map *map, bool exclude_ingress)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dst, *last_dst = NULL;
 	int excluded_devices[1+MAX_NEST_DEV];
 	struct hlist_head *head;
-	struct xdp_frame *xdpf;
 	int num_excluded = 0;
 	unsigned int i;
 	int err;
@@ -603,15 +597,11 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 		excluded_devices[num_excluded++] = dev_rx->ifindex;
 	}
 
-	xdpf = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		for (i = 0; i < map->max_entries; i++) {
 			dst = rcu_dereference_check(dtab->netdev_map[i],
 						    rcu_read_lock_bh_held());
-			if (!is_valid_dst(dst, xdp))
+			if (!is_valid_dst(dst, xdpf))
 				continue;
 
 			if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
@@ -634,7 +624,7 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 			head = dev_map_index_hash(dtab, i);
 			hlist_for_each_entry_rcu(dst, head, index_hlist,
 						 lockdep_is_held(&dtab->index_lock)) {
-				if (!is_valid_dst(dst, xdp))
+				if (!is_valid_dst(dst, xdpf))
 					continue;
 
 				if (is_ifindex_excluded(excluded_devices, num_excluded,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 32471ba02708..d29af9988f37 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
@@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
 	*insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
 			      offsetof(struct htab_elem, lru_node) +
@@ -2049,7 +2049,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_hash_map_info),
 };
 
-static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				  void *callback_ctx, u64 flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
@@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
 				val = elem->key + roundup_key_size;
 			}
 			num_elems++;
-			ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+			ret = callback_fn((u64)(long)map, (u64)(long)key,
+					  (u64)(long)val, (u64)(long)callback_ctx, 0);
 			/* return value: 0 - continue, 1 - stop and return */
 			if (ret) {
 				rcu_read_unlock();
@@ -2397,7 +2396,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9aabf84afd4b..01cfdf40c838 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  */
 #include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
 #include <linux/rcupdate.h>
 #include <linux/random.h>
 #include <linux/smp.h>
@@ -530,7 +531,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
 	.func		= bpf_strtol,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,
@@ -558,13 +559,27 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.func		= bpf_strtoul,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,
 };
 #endif
 
+BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
+{
+	return strncmp(s1, s2, s1_sz);
+}
+
+const struct bpf_func_proto bpf_strncmp_proto = {
+	.func		= bpf_strncmp,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_CONST_STR,
+};
+
 BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
 	   struct bpf_pidns_info *, nsdata, u32, size)
 {
@@ -630,7 +645,7 @@ const struct bpf_func_proto bpf_event_output_data_proto =  {
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_CONST_MAP_PTR,
 	.arg3_type      = ARG_ANYTHING,
-	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg4_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -667,7 +682,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
 const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.func		= bpf_per_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 	.arg2_type	= ARG_ANYTHING,
 };
@@ -680,7 +695,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
 const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
 	.func		= bpf_this_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 };
 
@@ -979,15 +994,13 @@ out:
 	return err;
 }
 
-#define MAX_SNPRINTF_VARARGS		12
-
 BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
 	   const void *, data, u32, data_len)
 {
 	int err, num_args;
 	u32 *bin_args;
 
-	if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
+	if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 ||
 	    (data_len && !data))
 		return -EINVAL;
 	num_args = data_len / 8;
@@ -1013,7 +1026,7 @@ const struct bpf_func_proto bpf_snprintf_proto = {
 	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_PTR_TO_CONST_STR,
-	.arg4_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type	= ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -1058,7 +1071,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 	struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer);
 	struct bpf_map *map = t->map;
 	void *value = t->value;
-	void *callback_fn;
+	bpf_callback_t callback_fn;
 	void *key;
 	u32 idx;
 
@@ -1083,8 +1096,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 		key = value - round_up(map->key_size, 8);
 	}
 
-	BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key,
-				   (u64)(long)value, 0, 0);
+	callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0);
 	/* The verifier checked that return value is zero. */
 
 	this_cpu_write(hrtimer_running, NULL);
@@ -1367,8 +1379,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
@@ -1381,6 +1391,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_query_proto;
 	case BPF_FUNC_for_each_map_elem:
 		return &bpf_for_each_map_elem_proto;
+	case BPF_FUNC_loop:
+		return &bpf_loop_proto;
+	case BPF_FUNC_strncmp:
+		return &bpf_strncmp_proto;
 	default:
 		break;
 	}
@@ -1437,6 +1451,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_task_pt_regs:
 		return &bpf_task_pt_regs_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return NULL;
 	}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 80da1db47c68..5a8d9f7467bf 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -648,12 +648,22 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	int opt;
 
 	opt = fs_parse(fc, bpf_fs_parameters, param, &result);
-	if (opt < 0)
+	if (opt < 0) {
 		/* We might like to report bad mount options here, but
 		 * traditionally we've ignored all mount options, so we'd
 		 * better continue to ignore non-existing options for bpf.
 		 */
-		return opt == -ENOPARAM ? 0 : opt;
+		if (opt == -ENOPARAM) {
+			opt = vfs_parse_fs_param_source(fc, param);
+			if (opt != -ENOPARAM)
+				return opt;
+
+			return 0;
+		}
+
+		if (opt < 0)
+			return opt;
+	}
 
 	switch (opt) {
 	case OPT_MODE:
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 035e9e3a7132..23f7f9d08a62 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -163,8 +163,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
 		return 0;
 	}
 
-	new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) +
-				   map->value_size,
+	new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size),
 				   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
 				   map->numa_node);
 	if (!new)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 423549d2c52e..5763cc7ac4f1 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -412,7 +412,7 @@ static int trie_update_elem(struct bpf_map *map,
 		rcu_assign_pointer(im_node->child[1], node);
 	}
 
-	/* Finally, assign the intermediate node to the determined spot */
+	/* Finally, assign the intermediate node to the determined slot */
 	rcu_assign_pointer(*slot, im_node);
 
 out:
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6a9542af4212..b0fa190b0979 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
-		  PTR_TO_RDONLY_BUF_OR_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
 		{ offsetof(struct bpf_iter__bpf_map_elem, value),
-		  PTR_TO_RDWR_BUF_OR_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL },
 	},
 };
 
diff --git a/kernel/bpf/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h
new file mode 100644
index 000000000000..5d18d7d85bef
--- /dev/null
+++ b/kernel/bpf/mmap_unlock_work.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2021 Facebook
+ */
+
+#ifndef __MMAP_UNLOCK_WORK_H__
+#define __MMAP_UNLOCK_WORK_H__
+#include <linux/irq_work.h>
+
+/* irq_work to run mmap_read_unlock() in irq_work */
+struct mmap_unlock_irq_work {
+	struct irq_work irq_work;
+	struct mm_struct *mm;
+};
+
+DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
+
+/*
+ * We cannot do mmap_read_unlock() when the irq is disabled, because of
+ * risk to deadlock with rq_lock. To look up vma when the irqs are
+ * disabled, we need to run mmap_read_unlock() in irq_work. We use a
+ * percpu variable to do the irq_work. If the irq_work is already used
+ * by another lookup, we fall over.
+ */
+static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr)
+{
+	struct mmap_unlock_irq_work *work = NULL;
+	bool irq_work_busy = false;
+
+	if (irqs_disabled()) {
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			work = this_cpu_ptr(&mmap_unlock_work);
+			if (irq_work_is_busy(&work->irq_work)) {
+				/* cannot queue more up_read, fallback */
+				irq_work_busy = true;
+			}
+		} else {
+			/*
+			 * PREEMPT_RT does not allow to trylock mmap sem in
+			 * interrupt disabled context. Force the fallback code.
+			 */
+			irq_work_busy = true;
+		}
+	}
+
+	*work_ptr = work;
+	return irq_work_busy;
+}
+
+static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm)
+{
+	if (!work) {
+		mmap_read_unlock(mm);
+	} else {
+		work->mm = mm;
+
+		/* The lock will be released once we're out of interrupt
+		 * context. Tell lockdep that we've released it now so
+		 * it doesn't complain that we forgot to release it.
+		 */
+		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
+		irq_work_queue(&work->irq_work);
+	}
+}
+
+#endif /* __MMAP_UNLOCK_WORK_H__ */
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 542f275bf252..868cc2c43899 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
+#include <linux/bpf-netns.h>
 #include <linux/filter.h>
 #include <net/net_namespace.h>
 
diff --git a/kernel/bpf/preload/.gitignore b/kernel/bpf/preload/.gitignore
index 856a4c5ad0dd..9452322902a5 100644
--- a/kernel/bpf/preload/.gitignore
+++ b/kernel/bpf/preload/.gitignore
@@ -1,4 +1,2 @@
-/FEATURE-DUMP.libbpf
-/bpf_helper_defs.h
-/feature
+/libbpf
 /bpf_preload_umd
diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile
index 1951332dd15f..1400ac58178e 100644
--- a/kernel/bpf/preload/Makefile
+++ b/kernel/bpf/preload/Makefile
@@ -1,21 +1,35 @@
 # SPDX-License-Identifier: GPL-2.0
 
 LIBBPF_SRCS = $(srctree)/tools/lib/bpf/
-LIBBPF_A = $(obj)/libbpf.a
-LIBBPF_OUT = $(abspath $(obj))
+LIBBPF_OUT = $(abspath $(obj))/libbpf
+LIBBPF_A = $(LIBBPF_OUT)/libbpf.a
+LIBBPF_DESTDIR = $(LIBBPF_OUT)
+LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
 
 # Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test
 # in tools/scripts/Makefile.include always succeeds when building the kernel
 # with $(O) pointing to a relative path, as in "make O=build bindeb-pkg".
-$(LIBBPF_A):
-	$(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a
+$(LIBBPF_A): | $(LIBBPF_OUT)
+	$(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/   \
+		DESTDIR=$(LIBBPF_DESTDIR) prefix=			       \
+		$(LIBBPF_OUT)/libbpf.a install_headers
+
+libbpf_hdrs: $(LIBBPF_A)
+
+.PHONY: libbpf_hdrs
+
+$(LIBBPF_OUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $@
 
 userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \
-	-I $(srctree)/tools/lib/ -Wno-unused-result
+	-I $(LIBBPF_INCLUDE) -Wno-unused-result
 
 userprogs := bpf_preload_umd
 
-clean-files := $(userprogs) bpf_helper_defs.h FEATURE-DUMP.libbpf staticobjs/ feature/
+clean-files := libbpf/
+
+$(obj)/iterators/iterators.o: | libbpf_hdrs
 
 bpf_preload_umd-objs := iterators/iterators.o
 bpf_preload_umd-userldlibs := $(LIBBPF_A) -lelf -lz
diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile
index 28fa8c1440f4..b8bd60511227 100644
--- a/kernel/bpf/preload/iterators/Makefile
+++ b/kernel/bpf/preload/iterators/Makefile
@@ -1,18 +1,26 @@
 # SPDX-License-Identifier: GPL-2.0
 OUTPUT := .output
+abs_out := $(abspath $(OUTPUT))
+
 CLANG ?= clang
 LLC ?= llc
 LLVM_STRIP ?= llvm-strip
+
+TOOLS_PATH := $(abspath ../../../../tools)
+BPFTOOL_SRC := $(TOOLS_PATH)/bpf/bpftool
+BPFTOOL_OUTPUT := $(abs_out)/bpftool
 DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
-LIBBPF_SRC := $(abspath ../../../../tools/lib/bpf)
-BPFOBJ := $(OUTPUT)/libbpf.a
-BPF_INCLUDE := $(OUTPUT)
-INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../../../tools/lib)        \
-       -I$(abspath ../../../../tools/include/uapi)
+
+LIBBPF_SRC := $(TOOLS_PATH)/lib/bpf
+LIBBPF_OUTPUT := $(abs_out)/libbpf
+LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
+BPFOBJ := $(LIBBPF_OUTPUT)/libbpf.a
+
+INCLUDES := -I$(OUTPUT) -I$(LIBBPF_INCLUDE) -I$(TOOLS_PATH)/include/uapi
 CFLAGS := -g -Wall
 
-abs_out := $(abspath $(OUTPUT))
 ifeq ($(V),1)
 Q =
 msg =
@@ -44,14 +52,18 @@ $(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT)
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
-$(OUTPUT):
+$(OUTPUT) $(LIBBPF_OUTPUT) $(BPFTOOL_OUTPUT):
 	$(call msg,MKDIR,$@)
-	$(Q)mkdir -p $(OUTPUT)
+	$(Q)mkdir -p $@
 
-$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)
+$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)			       \
-		    OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+		    OUTPUT=$(abspath $(dir $@))/ prefix=		       \
+		    DESTDIR=$(LIBBPF_DESTDIR) $(abspath $@) install_headers
 
-$(DEFAULT_BPFTOOL):
-	$(Q)$(MAKE) $(submake_extras) -C ../../../../tools/bpf/bpftool			      \
-		    prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(BPFTOOL_SRC)			       \
+		    OUTPUT=$(BPFTOOL_OUTPUT)/				       \
+		    LIBBPF_OUTPUT=$(LIBBPF_OUTPUT)/			       \
+		    LIBBPF_DESTDIR=$(LIBBPF_DESTDIR)/			       \
+		    prefix= DESTDIR=$(abs_out)/ install-bin
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 93a55391791a..556a769b5b80 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -152,16 +152,12 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
 {
 	int numa_node = bpf_map_attr_numa_node(attr);
 	struct reuseport_array *array;
-	u64 array_size;
 
 	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
-	array_size = sizeof(*array);
-	array_size += (u64)attr->max_entries * sizeof(struct sock *);
-
 	/* allocate all map elements and zero-initialize them */
-	array = bpf_map_area_alloc(array_size, numa_node);
+	array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node);
 	if (!array)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 9e0c10c6892a..710ba9de12ce 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -104,7 +104,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
 	}
 
 	rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
-		  VM_ALLOC | VM_USERMAP, PAGE_KERNEL);
+		  VM_MAP | VM_USERMAP, PAGE_KERNEL);
 	if (rb) {
 		kmemleak_not_leak(pages);
 		rb->pages = pages;
@@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = {
 	.func		= bpf_ringbuf_output,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 6e75bbee39f0..22c8ae94e4c1 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,10 +7,10 @@
 #include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
-#include <linux/irq_work.h>
 #include <linux/btf_ids.h>
 #include <linux/buildid.h>
 #include "percpu_freelist.h"
+#include "mmap_unlock_work.h"
 
 #define STACK_CREATE_FLAG_MASK					\
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
@@ -31,25 +31,6 @@ struct bpf_stack_map {
 	struct stack_map_bucket *buckets[];
 };
 
-/* irq_work to run up_read() for build_id lookup in nmi context */
-struct stack_map_irq_work {
-	struct irq_work irq_work;
-	struct mm_struct *mm;
-};
-
-static void do_up_read(struct irq_work *entry)
-{
-	struct stack_map_irq_work *work;
-
-	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
-		return;
-
-	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	mmap_read_unlock_non_owner(work->mm);
-}
-
-static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
-
 static inline bool stack_map_use_build_id(struct bpf_map *map)
 {
 	return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -149,35 +130,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 					  u64 *ips, u32 trace_nr, bool user)
 {
 	int i;
+	struct mmap_unlock_irq_work *work = NULL;
+	bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
 	struct vm_area_struct *vma;
-	bool irq_work_busy = false;
-	struct stack_map_irq_work *work = NULL;
-
-	if (irqs_disabled()) {
-		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-			work = this_cpu_ptr(&up_read_work);
-			if (irq_work_is_busy(&work->irq_work)) {
-				/* cannot queue more up_read, fallback */
-				irq_work_busy = true;
-			}
-		} else {
-			/*
-			 * PREEMPT_RT does not allow to trylock mmap sem in
-			 * interrupt disabled context. Force the fallback code.
-			 */
-			irq_work_busy = true;
-		}
-	}
 
-	/*
-	 * We cannot do up_read() when the irq is disabled, because of
-	 * risk to deadlock with rq_lock. To do build_id lookup when the
-	 * irqs are disabled, we need to run up_read() in irq_work. We use
-	 * a percpu variable to do the irq_work. If the irq_work is
-	 * already used by another lookup, we fall back to report ips.
-	 *
-	 * Same fallback is used for kernel stack (!user) on a stackmap
-	 * with build_id.
+	/* If the irq_work is in use, fall back to report ips. Same
+	 * fallback is used for kernel stack (!user) on a stackmap with
+	 * build_id.
 	 */
 	if (!user || !current || !current->mm || irq_work_busy ||
 	    !mmap_read_trylock(current->mm)) {
@@ -203,19 +162,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			- vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 	}
-
-	if (!work) {
-		mmap_read_unlock(current->mm);
-	} else {
-		work->mm = current->mm;
-
-		/* The lock will be released once we're out of interrupt
-		 * context. Tell lockdep that we've released it now so
-		 * it doesn't complain that we forgot to release it.
-		 */
-		rwsem_release(&current->mm->mmap_lock.dep_map, _RET_IP_);
-		irq_work_queue(&work->irq_work);
-	}
+	bpf_mmap_unlock_mm(work, current->mm);
 }
 
 static struct perf_callchain_entry *
@@ -525,13 +472,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	   u32, size, u64, flags)
 {
 	struct pt_regs *regs;
-	long res;
+	long res = -EINVAL;
 
 	if (!try_get_task_stack(task))
 		return -EFAULT;
 
 	regs = task_pt_regs(task);
-	res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	if (regs)
+		res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
 	put_task_stack(task);
 
 	return res;
@@ -542,7 +490,7 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id	= &btf_task_struct_ids[0],
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
@@ -719,16 +667,3 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_btf_name = "bpf_stack_map",
 	.map_btf_id = &stack_trace_map_btf_id,
 };
-
-static int __init stack_map_init(void)
-{
-	int cpu;
-	struct stack_map_irq_work *work;
-
-	for_each_possible_cpu(cpu) {
-		work = per_cpu_ptr(&up_read_work, cpu);
-		init_irq_work(&work->irq_work, do_up_read);
-	}
-	return 0;
-}
-subsys_initcall(stack_map_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1cad6979a0d0..fa4505f9b611 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  */
 #include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
 #include <linux/bpf_trace.h>
 #include <linux/bpf_lirc.h>
 #include <linux/bpf_verifier.h>
@@ -132,6 +133,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+	atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+	atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+	return atomic64_read(&map->writecnt) != 0;
+}
+
 static u32 bpf_map_value_size(const struct bpf_map *map)
 {
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -199,7 +215,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
 		err = bpf_fd_reuseport_array_update_elem(map, key, value,
 							 flags);
 	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
-		   map->map_type == BPF_MAP_TYPE_STACK) {
+		   map->map_type == BPF_MAP_TYPE_STACK ||
+		   map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
 		err = map->ops->map_push_elem(map, value, flags);
 	} else {
 		rcu_read_lock();
@@ -238,7 +255,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
 		err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
-		   map->map_type == BPF_MAP_TYPE_STACK) {
+		   map->map_type == BPF_MAP_TYPE_STACK ||
+		   map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
 		err = map->ops->map_peek_elem(map, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
 		/* struct_ops map requires directly updating "value" */
@@ -348,6 +366,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
 	map->max_entries = attr->max_entries;
 	map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
 	map->numa_node = bpf_map_attr_numa_node(attr);
+	map->map_extra = attr->map_extra;
 }
 
 static int bpf_map_alloc_id(struct bpf_map *map)
@@ -555,6 +574,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "value_size:\t%u\n"
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
+		   "map_extra:\t%#llx\n"
 		   "memlock:\t%lu\n"
 		   "map_id:\t%u\n"
 		   "frozen:\t%u\n",
@@ -563,6 +583,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
+		   (unsigned long long)map->map_extra,
 		   bpf_map_memory_footprint(map),
 		   map->id,
 		   READ_ONCE(map->frozen));
@@ -596,11 +617,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt++;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_inc(map);
 }
 
 /* called for all unmapped memory region (including initial) */
@@ -608,11 +626,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt--;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_dec(map);
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -663,7 +678,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 		goto out;
 
 	if (vma->vm_flags & VM_MAYWRITE)
-		map->writecnt++;
+		bpf_map_write_active_inc(map);
 out:
 	mutex_unlock(&map->freeze_mutex);
 	return err;
@@ -812,7 +827,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	return ret;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
+#define BPF_MAP_CREATE_LAST_FIELD map_extra
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -833,6 +848,10 @@ static int map_create(union bpf_attr *attr)
 		return -EINVAL;
 	}
 
+	if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
+	    attr->map_extra != 0)
+		return -EINVAL;
+
 	f_flags = bpf_get_file_flag(attr->map_flags);
 	if (f_flags < 0)
 		return f_flags;
@@ -1082,6 +1101,14 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!value)
 		goto free_key;
 
+	if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
+		if (copy_from_user(value, uvalue, value_size))
+			err = -EFAULT;
+		else
+			err = bpf_map_copy_value(map, key, value, attr->flags);
+		goto free_value;
+	}
+
 	err = bpf_map_copy_value(map, key, value, attr->flags);
 	if (err)
 		goto free_value;
@@ -1122,6 +1149,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1157,6 +1185,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1179,6 +1208,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1209,6 +1239,7 @@ static int map_delete_elem(union bpf_attr *attr)
 out:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1516,6 +1547,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
 	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
@@ -1580,6 +1612,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1607,8 +1640,7 @@ static int map_freeze(const union bpf_attr *attr)
 	}
 
 	mutex_lock(&map->freeze_mutex);
-
-	if (map->writecnt) {
+	if (bpf_map_write_active(map)) {
 		err = -EBUSY;
 		goto err_put;
 	}
@@ -1807,8 +1839,14 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+struct bpf_prog_kstats {
+	u64 nsecs;
+	u64 cnt;
+	u64 misses;
+};
+
 static void bpf_prog_get_stats(const struct bpf_prog *prog,
-			       struct bpf_prog_stats *stats)
+			       struct bpf_prog_kstats *stats)
 {
 	u64 nsecs = 0, cnt = 0, misses = 0;
 	int cpu;
@@ -1821,9 +1859,9 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog,
 		st = per_cpu_ptr(prog->stats, cpu);
 		do {
 			start = u64_stats_fetch_begin_irq(&st->syncp);
-			tnsecs = st->nsecs;
-			tcnt = st->cnt;
-			tmisses = st->misses;
+			tnsecs = u64_stats_read(&st->nsecs);
+			tcnt = u64_stats_read(&st->cnt);
+			tmisses = u64_stats_read(&st->misses);
 		} while (u64_stats_fetch_retry_irq(&st->syncp, start));
 		nsecs += tnsecs;
 		cnt += tcnt;
@@ -1839,7 +1877,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_prog *prog = filp->private_data;
 	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
-	struct bpf_prog_stats stats;
+	struct bpf_prog_kstats stats;
 
 	bpf_prog_get_stats(prog, &stats);
 	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
@@ -1851,7 +1889,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "prog_id:\t%u\n"
 		   "run_time_ns:\t%llu\n"
 		   "run_cnt:\t%llu\n"
-		   "recursion_misses:\t%llu\n",
+		   "recursion_misses:\t%llu\n"
+		   "verified_insns:\t%u\n",
 		   prog->type,
 		   prog->jited,
 		   prog_tag,
@@ -1859,7 +1898,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 		   prog->aux->id,
 		   stats.nsecs,
 		   stats.cnt,
-		   stats.misses);
+		   stats.misses,
+		   prog->aux->verified_insns);
 }
 #endif
 
@@ -2159,7 +2199,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD fd_array
+#define	BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 {
@@ -3578,7 +3618,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
 	struct bpf_prog_info info;
 	u32 info_len = attr->info.info_len;
-	struct bpf_prog_stats stats;
+	struct bpf_prog_kstats stats;
 	char __user *uinsns;
 	u32 ulen;
 	int err;
@@ -3628,6 +3668,8 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	info.run_cnt = stats.cnt;
 	info.recursion_misses = stats.misses;
 
+	info.verified_insns = prog->aux->verified_insns;
+
 	if (!bpf_capable()) {
 		info.jited_prog_len = 0;
 		info.xlated_prog_len = 0;
@@ -3874,6 +3916,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	info.value_size = map->value_size;
 	info.max_entries = map->max_entries;
 	info.map_flags = map->map_flags;
+	info.map_extra = map->map_extra;
 	memcpy(info.name, map->name, sizeof(map->name));
 
 	if (map->btf) {
@@ -4143,6 +4186,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr,
 			    int cmd)
 {
+	bool has_read  = cmd == BPF_MAP_LOOKUP_BATCH ||
+			 cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+	bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
 	struct bpf_map *map;
 	int err, ufd;
 	struct fd f;
@@ -4155,16 +4201,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if ((cmd == BPF_MAP_LOOKUP_BATCH ||
-	     cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+	if (has_write)
+		bpf_map_write_active_inc(map);
+	if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
-
-	if (cmd != BPF_MAP_LOOKUP_BATCH &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -4177,8 +4220,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 		BPF_DO_BATCH(map->ops->map_update_batch);
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch);
-
 err_put:
+	if (has_write)
+		bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -4729,7 +4773,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
@@ -4756,6 +4800,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = {
 	.arg1_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res)
+{
+	if (flags)
+		return -EINVAL;
+
+	if (name_sz <= 1 || name[name_sz - 1])
+		return -EINVAL;
+
+	if (!bpf_dump_raw_ok(current_cred()))
+		return -EPERM;
+
+	*res = kallsyms_lookup_name(name);
+	return *res ? 0 : -ENOENT;
+}
+
+const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = {
+	.func		= bpf_kallsyms_lookup_name,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_LONG,
+};
+
 static const struct bpf_func_proto *
 syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -4766,6 +4835,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
 		return &bpf_sys_close_proto;
+	case BPF_FUNC_kallsyms_lookup_name:
+		return &bpf_kallsyms_lookup_name_proto;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index b48750bfba5a..d94696198ef8 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -8,6 +8,7 @@
 #include <linux/fdtable.h>
 #include <linux/filter.h>
 #include <linux/btf_ids.h>
+#include "mmap_unlock_work.h"
 
 struct bpf_iter_seq_task_common {
 	struct pid_namespace *ns;
@@ -524,10 +525,6 @@ static const struct seq_operations task_vma_seq_ops = {
 	.show	= task_vma_seq_show,
 };
 
-BTF_ID_LIST(btf_task_file_ids)
-BTF_ID(struct, file)
-BTF_ID(struct, vm_area_struct)
-
 static const struct bpf_iter_seq_info task_seq_info = {
 	.seq_ops		= &task_seq_ops,
 	.init_seq_private	= init_seq_pidns,
@@ -586,23 +583,88 @@ static struct bpf_iter_reg task_vma_reg_info = {
 	.seq_info		= &task_vma_seq_info,
 };
 
+BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
+	   bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags)
+{
+	struct mmap_unlock_irq_work *work = NULL;
+	struct vm_area_struct *vma;
+	bool irq_work_busy = false;
+	struct mm_struct *mm;
+	int ret = -ENOENT;
+
+	if (flags)
+		return -EINVAL;
+
+	if (!task)
+		return -ENOENT;
+
+	mm = task->mm;
+	if (!mm)
+		return -ENOENT;
+
+	irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
+
+	if (irq_work_busy || !mmap_read_trylock(mm))
+		return -EBUSY;
+
+	vma = find_vma(mm, start);
+
+	if (vma && vma->vm_start <= start && vma->vm_end > start) {
+		callback_fn((u64)(long)task, (u64)(long)vma,
+			    (u64)(long)callback_ctx, 0, 0);
+		ret = 0;
+	}
+	bpf_mmap_unlock_mm(work, mm);
+	return ret;
+}
+
+const struct bpf_func_proto bpf_find_vma_proto = {
+	.func		= bpf_find_vma,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_FUNC,
+	.arg4_type	= ARG_PTR_TO_STACK_OR_NULL,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
+
+static void do_mmap_read_unlock(struct irq_work *entry)
+{
+	struct mmap_unlock_irq_work *work;
+
+	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
+		return;
+
+	work = container_of(entry, struct mmap_unlock_irq_work, irq_work);
+	mmap_read_unlock_non_owner(work->mm);
+}
+
 static int __init task_iter_init(void)
 {
-	int ret;
+	struct mmap_unlock_irq_work *work;
+	int ret, cpu;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&mmap_unlock_work, cpu);
+		init_irq_work(&work->irq_work, do_mmap_read_unlock);
+	}
 
-	task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0];
+	task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
 	ret = bpf_iter_reg_target(&task_reg_info);
 	if (ret)
 		return ret;
 
-	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0];
-	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0];
+	task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
+	task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE];
 	ret =  bpf_iter_reg_target(&task_file_reg_info);
 	if (ret)
 		return ret;
 
-	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0];
-	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
+	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
+	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
 	return bpf_iter_reg_target(&task_vma_reg_info);
 }
 late_initcall(task_iter_init);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index fe1e857324e6..5e7edf913060 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -10,6 +10,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/module.h>
+#include <linux/static_call.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -26,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
 /* serializes access to trampoline_table */
 static DEFINE_MUTEX(trampoline_mutex);
 
+bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
+{
+	enum bpf_attach_type eatype = prog->expected_attach_type;
+
+	return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
+	       eatype == BPF_MODIFY_RETURN;
+}
+
 void *bpf_jit_alloc_exec_page(void)
 {
 	void *image;
@@ -526,7 +535,7 @@ out:
 }
 
 #define NO_START_TIME 1
-static u64 notrace bpf_prog_start_time(void)
+static __always_inline u64 notrace bpf_prog_start_time(void)
 {
 	u64 start = NO_START_TIME;
 
@@ -541,11 +550,12 @@ static u64 notrace bpf_prog_start_time(void)
 static void notrace inc_misses_counter(struct bpf_prog *prog)
 {
 	struct bpf_prog_stats *stats;
+	unsigned int flags;
 
 	stats = this_cpu_ptr(prog->stats);
-	u64_stats_update_begin(&stats->syncp);
-	stats->misses++;
-	u64_stats_update_end(&stats->syncp);
+	flags = u64_stats_update_begin_irqsave(&stats->syncp);
+	u64_stats_inc(&stats->misses);
+	u64_stats_update_end_irqrestore(&stats->syncp, flags);
 }
 
 /* The logic is similar to bpf_prog_run(), but with an explicit
@@ -585,11 +595,13 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
 	     * Hence check that 'start' is valid.
 	     */
 	    start > NO_START_TIME) {
+		unsigned long flags;
+
 		stats = this_cpu_ptr(prog->stats);
-		u64_stats_update_begin(&stats->syncp);
-		stats->cnt++;
-		stats->nsecs += sched_clock() - start;
-		u64_stats_update_end(&stats->syncp);
+		flags = u64_stats_update_begin_irqsave(&stats->syncp);
+		u64_stats_inc(&stats->cnt);
+		u64_stats_add(&stats->nsecs, sched_clock() - start);
+		u64_stats_update_end_irqrestore(&stats->syncp, flags);
 	}
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e76b55917905..a39eedecc93a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
  */
 #include <uapi/linux/btf.h>
+#include <linux/bpf-cgroup.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
@@ -240,12 +241,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn)
 	       insn->src_reg == BPF_PSEUDO_KFUNC_CALL;
 }
 
-static bool bpf_pseudo_func(const struct bpf_insn *insn)
-{
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
-}
-
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
@@ -299,13 +294,15 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 	WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
 		  "verifier log line truncated - local buffer too short\n");
 
-	n = min(log->len_total - log->len_used - 1, n);
-	log->kbuf[n] = '\0';
-
 	if (log->level == BPF_LOG_KERNEL) {
-		pr_err("BPF:%s\n", log->kbuf);
+		bool newline = n > 0 && log->kbuf[n - 1] == '\n';
+
+		pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n");
 		return;
 	}
+
+	n = min(log->len_total - log->len_used - 1, n);
+	log->kbuf[n] = '\0';
 	if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
 		log->len_used += n;
 	else
@@ -445,18 +442,6 @@ static bool reg_type_not_null(enum bpf_reg_type type)
 		type == PTR_TO_SOCK_COMMON;
 }
 
-static bool reg_type_may_be_null(enum bpf_reg_type type)
-{
-	return type == PTR_TO_MAP_VALUE_OR_NULL ||
-	       type == PTR_TO_SOCKET_OR_NULL ||
-	       type == PTR_TO_SOCK_COMMON_OR_NULL ||
-	       type == PTR_TO_TCP_SOCK_OR_NULL ||
-	       type == PTR_TO_BTF_ID_OR_NULL ||
-	       type == PTR_TO_MEM_OR_NULL ||
-	       type == PTR_TO_RDONLY_BUF_OR_NULL ||
-	       type == PTR_TO_RDWR_BUF_OR_NULL;
-}
-
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return reg->type == PTR_TO_MAP_VALUE &&
@@ -465,12 +450,14 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 
 static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
 {
-	return type == PTR_TO_SOCKET ||
-		type == PTR_TO_SOCKET_OR_NULL ||
-		type == PTR_TO_TCP_SOCK ||
-		type == PTR_TO_TCP_SOCK_OR_NULL ||
-		type == PTR_TO_MEM ||
-		type == PTR_TO_MEM_OR_NULL;
+	return base_type(type) == PTR_TO_SOCKET ||
+		base_type(type) == PTR_TO_TCP_SOCK ||
+		base_type(type) == PTR_TO_MEM;
+}
+
+static bool type_is_rdonly_mem(u32 type)
+{
+	return type & MEM_RDONLY;
 }
 
 static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
@@ -478,14 +465,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
 	return type == ARG_PTR_TO_SOCK_COMMON;
 }
 
-static bool arg_type_may_be_null(enum bpf_arg_type type)
+static bool type_may_be_null(u32 type)
 {
-	return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
-	       type == ARG_PTR_TO_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_CTX_OR_NULL ||
-	       type == ARG_PTR_TO_SOCKET_OR_NULL ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_STACK_OR_NULL;
+	return type & PTR_MAYBE_NULL;
 }
 
 /* Determine whether the function releases some resources allocated by another
@@ -545,39 +527,56 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 	       insn->imm == BPF_CMPXCHG;
 }
 
-/* string representation of 'enum bpf_reg_type' */
-static const char * const reg_type_str[] = {
-	[NOT_INIT]		= "?",
-	[SCALAR_VALUE]		= "inv",
-	[PTR_TO_CTX]		= "ctx",
-	[CONST_PTR_TO_MAP]	= "map_ptr",
-	[PTR_TO_MAP_VALUE]	= "map_value",
-	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
-	[PTR_TO_STACK]		= "fp",
-	[PTR_TO_PACKET]		= "pkt",
-	[PTR_TO_PACKET_META]	= "pkt_meta",
-	[PTR_TO_PACKET_END]	= "pkt_end",
-	[PTR_TO_FLOW_KEYS]	= "flow_keys",
-	[PTR_TO_SOCKET]		= "sock",
-	[PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
-	[PTR_TO_SOCK_COMMON]	= "sock_common",
-	[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
-	[PTR_TO_TCP_SOCK]	= "tcp_sock",
-	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
-	[PTR_TO_TP_BUFFER]	= "tp_buffer",
-	[PTR_TO_XDP_SOCK]	= "xdp_sock",
-	[PTR_TO_BTF_ID]		= "ptr_",
-	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
-	[PTR_TO_PERCPU_BTF_ID]	= "percpu_ptr_",
-	[PTR_TO_MEM]		= "mem",
-	[PTR_TO_MEM_OR_NULL]	= "mem_or_null",
-	[PTR_TO_RDONLY_BUF]	= "rdonly_buf",
-	[PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
-	[PTR_TO_RDWR_BUF]	= "rdwr_buf",
-	[PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
-	[PTR_TO_FUNC]		= "func",
-	[PTR_TO_MAP_KEY]	= "map_key",
-};
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+static const char *reg_type_str(struct bpf_verifier_env *env,
+				enum bpf_reg_type type)
+{
+	char postfix[16] = {0}, prefix[16] = {0};
+	static const char * const str[] = {
+		[NOT_INIT]		= "?",
+		[SCALAR_VALUE]		= "inv",
+		[PTR_TO_CTX]		= "ctx",
+		[CONST_PTR_TO_MAP]	= "map_ptr",
+		[PTR_TO_MAP_VALUE]	= "map_value",
+		[PTR_TO_STACK]		= "fp",
+		[PTR_TO_PACKET]		= "pkt",
+		[PTR_TO_PACKET_META]	= "pkt_meta",
+		[PTR_TO_PACKET_END]	= "pkt_end",
+		[PTR_TO_FLOW_KEYS]	= "flow_keys",
+		[PTR_TO_SOCKET]		= "sock",
+		[PTR_TO_SOCK_COMMON]	= "sock_common",
+		[PTR_TO_TCP_SOCK]	= "tcp_sock",
+		[PTR_TO_TP_BUFFER]	= "tp_buffer",
+		[PTR_TO_XDP_SOCK]	= "xdp_sock",
+		[PTR_TO_BTF_ID]		= "ptr_",
+		[PTR_TO_PERCPU_BTF_ID]	= "percpu_ptr_",
+		[PTR_TO_MEM]		= "mem",
+		[PTR_TO_BUF]		= "buf",
+		[PTR_TO_FUNC]		= "func",
+		[PTR_TO_MAP_KEY]	= "map_key",
+	};
+
+	if (type & PTR_MAYBE_NULL) {
+		if (base_type(type) == PTR_TO_BTF_ID ||
+		    base_type(type) == PTR_TO_PERCPU_BTF_ID)
+			strncpy(postfix, "or_null_", 16);
+		else
+			strncpy(postfix, "_or_null", 16);
+	}
+
+	if (type & MEM_RDONLY)
+		strncpy(prefix, "rdonly_", 16);
+	if (type & MEM_ALLOC)
+		strncpy(prefix, "alloc_", 16);
+
+	snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
+		 prefix, str[base_type(type)], postfix);
+	return env->type_str_buf;
+}
 
 static char slot_type_char[] = {
 	[STACK_INVALID]	= '?',
@@ -612,8 +611,61 @@ static const char *kernel_type_name(const struct btf* btf, u32 id)
 	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
+static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+	env->scratched_regs |= 1U << regno;
+}
+
+static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+	env->scratched_stack_slots |= 1ULL << spi;
+}
+
+static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+	return (env->scratched_regs >> regno) & 1;
+}
+
+static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+	return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+	return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = 0U;
+	env->scratched_stack_slots = 0ULL;
+}
+
+/* Used for printing the entire verifier state. */
+static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = ~0U;
+	env->scratched_stack_slots = ~0ULL;
+}
+
+/* The reg state of a pointer or a bounded scalar was saved when
+ * it was spilled to the stack.
+ */
+static bool is_spilled_reg(const struct bpf_stack_state *stack)
+{
+	return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
+}
+
+static void scrub_spilled_slot(u8 *stype)
+{
+	if (*stype != STACK_INVALID)
+		*stype = STACK_MISC;
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
-				 const struct bpf_func_state *state)
+				 const struct bpf_func_state *state,
+				 bool print_all)
 {
 	const struct bpf_reg_state *reg;
 	enum bpf_reg_type t;
@@ -626,9 +678,11 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 		t = reg->type;
 		if (t == NOT_INIT)
 			continue;
+		if (!print_all && !reg_scratched(env, i))
+			continue;
 		verbose(env, " R%d", i);
 		print_liveness(env, reg->live);
-		verbose(env, "=%s", reg_type_str[t]);
+		verbose(env, "=%s", reg_type_str(env, t));
 		if (t == SCALAR_VALUE && reg->precise)
 			verbose(env, "P");
 		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
@@ -636,9 +690,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
-			if (t == PTR_TO_BTF_ID ||
-			    t == PTR_TO_BTF_ID_OR_NULL ||
-			    t == PTR_TO_PERCPU_BTF_ID)
+			if (base_type(t) == PTR_TO_BTF_ID ||
+			    base_type(t) == PTR_TO_PERCPU_BTF_ID)
 				verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
@@ -647,10 +700,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 				verbose(env, ",off=%d", reg->off);
 			if (type_is_pkt_pointer(t))
 				verbose(env, ",r=%d", reg->range);
-			else if (t == CONST_PTR_TO_MAP ||
-				 t == PTR_TO_MAP_KEY ||
-				 t == PTR_TO_MAP_VALUE ||
-				 t == PTR_TO_MAP_VALUE_OR_NULL)
+			else if (base_type(t) == CONST_PTR_TO_MAP ||
+				 base_type(t) == PTR_TO_MAP_KEY ||
+				 base_type(t) == PTR_TO_MAP_VALUE)
 				verbose(env, ",ks=%d,vs=%d",
 					reg->map_ptr->key_size,
 					reg->map_ptr->value_size);
@@ -715,12 +767,14 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 		types_buf[BPF_REG_SIZE] = 0;
 		if (!valid)
 			continue;
+		if (!print_all && !stack_slot_scratched(env, i))
+			continue;
 		verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 		print_liveness(env, state->stack[i].spilled_ptr.live);
-		if (state->stack[i].slot_type[0] == STACK_SPILL) {
+		if (is_spilled_reg(&state->stack[i])) {
 			reg = &state->stack[i].spilled_ptr;
 			t = reg->type;
-			verbose(env, "=%s", reg_type_str[t]);
+			verbose(env, "=%s", reg_type_str(env, t));
 			if (t == SCALAR_VALUE && reg->precise)
 				verbose(env, "P");
 			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
@@ -740,6 +794,26 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 	if (state->in_async_callback_fn)
 		verbose(env, " async_cb");
 	verbose(env, "\n");
+	mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+static void print_insn_state(struct bpf_verifier_env *env,
+			     const struct bpf_func_state *state)
+{
+	if (env->prev_log_len && env->prev_log_len == env->log.len_used) {
+		/* remove new line character */
+		bpf_vlog_reset(&env->log, env->prev_log_len - 1);
+		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' ');
+	} else {
+		verbose(env, "%d:", env->insn_idx);
+	}
+	print_verifier_state(env, state, false);
 }
 
 /* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1133,8 +1207,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
 
 static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 {
-	switch (reg->type) {
-	case PTR_TO_MAP_VALUE_OR_NULL: {
+	if (base_type(reg->type) == PTR_TO_MAP_VALUE) {
 		const struct bpf_map *map = reg->map_ptr;
 
 		if (map->inner_map_meta) {
@@ -1143,7 +1216,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 			/* transfer reg's id which is unique for every map_lookup_elem
 			 * as UID of the inner map.
 			 */
-			reg->map_uid = reg->id;
+			if (map_value_has_timer(map->inner_map_meta))
+				reg->map_uid = reg->id;
 		} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 			reg->type = PTR_TO_XDP_SOCK;
 		} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -1152,32 +1226,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 		} else {
 			reg->type = PTR_TO_MAP_VALUE;
 		}
-		break;
-	}
-	case PTR_TO_SOCKET_OR_NULL:
-		reg->type = PTR_TO_SOCKET;
-		break;
-	case PTR_TO_SOCK_COMMON_OR_NULL:
-		reg->type = PTR_TO_SOCK_COMMON;
-		break;
-	case PTR_TO_TCP_SOCK_OR_NULL:
-		reg->type = PTR_TO_TCP_SOCK;
-		break;
-	case PTR_TO_BTF_ID_OR_NULL:
-		reg->type = PTR_TO_BTF_ID;
-		break;
-	case PTR_TO_MEM_OR_NULL:
-		reg->type = PTR_TO_MEM;
-		break;
-	case PTR_TO_RDONLY_BUF_OR_NULL:
-		reg->type = PTR_TO_RDONLY_BUF;
-		break;
-	case PTR_TO_RDWR_BUF_OR_NULL:
-		reg->type = PTR_TO_RDWR_BUF;
-		break;
-	default:
-		WARN_ONCE(1, "unknown nullable register type");
+		return;
 	}
+
+	reg->type &= ~PTR_MAYBE_NULL;
 }
 
 static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
@@ -1357,22 +1409,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
 
+static bool __reg32_bound_s64(s32 a)
+{
+	return a >= 0 && a <= S32_MAX;
+}
+
 static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 {
 	reg->umin_value = reg->u32_min_value;
 	reg->umax_value = reg->u32_max_value;
-	/* Attempt to pull 32-bit signed bounds into 64-bit bounds
-	 * but must be positive otherwise set to worse case bounds
-	 * and refine later from tnum.
+
+	/* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+	 * be positive otherwise set to worse case bounds and refine later
+	 * from tnum.
 	 */
-	if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
-		reg->smax_value = reg->s32_max_value;
-	else
-		reg->smax_value = U32_MAX;
-	if (reg->s32_min_value >= 0)
+	if (__reg32_bound_s64(reg->s32_min_value) &&
+	    __reg32_bound_s64(reg->s32_max_value)) {
 		reg->smin_value = reg->s32_min_value;
-	else
+		reg->smax_value = reg->s32_max_value;
+	} else {
 		reg->smin_value = 0;
+		reg->smax_value = U32_MAX;
+	}
 }
 
 static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -1406,12 +1464,12 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
 
 static bool __reg64_bound_s32(s64 a)
 {
-	return a > S32_MIN && a < S32_MAX;
+	return a >= S32_MIN && a <= S32_MAX;
 }
 
 static bool __reg64_bound_u32(u64 a)
 {
-	return a > U32_MIN && a < U32_MAX;
+	return a >= U32_MIN && a <= U32_MAX;
 }
 
 static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
@@ -1529,6 +1587,7 @@ static void init_func_state(struct bpf_verifier_env *env,
 	state->frameno = frameno;
 	state->subprogno = subprogno;
 	init_reg_state(env, state);
+	mark_verifier_state_scratched(env);
 }
 
 /* Similar to push_stack(), but for async callbacks */
@@ -1626,52 +1685,168 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
 	return env->subprog_cnt - 1;
 }
 
+#define MAX_KFUNC_DESCS 256
+#define MAX_KFUNC_BTFS	256
+
 struct bpf_kfunc_desc {
 	struct btf_func_model func_model;
 	u32 func_id;
 	s32 imm;
+	u16 offset;
+};
+
+struct bpf_kfunc_btf {
+	struct btf *btf;
+	struct module *module;
+	u16 offset;
 };
 
-#define MAX_KFUNC_DESCS 256
 struct bpf_kfunc_desc_tab {
 	struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS];
 	u32 nr_descs;
 };
 
-static int kfunc_desc_cmp_by_id(const void *a, const void *b)
+struct bpf_kfunc_btf_tab {
+	struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS];
+	u32 nr_descs;
+};
+
+static int kfunc_desc_cmp_by_id_off(const void *a, const void *b)
 {
 	const struct bpf_kfunc_desc *d0 = a;
 	const struct bpf_kfunc_desc *d1 = b;
 
 	/* func_id is not greater than BTF_MAX_TYPE */
-	return d0->func_id - d1->func_id;
+	return d0->func_id - d1->func_id ?: d0->offset - d1->offset;
+}
+
+static int kfunc_btf_cmp_by_off(const void *a, const void *b)
+{
+	const struct bpf_kfunc_btf *d0 = a;
+	const struct bpf_kfunc_btf *d1 = b;
+
+	return d0->offset - d1->offset;
 }
 
 static const struct bpf_kfunc_desc *
-find_kfunc_desc(const struct bpf_prog *prog, u32 func_id)
+find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset)
 {
 	struct bpf_kfunc_desc desc = {
 		.func_id = func_id,
+		.offset = offset,
 	};
 	struct bpf_kfunc_desc_tab *tab;
 
 	tab = prog->aux->kfunc_tab;
 	return bsearch(&desc, tab->descs, tab->nr_descs,
-		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id);
+		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off);
+}
+
+static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
+					 s16 offset, struct module **btf_modp)
+{
+	struct bpf_kfunc_btf kf_btf = { .offset = offset };
+	struct bpf_kfunc_btf_tab *tab;
+	struct bpf_kfunc_btf *b;
+	struct module *mod;
+	struct btf *btf;
+	int btf_fd;
+
+	tab = env->prog->aux->kfunc_btf_tab;
+	b = bsearch(&kf_btf, tab->descs, tab->nr_descs,
+		    sizeof(tab->descs[0]), kfunc_btf_cmp_by_off);
+	if (!b) {
+		if (tab->nr_descs == MAX_KFUNC_BTFS) {
+			verbose(env, "too many different module BTFs\n");
+			return ERR_PTR(-E2BIG);
+		}
+
+		if (bpfptr_is_null(env->fd_array)) {
+			verbose(env, "kfunc offset > 0 without fd_array is invalid\n");
+			return ERR_PTR(-EPROTO);
+		}
+
+		if (copy_from_bpfptr_offset(&btf_fd, env->fd_array,
+					    offset * sizeof(btf_fd),
+					    sizeof(btf_fd)))
+			return ERR_PTR(-EFAULT);
+
+		btf = btf_get_by_fd(btf_fd);
+		if (IS_ERR(btf)) {
+			verbose(env, "invalid module BTF fd specified\n");
+			return btf;
+		}
+
+		if (!btf_is_module(btf)) {
+			verbose(env, "BTF fd for kfunc is not a module BTF\n");
+			btf_put(btf);
+			return ERR_PTR(-EINVAL);
+		}
+
+		mod = btf_try_get_module(btf);
+		if (!mod) {
+			btf_put(btf);
+			return ERR_PTR(-ENXIO);
+		}
+
+		b = &tab->descs[tab->nr_descs++];
+		b->btf = btf;
+		b->module = mod;
+		b->offset = offset;
+
+		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
+		     kfunc_btf_cmp_by_off, NULL);
+	}
+	if (btf_modp)
+		*btf_modp = b->module;
+	return b->btf;
+}
+
+void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab)
+{
+	if (!tab)
+		return;
+
+	while (tab->nr_descs--) {
+		module_put(tab->descs[tab->nr_descs].module);
+		btf_put(tab->descs[tab->nr_descs].btf);
+	}
+	kfree(tab);
+}
+
+static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env,
+				       u32 func_id, s16 offset,
+				       struct module **btf_modp)
+{
+	if (offset) {
+		if (offset < 0) {
+			/* In the future, this can be allowed to increase limit
+			 * of fd index into fd_array, interpreted as u16.
+			 */
+			verbose(env, "negative offset disallowed for kernel module function call\n");
+			return ERR_PTR(-EINVAL);
+		}
+
+		return __find_kfunc_desc_btf(env, offset, btf_modp);
+	}
+	return btf_vmlinux ?: ERR_PTR(-ENOENT);
 }
 
-static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
+static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
 {
 	const struct btf_type *func, *func_proto;
+	struct bpf_kfunc_btf_tab *btf_tab;
 	struct bpf_kfunc_desc_tab *tab;
 	struct bpf_prog_aux *prog_aux;
 	struct bpf_kfunc_desc *desc;
 	const char *func_name;
+	struct btf *desc_btf;
 	unsigned long addr;
 	int err;
 
 	prog_aux = env->prog->aux;
 	tab = prog_aux->kfunc_tab;
+	btf_tab = prog_aux->kfunc_btf_tab;
 	if (!tab) {
 		if (!btf_vmlinux) {
 			verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n");
@@ -1699,7 +1874,29 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 		prog_aux->kfunc_tab = tab;
 	}
 
-	if (find_kfunc_desc(env->prog, func_id))
+	/* func_id == 0 is always invalid, but instead of returning an error, be
+	 * conservative and wait until the code elimination pass before returning
+	 * error, so that invalid calls that get pruned out can be in BPF programs
+	 * loaded from userspace.  It is also required that offset be untouched
+	 * for such calls.
+	 */
+	if (!func_id && !offset)
+		return 0;
+
+	if (!btf_tab && offset) {
+		btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL);
+		if (!btf_tab)
+			return -ENOMEM;
+		prog_aux->kfunc_btf_tab = btf_tab;
+	}
+
+	desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL);
+	if (IS_ERR(desc_btf)) {
+		verbose(env, "failed to find BTF for kernel function\n");
+		return PTR_ERR(desc_btf);
+	}
+
+	if (find_kfunc_desc(env->prog, func_id, offset))
 		return 0;
 
 	if (tab->nr_descs == MAX_KFUNC_DESCS) {
@@ -1707,20 +1904,20 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 		return -E2BIG;
 	}
 
-	func = btf_type_by_id(btf_vmlinux, func_id);
+	func = btf_type_by_id(desc_btf, func_id);
 	if (!func || !btf_type_is_func(func)) {
 		verbose(env, "kernel btf_id %u is not a function\n",
 			func_id);
 		return -EINVAL;
 	}
-	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+	func_proto = btf_type_by_id(desc_btf, func->type);
 	if (!func_proto || !btf_type_is_func_proto(func_proto)) {
 		verbose(env, "kernel function btf_id %u does not have a valid func_proto\n",
 			func_id);
 		return -EINVAL;
 	}
 
-	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
+	func_name = btf_name_by_offset(desc_btf, func->name_off);
 	addr = kallsyms_lookup_name(func_name);
 	if (!addr) {
 		verbose(env, "cannot find address for kernel function %s\n",
@@ -1730,13 +1927,14 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 
 	desc = &tab->descs[tab->nr_descs++];
 	desc->func_id = func_id;
-	desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
-	err = btf_distill_func_proto(&env->log, btf_vmlinux,
+	desc->imm = BPF_CALL_IMM(addr);
+	desc->offset = offset;
+	err = btf_distill_func_proto(&env->log, desc_btf,
 				     func_proto, func_name,
 				     &desc->func_model);
 	if (!err)
 		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
-		     kfunc_desc_cmp_by_id, NULL);
+		     kfunc_desc_cmp_by_id_off, NULL);
 	return err;
 }
 
@@ -1807,16 +2005,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			return -EPERM;
 		}
 
-		if (bpf_pseudo_func(insn)) {
+		if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn))
 			ret = add_subprog(env, i + insn->imm + 1);
-			if (ret >= 0)
-				/* remember subprog */
-				insn[1].imm = ret;
-		} else if (bpf_pseudo_call(insn)) {
-			ret = add_subprog(env, i + insn->imm + 1);
-		} else {
-			ret = add_kfunc_call(env, insn->imm);
-		}
+		else
+			ret = add_kfunc_call(env, insn->imm, insn->off);
 
 		if (ret < 0)
 			return ret;
@@ -1899,7 +2091,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 			break;
 		if (parent->live & REG_LIVE_DONE) {
 			verbose(env, "verifier BUG type %s var_off %lld off %d\n",
-				reg_type_str[parent->type],
+				reg_type_str(env, parent->type),
 				parent->var_off.value, parent->off);
 			return -EFAULT;
 		}
@@ -2083,6 +2275,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 		return -EINVAL;
 	}
 
+	mark_reg_scratched(env, regno);
+
 	reg = &regs[regno];
 	rw64 = is_reg64(env, insn, regno, reg, t);
 	if (t == SRC_OP) {
@@ -2152,12 +2346,17 @@ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
 {
 	const struct btf_type *func;
+	struct btf *desc_btf;
 
 	if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
 		return NULL;
 
-	func = btf_type_by_id(btf_vmlinux, insn->imm);
-	return btf_name_by_offset(btf_vmlinux, func->name_off);
+	desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL);
+	if (IS_ERR(desc_btf))
+		return "<error>";
+
+	func = btf_type_by_id(desc_btf, insn->imm);
+	return btf_name_by_offset(desc_btf, func->name_off);
 }
 
 /* For given verifier state backtrack_insn() is called from the last insn to
@@ -2182,7 +2381,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 
 	if (insn->code == 0)
 		return 0;
-	if (env->log.level & BPF_LOG_LEVEL) {
+	if (env->log.level & BPF_LOG_LEVEL2) {
 		verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
 		verbose(env, "%d: ", idx);
 		print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
@@ -2232,8 +2431,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		 */
 		if (insn->src_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
@@ -2256,8 +2453,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		/* scalars can only be spilled into stack */
 		if (insn->dst_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 		spi = (-insn->off - 1) / BPF_REG_SIZE;
 		if (spi >= 64) {
 			verbose(env, "BUG spi %d\n", spi);
@@ -2373,7 +2568,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 				reg->precise = true;
 			}
 			for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
-				if (func->stack[j].slot_type[0] != STACK_SPILL)
+				if (!is_spilled_reg(&func->stack[j]))
 					continue;
 				reg = &func->stack[j].spilled_ptr;
 				if (reg->type != SCALAR_VALUE)
@@ -2415,7 +2610,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	}
 
 	while (spi >= 0) {
-		if (func->stack[spi].slot_type[0] != STACK_SPILL) {
+		if (!is_spilled_reg(&func->stack[spi])) {
 			stack_mask = 0;
 			break;
 		}
@@ -2440,7 +2635,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
 
-		if (env->log.level & BPF_LOG_LEVEL)
+		if (env->log.level & BPF_LOG_LEVEL2)
 			verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
 		for (i = last_idx;;) {
 			if (skip_first) {
@@ -2514,7 +2709,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 				return 0;
 			}
 
-			if (func->stack[i].slot_type[0] != STACK_SPILL) {
+			if (!is_spilled_reg(&func->stack[i])) {
 				stack_mask &= ~(1ull << i);
 				continue;
 			}
@@ -2527,11 +2722,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 				new_marks = true;
 			reg->precise = true;
 		}
-		if (env->log.level & BPF_LOG_LEVEL) {
-			print_verifier_state(env, func);
-			verbose(env, "parent %s regs=%x stack=%llx marks\n",
+		if (env->log.level & BPF_LOG_LEVEL2) {
+			verbose(env, "parent %s regs=%x stack=%llx marks:",
 				new_marks ? "didn't have" : "already had",
 				reg_mask, stack_mask);
+			print_verifier_state(env, func, true);
 		}
 
 		if (!reg_mask && !stack_mask)
@@ -2557,9 +2752,8 @@ static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi)
 
 static bool is_spillable_regtype(enum bpf_reg_type type)
 {
-	switch (type) {
+	switch (base_type(type)) {
 	case PTR_TO_MAP_VALUE:
-	case PTR_TO_MAP_VALUE_OR_NULL:
 	case PTR_TO_STACK:
 	case PTR_TO_CTX:
 	case PTR_TO_PACKET:
@@ -2568,21 +2762,13 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_FLOW_KEYS:
 	case CONST_PTR_TO_MAP:
 	case PTR_TO_SOCKET:
-	case PTR_TO_SOCKET_OR_NULL:
 	case PTR_TO_SOCK_COMMON:
-	case PTR_TO_SOCK_COMMON_OR_NULL:
 	case PTR_TO_TCP_SOCK:
-	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
-	case PTR_TO_BTF_ID_OR_NULL:
-	case PTR_TO_RDONLY_BUF:
-	case PTR_TO_RDONLY_BUF_OR_NULL:
-	case PTR_TO_RDWR_BUF:
-	case PTR_TO_RDWR_BUF_OR_NULL:
+	case PTR_TO_BUF:
 	case PTR_TO_PERCPU_BTF_ID:
 	case PTR_TO_MEM:
-	case PTR_TO_MEM_OR_NULL:
 	case PTR_TO_FUNC:
 	case PTR_TO_MAP_KEY:
 		return true;
@@ -2626,15 +2812,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 }
 
 static void save_register_state(struct bpf_func_state *state,
-				int spi, struct bpf_reg_state *reg)
+				int spi, struct bpf_reg_state *reg,
+				int size)
 {
 	int i;
 
 	state->stack[spi].spilled_ptr = *reg;
-	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+	if (size == BPF_REG_SIZE)
+		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 
-	for (i = 0; i < BPF_REG_SIZE; i++)
-		state->stack[spi].slot_type[i] = STACK_SPILL;
+	for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--)
+		state->stack[spi].slot_type[i - 1] = STACK_SPILL;
+
+	/* size < 8 bytes spill */
+	for (; i; i--)
+		scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
 }
 
 /* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
@@ -2681,7 +2873,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
 	}
 
-	if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
+	mark_stack_slot_scratched(env, spi);
+	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
 	    !register_is_null(reg) && env->bpf_capable) {
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
@@ -2694,7 +2887,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			if (err)
 				return err;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -2706,16 +2899,16 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
 			return -EINVAL;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else {
 		u8 type = STACK_MISC;
 
 		/* regular write of data into stack destroys any spilled ptr */
 		state->stack[spi].spilled_ptr.type = NOT_INIT;
 		/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
-		if (state->stack[spi].slot_type[0] == STACK_SPILL)
+		if (is_spilled_reg(&state->stack[spi]))
 			for (i = 0; i < BPF_REG_SIZE; i++)
-				state->stack[spi].slot_type[i] = STACK_MISC;
+				scrub_spilled_slot(&state->stack[spi].slot_type[i]);
 
 		/* only mark the slot as written if all 8 bytes were written
 		 * otherwise read propagation may incorrectly stop too soon
@@ -2802,6 +2995,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
 		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
 		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+		mark_stack_slot_scratched(env, spi);
 
 		if (!env->allow_ptr_leaks
 				&& *stype != NOT_INIT
@@ -2918,31 +3112,52 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
-	u8 *stype;
+	u8 *stype, type;
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
 
-	if (stype[0] == STACK_SPILL) {
-		if (size != BPF_REG_SIZE) {
+	if (is_spilled_reg(&reg_state->stack[spi])) {
+		u8 spill_size = 1;
+
+		for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--)
+			spill_size++;
+
+		if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) {
 			if (reg->type != SCALAR_VALUE) {
 				verbose_linfo(env, env->insn_idx, "; ");
 				verbose(env, "invalid size of register fill\n");
 				return -EACCES;
 			}
-			if (dst_regno >= 0) {
+
+			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			if (dst_regno < 0)
+				return 0;
+
+			if (!(off % BPF_REG_SIZE) && size == spill_size) {
+				/* The earlier check_reg_arg() has decided the
+				 * subreg_def for this insn.  Save it first.
+				 */
+				s32 subreg_def = state->regs[dst_regno].subreg_def;
+
+				state->regs[dst_regno] = *reg;
+				state->regs[dst_regno].subreg_def = subreg_def;
+			} else {
+				for (i = 0; i < size; i++) {
+					type = stype[(slot - i) % BPF_REG_SIZE];
+					if (type == STACK_SPILL)
+						continue;
+					if (type == STACK_MISC)
+						continue;
+					verbose(env, "invalid read from stack off %d+%d size %d\n",
+						off, i, size);
+					return -EACCES;
+				}
 				mark_reg_unknown(env, state->regs, dst_regno);
-				state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			}
-			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			return 0;
 		}
-		for (i = 1; i < BPF_REG_SIZE; i++) {
-			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
-				verbose(env, "corrupted spill memory\n");
-				return -EACCES;
-			}
-		}
 
 		if (dst_regno >= 0) {
 			/* restore register state from stack */
@@ -2965,8 +3180,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
-		u8 type;
-
 		for (i = 0; i < size; i++) {
 			type = stype[(slot - i) % BPF_REG_SIZE];
 			if (type == STACK_MISC)
@@ -3199,11 +3412,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
 	/* We may have adjusted the register pointing to memory region, so we
 	 * need to try adding each of min_value and max_value to off
 	 * to make sure our theoretical access will be safe.
-	 */
-	if (env->log.level & BPF_LOG_LEVEL)
-		print_verifier_state(env, state);
-
-	/* The minimum value is only important with signed
+	 *
+	 * The minimum value is only important with signed
 	 * comparisons where we can't assume the floor of a
 	 * value is 0.  If we are using signed variables for our
 	 * index'es we need to make sure that whatever we use
@@ -3398,7 +3608,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
+		if (base_type(*reg_type) == PTR_TO_BTF_ID) {
 			*btf = info.btf;
 			*btf_id = info.btf_id;
 		} else {
@@ -3466,7 +3676,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
 	}
 
 	verbose(env, "R%d invalid %s access off=%d size=%d\n",
-		regno, reg_type_str[reg->type], off, size);
+		regno, reg_type_str(env, reg->type), off, size);
 
 	return -EACCES;
 }
@@ -3761,16 +3971,17 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 }
 #endif
 
-int check_ctx_reg(struct bpf_verifier_env *env,
-		  const struct bpf_reg_state *reg, int regno)
+static int __check_ptr_off_reg(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg, int regno,
+			       bool fixed_off_ok)
 {
-	/* Access to ctx or passing it to a helper is only allowed in
-	 * its original, unmodified form.
+	/* Access to this pointer-typed register or passing it to a helper
+	 * is only allowed in its original, unmodified form.
 	 */
 
-	if (reg->off) {
-		verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
-			regno, reg->off);
+	if (!fixed_off_ok && reg->off) {
+		verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n",
+			reg_type_str(env, reg->type), regno, reg->off);
 		return -EACCES;
 	}
 
@@ -3778,13 +3989,20 @@ int check_ctx_reg(struct bpf_verifier_env *env,
 		char tn_buf[48];
 
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
+		verbose(env, "variable %s access var_off=%s disallowed\n",
+			reg_type_str(env, reg->type), tn_buf);
 		return -EACCES;
 	}
 
 	return 0;
 }
 
+int check_ptr_off_reg(struct bpf_verifier_env *env,
+		      const struct bpf_reg_state *reg, int regno)
+{
+	return __check_ptr_off_reg(env, reg, regno, false);
+}
+
 static int __check_buffer_access(struct bpf_verifier_env *env,
 				 const char *buf_info,
 				 const struct bpf_reg_state *reg,
@@ -3884,7 +4102,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
-	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+	/* A map is considered read-only if the following condition are true:
+	 *
+	 * 1) BPF program side cannot change any of the map content. The
+	 *    BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+	 *    and was set at map creation time.
+	 * 2) The map value(s) have been initialized from user space by a
+	 *    loader and then "frozen", such that no new map update/delete
+	 *    operations from syscall side are possible for the rest of
+	 *    the map's lifetime from that point onwards.
+	 * 3) Any parallel/pending map update/delete operations from syscall
+	 *    side have been completed. Only after that point, it's safe to
+	 *    assume that map value(s) are immutable.
+	 */
+	return (map->map_flags & BPF_F_RDONLY_PROG) &&
+	       READ_ONCE(map->frozen) &&
+	       !bpf_map_write_active(map);
 }
 
 static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -4178,15 +4411,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				mark_reg_unknown(env, regs, value_regno);
 			}
 		}
-	} else if (reg->type == PTR_TO_MEM) {
+	} else if (base_type(reg->type) == PTR_TO_MEM) {
+		bool rdonly_mem = type_is_rdonly_mem(reg->type);
+
+		if (type_may_be_null(reg->type)) {
+			verbose(env, "R%d invalid mem access '%s'\n", regno,
+				reg_type_str(env, reg->type));
+			return -EACCES;
+		}
+
+		if (t == BPF_WRITE && rdonly_mem) {
+			verbose(env, "R%d cannot write into %s\n",
+				regno, reg_type_str(env, reg->type));
+			return -EACCES;
+		}
+
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose(env, "R%d leaks addr into mem\n", value_regno);
 			return -EACCES;
 		}
+
 		err = check_mem_region_access(env, regno, off, size,
 					      reg->mem_size, false);
-		if (!err && t == BPF_READ && value_regno >= 0)
+		if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
@@ -4199,7 +4447,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			return -EACCES;
 		}
 
-		err = check_ctx_reg(env, reg, regno);
+		err = check_ptr_off_reg(env, reg, regno);
 		if (err < 0)
 			return err;
 
@@ -4216,7 +4464,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			} else {
 				mark_reg_known_zero(env, regs,
 						    value_regno);
-				if (reg_type_may_be_null(reg_type))
+				if (type_may_be_null(reg_type))
 					regs[value_regno].id = ++env->id_gen;
 				/* A load of ctx field could have different
 				 * actual load size with the one encoded in the
@@ -4224,8 +4472,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				 * a sub-register.
 				 */
 				regs[value_regno].subreg_def = DEF_NOT_SUBREG;
-				if (reg_type == PTR_TO_BTF_ID ||
-				    reg_type == PTR_TO_BTF_ID_OR_NULL) {
+				if (base_type(reg_type) == PTR_TO_BTF_ID) {
 					regs[value_regno].btf = btf;
 					regs[value_regno].btf_id = btf_id;
 				}
@@ -4278,7 +4525,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (type_is_sk_pointer(reg->type)) {
 		if (t == BPF_WRITE) {
 			verbose(env, "R%d cannot write into %s\n",
-				regno, reg_type_str[reg->type]);
+				regno, reg_type_str(env, reg->type));
 			return -EACCES;
 		}
 		err = check_sock_access(env, insn_idx, regno, off, size, t);
@@ -4294,26 +4541,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (reg->type == CONST_PTR_TO_MAP) {
 		err = check_ptr_to_map_access(env, regs, regno, off, size, t,
 					      value_regno);
-	} else if (reg->type == PTR_TO_RDONLY_BUF) {
-		if (t == BPF_WRITE) {
-			verbose(env, "R%d cannot write into %s\n",
-				regno, reg_type_str[reg->type]);
-			return -EACCES;
+	} else if (base_type(reg->type) == PTR_TO_BUF) {
+		bool rdonly_mem = type_is_rdonly_mem(reg->type);
+		const char *buf_info;
+		u32 *max_access;
+
+		if (rdonly_mem) {
+			if (t == BPF_WRITE) {
+				verbose(env, "R%d cannot write into %s\n",
+					regno, reg_type_str(env, reg->type));
+				return -EACCES;
+			}
+			buf_info = "rdonly";
+			max_access = &env->prog->aux->max_rdonly_access;
+		} else {
+			buf_info = "rdwr";
+			max_access = &env->prog->aux->max_rdwr_access;
 		}
+
 		err = check_buffer_access(env, reg, regno, off, size, false,
-					  "rdonly",
-					  &env->prog->aux->max_rdonly_access);
-		if (!err && value_regno >= 0)
-			mark_reg_unknown(env, regs, value_regno);
-	} else if (reg->type == PTR_TO_RDWR_BUF) {
-		err = check_buffer_access(env, reg, regno, off, size, false,
-					  "rdwr",
-					  &env->prog->aux->max_rdwr_access);
-		if (!err && t == BPF_READ && value_regno >= 0)
+					  buf_info, max_access);
+
+		if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
-			reg_type_str[reg->type]);
+			reg_type_str(env, reg->type));
 		return -EACCES;
 	}
 
@@ -4364,9 +4617,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 
 	if (insn->imm == BPF_CMPXCHG) {
 		/* Check comparison of R0 with memory location */
-		err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+		const u32 aux_reg = BPF_REG_0;
+
+		err = check_reg_arg(env, aux_reg, SRC_OP);
 		if (err)
 			return err;
+
+		if (is_pointer_value(env, aux_reg)) {
+			verbose(env, "R%d leaks addr into mem\n", aux_reg);
+			return -EACCES;
+		}
 	}
 
 	if (is_pointer_value(env, insn->src_reg)) {
@@ -4380,7 +4640,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	    is_sk_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
 			insn->dst_reg,
-			reg_type_str[reg_state(env, insn->dst_reg)->type]);
+			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
 		return -EACCES;
 	}
 
@@ -4401,13 +4661,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 		load_reg = -1;
 	}
 
-	/* check whether we can read the memory */
+	/* Check whether we can read the memory, with second call for fetch
+	 * case to simulate the register fill.
+	 */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, load_reg, true);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true);
+	if (!err && load_reg >= 0)
+		err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+				       BPF_SIZE(insn->code), BPF_READ, load_reg,
+				       true);
 	if (err)
 		return err;
 
-	/* check whether we can write into the same memory */
+	/* Check whether we can write into the same memory. */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 	if (err)
@@ -4514,17 +4780,17 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
 			goto mark;
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
 		     env->allow_ptr_leaks)) {
 			if (clobber) {
 				__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
 				for (j = 0; j < BPF_REG_SIZE; j++)
-					state->stack[spi].slot_type[j] = STACK_MISC;
+					scrub_spilled_slot(&state->stack[spi].slot_type[j]);
 			}
 			goto mark;
 		}
@@ -4557,8 +4823,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 				   struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	const char *buf_info;
+	u32 *max_access;
 
-	switch (reg->type) {
+	switch (base_type(reg->type)) {
 	case PTR_TO_PACKET:
 	case PTR_TO_PACKET_META:
 		return check_packet_access(env, regno, reg->off, access_size,
@@ -4577,18 +4845,20 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		return check_mem_region_access(env, regno, reg->off,
 					       access_size, reg->mem_size,
 					       zero_size_allowed);
-	case PTR_TO_RDONLY_BUF:
-		if (meta && meta->raw_mode)
-			return -EACCES;
-		return check_buffer_access(env, reg, regno, reg->off,
-					   access_size, zero_size_allowed,
-					   "rdonly",
-					   &env->prog->aux->max_rdonly_access);
-	case PTR_TO_RDWR_BUF:
+	case PTR_TO_BUF:
+		if (type_is_rdonly_mem(reg->type)) {
+			if (meta && meta->raw_mode)
+				return -EACCES;
+
+			buf_info = "rdonly";
+			max_access = &env->prog->aux->max_rdonly_access;
+		} else {
+			buf_info = "rdwr";
+			max_access = &env->prog->aux->max_rdwr_access;
+		}
 		return check_buffer_access(env, reg, regno, reg->off,
 					   access_size, zero_size_allowed,
-					   "rdwr",
-					   &env->prog->aux->max_rdwr_access);
+					   buf_info, max_access);
 	case PTR_TO_STACK:
 		return check_stack_range_initialized(
 				env,
@@ -4600,9 +4870,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		    register_is_null(reg))
 			return 0;
 
-		verbose(env, "R%d type=%s expected=%s\n", regno,
-			reg_type_str[reg->type],
-			reg_type_str[PTR_TO_STACK]);
+		verbose(env, "R%d type=%s ", regno,
+			reg_type_str(env, reg->type));
+		verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK));
 		return -EACCES;
 	}
 }
@@ -4613,7 +4883,7 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 	if (register_is_null(reg))
 		return 0;
 
-	if (reg_type_may_be_null(reg->type)) {
+	if (type_may_be_null(reg->type)) {
 		/* Assuming that the register contains a value check if the memory
 		 * access is safe. Temporarily save and restore the register's state as
 		 * the conversion shouldn't be visible to a caller.
@@ -4761,9 +5031,8 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 
 static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
 {
-	return type == ARG_PTR_TO_MEM ||
-	       type == ARG_PTR_TO_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_UNINIT_MEM;
+	return base_type(type) == ARG_PTR_TO_MEM ||
+	       base_type(type) == ARG_PTR_TO_UNINIT_MEM;
 }
 
 static bool arg_type_is_mem_size(enum bpf_arg_type type)
@@ -4813,7 +5082,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 		break;
-
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		if (meta->func_id == BPF_FUNC_map_peek_elem)
+			*arg_type = ARG_PTR_TO_MAP_VALUE;
+		break;
 	default:
 		break;
 	}
@@ -4865,8 +5137,8 @@ static const struct bpf_reg_types mem_types = {
 		PTR_TO_MAP_KEY,
 		PTR_TO_MAP_VALUE,
 		PTR_TO_MEM,
-		PTR_TO_RDONLY_BUF,
-		PTR_TO_RDWR_BUF,
+		PTR_TO_MEM | MEM_ALLOC,
+		PTR_TO_BUF,
 	},
 };
 
@@ -4883,7 +5155,7 @@ static const struct bpf_reg_types int_ptr_types = {
 static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
 static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
 static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
-static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } };
 static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
 static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
 static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
@@ -4897,31 +5169,26 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
 	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
 	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
-	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
 	[ARG_CONST_SIZE]		= &scalar_types,
 	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
 	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
 	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
 	[ARG_PTR_TO_CTX]		= &context_types,
-	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
 	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
 #ifdef CONFIG_NET
 	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
 #endif
 	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
-	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
 	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
 	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
 	[ARG_PTR_TO_MEM]		= &mem_types,
-	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
 	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
 	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
-	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
 	[ARG_PTR_TO_INT]		= &int_ptr_types,
 	[ARG_PTR_TO_LONG]		= &int_ptr_types,
 	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
 	[ARG_PTR_TO_FUNC]		= &func_ptr_types,
-	[ARG_PTR_TO_STACK_OR_NULL]	= &stack_ptr_types,
+	[ARG_PTR_TO_STACK]		= &stack_ptr_types,
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
 };
@@ -4935,12 +5202,27 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 	const struct bpf_reg_types *compatible;
 	int i, j;
 
-	compatible = compatible_reg_types[arg_type];
+	compatible = compatible_reg_types[base_type(arg_type)];
 	if (!compatible) {
 		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
 		return -EFAULT;
 	}
 
+	/* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY,
+	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY
+	 *
+	 * Same for MAYBE_NULL:
+	 *
+	 * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
+	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
+	 *
+	 * Therefore we fold these flags depending on the arg_type before comparison.
+	 */
+	if (arg_type & MEM_RDONLY)
+		type &= ~MEM_RDONLY;
+	if (arg_type & PTR_MAYBE_NULL)
+		type &= ~PTR_MAYBE_NULL;
+
 	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
 		expected = compatible->types[i];
 		if (expected == NOT_INIT)
@@ -4950,14 +5232,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 			goto found;
 	}
 
-	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type));
 	for (j = 0; j + 1 < i; j++)
-		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
-	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+		verbose(env, "%s, ", reg_type_str(env, compatible->types[j]));
+	verbose(env, "%s\n", reg_type_str(env, compatible->types[j]));
 	return -EACCES;
 
 found:
-	if (type == PTR_TO_BTF_ID) {
+	if (reg->type == PTR_TO_BTF_ID) {
 		if (!arg_btf_id) {
 			if (!compatible->btf_id) {
 				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
@@ -4973,12 +5255,6 @@ found:
 				kernel_type_name(btf_vmlinux, *arg_btf_id));
 			return -EACCES;
 		}
-
-		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
-			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
-				regno);
-			return -EACCES;
-		}
 	}
 
 	return 0;
@@ -5016,15 +5292,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		return -EACCES;
 	}
 
-	if (arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
+	if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+	    base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
 		err = resolve_map_arg_type(env, meta, &arg_type);
 		if (err)
 			return err;
 	}
 
-	if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+	if (register_is_null(reg) && type_may_be_null(arg_type))
 		/* A NULL register has a SCALAR_VALUE type, so skip
 		 * type checking.
 		 */
@@ -5034,10 +5309,33 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	if (err)
 		return err;
 
-	if (type == PTR_TO_CTX) {
-		err = check_ctx_reg(env, reg, regno);
+	switch ((u32)type) {
+	case SCALAR_VALUE:
+	/* Pointer types where reg offset is explicitly allowed: */
+	case PTR_TO_PACKET:
+	case PTR_TO_PACKET_META:
+	case PTR_TO_MAP_KEY:
+	case PTR_TO_MAP_VALUE:
+	case PTR_TO_MEM:
+	case PTR_TO_MEM | MEM_RDONLY:
+	case PTR_TO_MEM | MEM_ALLOC:
+	case PTR_TO_BUF:
+	case PTR_TO_BUF | MEM_RDONLY:
+	case PTR_TO_STACK:
+		/* Some of the argument types nevertheless require a
+		 * zero register offset.
+		 */
+		if (arg_type == ARG_PTR_TO_ALLOC_MEM)
+			goto force_off_check;
+		break;
+	/* All the rest must be rejected: */
+	default:
+force_off_check:
+		err = __check_ptr_off_reg(env, reg, regno,
+					  type == PTR_TO_BTF_ID);
 		if (err < 0)
 			return err;
+		break;
 	}
 
 skip_type_check:
@@ -5093,10 +5391,11 @@ skip_type_check:
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->key_size, false,
 					      NULL);
-	} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
-		   (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
-		    !register_is_null(reg)) ||
-		   arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+	} else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+		   base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+		if (type_may_be_null(arg_type) && register_is_null(reg))
+			return 0;
+
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
 		 */
@@ -5388,6 +5687,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_task_storage_delete)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		if (func_id != BPF_FUNC_map_peek_elem &&
+		    func_id != BPF_FUNC_map_push_elem)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -5455,13 +5759,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
-	case BPF_FUNC_map_peek_elem:
 	case BPF_FUNC_map_pop_elem:
-	case BPF_FUNC_map_push_elem:
 		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
 		    map->map_type != BPF_MAP_TYPE_STACK)
 			goto error;
 		break;
+	case BPF_FUNC_map_peek_elem:
+	case BPF_FUNC_map_push_elem:
+		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
+		    map->map_type != BPF_MAP_TYPE_STACK &&
+		    map->map_type != BPF_MAP_TYPE_BLOOM_FILTER)
+			goto error;
+		break;
 	case BPF_FUNC_sk_storage_get:
 	case BPF_FUNC_sk_storage_delete:
 		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
@@ -5750,6 +6059,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	}
 
 	if (insn->code == (BPF_JMP | BPF_CALL) &&
+	    insn->src_reg == 0 &&
 	    insn->imm == BPF_FUNC_timer_set_callback) {
 		struct bpf_verifier_state *async_cb;
 
@@ -5808,9 +6118,9 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "caller:\n");
-		print_verifier_state(env, caller);
+		print_verifier_state(env, caller, true);
 		verbose(env, "callee:\n");
-		print_verifier_state(env, callee);
+		print_verifier_state(env, callee, true);
 	}
 	return 0;
 }
@@ -5901,6 +6211,27 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int set_loop_callback_state(struct bpf_verifier_env *env,
+				   struct bpf_func_state *caller,
+				   struct bpf_func_state *callee,
+				   int insn_idx)
+{
+	/* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx,
+	 *	    u64 flags);
+	 * callback_fn(u32 index, void *callback_ctx);
+	 */
+	callee->regs[BPF_REG_1].type = SCALAR_VALUE;
+	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+
+	callee->in_callback_fn = true;
+	return 0;
+}
+
 static int set_timer_callback_state(struct bpf_verifier_env *env,
 				    struct bpf_func_state *caller,
 				    struct bpf_func_state *callee,
@@ -5930,6 +6261,33 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int set_find_vma_callback_state(struct bpf_verifier_env *env,
+				       struct bpf_func_state *caller,
+				       struct bpf_func_state *callee,
+				       int insn_idx)
+{
+	/* bpf_find_vma(struct task_struct *task, u64 addr,
+	 *               void *callback_fn, void *callback_ctx, u64 flags)
+	 * (callback_fn)(struct task_struct *task,
+	 *               struct vm_area_struct *vma, void *callback_ctx);
+	 */
+	callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];
+
+	callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
+	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
+	callee->regs[BPF_REG_2].btf =  btf_vmlinux;
+	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA],
+
+	/* pointer to stack or null */
+	callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+	callee->in_callback_fn = true;
+	return 0;
+}
+
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
 	struct bpf_verifier_state *state = env->cur_state;
@@ -5977,9 +6335,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	*insn_idx = callee->callsite + 1;
 	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
-		print_verifier_state(env, callee);
+		print_verifier_state(env, callee, true);
 		verbose(env, "to caller at %d:\n", *insn_idx);
-		print_verifier_state(env, caller);
+		print_verifier_state(env, caller, true);
 	}
 	/* clear everything in the callee */
 	free_func_state(callee);
@@ -6145,13 +6503,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
 
 static int check_get_func_ip(struct bpf_verifier_env *env)
 {
-	enum bpf_attach_type eatype = env->prog->expected_attach_type;
 	enum bpf_prog_type type = resolve_prog_type(env->prog);
 	int func_id = BPF_FUNC_get_func_ip;
 
 	if (type == BPF_PROG_TYPE_TRACING) {
-		if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT &&
-		    eatype != BPF_MODIFY_RETURN) {
+		if (!bpf_prog_has_trampoline(env->prog)) {
 			verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n",
 				func_id_name(func_id), func_id);
 			return -ENOTSUPP;
@@ -6170,6 +6526,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			     int *insn_idx_p)
 {
 	const struct bpf_func_proto *fn = NULL;
+	enum bpf_return_type ret_type;
+	enum bpf_type_flag ret_flag;
 	struct bpf_reg_state *regs;
 	struct bpf_call_arg_meta meta;
 	int insn_idx = *insn_idx_p;
@@ -6247,13 +6605,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return err;
 	}
 
-	if (func_id == BPF_FUNC_tail_call) {
-		err = check_reference_leak(env);
-		if (err) {
-			verbose(env, "tail_call would lead to reference leak\n");
-			return err;
-		}
-	} else if (is_release_function(func_id)) {
+	if (is_release_function(func_id)) {
 		err = release_reference(env, meta.ref_obj_id);
 		if (err) {
 			verbose(env, "func %s#%d reference has not been acquired before\n",
@@ -6264,35 +6616,47 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	regs = cur_regs(env);
 
-	/* check that flags argument in get_local_storage(map, flags) is 0,
-	 * this is required because get_local_storage() can't return an error.
-	 */
-	if (func_id == BPF_FUNC_get_local_storage &&
-	    !register_is_null(&regs[BPF_REG_2])) {
-		verbose(env, "get_local_storage() doesn't support non-zero flags\n");
-		return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_for_each_map_elem) {
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		err = check_reference_leak(env);
+		if (err) {
+			verbose(env, "tail_call would lead to reference leak\n");
+			return err;
+		}
+		break;
+	case BPF_FUNC_get_local_storage:
+		/* check that flags argument in get_local_storage(map, flags) is 0,
+		 * this is required because get_local_storage() can't return an error.
+		 */
+		if (!register_is_null(&regs[BPF_REG_2])) {
+			verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+			return -EINVAL;
+		}
+		break;
+	case BPF_FUNC_for_each_map_elem:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_map_elem_callback_state);
-		if (err < 0)
-			return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_timer_set_callback) {
+		break;
+	case BPF_FUNC_timer_set_callback:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_timer_callback_state);
-		if (err < 0)
-			return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_snprintf) {
+		break;
+	case BPF_FUNC_find_vma:
+		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
+					set_find_vma_callback_state);
+		break;
+	case BPF_FUNC_snprintf:
 		err = check_bpf_snprintf_call(env, regs);
-		if (err < 0)
-			return err;
+		break;
+	case BPF_FUNC_loop:
+		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
+					set_loop_callback_state);
+		break;
 	}
 
+	if (err)
+		return err;
+
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
@@ -6303,13 +6667,14 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
 
 	/* update return register (already marked as written above) */
-	if (fn->ret_type == RET_INTEGER) {
+	ret_type = fn->ret_type;
+	ret_flag = type_flag(fn->ret_type);
+	if (ret_type == RET_INTEGER) {
 		/* sets type to SCALAR_VALUE */
 		mark_reg_unknown(env, regs, BPF_REG_0);
-	} else if (fn->ret_type == RET_VOID) {
+	} else if (ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
-	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
-		   fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+	} else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) {
 		/* There is no offset yet applied, variable or fixed */
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		/* remember map_ptr, so that check_map_access()
@@ -6323,28 +6688,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
 		regs[BPF_REG_0].map_uid = meta.map_uid;
-		if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
-			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
-			if (map_value_has_spin_lock(meta.map_ptr))
-				regs[BPF_REG_0].id = ++env->id_gen;
-		} else {
-			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag;
+		if (!type_may_be_null(ret_type) &&
+		    map_value_has_spin_lock(meta.map_ptr)) {
+			regs[BPF_REG_0].id = ++env->id_gen;
 		}
-	} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
+	} else if (base_type(ret_type) == RET_PTR_TO_SOCKET) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
-	} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+		regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
+	} else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
-	} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
+	} else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
-	} else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
+		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
+	} else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+		regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
-	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
-		   fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
+	} else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) {
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -6362,29 +6724,30 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 					tname, PTR_ERR(ret));
 				return -EINVAL;
 			}
-			regs[BPF_REG_0].type =
-				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
-				PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
+			regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
 			regs[BPF_REG_0].mem_size = tsize;
 		} else {
-			regs[BPF_REG_0].type =
-				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
-				PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+			/* MEM_RDONLY may be carried from ret_flag, but it
+			 * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+			 * it will confuse the check of PTR_TO_BTF_ID in
+			 * check_mem_access().
+			 */
+			ret_flag &= ~MEM_RDONLY;
+
+			regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
 			regs[BPF_REG_0].btf = meta.ret_btf;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
-	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
-		   fn->ret_type == RET_PTR_TO_BTF_ID) {
+	} else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
 		int ret_btf_id;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
-						     PTR_TO_BTF_ID :
-						     PTR_TO_BTF_ID_OR_NULL;
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
 		ret_btf_id = *fn->ret_btf_id;
 		if (ret_btf_id == 0) {
-			verbose(env, "invalid return type %d of func %s#%d\n",
-				fn->ret_type, func_id_name(func_id), func_id);
+			verbose(env, "invalid return type %u of func %s#%d\n",
+				base_type(ret_type), func_id_name(func_id),
+				func_id);
 			return -EINVAL;
 		}
 		/* current BPF helper definitions are only coming from
@@ -6393,12 +6756,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].btf = btf_vmlinux;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
-		verbose(env, "unknown return type %d of func %s#%d\n",
-			fn->ret_type, func_id_name(func_id), func_id);
+		verbose(env, "unknown return type %u of func %s#%d\n",
+			base_type(ret_type), func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
-	if (reg_type_may_be_null(regs[BPF_REG_0].type))
+	if (type_may_be_null(regs[BPF_REG_0].type))
 		regs[BPF_REG_0].id = ++env->id_gen;
 
 	if (is_ptr_cast_function(func_id)) {
@@ -6485,23 +6848,33 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	struct bpf_reg_state *regs = cur_regs(env);
 	const char *func_name, *ptr_type_name;
 	u32 i, nargs, func_id, ptr_type_id;
+	struct module *btf_mod = NULL;
 	const struct btf_param *args;
+	struct btf *desc_btf;
 	int err;
 
+	/* skip for now, but return error when we find this in fixup_kfunc_call */
+	if (!insn->imm)
+		return 0;
+
+	desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod);
+	if (IS_ERR(desc_btf))
+		return PTR_ERR(desc_btf);
+
 	func_id = insn->imm;
-	func = btf_type_by_id(btf_vmlinux, func_id);
-	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
-	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+	func = btf_type_by_id(desc_btf, func_id);
+	func_name = btf_name_by_offset(desc_btf, func->name_off);
+	func_proto = btf_type_by_id(desc_btf, func->type);
 
 	if (!env->ops->check_kfunc_call ||
-	    !env->ops->check_kfunc_call(func_id)) {
+	    !env->ops->check_kfunc_call(func_id, btf_mod)) {
 		verbose(env, "calling kernel function %s is not allowed\n",
 			func_name);
 		return -EACCES;
 	}
 
 	/* Check the arguments */
-	err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs);
+	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs);
 	if (err)
 		return err;
 
@@ -6509,15 +6882,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		mark_reg_not_init(env, regs, caller_saved[i]);
 
 	/* Check return type */
-	t = btf_type_skip_modifiers(btf_vmlinux, func_proto->type, NULL);
+	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
 	if (btf_type_is_scalar(t)) {
 		mark_reg_unknown(env, regs, BPF_REG_0);
 		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
 	} else if (btf_type_is_ptr(t)) {
-		ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type,
+		ptr_type = btf_type_skip_modifiers(desc_btf, t->type,
 						   &ptr_type_id);
 		if (!btf_type_is_struct(ptr_type)) {
-			ptr_type_name = btf_name_by_offset(btf_vmlinux,
+			ptr_type_name = btf_name_by_offset(desc_btf,
 							   ptr_type->name_off);
 			verbose(env, "kernel function %s returns pointer type %s %s is not supported\n",
 				func_name, btf_type_str(ptr_type),
@@ -6525,7 +6898,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].btf = btf_vmlinux;
+		regs[BPF_REG_0].btf = desc_btf;
 		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
 		regs[BPF_REG_0].btf_id = ptr_type_id;
 		mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
@@ -6536,7 +6909,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	for (i = 0; i < nargs; i++) {
 		u32 regno = i + 1;
 
-		t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL);
+		t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL);
 		if (btf_type_is_ptr(t))
 			mark_btf_func_reg_size(env, regno, sizeof(void *));
 		else
@@ -6597,25 +6970,25 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
 
 	if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
 		verbose(env, "math between %s pointer and %lld is not allowed\n",
-			reg_type_str[type], val);
+			reg_type_str(env, type), val);
 		return false;
 	}
 
 	if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
 		verbose(env, "%s pointer offset %d is not allowed\n",
-			reg_type_str[type], reg->off);
+			reg_type_str(env, type), reg->off);
 		return false;
 	}
 
 	if (smin == S64_MIN) {
 		verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
-			reg_type_str[type]);
+			reg_type_str(env, type));
 		return false;
 	}
 
 	if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
 		verbose(env, "value %lld makes %s pointer be out of bounds\n",
-			smin, reg_type_str[type]);
+			smin, reg_type_str(env, type));
 		return false;
 	}
 
@@ -6992,11 +7365,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	switch (ptr_reg->type) {
-	case PTR_TO_MAP_VALUE_OR_NULL:
+	if (ptr_reg->type & PTR_MAYBE_NULL) {
 		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
-			dst, reg_type_str[ptr_reg->type]);
+			dst, reg_type_str(env, ptr_reg->type));
 		return -EACCES;
+	}
+
+	switch (base_type(ptr_reg->type)) {
 	case CONST_PTR_TO_MAP:
 		/* smin_val represents the known value */
 		if (known && smin_val == 0 && opcode == BPF_ADD)
@@ -7004,14 +7379,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		fallthrough;
 	case PTR_TO_PACKET_END:
 	case PTR_TO_SOCKET:
-	case PTR_TO_SOCKET_OR_NULL:
 	case PTR_TO_SOCK_COMMON:
-	case PTR_TO_SOCK_COMMON_OR_NULL:
 	case PTR_TO_TCP_SOCK:
-	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
-			dst, reg_type_str[ptr_reg->type]);
+			dst, reg_type_str(env, ptr_reg->type));
 		return -EACCES;
 	default:
 		break;
@@ -7984,12 +8356,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	/* Got here implies adding two SCALAR_VALUEs */
 	if (WARN_ON_ONCE(ptr_reg)) {
-		print_verifier_state(env, state);
+		print_verifier_state(env, state, true);
 		verbose(env, "verifier internal error: unexpected ptr_reg\n");
 		return -EINVAL;
 	}
 	if (WARN_ON(!src_reg)) {
-		print_verifier_state(env, state);
+		print_verifier_state(env, state, true);
 		verbose(env, "verifier internal error: no src_reg\n");
 		return -EINVAL;
 	}
@@ -8098,6 +8470,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 							 insn->dst_reg);
 				}
 				zext_32_to_64(dst_reg);
+
+				__update_reg_bounds(dst_reg);
+				__reg_deduce_bounds(dst_reg);
+				__reg_bound_offset(dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -8212,7 +8588,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 
 	new_range = dst_reg->off;
 	if (range_right_open)
-		new_range--;
+		new_range++;
 
 	/* Examples for register markings:
 	 *
@@ -8730,17 +9106,17 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 				 struct bpf_reg_state *reg, u32 id,
 				 bool is_null)
 {
-	if (reg_type_may_be_null(reg->type) && reg->id == id &&
+	if (type_may_be_null(reg->type) && reg->id == id &&
 	    !WARN_ON_ONCE(!reg->id)) {
-		/* Old offset (both fixed and variable parts) should
-		 * have been known-zero, because we don't allow pointer
-		 * arithmetic on pointers that might be NULL.
-		 */
 		if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
 				 !tnum_equals_const(reg->var_off, 0) ||
 				 reg->off)) {
-			__mark_reg_known_zero(reg);
-			reg->off = 0;
+			/* Old offset (both fixed and variable parts) should
+			 * have been known-zero, because we don't allow pointer
+			 * arithmetic on pointers that might be NULL. If we
+			 * see this happening, don't convert the register.
+			 */
+			return;
 		}
 		if (is_null) {
 			reg->type = SCALAR_VALUE;
@@ -9108,7 +9484,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 */
 	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
 	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
-	    reg_type_may_be_null(dst_reg->type)) {
+	    type_may_be_null(dst_reg->type)) {
 		/* Mark all identical registers in each branch as either
 		 * safe or unknown depending R == 0 or R != 0 conditional.
 		 */
@@ -9124,7 +9500,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 	if (env->log.level & BPF_LOG_LEVEL)
-		print_verifier_state(env, this_branch->frame[this_branch->curframe]);
+		print_insn_state(env, this_branch->frame[this_branch->curframe]);
 	return 0;
 }
 
@@ -9159,11 +9535,15 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return 0;
 	}
 
-	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
-		mark_reg_known_zero(env, regs, insn->dst_reg);
+	/* All special src_reg cases are listed below. From this point onwards
+	 * we either succeed and assign a corresponding dst_reg->type after
+	 * zeroing the offset, or fail and reject the program.
+	 */
+	mark_reg_known_zero(env, regs, insn->dst_reg);
 
+	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
 		dst_reg->type = aux->btf_var.reg_type;
-		switch (dst_reg->type) {
+		switch (base_type(dst_reg->type)) {
 		case PTR_TO_MEM:
 			dst_reg->mem_size = aux->btf_var.mem_size;
 			break;
@@ -9181,7 +9561,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	if (insn->src_reg == BPF_PSEUDO_FUNC) {
 		struct bpf_prog_aux *aux = env->prog->aux;
-		u32 subprogno = insn[1].imm;
+		u32 subprogno = find_subprog(env,
+					     env->insn_idx + insn->imm + 1);
 
 		if (!aux->func_info) {
 			verbose(env, "missing btf func_info\n");
@@ -9198,7 +9579,6 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	}
 
 	map = env->used_maps[aux->map_index];
-	mark_reg_known_zero(env, regs, insn->dst_reg);
 	dst_reg->map_ptr = map;
 
 	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
@@ -9302,7 +9682,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return err;
 	}
 
-	err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+	err = check_ptr_off_reg(env, &regs[ctx_reg], ctx_reg);
 	if (err < 0)
 		return err;
 
@@ -9361,7 +9741,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 		/* enforce return zero from async callbacks like timer */
 		if (reg->type != SCALAR_VALUE) {
 			verbose(env, "In async callback the register R0 is not a known value (%s)\n",
-				reg_type_str[reg->type]);
+				reg_type_str(env, reg->type));
 			return -EINVAL;
 		}
 
@@ -9375,7 +9755,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	if (is_subprog) {
 		if (reg->type != SCALAR_VALUE) {
 			verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
-				reg_type_str[reg->type]);
+				reg_type_str(env, reg->type));
 			return -EINVAL;
 		}
 		return 0;
@@ -9439,7 +9819,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 
 	if (reg->type != SCALAR_VALUE) {
 		verbose(env, "At program exit the register R0 is not a known value (%s)\n",
-			reg_type_str[reg->type]);
+			reg_type_str(env, reg->type));
 		return -EINVAL;
 	}
 
@@ -10022,6 +10402,78 @@ err_free:
 	return err;
 }
 
+#define MIN_CORE_RELO_SIZE	sizeof(struct bpf_core_relo)
+#define MAX_CORE_RELO_SIZE	MAX_FUNCINFO_REC_SIZE
+
+static int check_core_relo(struct bpf_verifier_env *env,
+			   const union bpf_attr *attr,
+			   bpfptr_t uattr)
+{
+	u32 i, nr_core_relo, ncopy, expected_size, rec_size;
+	struct bpf_core_relo core_relo = {};
+	struct bpf_prog *prog = env->prog;
+	const struct btf *btf = prog->aux->btf;
+	struct bpf_core_ctx ctx = {
+		.log = &env->log,
+		.btf = btf,
+	};
+	bpfptr_t u_core_relo;
+	int err;
+
+	nr_core_relo = attr->core_relo_cnt;
+	if (!nr_core_relo)
+		return 0;
+	if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo))
+		return -EINVAL;
+
+	rec_size = attr->core_relo_rec_size;
+	if (rec_size < MIN_CORE_RELO_SIZE ||
+	    rec_size > MAX_CORE_RELO_SIZE ||
+	    rec_size % sizeof(u32))
+		return -EINVAL;
+
+	u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel);
+	expected_size = sizeof(struct bpf_core_relo);
+	ncopy = min_t(u32, expected_size, rec_size);
+
+	/* Unlike func_info and line_info, copy and apply each CO-RE
+	 * relocation record one at a time.
+	 */
+	for (i = 0; i < nr_core_relo; i++) {
+		/* future proofing when sizeof(bpf_core_relo) changes */
+		err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size);
+		if (err) {
+			if (err == -E2BIG) {
+				verbose(env, "nonzero tailing record in core_relo");
+				if (copy_to_bpfptr_offset(uattr,
+							  offsetof(union bpf_attr, core_relo_rec_size),
+							  &expected_size, sizeof(expected_size)))
+					err = -EFAULT;
+			}
+			break;
+		}
+
+		if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) {
+			verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n",
+				i, core_relo.insn_off, prog->len);
+			err = -EINVAL;
+			break;
+		}
+
+		err = bpf_core_apply(&ctx, &core_relo, i,
+				     &prog->insnsi[core_relo.insn_off / 8]);
+		if (err)
+			break;
+		bpfptr_add(&u_core_relo, rec_size);
+	}
+	return err;
+}
+
 static int check_btf_info(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  bpfptr_t uattr)
@@ -10052,6 +10504,10 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	if (err)
 		return err;
 
+	err = check_core_relo(env, attr, uattr);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -10220,7 +10676,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		return true;
 	if (rcur->type == NOT_INIT)
 		return false;
-	switch (rold->type) {
+	switch (base_type(rold->type)) {
 	case SCALAR_VALUE:
 		if (env->explore_alu_limits)
 			return false;
@@ -10242,6 +10698,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		}
 	case PTR_TO_MAP_KEY:
 	case PTR_TO_MAP_VALUE:
+		/* a PTR_TO_MAP_VALUE could be safe to use as a
+		 * PTR_TO_MAP_VALUE_OR_NULL into the same map.
+		 * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
+		 * checked, doing so could have affected others with the same
+		 * id, and we can't check for that because we lost the id when
+		 * we converted to a PTR_TO_MAP_VALUE.
+		 */
+		if (type_may_be_null(rold->type)) {
+			if (!type_may_be_null(rcur->type))
+				return false;
+			if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
+				return false;
+			/* Check our ids match any regs they're supposed to */
+			return check_ids(rold->id, rcur->id, idmap);
+		}
+
 		/* If the new min/max/var_off satisfy the old ones and
 		 * everything else matches, we are OK.
 		 * 'id' is not compared, since it's only used for maps with
@@ -10253,20 +10725,6 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
 		       range_within(rold, rcur) &&
 		       tnum_in(rold->var_off, rcur->var_off);
-	case PTR_TO_MAP_VALUE_OR_NULL:
-		/* a PTR_TO_MAP_VALUE could be safe to use as a
-		 * PTR_TO_MAP_VALUE_OR_NULL into the same map.
-		 * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
-		 * checked, doing so could have affected others with the same
-		 * id, and we can't check for that because we lost the id when
-		 * we converted to a PTR_TO_MAP_VALUE.
-		 */
-		if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
-			return false;
-		if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
-			return false;
-		/* Check our ids match any regs they're supposed to */
-		return check_ids(rold->id, rcur->id, idmap);
 	case PTR_TO_PACKET_META:
 	case PTR_TO_PACKET:
 		if (rcur->type != rold->type)
@@ -10295,11 +10753,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 	case PTR_TO_PACKET_END:
 	case PTR_TO_FLOW_KEYS:
 	case PTR_TO_SOCKET:
-	case PTR_TO_SOCKET_OR_NULL:
 	case PTR_TO_SOCK_COMMON:
-	case PTR_TO_SOCK_COMMON_OR_NULL:
 	case PTR_TO_TCP_SOCK:
-	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 		/* Only valid matches are exact, which memcmp() above
 		 * would have accepted
@@ -10356,9 +10811,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			 * return false to continue verification of this path
 			 */
 			return false;
-		if (i % BPF_REG_SIZE)
+		if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1)
 			continue;
-		if (old->stack[spi].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&old->stack[spi]))
 			continue;
 		if (!regsafe(env, &old->stack[spi].spilled_ptr,
 			     &cur->stack[spi].spilled_ptr, idmap))
@@ -10565,7 +11020,7 @@ static int propagate_precision(struct bpf_verifier_env *env,
 	}
 
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		if (state->stack[i].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&state->stack[i]))
 			continue;
 		state_reg = &state->stack[i].spilled_ptr;
 		if (state_reg->type != SCALAR_VALUE ||
@@ -10825,17 +11280,13 @@ next:
 /* Return true if it's OK to have the same insn return a different type. */
 static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 {
-	switch (type) {
+	switch (base_type(type)) {
 	case PTR_TO_CTX:
 	case PTR_TO_SOCKET:
-	case PTR_TO_SOCKET_OR_NULL:
 	case PTR_TO_SOCK_COMMON:
-	case PTR_TO_SOCK_COMMON_OR_NULL:
 	case PTR_TO_TCP_SOCK:
-	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
-	case PTR_TO_BTF_ID_OR_NULL:
 		return false;
 	default:
 		return true;
@@ -10915,16 +11366,12 @@ static int do_check(struct bpf_verifier_env *env)
 		if (need_resched())
 			cond_resched();
 
-		if (env->log.level & BPF_LOG_LEVEL2 ||
-		    (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
-			if (env->log.level & BPF_LOG_LEVEL2)
-				verbose(env, "%d:", env->insn_idx);
-			else
-				verbose(env, "\nfrom %d to %d%s:",
-					env->prev_insn_idx, env->insn_idx,
-					env->cur_state->speculative ?
-					" (speculative execution)" : "");
-			print_verifier_state(env, state->frame[state->curframe]);
+		if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) {
+			verbose(env, "\nfrom %d to %d%s:",
+				env->prev_insn_idx, env->insn_idx,
+				env->cur_state->speculative ?
+				" (speculative execution)" : "");
+			print_verifier_state(env, state->frame[state->curframe], true);
 			do_print_state = false;
 		}
 
@@ -10935,9 +11382,15 @@ static int do_check(struct bpf_verifier_env *env)
 				.private_data	= env,
 			};
 
+			if (verifier_state_scratched(env))
+				print_insn_state(env, state->frame[state->curframe]);
+
 			verbose_linfo(env, env->insn_idx, "; ");
+			env->prev_log_len = env->log.len_used;
 			verbose(env, "%d: ", env->insn_idx);
 			print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
+			env->prev_insn_print_len = env->log.len_used - env->prev_log_len;
+			env->prev_log_len = env->log.len_used;
 		}
 
 		if (bpf_prog_is_dev_bound(env->prog->aux)) {
@@ -11059,7 +11512,7 @@ static int do_check(struct bpf_verifier_env *env)
 			if (is_ctx_reg(env, insn->dst_reg)) {
 				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
 					insn->dst_reg,
-					reg_type_str[reg_state(env, insn->dst_reg)->type]);
+					reg_type_str(env, reg_state(env, insn->dst_reg)->type));
 				return -EACCES;
 			}
 
@@ -11076,7 +11529,8 @@ static int do_check(struct bpf_verifier_env *env)
 			env->jmps_processed++;
 			if (opcode == BPF_CALL) {
 				if (BPF_SRC(insn->code) != BPF_K ||
-				    insn->off != 0 ||
+				    (insn->src_reg != BPF_PSEUDO_KFUNC_CALL
+				     && insn->off != 0) ||
 				    (insn->src_reg != BPF_REG_0 &&
 				     insn->src_reg != BPF_PSEUDO_CALL &&
 				     insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
@@ -11145,6 +11599,7 @@ static int do_check(struct bpf_verifier_env *env)
 				if (err)
 					return err;
 process_bpf_exit:
+				mark_verifier_state_scratched(env);
 				update_branch_counts(env, env->cur_state);
 				err = pop_stack(env, &prev_insn_idx,
 						&env->insn_idx, pop_log);
@@ -11310,7 +11765,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			err = -EINVAL;
 			goto err_put;
 		}
-		aux->btf_var.reg_type = PTR_TO_MEM;
+		aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
 		aux->btf_var.mem_size = tsize;
 	} else {
 		aux->btf_var.reg_type = PTR_TO_BTF_ID;
@@ -11435,6 +11890,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		}
 	}
 
+	if (map_value_has_timer(map)) {
+		if (is_tracing_prog_type(prog_type)) {
+			verbose(env, "tracing progs cannot use bpf_timer yet\n");
+			return -EINVAL;
+		}
+	}
+
 	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
 	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
@@ -11463,6 +11925,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 			}
 			break;
 		case BPF_MAP_TYPE_RINGBUF:
+		case BPF_MAP_TYPE_INODE_STORAGE:
+		case BPF_MAP_TYPE_SK_STORAGE:
+		case BPF_MAP_TYPE_TASK_STORAGE:
 			break;
 		default:
 			verbose(env,
@@ -12350,14 +12815,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		return 0;
 
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
-		if (bpf_pseudo_func(insn)) {
-			env->insn_aux_data[i].call_imm = insn->imm;
-			/* subprog is encoded in insn[1].imm */
+		if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn))
 			continue;
-		}
 
-		if (!bpf_pseudo_call(insn))
-			continue;
 		/* Upon error here we cannot fall back to interpreter but
 		 * need a hard reject of the program. Thus -EFAULT is
 		 * propagated in any case.
@@ -12378,6 +12838,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		env->insn_aux_data[i].call_imm = insn->imm;
 		/* point imm to __bpf_call_base+1 from JITs point of view */
 		insn->imm = 1;
+		if (bpf_pseudo_func(insn))
+			/* jit (e.g. x86_64) may emit fewer instructions
+			 * if it learns a u32 imm is the same as a u64 imm.
+			 * Force a non zero here.
+			 */
+			insn[1].imm = 1;
 	}
 
 	err = bpf_prog_alloc_jited_linfo(prog);
@@ -12432,6 +12898,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
 		func[i]->aux->kfunc_tab = prog->aux->kfunc_tab;
+		func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab;
 		func[i]->aux->linfo = prog->aux->linfo;
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
@@ -12461,7 +12928,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (bpf_pseudo_func(insn)) {
-				subprog = insn[1].imm;
+				subprog = insn->off;
 				insn[0].imm = (u32)(long)func[subprog]->bpf_func;
 				insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32;
 				continue;
@@ -12469,8 +12936,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			if (!bpf_pseudo_call(insn))
 				continue;
 			subprog = insn->off;
-			insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
-				    __bpf_call_base;
+			insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func);
 		}
 
 		/* we use the aux data to keep a list of the start addresses
@@ -12513,7 +12979,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
 		if (bpf_pseudo_func(insn)) {
 			insn[0].imm = env->insn_aux_data[i].call_imm;
-			insn[1].imm = find_subprog(env, i + insn[0].imm + 1);
+			insn[1].imm = insn->off;
+			insn->off = 0;
 			continue;
 		}
 		if (!bpf_pseudo_call(insn))
@@ -12618,10 +13085,15 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
 {
 	const struct bpf_kfunc_desc *desc;
 
+	if (!insn->imm) {
+		verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
+		return -EINVAL;
+	}
+
 	/* insn->imm has the btf func_id. Replace it with
 	 * an address (relative to __bpf_base_call).
 	 */
-	desc = find_kfunc_desc(env->prog, insn->imm);
+	desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
 	if (!desc) {
 		verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n",
 			insn->imm);
@@ -12639,6 +13111,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
 static int do_misc_fixups(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
+	enum bpf_attach_type eatype = prog->expected_attach_type;
 	bool expect_blinding = bpf_jit_blinding_enabled(prog);
 	enum bpf_prog_type prog_type = resolve_prog_type(prog);
 	struct bpf_insn *insn = prog->insnsi;
@@ -12902,7 +13375,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		     insn->imm == BPF_FUNC_map_push_elem   ||
 		     insn->imm == BPF_FUNC_map_pop_elem    ||
 		     insn->imm == BPF_FUNC_map_peek_elem   ||
-		     insn->imm == BPF_FUNC_redirect_map)) {
+		     insn->imm == BPF_FUNC_redirect_map    ||
+		     insn->imm == BPF_FUNC_for_each_map_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -12946,36 +13420,37 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_redirect,
 				     (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_for_each_callback,
+				     (int (*)(struct bpf_map *map,
+					      bpf_callback_t callback_fn,
+					      void *callback_ctx,
+					      u64 flags))NULL));
 
 patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_lookup_elem);
 				continue;
 			case BPF_FUNC_map_update_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_update_elem);
 				continue;
 			case BPF_FUNC_map_delete_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_delete_elem);
 				continue;
 			case BPF_FUNC_map_push_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_push_elem);
 				continue;
 			case BPF_FUNC_map_pop_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_pop_elem);
 				continue;
 			case BPF_FUNC_map_peek_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_peek_elem);
 				continue;
 			case BPF_FUNC_redirect_map:
-				insn->imm = BPF_CAST_CALL(ops->map_redirect) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_redirect);
+				continue;
+			case BPF_FUNC_for_each_map_elem:
+				insn->imm = BPF_CALL_IMM(ops->map_for_each_callback);
 				continue;
 			}
 
@@ -13007,11 +13482,79 @@ patch_map_ops_generic:
 			continue;
 		}
 
+		/* Implement bpf_get_func_arg inline. */
+		if (prog_type == BPF_PROG_TYPE_TRACING &&
+		    insn->imm == BPF_FUNC_get_func_arg) {
+			/* Load nr_args from ctx - 8 */
+			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+			insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6);
+			insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3);
+			insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1);
+			insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0);
+			insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+			insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0);
+			insn_buf[7] = BPF_JMP_A(1);
+			insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL);
+			cnt = 9;
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
+		/* Implement bpf_get_func_ret inline. */
+		if (prog_type == BPF_PROG_TYPE_TRACING &&
+		    insn->imm == BPF_FUNC_get_func_ret) {
+			if (eatype == BPF_TRACE_FEXIT ||
+			    eatype == BPF_MODIFY_RETURN) {
+				/* Load nr_args from ctx - 8 */
+				insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+				insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+				insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+				insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+				insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0);
+				insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0);
+				cnt = 6;
+			} else {
+				insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP);
+				cnt = 1;
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
+		/* Implement get_func_arg_cnt inline. */
+		if (prog_type == BPF_PROG_TYPE_TRACING &&
+		    insn->imm == BPF_FUNC_get_func_arg_cnt) {
+			/* Load nr_args from ctx - 8 */
+			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
+			if (!new_prog)
+				return -ENOMEM;
+
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		/* Implement bpf_get_func_ip inline. */
 		if (prog_type == BPF_PROG_TYPE_TRACING &&
 		    insn->imm == BPF_FUNC_get_func_ip) {
-			/* Load IP address from ctx - 8 */
-			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+			/* Load IP address from ctx - 16 */
+			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16);
 
 			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
 			if (!new_prog)
@@ -13125,7 +13668,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 				mark_reg_known_zero(env, regs, i);
 			else if (regs[i].type == SCALAR_VALUE)
 				mark_reg_unknown(env, regs, i);
-			else if (regs[i].type == PTR_TO_MEM_OR_NULL) {
+			else if (base_type(regs[i].type) == PTR_TO_MEM) {
 				const u32 mem_size = regs[i].mem_size;
 
 				mark_reg_known_zero(env, regs, i);
@@ -13319,7 +13862,7 @@ BTF_SET_START(btf_non_sleepable_error_inject)
 /* Three functions below can be called from sleepable and non-sleepable context.
  * Assume non-sleepable from bpf safety point of view.
  */
-BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, __filemap_add_folio)
 BTF_ID(func, should_fail_alloc_page)
 BTF_ID(func, should_failslab)
 BTF_SET_END(btf_non_sleepable_error_inject)
@@ -13713,13 +14256,15 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
 		log->ubuf = (char __user *) (unsigned long) attr->log_buf;
 		log->len_total = attr->log_size;
 
-		ret = -EINVAL;
 		/* log attributes have to be sane */
-		if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 ||
-		    !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
+		if (!bpf_verifier_log_attr_valid(log)) {
+			ret = -EINVAL;
 			goto err_unlock;
+		}
 	}
 
+	mark_verifier_state_clean(env);
+
 	if (IS_ERR(btf_vmlinux)) {
 		/* Either gcc or pahole or kernel are broken. */
 		verbose(env, "in-kernel BTF is malformed\n");
@@ -13826,6 +14371,7 @@ skip_full_check:
 
 	env->verification_time = ktime_get_ns() - start_time;
 	print_verification_stats(env);
+	env->prog->aux->verified_insns = env->insn_processed;
 
 	if (log->level && bpf_verifier_log_full(log))
 		ret = -ENOSPC;