Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-05-16

We've added 57 non-merge commits during the last 19 day(s) which contain
a total of 63 files changed, 3293 insertions(+), 690 deletions(-).

The main changes are:

1) Add precision propagation to verifier for subprogs and callbacks,
   from Andrii Nakryiko.

2) Improve BPF's {g,s}setsockopt() handling with wrong option lengths,
   from Stanislav Fomichev.

3) Utilize pahole v1.25 for the kernel's BTF generation to filter out
   inconsistent function prototypes, from Alan Maguire.

4) Various dyn-pointer verifier improvements to relax restrictions,
   from Daniel Rosenberg.

5) Add a new bpf_task_under_cgroup() kfunc for designated task,
   from Feng Zhou.

6) Unblock tests for arm64 BPF CI after ftrace supporting direct call,
   from Florent Revest.

7) Add XDP hint kfunc metadata for RX hash/timestamp for igc,
   from Jesper Dangaard Brouer.

8) Add several new dyn-pointer kfuncs to ease their usability,
   from Joanne Koong.

9) Add in-depth LRU internals description and dot function graph,
   from Joe Stringer.

10) Fix KCSAN report on bpf_lru_list when accessing node->ref,
    from Martin KaFai Lau.

11) Only dump unprivileged_bpf_disabled log warning upon write,
    from Kui-Feng Lee.

12) Extend test_progs to directly passing allow/denylist file,
    from Stephen Veiss.

13) Fix BPF trampoline memleak upon failure attaching to fentry,
    from Yafang Shao.

14) Fix emitting struct bpf_tcp_sock type in vmlinux BTF,
    from Yonghong Song.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (57 commits)
  bpf: Fix memleak due to fentry attach failure
  bpf: Remove bpf trampoline selector
  bpf, arm64: Support struct arguments in the BPF trampoline
  bpftool: JIT limited misreported as negative value on aarch64
  bpf: fix calculation of subseq_idx during precision backtracking
  bpf: Remove anonymous union in bpf_kfunc_call_arg_meta
  bpf: Document EFAULT changes for sockopt
  selftests/bpf: Correctly handle optlen > 4096
  selftests/bpf: Update EFAULT {g,s}etsockopt selftests
  bpf: Don't EFAULT for {g,s}setsockopt with wrong optlen
  libbpf: fix offsetof() and container_of() to work with CO-RE
  bpf: Address KCSAN report on bpf_lru_list
  bpf: Add --skip_encoding_btf_inconsistent_proto, --btf_gen_optimized to pahole flags for v1.25
  selftests/bpf: Accept mem from dynptr in helper funcs
  bpf: verifier: Accept dynptr mem as mem in helpers
  selftests/bpf: Check overflow in optional buffer
  selftests/bpf: Test allowing NULL buffer in dynptr slice
  bpf: Allow NULL buffers in bpf_dynptr_slice(_rw)
  selftests/bpf: Add testcase for bpf_task_under_cgroup
  bpf: Add bpf_task_under_cgroup() kfunc
  ...
====================

Link: https://lore.kernel.org/r/20230515225603.27027-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 750 insertions, 238 deletions

diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
index d99e89f113c4..3dabdd137d10 100644
--- a/kernel/bpf/bpf_lru_list.c
+++ b/kernel/bpf/bpf_lru_list.c
@@ -41,7 +41,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l)
 /* bpf_lru_node helpers */
 static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node)
 {
-	return node->ref;
+	return READ_ONCE(node->ref);
+}
+
+static void bpf_lru_node_clear_ref(struct bpf_lru_node *node)
+{
+	WRITE_ONCE(node->ref, 0);
 }
 
 static void bpf_lru_list_count_inc(struct bpf_lru_list *l,
@@ -89,7 +94,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l,
 
 	bpf_lru_list_count_inc(l, tgt_type);
 	node->type = tgt_type;
-	node->ref = 0;
+	bpf_lru_node_clear_ref(node);
 	list_move(&node->list, &l->lists[tgt_type]);
 }
 
@@ -110,7 +115,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l,
 		bpf_lru_list_count_inc(l, tgt_type);
 		node->type = tgt_type;
 	}
-	node->ref = 0;
+	bpf_lru_node_clear_ref(node);
 
 	/* If the moving node is the next_inactive_rotation candidate,
 	 * move the next_inactive_rotation pointer also.
@@ -353,7 +358,7 @@ static void __local_list_add_pending(struct bpf_lru *lru,
 	*(u32 *)((void *)node + lru->hash_offset) = hash;
 	node->cpu = cpu;
 	node->type = BPF_LRU_LOCAL_LIST_T_PENDING;
-	node->ref = 0;
+	bpf_lru_node_clear_ref(node);
 	list_add(&node->list, local_pending_list(loc_l));
 }
 
@@ -419,7 +424,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru,
 	if (!list_empty(free_list)) {
 		node = list_first_entry(free_list, struct bpf_lru_node, list);
 		*(u32 *)((void *)node + lru->hash_offset) = hash;
-		node->ref = 0;
+		bpf_lru_node_clear_ref(node);
 		__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE);
 	}
 
@@ -522,7 +527,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru,
 		}
 
 		node->type = BPF_LRU_LOCAL_LIST_T_FREE;
-		node->ref = 0;
+		bpf_lru_node_clear_ref(node);
 		list_move(&node->list, local_free_list(loc_l));
 
 		raw_spin_unlock_irqrestore(&loc_l->lock, flags);
@@ -568,7 +573,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,
 
 		node = (struct bpf_lru_node *)(buf + node_offset);
 		node->type = BPF_LRU_LIST_T_FREE;
-		node->ref = 0;
+		bpf_lru_node_clear_ref(node);
 		list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
 		buf += elem_size;
 	}
@@ -594,7 +599,7 @@ again:
 		node = (struct bpf_lru_node *)(buf + node_offset);
 		node->cpu = cpu;
 		node->type = BPF_LRU_LIST_T_FREE;
-		node->ref = 0;
+		bpf_lru_node_clear_ref(node);
 		list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
 		i++;
 		buf += elem_size;
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index 4ea227c9c1ad..8f3c8b2b4490 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -64,11 +64,8 @@ struct bpf_lru {
 
 static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node)
 {
-	/* ref is an approximation on access frequency.  It does not
-	 * have to be very accurate.  Hence, no protection is used.
-	 */
-	if (!node->ref)
-		node->ref = 1;
+	if (!READ_ONCE(node->ref))
+		WRITE_ONCE(node->ref, 1);
 }
 
 int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 517b6a5928cc..5b2741aa0d9b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1826,6 +1826,12 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		ret = 1;
 	} else if (ctx.optlen > max_optlen || ctx.optlen < -1) {
 		/* optlen is out of bounds */
+		if (*optlen > PAGE_SIZE && ctx.optlen >= 0) {
+			pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
+				     ctx.optlen, max_optlen);
+			ret = 0;
+			goto out;
+		}
 		ret = -EFAULT;
 	} else {
 		/* optlen within bounds, run kernel handler */
@@ -1881,8 +1887,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		.optname = optname,
 		.current_task = current,
 	};
+	int orig_optlen;
 	int ret;
 
+	orig_optlen = max_optlen;
 	ctx.optlen = max_optlen;
 	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
 	if (max_optlen < 0)
@@ -1905,6 +1913,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 			ret = -EFAULT;
 			goto out;
 		}
+		orig_optlen = ctx.optlen;
 
 		if (copy_from_user(ctx.optval, optval,
 				   min(ctx.optlen, max_optlen)) != 0) {
@@ -1922,6 +1931,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		goto out;
 
 	if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+		if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
+			pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
+				     ctx.optlen, max_optlen);
+			ret = retval;
+			goto out;
+		}
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 8d368fa353f9..4ef4c4f8a355 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1423,7 +1423,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = {
 #define DYNPTR_SIZE_MASK	0xFFFFFF
 #define DYNPTR_RDONLY_BIT	BIT(31)
 
-static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr)
+static bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr)
 {
 	return ptr->size & DYNPTR_RDONLY_BIT;
 }
@@ -1443,11 +1443,18 @@ static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *pt
 	return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT;
 }
 
-u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr)
+u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr)
 {
 	return ptr->size & DYNPTR_SIZE_MASK;
 }
 
+static void bpf_dynptr_set_size(struct bpf_dynptr_kern *ptr, u32 new_size)
+{
+	u32 metadata = ptr->size & ~DYNPTR_SIZE_MASK;
+
+	ptr->size = new_size | metadata;
+}
+
 int bpf_dynptr_check_size(u32 size)
 {
 	return size > DYNPTR_MAX_SIZE ? -E2BIG : 0;
@@ -1469,7 +1476,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
 
 static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
 {
-	u32 size = bpf_dynptr_get_size(ptr);
+	u32 size = __bpf_dynptr_size(ptr);
 
 	if (len > size || offset > size - len)
 		return -E2BIG;
@@ -1563,7 +1570,7 @@ BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, v
 	enum bpf_dynptr_type type;
 	int err;
 
-	if (!dst->data || bpf_dynptr_is_rdonly(dst))
+	if (!dst->data || __bpf_dynptr_is_rdonly(dst))
 		return -EINVAL;
 
 	err = bpf_dynptr_check_off_len(dst, offset, len);
@@ -1619,7 +1626,7 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3
 	if (err)
 		return 0;
 
-	if (bpf_dynptr_is_rdonly(ptr))
+	if (__bpf_dynptr_is_rdonly(ptr))
 		return 0;
 
 	type = bpf_dynptr_get_type(ptr);
@@ -2142,6 +2149,22 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid)
 		return NULL;
 	return cgrp;
 }
+
+/**
+ * bpf_task_under_cgroup - wrap task_under_cgroup_hierarchy() as a kfunc, test
+ * task's membership of cgroup ancestry.
+ * @task: the task to be tested
+ * @ancestor: possible ancestor of @task's cgroup
+ *
+ * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor.
+ * It follows all the same rules as cgroup_is_descendant, and only applies
+ * to the default hierarchy.
+ */
+__bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
+				       struct cgroup *ancestor)
+{
+	return task_under_cgroup_hierarchy(task, ancestor);
+}
 #endif /* CONFIG_CGROUPS */
 
 /**
@@ -2167,13 +2190,15 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
  * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data.
  * @ptr: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
- * @buffer: User-provided buffer to copy contents into
- * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
- *		 requested slice. This must be a constant.
+ * @buffer__opt: User-provided buffer to copy contents into.  May be NULL
+ * @buffer__szk: Size (in bytes) of the buffer if present. This is the
+ *               length of the requested slice. This must be a constant.
  *
  * For non-skb and non-xdp type dynptrs, there is no difference between
  * bpf_dynptr_slice and bpf_dynptr_data.
  *
+ *  If buffer__opt is NULL, the call will fail if buffer_opt was needed.
+ *
  * If the intention is to write to the data slice, please use
  * bpf_dynptr_slice_rdwr.
  *
@@ -2190,7 +2215,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
  * direct pointer)
  */
 __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset,
-				   void *buffer, u32 buffer__szk)
+				   void *buffer__opt, u32 buffer__szk)
 {
 	enum bpf_dynptr_type type;
 	u32 len = buffer__szk;
@@ -2210,15 +2235,17 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
 	case BPF_DYNPTR_TYPE_RINGBUF:
 		return ptr->data + ptr->offset + offset;
 	case BPF_DYNPTR_TYPE_SKB:
-		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer);
+		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
 	case BPF_DYNPTR_TYPE_XDP:
 	{
 		void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
 		if (xdp_ptr)
 			return xdp_ptr;
 
-		bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false);
-		return buffer;
+		if (!buffer__opt)
+			return NULL;
+		bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false);
+		return buffer__opt;
 	}
 	default:
 		WARN_ONCE(true, "unknown dynptr type %d\n", type);
@@ -2230,13 +2257,15 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
  * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data.
  * @ptr: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
- * @buffer: User-provided buffer to copy contents into
- * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
- *		 requested slice. This must be a constant.
+ * @buffer__opt: User-provided buffer to copy contents into. May be NULL
+ * @buffer__szk: Size (in bytes) of the buffer if present. This is the
+ *               length of the requested slice. This must be a constant.
  *
  * For non-skb and non-xdp type dynptrs, there is no difference between
  * bpf_dynptr_slice and bpf_dynptr_data.
  *
+ * If buffer__opt is NULL, the call will fail if buffer_opt was needed.
+ *
  * The returned pointer is writable and may point to either directly the dynptr
  * data at the requested offset or to the buffer if unable to obtain a direct
  * data pointer to (example: the requested slice is to the paged area of an skb
@@ -2267,9 +2296,9 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
  * direct pointer)
  */
 __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset,
-					void *buffer, u32 buffer__szk)
+					void *buffer__opt, u32 buffer__szk)
 {
-	if (!ptr->data || bpf_dynptr_is_rdonly(ptr))
+	if (!ptr->data || __bpf_dynptr_is_rdonly(ptr))
 		return NULL;
 
 	/* bpf_dynptr_slice_rdwr is the same logic as bpf_dynptr_slice.
@@ -2294,7 +2323,59 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o
 	 * will be copied out into the buffer and the user will need to call
 	 * bpf_dynptr_write() to commit changes.
 	 */
-	return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk);
+	return bpf_dynptr_slice(ptr, offset, buffer__opt, buffer__szk);
+}
+
+__bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 end)
+{
+	u32 size;
+
+	if (!ptr->data || start > end)
+		return -EINVAL;
+
+	size = __bpf_dynptr_size(ptr);
+
+	if (start > size || end > size)
+		return -ERANGE;
+
+	ptr->offset += start;
+	bpf_dynptr_set_size(ptr, end - start);
+
+	return 0;
+}
+
+__bpf_kfunc bool bpf_dynptr_is_null(struct bpf_dynptr_kern *ptr)
+{
+	return !ptr->data;
+}
+
+__bpf_kfunc bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr)
+{
+	if (!ptr->data)
+		return false;
+
+	return __bpf_dynptr_is_rdonly(ptr);
+}
+
+__bpf_kfunc __u32 bpf_dynptr_size(const struct bpf_dynptr_kern *ptr)
+{
+	if (!ptr->data)
+		return -EINVAL;
+
+	return __bpf_dynptr_size(ptr);
+}
+
+__bpf_kfunc int bpf_dynptr_clone(struct bpf_dynptr_kern *ptr,
+				 struct bpf_dynptr_kern *clone__uninit)
+{
+	if (!ptr->data) {
+		bpf_dynptr_set_null(clone__uninit);
+		return -EINVAL;
+	}
+
+	*clone__uninit = *ptr;
+
+	return 0;
 }
 
 __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj)
@@ -2341,6 +2422,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
 #endif
 BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
 BTF_SET8_END(generic_btf_ids)
@@ -2369,6 +2451,11 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_dynptr_adjust)
+BTF_ID_FLAGS(func, bpf_dynptr_is_null)
+BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
+BTF_ID_FLAGS(func, bpf_dynptr_size)
+BTF_ID_FLAGS(func, bpf_dynptr_clone)
 BTF_SET8_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 14f39c1e573e..909c112ef537 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5380,7 +5380,8 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write,
 		*(int *)table->data = unpriv_enable;
 	}
 
-	unpriv_ebpf_notify(unpriv_enable);
+	if (write)
+		unpriv_ebpf_notify(unpriv_enable);
 
 	return ret;
 }
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index ac021bc43a66..78acf28d4873 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -251,11 +251,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 	return tlinks;
 }
 
-static void __bpf_tramp_image_put_deferred(struct work_struct *work)
+static void bpf_tramp_image_free(struct bpf_tramp_image *im)
 {
-	struct bpf_tramp_image *im;
-
-	im = container_of(work, struct bpf_tramp_image, work);
 	bpf_image_ksym_del(&im->ksym);
 	bpf_jit_free_exec(im->image);
 	bpf_jit_uncharge_modmem(PAGE_SIZE);
@@ -263,6 +260,14 @@ static void __bpf_tramp_image_put_deferred(struct work_struct *work)
 	kfree_rcu(im, rcu);
 }
 
+static void __bpf_tramp_image_put_deferred(struct work_struct *work)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(work, struct bpf_tramp_image, work);
+	bpf_tramp_image_free(im);
+}
+
 /* callback, fexit step 3 or fentry step 2 */
 static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu)
 {
@@ -344,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
 	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
 }
 
-static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 {
 	struct bpf_tramp_image *im;
 	struct bpf_ksym *ksym;
@@ -371,7 +376,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
 
 	ksym = &im->ksym;
 	INIT_LIST_HEAD_RCU(&ksym->lnode);
-	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx);
+	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key);
 	bpf_image_ksym_add(image, ksym);
 	return im;
 
@@ -401,11 +406,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 		err = unregister_fentry(tr, tr->cur_image->image);
 		bpf_tramp_image_put(tr->cur_image);
 		tr->cur_image = NULL;
-		tr->selector = 0;
 		goto out;
 	}
 
-	im = bpf_tramp_image_alloc(tr->key, tr->selector);
+	im = bpf_tramp_image_alloc(tr->key);
 	if (IS_ERR(im)) {
 		err = PTR_ERR(im);
 		goto out;
@@ -438,12 +442,11 @@ again:
 					  &tr->func.model, tr->flags, tlinks,
 					  tr->func.addr);
 	if (err < 0)
-		goto out;
+		goto out_free;
 
 	set_memory_rox((long)im->image, 1);
 
-	WARN_ON(tr->cur_image && tr->selector == 0);
-	WARN_ON(!tr->cur_image && tr->selector);
+	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
 		/* progs already running at this address */
 		err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex);
@@ -468,18 +471,21 @@ again:
 	}
 #endif
 	if (err)
-		goto out;
+		goto out_free;
 
 	if (tr->cur_image)
 		bpf_tramp_image_put(tr->cur_image);
 	tr->cur_image = im;
-	tr->selector++;
 out:
 	/* If any error happens, restore previous flags */
 	if (err)
 		tr->flags = orig_flags;
 	kfree(tlinks);
 	return err;
+
+out_free:
+	bpf_tramp_image_free(im);
+	goto out;
 }
 
 static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fbcf5a4e2fcd..f597491259ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -240,6 +240,12 @@ static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
 			     (poisoned ? BPF_MAP_KEY_POISON : 0ULL);
 }
 
+static bool bpf_helper_call(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_JMP | BPF_CALL) &&
+	       insn->src_reg == 0;
+}
+
 static bool bpf_pseudo_call(const struct bpf_insn *insn)
 {
 	return insn->code == (BPF_JMP | BPF_CALL) &&
@@ -273,11 +279,6 @@ struct bpf_call_arg_meta {
 	struct btf_field *kptr_field;
 };
 
-struct btf_and_id {
-	struct btf *btf;
-	u32 btf_id;
-};
-
 struct bpf_kfunc_call_arg_meta {
 	/* In parameters */
 	struct btf *btf;
@@ -296,10 +297,18 @@ struct bpf_kfunc_call_arg_meta {
 		u64 value;
 		bool found;
 	} arg_constant;
-	union {
-		struct btf_and_id arg_obj_drop;
-		struct btf_and_id arg_refcount_acquire;
-	};
+
+	/* arg_btf and arg_btf_id are used by kfunc-specific handling,
+	 * generally to pass info about user-defined local kptr types to later
+	 * verification logic
+	 *   bpf_obj_drop
+	 *     Record the local kptr type to be drop'd
+	 *   bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type)
+	 *     Record the local kptr type to be refcount_incr'd
+	 */
+	struct btf *arg_btf;
+	u32 arg_btf_id;
+
 	struct {
 		struct btf_field *field;
 	} arg_list_head;
@@ -309,6 +318,7 @@ struct bpf_kfunc_call_arg_meta {
 	struct {
 		enum bpf_dynptr_type type;
 		u32 id;
+		u32 ref_obj_id;
 	} initialized_dynptr;
 	struct {
 		u8 spi;
@@ -468,6 +478,13 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 	return rec;
 }
 
+static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux;
+
+	return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
+}
+
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -515,6 +532,8 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_dynptr_data;
 }
 
+static bool is_callback_calling_kfunc(u32 btf_id);
+
 static bool is_callback_calling_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_for_each_map_elem ||
@@ -524,6 +543,11 @@ static bool is_callback_calling_function(enum bpf_func_id func_id)
 	       func_id == BPF_FUNC_user_ringbuf_drain;
 }
 
+static bool is_async_callback_calling_function(enum bpf_func_id func_id)
+{
+	return func_id == BPF_FUNC_timer_set_callback;
+}
+
 static bool is_storage_get_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_storage_get ||
@@ -604,9 +628,9 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 		 type & PTR_TRUSTED ? "trusted_" : ""
 	);
 
-	snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
+	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
 		 prefix, str[base_type(type)], postfix);
-	return env->type_str_buf;
+	return env->tmp_str_buf;
 }
 
 static char slot_type_char[] = {
@@ -847,11 +871,11 @@ static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env,
 				        struct bpf_func_state *state, int spi);
 
 static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-				   enum bpf_arg_type arg_type, int insn_idx)
+				   enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id)
 {
 	struct bpf_func_state *state = func(env, reg);
 	enum bpf_dynptr_type type;
-	int spi, i, id, err;
+	int spi, i, err;
 
 	spi = dynptr_get_spi(env, reg);
 	if (spi < 0)
@@ -887,7 +911,13 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
 
 	if (dynptr_type_refcounted(type)) {
 		/* The id is used to track proper releasing */
-		id = acquire_reference_state(env, insn_idx);
+		int id;
+
+		if (clone_ref_obj_id)
+			id = clone_ref_obj_id;
+		else
+			id = acquire_reference_state(env, insn_idx);
+
 		if (id < 0)
 			return id;
 
@@ -901,24 +931,15 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
 	return 0;
 }
 
-static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi)
 {
-	struct bpf_func_state *state = func(env, reg);
-	int spi, i;
-
-	spi = dynptr_get_spi(env, reg);
-	if (spi < 0)
-		return spi;
+	int i;
 
 	for (i = 0; i < BPF_REG_SIZE; i++) {
 		state->stack[spi].slot_type[i] = STACK_INVALID;
 		state->stack[spi - 1].slot_type[i] = STACK_INVALID;
 	}
 
-	/* Invalidate any slices associated with this dynptr */
-	if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type))
-		WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id));
-
 	__mark_reg_not_init(env, &state->stack[spi].spilled_ptr);
 	__mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr);
 
@@ -945,6 +966,50 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re
 	 */
 	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 	state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN;
+}
+
+static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi, ref_obj_id, i;
+
+	spi = dynptr_get_spi(env, reg);
+	if (spi < 0)
+		return spi;
+
+	if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) {
+		invalidate_dynptr(env, state, spi);
+		return 0;
+	}
+
+	ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id;
+
+	/* If the dynptr has a ref_obj_id, then we need to invalidate
+	 * two things:
+	 *
+	 * 1) Any dynptrs with a matching ref_obj_id (clones)
+	 * 2) Any slices derived from this dynptr.
+	 */
+
+	/* Invalidate any slices associated with this dynptr */
+	WARN_ON_ONCE(release_reference(env, ref_obj_id));
+
+	/* Invalidate any dynptr clones */
+	for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id)
+			continue;
+
+		/* it should always be the case that if the ref obj id
+		 * matches then the stack slot also belongs to a
+		 * dynptr
+		 */
+		if (state->stack[i].slot_type[0] != STACK_DYNPTR) {
+			verbose(env, "verifier internal error: misconfigured ref_obj_id\n");
+			return -EFAULT;
+		}
+		if (state->stack[i].spilled_ptr.dynptr.first_slot)
+			invalidate_dynptr(env, state, i);
+	}
 
 	return 0;
 }
@@ -1254,6 +1319,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack)
 	return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
 }
 
+static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack)
+{
+	return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL &&
+	       stack->spilled_ptr.type == SCALAR_VALUE;
+}
+
 static void scrub_spilled_slot(u8 *stype)
 {
 	if (*stype != STACK_INVALID)
@@ -3144,12 +3215,172 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
 	return btf_name_by_offset(desc_btf, func->name_off);
 }
 
+static inline void bt_init(struct backtrack_state *bt, u32 frame)
+{
+	bt->frame = frame;
+}
+
+static inline void bt_reset(struct backtrack_state *bt)
+{
+	struct bpf_verifier_env *env = bt->env;
+
+	memset(bt, 0, sizeof(*bt));
+	bt->env = env;
+}
+
+static inline u32 bt_empty(struct backtrack_state *bt)
+{
+	u64 mask = 0;
+	int i;
+
+	for (i = 0; i <= bt->frame; i++)
+		mask |= bt->reg_masks[i] | bt->stack_masks[i];
+
+	return mask == 0;
+}
+
+static inline int bt_subprog_enter(struct backtrack_state *bt)
+{
+	if (bt->frame == MAX_CALL_FRAMES - 1) {
+		verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame);
+		WARN_ONCE(1, "verifier backtracking bug");
+		return -EFAULT;
+	}
+	bt->frame++;
+	return 0;
+}
+
+static inline int bt_subprog_exit(struct backtrack_state *bt)
+{
+	if (bt->frame == 0) {
+		verbose(bt->env, "BUG subprog exit from frame 0\n");
+		WARN_ONCE(1, "verifier backtracking bug");
+		return -EFAULT;
+	}
+	bt->frame--;
+	return 0;
+}
+
+static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg)
+{
+	bt->reg_masks[frame] |= 1 << reg;
+}
+
+static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg)
+{
+	bt->reg_masks[frame] &= ~(1 << reg);
+}
+
+static inline void bt_set_reg(struct backtrack_state *bt, u32 reg)
+{
+	bt_set_frame_reg(bt, bt->frame, reg);
+}
+
+static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg)
+{
+	bt_clear_frame_reg(bt, bt->frame, reg);
+}
+
+static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	bt->stack_masks[frame] |= 1ull << slot;
+}
+
+static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	bt->stack_masks[frame] &= ~(1ull << slot);
+}
+
+static inline void bt_set_slot(struct backtrack_state *bt, u32 slot)
+{
+	bt_set_frame_slot(bt, bt->frame, slot);
+}
+
+static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot)
+{
+	bt_clear_frame_slot(bt, bt->frame, slot);
+}
+
+static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame)
+{
+	return bt->reg_masks[frame];
+}
+
+static inline u32 bt_reg_mask(struct backtrack_state *bt)
+{
+	return bt->reg_masks[bt->frame];
+}
+
+static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame)
+{
+	return bt->stack_masks[frame];
+}
+
+static inline u64 bt_stack_mask(struct backtrack_state *bt)
+{
+	return bt->stack_masks[bt->frame];
+}
+
+static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
+{
+	return bt->reg_masks[bt->frame] & (1 << reg);
+}
+
+static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
+{
+	return bt->stack_masks[bt->frame] & (1ull << slot);
+}
+
+/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
+static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask)
+{
+	DECLARE_BITMAP(mask, 64);
+	bool first = true;
+	int i, n;
+
+	buf[0] = '\0';
+
+	bitmap_from_u64(mask, reg_mask);
+	for_each_set_bit(i, mask, 32) {
+		n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i);
+		first = false;
+		buf += n;
+		buf_sz -= n;
+		if (buf_sz < 0)
+			break;
+	}
+}
+/* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */
+static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
+{
+	DECLARE_BITMAP(mask, 64);
+	bool first = true;
+	int i, n;
+
+	buf[0] = '\0';
+
+	bitmap_from_u64(mask, stack_mask);
+	for_each_set_bit(i, mask, 64) {
+		n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8);
+		first = false;
+		buf += n;
+		buf_sz -= n;
+		if (buf_sz < 0)
+			break;
+	}
+}
+
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
+ *
+ * @idx is an index of the instruction we are currently processing;
+ * @subseq_idx is an index of the subsequent instruction that:
+ *   - *would be* executed next, if jump history is viewed in forward order;
+ *   - *was* processed previously during backtracking.
  */
-static int backtrack_insn(struct bpf_verifier_env *env, int idx,
-			  u32 *reg_mask, u64 *stack_mask)
+static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
+			  struct backtrack_state *bt)
 {
 	const struct bpf_insn_cbs cbs = {
 		.cb_call	= disasm_kfunc_name,
@@ -3160,20 +3391,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 	u8 class = BPF_CLASS(insn->code);
 	u8 opcode = BPF_OP(insn->code);
 	u8 mode = BPF_MODE(insn->code);
-	u32 dreg = 1u << insn->dst_reg;
-	u32 sreg = 1u << insn->src_reg;
-	u32 spi;
+	u32 dreg = insn->dst_reg;
+	u32 sreg = insn->src_reg;
+	u32 spi, i;
 
 	if (insn->code == 0)
 		return 0;
 	if (env->log.level & BPF_LOG_LEVEL2) {
-		verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
+		fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt));
+		verbose(env, "mark_precise: frame%d: regs=%s ",
+			bt->frame, env->tmp_str_buf);
+		fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt));
+		verbose(env, "stack=%s before ", env->tmp_str_buf);
 		verbose(env, "%d: ", idx);
 		print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
 	}
 
 	if (class == BPF_ALU || class == BPF_ALU64) {
-		if (!(*reg_mask & dreg))
+		if (!bt_is_reg_set(bt, dreg))
 			return 0;
 		if (opcode == BPF_MOV) {
 			if (BPF_SRC(insn->code) == BPF_X) {
@@ -3181,8 +3416,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 				 * dreg needs precision after this insn
 				 * sreg needs precision before this insn
 				 */
-				*reg_mask &= ~dreg;
-				*reg_mask |= sreg;
+				bt_clear_reg(bt, dreg);
+				bt_set_reg(bt, sreg);
 			} else {
 				/* dreg = K
 				 * dreg needs precision after this insn.
@@ -3190,7 +3425,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 				 * as precise=true in this verifier state.
 				 * No further markings in parent are necessary
 				 */
-				*reg_mask &= ~dreg;
+				bt_clear_reg(bt, dreg);
 			}
 		} else {
 			if (BPF_SRC(insn->code) == BPF_X) {
@@ -3198,15 +3433,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 				 * both dreg and sreg need precision
 				 * before this insn
 				 */
-				*reg_mask |= sreg;
+				bt_set_reg(bt, sreg);
 			} /* else dreg += K
 			   * dreg still needs precision before this insn
 			   */
 		}
 	} else if (class == BPF_LDX) {
-		if (!(*reg_mask & dreg))
+		if (!bt_is_reg_set(bt, dreg))
 			return 0;
-		*reg_mask &= ~dreg;
+		bt_clear_reg(bt, dreg);
 
 		/* scalars can only be spilled into stack w/o losing precision.
 		 * Load from any other memory can be zero extended.
@@ -3227,9 +3462,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			WARN_ONCE(1, "verifier backtracking bug");
 			return -EFAULT;
 		}
-		*stack_mask |= 1ull << spi;
+		bt_set_slot(bt, spi);
 	} else if (class == BPF_STX || class == BPF_ST) {
-		if (*reg_mask & dreg)
+		if (bt_is_reg_set(bt, dreg))
 			/* stx & st shouldn't be using _scalar_ dst_reg
 			 * to access memory. It means backtracking
 			 * encountered a case of pointer subtraction.
@@ -3244,20 +3479,92 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			WARN_ONCE(1, "verifier backtracking bug");
 			return -EFAULT;
 		}
-		if (!(*stack_mask & (1ull << spi)))
+		if (!bt_is_slot_set(bt, spi))
 			return 0;
-		*stack_mask &= ~(1ull << spi);
+		bt_clear_slot(bt, spi);
 		if (class == BPF_STX)
-			*reg_mask |= sreg;
+			bt_set_reg(bt, sreg);
 	} else if (class == BPF_JMP || class == BPF_JMP32) {
-		if (opcode == BPF_CALL) {
-			if (insn->src_reg == BPF_PSEUDO_CALL)
-				return -ENOTSUPP;
-			/* BPF helpers that invoke callback subprogs are
-			 * equivalent to BPF_PSEUDO_CALL above
+		if (bpf_pseudo_call(insn)) {
+			int subprog_insn_idx, subprog;
+
+			subprog_insn_idx = idx + insn->imm + 1;
+			subprog = find_subprog(env, subprog_insn_idx);
+			if (subprog < 0)
+				return -EFAULT;
+
+			if (subprog_is_global(env, subprog)) {
+				/* check that jump history doesn't have any
+				 * extra instructions from subprog; the next
+				 * instruction after call to global subprog
+				 * should be literally next instruction in
+				 * caller program
+				 */
+				WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug");
+				/* r1-r5 are invalidated after subprog call,
+				 * so for global func call it shouldn't be set
+				 * anymore
+				 */
+				if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
+					verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+					WARN_ONCE(1, "verifier backtracking bug");
+					return -EFAULT;
+				}
+				/* global subprog always sets R0 */
+				bt_clear_reg(bt, BPF_REG_0);
+				return 0;
+			} else {
+				/* static subprog call instruction, which
+				 * means that we are exiting current subprog,
+				 * so only r1-r5 could be still requested as
+				 * precise, r0 and r6-r10 or any stack slot in
+				 * the current frame should be zero by now
+				 */
+				if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
+					verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+					WARN_ONCE(1, "verifier backtracking bug");
+					return -EFAULT;
+				}
+				/* we don't track register spills perfectly,
+				 * so fallback to force-precise instead of failing */
+				if (bt_stack_mask(bt) != 0)
+					return -ENOTSUPP;
+				/* propagate r1-r5 to the caller */
+				for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
+					if (bt_is_reg_set(bt, i)) {
+						bt_clear_reg(bt, i);
+						bt_set_frame_reg(bt, bt->frame - 1, i);
+					}
+				}
+				if (bt_subprog_exit(bt))
+					return -EFAULT;
+				return 0;
+			}
+		} else if ((bpf_helper_call(insn) &&
+			    is_callback_calling_function(insn->imm) &&
+			    !is_async_callback_calling_function(insn->imm)) ||
+			   (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
+			/* callback-calling helper or kfunc call, which means
+			 * we are exiting from subprog, but unlike the subprog
+			 * call handling above, we shouldn't propagate
+			 * precision of r1-r5 (if any requested), as they are
+			 * not actually arguments passed directly to callback
+			 * subprogs
 			 */
-			if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
+			if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
+				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+				WARN_ONCE(1, "verifier backtracking bug");
+				return -EFAULT;
+			}
+			if (bt_stack_mask(bt) != 0)
 				return -ENOTSUPP;
+			/* clear r1-r5 in callback subprog's mask */
+			for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+				bt_clear_reg(bt, i);
+			if (bt_subprog_exit(bt))
+				return -EFAULT;
+			return 0;
+		} else if (opcode == BPF_CALL) {
 			/* kfunc with imm==0 is invalid and fixup_kfunc_call will
 			 * catch this error later. Make backtracking conservative
 			 * with ENOTSUPP.
@@ -3265,19 +3572,51 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
 				return -ENOTSUPP;
 			/* regular helper call sets R0 */
-			*reg_mask &= ~1;
-			if (*reg_mask & 0x3f) {
+			bt_clear_reg(bt, BPF_REG_0);
+			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
 				/* if backtracing was looking for registers R1-R5
 				 * they should have been found already.
 				 */
-				verbose(env, "BUG regs %x\n", *reg_mask);
+				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
 			}
 		} else if (opcode == BPF_EXIT) {
-			return -ENOTSUPP;
+			bool r0_precise;
+
+			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
+				/* if backtracing was looking for registers R1-R5
+				 * they should have been found already.
+				 */
+				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+				WARN_ONCE(1, "verifier backtracking bug");
+				return -EFAULT;
+			}
+
+			/* BPF_EXIT in subprog or callback always returns
+			 * right after the call instruction, so by checking
+			 * whether the instruction at subseq_idx-1 is subprog
+			 * call or not we can distinguish actual exit from
+			 * *subprog* from exit from *callback*. In the former
+			 * case, we need to propagate r0 precision, if
+			 * necessary. In the former we never do that.
+			 */
+			r0_precise = subseq_idx - 1 >= 0 &&
+				     bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) &&
+				     bt_is_reg_set(bt, BPF_REG_0);
+
+			bt_clear_reg(bt, BPF_REG_0);
+			if (bt_subprog_enter(bt))
+				return -EFAULT;
+
+			if (r0_precise)
+				bt_set_reg(bt, BPF_REG_0);
+			/* r6-r9 and stack slots will stay set in caller frame
+			 * bitmasks until we return back from callee(s)
+			 */
+			return 0;
 		} else if (BPF_SRC(insn->code) == BPF_X) {
-			if (!(*reg_mask & (dreg | sreg)))
+			if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg))
 				return 0;
 			/* dreg <cond> sreg
 			 * Both dreg and sreg need precision before
@@ -3285,7 +3624,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			 * before it would be equally necessary to
 			 * propagate it to dreg.
 			 */
-			*reg_mask |= (sreg | dreg);
+			bt_set_reg(bt, dreg);
+			bt_set_reg(bt, sreg);
 			 /* else dreg <cond> K
 			  * Only dreg still needs precision before
 			  * this insn, so for the K-based conditional
@@ -3293,9 +3633,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			  */
 		}
 	} else if (class == BPF_LD) {
-		if (!(*reg_mask & dreg))
+		if (!bt_is_reg_set(bt, dreg))
 			return 0;
-		*reg_mask &= ~dreg;
+		bt_clear_reg(bt, dreg);
 		/* It's ld_imm64 or ld_abs or ld_ind.
 		 * For ld_imm64 no further tracking of precision
 		 * into parent is necessary
@@ -3366,6 +3706,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 	struct bpf_reg_state *reg;
 	int i, j;
 
+	if (env->log.level & BPF_LOG_LEVEL2) {
+		verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n",
+			st->curframe);
+	}
+
 	/* big hammer: mark all scalars precise in this path.
 	 * pop_stack may still get !precise scalars.
 	 * We also skip current state and go straight to first parent state,
@@ -3377,17 +3722,25 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 			func = st->frame[i];
 			for (j = 0; j < BPF_REG_FP; j++) {
 				reg = &func->regs[j];
-				if (reg->type != SCALAR_VALUE)
+				if (reg->type != SCALAR_VALUE || reg->precise)
 					continue;
 				reg->precise = true;
+				if (env->log.level & BPF_LOG_LEVEL2) {
+					verbose(env, "force_precise: frame%d: forcing r%d to be precise\n",
+						i, j);
+				}
 			}
 			for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
 				if (!is_spilled_reg(&func->stack[j]))
 					continue;
 				reg = &func->stack[j].spilled_ptr;
-				if (reg->type != SCALAR_VALUE)
+				if (reg->type != SCALAR_VALUE || reg->precise)
 					continue;
 				reg->precise = true;
+				if (env->log.level & BPF_LOG_LEVEL2) {
+					verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n",
+						i, -(j + 1) * 8);
+				}
 			}
 		}
 	}
@@ -3505,62 +3858,49 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
  * mark_all_scalars_imprecise() to hopefully get more permissive and generic
  * finalized states which help in short circuiting more future states.
  */
-static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno,
-				  int spi)
+static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 {
+	struct backtrack_state *bt = &env->bt;
 	struct bpf_verifier_state *st = env->cur_state;
 	int first_idx = st->first_insn_idx;
 	int last_idx = env->insn_idx;
+	int subseq_idx = -1;
 	struct bpf_func_state *func;
 	struct bpf_reg_state *reg;
-	u32 reg_mask = regno >= 0 ? 1u << regno : 0;
-	u64 stack_mask = spi >= 0 ? 1ull << spi : 0;
 	bool skip_first = true;
-	bool new_marks = false;
-	int i, err;
+	int i, fr, err;
 
 	if (!env->bpf_capable)
 		return 0;
 
+	/* set frame number from which we are starting to backtrack */
+	bt_init(bt, env->cur_state->curframe);
+
 	/* Do sanity checks against current state of register and/or stack
 	 * slot, but don't set precise flag in current state, as precision
 	 * tracking in the current state is unnecessary.
 	 */
-	func = st->frame[frame];
+	func = st->frame[bt->frame];
 	if (regno >= 0) {
 		reg = &func->regs[regno];
 		if (reg->type != SCALAR_VALUE) {
 			WARN_ONCE(1, "backtracing misuse");
 			return -EFAULT;
 		}
-		new_marks = true;
-	}
-
-	while (spi >= 0) {
-		if (!is_spilled_reg(&func->stack[spi])) {
-			stack_mask = 0;
-			break;
-		}
-		reg = &func->stack[spi].spilled_ptr;
-		if (reg->type != SCALAR_VALUE) {
-			stack_mask = 0;
-			break;
-		}
-		new_marks = true;
-		break;
+		bt_set_reg(bt, regno);
 	}
 
-	if (!new_marks)
-		return 0;
-	if (!reg_mask && !stack_mask)
+	if (bt_empty(bt))
 		return 0;
 
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
 
-		if (env->log.level & BPF_LOG_LEVEL2)
-			verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
+		if (env->log.level & BPF_LOG_LEVEL2) {
+			verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
+				bt->frame, last_idx, first_idx, subseq_idx);
+		}
 
 		if (last_idx < 0) {
 			/* we are at the entry into subprog, which
@@ -3571,12 +3911,13 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 			if (st->curframe == 0 &&
 			    st->frame[0]->subprogno > 0 &&
 			    st->frame[0]->callsite == BPF_MAIN_FUNC &&
-			    stack_mask == 0 && (reg_mask & ~0x3e) == 0) {
-				bitmap_from_u64(mask, reg_mask);
+			    bt_stack_mask(bt) == 0 &&
+			    (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) {
+				bitmap_from_u64(mask, bt_reg_mask(bt));
 				for_each_set_bit(i, mask, 32) {
 					reg = &st->frame[0]->regs[i];
 					if (reg->type != SCALAR_VALUE) {
-						reg_mask &= ~(1u << i);
+						bt_clear_reg(bt, i);
 						continue;
 					}
 					reg->precise = true;
@@ -3584,8 +3925,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 				return 0;
 			}
 
-			verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n",
-				st->frame[0]->subprogno, reg_mask, stack_mask);
+			verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n",
+				st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt));
 			WARN_ONCE(1, "verifier backtracking bug");
 			return -EFAULT;
 		}
@@ -3595,15 +3936,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 				err = 0;
 				skip_first = false;
 			} else {
-				err = backtrack_insn(env, i, &reg_mask, &stack_mask);
+				err = backtrack_insn(env, i, subseq_idx, bt);
 			}
 			if (err == -ENOTSUPP) {
-				mark_all_scalars_precise(env, st);
+				mark_all_scalars_precise(env, env->cur_state);
+				bt_reset(bt);
 				return 0;
 			} else if (err) {
 				return err;
 			}
-			if (!reg_mask && !stack_mask)
+			if (bt_empty(bt))
 				/* Found assignment(s) into tracked register in this state.
 				 * Since this state is already marked, just return.
 				 * Nothing to be tracked further in the parent state.
@@ -3611,6 +3953,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 				return 0;
 			if (i == first_idx)
 				break;
+			subseq_idx = i;
 			i = get_prev_insn_idx(st, i, &history);
 			if (i >= env->prog->len) {
 				/* This can happen if backtracking reached insn 0
@@ -3628,84 +3971,95 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 		if (!st)
 			break;
 
-		new_marks = false;
-		func = st->frame[frame];
-		bitmap_from_u64(mask, reg_mask);
-		for_each_set_bit(i, mask, 32) {
-			reg = &func->regs[i];
-			if (reg->type != SCALAR_VALUE) {
-				reg_mask &= ~(1u << i);
-				continue;
-			}
-			if (!reg->precise)
-				new_marks = true;
-			reg->precise = true;
-		}
-
-		bitmap_from_u64(mask, stack_mask);
-		for_each_set_bit(i, mask, 64) {
-			if (i >= func->allocated_stack / BPF_REG_SIZE) {
-				/* the sequence of instructions:
-				 * 2: (bf) r3 = r10
-				 * 3: (7b) *(u64 *)(r3 -8) = r0
-				 * 4: (79) r4 = *(u64 *)(r10 -8)
-				 * doesn't contain jmps. It's backtracked
-				 * as a single block.
-				 * During backtracking insn 3 is not recognized as
-				 * stack access, so at the end of backtracking
-				 * stack slot fp-8 is still marked in stack_mask.
-				 * However the parent state may not have accessed
-				 * fp-8 and it's "unallocated" stack space.
-				 * In such case fallback to conservative.
-				 */
-				mark_all_scalars_precise(env, st);
-				return 0;
+		for (fr = bt->frame; fr >= 0; fr--) {
+			func = st->frame[fr];
+			bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr));
+			for_each_set_bit(i, mask, 32) {
+				reg = &func->regs[i];
+				if (reg->type != SCALAR_VALUE) {
+					bt_clear_frame_reg(bt, fr, i);
+					continue;
+				}
+				if (reg->precise)
+					bt_clear_frame_reg(bt, fr, i);
+				else
+					reg->precise = true;
 			}
 
-			if (!is_spilled_reg(&func->stack[i])) {
-				stack_mask &= ~(1ull << i);
-				continue;
+			bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
+			for_each_set_bit(i, mask, 64) {
+				if (i >= func->allocated_stack / BPF_REG_SIZE) {
+					/* the sequence of instructions:
+					 * 2: (bf) r3 = r10
+					 * 3: (7b) *(u64 *)(r3 -8) = r0
+					 * 4: (79) r4 = *(u64 *)(r10 -8)
+					 * doesn't contain jmps. It's backtracked
+					 * as a single block.
+					 * During backtracking insn 3 is not recognized as
+					 * stack access, so at the end of backtracking
+					 * stack slot fp-8 is still marked in stack_mask.
+					 * However the parent state may not have accessed
+					 * fp-8 and it's "unallocated" stack space.
+					 * In such case fallback to conservative.
+					 */
+					mark_all_scalars_precise(env, env->cur_state);
+					bt_reset(bt);
+					return 0;
+				}
+
+				if (!is_spilled_scalar_reg(&func->stack[i])) {
+					bt_clear_frame_slot(bt, fr, i);
+					continue;
+				}
+				reg = &func->stack[i].spilled_ptr;
+				if (reg->precise)
+					bt_clear_frame_slot(bt, fr, i);
+				else
+					reg->precise = true;
 			}
-			reg = &func->stack[i].spilled_ptr;
-			if (reg->type != SCALAR_VALUE) {
-				stack_mask &= ~(1ull << i);
-				continue;
+			if (env->log.level & BPF_LOG_LEVEL2) {
+				fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
+					     bt_frame_reg_mask(bt, fr));
+				verbose(env, "mark_precise: frame%d: parent state regs=%s ",
+					fr, env->tmp_str_buf);
+				fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
+					       bt_frame_stack_mask(bt, fr));
+				verbose(env, "stack=%s: ", env->tmp_str_buf);
+				print_verifier_state(env, func, true);
 			}
-			if (!reg->precise)
-				new_marks = true;
-			reg->precise = true;
-		}
-		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)
-			break;
-		if (!new_marks)
-			break;
+		if (bt_empty(bt))
+			return 0;
 
+		subseq_idx = first_idx;
 		last_idx = st->last_insn_idx;
 		first_idx = st->first_insn_idx;
 	}
+
+	/* if we still have requested precise regs or slots, we missed
+	 * something (e.g., stack access through non-r10 register), so
+	 * fallback to marking all precise
+	 */
+	if (!bt_empty(bt)) {
+		mark_all_scalars_precise(env, env->cur_state);
+		bt_reset(bt);
+	}
+
 	return 0;
 }
 
 int mark_chain_precision(struct bpf_verifier_env *env, int regno)
 {
-	return __mark_chain_precision(env, env->cur_state->curframe, regno, -1);
+	return __mark_chain_precision(env, regno);
 }
 
-static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno)
-{
-	return __mark_chain_precision(env, frame, regno, -1);
-}
-
-static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi)
+/* mark_chain_precision_batch() assumes that env->bt is set in the caller to
+ * desired reg and stack masks across all relevant frames
+ */
+static int mark_chain_precision_batch(struct bpf_verifier_env *env)
 {
-	return __mark_chain_precision(env, frame, -1, spi);
+	return __mark_chain_precision(env, -1);
 }
 
 static bool is_spillable_regtype(enum bpf_reg_type type)
@@ -4067,6 +4421,7 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env,
 	for (i = min_off; i < max_off; i++) {
 		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
+		mark_stack_slot_scratched(env, spi);
 		stype = ptr_state->stack[spi].slot_type;
 		if (stype[slot % BPF_REG_SIZE] != STACK_ZERO)
 			break;
@@ -4118,6 +4473,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
 
+	mark_stack_slot_scratched(env, spi);
+
 	if (is_spilled_reg(&reg_state->stack[spi])) {
 		u8 spill_size = 1;
 
@@ -6677,7 +7034,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
  * type, and declare it as 'const struct bpf_dynptr *' in their prototype.
  */
 static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx,
-			       enum bpf_arg_type arg_type)
+			       enum bpf_arg_type arg_type, int clone_ref_obj_id)
 {
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	int err;
@@ -6721,7 +7078,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 				return err;
 		}
 
-		err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx);
+		err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id);
 	} else /* MEM_RDONLY and None case from above */ {
 		/* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */
 		if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) {
@@ -7143,12 +7500,16 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 	 * 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
 	 *
+	 * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type.
+	 *
 	 * 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;
+	if (base_type(arg_type) == ARG_PTR_TO_MEM)
+		type &= ~DYNPTR_TYPE_FLAG_MASK;
 
 	if (meta->func_id == BPF_FUNC_kptr_xchg && type & MEM_ALLOC)
 		type &= ~MEM_ALLOC;
@@ -7631,7 +7992,7 @@ skip_type_check:
 		err = check_mem_size_reg(env, reg, regno, true, meta);
 		break;
 	case ARG_PTR_TO_DYNPTR:
-		err = process_dynptr_func(env, regno, insn_idx, arg_type);
+		err = process_dynptr_func(env, regno, insn_idx, arg_type, 0);
 		if (err)
 			return err;
 		break;
@@ -8178,17 +8539,13 @@ static int set_callee_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *caller,
 			    struct bpf_func_state *callee, int insn_idx);
 
-static bool is_callback_calling_kfunc(u32 btf_id);
-
 static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx, int subprog,
 			     set_callee_state_fn set_callee_state_cb)
 {
 	struct bpf_verifier_state *state = env->cur_state;
-	struct bpf_func_info_aux *func_info_aux;
 	struct bpf_func_state *caller, *callee;
 	int err;
-	bool is_global = false;
 
 	if (state->curframe + 1 >= MAX_CALL_FRAMES) {
 		verbose(env, "the call stack of %d frames is too deep\n",
@@ -8203,13 +8560,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		return -EFAULT;
 	}
 
-	func_info_aux = env->prog->aux->func_info_aux;
-	if (func_info_aux)
-		is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
 	err = btf_check_subprog_call(env, subprog, caller->regs);
 	if (err == -EFAULT)
 		return err;
-	if (is_global) {
+	if (subprog_is_global(env, subprog)) {
 		if (err) {
 			verbose(env, "Caller passes invalid args into func#%d\n",
 				subprog);
@@ -9398,6 +9752,11 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf,
 	return __kfunc_param_match_suffix(btf, arg, "__szk");
 }
 
+static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__opt");
+}
+
 static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg)
 {
 	return __kfunc_param_match_suffix(btf, arg, "__k");
@@ -9595,6 +9954,7 @@ enum special_kfunc_type {
 	KF_bpf_dynptr_from_xdp,
 	KF_bpf_dynptr_slice,
 	KF_bpf_dynptr_slice_rdwr,
+	KF_bpf_dynptr_clone,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -9614,6 +9974,7 @@ BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
 BTF_ID(func, bpf_dynptr_slice)
 BTF_ID(func, bpf_dynptr_slice_rdwr)
+BTF_ID(func, bpf_dynptr_clone)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -9635,6 +9996,7 @@ BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
 BTF_ID(func, bpf_dynptr_slice)
 BTF_ID(func, bpf_dynptr_slice_rdwr)
+BTF_ID(func, bpf_dynptr_clone)
 
 static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -10323,13 +10685,14 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			}
 			if (meta->btf == btf_vmlinux &&
 			    meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
-				meta->arg_obj_drop.btf = reg->btf;
-				meta->arg_obj_drop.btf_id = reg->btf_id;
+				meta->arg_btf = reg->btf;
+				meta->arg_btf_id = reg->btf_id;
 			}
 			break;
 		case KF_ARG_PTR_TO_DYNPTR:
 		{
 			enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR;
+			int clone_ref_obj_id = 0;
 
 			if (reg->type != PTR_TO_STACK &&
 			    reg->type != CONST_PTR_TO_DYNPTR) {
@@ -10343,12 +10706,28 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			if (is_kfunc_arg_uninit(btf, &args[i]))
 				dynptr_arg_type |= MEM_UNINIT;
 
-			if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb])
+			if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
 				dynptr_arg_type |= DYNPTR_TYPE_SKB;
-			else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp])
+			} else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) {
 				dynptr_arg_type |= DYNPTR_TYPE_XDP;
+			} else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] &&
+				   (dynptr_arg_type & MEM_UNINIT)) {
+				enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type;
 
-			ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type);
+				if (parent_type == BPF_DYNPTR_TYPE_INVALID) {
+					verbose(env, "verifier internal error: no dynptr type for parent of clone\n");
+					return -EFAULT;
+				}
+
+				dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type);
+				clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id;
+				if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) {
+					verbose(env, "verifier internal error: missing ref obj id for parent of clone\n");
+					return -EFAULT;
+				}
+			}
+
+			ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id);
 			if (ret < 0)
 				return ret;
 
@@ -10361,6 +10740,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				}
 				meta->initialized_dynptr.id = id;
 				meta->initialized_dynptr.type = dynptr_get_type(env, reg);
+				meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg);
 			}
 
 			break;
@@ -10464,13 +10844,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			break;
 		case KF_ARG_PTR_TO_MEM_SIZE:
 		{
+			struct bpf_reg_state *buff_reg = &regs[regno];
+			const struct btf_param *buff_arg = &args[i];
 			struct bpf_reg_state *size_reg = &regs[regno + 1];
 			const struct btf_param *size_arg = &args[i + 1];
 
-			ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
-			if (ret < 0) {
-				verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
-				return ret;
+			if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) {
+				ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
+				if (ret < 0) {
+					verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
+					return ret;
+				}
 			}
 
 			if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) {
@@ -10513,8 +10897,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				verbose(env, "bpf_refcount_acquire calls are disabled for now\n");
 				return -EINVAL;
 			}
-			meta->arg_refcount_acquire.btf = reg->btf;
-			meta->arg_refcount_acquire.btf_id = reg->btf_id;
+			meta->arg_btf = reg->btf;
+			meta->arg_btf_id = reg->btf_id;
 			break;
 		}
 	}
@@ -10746,12 +11130,12 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
 				mark_reg_known_zero(env, regs, BPF_REG_0);
 				regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
-				regs[BPF_REG_0].btf = meta.arg_refcount_acquire.btf;
-				regs[BPF_REG_0].btf_id = meta.arg_refcount_acquire.btf_id;
+				regs[BPF_REG_0].btf = meta.arg_btf;
+				regs[BPF_REG_0].btf_id = meta.arg_btf_id;
 
 				insn_aux->kptr_struct_meta =
-					btf_find_struct_meta(meta.arg_refcount_acquire.btf,
-							     meta.arg_refcount_acquire.btf_id);
+					btf_find_struct_meta(meta.arg_btf,
+							     meta.arg_btf_id);
 			} else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] ||
 				   meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) {
 				struct btf_field *field = meta.arg_list_head.field;
@@ -10881,8 +11265,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
 			if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
 				insn_aux->kptr_struct_meta =
-					btf_find_struct_meta(meta.arg_obj_drop.btf,
-							     meta.arg_obj_drop.btf_id);
+					btf_find_struct_meta(meta.arg_btf,
+							     meta.arg_btf_id);
 			}
 		}
 	}
@@ -15118,20 +15502,25 @@ static int propagate_precision(struct bpf_verifier_env *env,
 	struct bpf_reg_state *state_reg;
 	struct bpf_func_state *state;
 	int i, err = 0, fr;
+	bool first;
 
 	for (fr = old->curframe; fr >= 0; fr--) {
 		state = old->frame[fr];
 		state_reg = state->regs;
+		first = true;
 		for (i = 0; i < BPF_REG_FP; i++, state_reg++) {
 			if (state_reg->type != SCALAR_VALUE ||
 			    !state_reg->precise ||
 			    !(state_reg->live & REG_LIVE_READ))
 				continue;
-			if (env->log.level & BPF_LOG_LEVEL2)
-				verbose(env, "frame %d: propagating r%d\n", fr, i);
-			err = mark_chain_precision_frame(env, fr, i);
-			if (err < 0)
-				return err;
+			if (env->log.level & BPF_LOG_LEVEL2) {
+				if (first)
+					verbose(env, "frame %d: propagating r%d", fr, i);
+				else
+					verbose(env, ",r%d", i);
+			}
+			bt_set_frame_reg(&env->bt, fr, i);
+			first = false;
 		}
 
 		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
@@ -15142,14 +15531,24 @@ static int propagate_precision(struct bpf_verifier_env *env,
 			    !state_reg->precise ||
 			    !(state_reg->live & REG_LIVE_READ))
 				continue;
-			if (env->log.level & BPF_LOG_LEVEL2)
-				verbose(env, "frame %d: propagating fp%d\n",
-					fr, (-i - 1) * BPF_REG_SIZE);
-			err = mark_chain_precision_stack_frame(env, fr, i);
-			if (err < 0)
-				return err;
+			if (env->log.level & BPF_LOG_LEVEL2) {
+				if (first)
+					verbose(env, "frame %d: propagating fp%d",
+						fr, (-i - 1) * BPF_REG_SIZE);
+				else
+					verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE);
+			}
+			bt_set_frame_slot(&env->bt, fr, i);
+			first = false;
 		}
+		if (!first)
+			verbose(env, "\n");
 	}
+
+	err = mark_chain_precision_batch(env);
+	if (err < 0)
+		return err;
+
 	return 0;
 }
 
@@ -18806,6 +19205,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (!env)
 		return -ENOMEM;
 
+	env->bt.env = env;
+
 	len = (*prog)->len;
 	env->insn_aux_data =
 		vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));