diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 85f73e0bbd0f..6691fe8a32c3 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -486,6 +486,16 @@ Example usage in BPF program:
 	/* note that the last argument is omitted */
         bpf_task_work_schedule_signal(task, &work->tw, &arrmap, task_work_callback);
 
+2.5.10 KF_PERFMON flag
+----------------------
+
+The KF_PERFMON flag is used for kfuncs that can expose kernel memory or kernel
+addresses to the BPF program, for example by reading through a pointer that the
+verifier does not check. Calling such a kfunc requires CAP_PERFMON, or
+CAP_SYS_ADMIN, in the same way that the equivalent BPF helpers are gated in
+bpf_base_func_proto(). A program loaded with CAP_BPF alone is rejected at load
+time.
+
 2.6 Registering the kfuncs
 --------------------------
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index c18e005a41db..c5f55d6161fe 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -600,6 +600,8 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 		 * 12 registers are on the stack
 		 */
 		emit(A64_SUB_I(1, A64_SP, A64_FP, 96), ctx);
+		/* The callback may use its own BPF stack, set up fp for it. */
+		ctx->fp_used = true;
 	}
 
 	/* Stack must be multiples of 16B */
diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c
index 40a878b672f5..15a2a153dc87 100644
--- a/arch/mips/net/bpf_jit_comp32.c
+++ b/arch/mips/net/bpf_jit_comp32.c
@@ -1111,7 +1111,7 @@ static void emit_jmp_i64(struct jit_context *ctx,
 			emit(ctx, xor, tmp, lo(dst), tmp);
 		}
 		if (imm < 0) { /* Compare sign extension */
-			emit(ctx, addu, MIPS_R_T9, hi(dst), 1);
+			emit(ctx, addiu, MIPS_R_T9, hi(dst), 1);
 			emit(ctx, or, tmp, tmp, MIPS_R_T9);
 		} else {       /* Compare zero extension */
 			emit(ctx, or, tmp, tmp, hi(dst));
diff --git a/arch/mips/net/bpf_jit_comp64.c b/arch/mips/net/bpf_jit_comp64.c
index fa7e9aa37f49..6681ccac9dd9 100644
--- a/arch/mips/net/bpf_jit_comp64.c
+++ b/arch/mips/net/bpf_jit_comp64.c
@@ -305,8 +305,7 @@ static void emit_bswap_r64(struct jit_context *ctx, u8 dst, u32 width)
 	case 16:
 		emit_sext(ctx, dst, dst);
 		emit_bswap_r(ctx, dst, width);
-		if (cpu_has_mips64r2 || cpu_has_mips64r6)
-			emit_zext(ctx, dst);
+		emit_zext(ctx, dst);
 		break;
 	}
 	clobber_reg(ctx, dst);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e57af902560c..1d2676782d70 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1651,8 +1651,9 @@ static inline void bpf_trampoline_set_flags(struct bpf_trampoline *tr, u32 flags
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
-	bool called : 1;
-	bool verified : 1;
+	/* Indexed by in_sleepable. */
+	bool called[2];
+	bool verified[2];
 };
 
 enum bpf_jit_poke_reason {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 36b65797877d..b83ec99f1a13 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -45,18 +45,20 @@ struct bpf_reg_state {
 	union {
 		/* valid when type == PTR_TO_PACKET */
 		int range;
-
-		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
-		 *   PTR_TO_MAP_VALUE_OR_NULL
+		/*
+		 * Valid when type == PTR_TO_STACK. Inside the callee two registers
+		 * can be both PTR_TO_STACK like R1=fp-8 and R2=fp-8, but one of them
+		 * points to this function stack while another to the caller's stack.
+		 * To differentiate them 'frameno' is used which is an index in
+		 * bpf_verifier_state->frame[] array pointing to bpf_func_state.
 		 */
-		struct {
-			struct bpf_map *map_ptr;
-			/* To distinguish map lookups from outer map
-			 * the map_uid is non-zero for registers
-			 * pointing to inner maps.
-			 */
-			u32 map_uid;
-		};
+		u8 frameno;
+
+		/*
+		 * For CONST_PTR_TO_MAP, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE and
+		 * PTR_TO_INSN.
+		 */
+		struct bpf_map *map_ptr;
 
 		/* for PTR_TO_BTF_ID */
 		struct {
@@ -155,13 +157,12 @@ struct bpf_reg_state {
 	 * gets parent_id set to the dynptr's id.
 	 */
 	u32 parent_id;
-	/* Inside the callee two registers can be both PTR_TO_STACK like
-	 * R1=fp-8 and R2=fp-8, but one of them points to this function stack
-	 * while another to the caller's stack. To differentiate them 'frameno'
-	 * is used which is an index in bpf_verifier_state->frame[] array
-	 * pointing to bpf_func_state.
+	/*
+	 * Distinguishes inner-map lookups and their keys and values. Zero for
+	 * other registers. Kept outside the metadata union for ID remapping
+	 * during state comparisons.
 	 */
-	u32 frameno;
+	u32 map_uid;
 	/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
 	bool precise;
 };
@@ -679,6 +680,7 @@ struct bpf_insn_aux_data {
 	bool nospec_result; /* result is unsafe under speculation, nospec must follow */
 	bool zext_dst; /* this insn zero extends dst reg */
 	bool needs_zext; /* alu op needs to clear upper bits */
+	bool prevent_zext; /* alu op cannot be zext (already used with 64-bit scalars) */
 	bool non_sleepable; /* helper/kfunc may be called from non-sleepable context */
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
 	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
@@ -1197,6 +1199,8 @@ static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id)
 
 int bpf_prepare_btf_info(struct bpf_verifier_env *env,
 			 const union bpf_attr *attr, bpfptr_t uattr);
+int bpf_check_core_relo(struct bpf_verifier_env *env,
+			const union bpf_attr *attr, bpfptr_t uattr);
 int bpf_check_btf_info(struct bpf_verifier_env *env,
 		       const union bpf_attr *attr, bpfptr_t uattr);
 
@@ -1236,11 +1240,18 @@ static inline int bpf_get_spi(s32 off)
 	return (-off - 1) / BPF_REG_SIZE;
 }
 
+/*
+ * Return the function state a stack pointer register refers to. frameno
+ * shares storage with other pointer metadata, so return NULL for any
+ * other register type instead of indexing frame[] with aliased bytes.
+ */
 static inline struct bpf_func_state *bpf_func(struct bpf_verifier_env *env,
 					      const struct bpf_reg_state *reg)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
 
+	if (reg->type != PTR_TO_STACK)
+		return NULL;
 	return cur->frame[reg->frameno];
 }
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 89d5a5c4f117..7c62ea17b116 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -80,6 +80,7 @@
 #define KF_ARENA_ARG2   (1 << 15) /* kfunc takes an arena pointer as its second argument */
 #define KF_IMPLICIT_ARGS (1 << 16) /* kfunc has implicit arguments supplied by the verifier */
 #define KF_SPINLOCK_SAFE (1 << 17) /* kfunc is allowed inside bpf_spin_lock-ed region */
+#define KF_PERFMON      (1 << 18) /* kfunc requires CAP_PERFMON */
 
 /*
  * Tag marking a kernel function as a kfunc. This is meant to minimize the
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 421f6fc45451..c8e21903074c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4372,7 +4372,10 @@ skb_header_pointer_careful(const struct sk_buff *skb, int offset,
 static inline void * __must_check
 skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len)
 {
-	if (likely(skb_headlen(skb) - offset >= len))
+	unsigned int uoffset = (unsigned int)offset;
+
+	if (likely(uoffset <= skb_headlen(skb) &&
+		   (unsigned int)len <= skb_headlen(skb) - uoffset))
 		return skb->data + offset;
 	return NULL;
 }
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9f33e95d5741..d870bc5e50bc 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4268,13 +4268,10 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 {
 	int i;
 
-	/* There are three types that signify ownership of some other type:
-	 *  kptr_ref, bpf_list_head, bpf_rb_root.
-	 * kptr_ref only supports storing kernel types, which can't store
-	 * references to program allocated local types.
-	 *
-	 * Hence we only need to ensure that bpf_{list_head,rb_root} ownership
-	 * does not form cycles.
+	/*
+	 * Check fields which require the complete BTF and initialize runtime
+	 * metadata. Ownership relationships are validated after every record has
+	 * been fixed up.
 	 */
 	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR)))
 		return 0;
@@ -4305,53 +4302,90 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 		if (!meta)
 			return -EFAULT;
 		rec->fields[i].graph_root.value_rec = meta->record;
-
-		/* We need to set value_rec for all root types, but no need
-		 * to check ownership cycle for a type unless it's also a
-		 * node type.
-		 */
-		if (!(rec->field_mask & BPF_GRAPH_NODE))
-			continue;
-
-		/* We need to ensure ownership acyclicity among all types. The
-		 * proper way to do it would be to topologically sort all BTF
-		 * IDs based on the ownership edges, since there can be multiple
-		 * bpf_{list_head,rb_node} in a type. Instead, we use the
-		 * following resaoning:
-		 *
-		 * - A type can only be owned by another type in user BTF if it
-		 *   has a bpf_{list,rb}_node. Let's call these node types.
-		 * - A type can only _own_ another type in user BTF if it has a
-		 *   bpf_{list_head,rb_root}. Let's call these root types.
-		 *
-		 * We ensure that if a type is both a root and node, its
-		 * element types cannot be root types.
-		 *
-		 * To ensure acyclicity:
-		 *
-		 * When A is an root type but not a node, its ownership
-		 * chain can be:
-		 *	A -> B -> C
-		 * Where:
-		 * - A is an root, e.g. has bpf_rb_root.
-		 * - B is both a root and node, e.g. has bpf_rb_node and
-		 *   bpf_list_head.
-		 * - C is only an root, e.g. has bpf_list_node
-		 *
-		 * When A is both a root and node, some other type already
-		 * owns it in the BTF domain, hence it can not own
-		 * another root type through any of the ownership edges.
-		 *	A -> B
-		 * Where:
-		 * - A is both an root and node.
-		 * - B is only an node.
-		 */
-		if (meta->record->field_mask & BPF_GRAPH_ROOT)
-			return -ELOOP;
 	}
 	return 0;
 }
 
+static int btf_owned_type_idx(const struct btf *btf, struct btf_struct_metas *tab,
+			      const struct btf_field *field)
+{
+	struct btf_struct_meta *meta;
+	u32 btf_id;
+
+	if (field->type & BPF_GRAPH_ROOT) {
+		btf_id = field->graph_root.value_btf_id;
+	} else if (field->type == BPF_KPTR_REF || field->type == BPF_KPTR_PERCPU) {
+		if (btf_is_kernel(field->kptr.btf))
+			return -ENOENT;
+		btf_id = field->kptr.btf_id;
+	} else {
+		return -ENOENT;
+	}
+
+	meta = btf_find_struct_meta(btf, btf_id);
+	if (!meta)
+		return field->type & BPF_GRAPH_ROOT ? -EFAULT : -ENOENT;
+	return meta - tab->types;
+}
+
+/*
+ * Each ownership edge adds kernel frames through bpf_obj_free_fields() and
+ * __bpf_obj_drop_impl(). Keep the bound deliberately small because object
+ * destruction can itself run below a BPF call chain. A final pointee without
+ * special fields is not present in the struct metadata table and adds only a
+ * non-recursing drop.
+ */
+#define BTF_MAX_OWNERSHIP_DEPTH 8
+
+static int btf_ownership_depth(const struct btf *btf,
+			       struct btf_struct_metas *tab, u8 *depth,
+			       int idx, int depth_left)
+{
+	const struct btf_record *rec = tab->types[idx].record;
+	int i, ret, max_depth = 0;
+
+	if (!depth_left)
+		return -ELOOP;
+	if (depth[idx])
+		goto done;
+
+	for (i = 0; i < rec->cnt; i++) {
+		ret = btf_owned_type_idx(btf, tab, &rec->fields[i]);
+		if (ret == -ENOENT)
+			continue;
+		if (ret < 0)
+			return ret;
+		ret = btf_ownership_depth(btf, tab, depth, ret, depth_left - 1);
+		if (ret < 0)
+			return ret;
+		max_depth = max(max_depth, ret);
+	}
+	depth[idx] = max_depth + 1;
+done:
+	return depth[idx] > depth_left ? -ELOOP : depth[idx];
+}
+
+static int btf_check_ownership_depth(const struct btf *btf,
+				     struct btf_struct_metas *tab)
+{
+	u8 *depth;
+	int i, ret = 0;
+
+	depth = kvcalloc(tab->cnt, sizeof(*depth), GFP_KERNEL | __GFP_NOWARN);
+	if (!depth)
+		return -ENOMEM;
+
+	for (i = 0; i < tab->cnt; i++) {
+		ret = btf_ownership_depth(btf, tab, depth, i,
+					  BTF_MAX_OWNERSHIP_DEPTH);
+		if (ret < 0)
+			break;
+		ret = 0;
+	}
+	kvfree(depth);
+	return ret;
+}
+
 static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
 			      u32 type_id, void *data, u8 bits_offset,
 			      struct btf_show *show)
@@ -6044,6 +6078,10 @@ static struct btf *btf_parse(const union bpf_attr *attr, bpfptr_t uattr,
 			if (err < 0)
 				goto errout_meta;
 		}
+
+		err = btf_check_ownership_depth(btf, struct_meta_tab);
+		if (err < 0)
+			goto errout_meta;
 	}
 
 	err = bpf_log_attr_finalize(attr_log, &env->log);
@@ -7187,7 +7225,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 		if (btf_type_is_int(t))
 			return WALK_SCALAR;
 
-		if (!btf_type_is_struct(t))
+		if (!btf_type_is_struct(t) || !t->size)
 			goto error;
 
 		off = (off - moff) % t->size;
diff --git a/kernel/bpf/check_btf.c b/kernel/bpf/check_btf.c
index 0e8b3ccc7a5b..4c1ed842f661 100644
--- a/kernel/bpf/check_btf.c
+++ b/kernel/bpf/check_btf.c
@@ -338,9 +338,9 @@ static int check_btf_line(struct bpf_verifier_env *env,
 #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)
+int bpf_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 = {};
@@ -414,7 +414,7 @@ int bpf_prepare_btf_info(struct bpf_verifier_env *env,
 	struct btf *btf;
 	int err;
 
-	if (!attr->func_info_cnt && !attr->line_info_cnt) {
+	if (!attr->func_info_cnt && !attr->line_info_cnt && !attr->core_relo_cnt) {
 		if (check_abnormal_return(env))
 			return -EINVAL;
 		return 0;
@@ -455,9 +455,5 @@ int bpf_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;
 }
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8b294dfc1ad4..2e3bf8113ae9 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -19,6 +19,7 @@
 
 #include <uapi/linux/btf.h>
 #include <linux/filter.h>
+#include <linux/sched/signal.h>
 #include <linux/skbuff.h>
 #include <linux/static_call.h>
 #include <linux/vmalloc.h>
@@ -1619,6 +1620,8 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bp
 			 * fix it up here on error.
 			 */
 			bpf_jit_prog_release_other(prog, clone);
+			if (env && fatal_signal_pending(current))
+				return ERR_PTR(-EINTR);
 			return IS_ERR(tmp) ? tmp : ERR_PTR(-ENOMEM);
 		}
 
@@ -2636,11 +2639,14 @@ static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struc
 	orig_prog = prog;
 	prog = bpf_jit_blind_constants(env, prog);
 	/*
-	 * If blinding was requested and we failed during blinding, we must fall
-	 * back to the interpreter.
+	 * Fall back to the interpreter after blinding failures, except when
+	 * the loader was killed.
 	 */
-	if (IS_ERR(prog))
+	if (IS_ERR(prog)) {
+		if (PTR_ERR(prog) == -EINTR)
+			return prog;
 		goto out_restore;
+	}
 
 	prog = bpf_int_jit_compile(env, prog);
 	if (prog->jited) {
@@ -2659,6 +2665,8 @@ static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struc
 struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp,
 					   int *err)
 {
+	struct bpf_prog *jit_prog;
+
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
@@ -2681,7 +2689,12 @@ struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct
 		if (*err)
 			return fp;
 
-		fp = bpf_prog_jit_compile(env, fp);
+		jit_prog = bpf_prog_jit_compile(env, fp);
+		if (IS_ERR(jit_prog)) {
+			*err = PTR_ERR(jit_prog);
+			return fp;
+		}
+		fp = jit_prog;
 		bpf_prog_jit_attempt_done(fp);
 		if (!fp->jited && jit_needed) {
 			*err = -ENOTSUPP;
diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 51f89cecefb4..3f3fe2450fc6 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -149,8 +149,9 @@ bpf_crypto_ctx_create(const struct bpf_crypto_params *params, u32 params__sz,
 	const struct bpf_crypto_type *type;
 	struct bpf_crypto_ctx *ctx;
 
-	if (!params || params->reserved[0] || params->reserved[1] ||
-	    params__sz != sizeof(struct bpf_crypto_params)) {
+	if (!params ||
+	    params__sz != sizeof(struct bpf_crypto_params) ||
+	    params->reserved[0] || params->reserved[1]) {
 		*err = -EINVAL;
 		return NULL;
 	}
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 52d3cec33672..d6f83521fc78 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -8,6 +8,7 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 #include <linux/perf_event.h>
+#include <linux/sched/signal.h>
 #include <net/xdp.h>
 #include "disasm.h"
 
@@ -306,12 +307,28 @@ static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len)
 	}
 }
 
+/*
+ * Some post-verification instruction rewriting passes require an
+ * O(prog->len) operation per instruction. Keep their shared primitives
+ * killable and preemptible.
+ */
+static bool bpf_rewrite_must_abort(void)
+{
+	if (fatal_signal_pending(current))
+		return true;
+	cond_resched();
+	return false;
+}
+
 struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
 				     const struct bpf_insn *patch, u32 len)
 {
 	struct bpf_prog *new_prog;
 	struct bpf_insn_aux_data *new_data = NULL;
 
+	if (bpf_rewrite_must_abort())
+		return NULL;
+
 	if (len > 1) {
 		new_data = vrealloc(env->insn_aux_data,
 				    array_size(env->prog->len + len - 1,
@@ -523,6 +540,9 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
 	unsigned int orig_prog_len = env->prog->len;
 	int err;
 
+	if (bpf_rewrite_must_abort())
+		return -EINTR;
+
 	if (bpf_prog_is_offloaded(env->prog->aux))
 		bpf_prog_offload_remove_insns(env, off, cnt);
 
@@ -1356,7 +1376,7 @@ int bpf_jit_subprogs(struct bpf_verifier_env *env)
 		}
 		prog = bpf_jit_blind_constants(env, prog);
 		if (IS_ERR(prog)) {
-			err = -ENOMEM;
+			err = PTR_ERR(prog);
 			prog = orig_prog;
 			goto out_restore;
 		}
@@ -1433,7 +1453,7 @@ int bpf_fixup_call_args(struct bpf_verifier_env *env)
 		err = bpf_jit_subprogs(env);
 		if (err == 0)
 			return 0;
-		if (err == -EFAULT)
+		if (err == -EFAULT || err == -EINTR)
 			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 6f331c80130d..f9464e566f10 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1054,14 +1054,17 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 	/* When not setting the initial value on all cpus, zero-fill element
 	 * values for other cpus. Otherwise, bpf program has no way to ensure
 	 * known initial values for cpus other than current one
-	 * (onallcpus=false always when coming from bpf prog).
+	 * (onallcpus=false always when coming from bpf prog,
+	 *  map_flags & BPF_F_CPU when coming from syscall but setting
+	 *  only one cpu).
 	 */
-	if (!onallcpus) {
-		int current_cpu = raw_smp_processor_id();
+	if (!onallcpus || (map_flags & BPF_F_CPU)) {
+		int init_cpu = (map_flags & BPF_F_CPU) ? map_flags >> 32 :
+			       raw_smp_processor_id();
 		int cpu;
 
 		for_each_possible_cpu(cpu) {
-			if (cpu == current_cpu)
+			if (cpu == init_cpu)
 				copy_map_value(&htab->map, per_cpu_ptr(pptr, cpu), value);
 			else /* Since elem is preallocated, we cannot touch special fields */
 				zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu));
@@ -1772,6 +1775,12 @@ static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
 						 flags);
 }
 
+/*
+ * Max consecutive empty buckets to walk in one RCU +
+ * instrumentation-disabled section before rescheduling.
+ */
+#define HTAB_BATCH_EMPTY_RESCHED 64
+
 static int
 __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 				   const union bpf_attr *attr,
@@ -1793,6 +1802,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	unsigned long flags = 0;
 	bool locked = false;
 	struct htab_elem *l;
+	u32 empty_cnt = 0;
 	struct bucket *b;
 	int ret = 0;
 
@@ -1971,30 +1981,41 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	}
 
 next_batch:
-	/* If we are not copying data, we can go to next bucket and avoid
-	 * unlocking the rcu.
+	/*
+	 * If we are not copying data, we can go to next bucket and avoid
+	 * unlocking the rcu. Bound the walk though: after
+	 * HTAB_BATCH_EMPTY_RESCHED consecutive empty buckets, fully exit
+	 * the critical section (no locks are held here) and reschedule.
 	 */
 	if (!bucket_cnt && (batch + 1 < htab->n_buckets)) {
 		batch++;
-		goto again_nocopy;
+		if (++empty_cnt < HTAB_BATCH_EMPTY_RESCHED)
+			goto again_nocopy;
+		empty_cnt = 0;
+		rcu_read_unlock();
+		bpf_enable_instrumentation();
+		cond_resched_tasks_rcu_qs();
+		goto again;
 	}
 
 	rcu_read_unlock();
 	bpf_enable_instrumentation();
-	if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys,
-	    key_size * bucket_cnt) ||
-	    copy_to_user(uvalues + total * value_size, values,
-	    value_size * bucket_cnt))) {
+	if (bucket_cnt && (copy_to_user(ukeys + (size_t)total * key_size, keys,
+	    (size_t)key_size * bucket_cnt) ||
+	    copy_to_user(uvalues + (size_t)total * value_size, values,
+	    (size_t)value_size * bucket_cnt))) {
 		ret = -EFAULT;
 		goto after_loop;
 	}
 
 	total += bucket_cnt;
+	empty_cnt = 0;
 	batch++;
 	if (batch >= htab->n_buckets) {
 		ret = -ENOENT;
 		goto after_loop;
 	}
+	cond_resched_tasks_rcu_qs();
 	goto again;
 
 after_loop:
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b3cc5c8fc875..712dca5a2c5b 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -4883,7 +4883,7 @@ BTF_ID(func, bpf_cgroup_release_dtor)
 
 BTF_KFUNCS_START(common_btf_ids)
 BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx, KF_FASTCALL)
-BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL)
+BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL | KF_PERFMON)
 BTF_ID_FLAGS(func, bpf_rcu_read_lock)
 BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
 BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL)
@@ -4920,26 +4920,26 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, bpf_wq_start)
 BTF_ID_FLAGS(func, bpf_preempt_disable)
 BTF_ID_FLAGS(func, bpf_preempt_enable)
-BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW | KF_PERFMON)
 BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_get_kmem_cache)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_get_kmem_cache, KF_PERFMON)
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_local_irq_save)
 BTF_ID_FLAGS(func, bpf_local_irq_restore)
 #ifdef CONFIG_BPF_EVENTS
-BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr)
-BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr)
-BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr)
-BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr)
-BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr, KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr, KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr, KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr, KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_PERFMON)
 #endif
 #ifdef CONFIG_DMA_SHARED_BUFFER
 BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE)
@@ -4947,26 +4947,26 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPAB
 BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
 #endif
 BTF_ID_FLAGS(func, __bpf_trap)
-BTF_ID_FLAGS(func, bpf_strcmp);
-BTF_ID_FLAGS(func, bpf_strcasecmp);
-BTF_ID_FLAGS(func, bpf_strncasecmp);
-BTF_ID_FLAGS(func, bpf_strchr);
-BTF_ID_FLAGS(func, bpf_strchrnul);
-BTF_ID_FLAGS(func, bpf_strnchr);
-BTF_ID_FLAGS(func, bpf_strrchr);
-BTF_ID_FLAGS(func, bpf_strlen);
-BTF_ID_FLAGS(func, bpf_strnlen);
-BTF_ID_FLAGS(func, bpf_strspn);
-BTF_ID_FLAGS(func, bpf_strcspn);
-BTF_ID_FLAGS(func, bpf_strstr);
-BTF_ID_FLAGS(func, bpf_strcasestr);
-BTF_ID_FLAGS(func, bpf_strnstr);
-BTF_ID_FLAGS(func, bpf_strncasestr);
+BTF_ID_FLAGS(func, bpf_strcmp, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strcasecmp, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strncasecmp, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strchr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strchrnul, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strnchr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strrchr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strlen, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strnlen, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strspn, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strcspn, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strstr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strcasestr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strnstr, KF_PERFMON);
+BTF_ID_FLAGS(func, bpf_strncasestr, KF_PERFMON);
 #if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS)
 BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)
 #endif
-BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE)
-BTF_ID_FLAGS(func, bpf_stream_print_stack, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE)
+BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE | KF_PERFMON)
+BTF_ID_FLAGS(func, bpf_stream_print_stack, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE | KF_PERFMON)
 BTF_ID_FLAGS(func, bpf_task_work_schedule_signal, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, bpf_task_work_schedule_resume, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, bpf_dynptr_from_file)
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index e9662db7198f..8a8f088e83e6 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -119,6 +119,7 @@ struct bpf_mem_cache {
 	struct llist_head waiting_for_gp_ttrace;
 	struct rcu_head rcu_ttrace;
 	atomic_t call_rcu_ttrace_in_progress;
+	raw_spinlock_t lock;
 };
 
 struct bpf_mem_caches {
@@ -214,25 +215,24 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
 	gfp = __GFP_NOWARN | __GFP_ACCOUNT;
 	gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
 
-	for (i = 0; i < cnt; i++) {
-		/*
-		 * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
-		 * done only by one CPU == current CPU. Other CPUs might
-		 * llist_add() and llist_del_all() in parallel.
-		 */
-		obj = llist_del_first(&c->free_by_rcu_ttrace);
-		if (!obj)
-			break;
-		add_obj_to_free_list(c, obj);
-	}
-	if (i >= cnt)
-		return;
+	/*
+	 * c->lock serializes concurrent llist_del_first() against
+	 * llist_del_all() in __free_rcu() and do_call_rcu_ttrace().
+	 */
+	scoped_guard(raw_spinlock_irqsave, &c->lock) {
+		for (i = 0; i < cnt; i++) {
+			obj = llist_del_first(&c->free_by_rcu_ttrace);
+			if (!obj)
+				break;
+			add_obj_to_free_list(c, obj);
+		}
 
-	for (; i < cnt; i++) {
-		obj = llist_del_first(&c->waiting_for_gp_ttrace);
-		if (!obj)
-			break;
-		add_obj_to_free_list(c, obj);
+		for (; i < cnt; i++) {
+			obj = llist_del_first(&c->waiting_for_gp_ttrace);
+			if (!obj)
+				break;
+			add_obj_to_free_list(c, obj);
+		}
 	}
 	if (i >= cnt)
 		return;
@@ -279,8 +279,12 @@ static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool per
 static void __free_rcu(struct rcu_head *head)
 {
 	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
+	struct llist_node *llnode;
 
-	free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+	scoped_guard(raw_spinlock_irqsave, &c->lock)
+		llnode = llist_del_all(&c->waiting_for_gp_ttrace);
+
+	free_all(c, llnode, !!c->percpu_size);
 	atomic_set(&c->call_rcu_ttrace_in_progress, 0);
 }
 
@@ -300,7 +304,8 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 
 	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
 		if (unlikely(READ_ONCE(c->draining))) {
-			llnode = llist_del_all(&c->free_by_rcu_ttrace);
+			scoped_guard(raw_spinlock_irqsave, &c->lock)
+				llnode = llist_del_all(&c->free_by_rcu_ttrace);
 			free_all(c, llnode, !!c->percpu_size);
 		}
 		return;
@@ -535,6 +540,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
+			raw_spin_lock_init(&c->lock);
 			init_refill_work(c);
 			prefill_mem_cache(c, cpu);
 		}
@@ -557,7 +563,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
-
+			raw_spin_lock_init(&c->lock);
 			init_refill_work(c);
 			prefill_mem_cache(c, cpu);
 		}
@@ -609,7 +615,7 @@ int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
 		c->objcg = objcg;
 		c->percpu_size = percpu_size;
 		c->tgt = c;
-
+		raw_spin_lock_init(&c->lock);
 		init_refill_work(c);
 		prefill_mem_cache(c, cpu);
 	}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 0d6f5569588c..d855399812ee 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -698,6 +698,8 @@ static bool __bpf_offload_dev_match(struct bpf_prog *prog,
 		return false;
 	if (offload->netdev == netdev)
 		return true;
+	if (!bpf_prog_is_offloaded(prog->aux))
+		return false;
 
 	ondev1 = bpf_offload_find_netdev(offload->netdev);
 	ondev2 = bpf_offload_find_netdev(netdev);
diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c
index 66fb11b6c6a7..012b82513a3b 100644
--- a/kernel/bpf/states.c
+++ b/kernel/bpf/states.c
@@ -491,7 +491,8 @@ static bool regs_exact(const struct bpf_reg_state *rold,
 {
 	return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
 	       check_ids(rold->id, rcur->id, idmap) &&
-	       check_ids(rold->parent_id, rcur->parent_id, idmap);
+	       check_ids(rold->parent_id, rcur->parent_id, idmap) &&
+	       check_ids(rold->map_uid, rcur->map_uid, idmap);
 }
 
 enum exact_level {
@@ -616,7 +617,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		       range_within(rold, rcur) &&
 		       tnum_in(rold->var_off, rcur->var_off) &&
 		       check_ids(rold->id, rcur->id, idmap) &&
-		       check_ids(rold->parent_id, rcur->parent_id, idmap);
+		       check_ids(rold->parent_id, rcur->parent_id, idmap) &&
+		       check_ids(rold->map_uid, rcur->map_uid, idmap);
 	case PTR_TO_PACKET_META:
 	case PTR_TO_PACKET:
 		/* We must have at least as much range as the old ptr
@@ -635,14 +637,14 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		/* id relations must be preserved */
 		if (!check_ids(rold->id, rcur->id, idmap))
 			return false;
+		/* Preserve displacements between pointers sharing an ID. */
+		if (rold->id && rold->r64.base != rcur->r64.base)
+			return false;
 		/* new val must satisfy old val knowledge */
 		return range_within(rold, rcur) &&
 		       tnum_in(rold->var_off, rcur->var_off);
 	case PTR_TO_STACK:
-		/* two stack pointers are equal only if they're pointing to
-		 * the same stack frame, since fp-8 in foo != fp-8 in bar
-		 */
-		return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno;
+		return regs_exact(rold, rcur, idmap);
 	case PTR_TO_ARENA:
 		return true;
 	case PTR_TO_INSN:
@@ -1121,7 +1123,7 @@ static bool states_maybe_looping(struct bpf_verifier_state *old,
 	fcur = cur->frame[fr];
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (memcmp(&fold->regs[i], &fcur->regs[i],
-			   offsetof(struct bpf_reg_state, frameno)))
+			   offsetof(struct bpf_reg_state, precise)))
 			return false;
 	return true;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c7bc9ba9b331..244a939b9d2d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2036,7 +2036,7 @@ int generic_map_delete_batch(struct bpf_map *map,
 
 	for (cp = 0; cp < max_count; cp++) {
 		err = -EFAULT;
-		if (copy_from_user(key, keys + cp * map->key_size,
+		if (copy_from_user(key, keys + (size_t)cp * map->key_size,
 				   map->key_size))
 			break;
 
@@ -2098,9 +2098,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 
 	for (cp = 0; cp < max_count; cp++) {
 		err = -EFAULT;
-		if (copy_from_user(key, keys + cp * map->key_size,
+		if (copy_from_user(key, keys + (size_t)cp * map->key_size,
 		    map->key_size) ||
-		    copy_from_user(value, values + cp * value_size, value_size))
+		    copy_from_user(value, values + (size_t)cp * value_size, value_size))
 			break;
 
 		err = bpf_map_update_value(map, map_file, key, value,
@@ -2179,12 +2179,12 @@ int generic_map_lookup_batch(struct bpf_map *map,
 		if (err)
 			goto free_buf;
 
-		if (copy_to_user(keys + cp * map->key_size, key,
+		if (copy_to_user(keys + (size_t)cp * map->key_size, key,
 				 map->key_size)) {
 			err = -EFAULT;
 			goto free_buf;
 		}
-		if (copy_to_user(values + cp * value_size, value, value_size)) {
+		if (copy_to_user(values + (size_t)cp * value_size, value, value_size)) {
 			err = -EFAULT;
 			goto free_buf;
 		}
@@ -6042,7 +6042,10 @@ struct bpf_link *bpf_link_get_curr_or_next(u32 *id)
 again:
 	link = idr_get_next(&link_idr, id);
 	if (link) {
-		link = bpf_link_inc_not_zero(link);
+		if (link->id)
+			link = bpf_link_inc_not_zero(link);
+		else
+			link = ERR_PTR(-EAGAIN);
 		if (IS_ERR(link)) {
 			(*id)++;
 			goto again;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 72a3f5998dd2..41b49c56e123 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -567,7 +567,7 @@ static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_s
 	}
 
 	off = reg->var_off.value;
-	if (off % BPF_REG_SIZE) {
+	if (off >= 0 || off % BPF_REG_SIZE) {
 		verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off);
 		return -EINVAL;
 	}
@@ -1864,6 +1864,7 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
 	       offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
 	reg->id = 0;
 	reg->parent_id = 0;
+	reg->map_uid = 0;
 	___mark_reg_known(reg, imm);
 }
 
@@ -1925,17 +1926,18 @@ static void refine_map_lookup_value(struct bpf_reg_state *reg)
 	if (map->inner_map_meta) {
 		reg->type = CONST_PTR_TO_MAP | maybe_null;
 		reg->map_ptr = map->inner_map_meta;
-		/* transfer reg's id which is unique for every map_lookup_elem
+		/*
+		 * transfer reg's id which is unique for every map_lookup_elem
 		 * as UID of the inner map.
 		 */
-		if (btf_record_has_field(map->inner_map_meta->record,
-					 BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK))
-			reg->map_uid = reg->id;
+		reg->map_uid = reg->id;
 	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 		reg->type = PTR_TO_XDP_SOCK | maybe_null;
+		reg->map_uid = 0;
 	} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
 		   map->map_type == BPF_MAP_TYPE_SOCKHASH) {
 		reg->type = PTR_TO_SOCKET | maybe_null;
+		reg->map_uid = 0;
 	}
 }
 
@@ -3042,6 +3044,8 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			subprog[cur_subprog].exit_idx = i;
 			goto next;
 		}
+		if (insn_is_gotox(&insn[i]))
+			goto next;
 		off = i + bpf_jmp_offset(&insn[i]) + 1;
 		if (off < subprog_start || off >= subprog_end) {
 			verbose(env, "jump out of range from insn %d to %d\n", i, off);
@@ -3061,7 +3065,8 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			 */
 			if (code != (BPF_JMP | BPF_EXIT) &&
 			    code != (BPF_JMP32 | BPF_JA) &&
-			    code != (BPF_JMP | BPF_JA)) {
+			    code != (BPF_JMP | BPF_JA) &&
+			    !insn_is_gotox(&insn[i])) {
 				verbose(env, "last insn is not an exit or jmp\n");
 				bpf_diag_program_structure(
 					env, i, "subprogram can fall through",
@@ -3582,7 +3587,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		save_register_state(env, state, spi, reg, size);
 		/* Break the relation on a narrowing spill. */
 		if (!reg_value_fits)
-			state->stack[spi].spilled_ptr.id = 0;
+			clear_scalar_id(&state->stack[spi].spilled_ptr);
 	} else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) &&
 		   env->bpf_capable) {
 		struct bpf_reg_state *tmp_reg = &env->fake_reg[0];
@@ -6453,6 +6458,15 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, struct b
 			return -EACCES;
 		}
 
+		if (rdonly_untrusted && !env->allow_ptr_leaks) {
+			verbose(env, "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+				reg_type_str(env, reg->type));
+			bpf_diag_policy(env, insn_idx, "read from untrusted read-only memory",
+					"the access requires CAP_PERFMON",
+					"Load the program with CAP_PERFMON, or avoid dereferencing untrusted pointers.");
+			return -EPERM;
+		}
+
 		/*
 		 * Accesses to untrusted PTR_TO_MEM are done through probe
 		 * instructions, hence no need to check bounds in that case.
@@ -9736,6 +9750,16 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 			if (check_mem_reg(env, reg, argno, arg->mem_size, BPF_READ | BPF_WRITE, NULL,
 					  NULL))
 				return -EINVAL;
+			/*
+			 * PTR_TO_PACKET get passed as PTR_TO_MEM, preventing
+			 * us from adjusting bounds tracking info.
+			 */
+			if ((reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) &&
+			    sub->changes_pkt_data) {
+				bpf_log(log, "%s is a packet pointer, but func#%d may change packet data\n",
+						reg_arg_name(env, argno), subprog);
+				return -EINVAL;
+			}
 			if (!(arg->arg_type & PTR_MAYBE_NULL) &&
 			    (type_may_be_null(reg->type) || bpf_register_is_null(reg))) {
 				bpf_log(log, "%s is expected to be non-NULL\n",
@@ -9919,6 +9943,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	if (err == -EFAULT)
 		return err;
 	if (bpf_subprog_is_global(env, subprog)) {
+		struct bpf_func_info_aux *sub_aux = subprog_aux(env, subprog);
 		const char *sub_name = bpf_subprog_name(env, subprog);
 		const char *operation;
 		bool returns_void;
@@ -9950,11 +9975,10 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		if (env->log.level & BPF_LOG_LEVEL)
 			verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
 				subprog, sub_name);
+		sub_aux->called[in_sleepable_context(env)] = true;
 		returns_void = subprog_returns_void(env, subprog);
 		if (env->subprog_info[subprog].changes_pkt_data)
 			clear_all_pkt_pointers(env);
-		/* mark global subprog for verifying after main prog */
-		subprog_aux(env, subprog)->called = true;
 		if (returns_void)
 			bpf_diag_record_scrub(env, &caller->regs[BPF_REG_0], BPF_DIAG_MOD_CALLER_SAVED);
 		else
@@ -10036,6 +10060,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
 	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
 	callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr;
 	callee->regs[BPF_REG_3].map_uid = caller->regs[BPF_REG_1].map_uid;
+	callee->regs[BPF_REG_3].id = ++env->id_gen;
 
 	/* pointer to stack or null */
 	callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3];
@@ -10132,6 +10157,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
 	callee->regs[BPF_REG_3].map_ptr = map_ptr;
 	callee->regs[BPF_REG_3].map_uid = map_uid;
+	callee->regs[BPF_REG_3].id = ++env->id_gen;
 
 	/* unused */
 	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
@@ -10250,6 +10276,7 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
 	callee->regs[BPF_REG_3].map_ptr = map_ptr;
 	callee->regs[BPF_REG_3].map_uid = map_uid;
+	callee->regs[BPF_REG_3].id = ++env->id_gen;
 
 	/* unused */
 	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
@@ -10772,11 +10799,7 @@ int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id,
 /* Check if we're in a sleepable context. */
 static inline bool in_sleepable_context(struct bpf_verifier_env *env)
 {
-	return !env->cur_state->active_rcu_locks &&
-	       !env->cur_state->active_preempt_locks &&
-	       !env->cur_state->active_locks &&
-	       !env->cur_state->active_irq_id &&
-	       in_sleepable(env);
+	return !in_rcu_cs(env);
 }
 
 static const char *non_sleepable_context_description(struct bpf_verifier_env *env)
@@ -11356,6 +11379,11 @@ static bool is_kfunc_destructive(struct bpf_call_arg_meta *meta)
 	return meta->kfunc_flags & KF_DESTRUCTIVE;
 }
 
+static bool is_kfunc_perfmon(struct bpf_call_arg_meta *meta)
+{
+	return meta->kfunc_flags & KF_PERFMON;
+}
+
 static bool is_kfunc_rcu(struct bpf_call_arg_meta *meta)
 {
 	return meta->kfunc_flags & KF_RCU;
@@ -13834,6 +13862,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EACCES;
 	}
 
+	if (is_kfunc_perfmon(&meta) && !env->allow_ptr_leaks) {
+		verbose(env, "%s is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+			func_name);
+		operation = bpf_diag_fmt(env, "kfunc %s", func_name);
+		bpf_diag_policy(env, insn_idx, operation, "the kfunc requires CAP_PERFMON",
+				"Load the program with CAP_PERFMON, or avoid the kfunc.");
+		return -EPERM;
+	}
+
 	sleepable = bpf_is_kfunc_sleepable(&meta);
 	if (sleepable && !in_sleepable(env)) {
 		verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name);
@@ -15704,6 +15741,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
 	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
 	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+	struct bpf_insn_aux_data *aux = cur_aux(env);
 	u8 opcode = BPF_OP(insn->code);
 	int err;
 
@@ -15715,12 +15753,23 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	/* Case where at least one operand is an arena. */
 	if (dst_reg->type == PTR_TO_ARENA || (src_reg && src_reg->type == PTR_TO_ARENA)) {
-		struct bpf_insn_aux_data *aux = cur_aux(env);
 
 		if (dst_reg->type != PTR_TO_ARENA)
 			*dst_reg = *src_reg;
 
 		if (BPF_CLASS(insn->code) == BPF_ALU64) {
+			/*
+			 * Only arena pointers set needs_zext, but doing so
+			 * modifies the instruction at fixup time to an ALU32
+			 * and makes it unsuitable for 64-bit scalar args. We
+			 * prevent zext from being set if the instruction has
+			 * been previously called with non-arena registers.
+			 */
+			if (aux->prevent_zext) {
+				verbose(env, "same insn cannot be used with and without arena pointer\n");
+				return -EINVAL;
+			}
+
 			/*
 			 * 32-bit operations zero upper bits automatically.
 			 * 64-bit operations need to be converted to 32.
@@ -15733,6 +15782,16 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		return 0;
 	}
 
+	/* Prevent the instruction from being used with arena pointers (see above). */
+	if (env->prog->aux->arena && BPF_CLASS(insn->code) == BPF_ALU64) {
+		if (aux->needs_zext) {
+			verbose(env, "same insn cannot be used with and without arena pointer\n");
+			return -EINVAL;
+		}
+
+		aux->prevent_zext = true;
+	}
+
 	if (dst_reg->type != SCALAR_VALUE)
 		ptr_reg = dst_reg;
 
@@ -19421,13 +19480,14 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_sleepable)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_prog_aux *aux = env->prog->aux;
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
+	u32 old_insns_total = sub->insns_total;
 	u32 insn_processed = env->insn_processed;
 	int ret, i;
 
@@ -19440,7 +19500,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 	state->curframe = 0;
 	state->speculative = false;
 	state->branches = 1;
-	state->in_sleepable = env->prog->sleepable;
+	state->in_sleepable = is_sleepable;
 	state->frame[0] = kzalloc_obj(struct bpf_func_state, GFP_KERNEL_ACCOUNT);
 	if (!state->frame[0]) {
 		kfree(state);
@@ -19581,8 +19641,10 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 	 * not accounted as callees by account_current_path().
 	 * Accumulate their total counts as total counts of the main or
 	 * global subprog hosting the async call.
+	 * Start from the saved total of earlier contexts: adding to the current
+	 * total would count this pass's synchronous paths twice.
 	 */
-	env->subprog_info[subprog].insns_total = env->insn_processed - insn_processed;
+	sub->insns_total = old_insns_total + (env->insn_processed - insn_processed);
 	return ret;
 }
 
@@ -19610,14 +19672,19 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_aux *aux = env->prog->aux;
 	struct bpf_func_info_aux *sub_aux;
-	int i, ret, new_cnt;
+	int context, i, ret, new_cnt;
 
 	if (!aux->func_info)
 		return 0;
 
-	/* exception callback is presumed to be always called */
-	if (env->exception_callback_subprog)
-		subprog_aux(env, env->exception_callback_subprog)->called = true;
+	/*
+	 * Callbacks cannot throw, so the exception callback always runs in the
+	 * main program's context. It is presumed to be always called.
+	 */
+	if (env->exception_callback_subprog) {
+		sub_aux = subprog_aux(env, env->exception_callback_subprog);
+		sub_aux->called[env->prog->sleepable] = true;
+	}
 
 again:
 	new_cnt = 0;
@@ -19626,29 +19693,28 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 			continue;
 
 		sub_aux = subprog_aux(env, i);
-		if (!sub_aux->called || sub_aux->verified)
-			continue;
+		for (context = 0; context < ARRAY_SIZE(sub_aux->called); context++) {
+			if (!sub_aux->called[context] || sub_aux->verified[context])
+				continue;
 
-		env->insn_idx = env->subprog_info[i].start;
-		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i);
-		if (ret) {
-			return ret;
-		} else if (env->log.level & BPF_LOG_LEVEL) {
-			verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
-				i, bpf_subprog_name(env, i));
+			env->insn_idx = env->subprog_info[i].start;
+			WARN_ON_ONCE(env->insn_idx == 0);
+			ret = do_check_common(env, i, context);
+			if (ret)
+				return ret;
+			if (env->log.level & BPF_LOG_LEVEL)
+				verbose(env, "Func#%d ('%s') is safe for any args "
+					"that match its prototype\n",
+					i, bpf_subprog_name(env, i));
+
+			sub_aux->verified[context] = true;
+			new_cnt++;
 		}
-
-		/* We verified new global subprog, it might have called some
-		 * more global subprogs that we haven't verified yet, so we
-		 * need to do another pass over subprogs to verify those.
-		 */
-		sub_aux->verified = true;
-		new_cnt++;
 	}
 
-	/* We can't loop forever as we verify at least one global subprog on
-	 * each pass.
+	/*
+	 * We can't loop forever as each pass verifies at least one new context,
+	 * and there are only two contexts per global subprog.
 	 */
 	if (new_cnt)
 		goto again;
@@ -19661,7 +19727,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0);
+	ret = do_check_common(env, 0, env->prog->sleepable);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
@@ -21170,6 +21236,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
 	ret = bpf_diag_init(env);
 	if (ret)
 		goto err_prep;
+	if (env->prog->insnsi[env->prog->len - 1].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+		verbose(env, "invalid bpf_ld_imm64 insn\n");
+		ret = -EINVAL;
+		goto err_prep;
+	}
 	if (env->signature) {
 		ret = bpf_prog_calc_tag(env->prog);
 		if (ret < 0)
@@ -21245,6 +21316,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
 	if (ret < 0)
 		goto skip_full_check;
 
+	/* Apply CO-RE before validating the program's instruction layout. */
+	ret = bpf_check_core_relo(env, attr, uattr);
+	if (ret < 0)
+		goto skip_full_check;
+
 	/* Discover all subprograms before validating their layout and BTF. */
 	ret = add_subprogs(env);
 	if (ret < 0)
@@ -21254,7 +21330,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
 	if (ret < 0)
 		goto skip_full_check;
 
-	/* Validate BTF against the complete subprogram layout and apply CO-RE. */
+	/* Validate BTF against the complete subprogram layout. */
 	ret = bpf_check_btf_info(env, attr, uattr);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 5d51f6cb7d15..513354e928cb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -205,8 +205,8 @@ static void xdp_test_run_teardown(struct xdp_test_data *xdp)
 {
 	xdp_unreg_mem_model(&xdp->mem);
 	page_pool_destroy(xdp->pp);
-	kfree(xdp->frames);
-	kfree(xdp->skbs);
+	kvfree(xdp->frames);
+	kvfree(xdp->skbs);
 }
 
 static bool frame_was_changed(const struct xdp_page_head *head)
diff --git a/net/core/filter.c b/net/core/filter.c
index 61940e753552..70dc621672f2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3961,12 +3961,6 @@ static u32 __bpf_skb_min_len(const struct sk_buff *skb)
 		if (offset > 0)
 			min_len = offset;
 	}
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		offset = skb_checksum_start_offset(skb) +
-			 skb->csum_offset + sizeof(__sum16);
-		if (offset > 0)
-			min_len = offset;
-	}
 	return min_len;
 }
 
@@ -3983,6 +3977,11 @@ static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len)
 
 static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 {
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    new_len < skb_checksum_start_offset(skb) + skb->csum_offset +
+		      sizeof(__sum16))
+		skb->ip_summed = CHECKSUM_NONE;
+
 	return __skb_trim_rcsum(skb, new_len);
 }
 
@@ -9045,6 +9044,8 @@ static const struct bpf_func_proto *
 lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+	case BPF_FUNC_skb_pull_data:
+		return NULL;
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	case BPF_FUNC_lwt_seg6_store_bytes:
 		return &bpf_lwt_seg6_store_bytes_proto;
@@ -10565,11 +10566,12 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				       target_size));
 		*insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING,
 				      1);
-		*insn++ = BPF_MOV64_IMM(si->dst_reg, -1);
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, -1);
 #else
-		*insn++ = BPF_MOV64_IMM(si->dst_reg, -1);
-		*target_size = 2;
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, -1);
 #endif
+		*target_size = sizeof_field(struct bpf_sock, rx_queue_mapping);
+
 		break;
 	}
 
@@ -11105,18 +11107,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct bpf_sock_ops, rtt_min):
-		BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) !=
-			     sizeof(struct minmax));
-		BUILD_BUG_ON(sizeof(struct minmax) <
-			     sizeof(struct minmax_sample));
-
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
-						struct bpf_sock_ops_kern, sk),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct bpf_sock_ops_kern, sk));
-		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
-				      offsetof(struct tcp_sock, rtt_min) +
-				      sizeof_field(struct minmax_sample, t));
+		SOCK_OPS_GET_FIELD(rtt_min, rtt_min.s[0].v, struct tcp_sock);
 		break;
 
 	case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags):
@@ -12912,8 +12903,9 @@ __bpf_kfunc_start_defs();
  * @sock: Pointer to socket to be destroyed
  *
  * Return:
- * On error, may return EPROTONOSUPPORT, EINVAL.
- * EPROTONOSUPPORT if protocol specific destroy handler is not supported.
+ * On error, may return EOPNOTSUPP, or whatever the protocol specific
+ * destroy handler returns.
+ * EOPNOTSUPP if protocol specific destroy handler is not supported.
  * 0 otherwise
  */
 __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
@@ -12925,8 +12917,12 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
 	 * Supporting protocols will need to acquire sock lock in the BPF context
 	 * prior to invoking this kfunc.
 	 */
-	if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP &&
-					   sk->sk_protocol != IPPROTO_UDP))
+	if (!sk->sk_prot->diag_destroy)
+		return -EOPNOTSUPP;
+
+	if (sk_fullsock(sk) &&
+	    sk->sk_protocol != IPPROTO_TCP &&
+	    sk->sk_protocol != IPPROTO_UDP)
 		return -EOPNOTSUPP;
 
 	return sk->sk_prot->diag_destroy(sk, ECONNABORTED);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2521b643fa05..df385a5a961e 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1000,6 +1000,10 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 	int err = 0;
 	u32 len, off;
 
+	if (verdict == __SK_REDIRECT && skb_bpf_ingress(skb) &&
+	    skb_bpf_redirect_fetch(skb) == psock->sk)
+		verdict = __SK_PASS;
+
 	switch (verdict) {
 	case __SK_PASS:
 		err = -EIO;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ca49bc7f8687..38df84284328 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -41,6 +41,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	struct bpf_stab *stab;
 
 	if (attr->max_entries == 0 ||
+	    attr->max_entries > INT_MAX ||
 	    attr->key_size    != 4 ||
 	    (attr->value_size != sizeof(u32) &&
 	     attr->value_size != sizeof(u64)) ||
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6257459bcee2..6a30f1138454 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1520,7 +1520,8 @@ void inet_csk_listen_stop(struct sock *sk)
 		local_bh_enable();
 		sock_put(child);
 
-		cond_resched();
+		if (!has_current_bpf_ctx())
+			cond_resched();
 	}
 	if (queue->fastopenq.rskq_rst_head) {
 		/* Free all the reqs queued in rskq_rst_head. */
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 3bff346308d0..bf00d6463c19 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -124,7 +124,7 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	struct bpf_insn *insn = insn_buf;
 
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	*insn++ = BPF_JMP32_IMM(BPF_JGE, ret, map->max_entries, 5);
 	*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
 	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b749c01742ee..bfa64ae6c94d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6206,6 +6206,13 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 				return -EINVAL;
 			insn = &prog->insns[insn_idx];
 
+			if (is_ldimm64_insn(insn) && (size_t)insn_idx + 1 >= prog->insns_cnt) {
+				pr_warn("prog '%s': relo #%d: insn #%d (LDIMM64) is truncated\n",
+					prog->name, i, insn_idx);
+				err = -EINVAL;
+				goto out;
+			}
+
 			err = record_relo_core(prog, rec, insn_idx);
 			if (err) {
 				pr_warn("prog '%s': relo #%d: failed to record relocation: %s\n",
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 8ad2715721cf..2672623a4198 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -980,23 +980,30 @@ static int bpf_core_calc_relo(const char *prog_name,
 }
 
 /*
- * Turn instruction for which CO_RE relocation failed into invalid one with
+ * Turn instruction for which CO-RE relocation failed into invalid one with
  * distinct signature.
  */
-static void bpf_core_poison_insn(const char *prog_name, int relo_idx,
-				 int insn_idx, struct bpf_insn *insn)
+static int bpf_core_poison_insn(const char *prog_name, int relo_idx,
+				struct bpf_insn *insn, int insn_idx)
 {
-	pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n",
-		 prog_name, relo_idx, insn_idx);
-	insn->code = BPF_JMP | BPF_CALL;
-	insn->dst_reg = 0;
-	insn->src_reg = 0;
-	insn->off = 0;
-	/* if this instruction is reachable (not a dead code),
-	 * verifier will complain with the following message:
-	 * invalid func unknown#195896080
-	 */
-	insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */
+	int insn_cnt = is_ldimm64_insn(insn) ? 2 : 1;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++) {
+		pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n",
+			 prog_name, relo_idx, insn_idx + i);
+		insn[i].code = BPF_JMP | BPF_CALL;
+		insn[i].dst_reg = 0;
+		insn[i].src_reg = 0;
+		insn[i].off = 0;
+		/*
+		 * If this instruction is reachable (not dead code), the verifier
+		 * will complain with "invalid func unknown#195896080".
+		 */
+		insn[i].imm = 195896080; /* => 0xbad2310 => "bad relo" */
+	}
+
+	return 0;
 }
 
 static int insn_bpf_size_to_bytes(struct bpf_insn *insn)
@@ -1047,17 +1054,6 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 
 	class = BPF_CLASS(insn->code);
 
-	if (res->poison) {
-poison:
-		/* poison second part of ldimm64 to avoid confusing error from
-		 * verifier about "unknown opcode 00"
-		 */
-		if (is_ldimm64_insn(insn))
-			bpf_core_poison_insn(prog_name, relo_idx, insn_idx + 1, insn + 1);
-		bpf_core_poison_insn(prog_name, relo_idx, insn_idx, insn);
-		return 0;
-	}
-
 	orig_val = res->orig_val;
 	new_val = res->new_val;
 
@@ -1065,7 +1061,9 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 	case BPF_ALU:
 	case BPF_ALU64:
 		if (BPF_SRC(insn->code) != BPF_K)
-			return -EINVAL;
+			goto bad_insn;
+		if (res->poison)
+			return bpf_core_poison_insn(prog_name, relo_idx, insn, insn_idx);
 		if (res->validate && insn->imm != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %d, exp %llu -> %llu\n",
 				prog_name, relo_idx,
@@ -1082,6 +1080,8 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 	case BPF_LDX:
 	case BPF_ST:
 	case BPF_STX:
+		if (res->poison)
+			return bpf_core_poison_insn(prog_name, relo_idx, insn, insn_idx);
 		if (res->validate && insn->off != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %d, exp %llu -> %llu\n",
 				prog_name, relo_idx, insn_idx, insn->off, (unsigned long long)orig_val,
@@ -1097,7 +1097,7 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 			pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) accesses field incorrectly. "
 				"Make sure you are accessing pointers, unsigned integers, or fields of matching type and size.\n",
 				prog_name, relo_idx, insn_idx);
-			goto poison;
+			return bpf_core_poison_insn(prog_name, relo_idx, insn, insn_idx);
 		}
 
 		orig_val = insn->off;
@@ -1140,6 +1140,9 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 			return -EINVAL;
 		}
 
+		if (res->poison)
+			return bpf_core_poison_insn(prog_name, relo_idx, insn, insn_idx);
+
 		imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32);
 		if (res->validate && imm != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %llu -> %llu\n",
@@ -1157,6 +1160,7 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 		break;
 	}
 	default:
+bad_insn:
 		pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:0x%x, src:0x%x, dst:0x%x, off:0x%x, imm:0x%x\n",
 			prog_name, relo_idx, insn_idx, insn->code,
 			(unsigned)insn->src_reg, (unsigned)insn->dst_reg, (unsigned)insn->off, (unsigned)insn->imm);
diff --git a/tools/testing/selftests/bpf/prog_tests/cb_refs.c b/tools/testing/selftests/bpf/prog_tests/cb_refs.c
index 78566b817fd7..490e15e7126d 100644
--- a/tools/testing/selftests/bpf/prog_tests/cb_refs.c
+++ b/tools/testing/selftests/bpf/prog_tests/cb_refs.c
@@ -13,7 +13,7 @@ struct {
 } cb_refs_tests[] = {
 	{ "underflow_prog", "release kfunc bpf_kfunc_call_test_release expects referenced PTR_TO_BTF_ID passed to R1" },
 	{ "leak_prog", "Possibly NULL pointer passed to helper R2" },
-	{ "nested_cb", "Unreleased reference id=4 alloc_insn=2" }, /* alloc_insn=2{4,5} */
+	{ "nested_cb", "Unreleased reference id=5 alloc_insn=2" }, /* alloc_insn=2{4,5} */
 	{ "non_cb_transfer_ref", "Unreleased reference id=4 alloc_insn=1" }, /* alloc_insn=1{1,2} */
 };
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
index a18d3680fb16..51f42b02a267 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
@@ -14,6 +14,197 @@
 
 static char log[16 * 1024];
 
+static int load_core_relo_insns(int btf_fd, struct bpf_insn *insns, int insn_cnt,
+				struct bpf_func_info *funcs, int func_cnt,
+				int enum_id, int access_str_off, int insn_idx,
+				bool relocate)
+{
+	struct bpf_core_relo relo = {
+		.insn_off = insn_idx * sizeof(struct bpf_insn),
+		.type_id = enum_id,
+		.access_str_off = access_str_off,
+		.kind = BPF_CORE_ENUMVAL_VALUE,
+	};
+	union bpf_attr attr = {
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.insn_cnt = insn_cnt,
+		.insns = (__u64)insns,
+		.license = (__u64)"GPL",
+		.log_buf = (__u64)log,
+		.log_size = sizeof(log),
+		.log_level = 2,
+		.prog_btf_fd = btf_fd,
+		.func_info_rec_size = sizeof(struct bpf_func_info),
+		.func_info = (__u64)funcs,
+		.func_info_cnt = func_cnt,
+	};
+
+	if (relocate) {
+		attr.core_relo_cnt = 1;
+		attr.core_relos = (__u64)&relo;
+		attr.core_relo_rec_size = sizeof(relo);
+	}
+	memset(log, 0, sizeof(log));
+	return sys_bpf_prog_load(&attr, sizeof(attr), 1);
+}
+
+static void test_early_core_relo(void)
+{
+	static const char unrecognized[] = "trying to relocate unrecognized insn #2";
+	static const struct {
+		const char *name;
+		struct bpf_insn insns[2];
+		const char *err_msg;
+	} tests[] = {
+		{ "poison_exit", { BPF_EXIT_INSN() }, unrecognized },
+		{ "poison_ja", { BPF_JMP_A(1) }, unrecognized },
+		{ "poison_jmp", { BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1) }, unrecognized },
+		{ "poison_jmp32", { BPF_JMP32_IMM(BPF_JEQ, BPF_REG_0, 0, 1) }, unrecognized },
+		{ "poison_call", { BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32) }, unrecognized },
+		{ "poison_alu_reg", { BPF_MOV32_REG(BPF_REG_0, BPF_REG_1) }, unrecognized },
+		{ "poison_alu64_reg", { BPF_MOV64_REG(BPF_REG_0, BPF_REG_1) }, unrecognized },
+		{ "poison_ld_abs", { BPF_LD_ABS(BPF_W, 0) },
+		  "insn #2 (LDIMM64) has unexpected form" },
+		{ "poison_alu_imm", { BPF_MOV32_IMM(BPF_REG_0, 0) } },
+		{ "poison_alu64_imm", { BPF_MOV64_IMM(BPF_REG_0, 0) } },
+		{ "poison_ldx", { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0) } },
+		{ "poison_st", { BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0) } },
+		{ "poison_stx", { BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4) } },
+		{ "poison_ldimm64", { BPF_LD_IMM64(BPF_REG_0, 0) } },
+	};
+	struct test_btf {
+		struct btf_header hdr;
+		__u32 types[18];
+		char strings[64];
+	} raw_btf = {
+		.hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_off = 0,
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct test_btf, strings) -
+				   offsetof(struct test_btf, types),
+			.str_len = sizeof(raw_btf.strings),
+		},
+		.types = {
+			BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] int */
+			BTF_FUNC_PROTO_ENC(1, 0),	/* [2] int (*)(void) */
+			BTF_FUNC_ENC(5, 2),		/* [3] main_fn */
+			BTF_FUNC_ENC(13, 2),		/* [4] sub_fn */
+			BTF_TYPE_ENC(20, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), /* [5] enum */
+			BTF_ENUM_ENC(45, 0),		/* value = 0 */
+		},
+		.strings = "\0int\0main_fn\0sub_fn\0core_relo_poison_missing\0value\0" "0",
+	};
+	struct bpf_func_info funcs[] = {
+		{ .insn_off = 0, .type_id = 3 },
+		{ .insn_off = 3, .type_id = 4 },
+	};
+	struct bpf_insn core_only[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	struct bpf_insn subprog[] = {
+		BPF_CALL_REL(2),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	struct bpf_insn truncated_ldimm64[] = {
+		BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0),
+	};
+	int access_str_off = 51; /* offset of "0" */
+	int enum_id = 5;
+	int btf_fd, prog_fd = -1, i;
+
+	btf_fd = bpf_btf_load(&raw_btf, sizeof(raw_btf), NULL);
+	if (!ASSERT_GE(btf_fd, 0, "btf_load"))
+		goto cleanup;
+
+	if (test__start_subtest("without_func_info")) {
+		prog_fd = load_core_relo_insns(btf_fd, core_only, ARRAY_SIZE(core_only), NULL, 0,
+					       enum_id, access_str_off, 2, false);
+		if (!ASSERT_GE(prog_fd, 0, "control_load"))
+			goto cleanup;
+		close(prog_fd);
+		prog_fd = load_core_relo_insns(btf_fd, core_only, ARRAY_SIZE(core_only), NULL, 0,
+					       enum_id, access_str_off, 2, true);
+		if (!ASSERT_GE(prog_fd, 0, "poisoned_load"))
+			goto cleanup;
+		ASSERT_HAS_SUBSTR(log, "substituting insn #2", "poison_log");
+		close(prog_fd);
+		prog_fd = -1;
+	}
+
+	if (test__start_subtest("before_subprog_validation")) {
+		prog_fd = load_core_relo_insns(btf_fd, subprog, ARRAY_SIZE(subprog), funcs, 2,
+					       enum_id, access_str_off, 2, true);
+		if (!ASSERT_LT(prog_fd, 0, "poisoned_load"))
+			goto cleanup;
+		ASSERT_HAS_SUBSTR(log, "substituting insn #2", "poison_log");
+		ASSERT_HAS_SUBSTR(log, "last insn is not an exit or jmp", "poisoned_load_log");
+	}
+
+	if (test__start_subtest("truncated_ldimm64")) {
+		prog_fd = load_core_relo_insns(btf_fd, truncated_ldimm64,
+					       ARRAY_SIZE(truncated_ldimm64), NULL, 0,
+					       enum_id, access_str_off, 0, true);
+		if (!ASSERT_LT(prog_fd, 0, "truncated_load"))
+			goto cleanup;
+		ASSERT_HAS_SUBSTR(log, "invalid bpf_ld_imm64 insn", "truncated_load_log");
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		struct bpf_insn insns[] = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			tests[i].insns[0],
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		};
+		bool is_ldimm64 = insns[2].code == (BPF_LD | BPF_DW | BPF_IMM);
+
+		if (!test__start_subtest(tests[i].name))
+			continue;
+		if (is_ldimm64) {
+			insns[1].off = 2;
+			insns[3] = tests[i].insns[1];
+		}
+		prog_fd = load_core_relo_insns(btf_fd, insns, ARRAY_SIZE(insns), funcs, 1,
+					       enum_id, access_str_off, 2, false);
+		if (!ASSERT_GE(prog_fd, 0, "control_load"))
+			goto cleanup;
+		close(prog_fd);
+		prog_fd = load_core_relo_insns(btf_fd, insns, ARRAY_SIZE(insns), funcs, 1,
+					       enum_id, access_str_off, 2, true);
+		if (!tests[i].err_msg) {
+			ASSERT_GE(prog_fd, 0, "dead_poison_load");
+			ASSERT_HAS_SUBSTR(log, "substituting insn #2", "poison_log");
+			if (is_ldimm64)
+				ASSERT_HAS_SUBSTR(log, "substituting insn #3", "poison_ldimm64_log");
+		} else {
+			ASSERT_LT(prog_fd, 0, "invalid_poison_load");
+			ASSERT_HAS_SUBSTR(log, tests[i].err_msg, "invalid_poison_log");
+			ASSERT_NULL(strstr(log, "substituting insn"), "invalid_poison_substitution");
+		}
+		close(prog_fd);
+		prog_fd = -1;
+	}
+
+cleanup:
+	if (env.verbosity > VERBOSE_NORMAL && log[0]) {
+		printf("-------- program load log start --------\n");
+		printf("%s", log);
+		printf("-------- program load log end ----------\n");
+	}
+	close(prog_fd);
+	close(btf_fd);
+}
+
 /* Check that verifier rejects BPF program containing relocation
  * pointing to non-existent BTF type.
  */
@@ -120,6 +311,7 @@ static void test_bad_local_id(void)
 
 void test_core_reloc_raw(void)
 {
+	test_early_core_relo();
 	if (test__start_subtest("bad_local_id"))
 		test_bad_local_id();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index 5fda11590708..4396560365e8 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -9,6 +9,7 @@
 enum test_setup_type {
 	SETUP_SYSCALL_SLEEP,
 	SETUP_SKB_PROG,
+	SETUP_SKB_PROG_NONLINEAR,
 	SETUP_SKB_PROG_TP,
 	SETUP_XDP_PROG,
 };
@@ -32,6 +33,7 @@ static struct {
 	{"test_ringbuf", SETUP_SYSCALL_SLEEP},
 	{"test_skb_readonly", SETUP_SKB_PROG},
 	{"test_dynptr_skb_data", SETUP_SKB_PROG},
+	{"test_dynptr_skb_slice_non_linear", SETUP_SKB_PROG_NONLINEAR},
 	{"test_dynptr_skb_meta_data", SETUP_SKB_PROG},
 	{"test_dynptr_skb_meta_flags", SETUP_SKB_PROG},
 	{"test_adjust", SETUP_SYSCALL_SLEEP},
@@ -94,7 +96,9 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 		bpf_link__destroy(link);
 		break;
 	case SETUP_SKB_PROG:
+	case SETUP_SKB_PROG_NONLINEAR:
 	{
+		struct __sk_buff ctx = {};
 		int prog_fd;
 		char buf[64];
 
@@ -106,6 +110,12 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 			    .repeat = 1,
 		);
 
+		if (setup_type == SETUP_SKB_PROG_NONLINEAR) {
+			ctx.data_end = ETH_HLEN + sizeof(struct iphdr);
+			topts.ctx_in = &ctx;
+			topts.ctx_size_in = sizeof(ctx);
+		}
+
 		prog_fd = bpf_program__fd(prog);
 		if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
 			goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions.c b/tools/testing/selftests/bpf/prog_tests/exceptions.c
index 3588d6f97fd4..639866ce09a9 100644
--- a/tools/testing/selftests/bpf/prog_tests/exceptions.c
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions.c
@@ -55,6 +55,7 @@ static void test_exceptions_success(void)
 	RUN_SUCCESS(exception_ext, 0);
 	RUN_SUCCESS(exception_ext_mod_cb_runtime, 35);
 	RUN_SUCCESS(exception_throw_subprog, 1);
+	RUN_SUCCESS(exception_throw_subprog_stack_cb, 0x1234);
 	RUN_SUCCESS(exception_assert_nz_gfunc, 1);
 	RUN_SUCCESS(exception_assert_zero_gfunc, 1);
 	RUN_SUCCESS(exception_assert_neg_gfunc, 1);
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index c3d133c6a00d..52fabbee3dd5 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -714,7 +714,7 @@ static void test_btf(void)
 			break;
 
 		err = btf__load_into_kernel(btf);
-		ASSERT_EQ(err, -ELOOP, "check btf");
+		ASSERT_EQ(err, 0, "check btf");
 		btf__free(btf);
 		break;
 	}
@@ -773,7 +773,7 @@ static void test_btf(void)
 			break;
 
 		err = btf__load_into_kernel(btf);
-		ASSERT_EQ(err, -ELOOP, "check btf");
+		ASSERT_EQ(err, 0, "check btf");
 		btf__free(btf);
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_ownership.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_ownership.c
new file mode 100644
index 000000000000..a487aa68f2ee
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_ownership.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <bpf/btf.h>
+#include <linux/btf.h>
+#include <test_progs.h>
+
+#define SPIN_LOCK 2
+#define LIST_HEAD 3
+#define LIST_NODE 4
+/* Keep in sync with BTF_MAX_OWNERSHIP_DEPTH. */
+#define MAX_OWNERSHIP_DEPTH 8
+
+static struct btf *init_btf(void)
+{
+	struct btf *btf;
+	int id;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "btf__new_empty"))
+		return NULL;
+	id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED);
+	if (!ASSERT_EQ(id, 1, "btf__add_int"))
+		goto err_out;
+	id = btf__add_struct(btf, "bpf_spin_lock", 4);
+	if (!ASSERT_EQ(id, SPIN_LOCK, "btf__add_struct bpf_spin_lock"))
+		goto err_out;
+	id = btf__add_struct(btf, "bpf_list_head", 16);
+	if (!ASSERT_EQ(id, LIST_HEAD, "btf__add_struct bpf_list_head"))
+		goto err_out;
+	id = btf__add_struct(btf, "bpf_list_node", 24);
+	if (!ASSERT_EQ(id, LIST_NODE, "btf__add_struct bpf_list_node"))
+		goto err_out;
+	return btf;
+
+err_out:
+	btf__free(btf);
+	return NULL;
+}
+
+static int add_local_kptr(struct btf *btf, int pointee_id, const char *tag)
+{
+	int id;
+
+	id = btf__add_type_tag(btf, tag, pointee_id);
+	if (!ASSERT_GT(id, 0, "btf__add_type_tag"))
+		return id;
+	id = btf__add_ptr(btf, id);
+	ASSERT_GT(id, 0, "btf__add_ptr");
+	return id;
+}
+
+static void test_self_cycle(const char *tag, int expected_err)
+{
+	struct btf *btf;
+	int id, err;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+	id = add_local_kptr(btf, 7, tag);
+	if (id <= 0)
+		goto out;
+	id = btf__add_struct(btf, "self_cycle", 8);
+	if (!ASSERT_EQ(id, 7, "btf__add_struct self_cycle"))
+		goto out;
+	err = btf__add_field(btf, "next", 6, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field self_cycle::next"))
+		goto out;
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, expected_err, "check btf");
+out:
+	btf__free(btf);
+}
+
+static void test_aba_cycle(void)
+{
+	struct btf *btf;
+	int id, err;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+	id = add_local_kptr(btf, 10, "kptr");
+	if (id <= 0)
+		goto out;
+	id = add_local_kptr(btf, 9, "kptr");
+	if (id <= 0)
+		goto out;
+	id = btf__add_struct(btf, "cycle_a", 8);
+	if (!ASSERT_EQ(id, 9, "btf__add_struct cycle_a"))
+		goto out;
+	err = btf__add_field(btf, "b", 6, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field cycle_a::b"))
+		goto out;
+	id = btf__add_struct(btf, "cycle_b", 8);
+	if (!ASSERT_EQ(id, 10, "btf__add_struct cycle_b"))
+		goto out;
+	err = btf__add_field(btf, "a", 8, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field cycle_b::a"))
+		goto out;
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, -ELOOP, "check btf");
+out:
+	btf__free(btf);
+}
+
+static void test_mixed_cycle(void)
+{
+	struct btf *btf;
+	int id, err;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+	id = add_local_kptr(btf, 7, "kptr");
+	if (id <= 0)
+		goto out;
+	id = btf__add_struct(btf, "mixed_owner", 20);
+	if (!ASSERT_EQ(id, 7, "btf__add_struct mixed_owner"))
+		goto out;
+	err = btf__add_field(btf, "root", LIST_HEAD, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field mixed_owner::root"))
+		goto out;
+	err = btf__add_field(btf, "lock", SPIN_LOCK, 128, 0);
+	if (!ASSERT_OK(err, "btf__add_field mixed_owner::lock"))
+		goto out;
+	id = btf__add_decl_tag(btf, "contains:mixed_node:node", 7, 0);
+	if (!ASSERT_EQ(id, 8, "btf__add_decl_tag mixed_owner"))
+		goto out;
+	id = btf__add_struct(btf, "mixed_node", 32);
+	if (!ASSERT_EQ(id, 9, "btf__add_struct mixed_node"))
+		goto out;
+	err = btf__add_field(btf, "node", LIST_NODE, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field mixed_node::node"))
+		goto out;
+	err = btf__add_field(btf, "owner", 6, 192, 0);
+	if (!ASSERT_OK(err, "btf__add_field mixed_node::owner"))
+		goto out;
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, -ELOOP, "check btf");
+out:
+	btf__free(btf);
+}
+
+static void test_acyclic_depth(int depth, bool child_first, bool shared_suffix, int expected_err)
+{
+	int ptr_id[MAX_OWNERSHIP_DEPTH + 1];
+	int first_struct_id;
+	struct btf *btf;
+	int id, err, i, n, pointee_id;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+	first_struct_id = 5 + 2 * depth;
+	for (i = 0; i < depth; i++) {
+		if (i == depth - 1)
+			pointee_id = first_struct_id + depth;
+		else
+			pointee_id = first_struct_id + (child_first ? depth - 2 - i : i + 1);
+		ptr_id[i] = add_local_kptr(btf, pointee_id, "kptr");
+		if (ptr_id[i] <= 0)
+			goto out;
+	}
+	for (n = 0; n < depth; n++) {
+		char name[32];
+		int offset = 0;
+
+		i = child_first ? depth - 1 - n : n;
+		snprintf(name, sizeof(name), "owner_%d", i);
+		id = btf__add_struct(btf, name, shared_suffix && !i ? 16 : 8);
+		if (!ASSERT_EQ(id, first_struct_id + n, "btf__add_struct owner"))
+			goto out;
+		if (shared_suffix && !i) {
+			/*
+			 * Visit the shared suffix through the shorter path before
+			 * reaching it again with less remaining depth.
+			 */
+			err = btf__add_field(btf, "suffix", ptr_id[1], 0, 0);
+			if (!ASSERT_OK(err, "btf__add_field owner::suffix"))
+				goto out;
+			offset = 64;
+		}
+		err = btf__add_field(btf, "next", ptr_id[i], offset, 0);
+		if (!ASSERT_OK(err, "btf__add_field owner::next"))
+			goto out;
+	}
+	id = btf__add_struct(btf, "plain_leaf", 4);
+	if (!ASSERT_EQ(id, first_struct_id + depth, "btf__add_struct plain_leaf"))
+		goto out;
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, expected_err, "check btf");
+out:
+	btf__free(btf);
+}
+
+static void test_graph_depth(bool rbtree, int depth, int expected_err)
+{
+	int root_type = LIST_HEAD, node_type = LIST_NODE, node_size = 24;
+	int id, err, i, lock_off, root_off, size;
+	struct btf *btf;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+	if (rbtree) {
+		root_type = btf__add_struct(btf, "bpf_rb_root", 16);
+		if (!ASSERT_GT(root_type, 0, "btf__add_struct bpf_rb_root"))
+			goto out;
+		node_type = btf__add_struct(btf, "bpf_rb_node", 32);
+		if (!ASSERT_GT(node_type, 0, "btf__add_struct bpf_rb_node"))
+			goto out;
+		node_size = 32;
+	}
+
+	for (i = 0; i < depth; i++) {
+		char name[32], tag[64];
+
+		lock_off = i ? node_size : 0;
+		root_off = lock_off + 8;
+		size = i == depth - 1 ? node_size : root_off + 16;
+		snprintf(name, sizeof(name), "graph_owner_%d", i);
+		id = btf__add_struct(btf, name, size);
+		if (!ASSERT_GT(id, 0, "btf__add_struct graph_owner"))
+			goto out;
+		if (i) {
+			err = btf__add_field(btf, "node", node_type, 0, 0);
+			if (!ASSERT_OK(err, "btf__add_field graph_owner::node"))
+				goto out;
+		}
+		if (i == depth - 1)
+			continue;
+		err = btf__add_field(btf, "lock", SPIN_LOCK, lock_off * 8, 0);
+		if (!ASSERT_OK(err, "btf__add_field graph_owner::lock"))
+			goto out;
+		err = btf__add_field(btf, "root", root_type, root_off * 8, 0);
+		if (!ASSERT_OK(err, "btf__add_field graph_owner::root"))
+			goto out;
+		snprintf(tag, sizeof(tag), "contains:graph_owner_%d:node", i + 1);
+		err = btf__add_decl_tag(btf, tag, id, i ? 2 : 1);
+		if (!ASSERT_GT(err, 0, "btf__add_decl_tag graph_owner"))
+			goto out;
+	}
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, expected_err, "check btf");
+out:
+	btf__free(btf);
+}
+
+void test_local_kptr_ownership(void)
+{
+	if (test__start_subtest("self_cycle"))
+		test_self_cycle("kptr", -ELOOP);
+	if (test__start_subtest("untrusted_self_cycle"))
+		test_self_cycle("kptr_untrusted", 0);
+	if (test__start_subtest("percpu_self_cycle"))
+		test_self_cycle("percpu_kptr", -ELOOP);
+	if (test__start_subtest("ABA_cycle"))
+		test_aba_cycle();
+	if (test__start_subtest("mixed_graph_root_cycle"))
+		test_mixed_cycle();
+	if (test__start_subtest("max_acyclic"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH, false, false, 0);
+	if (test__start_subtest("too_deep_acyclic"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH + 1, false, false, -ELOOP);
+	if (test__start_subtest("max_acyclic_child_first"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH, true, false, 0);
+	if (test__start_subtest("too_deep_acyclic_child_first"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH + 1, true, false, -ELOOP);
+	if (test__start_subtest("max_acyclic_shared_suffix"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH, false, true, 0);
+	if (test__start_subtest("too_deep_acyclic_shared_suffix"))
+		test_acyclic_depth(MAX_OWNERSHIP_DEPTH + 1, false, true, -ELOOP);
+	if (test__start_subtest("list_three_types"))
+		test_graph_depth(false, 3, 0);
+	if (test__start_subtest("list_four_types"))
+		test_graph_depth(false, 4, 0);
+	if (test__start_subtest("list_max_depth"))
+		test_graph_depth(false, MAX_OWNERSHIP_DEPTH, 0);
+	if (test__start_subtest("list_too_deep"))
+		test_graph_depth(false, MAX_OWNERSHIP_DEPTH + 1, -ELOOP);
+	if (test__start_subtest("rbtree_three_types"))
+		test_graph_depth(true, 3, 0);
+	if (test__start_subtest("rbtree_four_types"))
+		test_graph_depth(true, 4, 0);
+	if (test__start_subtest("rbtree_max_depth"))
+		test_graph_depth(true, MAX_OWNERSHIP_DEPTH, 0);
+	if (test__start_subtest("rbtree_too_deep"))
+		test_graph_depth(true, MAX_OWNERSHIP_DEPTH + 1, -ELOOP);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index a72ae0b29f6e..7b4a1e24363b 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "percpu_alloc_array.skel.h"
@@ -350,6 +352,103 @@ static void test_lru_percpu_hash_cpu_flag(void)
 	test_percpu_map_cpu_flag(BPF_MAP_TYPE_LRU_PERCPU_HASH);
 }
 
+/*
+ * A BPF_F_CPU update that creates an element must zero the value on the other
+ * cpus, rather than leave them holding whatever the recycled element last
+ * contained. max_entries is 1 so the second key can only reuse the element
+ * the first one released.
+ */
+static void test_percpu_map_cpu_flag_create(enum bpf_map_type map_type, __u32 map_flags)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
+	const u32 stale = 0xDEADC0DE, fresh = 0xC0FFEE;
+	int nr_cpus, cpu, map_fd, err, key;
+	int pinned_cpu, value_cpu;
+	cpu_set_t old_mask, new_mask;
+	bool restore_mask = false;
+	u32 value;
+	u64 flags;
+
+	nr_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(nr_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	if (nr_cpus < 2) {
+		test__skip();
+		return;
+	}
+
+	map_fd = bpf_map_create(map_type, "cpu_flag_create", sizeof(key), sizeof(value), 1, &opts);
+	if (!ASSERT_GE(map_fd, 0, "bpf_map_create"))
+		return;
+
+	/* NO_PREALLOC recycles per cpu, so keep the delete and the create on one cpu. */
+	err = sched_getaffinity(0, sizeof(old_mask), &old_mask);
+	if (!ASSERT_OK(err, "sched_getaffinity"))
+		goto out;
+
+	pinned_cpu = sched_getcpu();
+	if (!ASSERT_GE(pinned_cpu, 0, "sched_getcpu"))
+		goto out;
+
+	CPU_ZERO(&new_mask);
+	CPU_SET(pinned_cpu, &new_mask);
+	err = sched_setaffinity(0, sizeof(new_mask), &new_mask);
+	if (!ASSERT_OK(err, "sched_setaffinity"))
+		goto out;
+	restore_mask = true;
+
+	value_cpu = pinned_cpu ? 0 : 1;
+
+	key = 1;
+	value = stale;
+	err = bpf_map_update_elem(map_fd, &key, &value, BPF_F_ALL_CPUS);
+	if (!ASSERT_OK(err, "bpf_map_update_elem all_cpus"))
+		goto out;
+
+	err = bpf_map_delete_elem(map_fd, &key);
+	if (!ASSERT_OK(err, "bpf_map_delete_elem"))
+		goto out;
+
+	key = 2;
+	value = fresh;
+	flags = (u64)value_cpu << 32 | BPF_F_CPU;
+	err = bpf_map_update_elem(map_fd, &key, &value, flags);
+	if (!ASSERT_OK(err, "bpf_map_update_elem specified cpu"))
+		goto out;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		value = 0;
+		flags = (u64)cpu << 32 | BPF_F_CPU;
+		err = bpf_map_lookup_elem_flags(map_fd, &key, &value, flags);
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem_flags specified cpu"))
+			goto out;
+		if (!ASSERT_EQ(value, cpu == value_cpu ? fresh : 0, "value on specified cpu"))
+			goto out;
+	}
+
+out:
+	if (restore_mask)
+		sched_setaffinity(0, sizeof(old_mask), &old_mask);
+	close(map_fd);
+}
+
+static void test_percpu_hash_cpu_flag_create(void)
+{
+	test_percpu_map_cpu_flag_create(BPF_MAP_TYPE_PERCPU_HASH, 0);
+}
+
+static void test_percpu_hash_cpu_flag_create_malloc(void)
+{
+	test_percpu_map_cpu_flag_create(BPF_MAP_TYPE_PERCPU_HASH, BPF_F_NO_PREALLOC);
+}
+
+static void test_lru_percpu_hash_cpu_flag_create(void)
+{
+	/* lru without prealloc is -ENOTSUPP, so there is no malloc variant */
+	test_percpu_map_cpu_flag_create(BPF_MAP_TYPE_LRU_PERCPU_HASH, 0);
+}
+
 static void test_percpu_cgroup_storage_cpu_flag(void)
 {
 	struct percpu_alloc_array *skel = NULL;
@@ -454,6 +553,12 @@ void test_percpu_alloc(void)
 		test_percpu_hash_cpu_flag();
 	if (test__start_subtest("cpu_flag_lru_percpu_hash"))
 		test_lru_percpu_hash_cpu_flag();
+	if (test__start_subtest("cpu_flag_create_percpu_hash"))
+		test_percpu_hash_cpu_flag_create();
+	if (test__start_subtest("cpu_flag_create_percpu_hash_malloc"))
+		test_percpu_hash_cpu_flag_create_malloc();
+	if (test__start_subtest("cpu_flag_create_lru_percpu_hash"))
+		test_lru_percpu_hash_cpu_flag_create();
 	if (test__start_subtest("cpu_flag_percpu_cgroup_storage"))
 		test_percpu_cgroup_storage_cpu_flag();
 	if (test__start_subtest("cpu_flag_array"))
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
index 9c11938fe597..78d642a02bdb 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <poll.h>
 #include <test_progs.h>
 #include <bpf/bpf_endian.h>
 
@@ -110,6 +111,122 @@ static void test_tcp_server(struct sock_destroy_prog *skel)
 		close(serv);
 }
 
+static void test_tcp_listen_pending(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n, serv_port;
+	struct pollfd pfd = { .events = POLLIN };
+	char buf[1];
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(serv);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16)serv_port;
+
+	/*
+	 * Connect but never accept, so the child sits in the accept queue
+	 * of the listener. Wait until it's actually there.
+	 */
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+	pfd.fd = serv;
+	if (!ASSERT_EQ(poll(&pfd, 1, -1), 1, "poll listener"))
+		goto cleanup;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_server);
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_LT(accept_serv, 0, "accept on destroyed listener"))
+		goto cleanup;
+	ASSERT_EQ(errno, EINVAL, "error code on destroyed listener");
+
+	/* The unaccepted child was reset along with the listener. */
+	n = recv(clien, buf, sizeof(buf), 0);
+	if (!ASSERT_LT(n, 0, "client recv on reset child"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNRESET, "error code on reset child");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_tcp_timewait(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n;
+	struct timeval tv = {};
+	char buf[1];
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	/*
+	 * Active close from the client, then close the server side. Once
+	 * recv() sees EOF the server FIN has been processed and the client
+	 * sock is in TIME_WAIT. Block without timeout so a loaded CI box
+	 * can't race us.
+	 */
+	if (!ASSERT_OK(setsockopt(clien, SOL_SOCKET, SO_RCVTIMEO, &tv,
+				  sizeof(tv)), "clear rcvtimeo"))
+		goto cleanup;
+	if (!ASSERT_OK(shutdown(clien, SHUT_WR), "client shutdown"))
+		goto cleanup;
+
+	/*
+	 * Make sure the server has seen the client FIN before it closes,
+	 * so the two FINs never cross.
+	 */
+	n = recv(accept_serv, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(n, 0, "server recv EOF"))
+		goto cleanup;
+
+	close(accept_serv);
+	accept_serv = -1;
+
+	/* block until return EOF */
+	n = recv(clien, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(n, 0, "client recv EOF"))
+		goto cleanup;
+
+	/* Run iterator program that destroys the timewait client sock. */
+	skel->bss->tw_found = 0;
+	start_iter_sockets(skel->progs.iter_tcp6_timewait);
+	if (!ASSERT_EQ(skel->bss->tw_found, 1, "timewait sock found"))
+		goto cleanup;
+
+	ASSERT_OK(skel->bss->tw_destroy_err, "destroy timewait sock");
+
+	/* The destroyed timewait sock must be gone. */
+	skel->bss->tw_found = 0;
+	start_iter_sockets(skel->progs.iter_tcp6_timewait);
+	ASSERT_EQ(skel->bss->tw_found, 0, "timewait sock destroyed");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
 static void test_udp_client(struct sock_destroy_prog *skel)
 {
 	int serv = -1, clien = -1, n = 0;
@@ -204,6 +321,10 @@ void test_sock_destroy(void)
 		test_tcp_client(skel);
 	if (test__start_subtest("tcp_server"))
 		test_tcp_server(skel);
+	if (test__start_subtest("tcp_listen_pending"))
+		test_tcp_listen_pending(skel);
+	if (test__start_subtest("tcp_timewait"))
+		test_tcp_timewait(skel);
 	if (test__start_subtest("udp_client"))
 		test_udp_client(skel);
 	if (test__start_subtest("udp_server"))
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index 5c3579438427..e368370262c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -54,6 +54,8 @@ static struct {
 	{ "lock_global_sleepable_helper_subprog", "global function calls are not allowed while holding a lock" },
 	{ "lock_global_sleepable_kfunc_subprog", "global function calls are not allowed while holding a lock" },
 	{ "lock_global_sleepable_subprog_indirect", "global function calls are not allowed while holding a lock" },
+	{ "callback_value_lock_identity", "bpf_spin_unlock of different lock" },
+	{ "callback_inner_map_value_lock_identity", "bpf_spin_unlock of different lock" },
 };
 
 static int match_regex(const char *pattern, const char *string)
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail_pmtu.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail_pmtu.c
new file mode 100644
index 000000000000..7acdbd5757a9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail_pmtu.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <netinet/tcp.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_tc_change_tail_pmtu.skel.h"
+
+#define CLIENT_NS	"tc-change-tail-cli-ns"
+#define SERVER_NS	"tc-change-tail-srv-ns"
+#define CLIENT_IP	"192.168.1.1"
+#define SERVER_IP	"192.168.1.2"
+
+#define TEST_PMTU	1000
+#define TEST_MSS_MAX	(TEST_PMTU - 20 - 20)
+#define TIMEOUT_MS	3000
+#define XFER_BYTES	8192
+
+void test_tc_change_tail_pmtu(void)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
+	int mss_before = 0, mss_after = 0, ifindex, port;
+	int srv_fd = -1, srv_conn_fd = -1, cli_fd = -1;
+	struct test_tc_change_tail_pmtu *skel = NULL;
+	struct nstoken *nstoken = NULL;
+	static char buf[XFER_BYTES];
+	socklen_t optlen;
+	ssize_t bytes;
+	size_t total;
+
+	if (!ASSERT_OK(make_netns(CLIENT_NS), "make client ns"))
+		return;
+	if (!ASSERT_OK(make_netns(SERVER_NS), "make server ns"))
+		goto out_client_ns;
+
+	nstoken = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open client ns"))
+		goto out;
+	SYS(out, "ip link add veth1 type veth peer name veth2 netns " SERVER_NS);
+	SYS(out, "ip -4 addr add " CLIENT_IP "/24 dev veth1");
+	SYS(out, "ip link set veth1 up");
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex"))
+		goto out;
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	nstoken = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open server ns"))
+		goto out;
+	SYS(out, "ip -4 addr add " SERVER_IP "/24 dev veth2");
+	SYS(out, "ip link set veth2 up");
+	srv_fd = start_server(AF_INET, SOCK_STREAM, SERVER_IP, 0, TIMEOUT_MS);
+	if (!ASSERT_OK_FD(srv_fd, "start server"))
+		goto out;
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	skel = test_tc_change_tail_pmtu__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto out;
+
+	port = get_socket_local_port(srv_fd);
+	if (!ASSERT_GE(port, 0, "get server port"))
+		goto out;
+
+	skel->bss->server_port = port;
+	skel->bss->pmtu = TEST_PMTU;
+
+	nstoken = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open client ns"))
+		goto out;
+
+	skel->links.change_tail_icmp =
+		bpf_program__attach_tcx(skel->progs.change_tail_icmp, ifindex,
+					&tcx_opts);
+	if (!ASSERT_OK_PTR(skel->links.change_tail_icmp, "attach tcx"))
+		goto out;
+
+	cli_fd = connect_to_fd(srv_fd, TIMEOUT_MS);
+	if (!ASSERT_OK_FD(cli_fd, "connect to server"))
+		goto out;
+	srv_conn_fd = accept(srv_fd, NULL, NULL);
+	if (!ASSERT_OK_FD(srv_conn_fd, "accept connection"))
+		goto out;
+	if (!ASSERT_OK(settimeo(srv_conn_fd, TIMEOUT_MS), "set server timeout"))
+		goto out;
+
+	optlen = sizeof(mss_before);
+	if (!ASSERT_OK(getsockopt(cli_fd, IPPROTO_TCP, TCP_MAXSEG, &mss_before,
+				  &optlen), "get mss before"))
+		goto out;
+
+	bytes = send(cli_fd, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(bytes, (ssize_t)sizeof(buf), "send data"))
+		goto out;
+
+	for (total = 0; total < sizeof(buf); total += bytes) {
+		bytes = recv(srv_conn_fd, buf, sizeof(buf), 0);
+		if (bytes <= 0)
+			break;
+	}
+
+	ASSERT_EQ(total, sizeof(buf), "receive data");
+	ASSERT_OK(skel->data->change_tail_ret, "change tail");
+	ASSERT_OK(skel->bss->adjust_room_ret, "adjust room");
+	ASSERT_TRUE(skel->bss->icmp_sent, "icmp sent");
+
+	optlen = sizeof(mss_after);
+	if (!ASSERT_OK(getsockopt(cli_fd, IPPROTO_TCP, TCP_MAXSEG, &mss_after,
+				  &optlen), "get mss after"))
+		goto out;
+
+	ASSERT_LT(mss_after, mss_before, "mss reduced");
+	ASSERT_LE(mss_after, TEST_MSS_MAX, "mss below pmtu");
+out:
+	close(srv_conn_fd);
+	close(cli_fd);
+	close(srv_fd);
+	test_tc_change_tail_pmtu__destroy(skel);
+	close_netns(nstoken);
+	remove_netns(SERVER_NS);
+out_client_ns:
+	remove_netns(CLIENT_NS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 64ac49ad67e6..8b439e194bcc 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -23,6 +23,7 @@
 #include "verifier_bpf_trap.skel.h"
 #include "verifier_bswap.skel.h"
 #include "verifier_btf_ctx_access.skel.h"
+#include "verifier_btf_flex_array.skel.h"
 #include "verifier_btf_unreliable_prog.skel.h"
 #include "verifier_call_large_imm.skel.h"
 #include "verifier_cfg.skel.h"
@@ -53,6 +54,7 @@
 #include "verifier_iterating_callbacks.skel.h"
 #include "verifier_jeq_infer_not_null.skel.h"
 #include "verifier_jit_convergence.skel.h"
+#include "verifier_kfunc_perfmon.skel.h"
 #include "verifier_ld_ind.skel.h"
 #include "verifier_ldsx.skel.h"
 #include "verifier_leak_ptr.skel.h"
@@ -186,6 +188,7 @@ void test_verifier_bpf_get_stack(void)        { RUN(verifier_bpf_get_stack); }
 void test_verifier_bpf_trap(void)             { RUN(verifier_bpf_trap); }
 void test_verifier_bswap(void)                { RUN(verifier_bswap); }
 void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
+void test_verifier_btf_flex_array(void)       { RUN(verifier_btf_flex_array); }
 void test_verifier_btf_unreliable_prog(void)  { RUN(verifier_btf_unreliable_prog); }
 void test_verifier_call_large_imm(void)       { RUN(verifier_call_large_imm); }
 void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
@@ -216,6 +219,7 @@ void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
 void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
 void test_verifier_jit_convergence(void)      { RUN(verifier_jit_convergence); }
+void test_verifier_kfunc_perfmon(void)        { RUN(verifier_kfunc_perfmon); }
 void test_verifier_load_acquire(void)         { RUN(verifier_load_acquire); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
 void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index e0745b6e467e..b668ebd61fc7 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_success.c
@@ -10,6 +10,7 @@
 #include "errno.h"
 
 #define PAGE_SIZE_64K 65536
+#define TEST_SKB_LINEAR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr))
 
 char _license[] SEC("license") = "GPL";
 
@@ -211,6 +212,25 @@ int test_dynptr_skb_data(struct __sk_buff *skb)
 	return 1;
 }
 
+SEC("?tc")
+int test_dynptr_skb_slice_non_linear(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	void *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* Ensure we cannot read past the end of the buffer. */
+	data = bpf_dynptr_slice(&ptr, TEST_SKB_LINEAR_SIZE + 1, NULL, 1);
+	if (data)
+		err = 2;
+
+	return 1;
+}
+
 SEC("?tc")
 int test_dynptr_skb_meta_data(struct __sk_buff *skb)
 {
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
index c8d716fbd419..91c81971e58c 100644
--- a/tools/testing/selftests/bpf/progs/exceptions.c
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -212,6 +212,36 @@ int exception_throw_subprog(struct __sk_buff *ctx)
 	return 0;
 }
 
+u64 exception_cb_stack_src = 0x1234;
+
+/*
+ * The address handed to the helper has to be this callback's own stack
+ * slot, not one from a frame that is already gone.
+ */
+__noinline int exception_cb_stack(u64 cookie)
+{
+	volatile u64 val = 0xdead;
+
+	bpf_probe_read_kernel((void *)&val, sizeof(val), &exception_cb_stack_src);
+	return val;
+}
+
+/* Throws from a subprogram that has a stack of its own. */
+__noinline static int throwing_subprog_stack(struct __sk_buff *ctx)
+{
+	volatile u64 pad[4] = {};
+
+	bpf_throw(pad[0]);
+	return 0;
+}
+
+SEC("tc")
+__exception_cb(exception_cb_stack)
+int exception_throw_subprog_stack_cb(struct __sk_buff *ctx)
+{
+	return throwing_subprog_stack(ctx);
+}
+
 __noinline int assert_nz_gfunc(u64 c)
 {
 	volatile u64 cookie = c;
diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c
index 646026430e9b..e5bb9fe6d5e5 100644
--- a/tools/testing/selftests/bpf/progs/iters_state_safety.c
+++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c
@@ -52,6 +52,28 @@ int create_and_destroy(void *ctx)
 	return 0;
 }
 
+/* fp+0 is not a stack slot. bpf_get_spi(0) used to alias spi 0 (fp-8). */
+SEC("?raw_tp")
+__failure __msg("cannot pass in iter at an offset=0")
+int destroy_fp0_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile ("r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* r10 is fp+0, one byte above the top of the BPF stack */
+		"r1 = r10;"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
 SEC("?raw_tp")
 __failure __msg("Unreleased reference id=1")
 int create_and_forget_to_destroy_fail(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
index 9e0bf7a54cec..0a8887543218 100644
--- a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
+++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
@@ -7,6 +7,8 @@
 #include "bpf_tracing_net.h"
 
 __be16 serv_port = 0;
+int tw_found = 0;
+int tw_destroy_err = 0;
 
 int bpf_sock_destroy(struct sock_common *sk) __ksym;
 
@@ -100,6 +102,34 @@ int iter_tcp6_server(struct bpf_iter__tcp *ctx)
 	return 0;
 }
 
+SEC("iter/tcp")
+int iter_tcp6_timewait(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	__u64 *val;
+	int key = 0;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	if (!bpf_skc_to_tcp_timewait_sock(sk_common))
+		return 0;
+
+	val = bpf_map_lookup_elem(&tcp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* The timewait sock inherits the cookie of the closed client sock. */
+	if (bpf_get_socket_cookie(sk_common) != *val)
+		return 0;
+
+	tw_found++;
+	tw_destroy_err = bpf_sock_destroy(sk_common);
+
+	return 0;
+}
 
 SEC("iter/udp")
 int iter_udp6_client(struct bpf_iter__udp *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
index f678ee6bd7ea..55282f20fa32 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
@@ -14,17 +14,18 @@ struct array_map {
 	__type(key, int);
 	__type(value, struct foo);
 	__uint(max_entries, 1);
-} array_map SEC(".maps");
+} array_map SEC(".maps"), array_map_b SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
-	__uint(max_entries, 1);
+	__uint(max_entries, 2);
 	__type(key, int);
 	__type(value, int);
 	__array(values, struct array_map);
 } map_of_maps SEC(".maps") = {
 	.values = {
 		[0] = &array_map,
+		[1] = &array_map_b,
 	},
 };
 
@@ -314,4 +315,66 @@ int lock_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
 	return ret;
 }
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, struct foo);
+} callback_array_map SEC(".maps");
+
+struct callback_ctx {
+	struct foo *value;
+};
+
+static long lock_different_value(struct bpf_map *map, int *key,
+				 struct foo *value, struct callback_ctx *ctx)
+{
+	bpf_spin_lock(&value->lock);
+	bpf_spin_unlock(&ctx->value->lock);
+	return 0;
+}
+
+static long nest_lock_different_value(struct bpf_map *map, int *key,
+				      struct foo *value, void *data)
+{
+	struct callback_ctx ctx = { .value = value };
+
+	bpf_for_each_map_elem(&callback_array_map, lock_different_value, &ctx, 0);
+	return 0;
+}
+
+SEC("?tc")
+int callback_value_lock_identity(void *ctx)
+{
+	bpf_for_each_map_elem(&callback_array_map, nest_lock_different_value, NULL, 0);
+	return 0;
+}
+
+static long nest_lock_different_inner_value(struct bpf_map *map, int *key,
+					    struct foo *value, void *data)
+{
+	struct callback_ctx ctx = { .value = value };
+	int inner_key = 1;
+	void *inner_map;
+
+	inner_map = bpf_map_lookup_elem(&map_of_maps, &inner_key);
+	if (!inner_map)
+		return 0;
+	bpf_for_each_map_elem(inner_map, lock_different_value, &ctx, 0);
+	return 0;
+}
+
+SEC("?tc")
+int callback_inner_map_value_lock_identity(void *ctx)
+{
+	int inner_key = 0;
+	void *inner_map;
+
+	inner_map = bpf_map_lookup_elem(&map_of_maps, &inner_key);
+	if (!inner_map)
+		return 0;
+	bpf_for_each_map_elem(inner_map, nest_lock_different_inner_value, NULL, 0);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail_pmtu.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail_pmtu.c
new file mode 100644
index 000000000000..5c4c07545bc9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail_pmtu.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdbool.h>
+#include <stddef.h>
+
+#include <linux/bpf.h>
+#include <linux/icmp.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define ICMP_SAMPLE_LEN	(sizeof(struct iphdr) + 8)
+#define ICMP_HDRS_LEN	(sizeof(struct iphdr) + sizeof(struct icmphdr))
+
+__be16 server_port = 0;
+__u16 pmtu = 0;
+
+long change_tail_ret = 1;
+long adjust_room_ret = 0;
+bool icmp_sent = false;
+bool icmp_err = false;
+
+static __always_inline __sum16 csum_fold(__wsum csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+
+	return (__sum16)~csum;
+}
+
+SEC("tc/egress")
+int change_tail_icmp(struct __sk_buff *skb)
+{
+	__u8 smac[ETH_ALEN], dmac[ETH_ALEN];
+	void *data, *data_end;
+	struct icmphdr *icmp;
+	struct ethhdr *eth;
+	struct tcphdr *tcp;
+	__be32 saddr, daddr;
+	struct iphdr *ip;
+	__wsum csum;
+
+	if (icmp_sent || icmp_err)
+		return TCX_PASS;
+
+	data = (void *)(long)skb->data;
+	data_end = (void *)(long)skb->data_end;
+
+	eth = data;
+	if ((void *)(eth + 1) > data_end)
+		return TCX_PASS;
+	if (eth->h_proto != bpf_htons(ETH_P_IP))
+		return TCX_PASS;
+
+	ip = (void *)(eth + 1);
+	if ((void *)(ip + 1) > data_end)
+		return TCX_PASS;
+	if (ip->ihl != 5 || ip->protocol != IPPROTO_TCP)
+		return TCX_PASS;
+
+	tcp = (void *)(ip + 1);
+	if ((void *)(tcp + 1) > data_end)
+		return TCX_PASS;
+	if (tcp->dest != server_port)
+		return TCX_PASS;
+	if (bpf_ntohs(ip->tot_len) <= sizeof(*ip) + tcp->doff * 4)
+		return TCX_PASS;
+
+	__builtin_memcpy(smac, eth->h_source, ETH_ALEN);
+	__builtin_memcpy(dmac, eth->h_dest, ETH_ALEN);
+	saddr = ip->saddr;
+	daddr = ip->daddr;
+
+	change_tail_ret = bpf_skb_change_tail(skb, ETH_HLEN + ICMP_SAMPLE_LEN, 0);
+	if (change_tail_ret) {
+		icmp_err = true;
+		return TCX_PASS;
+	}
+
+	adjust_room_ret = bpf_skb_adjust_room(skb, ICMP_HDRS_LEN,
+					      BPF_ADJ_ROOM_MAC,
+					      BPF_F_ADJ_ROOM_NO_CSUM_RESET);
+	if (adjust_room_ret) {
+		icmp_err = true;
+		return TCX_DROP;
+	}
+
+	data = (void *)(long)skb->data;
+	data_end = (void *)(long)skb->data_end;
+
+	eth = data;
+	ip = (void *)(eth + 1);
+	icmp = (void *)(ip + 1);
+	if ((void *)icmp + sizeof(*icmp) + ICMP_SAMPLE_LEN > data_end) {
+		icmp_err = true;
+		return TCX_DROP;
+	}
+
+	__builtin_memcpy(eth->h_dest, smac, ETH_ALEN);
+	__builtin_memcpy(eth->h_source, dmac, ETH_ALEN);
+
+	__builtin_memset(icmp, 0, sizeof(*icmp));
+	icmp->type = ICMP_DEST_UNREACH;
+	icmp->code = ICMP_FRAG_NEEDED;
+	icmp->un.frag.mtu = bpf_htons(pmtu);
+
+	__builtin_memset(ip, 0, sizeof(*ip));
+	ip->version = 4;
+	ip->ihl = 5;
+	ip->ttl = 64;
+	ip->protocol = IPPROTO_ICMP;
+	ip->tot_len = bpf_htons(ICMP_HDRS_LEN + ICMP_SAMPLE_LEN);
+	ip->saddr = daddr;
+	ip->daddr = saddr;
+
+	csum = bpf_csum_diff(NULL, 0, (__be32 *)icmp,
+			     sizeof(*icmp) + ICMP_SAMPLE_LEN, 0);
+	icmp->checksum = csum_fold(csum);
+	csum = bpf_csum_diff(NULL, 0, (__be32 *)ip, sizeof(*ip), 0);
+	ip->check = csum_fold(csum);
+	icmp_sent = true;
+	return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c
index 815f342eb4b0..3e33766547c0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_arena.c
+++ b/tools/testing/selftests/bpf/progs/verifier_arena.c
@@ -561,6 +561,55 @@ int arena_ptr_add_arena_ptr(void *ctx)
 	return 0;
 }
 
+SEC("syscall")
+__failure __msg("same insn cannot be used with and without arena pointer")
+int mixed_arena_scalar_alu64_scalar_first(void *ctx)
+{
+	volatile register __u64 reg asm("r3");
+	__u32 pick_arena = bpf_get_prandom_u32();
+
+	reg = 1ULL << 32;
+
+	if (pick_arena) {
+		asm volatile (
+			"r9 = %[arena] ll;"
+			"%[reg] = 0;"
+			"%[reg] = addr_space_cast(%[reg], 0x0, 0x1);"
+			: [reg] "=r"(reg)
+			: __imm_addr(arena)
+			: "r9"
+		);
+	}
+
+	reg += 1;
+
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("same insn cannot be used with and without arena pointer")
+int mixed_arena_scalar_alu64_arena_first(void *ctx)
+{
+	volatile register __u64 reg asm("r3");
+	__u32 pick_scalar = bpf_get_prandom_u32();
+
+	asm volatile (
+		"r9 = %[arena] ll;"
+		"%[reg] = 0;"
+		"%[reg] = addr_space_cast(%[reg], 0x0, 0x1);"
+		: [reg] "=r"(reg)
+		: __imm_addr(arena)
+		: "r9"
+	);
+
+	if (pick_scalar)
+		reg = 1ULL << 32;
+
+	reg += 1;
+
+	return 0;
+}
+
 SEC("syscall")
 __success __retval(0)
 int scalar_xor_arena_ptr(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
index e0926767bbd3..1b653bfb63eb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
+++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
@@ -9,6 +9,11 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
 /* Timer tests */
 
 struct timer_elem {
@@ -164,6 +169,7 @@ int syscall_btf_find_prog(void *ctx)
 
 struct wq_elem {
 	struct bpf_wq w;
+	struct task_struct __kptr *task;
 };
 
 struct {
@@ -217,6 +223,106 @@ int wq_sleepable_prog(void *ctx)
 	return 0;
 }
 
+__noinline int wq_global_acquire(void)
+{
+	struct task_struct *task, *acquired;
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	task = val->task;
+	if (!task)
+		return 0;
+
+	acquired = bpf_task_acquire(task);
+	if (acquired)
+		bpf_task_release(acquired);
+	return 0;
+}
+
+static int wq_global_rcu_cb(void *map, int *key, void *value)
+{
+	wq_global_acquire();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__failure __msg("R1 must be a rcu pointer")
+int wq_global_rcu_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_rcu_cb, 0);
+	return 0;
+}
+
+static int wq_global_rcu_lock_cb(void *map, int *key, void *value)
+{
+	bpf_rcu_read_lock();
+	wq_global_acquire();
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success
+int wq_global_rcu_lock_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	/* Verify the same global subprog in non-sleepable and protected contexts. */
+	wq_global_acquire();
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_rcu_lock_cb, 0);
+	return 0;
+}
+
+__weak __noinline int wq_global_no_rcu(void)
+{
+	return 0;
+}
+
+static int wq_global_no_rcu_cb(void *map, int *key, void *value)
+{
+	wq_global_no_rcu();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success __log_level(4)
+__msg("subprog {{[0-9]+}} (wq_global_no_rcu) global insns_self 4 insns_total 4 stack 0")
+int wq_global_no_rcu_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	/* Verify the same global in non-sleepable and unprotected contexts. */
+	wq_global_no_rcu();
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_no_rcu_cb, 0);
+	return 0;
+}
+
 /* Task work tests */
 
 struct task_work_elem {
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_flex_array.c b/tools/testing/selftests/bpf/progs/verifier_btf_flex_array.c
new file mode 100644
index 000000000000..59b84261f622
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_flex_array.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct test_empty_event {};
+
+struct test_flex_batch {
+	int nr;
+	struct test_empty_event events[];
+};
+
+struct map_value {
+	struct test_flex_batch __kptr *batch;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} batches SEC(".maps");
+
+SEC("syscall")
+__description("btf walk into flexible array of zero-sized elements")
+__failure __msg("access beyond struct test_flex_batch at off 4 size 1")
+int stash_and_peek(void *ctx)
+{
+	struct test_flex_batch *b, *old;
+	struct map_value *v;
+	int key = 0;
+
+	v = bpf_map_lookup_elem(&batches, &key);
+	if (!v)
+		return 0;
+
+	b = bpf_obj_new(struct test_flex_batch);
+	if (!b)
+		return 0;
+	b->nr = 1;
+
+	old = bpf_kptr_xchg(&v->batch, b);
+	if (old)
+		bpf_obj_drop(old);
+
+	b = v->batch;
+	if (!b)
+		return 0;
+
+	return b->nr + *(char *)&b->events[0];
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
index a3d2af8dc839..dcc2dd46751a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -350,4 +350,57 @@ int anything_to_untrusted_mem(void *ctx)
 	return 0;
 }
 
+struct pkt_arg {
+	__u64 x;
+	__u8 pad[56];
+};
+
+__weak int subprog_pkt_ptr_no_change(struct pkt_arg *p)
+{
+	if (!p)
+		return 0;
+
+	return p->x;
+}
+
+SEC("?tc")
+__success
+int pkt_ptr_to_global_mem_arg_no_change(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	void *data_end = (void *)(long)skb->data_end;
+	struct pkt_arg *p = data;
+
+	if ((void *)(p + 1) > data_end)
+		return 0;
+
+	return subprog_pkt_ptr_no_change(p);
+}
+
+__weak int subprog_pkt_ptr_changes_data(struct __sk_buff *skb __arg_ctx,
+					struct pkt_arg *p)
+{
+	if (!p)
+		return 0;
+
+	bpf_skb_pull_data(skb, 0);
+	return p->x;
+}
+
+SEC("?tc")
+__failure __log_level(2)
+__msg("R2 is a packet pointer, but func#{{[0-9]+}} may change packet data")
+__msg("Caller passes invalid args into func#{{[0-9]+}} ('subprog_pkt_ptr_changes_data')")
+int pkt_ptr_to_global_mem_arg_changes_data(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	void *data_end = (void *)(long)skb->data_end;
+	struct pkt_arg *p = data;
+
+	if ((void *)(p + 1) > data_end)
+		return 0;
+
+	return subprog_pkt_ptr_changes_data(skb, p);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotox.c b/tools/testing/selftests/bpf/progs/verifier_gotox.c
index 5b18c9a27717..0e27c2c79c57 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotox.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotox.c
@@ -47,6 +47,54 @@ DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_src_reg,      BPF_REG_1, 0, 0, __fa
 DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_off, BPF_REG_0, 1, 0, __failure __msg("BPF_JA|BPF_X uses reserved fields"))
 DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_imm, BPF_REG_0, 0, 1, __failure __msg("BPF_JA|BPF_X uses reserved fields"))
 
+#define DEFINE_TERMINAL_GOTOX_PROG(NAME, BASE)			\
+	__naked void NAME(void)					\
+	{							\
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:							\
+	.quad ret0_%= - " BASE ";				\
+	.size jt0_%=, 8;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	goto end_%=;						\
+ret0_%=:							\
+	r0 = 0;							\
+	exit;							\
+end_%=:							\
+	.8byte %[gotox_r0];					\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X,	\
+					    BPF_REG_0, 0, 0, 0))	\
+	: __clobber_all);					\
+	}
+
+SEC("socket")
+__success __retval(0)
+DEFINE_TERMINAL_GOTOX_PROG(jump_table_terminal_gotox, "socket")
+
+static __noinline __used
+DEFINE_TERMINAL_GOTOX_PROG(terminal_gotox_subprog1, ".text")
+
+static __noinline __used int terminal_gotox_subprog2(void)
+{
+	return 0;
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void jump_table_terminal_gotox_subprog(void)
+{
+	asm volatile ("						\
+	call terminal_gotox_subprog1;				\
+	call terminal_gotox_subprog2;				\
+	exit;							\
+"	::: __clobber_all);
+}
+
 /*
  * Gotox is forbidden when there is no jump table loaded
  * which points to the sub-function where the gotox is used
diff --git a/tools/testing/selftests/bpf/progs/verifier_kfunc_perfmon.c b/tools/testing/selftests/bpf/progs/verifier_kfunc_perfmon.c
new file mode 100644
index 000000000000..76c39ef30e96
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_kfunc_perfmon.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+void *user_ptr;
+char dynptr_buf[8];
+u64 kaddr;
+
+extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym;
+
+SEC("socket")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv
+__msg_unpriv("bpf_rdonly_cast is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+int rdonly_cast_noperfmon(void *ctx)
+{
+	char *p = bpf_rdonly_cast(0, 0);
+
+	return p[0x7fff];
+}
+
+SEC("socket")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv
+__msg_unpriv("bpf_probe_read_kernel_dynptr is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+int probe_read_kernel_dynptr_noperfmon(void *ctx)
+{
+	struct bpf_dynptr dptr;
+
+	bpf_dynptr_from_mem(dynptr_buf, sizeof(dynptr_buf), 0, &dptr);
+	bpf_probe_read_kernel_dynptr(&dptr, 0, sizeof(dynptr_buf), user_ptr);
+	return 0;
+}
+
+SEC("socket")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv
+__msg_unpriv("bpf_stream_vprintk is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+int stream_vprintk_noperfmon(void *ctx)
+{
+	bpf_stream_printk(BPF_STDOUT, "%pB", (void *)kaddr);
+	return 0;
+}
+
+SEC("socket")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv
+__msg_unpriv("bpf_get_kmem_cache is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+int get_kmem_cache_noperfmon(void *ctx)
+{
+	return !!bpf_get_kmem_cache(kaddr);
+}
+
+__weak int subprog_untrusted_read(void *p __arg_untrusted)
+{
+	return *(char *)p;
+}
+
+SEC("socket")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv
+__msg_unpriv("rdonly_untrusted_mem access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+int arg_untrusted_read_noperfmon(void *ctx)
+{
+	return subprog_untrusted_read(0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index d248ce877f14..48a966cda199 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -303,4 +303,40 @@ __naked void maybe_exit_scc_bug1(void)
 	::: __clobber_all);
 }
 
+/*
+ * The loop reads zero from the caller's stack on its first iteration and
+ * one from the callee's stack on its second iteration. At the loop header,
+ * only the frame number of the pointer in r1 changes.
+ */
+static __naked __noinline __used
+void loop_stack_frames_reg(void)
+{
+	asm volatile (
+	"*(u64 *)(r10 - 8) = 1;"
+"1:"
+	"r0 = *(u64 *)(r1 + 0);"
+	"if r0 != 0 goto 2f;"
+	"r1 = r10;"
+	"r1 += -8;"
+	"goto 1b;"
+"2:"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("bounded loop changing stack frame in a register")
+__success __retval(1)
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void bounded_loop_stack_frames_reg(void)
+{
+	asm volatile (
+	"*(u64 *)(r10 - 8) = 0;"
+	"r1 = r10;"
+	"r1 += -8;"
+	"call loop_stack_frames_reg;"
+	"exit;"
+	::: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
index 4f2f3209eec8..bf9f6fb6582c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -88,6 +88,44 @@ l0_%=:	r0 = *(u32*)(r1 + %[bpf_sock_family]);		\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("skb->sk: sk->rx_queue_mapping [no sign extension]")
+__success __success_unpriv __retval(0)
+__naked void sk_rx_queue_mapping_no_sign_ext(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0xdead;					\
+	exit;						\
+l0_%=:	r0 = *(u32*)(r1 + %[bpf_sock_rx_queue_mapping]);	\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_rx_queue_mapping, offsetof(struct bpf_sock, rx_queue_mapping))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("skb->sk: sk->rx_queue_mapping [narrow load mask]")
+__success __success_unpriv __retval(0)
+__naked void sk_rx_queue_mapping_narrow_load_mask(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0xdead;					\
+	exit;						\
+l0_%=:	r0 = *(u16*)(r1 + %[bpf_sock_rx_queue_mapping]);	\
+	r0 >>= 16;					\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_rx_queue_mapping, offsetof(struct bpf_sock, rx_queue_mapping))
+	: __clobber_all);
+}
+
 SEC("cgroup/skb")
 __description("skb->sk: sk->type [fullsock field]")
 __failure __msg("invalid sock_common access")
diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c
index 0b86d95a4133..9866bc154194 100644
--- a/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c
@@ -1719,4 +1719,39 @@ l0_%=:	r0 = 0;						\
 	: __clobber_all);
 }
 
+SEC("xdp")
+__description("XDP pkt regsafe preserves packet pointer class displacement")
+__failure __msg("R2 min value is outside of the allowed memory range")
+__flag(BPF_F_ANY_ALIGNMENT) __flag(BPF_F_TEST_STATE_FREQ)
+__naked void pkt_regsafe_class_displacement(void)
+{
+	asm volatile ("					\
+	r8 = *(u32 *)(r1 + %[xdp_md_data_end]);		\
+	r9 = *(u32 *)(r1 + %[xdp_md_data]);		\
+	r4 = *(u32 *)(r1 + %[xdp_md_rx_queue_index]);	\
+	r4 &= 15;					\
+	r0 = *(u32 *)(r1 + %[xdp_md_ingress_ifindex]);	\
+	if r0 != 0 goto l0_%=;				\
+	r2 = r9;					\
+	r2 += r4;					\
+	r3 = r2;					\
+	r3 += 8;					\
+	goto l1_%=;					\
+l0_%=:	r4 &= 3;					\
+	r4 += 8;					\
+	r2 = r9;					\
+	r2 += r4;					\
+	r3 = r2;					\
+l1_%=:	if r3 > r8 goto l2_%=;				\
+	r0 = *(u64 *)(r2 + 0);				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_const(xdp_md_rx_queue_index, offsetof(struct xdp_md, rx_queue_index)),
+	  __imm_const(xdp_md_ingress_ifindex, offsetof(struct xdp_md, ingress_ifindex))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";