Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 1244 insertions, 1257 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890d4c4bf9..19e575e6b7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -195,6 +195,8 @@ struct bpf_verifier_stack_elem {
 					  POISON_POINTER_DELTA))
 #define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
 
+#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE  512
+
 static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
 static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
 static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
@@ -339,30 +341,14 @@ struct bpf_kfunc_call_arg_meta {
 
 struct btf *btf_vmlinux;
 
-static DEFINE_MUTEX(bpf_verifier_lock);
-static DEFINE_MUTEX(bpf_percpu_ma_lock);
-
-static const struct bpf_line_info *
-find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+static const char *btf_type_name(const struct btf *btf, u32 id)
 {
-	const struct bpf_line_info *linfo;
-	const struct bpf_prog *prog;
-	u32 i, nr_linfo;
-
-	prog = env->prog;
-	nr_linfo = prog->aux->nr_linfo;
-
-	if (!nr_linfo || insn_off >= prog->len)
-		return NULL;
-
-	linfo = prog->aux->linfo;
-	for (i = 1; i < nr_linfo; i++)
-		if (insn_off < linfo[i].insn_off)
-			break;
-
-	return &linfo[i - 1];
+	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
+static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
+
 __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 {
 	struct bpf_verifier_env *env = private_data;
@@ -376,73 +362,25 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
-static const char *ltrim(const char *s)
-{
-	while (isspace(*s))
-		s++;
-
-	return s;
-}
-
-__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
-					 u32 insn_off,
-					 const char *prefix_fmt, ...)
-{
-	const struct bpf_line_info *linfo;
-
-	if (!bpf_verifier_log_needed(&env->log))
-		return;
-
-	linfo = find_linfo(env, insn_off);
-	if (!linfo || linfo == env->prev_linfo)
-		return;
-
-	if (prefix_fmt) {
-		va_list args;
-
-		va_start(args, prefix_fmt);
-		bpf_verifier_vlog(&env->log, prefix_fmt, args);
-		va_end(args);
-	}
-
-	verbose(env, "%s\n",
-		ltrim(btf_name_by_offset(env->prog->aux->btf,
-					 linfo->line_off)));
-
-	env->prev_linfo = linfo;
-}
-
 static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 				   struct bpf_reg_state *reg,
-				   struct tnum *range, const char *ctx,
+				   struct bpf_retval_range range, const char *ctx,
 				   const char *reg_name)
 {
-	char tn_buf[48];
+	bool unknown = true;
 
-	verbose(env, "At %s the register %s ", ctx, reg_name);
-	if (!tnum_is_unknown(reg->var_off)) {
-		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "has value %s", tn_buf);
-	} else {
-		verbose(env, "has unknown scalar value");
+	verbose(env, "%s the register %s has", ctx, reg_name);
+	if (reg->smin_value > S64_MIN) {
+		verbose(env, " smin=%lld", reg->smin_value);
+		unknown = false;
 	}
-	tnum_strn(tn_buf, sizeof(tn_buf), *range);
-	verbose(env, " should have been in %s\n", tn_buf);
-}
-
-static bool type_is_pkt_pointer(enum bpf_reg_type type)
-{
-	type = base_type(type);
-	return type == PTR_TO_PACKET ||
-	       type == PTR_TO_PACKET_META;
-}
-
-static bool type_is_sk_pointer(enum bpf_reg_type type)
-{
-	return type == PTR_TO_SOCKET ||
-		type == PTR_TO_SOCK_COMMON ||
-		type == PTR_TO_TCP_SOCK ||
-		type == PTR_TO_XDP_SOCK;
+	if (reg->smax_value < S64_MAX) {
+		verbose(env, " smax=%lld", reg->smax_value);
+		unknown = false;
+	}
+	if (unknown)
+		verbose(env, " unknown scalar value");
+	verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval);
 }
 
 static bool type_may_be_null(u32 type)
@@ -468,16 +406,6 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
 		type == PTR_TO_MEM;
 }
 
-static bool type_is_ptr_alloc_obj(u32 type)
-{
-	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
-}
-
-static bool type_is_non_owning_ref(u32 type)
-{
-	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
-}
-
 static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 {
 	struct btf_record *rec = NULL;
@@ -500,6 +428,31 @@ static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
 	return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
 }
 
+static const char *subprog_name(const struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_func_info *info;
+
+	if (!env->prog->aux->func_info)
+		return "";
+
+	info = &env->prog->aux->func_info[subprog];
+	return btf_type_name(env->prog->aux->btf, info->type_id);
+}
+
+static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_subprog_info *info = subprog_info(env, subprog);
+
+	info->is_cb = true;
+	info->is_async_cb = true;
+	info->is_exception_cb = true;
+}
+
+static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	return subprog_info(env, subprog)->is_exception_cb;
+}
+
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -605,83 +558,6 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 	       insn->imm == BPF_CMPXCHG;
 }
 
-/* string representation of 'enum bpf_reg_type'
- *
- * Note that reg_type_str() can not appear more than once in a single verbose()
- * statement.
- */
-static const char *reg_type_str(struct bpf_verifier_env *env,
-				enum bpf_reg_type type)
-{
-	char postfix[16] = {0}, prefix[64] = {0};
-	static const char * const str[] = {
-		[NOT_INIT]		= "?",
-		[SCALAR_VALUE]		= "scalar",
-		[PTR_TO_CTX]		= "ctx",
-		[CONST_PTR_TO_MAP]	= "map_ptr",
-		[PTR_TO_MAP_VALUE]	= "map_value",
-		[PTR_TO_STACK]		= "fp",
-		[PTR_TO_PACKET]		= "pkt",
-		[PTR_TO_PACKET_META]	= "pkt_meta",
-		[PTR_TO_PACKET_END]	= "pkt_end",
-		[PTR_TO_FLOW_KEYS]	= "flow_keys",
-		[PTR_TO_SOCKET]		= "sock",
-		[PTR_TO_SOCK_COMMON]	= "sock_common",
-		[PTR_TO_TCP_SOCK]	= "tcp_sock",
-		[PTR_TO_TP_BUFFER]	= "tp_buffer",
-		[PTR_TO_XDP_SOCK]	= "xdp_sock",
-		[PTR_TO_BTF_ID]		= "ptr_",
-		[PTR_TO_MEM]		= "mem",
-		[PTR_TO_BUF]		= "buf",
-		[PTR_TO_FUNC]		= "func",
-		[PTR_TO_MAP_KEY]	= "map_key",
-		[CONST_PTR_TO_DYNPTR]	= "dynptr_ptr",
-	};
-
-	if (type & PTR_MAYBE_NULL) {
-		if (base_type(type) == PTR_TO_BTF_ID)
-			strncpy(postfix, "or_null_", 16);
-		else
-			strncpy(postfix, "_or_null", 16);
-	}
-
-	snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
-		 type & MEM_RDONLY ? "rdonly_" : "",
-		 type & MEM_RINGBUF ? "ringbuf_" : "",
-		 type & MEM_USER ? "user_" : "",
-		 type & MEM_PERCPU ? "percpu_" : "",
-		 type & MEM_RCU ? "rcu_" : "",
-		 type & PTR_UNTRUSTED ? "untrusted_" : "",
-		 type & PTR_TRUSTED ? "trusted_" : ""
-	);
-
-	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
-		 prefix, str[base_type(type)], postfix);
-	return env->tmp_str_buf;
-}
-
-static char slot_type_char[] = {
-	[STACK_INVALID]	= '?',
-	[STACK_SPILL]	= 'r',
-	[STACK_MISC]	= 'm',
-	[STACK_ZERO]	= '0',
-	[STACK_DYNPTR]	= 'd',
-	[STACK_ITER]	= 'i',
-};
-
-static void print_liveness(struct bpf_verifier_env *env,
-			   enum bpf_reg_liveness live)
-{
-	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
-	    verbose(env, "_");
-	if (live & REG_LIVE_READ)
-		verbose(env, "r");
-	if (live & REG_LIVE_WRITTEN)
-		verbose(env, "w");
-	if (live & REG_LIVE_DONE)
-		verbose(env, "D");
-}
-
 static int __get_spi(s32 off)
 {
 	return (-off - 1) / BPF_REG_SIZE;
@@ -746,92 +622,6 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 	return stack_slot_obj_get_spi(env, reg, "iter", nr_slots);
 }
 
-static const char *btf_type_name(const struct btf *btf, u32 id)
-{
-	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
-}
-
-static const char *dynptr_type_str(enum bpf_dynptr_type type)
-{
-	switch (type) {
-	case BPF_DYNPTR_TYPE_LOCAL:
-		return "local";
-	case BPF_DYNPTR_TYPE_RINGBUF:
-		return "ringbuf";
-	case BPF_DYNPTR_TYPE_SKB:
-		return "skb";
-	case BPF_DYNPTR_TYPE_XDP:
-		return "xdp";
-	case BPF_DYNPTR_TYPE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown dynptr type %d\n", type);
-		return "<unknown>";
-	}
-}
-
-static const char *iter_type_str(const struct btf *btf, u32 btf_id)
-{
-	if (!btf || btf_id == 0)
-		return "<invalid>";
-
-	/* we already validated that type is valid and has conforming name */
-	return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
-}
-
-static const char *iter_state_str(enum bpf_iter_state state)
-{
-	switch (state) {
-	case BPF_ITER_STATE_ACTIVE:
-		return "active";
-	case BPF_ITER_STATE_DRAINED:
-		return "drained";
-	case BPF_ITER_STATE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown iter state %d\n", state);
-		return "<unknown>";
-	}
-}
-
-static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
-{
-	env->scratched_regs |= 1U << regno;
-}
-
-static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
-{
-	env->scratched_stack_slots |= 1ULL << spi;
-}
-
-static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
-{
-	return (env->scratched_regs >> regno) & 1;
-}
-
-static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
-{
-	return (env->scratched_stack_slots >> regno) & 1;
-}
-
-static bool verifier_state_scratched(const struct bpf_verifier_env *env)
-{
-	return env->scratched_regs || env->scratched_stack_slots;
-}
-
-static void mark_verifier_state_clean(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = 0U;
-	env->scratched_stack_slots = 0ULL;
-}
-
-/* Used for printing the entire verifier state. */
-static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = ~0U;
-	env->scratched_stack_slots = ~0ULL;
-}
-
 static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 {
 	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
@@ -1365,230 +1155,25 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack)
 	       stack->spilled_ptr.type == SCALAR_VALUE;
 }
 
-static void scrub_spilled_slot(u8 *stype)
-{
-	if (*stype != STACK_INVALID)
-		*stype = STACK_MISC;
-}
-
-static void print_scalar_ranges(struct bpf_verifier_env *env,
-				const struct bpf_reg_state *reg,
-				const char **sep)
-{
-	struct {
-		const char *name;
-		u64 val;
-		bool omit;
-	} minmaxs[] = {
-		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
-		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
-		{"umin",   reg->umin_value,         reg->umin_value == 0},
-		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
-		{"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
-		{"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
-		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
-		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
-	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
-	bool neg1, neg2;
-
-	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
-		if (m1->omit)
-			continue;
-
-		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
-
-		verbose(env, "%s%s=", *sep, m1->name);
-		*sep = ",";
-
-		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
-			if (m2->omit || m2->val != m1->val)
-				continue;
-			/* don't mix negatives with positives */
-			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
-			if (neg2 != neg1)
-				continue;
-			m2->omit = true;
-			verbose(env, "%s=", m2->name);
-		}
-
-		verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
-	}
-}
-
-static void print_verifier_state(struct bpf_verifier_env *env,
-				 const struct bpf_func_state *state,
-				 bool print_all)
-{
-	const struct bpf_reg_state *reg;
-	enum bpf_reg_type t;
-	int i;
-
-	if (state->frameno)
-		verbose(env, " frame%d:", state->frameno);
-	for (i = 0; i < MAX_BPF_REG; i++) {
-		reg = &state->regs[i];
-		t = reg->type;
-		if (t == NOT_INIT)
-			continue;
-		if (!print_all && !reg_scratched(env, i))
-			continue;
-		verbose(env, " R%d", i);
-		print_liveness(env, reg->live);
-		verbose(env, "=");
-		if (t == SCALAR_VALUE && reg->precise)
-			verbose(env, "P");
-		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
-		    tnum_is_const(reg->var_off)) {
-			/* reg->off should be 0 for SCALAR_VALUE */
-			verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			verbose(env, "%lld", reg->var_off.value + reg->off);
-		} else {
-			const char *sep = "";
-
-			verbose(env, "%s", reg_type_str(env, t));
-			if (base_type(t) == PTR_TO_BTF_ID)
-				verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
-			verbose(env, "(");
-/*
- * _a stands for append, was shortened to avoid multiline statements below.
- * This macro is used to output a comma separated list of attributes.
+/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which
+ * case they are equivalent, or it's STACK_ZERO, in which case we preserve
+ * more precise STACK_ZERO.
+ * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take
+ * env->allow_ptr_leaks into account and force STACK_MISC, if necessary.
  */
-#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; })
-
-			if (reg->id)
-				verbose_a("id=%d", reg->id);
-			if (reg->ref_obj_id)
-				verbose_a("ref_obj_id=%d", reg->ref_obj_id);
-			if (type_is_non_owning_ref(reg->type))
-				verbose_a("%s", "non_own_ref");
-			if (t != SCALAR_VALUE)
-				verbose_a("off=%d", reg->off);
-			if (type_is_pkt_pointer(t))
-				verbose_a("r=%d", reg->range);
-			else if (base_type(t) == CONST_PTR_TO_MAP ||
-				 base_type(t) == PTR_TO_MAP_KEY ||
-				 base_type(t) == PTR_TO_MAP_VALUE)
-				verbose_a("ks=%d,vs=%d",
-					  reg->map_ptr->key_size,
-					  reg->map_ptr->value_size);
-			if (tnum_is_const(reg->var_off)) {
-				/* Typically an immediate SCALAR_VALUE, but
-				 * could be a pointer whose offset is too big
-				 * for reg->off
-				 */
-				verbose_a("imm=%llx", reg->var_off.value);
-			} else {
-				print_scalar_ranges(env, reg, &sep);
-				if (!tnum_is_unknown(reg->var_off)) {
-					char tn_buf[48];
-
-					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-					verbose_a("var_off=%s", tn_buf);
-				}
-			}
-#undef verbose_a
-
-			verbose(env, ")");
-		}
-	}
-	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		char types_buf[BPF_REG_SIZE + 1];
-		bool valid = false;
-		int j;
-
-		for (j = 0; j < BPF_REG_SIZE; j++) {
-			if (state->stack[i].slot_type[j] != STACK_INVALID)
-				valid = true;
-			types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-		}
-		types_buf[BPF_REG_SIZE] = 0;
-		if (!valid)
-			continue;
-		if (!print_all && !stack_slot_scratched(env, i))
-			continue;
-		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
-		case STACK_SPILL:
-			reg = &state->stack[i].spilled_ptr;
-			t = reg->type;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			if (t == SCALAR_VALUE && reg->precise)
-				verbose(env, "P");
-			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
-				verbose(env, "%lld", reg->var_off.value + reg->off);
-			break;
-		case STACK_DYNPTR:
-			i += BPF_DYNPTR_NR_SLOTS - 1;
-			reg = &state->stack[i].spilled_ptr;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
-			if (reg->ref_obj_id)
-				verbose(env, "(ref_id=%d)", reg->ref_obj_id);
-			break;
-		case STACK_ITER:
-			/* only main slot has ref_obj_id set; skip others */
-			reg = &state->stack[i].spilled_ptr;
-			if (!reg->ref_obj_id)
-				continue;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
-				iter_type_str(reg->iter.btf, reg->iter.btf_id),
-				reg->ref_obj_id, iter_state_str(reg->iter.state),
-				reg->iter.depth);
-			break;
-		case STACK_MISC:
-		case STACK_ZERO:
-		default:
-			reg = &state->stack[i].spilled_ptr;
-
-			for (j = 0; j < BPF_REG_SIZE; j++)
-				types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-			types_buf[BPF_REG_SIZE] = 0;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", types_buf);
-			break;
-		}
-	}
-	if (state->acquired_refs && state->refs[0].id) {
-		verbose(env, " refs=%d", state->refs[0].id);
-		for (i = 1; i < state->acquired_refs; i++)
-			if (state->refs[i].id)
-				verbose(env, ",%d", state->refs[i].id);
-	}
-	if (state->in_callback_fn)
-		verbose(env, " cb");
-	if (state->in_async_callback_fn)
-		verbose(env, " async_cb");
-	verbose(env, "\n");
-	if (!print_all)
-		mark_verifier_state_clean(env);
-}
-
-static inline u32 vlog_alignment(u32 pos)
+static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype)
 {
-	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
-			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+	if (*stype == STACK_ZERO)
+		return;
+	if (env->allow_ptr_leaks && *stype == STACK_INVALID)
+		return;
+	*stype = STACK_MISC;
 }
 
-static void print_insn_state(struct bpf_verifier_env *env,
-			     const struct bpf_func_state *state)
+static void scrub_spilled_slot(u8 *stype)
 {
-	if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
-		/* remove new line character */
-		bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
-		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
-	} else {
-		verbose(env, "%d:", env->insn_idx);
-	}
-	print_verifier_state(env, state, false);
+	if (*stype != STACK_INVALID)
+		*stype = STACK_MISC;
 }
 
 /* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1690,7 +1275,11 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n)
  */
 static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size)
 {
-	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
+	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n;
+
+	/* The stack size is always a multiple of BPF_REG_SIZE. */
+	size = round_up(size, BPF_REG_SIZE);
+	n = size / BPF_REG_SIZE;
 
 	if (old_n >= n)
 		return 0;
@@ -1804,8 +1393,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	int i, err;
 
 	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
-					    src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
-					    GFP_USER);
+					  src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+					  GFP_USER);
 	if (!dst_state->jmp_history)
 		return -ENOMEM;
 	dst_state->jmp_history_cnt = src->jmp_history_cnt;
@@ -2180,10 +1769,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg)
 	__mark_reg_known(reg, 0);
 }
 
-static void __mark_reg_const_zero(struct bpf_reg_state *reg)
+static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
 {
 	__mark_reg_known(reg, 0);
 	reg->type = SCALAR_VALUE;
+	/* all scalars are assumed imprecise initially (unless unprivileged,
+	 * in which case everything is forced to be precise)
+	 */
+	reg->precise = !env->bpf_capable;
 }
 
 static void mark_reg_known_zero(struct bpf_verifier_env *env,
@@ -2349,69 +1942,214 @@ static void __update_reg_bounds(struct bpf_reg_state *reg)
 /* Uses signed min/max values to inform unsigned, and vice-versa */
 static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
 {
-	/* Learn sign from signed bounds.
-	 * If we cannot cross the sign boundary, then signed and unsigned bounds
-	 * are the same, so combine.  This works even in the negative case, e.g.
-	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+	/* If upper 32 bits of u64/s64 range don't change, we can use lower 32
+	 * bits to improve our u32/s32 boundaries.
+	 *
+	 * E.g., the case where we have upper 32 bits as zero ([10, 20] in
+	 * u64) is pretty trivial, it's obvious that in u32 we'll also have
+	 * [10, 20] range. But this property holds for any 64-bit range as
+	 * long as upper 32 bits in that entire range of values stay the same.
+	 *
+	 * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311]
+	 * in decimal) has the same upper 32 bits throughout all the values in
+	 * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15])
+	 * range.
+	 *
+	 * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32,
+	 * following the rules outlined below about u64/s64 correspondence
+	 * (which equally applies to u32 vs s32 correspondence). In general it
+	 * depends on actual hexadecimal values of 32-bit range. They can form
+	 * only valid u32, or only valid s32 ranges in some cases.
+	 *
+	 * So we use all these insights to derive bounds for subregisters here.
 	 */
-	if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
-		reg->s32_min_value = reg->u32_min_value =
-			max_t(u32, reg->s32_min_value, reg->u32_min_value);
-		reg->s32_max_value = reg->u32_max_value =
-			min_t(u32, reg->s32_max_value, reg->u32_max_value);
-		return;
+	if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) {
+		/* u64 to u32 casting preserves validity of low 32 bits as
+		 * a range, if upper 32 bits are the same
+		 */
+		reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value);
+		reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value);
+
+		if ((s32)reg->umin_value <= (s32)reg->umax_value) {
+			reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+			reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+		}
+	}
+	if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) {
+		/* low 32 bits should form a proper u32 range */
+		if ((u32)reg->smin_value <= (u32)reg->smax_value) {
+			reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value);
+			reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value);
+		}
+		/* low 32 bits should form a proper s32 range */
+		if ((s32)reg->smin_value <= (s32)reg->smax_value) {
+			reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+			reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+		}
+	}
+	/* Special case where upper bits form a small sequence of two
+	 * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+	 * 0x00000000 is also valid), while lower bits form a proper s32 range
+	 * going from negative numbers to positive numbers. E.g., let's say we
+	 * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]).
+	 * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff,
+	 * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits,
+	 * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]).
+	 * Note that it doesn't have to be 0xffffffff going to 0x00000000 in
+	 * upper 32 bits. As a random example, s64 range
+	 * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range
+	 * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister.
+	 */
+	if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) &&
+	    (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value);
+	}
+	if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) &&
+	    (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value);
+	}
+	/* if u32 range forms a valid s32 range (due to matching sign bit),
+	 * try to learn from that
+	 */
+	if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) {
+		reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value);
+		reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value);
 	}
-	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
-	 * boundary, so we must be careful.
+	/* If we cannot cross the sign boundary, then signed and unsigned bounds
+	 * are the same, so combine.  This works even in the negative case, e.g.
+	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
 	 */
-	if ((s32)reg->u32_max_value >= 0) {
-		/* Positive.  We can't learn anything from the smin, but smax
-		 * is positive, hence safe.
-		 */
-		reg->s32_min_value = reg->u32_min_value;
-		reg->s32_max_value = reg->u32_max_value =
-			min_t(u32, reg->s32_max_value, reg->u32_max_value);
-	} else if ((s32)reg->u32_min_value < 0) {
-		/* Negative.  We can't learn anything from the smax, but smin
-		 * is negative, hence safe.
-		 */
-		reg->s32_min_value = reg->u32_min_value =
-			max_t(u32, reg->s32_min_value, reg->u32_min_value);
-		reg->s32_max_value = reg->u32_max_value;
+	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+		reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value);
+		reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value);
 	}
 }
 
 static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
 {
-	/* Learn sign from signed bounds.
-	 * If we cannot cross the sign boundary, then signed and unsigned bounds
+	/* If u64 range forms a valid s64 range (due to matching sign bit),
+	 * try to learn from that. Let's do a bit of ASCII art to see when
+	 * this is happening. Let's take u64 range first:
+	 *
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 *
+	 * Valid u64 range is formed when umin and umax are anywhere in the
+	 * range [0, U64_MAX], and umin <= umax. u64 case is simple and
+	 * straightforward. Let's see how s64 range maps onto the same range
+	 * of values, annotated below the line for comparison:
+	 *
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 * 0                        S64_MAX S64_MIN                        -1
+	 *
+	 * So s64 values basically start in the middle and they are logically
+	 * contiguous to the right of it, wrapping around from -1 to 0, and
+	 * then finishing as S64_MAX (0x7fffffffffffffff) right before
+	 * S64_MIN. We can try drawing the continuity of u64 vs s64 values
+	 * more visually as mapped to sign-agnostic range of hex values.
+	 *
+	 *  u64 start                                               u64 end
+	 *  _______________________________________________________________
+	 * /                                                               \
+	 * 0             0x7fffffffffffffff 0x8000000000000000        U64_MAX
+	 * |-------------------------------|--------------------------------|
+	 * 0                        S64_MAX S64_MIN                        -1
+	 *                                / \
+	 * >------------------------------   ------------------------------->
+	 * s64 continues...        s64 end   s64 start          s64 "midpoint"
+	 *
+	 * What this means is that, in general, we can't always derive
+	 * something new about u64 from any random s64 range, and vice versa.
+	 *
+	 * But we can do that in two particular cases. One is when entire
+	 * u64/s64 range is *entirely* contained within left half of the above
+	 * diagram or when it is *entirely* contained in the right half. I.e.:
+	 *
+	 * |-------------------------------|--------------------------------|
+	 *     ^                   ^            ^                 ^
+	 *     A                   B            C                 D
+	 *
+	 * [A, B] and [C, D] are contained entirely in their respective halves
+	 * and form valid contiguous ranges as both u64 and s64 values. [A, B]
+	 * will be non-negative both as u64 and s64 (and in fact it will be
+	 * identical ranges no matter the signedness). [C, D] treated as s64
+	 * will be a range of negative values, while in u64 it will be
+	 * non-negative range of values larger than 0x8000000000000000.
+	 *
+	 * Now, any other range here can't be represented in both u64 and s64
+	 * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid
+	 * contiguous u64 ranges, but they are discontinuous in s64. [B, C]
+	 * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX],
+	 * for example. Similarly, valid s64 range [D, A] (going from negative
+	 * to positive values), would be two separate [D, U64_MAX] and [0, A]
+	 * ranges as u64. Currently reg_state can't represent two segments per
+	 * numeric domain, so in such situations we can only derive maximal
+	 * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64).
+	 *
+	 * So we use these facts to derive umin/umax from smin/smax and vice
+	 * versa only if they stay within the same "half". This is equivalent
+	 * to checking sign bit: lower half will have sign bit as zero, upper
+	 * half have sign bit 1. Below in code we simplify this by just
+	 * casting umin/umax as smin/smax and checking if they form valid
+	 * range, and vice versa. Those are equivalent checks.
+	 */
+	if ((s64)reg->umin_value <= (s64)reg->umax_value) {
+		reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value);
+		reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value);
+	}
+	/* If we cannot cross the sign boundary, then signed and unsigned bounds
 	 * are the same, so combine.  This works even in the negative case, e.g.
 	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
 	 */
-	if (reg->smin_value >= 0 || reg->smax_value < 0) {
-		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
-							  reg->umin_value);
-		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
-							  reg->umax_value);
-		return;
+	if ((u64)reg->smin_value <= (u64)reg->smax_value) {
+		reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value);
+		reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value);
 	}
-	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
-	 * boundary, so we must be careful.
+}
+
+static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg)
+{
+	/* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit
+	 * values on both sides of 64-bit range in hope to have tigher range.
+	 * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from
+	 * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff].
+	 * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound
+	 * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of
+	 * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a
+	 * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff].
+	 * We just need to make sure that derived bounds we are intersecting
+	 * with are well-formed ranges in respecitve s64 or u64 domain, just
+	 * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments.
 	 */
-	if ((s64)reg->umax_value >= 0) {
-		/* Positive.  We can't learn anything from the smin, but smax
-		 * is positive, hence safe.
-		 */
-		reg->smin_value = reg->umin_value;
-		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
-							  reg->umax_value);
-	} else if ((s64)reg->umin_value < 0) {
-		/* Negative.  We can't learn anything from the smax, but smin
-		 * is negative, hence safe.
-		 */
-		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
-							  reg->umin_value);
-		reg->smax_value = reg->umax_value;
+	__u64 new_umin, new_umax;
+	__s64 new_smin, new_smax;
+
+	/* u32 -> u64 tightening, it's always well-formed */
+	new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value;
+	new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value;
+	reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+	reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+	/* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */
+	new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value;
+	new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value;
+	reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+	reg->smax_value = min_t(s64, reg->smax_value, new_smax);
+
+	/* if s32 can be treated as valid u32 range, we can use it as well */
+	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
+		/* s32 -> u64 tightening */
+		new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+		new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+		reg->umin_value = max_t(u64, reg->umin_value, new_umin);
+		reg->umax_value = min_t(u64, reg->umax_value, new_umax);
+		/* s32 -> s64 tightening */
+		new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value;
+		new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value;
+		reg->smin_value = max_t(s64, reg->smin_value, new_smin);
+		reg->smax_value = min_t(s64, reg->smax_value, new_smax);
 	}
 }
 
@@ -2419,6 +2157,7 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg)
 {
 	__reg32_deduce_bounds(reg);
 	__reg64_deduce_bounds(reg);
+	__reg_deduce_mixed_bounds(reg);
 }
 
 /* Attempts to improve var_off based on unsigned min/max information */
@@ -2440,6 +2179,7 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
 	__update_reg_bounds(reg);
 	/* We might have learned something about the sign bit. */
 	__reg_deduce_bounds(reg);
+	__reg_deduce_bounds(reg);
 	/* We might have learned some bits from the bounds. */
 	__reg_bound_offset(reg);
 	/* Intersecting with the old var_off might have improved our bounds
@@ -2449,6 +2189,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
 	__update_reg_bounds(reg);
 }
 
+static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *reg, const char *ctx)
+{
+	const char *msg;
+
+	if (reg->umin_value > reg->umax_value ||
+	    reg->smin_value > reg->smax_value ||
+	    reg->u32_min_value > reg->u32_max_value ||
+	    reg->s32_min_value > reg->s32_max_value) {
+		    msg = "range bounds violation";
+		    goto out;
+	}
+
+	if (tnum_is_const(reg->var_off)) {
+		u64 uval = reg->var_off.value;
+		s64 sval = (s64)uval;
+
+		if (reg->umin_value != uval || reg->umax_value != uval ||
+		    reg->smin_value != sval || reg->smax_value != sval) {
+			msg = "const tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	if (tnum_subreg_is_const(reg->var_off)) {
+		u32 uval32 = tnum_subreg(reg->var_off).value;
+		s32 sval32 = (s32)uval32;
+
+		if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 ||
+		    reg->s32_min_value != sval32 || reg->s32_max_value != sval32) {
+			msg = "const subreg tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	return 0;
+out:
+	verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] "
+		"s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n",
+		ctx, msg, reg->umin_value, reg->umax_value,
+		reg->smin_value, reg->smax_value,
+		reg->u32_min_value, reg->u32_max_value,
+		reg->s32_min_value, reg->s32_max_value,
+		reg->var_off.value, reg->var_off.mask);
+	if (env->test_reg_invariants)
+		return -EFAULT;
+	__mark_reg_unbounded(reg);
+	return 0;
+}
+
 static bool __reg32_bound_s64(s32 a)
 {
 	return a >= 0 && a <= S32_MAX;
@@ -2473,51 +2263,6 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 	}
 }
 
-static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
-{
-	/* special case when 64-bit register has upper 32-bit register
-	 * zeroed. Typically happens after zext or <<32, >>32 sequence
-	 * allowing us to use 32-bit bounds directly,
-	 */
-	if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
-		__reg_assign_32_into_64(reg);
-	} else {
-		/* Otherwise the best we can do is push lower 32bit known and
-		 * unknown bits into register (var_off set from jmp logic)
-		 * then learn as much as possible from the 64-bit tnum
-		 * known and unknown bits. The previous smin/smax bounds are
-		 * invalid here because of jmp32 compare so mark them unknown
-		 * so they do not impact tnum bounds calculation.
-		 */
-		__mark_reg64_unbounded(reg);
-	}
-	reg_bounds_sync(reg);
-}
-
-static bool __reg64_bound_s32(s64 a)
-{
-	return a >= S32_MIN && a <= S32_MAX;
-}
-
-static bool __reg64_bound_u32(u64 a)
-{
-	return a >= U32_MIN && a <= U32_MAX;
-}
-
-static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
-{
-	__mark_reg32_unbounded(reg);
-	if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
-		reg->s32_min_value = (s32)reg->smin_value;
-		reg->s32_max_value = (s32)reg->smax_value;
-	}
-	if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
-		reg->u32_min_value = (u32)reg->umin_value;
-		reg->u32_max_value = (u32)reg->umax_value;
-	}
-	reg_bounds_sync(reg);
-}
-
 /* Mark a register as having a completely unknown (scalar) value. */
 static void __mark_reg_unknown(const struct bpf_verifier_env *env,
 			       struct bpf_reg_state *reg)
@@ -2605,6 +2350,11 @@ static void init_reg_state(struct bpf_verifier_env *env,
 	regs[BPF_REG_FP].frameno = state->frameno;
 }
 
+static struct bpf_retval_range retval_range(s32 minval, s32 maxval)
+{
+	return (struct bpf_retval_range){ minval, maxval };
+}
+
 #define BPF_MAIN_FUNC (-1)
 static void init_func_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *state,
@@ -2613,7 +2363,7 @@ static void init_func_state(struct bpf_verifier_env *env,
 	state->callsite = callsite;
 	state->frameno = frameno;
 	state->subprogno = subprogno;
-	state->callback_ret_range = tnum_range(0, 0);
+	state->callback_ret_range = retval_range(0, 0);
 	init_reg_state(env, state);
 	mark_verifier_state_scratched(env);
 }
@@ -3157,6 +2907,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			if (env->subprog_info[i].start != ex_cb_insn)
 				continue;
 			env->exception_callback_subprog = i;
+			mark_subprog_exc_cb(env, i);
 			break;
 		}
 	}
@@ -3513,6 +3264,21 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 	return __check_reg_arg(env, state->regs, regno, t);
 }
 
+static int insn_stack_access_flags(int frameno, int spi)
+{
+	return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno;
+}
+
+static int insn_stack_access_spi(int insn_flags)
+{
+	return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK;
+}
+
+static int insn_stack_access_frameno(int insn_flags)
+{
+	return insn_flags & INSN_F_FRAMENO_MASK;
+}
+
 static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
 {
 	env->insn_aux_data[idx].jmp_point = true;
@@ -3524,28 +3290,51 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx)
 }
 
 /* for any branch, call, exit record the history of jmps in the given state */
-static int push_jmp_history(struct bpf_verifier_env *env,
-			    struct bpf_verifier_state *cur)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+			    int insn_flags)
 {
 	u32 cnt = cur->jmp_history_cnt;
-	struct bpf_idx_pair *p;
+	struct bpf_jmp_history_entry *p;
 	size_t alloc_size;
 
-	if (!is_jmp_point(env, env->insn_idx))
+	/* combine instruction flags if we already recorded this instruction */
+	if (env->cur_hist_ent) {
+		/* atomic instructions push insn_flags twice, for READ and
+		 * WRITE sides, but they should agree on stack slot
+		 */
+		WARN_ONCE((env->cur_hist_ent->flags & insn_flags) &&
+			  (env->cur_hist_ent->flags & insn_flags) != insn_flags,
+			  "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
+			  env->insn_idx, env->cur_hist_ent->flags, insn_flags);
+		env->cur_hist_ent->flags |= insn_flags;
 		return 0;
+	}
 
 	cnt++;
 	alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
 	p = krealloc(cur->jmp_history, alloc_size, GFP_USER);
 	if (!p)
 		return -ENOMEM;
-	p[cnt - 1].idx = env->insn_idx;
-	p[cnt - 1].prev_idx = env->prev_insn_idx;
 	cur->jmp_history = p;
+
+	p = &cur->jmp_history[cnt - 1];
+	p->idx = env->insn_idx;
+	p->prev_idx = env->prev_insn_idx;
+	p->flags = insn_flags;
 	cur->jmp_history_cnt = cnt;
+	env->cur_hist_ent = p;
+
 	return 0;
 }
 
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+						        u32 hist_end, int insn_idx)
+{
+	if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+		return &st->jmp_history[hist_end - 1];
+	return NULL;
+}
+
 /* Backtrack one insn at a time. If idx is not at the top of recorded
  * history then previous instruction came from straight line execution.
  * Return -ENOENT if we exhausted all instructions within given state.
@@ -3672,16 +3461,6 @@ static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u3
 	bt->stack_masks[frame] &= ~(1ull << slot);
 }
 
-static inline void bt_set_slot(struct backtrack_state *bt, u32 slot)
-{
-	bt_set_frame_slot(bt, bt->frame, slot);
-}
-
-static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot)
-{
-	bt_clear_frame_slot(bt, bt->frame, slot);
-}
-
 static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame)
 {
 	return bt->reg_masks[frame];
@@ -3707,9 +3486,9 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
 	return bt->reg_masks[bt->frame] & (1 << reg);
 }
 
-static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
+static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
 {
-	return bt->stack_masks[bt->frame] & (1ull << slot);
+	return bt->stack_masks[frame] & (1ull << slot);
 }
 
 /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
@@ -3763,7 +3542,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
  *   - *was* processed previously during backtracking.
  */
 static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
-			  struct backtrack_state *bt)
+			  struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
 {
 	const struct bpf_insn_cbs cbs = {
 		.cb_call	= disasm_kfunc_name,
@@ -3776,7 +3555,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	u8 mode = BPF_MODE(insn->code);
 	u32 dreg = insn->dst_reg;
 	u32 sreg = insn->src_reg;
-	u32 spi, i;
+	u32 spi, i, fr;
 
 	if (insn->code == 0)
 		return 0;
@@ -3837,20 +3616,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		 * by 'precise' mark in corresponding register of this state.
 		 * No further tracking necessary.
 		 */
-		if (insn->src_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
 		 * tracked with precision
 		 */
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		bt_set_slot(bt, spi);
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		bt_set_frame_slot(bt, fr, spi);
 	} else if (class == BPF_STX || class == BPF_ST) {
 		if (bt_is_reg_set(bt, dreg))
 			/* stx & st shouldn't be using _scalar_ dst_reg
@@ -3859,17 +3633,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 */
 			return -ENOTSUPP;
 		/* scalars can only be spilled into stack */
-		if (insn->dst_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		if (!bt_is_slot_set(bt, spi))
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		if (!bt_is_frame_slot_set(bt, fr, spi))
 			return 0;
-		bt_clear_slot(bt, spi);
+		bt_clear_frame_slot(bt, fr, spi);
 		if (class == BPF_STX)
 			bt_set_reg(bt, sreg);
 	} else if (class == BPF_JMP || class == BPF_JMP32) {
@@ -3913,10 +3683,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					WARN_ONCE(1, "verifier backtracking bug");
 					return -EFAULT;
 				}
-				/* we don't track register spills perfectly,
-				 * so fallback to force-precise instead of failing */
-				if (bt_stack_mask(bt) != 0)
-					return -ENOTSUPP;
+				/* we are now tracking register spills correctly,
+				 * so any instance of leftover slots is a bug
+				 */
+				if (bt_stack_mask(bt) != 0) {
+					verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+					WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)");
+					return -EFAULT;
+				}
 				/* propagate r1-r5 to the caller */
 				for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
 					if (bt_is_reg_set(bt, i)) {
@@ -3941,8 +3715,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
 			}
-			if (bt_stack_mask(bt) != 0)
-				return -ENOTSUPP;
+			if (bt_stack_mask(bt) != 0) {
+				verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+				WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)");
+				return -EFAULT;
+			}
 			/* clear r1-r5 in callback subprog's mask */
 			for (i = BPF_REG_1; i <= BPF_REG_5; i++)
 				bt_clear_reg(bt, i);
@@ -4379,6 +4156,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
+		struct bpf_jmp_history_entry *hist;
 
 		if (env->log.level & BPF_LOG_LEVEL2) {
 			verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4442,7 +4220,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				err = 0;
 				skip_first = false;
 			} else {
-				err = backtrack_insn(env, i, subseq_idx, bt);
+				hist = get_jmp_hist_entry(st, history, i);
+				err = backtrack_insn(env, i, subseq_idx, hist, bt);
 			}
 			if (err == -ENOTSUPP) {
 				mark_all_scalars_precise(env, env->cur_state);
@@ -4495,22 +4274,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 			bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
 			for_each_set_bit(i, mask, 64) {
 				if (i >= func->allocated_stack / BPF_REG_SIZE) {
-					/* the sequence of instructions:
-					 * 2: (bf) r3 = r10
-					 * 3: (7b) *(u64 *)(r3 -8) = r0
-					 * 4: (79) r4 = *(u64 *)(r10 -8)
-					 * doesn't contain jmps. It's backtracked
-					 * as a single block.
-					 * During backtracking insn 3 is not recognized as
-					 * stack access, so at the end of backtracking
-					 * stack slot fp-8 is still marked in stack_mask.
-					 * However the parent state may not have accessed
-					 * fp-8 and it's "unallocated" stack space.
-					 * In such case fallback to conservative.
-					 */
-					mark_all_scalars_precise(env, env->cur_state);
-					bt_reset(bt);
-					return 0;
+					verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n",
+						i, func->allocated_stack / BPF_REG_SIZE);
+					WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)");
+					return -EFAULT;
 				}
 
 				if (!is_spilled_scalar_reg(&func->stack[i])) {
@@ -4600,9 +4367,17 @@ static bool register_is_null(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
 }
 
-static bool register_is_const(struct bpf_reg_state *reg)
+/* check if register is a constant scalar value */
+static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32)
+{
+	return reg->type == SCALAR_VALUE &&
+	       tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off);
+}
+
+/* assuming is_reg_const() is true, return constant value of a register */
+static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32)
 {
-	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
+	return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value;
 }
 
 static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
@@ -4639,7 +4414,8 @@ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_
 	dst->live = live;
 }
 
-static void save_register_state(struct bpf_func_state *state,
+static void save_register_state(struct bpf_verifier_env *env,
+				struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg,
 				int size)
 {
@@ -4654,7 +4430,7 @@ static void save_register_state(struct bpf_func_state *state,
 
 	/* size < 8 bytes spill */
 	for (; i; i--)
-		scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
+		mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]);
 }
 
 static bool is_bpf_st_mem(struct bpf_insn *insn)
@@ -4675,7 +4451,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
 	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
 	struct bpf_reg_state *reg = NULL;
-	u32 dst_reg = insn->dst_reg;
+	int insn_flags = insn_stack_access_flags(state->frameno, spi);
 
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
 	 * so it's aligned access and [off, off + size) are within stack limits
@@ -4711,20 +4487,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		return err;
 
 	mark_stack_slot_scratched(env, spi);
-	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
-	    !register_is_null(reg) && env->bpf_capable) {
-		if (dst_reg != BPF_REG_FP) {
-			/* The backtracking logic can only recognize explicit
-			 * stack slot address like [fp - 8]. Other spill of
-			 * scalar via different register has to be conservative.
-			 * Backtrack from here and mark all registers as precise
-			 * that contributed into 'reg' being a constant.
-			 */
-			err = mark_chain_precision(env, value_regno);
-			if (err)
-				return err;
-		}
-		save_register_state(state, spi, reg, size);
+	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) {
+		save_register_state(env, state, spi, reg, size);
 		/* Break the relation on a narrowing spill. */
 		if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
 			state->stack[spi].spilled_ptr.id = 0;
@@ -4734,7 +4498,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 
 		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
-		save_register_state(state, spi, &fake_reg, size);
+		save_register_state(env, state, spi, &fake_reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -4746,7 +4510,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
 			return -EINVAL;
 		}
-		save_register_state(state, spi, reg, size);
+		save_register_state(env, state, spi, reg, size);
 	} else {
 		u8 type = STACK_MISC;
 
@@ -4771,7 +4535,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		/* when we zero initialize stack slots mark them as such */
 		if ((reg && register_is_null(reg)) ||
 		    (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) {
-			/* backtracking doesn't work for STACK_ZERO yet. */
+			/* STACK_ZERO case happened because register spill
+			 * wasn't properly aligned at the stack slot boundary,
+			 * so it's not a register spill anymore; force
+			 * originating register to be precise to make
+			 * STACK_ZERO correct for subsequent states
+			 */
 			err = mark_chain_precision(env, value_regno);
 			if (err)
 				return err;
@@ -4780,9 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 
 		/* Mark slots affected by this stack write. */
 		for (i = 0; i < size; i++)
-			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
-				type;
+			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type;
+		insn_flags = 0; /* not a register spill */
 	}
+
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -4930,21 +4702,10 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env,
 		zeros++;
 	}
 	if (zeros == max_off - min_off) {
-		/* any access_size read into register is zero extended,
-		 * so the whole register == const_zero
-		 */
-		__mark_reg_const_zero(&state->regs[dst_regno]);
-		/* backtracking doesn't support STACK_ZERO yet,
-		 * so mark it precise here, so that later
-		 * backtracking can stop here.
-		 * Backtracking may not need this if this register
-		 * doesn't participate in pointer adjustment.
-		 * Forward propagation of precise flag is not
-		 * necessary either. This mark is only to stop
-		 * backtracking. Any register that contributed
-		 * to const 0 was marked precise before spill.
+		/* Any access_size read into register is zero extended,
+		 * so the whole register == const_zero.
 		 */
-		state->regs[dst_regno].precise = true;
+		__mark_reg_const_zero(env, &state->regs[dst_regno]);
 	} else {
 		/* have read misc data from the stack */
 		mark_reg_unknown(env, state->regs, dst_regno);
@@ -4971,6 +4732,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
 	u8 *stype, type;
+	int insn_flags = insn_stack_access_flags(reg_state->frameno, spi);
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
@@ -5003,25 +4765,42 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 				copy_register_state(&state->regs[dst_regno], reg);
 				state->regs[dst_regno].subreg_def = subreg_def;
 			} else {
+				int spill_cnt = 0, zero_cnt = 0;
+
 				for (i = 0; i < size; i++) {
 					type = stype[(slot - i) % BPF_REG_SIZE];
-					if (type == STACK_SPILL)
+					if (type == STACK_SPILL) {
+						spill_cnt++;
 						continue;
+					}
 					if (type == STACK_MISC)
 						continue;
+					if (type == STACK_ZERO) {
+						zero_cnt++;
+						continue;
+					}
 					if (type == STACK_INVALID && env->allow_uninit_stack)
 						continue;
 					verbose(env, "invalid read from stack off %d+%d size %d\n",
 						off, i, size);
 					return -EACCES;
 				}
-				mark_reg_unknown(env, state->regs, dst_regno);
+
+				if (spill_cnt == size &&
+				    tnum_is_const(reg->var_off) && reg->var_off.value == 0) {
+					__mark_reg_const_zero(env, &state->regs[dst_regno]);
+					/* this IS register fill, so keep insn_flags */
+				} else if (zero_cnt == size) {
+					/* similarly to mark_reg_stack_read(), preserve zeroes */
+					__mark_reg_const_zero(env, &state->regs[dst_regno]);
+					insn_flags = 0; /* not restoring original register state */
+				} else {
+					mark_reg_unknown(env, state->regs, dst_regno);
+					insn_flags = 0; /* not restoring original register state */
+				}
 			}
 			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
-			return 0;
-		}
-
-		if (dst_regno >= 0) {
+		} else if (dst_regno >= 0) {
 			/* restore register state from stack */
 			copy_register_state(&state->regs[dst_regno], reg);
 			/* mark reg as written since spilled pointer state likely
@@ -5057,7 +4836,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 		if (dst_regno >= 0)
 			mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
+		insn_flags = 0; /* we are not restoring spilled register */
 	}
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -5347,8 +5129,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno)
+static int check_ptr_off_reg(struct bpf_verifier_env *env,
+		             const struct bpf_reg_state *reg, int regno)
 {
 	return __check_ptr_off_reg(env, reg, regno, false);
 }
@@ -5454,10 +5236,23 @@ BTF_SET_END(rcu_protected_types)
 static bool rcu_protected_object(const struct btf *btf, u32 btf_id)
 {
 	if (!btf_is_kernel(btf))
-		return false;
+		return true;
 	return btf_id_set_contains(&rcu_protected_types, btf_id);
 }
 
+static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field)
+{
+	struct btf_struct_meta *meta;
+
+	if (btf_is_kernel(kptr_field->kptr.btf))
+		return NULL;
+
+	meta = btf_find_struct_meta(kptr_field->kptr.btf,
+				    kptr_field->kptr.btf_id);
+
+	return meta ? meta->record : NULL;
+}
+
 static bool rcu_safe_kptr(const struct btf_field *field)
 {
 	const struct btf_field_kptr *kptr = &field->kptr;
@@ -5468,12 +5263,25 @@ static bool rcu_safe_kptr(const struct btf_field *field)
 
 static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
 {
+	struct btf_record *rec;
+	u32 ret;
+
+	ret = PTR_MAYBE_NULL;
 	if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
-		if (kptr_field->type != BPF_KPTR_PERCPU)
-			return PTR_MAYBE_NULL | MEM_RCU;
-		return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU;
+		ret |= MEM_RCU;
+		if (kptr_field->type == BPF_KPTR_PERCPU)
+			ret |= MEM_PERCPU;
+		else if (!btf_is_kernel(kptr_field->kptr.btf))
+			ret |= MEM_ALLOC;
+
+		rec = kptr_pointee_btf_record(kptr_field);
+		if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE))
+			ret |= NON_OWN_REF;
+	} else {
+		ret |= PTR_UNTRUSTED;
 	}
-	return PTR_MAYBE_NULL | PTR_UNTRUSTED;
+
+	return ret;
 }
 
 static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -6233,9 +6041,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	 * values are also truncated so we push 64-bit bounds into
 	 * 32-bit bounds. Above were truncated < 32-bits already.
 	 */
-	if (size >= 4)
-		return;
-	__reg_combine_64_into_32(reg);
+	if (size < 4) {
+		__mark_reg32_unbounded(reg);
+		reg_bounds_sync(reg);
+	}
 }
 
 static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
@@ -6809,6 +6618,11 @@ static int check_stack_access_within_bounds(
 	err = check_stack_slot_within_bounds(env, min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
+	if (!err && access_size < 0)
+		/* access_size should not be negative (or overflow an int); others checks
+		 * along the way should have prevented such an access.
+		 */
+		err = -EFAULT; /* invalid negative access size; integer overflow? */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
@@ -6818,13 +6632,16 @@ static int check_stack_access_within_bounds(
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-			verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n",
-				err_extra, regno, tn_buf, access_size);
+			verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n",
+				err_extra, regno, tn_buf, off, access_size);
 		}
 		return err;
 	}
 
-	return grow_stack_state(env, state, round_up(-min_off, BPF_REG_SIZE));
+	/* Note that there is no stack access with offset zero, so the needed stack
+	 * size is -min_off, not -min_off+1.
+	 */
+	return grow_stack_state(env, state, -min_off /* size */);
 }
 
 /* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -7169,7 +6986,6 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
 	if (err)
 		return err;
-
 	return 0;
 }
 
@@ -7432,6 +7248,12 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	}
 }
 
+/* verify arguments to helpers or kfuncs consisting of a pointer and an access
+ * size.
+ *
+ * @regno is the register containing the access size. regno-1 is the register
+ * containing the pointer.
+ */
 static int check_mem_size_reg(struct bpf_verifier_env *env,
 			      struct bpf_reg_state *reg, u32 regno,
 			      bool zero_size_allowed,
@@ -7466,12 +7288,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	if (reg->umin_value == 0) {
-		err = check_helper_mem_access(env, regno - 1, 0,
-					      zero_size_allowed,
-					      meta);
-		if (err)
-			return err;
+	if (reg->umin_value == 0 && !zero_size_allowed) {
+		verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n",
+			regno, reg->umin_value, reg->umax_value);
+		return -EACCES;
 	}
 
 	if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
@@ -7487,8 +7307,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 	return err;
 }
 
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size)
+static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+			 u32 regno, u32 mem_size)
 {
 	bool may_be_null = type_may_be_null(reg->type);
 	struct bpf_reg_state saved_reg;
@@ -8133,7 +7953,7 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
 	/* switch to DRAINED state, but keep the depth unchanged */
 	/* mark current iter state as drained and assume returned NULL */
 	cur_iter->iter.state = BPF_ITER_STATE_DRAINED;
-	__mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]);
+	__mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]);
 
 	return 0;
 }
@@ -8473,9 +8293,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields)
 	return field;
 }
 
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type)
+static int check_func_arg_reg_off(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg, int regno,
+				  enum bpf_arg_type arg_type)
 {
 	u32 type = reg->type;
 
@@ -8609,6 +8429,54 @@ static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env,
 	return state->stack[spi].spilled_ptr.dynptr.type;
 }
 
+static int check_reg_const_str(struct bpf_verifier_env *env,
+			       struct bpf_reg_state *reg, u32 regno)
+{
+	struct bpf_map *map = reg->map_ptr;
+	int err;
+	int map_off;
+	u64 map_addr;
+	char *str_ptr;
+
+	if (reg->type != PTR_TO_MAP_VALUE)
+		return -EINVAL;
+
+	if (!bpf_map_is_rdonly(map)) {
+		verbose(env, "R%d does not point to a readonly map'\n", regno);
+		return -EACCES;
+	}
+
+	if (!tnum_is_const(reg->var_off)) {
+		verbose(env, "R%d is not a constant address'\n", regno);
+		return -EACCES;
+	}
+
+	if (!map->ops->map_direct_value_addr) {
+		verbose(env, "no direct value access support for this map type\n");
+		return -EACCES;
+	}
+
+	err = check_map_access(env, regno, reg->off,
+			       map->value_size - reg->off, false,
+			       ACCESS_HELPER);
+	if (err)
+		return err;
+
+	map_off = reg->off + reg->var_off.value;
+	err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
+	if (err) {
+		verbose(env, "direct value access on string failed\n");
+		return err;
+	}
+
+	str_ptr = (char *)(long)(map_addr);
+	if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
+		verbose(env, "string is not zero-terminated\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn,
@@ -8853,44 +8721,9 @@ skip_type_check:
 	}
 	case ARG_PTR_TO_CONST_STR:
 	{
-		struct bpf_map *map = reg->map_ptr;
-		int map_off;
-		u64 map_addr;
-		char *str_ptr;
-
-		if (!bpf_map_is_rdonly(map)) {
-			verbose(env, "R%d does not point to a readonly map'\n", regno);
-			return -EACCES;
-		}
-
-		if (!tnum_is_const(reg->var_off)) {
-			verbose(env, "R%d is not a constant address'\n", regno);
-			return -EACCES;
-		}
-
-		if (!map->ops->map_direct_value_addr) {
-			verbose(env, "no direct value access support for this map type\n");
-			return -EACCES;
-		}
-
-		err = check_map_access(env, regno, reg->off,
-				       map->value_size - reg->off, false,
-				       ACCESS_HELPER);
+		err = check_reg_const_str(env, reg, regno);
 		if (err)
 			return err;
-
-		map_off = reg->off + reg->var_off.value;
-		err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
-		if (err) {
-			verbose(env, "direct value access on string failed\n");
-			return err;
-		}
-
-		str_ptr = (char *)(long)(map_addr);
-		if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
-			verbose(env, "string is not zero-terminated\n");
-			return -EINVAL;
-		}
 		break;
 	}
 	case ARG_PTR_TO_KPTR:
@@ -9423,6 +9256,102 @@ err_out:
 	return err;
 }
 
+static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+				    const struct btf *btf,
+				    struct bpf_reg_state *regs)
+{
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
+	struct bpf_verifier_log *log = &env->log;
+	u32 i;
+	int ret;
+
+	ret = btf_prepare_func_args(env, subprog);
+	if (ret)
+		return ret;
+
+	/* check that BTF function arguments match actual types that the
+	 * verifier sees.
+	 */
+	for (i = 0; i < sub->arg_cnt; i++) {
+		u32 regno = i + 1;
+		struct bpf_reg_state *reg = &regs[regno];
+		struct bpf_subprog_arg_info *arg = &sub->args[i];
+
+		if (arg->arg_type == ARG_ANYTHING) {
+			if (reg->type != SCALAR_VALUE) {
+				bpf_log(log, "R%d is not a scalar\n", regno);
+				return -EINVAL;
+			}
+		} else if (arg->arg_type == ARG_PTR_TO_CTX) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+			if (ret < 0)
+				return ret;
+			/* If function expects ctx type in BTF check that caller
+			 * is passing PTR_TO_CTX.
+			 */
+			if (reg->type != PTR_TO_CTX) {
+				bpf_log(log, "arg#%d expects pointer to ctx\n", i);
+				return -EINVAL;
+			}
+		} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE);
+			if (ret < 0)
+				return ret;
+			if (check_mem_reg(env, reg, regno, arg->mem_size))
+				return -EINVAL;
+			if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) {
+				bpf_log(log, "arg#%d is expected to be non-NULL\n", i);
+				return -EINVAL;
+			}
+		} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+			ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
+			if (ret)
+				return ret;
+		} else {
+			bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n",
+				i, arg->arg_type);
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+/* Compare BTF of a function call with given bpf_reg_state.
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - there is a type mismatch or BTF is not available.
+ * 0 - BTF matches with what bpf_reg_state expects.
+ * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
+ */
+static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
+				  struct bpf_reg_state *regs)
+{
+	struct bpf_prog *prog = env->prog;
+	struct btf *btf = prog->aux->btf;
+	u32 btf_id;
+	int err;
+
+	if (!prog->aux->func_info)
+		return -EINVAL;
+
+	btf_id = prog->aux->func_info[subprog].type_id;
+	if (!btf_id)
+		return -EFAULT;
+
+	if (prog->aux->func_info_aux[subprog].unreliable)
+		return -EINVAL;
+
+	err = btf_check_func_arg_match(env, subprog, btf, regs);
+	/* Compiler optimizations can remove arguments from static functions
+	 * or mismatched type can be passed into a global function.
+	 * In such cases mark the function as unreliable from BTF point of view.
+	 */
+	if (err)
+		prog->aux->func_info_aux[subprog].unreliable = true;
+	return err;
+}
+
 static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			      int insn_idx, int subprog,
 			      set_callee_state_fn set_callee_state_cb)
@@ -9512,13 +9441,18 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	if (err == -EFAULT)
 		return err;
 	if (subprog_is_global(env, subprog)) {
+		const char *sub_name = subprog_name(env, subprog);
+
 		if (err) {
-			verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+			verbose(env, "Caller passes invalid args into func#%d ('%s')\n",
+				subprog, sub_name);
 			return err;
 		}
 
-		if (env->log.level & BPF_LOG_LEVEL)
-			verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
+		verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
+			subprog, sub_name);
+		/* mark global subprog for verifying after main prog */
+		subprog_aux(env, subprog)->called = true;
 		clear_caller_saved_regs(env, caller->regs);
 
 		/* All global functions return a 64-bit SCALAR_VALUE */
@@ -9618,7 +9552,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 		return err;
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9640,7 +9574,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9670,7 +9604,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_async_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9689,7 +9623,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
 	callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
 	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
 	callee->regs[BPF_REG_2].btf =  btf_vmlinux;
-	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA],
+	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
 
 	/* pointer to stack or null */
 	callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];
@@ -9698,7 +9632,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9721,7 +9655,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9753,7 +9687,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9782,6 +9716,11 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
 	return is_rbtree_lock_required_kfunc(kfunc_btf_id);
 }
 
+static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
+{
+	return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
+}
+
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
 	struct bpf_verifier_state *state = env->cur_state, *prev_st;
@@ -9805,9 +9744,6 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 
 	caller = state->frame[state->curframe - 1];
 	if (callee->in_callback_fn) {
-		/* enforce R0 return value range [0, 1]. */
-		struct tnum range = callee->callback_ret_range;
-
 		if (r0->type != SCALAR_VALUE) {
 			verbose(env, "R0 not a scalar value\n");
 			return -EACCES;
@@ -9819,8 +9755,10 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		if (err)
 			return err;
 
-		if (!tnum_in(range, r0->var_off)) {
-			verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
+		/* enforce R0 return value range */
+		if (!retval_range_within(callee->callback_ret_range, r0)) {
+			verbose_invalid_scalar(env, r0, callee->callback_ret_range,
+					       "At callback return", "R0");
 			return -EINVAL;
 		}
 		if (!calls_callback(env, callee->callsite)) {
@@ -9886,14 +9824,15 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	return 0;
 }
 
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
-				   int func_id,
-				   struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+				  struct bpf_reg_state *regs, int ret_type,
+				  int func_id,
+				  struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
 
 	if (ret_type != RET_INTEGER)
-		return;
+		return 0;
 
 	switch (func_id) {
 	case BPF_FUNC_get_stack:
@@ -9919,6 +9858,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 		reg_bounds_sync(ret_reg);
 		break;
 	}
+
+	return reg_bounds_sanity_check(env, ret_reg, "retval");
 }
 
 static int
@@ -9988,7 +9929,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	val = reg->var_off.value;
 	max = map->max_entries;
 
-	if (!(register_is_const(reg) && val < max)) {
+	if (!(is_reg_const(reg, false) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -10583,7 +10524,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].ref_obj_id = id;
 	}
 
-	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+	err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+	if (err)
+		return err;
 
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
@@ -10761,6 +10704,11 @@ static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param
 	return __kfunc_param_match_suffix(btf, arg, "__nullable");
 }
 
+static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__str");
+}
+
 static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
 					  const struct btf_param *arg,
 					  const char *name)
@@ -10904,6 +10852,7 @@ enum kfunc_ptr_arg_type {
 	KF_ARG_PTR_TO_RB_ROOT,
 	KF_ARG_PTR_TO_RB_NODE,
 	KF_ARG_PTR_TO_NULL,
+	KF_ARG_PTR_TO_CONST_STR,
 };
 
 enum special_kfunc_type {
@@ -11054,6 +11003,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_RB_NODE;
 
+	if (is_kfunc_arg_const_str(meta->btf, &args[argno]))
+		return KF_ARG_PTR_TO_CONST_STR;
+
 	if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) {
 		if (!btf_type_is_struct(ref_t)) {
 			verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n",
@@ -11685,6 +11637,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_MEM_SIZE:
 		case KF_ARG_PTR_TO_CALLBACK:
 		case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
+		case KF_ARG_PTR_TO_CONST_STR:
 			/* Trusted by default */
 			break;
 		default:
@@ -11956,6 +11909,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			meta->arg_btf = reg->btf;
 			meta->arg_btf_id = reg->btf_id;
 			break;
+		case KF_ARG_PTR_TO_CONST_STR:
+			if (reg->type != PTR_TO_MAP_VALUE) {
+				verbose(env, "arg#%d doesn't point to a const string\n", i);
+				return -EINVAL;
+			}
+			ret = check_reg_const_str(env, reg, regno);
+			if (ret)
+				return ret;
+			break;
 		}
 	}
 
@@ -12010,7 +11972,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_return_code(struct bpf_verifier_env *env, int regno);
+static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);
 
 static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			    int *insn_idx_p)
@@ -12147,7 +12109,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		 * to bpf_throw becomes the return value of the program.
 		 */
 		if (!env->exception_callback_subprog) {
-			err = check_return_code(env, BPF_REG_1);
+			err = check_return_code(env, BPF_REG_1, "R1");
 			if (err < 0)
 				return err;
 		}
@@ -12186,20 +12148,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-					if (!bpf_global_percpu_ma_set) {
-						mutex_lock(&bpf_percpu_ma_lock);
-						if (!bpf_global_percpu_ma_set) {
-							err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-							if (!err)
-								bpf_global_percpu_ma_set = true;
-						}
-						mutex_unlock(&bpf_percpu_ma_lock);
-						if (err)
-							return err;
-					}
-				}
-
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
 					return -EINVAL;
@@ -12220,6 +12168,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 					return -EINVAL;
 				}
 
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
+						verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
+							ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
+						return -EINVAL;
+					}
+
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							/* Charge memory allocated with bpf_global_percpu_ma to
+							 * root memcg. The obj_cgroup for root memcg is NULL.
+							 */
+							err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+
+					mutex_lock(&bpf_percpu_ma_lock);
+					err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+					mutex_unlock(&bpf_percpu_ma_lock);
+					if (err)
+						return err;
+				}
+
 				struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
 				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
 					if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
@@ -14080,13 +14057,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		/* check dest operand */
 		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+		err = err ?: adjust_reg_min_max_vals(env, insn);
 		if (err)
 			return err;
-
-		return adjust_reg_min_max_vals(env, insn);
 	}
 
-	return 0;
+	return reg_bounds_sanity_check(env, &regs[insn->dst_reg], "alu");
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
@@ -14168,161 +14144,130 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	}));
 }
 
-static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
-{
-	struct tnum subreg = tnum_subreg(reg->var_off);
-	s32 sval = (s32)val;
-
-	switch (opcode) {
-	case BPF_JEQ:
-		if (tnum_is_const(subreg))
-			return !!tnum_equals_const(subreg, val);
-		else if (val < reg->u32_min_value || val > reg->u32_max_value)
-			return 0;
-		else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
-			return 0;
-		break;
-	case BPF_JNE:
-		if (tnum_is_const(subreg))
-			return !tnum_equals_const(subreg, val);
-		else if (val < reg->u32_min_value || val > reg->u32_max_value)
-			return 1;
-		else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
-			return 1;
-		break;
-	case BPF_JSET:
-		if ((~subreg.mask & subreg.value) & val)
-			return 1;
-		if (!((subreg.mask | subreg.value) & val))
-			return 0;
-		break;
-	case BPF_JGT:
-		if (reg->u32_min_value > val)
-			return 1;
-		else if (reg->u32_max_value <= val)
-			return 0;
-		break;
-	case BPF_JSGT:
-		if (reg->s32_min_value > sval)
-			return 1;
-		else if (reg->s32_max_value <= sval)
-			return 0;
-		break;
-	case BPF_JLT:
-		if (reg->u32_max_value < val)
-			return 1;
-		else if (reg->u32_min_value >= val)
-			return 0;
-		break;
-	case BPF_JSLT:
-		if (reg->s32_max_value < sval)
-			return 1;
-		else if (reg->s32_min_value >= sval)
-			return 0;
-		break;
-	case BPF_JGE:
-		if (reg->u32_min_value >= val)
-			return 1;
-		else if (reg->u32_max_value < val)
-			return 0;
-		break;
-	case BPF_JSGE:
-		if (reg->s32_min_value >= sval)
-			return 1;
-		else if (reg->s32_max_value < sval)
-			return 0;
-		break;
-	case BPF_JLE:
-		if (reg->u32_max_value <= val)
-			return 1;
-		else if (reg->u32_min_value > val)
-			return 0;
-		break;
-	case BPF_JSLE:
-		if (reg->s32_max_value <= sval)
-			return 1;
-		else if (reg->s32_min_value > sval)
-			return 0;
-		break;
-	}
-
-	return -1;
-}
-
-
-static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
-{
-	s64 sval = (s64)val;
+/*
+ * <reg1> <op> <reg2>, currently assuming reg2 is a constant
+ */
+static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+				  u8 opcode, bool is_jmp32)
+{
+	struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off;
+	struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off;
+	u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value;
+	u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value;
+	s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value;
+	s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value;
+	u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value;
+	u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value;
+	s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value;
+	s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value;
 
 	switch (opcode) {
 	case BPF_JEQ:
-		if (tnum_is_const(reg->var_off))
-			return !!tnum_equals_const(reg->var_off, val);
-		else if (val < reg->umin_value || val > reg->umax_value)
+		/* constants, umin/umax and smin/smax checks would be
+		 * redundant in this case because they all should match
+		 */
+		if (tnum_is_const(t1) && tnum_is_const(t2))
+			return t1.value == t2.value;
+		/* non-overlapping ranges */
+		if (umin1 > umax2 || umax1 < umin2)
 			return 0;
-		else if (sval < reg->smin_value || sval > reg->smax_value)
+		if (smin1 > smax2 || smax1 < smin2)
 			return 0;
+		if (!is_jmp32) {
+			/* if 64-bit ranges are inconclusive, see if we can
+			 * utilize 32-bit subrange knowledge to eliminate
+			 * branches that can't be taken a priori
+			 */
+			if (reg1->u32_min_value > reg2->u32_max_value ||
+			    reg1->u32_max_value < reg2->u32_min_value)
+				return 0;
+			if (reg1->s32_min_value > reg2->s32_max_value ||
+			    reg1->s32_max_value < reg2->s32_min_value)
+				return 0;
+		}
 		break;
 	case BPF_JNE:
-		if (tnum_is_const(reg->var_off))
-			return !tnum_equals_const(reg->var_off, val);
-		else if (val < reg->umin_value || val > reg->umax_value)
+		/* constants, umin/umax and smin/smax checks would be
+		 * redundant in this case because they all should match
+		 */
+		if (tnum_is_const(t1) && tnum_is_const(t2))
+			return t1.value != t2.value;
+		/* non-overlapping ranges */
+		if (umin1 > umax2 || umax1 < umin2)
 			return 1;
-		else if (sval < reg->smin_value || sval > reg->smax_value)
+		if (smin1 > smax2 || smax1 < smin2)
 			return 1;
+		if (!is_jmp32) {
+			/* if 64-bit ranges are inconclusive, see if we can
+			 * utilize 32-bit subrange knowledge to eliminate
+			 * branches that can't be taken a priori
+			 */
+			if (reg1->u32_min_value > reg2->u32_max_value ||
+			    reg1->u32_max_value < reg2->u32_min_value)
+				return 1;
+			if (reg1->s32_min_value > reg2->s32_max_value ||
+			    reg1->s32_max_value < reg2->s32_min_value)
+				return 1;
+		}
 		break;
 	case BPF_JSET:
-		if ((~reg->var_off.mask & reg->var_off.value) & val)
+		if (!is_reg_const(reg2, is_jmp32)) {
+			swap(reg1, reg2);
+			swap(t1, t2);
+		}
+		if (!is_reg_const(reg2, is_jmp32))
+			return -1;
+		if ((~t1.mask & t1.value) & t2.value)
 			return 1;
-		if (!((reg->var_off.mask | reg->var_off.value) & val))
+		if (!((t1.mask | t1.value) & t2.value))
 			return 0;
 		break;
 	case BPF_JGT:
-		if (reg->umin_value > val)
+		if (umin1 > umax2)
 			return 1;
-		else if (reg->umax_value <= val)
+		else if (umax1 <= umin2)
 			return 0;
 		break;
 	case BPF_JSGT:
-		if (reg->smin_value > sval)
+		if (smin1 > smax2)
 			return 1;
-		else if (reg->smax_value <= sval)
+		else if (smax1 <= smin2)
 			return 0;
 		break;
 	case BPF_JLT:
-		if (reg->umax_value < val)
+		if (umax1 < umin2)
 			return 1;
-		else if (reg->umin_value >= val)
+		else if (umin1 >= umax2)
 			return 0;
 		break;
 	case BPF_JSLT:
-		if (reg->smax_value < sval)
+		if (smax1 < smin2)
 			return 1;
-		else if (reg->smin_value >= sval)
+		else if (smin1 >= smax2)
 			return 0;
 		break;
 	case BPF_JGE:
-		if (reg->umin_value >= val)
+		if (umin1 >= umax2)
 			return 1;
-		else if (reg->umax_value < val)
+		else if (umax1 < umin2)
 			return 0;
 		break;
 	case BPF_JSGE:
-		if (reg->smin_value >= sval)
+		if (smin1 >= smax2)
 			return 1;
-		else if (reg->smax_value < sval)
+		else if (smax1 < smin2)
 			return 0;
 		break;
 	case BPF_JLE:
-		if (reg->umax_value <= val)
+		if (umax1 <= umin2)
 			return 1;
-		else if (reg->umin_value > val)
+		else if (umin1 > umax2)
 			return 0;
 		break;
 	case BPF_JSLE:
-		if (reg->smax_value <= sval)
+		if (smax1 <= smin2)
 			return 1;
-		else if (reg->smin_value > sval)
+		else if (smin1 > smax2)
 			return 0;
 		break;
 	}
@@ -14330,41 +14275,6 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 	return -1;
 }
 
-/* compute branch direction of the expression "if (reg opcode val) goto target;"
- * and return:
- *  1 - branch will be taken and "goto target" will be executed
- *  0 - branch will not be taken and fall-through to next insn
- * -1 - unknown. Example: "if (reg < 5)" is unknown when register value
- *      range [0,10]
- */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
-			   bool is_jmp32)
-{
-	if (__is_pointer_value(false, reg)) {
-		if (!reg_not_null(reg))
-			return -1;
-
-		/* If pointer is valid tests against zero will fail so we can
-		 * use this to direct branch taken.
-		 */
-		if (val != 0)
-			return -1;
-
-		switch (opcode) {
-		case BPF_JEQ:
-			return 0;
-		case BPF_JNE:
-			return 1;
-		default:
-			return -1;
-		}
-	}
-
-	if (is_jmp32)
-		return is_branch32_taken(reg, val, opcode);
-	return is_branch64_taken(reg, val, opcode);
-}
-
 static int flip_opcode(u32 opcode)
 {
 	/* How can we transform "a <op> b" into "b <op> a"? */
@@ -14426,216 +14336,280 @@ static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
 	return -1;
 }
 
-/* Adjusts the register min/max values in the case that the dst_reg is the
- * variable register that we are working on, and src_reg is a constant or we're
- * simply doing a BPF_K check.
- * In JEQ/JNE cases we also adjust the var_off values.
+/* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;"
+ * and return:
+ *  1 - branch will be taken and "goto target" will be executed
+ *  0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value
+ *      range [0,10]
  */
-static void reg_set_min_max(struct bpf_reg_state *true_reg,
-			    struct bpf_reg_state *false_reg,
-			    u64 val, u32 val32,
-			    u8 opcode, bool is_jmp32)
-{
-	struct tnum false_32off = tnum_subreg(false_reg->var_off);
-	struct tnum false_64off = false_reg->var_off;
-	struct tnum true_32off = tnum_subreg(true_reg->var_off);
-	struct tnum true_64off = true_reg->var_off;
-	s64 sval = (s64)val;
-	s32 sval32 = (s32)val32;
-
-	/* If the dst_reg is a pointer, we can't learn anything about its
-	 * variable offset from the compare (unless src_reg were a pointer into
-	 * the same object, but we don't bother with that.
-	 * Since false_reg and true_reg have the same type by construction, we
-	 * only need to check one of them for pointerness.
-	 */
-	if (__is_pointer_value(false, false_reg))
-		return;
+static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+			   u8 opcode, bool is_jmp32)
+{
+	if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32)
+		return is_pkt_ptr_branch_taken(reg1, reg2, opcode);
+
+	if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) {
+		u64 val;
+
+		/* arrange that reg2 is a scalar, and reg1 is a pointer */
+		if (!is_reg_const(reg2, is_jmp32)) {
+			opcode = flip_opcode(opcode);
+			swap(reg1, reg2);
+		}
+		/* and ensure that reg2 is a constant */
+		if (!is_reg_const(reg2, is_jmp32))
+			return -1;
+
+		if (!reg_not_null(reg1))
+			return -1;
+
+		/* If pointer is valid tests against zero will fail so we can
+		 * use this to direct branch taken.
+		 */
+		val = reg_const_value(reg2, is_jmp32);
+		if (val != 0)
+			return -1;
+
+		switch (opcode) {
+		case BPF_JEQ:
+			return 0;
+		case BPF_JNE:
+			return 1;
+		default:
+			return -1;
+		}
+	}
+
+	/* now deal with two scalars, but not necessarily constants */
+	return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32);
+}
 
+/* Opcode that corresponds to a *false* branch condition.
+ * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2
+ */
+static u8 rev_opcode(u8 opcode)
+{
 	switch (opcode) {
-	/* JEQ/JNE comparison doesn't change the register equivalence.
-	 *
-	 * r1 = r2;
-	 * if (r1 == 42) goto label;
-	 * ...
-	 * label: // here both r1 and r2 are known to be 42.
-	 *
-	 * Hence when marking register as known preserve it's ID.
+	case BPF_JEQ:		return BPF_JNE;
+	case BPF_JNE:		return BPF_JEQ;
+	/* JSET doesn't have it's reverse opcode in BPF, so add
+	 * BPF_X flag to denote the reverse of that operation
 	 */
+	case BPF_JSET:		return BPF_JSET | BPF_X;
+	case BPF_JSET | BPF_X:	return BPF_JSET;
+	case BPF_JGE:		return BPF_JLT;
+	case BPF_JGT:		return BPF_JLE;
+	case BPF_JLE:		return BPF_JGT;
+	case BPF_JLT:		return BPF_JGE;
+	case BPF_JSGE:		return BPF_JSLT;
+	case BPF_JSGT:		return BPF_JSLE;
+	case BPF_JSLE:		return BPF_JSGT;
+	case BPF_JSLT:		return BPF_JSGE;
+	default:		return 0;
+	}
+}
+
+/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */
+static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+				u8 opcode, bool is_jmp32)
+{
+	struct tnum t;
+	u64 val;
+
+again:
+	switch (opcode) {
 	case BPF_JEQ:
 		if (is_jmp32) {
-			__mark_reg32_known(true_reg, val32);
-			true_32off = tnum_subreg(true_reg->var_off);
+			reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->u32_min_value = reg1->u32_min_value;
+			reg2->u32_max_value = reg1->u32_max_value;
+			reg2->s32_min_value = reg1->s32_min_value;
+			reg2->s32_max_value = reg1->s32_max_value;
+
+			t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
+			reg2->var_off = tnum_with_subreg(reg2->var_off, t);
 		} else {
-			___mark_reg_known(true_reg, val);
-			true_64off = true_reg->var_off;
+			reg1->umin_value = max(reg1->umin_value, reg2->umin_value);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg1->smin_value = max(reg1->smin_value, reg2->smin_value);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->umin_value = reg1->umin_value;
+			reg2->umax_value = reg1->umax_value;
+			reg2->smin_value = reg1->smin_value;
+			reg2->smax_value = reg1->smax_value;
+
+			reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off);
+			reg2->var_off = reg1->var_off;
 		}
 		break;
 	case BPF_JNE:
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+
+		/* try to recompute the bound of reg1 if reg2 is a const and
+		 * is exactly the edge of reg1.
+		 */
+		val = reg_const_value(reg2, is_jmp32);
 		if (is_jmp32) {
-			__mark_reg32_known(false_reg, val32);
-			false_32off = tnum_subreg(false_reg->var_off);
+			/* u32_min_value is not equal to 0xffffffff at this point,
+			 * because otherwise u32_max_value is 0xffffffff as well,
+			 * in such a case both reg1 and reg2 would be constants,
+			 * jump would be predicted and reg_set_min_max() won't
+			 * be called.
+			 *
+			 * Same reasoning works for all {u,s}{min,max}{32,64} cases
+			 * below.
+			 */
+			if (reg1->u32_min_value == (u32)val)
+				reg1->u32_min_value++;
+			if (reg1->u32_max_value == (u32)val)
+				reg1->u32_max_value--;
+			if (reg1->s32_min_value == (s32)val)
+				reg1->s32_min_value++;
+			if (reg1->s32_max_value == (s32)val)
+				reg1->s32_max_value--;
 		} else {
-			___mark_reg_known(false_reg, val);
-			false_64off = false_reg->var_off;
+			if (reg1->umin_value == (u64)val)
+				reg1->umin_value++;
+			if (reg1->umax_value == (u64)val)
+				reg1->umax_value--;
+			if (reg1->smin_value == (s64)val)
+				reg1->smin_value++;
+			if (reg1->smax_value == (s64)val)
+				reg1->smax_value--;
 		}
 		break;
 	case BPF_JSET:
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
+		/* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X)
+		 * requires single bit to learn something useful. E.g., if we
+		 * know that `r1 & 0x3` is true, then which bits (0, 1, or both)
+		 * are actually set? We can learn something definite only if
+		 * it's a single-bit value to begin with.
+		 *
+		 * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have
+		 * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor
+		 * bit 1 is set, which we can readily use in adjustments.
+		 */
+		if (!is_power_of_2(val))
+			break;
 		if (is_jmp32) {
-			false_32off = tnum_and(false_32off, tnum_const(~val32));
-			if (is_power_of_2(val32))
-				true_32off = tnum_or(true_32off,
-						     tnum_const(val32));
+			t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			false_64off = tnum_and(false_64off, tnum_const(~val));
-			if (is_power_of_2(val))
-				true_64off = tnum_or(true_64off,
-						     tnum_const(val));
+			reg1->var_off = tnum_or(reg1->var_off, tnum_const(val));
 		}
 		break;
-	case BPF_JGE:
-	case BPF_JGT:
-	{
+	case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
 		if (is_jmp32) {
-			u32 false_umax = opcode == BPF_JGT ? val32  : val32 - 1;
-			u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
-
-			false_reg->u32_max_value = min(false_reg->u32_max_value,
-						       false_umax);
-			true_reg->u32_min_value = max(true_reg->u32_min_value,
-						      true_umin);
+			t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
-			u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
-			false_reg->umax_value = min(false_reg->umax_value, false_umax);
-			true_reg->umin_value = max(true_reg->umin_value, true_umin);
+			reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val));
 		}
 		break;
-	}
-	case BPF_JSGE:
-	case BPF_JSGT:
-	{
+	case BPF_JLE:
 		if (is_jmp32) {
-			s32 false_smax = opcode == BPF_JSGT ? sval32    : sval32 - 1;
-			s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
-
-			false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
-			true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
 		} else {
-			s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
-			s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
-
-			false_reg->smax_value = min(false_reg->smax_value, false_smax);
-			true_reg->smin_value = max(true_reg->smin_value, true_smin);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg2->umin_value = max(reg1->umin_value, reg2->umin_value);
 		}
 		break;
-	}
-	case BPF_JLE:
 	case BPF_JLT:
-	{
 		if (is_jmp32) {
-			u32 false_umin = opcode == BPF_JLT ? val32  : val32 + 1;
-			u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
-
-			false_reg->u32_min_value = max(false_reg->u32_min_value,
-						       false_umin);
-			true_reg->u32_max_value = min(true_reg->u32_max_value,
-						      true_umax);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1);
+			reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value);
 		} else {
-			u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
-			u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
-			false_reg->umin_value = max(false_reg->umin_value, false_umin);
-			true_reg->umax_value = min(true_reg->umax_value, true_umax);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1);
+			reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value);
 		}
 		break;
-	}
 	case BPF_JSLE:
+		if (is_jmp32) {
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+		} else {
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->smin_value = max(reg1->smin_value, reg2->smin_value);
+		}
+		break;
 	case BPF_JSLT:
-	{
 		if (is_jmp32) {
-			s32 false_smin = opcode == BPF_JSLT ? sval32    : sval32 + 1;
-			s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
-
-			false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
-			true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1);
+			reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value);
 		} else {
-			s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
-			s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
-
-			false_reg->smin_value = max(false_reg->smin_value, false_smin);
-			true_reg->smax_value = min(true_reg->smax_value, true_smax);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1);
+			reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value);
 		}
 		break;
-	}
+	case BPF_JGE:
+	case BPF_JGT:
+	case BPF_JSGE:
+	case BPF_JSGT:
+		/* just reuse LE/LT logic above */
+		opcode = flip_opcode(opcode);
+		swap(reg1, reg2);
+		goto again;
 	default:
 		return;
 	}
-
-	if (is_jmp32) {
-		false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
-					     tnum_subreg(false_32off));
-		true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
-					    tnum_subreg(true_32off));
-		__reg_combine_32_into_64(false_reg);
-		__reg_combine_32_into_64(true_reg);
-	} else {
-		false_reg->var_off = false_64off;
-		true_reg->var_off = true_64off;
-		__reg_combine_64_into_32(false_reg);
-		__reg_combine_64_into_32(true_reg);
-	}
 }
 
-/* Same as above, but for the case that dst_reg holds a constant and src_reg is
- * the variable reg.
+/* Adjusts the register min/max values in the case that the dst_reg and
+ * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K
+ * check, in which case we havea fake SCALAR_VALUE representing insn->imm).
+ * Technically we can do similar adjustments for pointers to the same object,
+ * but we don't support that right now.
  */
-static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
-				struct bpf_reg_state *false_reg,
-				u64 val, u32 val32,
-				u8 opcode, bool is_jmp32)
+static int reg_set_min_max(struct bpf_verifier_env *env,
+			   struct bpf_reg_state *true_reg1,
+			   struct bpf_reg_state *true_reg2,
+			   struct bpf_reg_state *false_reg1,
+			   struct bpf_reg_state *false_reg2,
+			   u8 opcode, bool is_jmp32)
 {
-	opcode = flip_opcode(opcode);
-	/* This uses zero as "not present in table"; luckily the zero opcode,
-	 * BPF_JA, can't get here.
+	int err;
+
+	/* If either register is a pointer, we can't learn anything about its
+	 * variable offset from the compare (unless they were a pointer into
+	 * the same object, but we don't bother with that).
 	 */
-	if (opcode)
-		reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
-}
-
-/* Regs are known to be equal, so intersect their min/max/var_off */
-static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
-				  struct bpf_reg_state *dst_reg)
-{
-	src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
-							dst_reg->umin_value);
-	src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
-							dst_reg->umax_value);
-	src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
-							dst_reg->smin_value);
-	src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
-							dst_reg->smax_value);
-	src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
-							     dst_reg->var_off);
-	reg_bounds_sync(src_reg);
-	reg_bounds_sync(dst_reg);
-}
+	if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
+		return 0;
 
-static void reg_combine_min_max(struct bpf_reg_state *true_src,
-				struct bpf_reg_state *true_dst,
-				struct bpf_reg_state *false_src,
-				struct bpf_reg_state *false_dst,
-				u8 opcode)
-{
-	switch (opcode) {
-	case BPF_JEQ:
-		__reg_combine_min_max(true_src, true_dst);
-		break;
-	case BPF_JNE:
-		__reg_combine_min_max(false_src, false_dst);
-		break;
-	}
+	/* fallthrough (FALSE) branch */
+	regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32);
+	reg_bounds_sync(false_reg1);
+	reg_bounds_sync(false_reg2);
+
+	/* jump (TRUE) branch */
+	regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32);
+	reg_bounds_sync(true_reg1);
+	reg_bounds_sync(true_reg2);
+
+	err = reg_bounds_sanity_check(env, true_reg1, "true_reg1");
+	err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2");
+	err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1");
+	err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2");
+	return err;
 }
 
 static void mark_ptr_or_null_reg(struct bpf_func_state *state,
@@ -14833,6 +14807,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
 	struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
 	struct bpf_reg_state *eq_branch_regs;
+	struct bpf_reg_state fake_reg = {};
 	u8 opcode = BPF_OP(insn->code);
 	bool is_jmp32;
 	int pred = -1;
@@ -14873,42 +14848,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
 			return -EINVAL;
 		}
+		src_reg = &fake_reg;
+		src_reg->type = SCALAR_VALUE;
+		__mark_reg_known(src_reg, insn->imm);
 	}
 
 	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
-
-	if (BPF_SRC(insn->code) == BPF_K) {
-		pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
-	} else if (src_reg->type == SCALAR_VALUE &&
-		   is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
-		pred = is_branch_taken(dst_reg,
-				       tnum_subreg(src_reg->var_off).value,
-				       opcode,
-				       is_jmp32);
-	} else if (src_reg->type == SCALAR_VALUE &&
-		   !is_jmp32 && tnum_is_const(src_reg->var_off)) {
-		pred = is_branch_taken(dst_reg,
-				       src_reg->var_off.value,
-				       opcode,
-				       is_jmp32);
-	} else if (dst_reg->type == SCALAR_VALUE &&
-		   is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off))) {
-		pred = is_branch_taken(src_reg,
-				       tnum_subreg(dst_reg->var_off).value,
-				       flip_opcode(opcode),
-				       is_jmp32);
-	} else if (dst_reg->type == SCALAR_VALUE &&
-		   !is_jmp32 && tnum_is_const(dst_reg->var_off)) {
-		pred = is_branch_taken(src_reg,
-				       dst_reg->var_off.value,
-				       flip_opcode(opcode),
-				       is_jmp32);
-	} else if (reg_is_pkt_pointer_any(dst_reg) &&
-		   reg_is_pkt_pointer_any(src_reg) &&
-		   !is_jmp32) {
-		pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
-	}
-
+	pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32);
 	if (pred >= 0) {
 		/* If we get here with a dst_reg pointer type it is because
 		 * above is_branch_taken() special cased the 0 comparison.
@@ -14956,53 +14902,27 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		return -EFAULT;
 	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
 
-	/* detect if we are comparing against a constant value so we can adjust
-	 * our min/max values for our dst register.
-	 * this is only legit if both are scalars (or pointers to the same
-	 * object, I suppose, see the PTR_MAYBE_NULL related if block below),
-	 * because otherwise the different base pointers mean the offsets aren't
-	 * comparable.
-	 */
 	if (BPF_SRC(insn->code) == BPF_X) {
-		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
-
-		if (dst_reg->type == SCALAR_VALUE &&
-		    src_reg->type == SCALAR_VALUE) {
-			if (tnum_is_const(src_reg->var_off) ||
-			    (is_jmp32 &&
-			     tnum_is_const(tnum_subreg(src_reg->var_off))))
-				reg_set_min_max(&other_branch_regs[insn->dst_reg],
-						dst_reg,
-						src_reg->var_off.value,
-						tnum_subreg(src_reg->var_off).value,
-						opcode, is_jmp32);
-			else if (tnum_is_const(dst_reg->var_off) ||
-				 (is_jmp32 &&
-				  tnum_is_const(tnum_subreg(dst_reg->var_off))))
-				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
-						    src_reg,
-						    dst_reg->var_off.value,
-						    tnum_subreg(dst_reg->var_off).value,
-						    opcode, is_jmp32);
-			else if (!is_jmp32 &&
-				 (opcode == BPF_JEQ || opcode == BPF_JNE))
-				/* Comparing for equality, we can combine knowledge */
-				reg_combine_min_max(&other_branch_regs[insn->src_reg],
-						    &other_branch_regs[insn->dst_reg],
-						    src_reg, dst_reg, opcode);
-			if (src_reg->id &&
-			    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
-				find_equal_scalars(this_branch, src_reg);
-				find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
-			}
-
-		}
-	} else if (dst_reg->type == SCALAR_VALUE) {
-		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-					dst_reg, insn->imm, (u32)insn->imm,
-					opcode, is_jmp32);
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      &other_branch_regs[insn->src_reg],
+				      dst_reg, src_reg, opcode, is_jmp32);
+	} else /* BPF_SRC(insn->code) == BPF_K */ {
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      src_reg /* fake one */,
+				      dst_reg, src_reg /* same fake one */,
+				      opcode, is_jmp32);
 	}
+	if (err)
+		return err;
 
+	if (BPF_SRC(insn->code) == BPF_X &&
+	    src_reg->type == SCALAR_VALUE && src_reg->id &&
+	    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
+		find_equal_scalars(this_branch, src_reg);
+		find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+	}
 	if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
 	    !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
 		find_equal_scalars(this_branch, dst_reg);
@@ -15274,12 +15194,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
-static int check_return_code(struct bpf_verifier_env *env, int regno)
+static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name)
 {
+	const char *exit_ctx = "At program exit";
 	struct tnum enforce_attach_type_range = tnum_unknown;
 	const struct bpf_prog *prog = env->prog;
 	struct bpf_reg_state *reg;
-	struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
+	struct bpf_retval_range range = retval_range(0, 1);
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	int err;
 	struct bpf_func_state *frame = env->cur_state->frame[0];
@@ -15321,17 +15242,9 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 
 	if (frame->in_async_callback_fn) {
 		/* enforce return zero from async callbacks like timer */
-		if (reg->type != SCALAR_VALUE) {
-			verbose(env, "In async callback the register R%d is not a known value (%s)\n",
-				regno, reg_type_str(env, reg->type));
-			return -EINVAL;
-		}
-
-		if (!tnum_in(const_0, reg->var_off)) {
-			verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
-			return -EINVAL;
-		}
-		return 0;
+		exit_ctx = "At async callback return";
+		range = retval_range(0, 0);
+		goto enforce_retval;
 	}
 
 	if (is_subprog && !frame->in_exception_callback_fn) {
@@ -15354,14 +15267,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
-			range = tnum_range(1, 1);
+			range = retval_range(1, 1);
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
-			range = tnum_range(0, 3);
+			range = retval_range(0, 3);
 		break;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
-			range = tnum_range(0, 3);
+			range = retval_range(0, 3);
 			enforce_attach_type_range = tnum_range(2, 3);
 		}
 		break;
@@ -15374,13 +15287,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 		if (!env->prog->aux->attach_btf_id)
 			return 0;
-		range = tnum_const(0);
+		range = retval_range(0, 0);
 		break;
 	case BPF_PROG_TYPE_TRACING:
 		switch (env->prog->expected_attach_type) {
 		case BPF_TRACE_FENTRY:
 		case BPF_TRACE_FEXIT:
-			range = tnum_const(0);
+			range = retval_range(0, 0);
 			break;
 		case BPF_TRACE_RAW_TP:
 		case BPF_MODIFY_RETURN:
@@ -15392,7 +15305,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		}
 		break;
 	case BPF_PROG_TYPE_SK_LOOKUP:
-		range = tnum_range(SK_DROP, SK_PASS);
+		range = retval_range(SK_DROP, SK_PASS);
 		break;
 
 	case BPF_PROG_TYPE_LSM:
@@ -15406,12 +15319,12 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 			/* Make sure programs that attach to void
 			 * hooks don't try to modify return value.
 			 */
-			range = tnum_range(1, 1);
+			range = retval_range(1, 1);
 		}
 		break;
 
 	case BPF_PROG_TYPE_NETFILTER:
-		range = tnum_range(NF_DROP, NF_ACCEPT);
+		range = retval_range(NF_DROP, NF_ACCEPT);
 		break;
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
@@ -15421,15 +15334,21 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 		return 0;
 	}
 
+enforce_retval:
 	if (reg->type != SCALAR_VALUE) {
-		verbose(env, "At program exit the register R%d is not a known value (%s)\n",
-			regno, reg_type_str(env, reg->type));
+		verbose(env, "%s the register R%d is not a known value (%s)\n",
+			exit_ctx, regno, reg_type_str(env, reg->type));
 		return -EINVAL;
 	}
 
-	if (!tnum_in(range, reg->var_off)) {
-		verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
-		if (prog->expected_attach_type == BPF_LSM_CGROUP &&
+	err = mark_chain_precision(env, regno);
+	if (err)
+		return err;
+
+	if (!retval_range_within(range, reg)) {
+		verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name);
+		if (!is_subprog &&
+		    prog->expected_attach_type == BPF_LSM_CGROUP &&
 		    prog_type == BPF_PROG_TYPE_LSM &&
 		    !prog->aux->attach_func_proto->type)
 			verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
@@ -17197,7 +17116,8 @@ hit:
 			 * the precision needs to be propagated back in
 			 * the current state.
 			 */
-			err = err ? : push_jmp_history(env, cur);
+			if (is_jmp_point(env, env->insn_idx))
+				err = err ? : push_jmp_history(env, cur, 0);
 			err = err ? : propagate_precision(env, &sl->state);
 			if (err)
 				return err;
@@ -17422,6 +17342,9 @@ static int do_check(struct bpf_verifier_env *env)
 		u8 class;
 		int err;
 
+		/* reset current history entry on each new instruction */
+		env->cur_hist_ent = NULL;
+
 		env->prev_insn_idx = prev_insn_idx;
 		if (env->insn_idx >= insn_cnt) {
 			verbose(env, "invalid insn idx %d insn_cnt %d\n",
@@ -17461,7 +17384,7 @@ static int do_check(struct bpf_verifier_env *env)
 		}
 
 		if (is_jmp_point(env, env->insn_idx)) {
-			err = push_jmp_history(env, state);
+			err = push_jmp_history(env, state, 0);
 			if (err)
 				return err;
 		}
@@ -17538,10 +17461,8 @@ static int do_check(struct bpf_verifier_env *env)
 					       insn->off, BPF_SIZE(insn->code),
 					       BPF_READ, insn->dst_reg, false,
 					       BPF_MODE(insn->code) == BPF_MEMSX);
-			if (err)
-				return err;
-
-			err = save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: reg_bounds_sanity_check(env, &regs[insn->dst_reg], "ldx");
 			if (err)
 				return err;
 		} else if (class == BPF_STX) {
@@ -17717,7 +17638,7 @@ process_bpf_exit_full:
 					continue;
 				}
 
-				err = check_return_code(env, BPF_REG_0);
+				err = check_return_code(env, BPF_REG_0, "R0");
 				if (err)
 					return err;
 process_bpf_exit:
@@ -18178,10 +18099,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				return -E2BIG;
 			}
 
+			if (env->prog->aux->sleepable)
+				atomic64_inc(&map->sleepable_refcnt);
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
-			 * and all maps are released in free_used_maps()
+			 * and all maps are released in bpf_free_used_maps()
 			 */
 			bpf_map_inc(map);
 
@@ -19398,9 +19321,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 
 		env->exception_callback_subprog = env->subprog_cnt - 1;
 		/* Don't update insn_cnt, as add_hidden_subprog always appends insns */
-		env->subprog_info[env->exception_callback_subprog].is_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+		mark_subprog_exc_cb(env, env->exception_callback_subprog);
 	}
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
@@ -20100,9 +20021,10 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
 	int ret, i;
@@ -20129,46 +20051,71 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex
 	state->first_insn_idx = env->subprog_info[subprog].start;
 	state->last_insn_idx = -1;
 
+
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
+		const char *sub_name = subprog_name(env, subprog);
+		struct bpf_subprog_arg_info *arg;
+		struct bpf_reg_state *reg;
+
+		verbose(env, "Validating %s() func#%d...\n", sub_name, subprog);
+		ret = btf_prepare_func_args(env, subprog);
 		if (ret)
 			goto out;
-		for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
-			if (regs[i].type == PTR_TO_CTX)
+
+		if (subprog_is_exc_cb(env, subprog)) {
+			state->frame[0]->in_exception_callback_fn = true;
+			/* We have already ensured that the callback returns an integer, just
+			 * like all global subprogs. We need to determine it only has a single
+			 * scalar argument.
+			 */
+			if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) {
+				verbose(env, "exception cb only supports single integer argument\n");
+				ret = -EINVAL;
+				goto out;
+			}
+		}
+		for (i = BPF_REG_1; i <= sub->arg_cnt; i++) {
+			arg = &sub->args[i - BPF_REG_1];
+			reg = &regs[i];
+
+			if (arg->arg_type == ARG_PTR_TO_CTX) {
+				reg->type = PTR_TO_CTX;
 				mark_reg_known_zero(env, regs, i);
-			else if (regs[i].type == SCALAR_VALUE)
+			} else if (arg->arg_type == ARG_ANYTHING) {
+				reg->type = SCALAR_VALUE;
 				mark_reg_unknown(env, regs, i);
-			else if (base_type(regs[i].type) == PTR_TO_MEM) {
-				const u32 mem_size = regs[i].mem_size;
-
+			} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+				/* assume unspecial LOCAL dynptr type */
+				__mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen);
+			} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+				reg->type = PTR_TO_MEM;
+				if (arg->arg_type & PTR_MAYBE_NULL)
+					reg->type |= PTR_MAYBE_NULL;
 				mark_reg_known_zero(env, regs, i);
-				regs[i].mem_size = mem_size;
-				regs[i].id = ++env->id_gen;
+				reg->mem_size = arg->mem_size;
+				reg->id = ++env->id_gen;
+			} else {
+				WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n",
+					  i - BPF_REG_1, arg->arg_type);
+				ret = -EFAULT;
+				goto out;
 			}
 		}
-		if (is_ex_cb) {
-			state->frame[0]->in_exception_callback_fn = true;
-			env->subprog_info[subprog].is_cb = true;
-			env->subprog_info[subprog].is_async_cb = true;
-			env->subprog_info[subprog].is_exception_cb = true;
-		}
 	} else {
+		/* if main BPF program has associated BTF info, validate that
+		 * it's matching expected signature, and otherwise mark BTF
+		 * info for main program as unreliable
+		 */
+		if (env->prog->aux->func_info_aux) {
+			ret = btf_prepare_func_args(env, 0);
+			if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX)
+				env->prog->aux->func_info_aux[0].unreliable = true;
+		}
+
 		/* 1st arg to a function */
 		regs[BPF_REG_1].type = PTR_TO_CTX;
 		mark_reg_known_zero(env, regs, BPF_REG_1);
-		ret = btf_check_subprog_arg_match(env, subprog, regs);
-		if (ret == -EFAULT)
-			/* unlikely verifier bug. abort.
-			 * ret == 0 and ret < 0 are sadly acceptable for
-			 * main() function due to backward compatibility.
-			 * Like socket filter program may be written as:
-			 * int bpf_prog(struct pt_regs *ctx)
-			 * and never dereference that ctx in the program.
-			 * 'struct pt_regs' is a type mismatch for socket
-			 * filter that should be using 'struct __sk_buff'.
-			 */
-			goto out;
 	}
 
 	ret = do_check(env);
@@ -20187,8 +20134,11 @@ out:
 	return ret;
 }
 
-/* Verify all global functions in a BPF program one by one based on their BTF.
- * All global functions must pass verification. Otherwise the whole program is rejected.
+/* Lazily verify all global functions based on their BTF, if they are called
+ * from main BPF program or any of subprograms transitively.
+ * BPF global subprogs called from dead code are not validated.
+ * All callable global functions must pass verification.
+ * Otherwise the whole program is rejected.
  * Consider:
  * int bar(int);
  * int foo(int f)
@@ -20207,25 +20157,50 @@ out:
 static int do_check_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_aux *aux = env->prog->aux;
-	int i, ret;
+	struct bpf_func_info_aux *sub_aux;
+	int 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;
+
+again:
+	new_cnt = 0;
 	for (i = 1; i < env->subprog_cnt; i++) {
-		if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+		if (!subprog_is_global(env, i))
+			continue;
+
+		sub_aux = subprog_aux(env, i);
+		if (!sub_aux->called || sub_aux->verified)
 			continue;
+
 		env->insn_idx = env->subprog_info[i].start;
 		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i, env->exception_callback_subprog == i);
+		ret = do_check_common(env, i);
 		if (ret) {
 			return ret;
 		} else if (env->log.level & BPF_LOG_LEVEL) {
-			verbose(env,
-				"Func#%d is safe for any args that match its prototype\n",
-				i);
+			verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
+				i, subprog_name(env, i));
 		}
+
+		/* 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.
+	 */
+	if (new_cnt)
+		goto again;
+
 	return 0;
 }
 
@@ -20234,7 +20209,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0, false);
+	ret = do_check_common(env, 0);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
@@ -20356,6 +20331,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    struct bpf_attach_target_info *tgt_info)
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
 	const char prefix[] = "btf_trace_";
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
@@ -20426,10 +20402,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
-		if (tgt_prog->type == prog->type) {
-			/* Cannot fentry/fexit another fentry/fexit program.
-			 * Cannot attach program extension to another extension.
-			 * It's ok to attach fentry/fexit to extension program.
+		if (prog_tracing) {
+			if (aux->attach_tracing_prog) {
+				/*
+				 * Target program is an fentry/fexit which is already attached
+				 * to another tracing program. More levels of nesting
+				 * attachment are not allowed.
+				 */
+				bpf_log(log, "Cannot nest tracing program attach more than once\n");
+				return -EINVAL;
+			}
+		} else if (tgt_prog->type == prog->type) {
+			/*
+			 * To avoid potential call chain cycles, prevent attaching of a
+			 * program extension to another extension. It's ok to attach
+			 * fentry/fexit to extension program.
 			 */
 			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
@@ -20442,16 +20429,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			 * except fentry/fexit. The reason is the following.
 			 * The fentry/fexit programs are used for performance
 			 * analysis, stats and can be attached to any program
-			 * type except themselves. When extension program is
-			 * replacing XDP function it is necessary to allow
-			 * performance analysis of all functions. Both original
-			 * XDP program and its program extension. Hence
-			 * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
-			 * allowed. If extending of fentry/fexit was allowed it
-			 * would be possible to create long call chain
-			 * fentry->extension->fentry->extension beyond
-			 * reasonable stack size. Hence extending fentry is not
-			 * allowed.
+			 * type. When extension program is replacing XDP function
+			 * it is necessary to allow performance analysis of all
+			 * functions. Both original XDP program and its program
+			 * extension. Hence attaching fentry/fexit to
+			 * BPF_PROG_TYPE_EXT is allowed. If extending of
+			 * fentry/fexit was allowed it would be possible to create
+			 * long call chain fentry->extension->fentry->extension
+			 * beyond reasonable stack size. Hence extending fentry
+			 * is not allowed.
 			 */
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
@@ -20828,6 +20814,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
+	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
 
 	env->explored_states = kvcalloc(state_htab_size(env),
 				       sizeof(struct bpf_verifier_state_list *),
@@ -20870,8 +20857,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
-	ret = do_check_subprogs(env);
-	ret = ret ?: do_check_main(env);
+	ret = do_check_main(env);
+	ret = ret ?: do_check_subprogs(env);
 
 	if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
 		ret = bpf_prog_offload_finalize(env);