1 files changed, 309 insertions, 279 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3eadb14e090b..6f6d2d511c06 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -23,6 +23,7 @@
 #include <linux/error-injection.h>
 #include <linux/bpf_lsm.h>
 #include <linux/btf_ids.h>
+#include <linux/poison.h>
 
 #include "disasm.h"
 
@@ -370,6 +371,7 @@ __printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
 	bpf_verifier_vlog(log, fmt, args);
 	va_end(args);
 }
+EXPORT_SYMBOL_GPL(bpf_log);
 
 static const char *ltrim(const char *s)
 {
@@ -427,6 +429,7 @@ static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 
 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;
 }
@@ -456,10 +459,9 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 
 static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
 {
-	return base_type(type) == PTR_TO_SOCKET ||
-		base_type(type) == PTR_TO_TCP_SOCK ||
-		base_type(type) == PTR_TO_MEM ||
-		base_type(type) == PTR_TO_BTF_ID;
+	type = base_type(type);
+	return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_MEM || type == PTR_TO_BTF_ID;
 }
 
 static bool type_is_rdonly_mem(u32 type)
@@ -467,25 +469,11 @@ static bool type_is_rdonly_mem(u32 type)
 	return type & MEM_RDONLY;
 }
 
-static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_SOCK_COMMON;
-}
-
 static bool type_may_be_null(u32 type)
 {
 	return type & PTR_MAYBE_NULL;
 }
 
-static bool may_be_acquire_function(enum bpf_func_id func_id)
-{
-	return func_id == BPF_FUNC_sk_lookup_tcp ||
-		func_id == BPF_FUNC_sk_lookup_udp ||
-		func_id == BPF_FUNC_skc_lookup_tcp ||
-		func_id == BPF_FUNC_map_lookup_elem ||
-	        func_id == BPF_FUNC_ringbuf_reserve;
-}
-
 static bool is_acquire_function(enum bpf_func_id func_id,
 				const struct bpf_map *map)
 {
@@ -518,6 +506,26 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
+static bool is_dynptr_ref_function(enum bpf_func_id func_id)
+{
+	return func_id == BPF_FUNC_dynptr_data;
+}
+
+static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id,
+					const struct bpf_map *map)
+{
+	int ref_obj_uses = 0;
+
+	if (is_ptr_cast_function(func_id))
+		ref_obj_uses++;
+	if (is_acquire_function(func_id, map))
+		ref_obj_uses++;
+	if (is_dynptr_ref_function(func_id))
+		ref_obj_uses++;
+
+	return ref_obj_uses > 1;
+}
+
 static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 {
 	return BPF_CLASS(insn->code) == BPF_STX &&
@@ -555,6 +563,7 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 		[PTR_TO_BUF]		= "buf",
 		[PTR_TO_FUNC]		= "func",
 		[PTR_TO_MAP_KEY]	= "map_key",
+		[PTR_TO_DYNPTR]		= "dynptr_ptr",
 	};
 
 	if (type & PTR_MAYBE_NULL) {
@@ -773,8 +782,8 @@ static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_
 	return true;
 }
 
-static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-				     enum bpf_arg_type arg_type)
+bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env,
+			      struct bpf_reg_state *reg)
 {
 	struct bpf_func_state *state = func(env, reg);
 	int spi = get_spi(reg->off);
@@ -790,11 +799,24 @@ static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_re
 			return false;
 	}
 
+	return true;
+}
+
+bool is_dynptr_type_expected(struct bpf_verifier_env *env,
+			     struct bpf_reg_state *reg,
+			     enum bpf_arg_type arg_type)
+{
+	struct bpf_func_state *state = func(env, reg);
+	enum bpf_dynptr_type dynptr_type;
+	int spi = get_spi(reg->off);
+
 	/* ARG_PTR_TO_DYNPTR takes any type of dynptr */
 	if (arg_type == ARG_PTR_TO_DYNPTR)
 		return true;
 
-	return state->stack[spi].spilled_ptr.dynptr.type == arg_to_dynptr_type(arg_type);
+	dynptr_type = arg_to_dynptr_type(arg_type);
+
+	return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type;
 }
 
 /* The reg state of a pointer or a bounded scalar was saved when
@@ -1086,6 +1108,7 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
 	id = ++env->id_gen;
 	state->refs[new_ofs].id = id;
 	state->refs[new_ofs].insn_idx = insn_idx;
+	state->refs[new_ofs].callback_ref = state->in_callback_fn ? state->frameno : 0;
 
 	return id;
 }
@@ -1098,6 +1121,9 @@ static int release_reference_state(struct bpf_func_state *state, int ptr_id)
 	last_idx = state->acquired_refs - 1;
 	for (i = 0; i < state->acquired_refs; i++) {
 		if (state->refs[i].id == ptr_id) {
+			/* Cannot release caller references in callbacks */
+			if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+				return -EINVAL;
 			if (last_idx && i != last_idx)
 				memcpy(&state->refs[i], &state->refs[last_idx],
 				       sizeof(*state->refs));
@@ -1739,6 +1765,7 @@ 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);
 	init_reg_state(env, state);
 	mark_verifier_state_scratched(env);
 }
@@ -2898,7 +2925,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	return 0;
 }
 
-static int mark_chain_precision(struct bpf_verifier_env *env, int regno)
+int mark_chain_precision(struct bpf_verifier_env *env, int regno)
 {
 	return __mark_chain_precision(env, regno, -1);
 }
@@ -5223,6 +5250,25 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 				env,
 				regno, reg->off, access_size,
 				zero_size_allowed, ACCESS_HELPER, meta);
+	case PTR_TO_CTX:
+		/* in case the function doesn't know how to access the context,
+		 * (because we are in a program of type SYSCALL for example), we
+		 * can not statically check its size.
+		 * Dynamically check it now.
+		 */
+		if (!env->ops->convert_ctx_access) {
+			enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ;
+			int offset = access_size - 1;
+
+			/* Allow zero-byte read from PTR_TO_CTX */
+			if (access_size == 0)
+				return zero_size_allowed ? 0 : -EACCES;
+
+			return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
+						atype, -1, false);
+		}
+
+		fallthrough;
 	default: /* scalar_value or invalid ptr */
 		/* Allow zero-byte read from NULL, regardless of pointer type */
 		if (zero_size_allowed && access_size == 0 &&
@@ -5656,6 +5702,12 @@ static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK }
 static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
 static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } };
 static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } };
+static const struct bpf_reg_types dynptr_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL,
+	}
+};
 
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -5682,7 +5734,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
 	[ARG_PTR_TO_KPTR]		= &kptr_types,
-	[ARG_PTR_TO_DYNPTR]		= &stack_ptr_types,
+	[ARG_PTR_TO_DYNPTR]		= &dynptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -5751,13 +5803,22 @@ found:
 		if (meta->func_id == BPF_FUNC_kptr_xchg) {
 			if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno))
 				return -EACCES;
-		} else if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
-						 btf_vmlinux, *arg_btf_id,
-						 strict_type_match)) {
-			verbose(env, "R%d is of type %s but %s is expected\n",
-				regno, kernel_type_name(reg->btf, reg->btf_id),
-				kernel_type_name(btf_vmlinux, *arg_btf_id));
-			return -EACCES;
+		} else {
+			if (arg_btf_id == BPF_PTR_POISON) {
+				verbose(env, "verifier internal error:");
+				verbose(env, "R%d has non-overwritten BPF_PTR_POISON type\n",
+					regno);
+				return -EACCES;
+			}
+
+			if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+						  btf_vmlinux, *arg_btf_id,
+						  strict_type_match)) {
+				verbose(env, "R%d is of type %s but %s is expected\n",
+					regno, kernel_type_name(reg->btf, reg->btf_id),
+					kernel_type_name(btf_vmlinux, *arg_btf_id));
+				return -EACCES;
+			}
 		}
 	}
 
@@ -6025,6 +6086,13 @@ skip_type_check:
 		err = check_mem_size_reg(env, reg, regno, true, meta);
 		break;
 	case ARG_PTR_TO_DYNPTR:
+		/* We only need to check for initialized / uninitialized helper
+		 * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the
+		 * assumption is that if it is, that a helper function
+		 * initialized the dynptr on behalf of the BPF program.
+		 */
+		if (base_type(reg->type) == PTR_TO_DYNPTR)
+			break;
 		if (arg_type & MEM_UNINIT) {
 			if (!is_dynptr_reg_valid_uninit(env, reg)) {
 				verbose(env, "Dynptr has to be an uninitialized dynptr\n");
@@ -6040,21 +6108,27 @@ skip_type_check:
 			}
 
 			meta->uninit_dynptr_regno = regno;
-		} else if (!is_dynptr_reg_valid_init(env, reg, arg_type)) {
+		} else if (!is_dynptr_reg_valid_init(env, reg)) {
+			verbose(env,
+				"Expected an initialized dynptr as arg #%d\n",
+				arg + 1);
+			return -EINVAL;
+		} else if (!is_dynptr_type_expected(env, reg, arg_type)) {
 			const char *err_extra = "";
 
 			switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
 			case DYNPTR_TYPE_LOCAL:
-				err_extra = "local ";
+				err_extra = "local";
 				break;
 			case DYNPTR_TYPE_RINGBUF:
-				err_extra = "ringbuf ";
+				err_extra = "ringbuf";
 				break;
 			default:
+				err_extra = "<unknown>";
 				break;
 			}
-
-			verbose(env, "Expected an initialized %sdynptr as arg #%d\n",
+			verbose(env,
+				"Expected a dynptr of type %s as arg #%d\n",
 				err_extra, arg + 1);
 			return -EINVAL;
 		}
@@ -6199,6 +6273,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_ringbuf_discard_dynptr)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_USER_RINGBUF:
+		if (func_id != BPF_FUNC_user_ringbuf_drain)
+			goto error;
+		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
 		if (func_id != BPF_FUNC_get_stackid)
 			goto error;
@@ -6318,6 +6396,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_RINGBUF)
 			goto error;
 		break;
+	case BPF_FUNC_user_ringbuf_drain:
+		if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF)
+			goto error;
+		break;
 	case BPF_FUNC_get_stackid:
 		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
 			goto error;
@@ -6456,33 +6538,6 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
-{
-	int count = 0;
-
-	if (arg_type_may_be_refcounted(fn->arg1_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg2_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg3_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg4_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg5_type))
-		count++;
-
-	/* A reference acquiring function cannot acquire
-	 * another refcounted ptr.
-	 */
-	if (may_be_acquire_function(func_id) && count)
-		return false;
-
-	/* We only support one arg being unreferenced at the moment,
-	 * which is sufficient for the helper functions we have right now.
-	 */
-	return count <= 1;
-}
-
 static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 {
 	int i;
@@ -6501,43 +6556,25 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static int check_func_proto(const struct bpf_func_proto *fn, int func_id,
-			    struct bpf_call_arg_meta *meta)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
-	       check_btf_id_ok(fn) &&
-	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
+	       check_btf_id_ok(fn) ? 0 : -EINVAL;
 }
 
 /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
  * are now invalid, so turn them into unknown SCALAR_VALUE.
  */
-static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
-				     struct bpf_func_state *state)
+static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 {
-	struct bpf_reg_state *regs = state->regs, *reg;
-	int i;
-
-	for (i = 0; i < MAX_BPF_REG; i++)
-		if (reg_is_pkt_pointer_any(&regs[i]))
-			mark_reg_unknown(env, regs, i);
+	struct bpf_func_state *state;
+	struct bpf_reg_state *reg;
 
-	bpf_for_each_spilled_reg(i, state, reg) {
-		if (!reg)
-			continue;
+	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
 		if (reg_is_pkt_pointer_any(reg))
 			__mark_reg_unknown(env, reg);
-	}
-}
-
-static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
-{
-	struct bpf_verifier_state *vstate = env->cur_state;
-	int i;
-
-	for (i = 0; i <= vstate->curframe; i++)
-		__clear_all_pkt_pointers(env, vstate->frame[i]);
+	}));
 }
 
 enum {
@@ -6566,41 +6603,24 @@ static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range
 		reg->range = AT_PKT_END;
 }
 
-static void release_reg_references(struct bpf_verifier_env *env,
-				   struct bpf_func_state *state,
-				   int ref_obj_id)
-{
-	struct bpf_reg_state *regs = state->regs, *reg;
-	int i;
-
-	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].ref_obj_id == ref_obj_id)
-			mark_reg_unknown(env, regs, i);
-
-	bpf_for_each_spilled_reg(i, state, reg) {
-		if (!reg)
-			continue;
-		if (reg->ref_obj_id == ref_obj_id)
-			__mark_reg_unknown(env, reg);
-	}
-}
-
 /* The pointer with the specified id has released its reference to kernel
  * resources. Identify all copies of the same pointer and clear the reference.
  */
 static int release_reference(struct bpf_verifier_env *env,
 			     int ref_obj_id)
 {
-	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_func_state *state;
+	struct bpf_reg_state *reg;
 	int err;
-	int i;
 
 	err = release_reference_state(cur_func(env), ref_obj_id);
 	if (err)
 		return err;
 
-	for (i = 0; i <= vstate->curframe; i++)
-		release_reg_references(env, vstate->frame[i], ref_obj_id);
+	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+		if (reg->ref_obj_id == ref_obj_id)
+			__mark_reg_unknown(env, reg);
+	}));
 
 	return 0;
 }
@@ -6648,7 +6668,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	func_info_aux = env->prog->aux->func_info_aux;
 	if (func_info_aux)
 		is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_subprog_arg_match(env, subprog, caller->regs);
+	err = btf_check_subprog_call(env, subprog, caller->regs);
 	if (err == -EFAULT)
 		return err;
 	if (is_global) {
@@ -6822,6 +6842,7 @@ 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);
 	return 0;
 }
 
@@ -6843,6 +6864,7 @@ 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);
 	return 0;
 }
 
@@ -6872,6 +6894,7 @@ 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);
 	return 0;
 }
 
@@ -6899,6 +6922,30 @@ 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);
+	return 0;
+}
+
+static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
+					   struct bpf_func_state *caller,
+					   struct bpf_func_state *callee,
+					   int insn_idx)
+{
+	/* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void
+	 *			  callback_ctx, u64 flags);
+	 * callback_fn(struct bpf_dynptr_t* dynptr, void *callback_ctx);
+	 */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_0]);
+	callee->regs[BPF_REG_1].type = PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL;
+	__mark_reg_known_zero(&callee->regs[BPF_REG_1]);
+	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+
+	callee->in_callback_fn = true;
 	return 0;
 }
 
@@ -6926,7 +6973,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	caller = state->frame[state->curframe];
 	if (callee->in_callback_fn) {
 		/* enforce R0 return value range [0, 1]. */
-		struct tnum range = tnum_range(0, 1);
+		struct tnum range = callee->callback_ret_range;
 
 		if (r0->type != SCALAR_VALUE) {
 			verbose(env, "R0 not a scalar value\n");
@@ -6941,10 +6988,17 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		caller->regs[BPF_REG_0] = *r0;
 	}
 
-	/* Transfer references to the caller */
-	err = copy_reference_state(caller, callee);
-	if (err)
-		return err;
+	/* callback_fn frame should have released its own additions to parent's
+	 * reference state at this point, or check_reference_leak would
+	 * complain, hence it must be the same as the caller. There is no need
+	 * to copy it back.
+	 */
+	if (!callee->in_callback_fn) {
+		/* Transfer references to the caller */
+		err = copy_reference_state(caller, callee);
+		if (err)
+			return err;
+	}
 
 	*insn_idx = callee->callsite + 1;
 	if (env->log.level & BPF_LOG_LEVEL) {
@@ -7066,13 +7120,20 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 static int check_reference_leak(struct bpf_verifier_env *env)
 {
 	struct bpf_func_state *state = cur_func(env);
+	bool refs_lingering = false;
 	int i;
 
+	if (state->frameno && !state->in_callback_fn)
+		return 0;
+
 	for (i = 0; i < state->acquired_refs; i++) {
+		if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+			continue;
 		verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
 			state->refs[i].id, state->refs[i].insn_idx);
+		refs_lingering = true;
 	}
-	return state->acquired_refs ? -EINVAL : 0;
+	return refs_lingering ? -EINVAL : 0;
 }
 
 static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
@@ -7219,7 +7280,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
 
-	err = check_func_proto(fn, func_id, &meta);
+	err = check_func_proto(fn, func_id);
 	if (err) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
@@ -7344,6 +7405,33 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			}
 		}
 		break;
+	case BPF_FUNC_dynptr_data:
+		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
+			if (arg_type_is_dynptr(fn->arg_type[i])) {
+				struct bpf_reg_state *reg = &regs[BPF_REG_1 + i];
+
+				if (meta.ref_obj_id) {
+					verbose(env, "verifier internal error: meta.ref_obj_id already set\n");
+					return -EFAULT;
+				}
+
+				if (base_type(reg->type) != PTR_TO_DYNPTR)
+					/* Find the id of the dynptr we're
+					 * tracking the reference of
+					 */
+					meta.ref_obj_id = stack_slot_get_id(env, reg);
+				break;
+			}
+		}
+		if (i == MAX_BPF_FUNC_REG_ARGS) {
+			verbose(env, "verifier internal error: no dynptr in bpf_dynptr_data()\n");
+			return -EFAULT;
+		}
+		break;
+	case BPF_FUNC_user_ringbuf_drain:
+		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
+					set_user_ringbuf_callback_state);
+		break;
 	}
 
 	if (err)
@@ -7360,13 +7448,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	/* update return register (already marked as written above) */
 	ret_type = fn->ret_type;
-	ret_flag = type_flag(fn->ret_type);
-	if (ret_type == RET_INTEGER) {
+	ret_flag = type_flag(ret_type);
+
+	switch (base_type(ret_type)) {
+	case RET_INTEGER:
 		/* sets type to SCALAR_VALUE */
 		mark_reg_unknown(env, regs, BPF_REG_0);
-	} else if (ret_type == RET_VOID) {
+		break;
+	case RET_VOID:
 		regs[BPF_REG_0].type = NOT_INIT;
-	} else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) {
+		break;
+	case RET_PTR_TO_MAP_VALUE:
 		/* There is no offset yet applied, variable or fixed */
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		/* remember map_ptr, so that check_map_access()
@@ -7385,20 +7477,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		    map_value_has_spin_lock(meta.map_ptr)) {
 			regs[BPF_REG_0].id = ++env->id_gen;
 		}
-	} else if (base_type(ret_type) == RET_PTR_TO_SOCKET) {
+		break;
+	case RET_PTR_TO_SOCKET:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) {
+		break;
+	case RET_PTR_TO_SOCK_COMMON:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) {
+		break;
+	case RET_PTR_TO_TCP_SOCK:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) {
+		break;
+	case RET_PTR_TO_ALLOC_MEM:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
-	} else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) {
+		break;
+	case RET_PTR_TO_MEM_OR_BTF_ID:
+	{
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -7430,7 +7528,10 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			regs[BPF_REG_0].btf = meta.ret_btf;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
-	} else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
+		break;
+	}
+	case RET_PTR_TO_BTF_ID:
+	{
 		struct btf *ret_btf;
 		int ret_btf_id;
 
@@ -7440,6 +7541,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			ret_btf = meta.kptr_off_desc->kptr.btf;
 			ret_btf_id = meta.kptr_off_desc->kptr.btf_id;
 		} else {
+			if (fn->ret_btf_id == BPF_PTR_POISON) {
+				verbose(env, "verifier internal error:");
+				verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n",
+					func_id_name(func_id));
+				return -EINVAL;
+			}
 			ret_btf = btf_vmlinux;
 			ret_btf_id = *fn->ret_btf_id;
 		}
@@ -7451,7 +7558,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		regs[BPF_REG_0].btf = ret_btf;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
-	} else {
+		break;
+	}
+	default:
 		verbose(env, "unknown return type %u of func %s#%d\n",
 			base_type(ret_type), func_id_name(func_id), func_id);
 		return -EINVAL;
@@ -7460,7 +7569,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	if (type_may_be_null(regs[BPF_REG_0].type))
 		regs[BPF_REG_0].id = ++env->id_gen;
 
-	if (is_ptr_cast_function(func_id)) {
+	if (helper_multiple_ref_obj_use(func_id, meta.map_ptr)) {
+		verbose(env, "verifier internal error: func %s#%d sets ref_obj_id more than once\n",
+			func_id_name(func_id), func_id);
+		return -EFAULT;
+	}
+
+	if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) {
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
 	} else if (is_acquire_function(func_id, meta.map_ptr)) {
@@ -7472,21 +7587,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].id = id;
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = id;
-	} else if (func_id == BPF_FUNC_dynptr_data) {
-		int dynptr_id = 0, i;
-
-		/* Find the id of the dynptr we're acquiring a reference to */
-		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
-			if (arg_type_is_dynptr(fn->arg_type[i])) {
-				if (dynptr_id) {
-					verbose(env, "verifier internal error: multiple dynptr args in func\n");
-					return -EFAULT;
-				}
-				dynptr_id = stack_slot_get_id(env, &regs[BPF_REG_1 + i]);
-			}
-		}
-		/* For release_reference() */
-		regs[BPF_REG_0].ref_obj_id = dynptr_id;
 	}
 
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
@@ -7558,6 +7658,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 {
 	const struct btf_type *t, *func, *func_proto, *ptr_type;
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_kfunc_arg_meta meta = { 0 };
 	const char *func_name, *ptr_type_name;
 	u32 i, nargs, func_id, ptr_type_id;
 	int err, insn_idx = *insn_idx_p;
@@ -7585,10 +7686,17 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			func_name);
 		return -EACCES;
 	}
+	if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) {
+		verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n");
+		return -EACCES;
+	}
+
 	acq = *kfunc_flags & KF_ACQUIRE;
 
+	meta.flags = *kfunc_flags;
+
 	/* Check the arguments */
-	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, *kfunc_flags);
+	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta);
 	if (err < 0)
 		return err;
 	/* In case of release function, we get register number of refcounted
@@ -7609,7 +7717,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* Check return type */
 	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
 
-	if (acq && !btf_type_is_ptr(t)) {
+	if (acq && !btf_type_is_struct_ptr(desc_btf, t)) {
 		verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
 		return -EINVAL;
 	}
@@ -7621,17 +7729,33 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		ptr_type = btf_type_skip_modifiers(desc_btf, t->type,
 						   &ptr_type_id);
 		if (!btf_type_is_struct(ptr_type)) {
-			ptr_type_name = btf_name_by_offset(desc_btf,
-							   ptr_type->name_off);
-			verbose(env, "kernel function %s returns pointer type %s %s is not supported\n",
-				func_name, btf_type_str(ptr_type),
-				ptr_type_name);
-			return -EINVAL;
+			if (!meta.r0_size) {
+				ptr_type_name = btf_name_by_offset(desc_btf,
+								   ptr_type->name_off);
+				verbose(env,
+					"kernel function %s returns pointer type %s %s is not supported\n",
+					func_name,
+					btf_type_str(ptr_type),
+					ptr_type_name);
+				return -EINVAL;
+			}
+
+			mark_reg_known_zero(env, regs, BPF_REG_0);
+			regs[BPF_REG_0].type = PTR_TO_MEM;
+			regs[BPF_REG_0].mem_size = meta.r0_size;
+
+			if (meta.r0_rdonly)
+				regs[BPF_REG_0].type |= MEM_RDONLY;
+
+			/* Ensures we don't access the memory after a release_reference() */
+			if (meta.ref_obj_id)
+				regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+		} else {
+			mark_reg_known_zero(env, regs, BPF_REG_0);
+			regs[BPF_REG_0].btf = desc_btf;
+			regs[BPF_REG_0].type = PTR_TO_BTF_ID;
+			regs[BPF_REG_0].btf_id = ptr_type_id;
 		}
-		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].btf = desc_btf;
-		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
-		regs[BPF_REG_0].btf_id = ptr_type_id;
 		if (*kfunc_flags & KF_RET_NULL) {
 			regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
 			/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
@@ -9274,34 +9398,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
-static void __find_good_pkt_pointers(struct bpf_func_state *state,
-				     struct bpf_reg_state *dst_reg,
-				     enum bpf_reg_type type, int new_range)
-{
-	struct bpf_reg_state *reg;
-	int i;
-
-	for (i = 0; i < MAX_BPF_REG; i++) {
-		reg = &state->regs[i];
-		if (reg->type == type && reg->id == dst_reg->id)
-			/* keep the maximum range already checked */
-			reg->range = max(reg->range, new_range);
-	}
-
-	bpf_for_each_spilled_reg(i, state, reg) {
-		if (!reg)
-			continue;
-		if (reg->type == type && reg->id == dst_reg->id)
-			reg->range = max(reg->range, new_range);
-	}
-}
-
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 				   struct bpf_reg_state *dst_reg,
 				   enum bpf_reg_type type,
 				   bool range_right_open)
 {
-	int new_range, i;
+	struct bpf_func_state *state;
+	struct bpf_reg_state *reg;
+	int new_range;
 
 	if (dst_reg->off < 0 ||
 	    (dst_reg->off == 0 && range_right_open))
@@ -9366,9 +9470,11 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	 * the range won't allow anything.
 	 * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
 	 */
-	for (i = 0; i <= vstate->curframe; i++)
-		__find_good_pkt_pointers(vstate->frame[i], dst_reg, type,
-					 new_range);
+	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+		if (reg->type == type && reg->id == dst_reg->id)
+			/* keep the maximum range already checked */
+			reg->range = max(reg->range, new_range);
+	}));
 }
 
 static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
@@ -9857,7 +9963,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 
 		if (!reg_may_point_to_spin_lock(reg)) {
 			/* For not-NULL ptr, reg->ref_obj_id will be reset
-			 * in release_reg_references().
+			 * in release_reference().
 			 *
 			 * reg->id is still used by spin_lock ptr. Other
 			 * than spin_lock ptr type, reg->id can be reset.
@@ -9867,22 +9973,6 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 	}
 }
 
-static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id,
-				    bool is_null)
-{
-	struct bpf_reg_state *reg;
-	int i;
-
-	for (i = 0; i < MAX_BPF_REG; i++)
-		mark_ptr_or_null_reg(state, &state->regs[i], id, is_null);
-
-	bpf_for_each_spilled_reg(i, state, reg) {
-		if (!reg)
-			continue;
-		mark_ptr_or_null_reg(state, reg, id, is_null);
-	}
-}
-
 /* The logic is similar to find_good_pkt_pointers(), both could eventually
  * be folded together at some point.
  */
@@ -9890,10 +9980,9 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 				  bool is_null)
 {
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
-	struct bpf_reg_state *regs = state->regs;
+	struct bpf_reg_state *regs = state->regs, *reg;
 	u32 ref_obj_id = regs[regno].ref_obj_id;
 	u32 id = regs[regno].id;
-	int i;
 
 	if (ref_obj_id && ref_obj_id == id && is_null)
 		/* regs[regno] is in the " == NULL" branch.
@@ -9902,8 +9991,9 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 		 */
 		WARN_ON_ONCE(release_reference_state(state, id));
 
-	for (i = 0; i <= vstate->curframe; i++)
-		__mark_ptr_or_null_regs(vstate->frame[i], id, is_null);
+	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+		mark_ptr_or_null_reg(state, reg, id, is_null);
+	}));
 }
 
 static bool try_match_pkt_pointers(const struct bpf_insn *insn,
@@ -10016,23 +10106,11 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate,
 {
 	struct bpf_func_state *state;
 	struct bpf_reg_state *reg;
-	int i, j;
-
-	for (i = 0; i <= vstate->curframe; i++) {
-		state = vstate->frame[i];
-		for (j = 0; j < MAX_BPF_REG; j++) {
-			reg = &state->regs[j];
-			if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
-				*reg = *known_reg;
-		}
 
-		bpf_for_each_spilled_reg(j, state, reg) {
-			if (!reg)
-				continue;
-			if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
-				*reg = *known_reg;
-		}
-	}
+	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+		if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+			*reg = *known_reg;
+	}));
 }
 
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
@@ -12333,6 +12411,16 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
+				/* We must do check_reference_leak here before
+				 * prepare_func_exit to handle the case when
+				 * state->curframe > 0, it may be a callback
+				 * function, for which reference_state must
+				 * match caller reference state when it exits.
+				 */
+				err = check_reference_leak(env);
+				if (err)
+					return err;
+
 				if (state->curframe) {
 					/* exit from nested function */
 					err = prepare_func_exit(env, &env->insn_idx);
@@ -12342,10 +12430,6 @@ static int do_check(struct bpf_verifier_env *env)
 					continue;
 				}
 
-				err = check_reference_leak(env);
-				if (err)
-					return err;
-
 				err = check_return_code(env);
 				if (err)
 					return err;
@@ -12558,14 +12642,6 @@ err_put:
 	return err;
 }
 
-static int check_map_prealloc(struct bpf_map *map)
-{
-	return (map->map_type != BPF_MAP_TYPE_HASH &&
-		map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
-		map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
-		!(map->map_flags & BPF_F_NO_PREALLOC);
-}
-
 static bool is_tracing_prog_type(enum bpf_prog_type type)
 {
 	switch (type) {
@@ -12580,50 +12656,12 @@ static bool is_tracing_prog_type(enum bpf_prog_type type)
 	}
 }
 
-static bool is_preallocated_map(struct bpf_map *map)
-{
-	if (!check_map_prealloc(map))
-		return false;
-	if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta))
-		return false;
-	return true;
-}
-
 static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(prog);
-	/*
-	 * Validate that trace type programs use preallocated hash maps.
-	 *
-	 * For programs attached to PERF events this is mandatory as the
-	 * perf NMI can hit any arbitrary code sequence.
-	 *
-	 * All other trace types using preallocated hash maps are unsafe as
-	 * well because tracepoint or kprobes can be inside locked regions
-	 * of the memory allocator or at a place where a recursion into the
-	 * memory allocator would see inconsistent state.
-	 *
-	 * On RT enabled kernels run-time allocation of all trace type
-	 * programs is strictly prohibited due to lock type constraints. On
-	 * !RT kernels it is allowed for backwards compatibility reasons for
-	 * now, but warnings are emitted so developers are made aware of
-	 * the unsafety and can fix their programs before this is enforced.
-	 */
-	if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) {
-		if (prog_type == BPF_PROG_TYPE_PERF_EVENT) {
-			verbose(env, "perf_event programs can only use preallocated hash map\n");
-			return -EINVAL;
-		}
-		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-			verbose(env, "trace type programs can only use preallocated hash map\n");
-			return -EINVAL;
-		}
-		WARN_ONCE(1, "trace type BPF program uses run-time allocation\n");
-		verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
-	}
 
 	if (map_value_has_spin_lock(map)) {
 		if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
@@ -12670,13 +12708,8 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 		case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 		case BPF_MAP_TYPE_HASH_OF_MAPS:
-			if (!is_preallocated_map(map)) {
-				verbose(env,
-					"Sleepable programs can only use preallocated maps\n");
-				return -EINVAL;
-			}
-			break;
 		case BPF_MAP_TYPE_RINGBUF:
+		case BPF_MAP_TYPE_USER_RINGBUF:
 		case BPF_MAP_TYPE_INODE_STORAGE:
 		case BPF_MAP_TYPE_SK_STORAGE:
 		case BPF_MAP_TYPE_TASK_STORAGE:
@@ -13470,9 +13503,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 				insn->code = BPF_LDX | BPF_PROBE_MEM |
 					BPF_SIZE((insn)->code);
 				env->prog->aux->num_exentries++;
-			} else if (resolve_prog_type(env->prog) != BPF_PROG_TYPE_STRUCT_OPS) {
-				verbose(env, "Writes through BTF pointers are not allowed\n");
-				return -EINVAL;
 			}
 			continue;
 		default: