1 files changed, 397 insertions, 110 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d175b70067b3..813f6ee80419 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -245,6 +245,7 @@ struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
 	bool pkt_access;
+	u8 release_regno;
 	int regno;
 	int access_size;
 	int mem_size;
@@ -257,6 +258,7 @@ struct bpf_call_arg_meta {
 	struct btf *ret_btf;
 	u32 ret_btf_id;
 	u32 subprogno;
+	struct bpf_map_value_off_desc *kptr_off_desc;
 };
 
 struct btf *btf_vmlinux;
@@ -471,17 +473,6 @@ static bool type_may_be_null(u32 type)
 	return type & PTR_MAYBE_NULL;
 }
 
-/* Determine whether the function releases some resources allocated by another
- * function call. The first reference type argument will be assumed to be
- * released by release_reference().
- */
-static bool is_release_function(enum bpf_func_id func_id)
-{
-	return func_id == BPF_FUNC_sk_release ||
-	       func_id == BPF_FUNC_ringbuf_submit ||
-	       func_id == BPF_FUNC_ringbuf_discard;
-}
-
 static bool may_be_acquire_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_lookup_tcp ||
@@ -499,7 +490,8 @@ static bool is_acquire_function(enum bpf_func_id func_id,
 	if (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_ringbuf_reserve)
+	    func_id == BPF_FUNC_ringbuf_reserve ||
+	    func_id == BPF_FUNC_kptr_xchg)
 		return true;
 
 	if (func_id == BPF_FUNC_map_lookup_elem &&
@@ -575,6 +567,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 		strncpy(prefix, "user_", 32);
 	if (type & MEM_PERCPU)
 		strncpy(prefix, "percpu_", 32);
+	if (type & PTR_UNTRUSTED)
+		strncpy(prefix, "untrusted_", 32);
 
 	snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
 		 prefix, str[base_type(type)], postfix);
@@ -3211,7 +3205,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	return 0;
 }
 
-enum stack_access_src {
+enum bpf_access_src {
 	ACCESS_DIRECT = 1,  /* the access is performed by an instruction */
 	ACCESS_HELPER = 2,  /* the access is performed by a helper */
 };
@@ -3219,7 +3213,7 @@ enum stack_access_src {
 static int check_stack_range_initialized(struct bpf_verifier_env *env,
 					 int regno, int off, int access_size,
 					 bool zero_size_allowed,
-					 enum stack_access_src type,
+					 enum bpf_access_src type,
 					 struct bpf_call_arg_meta *meta);
 
 static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
@@ -3469,9 +3463,175 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
 	return 0;
 }
 
+static int __check_ptr_off_reg(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg, int regno,
+			       bool fixed_off_ok)
+{
+	/* Access to this pointer-typed register or passing it to a helper
+	 * is only allowed in its original, unmodified form.
+	 */
+
+	if (reg->off < 0) {
+		verbose(env, "negative offset %s ptr R%d off=%d disallowed\n",
+			reg_type_str(env, reg->type), regno, reg->off);
+		return -EACCES;
+	}
+
+	if (!fixed_off_ok && reg->off) {
+		verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n",
+			reg_type_str(env, reg->type), regno, reg->off);
+		return -EACCES;
+	}
+
+	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env, "variable %s access var_off=%s disallowed\n",
+			reg_type_str(env, reg->type), tn_buf);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+int check_ptr_off_reg(struct bpf_verifier_env *env,
+		      const struct bpf_reg_state *reg, int regno)
+{
+	return __check_ptr_off_reg(env, reg, regno, false);
+}
+
+static int map_kptr_match_type(struct bpf_verifier_env *env,
+			       struct bpf_map_value_off_desc *off_desc,
+			       struct bpf_reg_state *reg, u32 regno)
+{
+	const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id);
+	int perm_flags = PTR_MAYBE_NULL;
+	const char *reg_name = "";
+
+	/* Only unreferenced case accepts untrusted pointers */
+	if (off_desc->type == BPF_KPTR_UNREF)
+		perm_flags |= PTR_UNTRUSTED;
+
+	if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
+		goto bad_type;
+
+	if (!btf_is_kernel(reg->btf)) {
+		verbose(env, "R%d must point to kernel BTF\n", regno);
+		return -EINVAL;
+	}
+	/* We need to verify reg->type and reg->btf, before accessing reg->btf */
+	reg_name = kernel_type_name(reg->btf, reg->btf_id);
+
+	/* For ref_ptr case, release function check should ensure we get one
+	 * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the
+	 * normal store of unreferenced kptr, we must ensure var_off is zero.
+	 * Since ref_ptr cannot be accessed directly by BPF insns, checks for
+	 * reg->off and reg->ref_obj_id are not needed here.
+	 */
+	if (__check_ptr_off_reg(env, reg, regno, true))
+		return -EACCES;
+
+	/* A full type match is needed, as BTF can be vmlinux or module BTF, and
+	 * we also need to take into account the reg->off.
+	 *
+	 * We want to support cases like:
+	 *
+	 * struct foo {
+	 *         struct bar br;
+	 *         struct baz bz;
+	 * };
+	 *
+	 * struct foo *v;
+	 * v = func();	      // PTR_TO_BTF_ID
+	 * val->foo = v;      // reg->off is zero, btf and btf_id match type
+	 * val->bar = &v->br; // reg->off is still zero, but we need to retry with
+	 *                    // first member type of struct after comparison fails
+	 * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked
+	 *                    // to match type
+	 *
+	 * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off
+	 * is zero. We must also ensure that btf_struct_ids_match does not walk
+	 * the struct to match type against first member of struct, i.e. reject
+	 * second case from above. Hence, when type is BPF_KPTR_REF, we set
+	 * strict mode to true for type match.
+	 */
+	if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+				  off_desc->kptr.btf, off_desc->kptr.btf_id,
+				  off_desc->type == BPF_KPTR_REF))
+		goto bad_type;
+	return 0;
+bad_type:
+	verbose(env, "invalid kptr access, R%d type=%s%s ", regno,
+		reg_type_str(env, reg->type), reg_name);
+	verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name);
+	if (off_desc->type == BPF_KPTR_UNREF)
+		verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED),
+			targ_name);
+	else
+		verbose(env, "\n");
+	return -EINVAL;
+}
+
+static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
+				 int value_regno, int insn_idx,
+				 struct bpf_map_value_off_desc *off_desc)
+{
+	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
+	int class = BPF_CLASS(insn->code);
+	struct bpf_reg_state *val_reg;
+
+	/* Things we already checked for in check_map_access and caller:
+	 *  - Reject cases where variable offset may touch kptr
+	 *  - size of access (must be BPF_DW)
+	 *  - tnum_is_const(reg->var_off)
+	 *  - off_desc->offset == off + reg->var_off.value
+	 */
+	/* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */
+	if (BPF_MODE(insn->code) != BPF_MEM) {
+		verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n");
+		return -EACCES;
+	}
+
+	/* We only allow loading referenced kptr, since it will be marked as
+	 * untrusted, similar to unreferenced kptr.
+	 */
+	if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) {
+		verbose(env, "store to referenced kptr disallowed\n");
+		return -EACCES;
+	}
+
+	if (class == BPF_LDX) {
+		val_reg = reg_state(env, value_regno);
+		/* We can simply mark the value_regno receiving the pointer
+		 * value from map as PTR_TO_BTF_ID, with the correct type.
+		 */
+		mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf,
+				off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED);
+		/* For mark_ptr_or_null_reg */
+		val_reg->id = ++env->id_gen;
+	} else if (class == BPF_STX) {
+		val_reg = reg_state(env, value_regno);
+		if (!register_is_null(val_reg) &&
+		    map_kptr_match_type(env, off_desc, val_reg, value_regno))
+			return -EACCES;
+	} else if (class == BPF_ST) {
+		if (insn->imm) {
+			verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n",
+				off_desc->offset);
+			return -EACCES;
+		}
+	} else {
+		verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n");
+		return -EACCES;
+	}
+	return 0;
+}
+
 /* check read/write into a map element with possible variable offset */
 static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-			    int off, int size, bool zero_size_allowed)
+			    int off, int size, bool zero_size_allowed,
+			    enum bpf_access_src src)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
@@ -3507,6 +3667,36 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			return -EACCES;
 		}
 	}
+	if (map_value_has_kptrs(map)) {
+		struct bpf_map_value_off *tab = map->kptr_off_tab;
+		int i;
+
+		for (i = 0; i < tab->nr_off; i++) {
+			u32 p = tab->off[i].offset;
+
+			if (reg->smin_value + off < p + sizeof(u64) &&
+			    p < reg->umax_value + off + size) {
+				if (src != ACCESS_DIRECT) {
+					verbose(env, "kptr cannot be accessed indirectly by helper\n");
+					return -EACCES;
+				}
+				if (!tnum_is_const(reg->var_off)) {
+					verbose(env, "kptr access cannot have variable offset\n");
+					return -EACCES;
+				}
+				if (p != off + reg->var_off.value) {
+					verbose(env, "kptr access misaligned expected=%u off=%llu\n",
+						p, off + reg->var_off.value);
+					return -EACCES;
+				}
+				if (size != bpf_size_to_bytes(BPF_DW)) {
+					verbose(env, "kptr access size must be BPF_DW\n");
+					return -EACCES;
+				}
+				break;
+			}
+		}
+	}
 	return err;
 }
 
@@ -3980,44 +4170,6 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 }
 #endif
 
-static int __check_ptr_off_reg(struct bpf_verifier_env *env,
-			       const struct bpf_reg_state *reg, int regno,
-			       bool fixed_off_ok)
-{
-	/* Access to this pointer-typed register or passing it to a helper
-	 * is only allowed in its original, unmodified form.
-	 */
-
-	if (reg->off < 0) {
-		verbose(env, "negative offset %s ptr R%d off=%d disallowed\n",
-			reg_type_str(env, reg->type), regno, reg->off);
-		return -EACCES;
-	}
-
-	if (!fixed_off_ok && reg->off) {
-		verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n",
-			reg_type_str(env, reg->type), regno, reg->off);
-		return -EACCES;
-	}
-
-	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
-		char tn_buf[48];
-
-		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "variable %s access var_off=%s disallowed\n",
-			reg_type_str(env, reg->type), tn_buf);
-		return -EACCES;
-	}
-
-	return 0;
-}
-
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno)
-{
-	return __check_ptr_off_reg(env, reg, regno, false);
-}
-
 static int __check_buffer_access(struct bpf_verifier_env *env,
 				 const char *buf_info,
 				 const struct bpf_reg_state *reg,
@@ -4224,6 +4376,12 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
+	/* If this is an untrusted pointer, all pointers formed by walking it
+	 * also inherit the untrusted flag.
+	 */
+	if (type_flag(reg->type) & PTR_UNTRUSTED)
+		flag |= PTR_UNTRUSTED;
+
 	if (atype == BPF_READ && value_regno >= 0)
 		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
 
@@ -4316,7 +4474,7 @@ static int check_stack_slot_within_bounds(int off,
 static int check_stack_access_within_bounds(
 		struct bpf_verifier_env *env,
 		int regno, int off, int access_size,
-		enum stack_access_src src, enum bpf_access_type type)
+		enum bpf_access_src src, enum bpf_access_type type)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
@@ -4412,6 +4570,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_MAP_VALUE) {
+		struct bpf_map_value_off_desc *kptr_off_desc = NULL;
+
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose(env, "R%d leaks addr into map\n", value_regno);
@@ -4420,8 +4580,16 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_map_access_type(env, regno, off, size, t);
 		if (err)
 			return err;
-		err = check_map_access(env, regno, off, size, false);
-		if (!err && t == BPF_READ && value_regno >= 0) {
+		err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT);
+		if (err)
+			return err;
+		if (tnum_is_const(reg->var_off))
+			kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr,
+								  off + reg->var_off.value);
+		if (kptr_off_desc) {
+			err = check_map_kptr_access(env, regno, value_regno, insn_idx,
+						    kptr_off_desc);
+		} else if (t == BPF_READ && value_regno >= 0) {
 			struct bpf_map *map = reg->map_ptr;
 
 			/* if map is read-only, track its contents as scalars */
@@ -4724,7 +4892,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 static int check_stack_range_initialized(
 		struct bpf_verifier_env *env, int regno, int off,
 		int access_size, bool zero_size_allowed,
-		enum stack_access_src type, struct bpf_call_arg_meta *meta)
+		enum bpf_access_src type, struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
@@ -4861,6 +5029,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		return check_packet_access(env, regno, reg->off, access_size,
 					   zero_size_allowed);
 	case PTR_TO_MAP_KEY:
+		if (meta && meta->raw_mode) {
+			verbose(env, "R%d cannot write into %s\n", regno,
+				reg_type_str(env, reg->type));
+			return -EACCES;
+		}
 		return check_mem_region_access(env, regno, reg->off, access_size,
 					       reg->map_ptr->key_size, false);
 	case PTR_TO_MAP_VALUE:
@@ -4869,15 +5042,25 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 					  BPF_READ))
 			return -EACCES;
 		return check_map_access(env, regno, reg->off, access_size,
-					zero_size_allowed);
+					zero_size_allowed, ACCESS_HELPER);
 	case PTR_TO_MEM:
+		if (type_is_rdonly_mem(reg->type)) {
+			if (meta && meta->raw_mode) {
+				verbose(env, "R%d cannot write into %s\n", regno,
+					reg_type_str(env, reg->type));
+				return -EACCES;
+			}
+		}
 		return check_mem_region_access(env, regno, reg->off,
 					       access_size, reg->mem_size,
 					       zero_size_allowed);
 	case PTR_TO_BUF:
 		if (type_is_rdonly_mem(reg->type)) {
-			if (meta && meta->raw_mode)
+			if (meta && meta->raw_mode) {
+				verbose(env, "R%d cannot write into %s\n", regno,
+					reg_type_str(env, reg->type));
 				return -EACCES;
+			}
 
 			max_access = &env->prog->aux->max_rdonly_access;
 		} else {
@@ -4919,8 +5102,7 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 	 * out. Only upper bounds can be learned because retval is an
 	 * int type and negative retvals are allowed.
 	 */
-	if (meta)
-		meta->msize_max_value = reg->umax_value;
+	meta->msize_max_value = reg->umax_value;
 
 	/* The register is SCALAR_VALUE; the access check
 	 * happens using its boundaries.
@@ -4963,24 +5145,33 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 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;
+	struct bpf_call_arg_meta meta;
+	int err;
+
 	if (register_is_null(reg))
 		return 0;
 
-	if (type_may_be_null(reg->type)) {
-		/* Assuming that the register contains a value check if the memory
-		 * access is safe. Temporarily save and restore the register's state as
-		 * the conversion shouldn't be visible to a caller.
-		 */
-		const struct bpf_reg_state saved_reg = *reg;
-		int rv;
-
+	memset(&meta, 0, sizeof(meta));
+	/* Assuming that the register contains a value check if the memory
+	 * access is safe. Temporarily save and restore the register's state as
+	 * the conversion shouldn't be visible to a caller.
+	 */
+	if (may_be_null) {
+		saved_reg = *reg;
 		mark_ptr_not_null_reg(reg);
-		rv = check_helper_mem_access(env, regno, mem_size, true, NULL);
-		*reg = saved_reg;
-		return rv;
 	}
 
-	return check_helper_mem_access(env, regno, mem_size, true, NULL);
+	err = check_helper_mem_access(env, regno, mem_size, true, &meta);
+	/* Check access for BPF_WRITE */
+	meta.raw_mode = true;
+	err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta);
+
+	if (may_be_null)
+		*reg = saved_reg;
+
+	return err;
 }
 
 int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
@@ -4989,16 +5180,22 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state
 	struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1];
 	bool may_be_null = type_may_be_null(mem_reg->type);
 	struct bpf_reg_state saved_reg;
+	struct bpf_call_arg_meta meta;
 	int err;
 
 	WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5);
 
+	memset(&meta, 0, sizeof(meta));
+
 	if (may_be_null) {
 		saved_reg = *mem_reg;
 		mark_ptr_not_null_reg(mem_reg);
 	}
 
-	err = check_mem_size_reg(env, reg, regno, true, NULL);
+	err = check_mem_size_reg(env, reg, regno, true, &meta);
+	/* Check access for BPF_WRITE */
+	meta.raw_mode = true;
+	err = err ?: check_mem_size_reg(env, reg, regno, true, &meta);
 
 	if (may_be_null)
 		*mem_reg = saved_reg;
@@ -5134,6 +5331,53 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 	return 0;
 }
 
+static int process_kptr_func(struct bpf_verifier_env *env, int regno,
+			     struct bpf_call_arg_meta *meta)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	struct bpf_map_value_off_desc *off_desc;
+	struct bpf_map *map_ptr = reg->map_ptr;
+	u32 kptr_off;
+	int ret;
+
+	if (!tnum_is_const(reg->var_off)) {
+		verbose(env,
+			"R%d doesn't have constant offset. kptr has to be at the constant offset\n",
+			regno);
+		return -EINVAL;
+	}
+	if (!map_ptr->btf) {
+		verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n",
+			map_ptr->name);
+		return -EINVAL;
+	}
+	if (!map_value_has_kptrs(map_ptr)) {
+		ret = PTR_ERR(map_ptr->kptr_off_tab);
+		if (ret == -E2BIG)
+			verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name,
+				BPF_MAP_VALUE_OFF_MAX);
+		else if (ret == -EEXIST)
+			verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name);
+		else
+			verbose(env, "map '%s' has no valid kptr\n", map_ptr->name);
+		return -EINVAL;
+	}
+
+	meta->map_ptr = map_ptr;
+	kptr_off = reg->off + reg->var_off.value;
+	off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off);
+	if (!off_desc) {
+		verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
+		return -EACCES;
+	}
+	if (off_desc->type != BPF_KPTR_REF) {
+		verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
+		return -EACCES;
+	}
+	meta->kptr_off_desc = off_desc;
+	return 0;
+}
+
 static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
 {
 	return base_type(type) == ARG_PTR_TO_MEM ||
@@ -5157,6 +5401,11 @@ static bool arg_type_is_int_ptr(enum bpf_arg_type type)
 	       type == ARG_PTR_TO_LONG;
 }
 
+static bool arg_type_is_release(enum bpf_arg_type type)
+{
+	return type & OBJ_RELEASE;
+}
+
 static int int_ptr_type_to_size(enum bpf_arg_type type)
 {
 	if (type == ARG_PTR_TO_INT)
@@ -5269,6 +5518,7 @@ static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
 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 *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -5296,11 +5546,13 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_STACK]		= &stack_ptr_types,
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
+	[ARG_PTR_TO_KPTR]		= &kptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 			  enum bpf_arg_type arg_type,
-			  const u32 *arg_btf_id)
+			  const u32 *arg_btf_id,
+			  struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected, type = reg->type;
@@ -5345,6 +5597,13 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 
 found:
 	if (reg->type == PTR_TO_BTF_ID) {
+		/* For bpf_sk_release, it needs to match against first member
+		 * 'struct sock_common', hence make an exception for it. This
+		 * allows bpf_sk_release to work for multiple socket types.
+		 */
+		bool strict_type_match = arg_type_is_release(arg_type) &&
+					 meta->func_id != BPF_FUNC_sk_release;
+
 		if (!arg_btf_id) {
 			if (!compatible->btf_id) {
 				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
@@ -5353,8 +5612,12 @@ found:
 			arg_btf_id = compatible->btf_id;
 		}
 
-		if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
-					  btf_vmlinux, *arg_btf_id)) {
+		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));
@@ -5367,11 +5630,10 @@ found:
 
 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,
-			   bool is_release_func)
+			   enum bpf_arg_type arg_type)
 {
-	bool fixed_off_ok = false, release_reg;
 	enum bpf_reg_type type = reg->type;
+	bool fixed_off_ok = false;
 
 	switch ((u32)type) {
 	case SCALAR_VALUE:
@@ -5389,7 +5651,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 		/* Some of the argument types nevertheless require a
 		 * zero register offset.
 		 */
-		if (arg_type != ARG_PTR_TO_ALLOC_MEM)
+		if (base_type(arg_type) != ARG_PTR_TO_ALLOC_MEM)
 			return 0;
 		break;
 	/* All the rest must be rejected, except PTR_TO_BTF_ID which allows
@@ -5397,19 +5659,17 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	 */
 	case PTR_TO_BTF_ID:
 		/* When referenced PTR_TO_BTF_ID is passed to release function,
-		 * it's fixed offset must be 0. We rely on the property that
-		 * only one referenced register can be passed to BPF helpers and
-		 * kfuncs. In the other cases, fixed offset can be non-zero.
+		 * it's fixed offset must be 0.	In the other cases, fixed offset
+		 * can be non-zero.
 		 */
-		release_reg = is_release_func && reg->ref_obj_id;
-		if (release_reg && reg->off) {
+		if (arg_type_is_release(arg_type) && reg->off) {
 			verbose(env, "R%d must have zero offset when passed to release func\n",
 				regno);
 			return -EINVAL;
 		}
-		/* For release_reg == true, fixed_off_ok must be false, but we
-		 * already checked and rejected reg->off != 0 above, so set to
-		 * true to allow fixed offset for all other cases.
+		/* For arg is release pointer, fixed_off_ok must be false, but
+		 * we already checked and rejected reg->off != 0 above, so set
+		 * to true to allow fixed offset for all other cases.
 		 */
 		fixed_off_ok = true;
 		break;
@@ -5464,18 +5724,28 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		 */
 		goto skip_type_check;
 
-	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);
+	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg], meta);
 	if (err)
 		return err;
 
-	err = check_func_arg_reg_off(env, reg, regno, arg_type, is_release_function(meta->func_id));
+	err = check_func_arg_reg_off(env, reg, regno, arg_type);
 	if (err)
 		return err;
 
 skip_type_check:
-	/* check_func_arg_reg_off relies on only one referenced register being
-	 * allowed for BPF helpers.
-	 */
+	if (arg_type_is_release(arg_type)) {
+		if (!reg->ref_obj_id && !register_is_null(reg)) {
+			verbose(env, "R%d must be referenced when passed to release function\n",
+				regno);
+			return -EINVAL;
+		}
+		if (meta->release_regno) {
+			verbose(env, "verifier internal error: more than one release argument\n");
+			return -EFAULT;
+		}
+		meta->release_regno = regno;
+	}
+
 	if (reg->ref_obj_id) {
 		if (meta->ref_obj_id) {
 			verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
@@ -5613,7 +5883,8 @@ skip_type_check:
 		}
 
 		err = check_map_access(env, regno, reg->off,
-				       map->value_size - reg->off, false);
+				       map->value_size - reg->off, false,
+				       ACCESS_HELPER);
 		if (err)
 			return err;
 
@@ -5629,6 +5900,9 @@ skip_type_check:
 			verbose(env, "string is not zero-terminated\n");
 			return -EINVAL;
 		}
+	} else if (arg_type == ARG_PTR_TO_KPTR) {
+		if (process_kptr_func(env, regno, meta))
+			return -EACCES;
 	}
 
 	return err;
@@ -5971,17 +6245,18 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
-		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+		if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
 			return false;
 
-		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+		if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
 			return false;
 	}
 
 	return true;
 }
 
-static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id,
+			    struct bpf_call_arg_meta *meta)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
@@ -6665,7 +6940,7 @@ 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);
+	err = check_func_proto(fn, func_id, &meta);
 	if (err) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
@@ -6698,8 +6973,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return err;
 	}
 
-	if (is_release_function(func_id)) {
-		err = release_reference(env, meta.ref_obj_id);
+	regs = cur_regs(env);
+
+	if (meta.release_regno) {
+		err = -EINVAL;
+		if (meta.ref_obj_id)
+			err = release_reference(env, meta.ref_obj_id);
+		/* meta.ref_obj_id can only be 0 if register that is meant to be
+		 * released is NULL, which must be > R0.
+		 */
+		else if (register_is_null(&regs[meta.release_regno]))
+			err = 0;
 		if (err) {
 			verbose(env, "func %s#%d reference has not been acquired before\n",
 				func_id_name(func_id), func_id);
@@ -6707,8 +6991,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 	}
 
-	regs = cur_regs(env);
-
 	switch (func_id) {
 	case BPF_FUNC_tail_call:
 		err = check_reference_leak(env);
@@ -6832,21 +7114,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
 	} else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
+		struct btf *ret_btf;
 		int ret_btf_id;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
-		ret_btf_id = *fn->ret_btf_id;
+		if (func_id == BPF_FUNC_kptr_xchg) {
+			ret_btf = meta.kptr_off_desc->kptr.btf;
+			ret_btf_id = meta.kptr_off_desc->kptr.btf_id;
+		} else {
+			ret_btf = btf_vmlinux;
+			ret_btf_id = *fn->ret_btf_id;
+		}
 		if (ret_btf_id == 0) {
 			verbose(env, "invalid return type %u of func %s#%d\n",
 				base_type(ret_type), func_id_name(func_id),
 				func_id);
 			return -EINVAL;
 		}
-		/* current BPF helper definitions are only coming from
-		 * built-in code with type IDs from  vmlinux BTF
-		 */
-		regs[BPF_REG_0].btf = btf_vmlinux;
+		regs[BPF_REG_0].btf = ret_btf;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %u of func %s#%d\n",
@@ -7433,7 +7719,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
 			return -EACCES;
 		break;
 	case PTR_TO_MAP_VALUE:
-		if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+		if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) {
 			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
 				"prohibited for !root\n", dst);
 			return -EACCES;
@@ -12822,7 +13108,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		if (!ctx_access)
 			continue;
 
-		switch (env->insn_aux_data[i + delta].ptr_type) {
+		switch ((int)env->insn_aux_data[i + delta].ptr_type) {
 		case PTR_TO_CTX:
 			if (!ops->convert_ctx_access)
 				continue;
@@ -12839,6 +13125,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
 			break;
 		case PTR_TO_BTF_ID:
+		case PTR_TO_BTF_ID | PTR_UNTRUSTED:
 			if (type == BPF_READ) {
 				insn->code = BPF_LDX | BPF_PROBE_MEM |
 					BPF_SIZE((insn)->code);