bpf: reject program if a __user tagged memory accessed in kernel way

BPF verifier supports direct memory access for BPF_PROG_TYPE_TRACING type
of bpf programs, e.g., a->b. If "a" is a pointer
pointing to kernel memory, bpf verifier will allow user to write
code in C like a->b and the verifier will translate it to a kernel
load properly. If "a" is a pointer to user memory, it is expected
that bpf developer should be bpf_probe_read_user() helper to
get the value a->b. Without utilizing BTF __user tagging information,
current verifier will assume that a->b is a kernel memory access
and this may generate incorrect result.

Now BTF contains __user information, it can check whether the
pointer points to a user memory or not. If it is, the verifier
can reject the program and force users to use bpf_probe_read_user()
helper explicitly.

In the future, we can easily extend btf_add_space for other
address space tagging, for example, rcu/percpu etc.

Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220127154606.654961-1-yhs@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 24 insertions, 11 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dcf065ec2774..1ae41d0cf96c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -536,7 +536,7 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 static const char *reg_type_str(struct bpf_verifier_env *env,
 				enum bpf_reg_type type)
 {
-	char postfix[16] = {0}, prefix[16] = {0};
+	char postfix[16] = {0}, prefix[32] = {0};
 	static const char * const str[] = {
 		[NOT_INIT]		= "?",
 		[SCALAR_VALUE]		= "inv",
@@ -570,9 +570,11 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 	}
 
 	if (type & MEM_RDONLY)
-		strncpy(prefix, "rdonly_", 16);
+		strncpy(prefix, "rdonly_", 32);
 	if (type & MEM_ALLOC)
-		strncpy(prefix, "alloc_", 16);
+		strncpy(prefix, "alloc_", 32);
+	if (type & MEM_USER)
+		strncpy(prefix, "user_", 32);
 
 	snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
 		 prefix, str[base_type(type)], postfix);
@@ -1547,14 +1549,15 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
 static void mark_btf_ld_reg(struct bpf_verifier_env *env,
 			    struct bpf_reg_state *regs, u32 regno,
 			    enum bpf_reg_type reg_type,
-			    struct btf *btf, u32 btf_id)
+			    struct btf *btf, u32 btf_id,
+			    enum bpf_type_flag flag)
 {
 	if (reg_type == SCALAR_VALUE) {
 		mark_reg_unknown(env, regs, regno);
 		return;
 	}
 	mark_reg_known_zero(env, regs, regno);
-	regs[regno].type = PTR_TO_BTF_ID;
+	regs[regno].type = PTR_TO_BTF_ID | flag;
 	regs[regno].btf = btf;
 	regs[regno].btf_id = btf_id;
 }
@@ -4152,6 +4155,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	struct bpf_reg_state *reg = regs + regno;
 	const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
 	const char *tname = btf_name_by_offset(reg->btf, t->name_off);
+	enum bpf_type_flag flag = 0;
 	u32 btf_id;
 	int ret;
 
@@ -4171,9 +4175,16 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
+	if (reg->type & MEM_USER) {
+		verbose(env,
+			"R%d is ptr_%s access user memory: off=%d\n",
+			regno, tname, off);
+		return -EACCES;
+	}
+
 	if (env->ops->btf_struct_access) {
 		ret = env->ops->btf_struct_access(&env->log, reg->btf, t,
-						  off, size, atype, &btf_id);
+						  off, size, atype, &btf_id, &flag);
 	} else {
 		if (atype != BPF_READ) {
 			verbose(env, "only read is supported\n");
@@ -4181,14 +4192,14 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 		}
 
 		ret = btf_struct_access(&env->log, reg->btf, t, off, size,
-					atype, &btf_id);
+					atype, &btf_id, &flag);
 	}
 
 	if (ret < 0)
 		return ret;
 
 	if (atype == BPF_READ && value_regno >= 0)
-		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id);
+		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
 
 	return 0;
 }
@@ -4201,6 +4212,7 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
 {
 	struct bpf_reg_state *reg = regs + regno;
 	struct bpf_map *map = reg->map_ptr;
+	enum bpf_type_flag flag = 0;
 	const struct btf_type *t;
 	const char *tname;
 	u32 btf_id;
@@ -4238,12 +4250,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id);
+	ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id, &flag);
 	if (ret < 0)
 		return ret;
 
 	if (value_regno >= 0)
-		mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id);
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag);
 
 	return 0;
 }
@@ -4444,7 +4456,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err < 0)
 			return err;
 
-		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf, &btf_id);
+		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf,
+				       &btf_id);
 		if (err)
 			verbose_linfo(env, insn_idx, "; ");
 		if (!err && t == BPF_READ && value_regno >= 0) {