bpf: Implement accurate raw_tp context access via BTF

libbpf analyzes bpf C program, searches in-kernel BTF for given type name
and stores it into expected_attach_type.
The kernel verifier expects this btf_id to point to something like:
typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc);
which represents signature of raw_tracepoint "kfree_skb".

Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb'
and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint.
In first case it passes btf_id of 'struct sk_buff *' back to the verifier core
and 'void *' in second case.

Then the verifier tracks PTR_TO_BTF_ID as any other pointer type.
Like PTR_TO_SOCKET points to 'struct bpf_sock',
PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on.
PTR_TO_BTF_ID points to in-kernel structs.
If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF
then PTR_TO_BTF_ID#1234 points to one of in kernel skbs.

When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32)
the btf_struct_access() checks which field of 'struct sk_buff' is
at offset 32. Checks that size of access matches type definition
of the field and continues to track the dereferenced type.
If that field was a pointer to 'struct net_device' the r2's type
will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device'
in vmlinux's BTF.

Such verifier analysis prevents "cheating" in BPF C program.
The program cannot cast arbitrary pointer to 'struct sk_buff *'
and access it. C compiler would allow type cast, of course,
but the verifier will notice type mismatch based on BPF assembly
and in-kernel BTF.

Signed-off-by: Alexei Starovoitov <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Acked-by: Martin KaFai Lau <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Alexei Starovoitov

include/linux/bpf.h

@@ -16,6 +16,7 @@
 #include <linux/u64_stats_sync.h>
 
 struct bpf_verifier_env;
+struct bpf_verifier_log;
 struct perf_event;
 struct bpf_prog;
 struct bpf_map;
@@ -281,14 +282,19 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
+	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
 };
 
 /* The information passed from prog-specific *_is_valid_access
  * back to the verifier.
  */
 struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
-	int ctx_field_size;
+	union {
+		int ctx_field_size;
+		u32 btf_id;
+	};
+	struct bpf_verifier_log *log; /* for verbose logs */
 };
 
 static inline void
@@ -483,6 +489,7 @@ struct bpf_event_entry {
 
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
+const char *kernel_type_name(u32 btf_type_id);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 
@@ -748,6 +755,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
+bool btf_ctx_access(int off, int size, enum bpf_access_type type,
+		    const struct bpf_prog *prog,
+		    struct bpf_insn_access_aux *info);
+int btf_struct_access(struct bpf_verifier_log *log,
+		      const struct btf_type *t, int off, int size,
+		      enum bpf_access_type atype,
+		      u32 *next_btf_id);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {

include/linux/bpf_verifier.h

@@ -52,6 +52,8 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 
+		u32 btf_id; /* for PTR_TO_BTF_ID */
+
 		/* Max size from any of the above. */
 		unsigned long raw;
 	};
@@ -399,6 +401,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
 				      const char *fmt, va_list args);
 __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
 					   const char *fmt, ...);
+__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
+			    const char *fmt, ...);
 
 static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
 {

kernel/bpf/btf.c

@@ -3436,6 +3436,196 @@ struct btf *btf_parse_vmlinux(void)
 	return ERR_PTR(err);
 }
 
+extern struct btf *btf_vmlinux;
+
+bool btf_ctx_access(int off, int size, enum bpf_access_type type,
+		    const struct bpf_prog *prog,
+		    struct bpf_insn_access_aux *info)
+{
+	struct bpf_verifier_log *log = info->log;
+	u32 btf_id = prog->aux->attach_btf_id;
+	const struct btf_param *args;
+	const struct btf_type *t;
+	const char prefix[] = "btf_trace_";
+	const char *tname;
+	u32 nr_args, arg;
+
+	if (!btf_id)
+		return true;
+
+	if (IS_ERR(btf_vmlinux)) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return false;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, btf_id);
+	if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
+		bpf_log(log, "btf_id is invalid\n");
+		return false;
+	}
+
+	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+	if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
+		bpf_log(log, "btf_id points to wrong type name %s\n", tname);
+		return false;
+	}
+	tname += sizeof(prefix) - 1;
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_ptr(t))
+		return false;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_func_proto(t))
+		return false;
+
+	if (off % 8) {
+		bpf_log(log, "raw_tp '%s' offset %d is not multiple of 8\n",
+			tname, off);
+		return false;
+	}
+	arg = off / 8;
+	args = (const struct btf_param *)(t + 1);
+	/* skip first 'void *__data' argument in btf_trace_##name typedef */
+	args++;
+	nr_args = btf_type_vlen(t) - 1;
+	if (arg >= nr_args) {
+		bpf_log(log, "raw_tp '%s' doesn't have %d-th argument\n",
+			tname, arg);
+		return false;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, args[arg].type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	if (btf_type_is_int(t))
+		/* accessing a scalar */
+		return true;
+	if (!btf_type_is_ptr(t)) {
+		bpf_log(log,
+			"raw_tp '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
+			tname, arg,
+			__btf_name_by_offset(btf_vmlinux, t->name_off),
+			btf_kind_str[BTF_INFO_KIND(t->info)]);
+		return false;
+	}
+	if (t->type == 0)
+		/* This is a pointer to void.
+		 * It is the same as scalar from the verifier safety pov.
+		 * No further pointer walking is allowed.
+		 */
+		return true;
+
+	/* this is a pointer to another type */
+	info->reg_type = PTR_TO_BTF_ID;
+	info->btf_id = t->type;
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log,
+			"raw_tp '%s' arg%d type %s is not a struct\n",
+			tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]);
+		return false;
+	}
+	bpf_log(log, "raw_tp '%s' arg%d has btf_id %d type %s '%s'\n",
+		tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)],
+		__btf_name_by_offset(btf_vmlinux, t->name_off));
+	return true;
+}
+
+int btf_struct_access(struct bpf_verifier_log *log,
+		      const struct btf_type *t, int off, int size,
+		      enum bpf_access_type atype,
+		      u32 *next_btf_id)
+{
+	const struct btf_member *member;
+	const struct btf_type *mtype;
+	const char *tname, *mname;
+	int i, moff = 0, msize;
+
+again:
+	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log, "Type '%s' is not a struct", tname);
+		return -EINVAL;
+	}
+
+	for_each_member(i, t, member) {
+		/* offset of the field in bits */
+		moff = btf_member_bit_offset(t, member);
+
+		if (btf_member_bitfield_size(t, member))
+			/* bitfields are not supported yet */
+			continue;
+
+		if (off + size <= moff / 8)
+			/* won't find anything, field is already too far */
+			break;
+
+		/* type of the field */
+		mtype = btf_type_by_id(btf_vmlinux, member->type);
+		mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
+
+		/* skip modifiers */
+		while (btf_type_is_modifier(mtype))
+			mtype = btf_type_by_id(btf_vmlinux, mtype->type);
+
+		if (btf_type_is_array(mtype))
+			/* array deref is not supported yet */
+			continue;
+
+		if (!btf_type_has_size(mtype) && !btf_type_is_ptr(mtype)) {
+			bpf_log(log, "field %s doesn't have size\n", mname);
+			return -EFAULT;
+		}
+		if (btf_type_is_ptr(mtype))
+			msize = 8;
+		else
+			msize = mtype->size;
+		if (off >= moff / 8 + msize)
+			/* no overlap with member, keep iterating */
+			continue;
+		/* the 'off' we're looking for is either equal to start
+		 * of this field or inside of this struct
+		 */
+		if (btf_type_is_struct(mtype)) {
+			/* our field must be inside that union or struct */
+			t = mtype;
+
+			/* adjust offset we're looking for */
+			off -= moff / 8;
+			goto again;
+		}
+		if (msize != size) {
+			/* field access size doesn't match */
+			bpf_log(log,
+				"cannot access %d bytes in struct %s field %s that has size %d\n",
+				size, tname, mname, msize);
+			return -EACCES;
+		}
+
+		if (btf_type_is_ptr(mtype)) {
+			const struct btf_type *stype;
+
+			stype = btf_type_by_id(btf_vmlinux, mtype->type);
+			/* skip modifiers */
+			while (btf_type_is_modifier(stype))
+				stype = btf_type_by_id(btf_vmlinux, stype->type);
+			if (btf_type_is_struct(stype)) {
+				*next_btf_id = mtype->type;
+				return PTR_TO_BTF_ID;
+			}
+		}
+		/* all other fields are treated as scalars */
+		return SCALAR_VALUE;
+	}
+	bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off);
+	return -EINVAL;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {