bpf: add new helper fd2path for mapping a file descriptor to a pathname

When people want to identify which file system files are being opened,
read, and written to, they can use this helper with file descriptor as
input to achieve this goal. Other pseudo filesystems are also supported.

This requirement is mainly discussed here:

  iovisor/bcc#237

v3->v4:
- fix missing fdput()
- move fd2path from kernel/bpf/trace.c to kernel/trace/bpf_trace.c
- move fd2path's test code to another patch

v2->v3:
- remove unnecessary LOCKDOWN_BPF_READ
- refactor error handling section for enhanced readability
- provide a test case in tools/testing/selftests/bpf

v1->v2:
- fix backward compatibility
- add this helper description
- fix signed-off name

Signed-off-by: Wenbo Zhang <ethercflow@gmail.com>

include/uapi/linux/bpf.h

@@ -2775,6 +2775,17 @@ union bpf_attr {
  * 		restricted to raw_tracepoint bpf programs.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_fd2path(char *path, u32 size, int fd)
+ *	Description
+ *		Get **file** atrribute from the current task by *fd*, then call
+ *		**d_path** to get it's absolute path and copy it as string into
+ *		*path* of *size*. The **path** also support pseudo filesystems
+ *		(whether or not it can be mounted). The *size* must be strictly
+ *		positive. On success, the helper makes sure that the *path* is
+ *		NUL-terminated. On failure, it is filled with zeroes.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2888,7 +2899,8 @@ union bpf_attr {
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
 	FN(tcp_gen_syncookie),		\
-	FN(skb_output),
+	FN(skb_output),			\
+	FN(fd2path),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/trace/bpf_trace.c

@@ -683,6 +683,44 @@ static const struct bpf_func_proto bpf_send_signal_proto = {
 	.arg1_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_fd2path, char *, dst, u32, size, int, fd)
+{
+	struct fd f;
+	char *p;
+	int ret = -EINVAL;
+
+	/* Use fdget_raw instead of fdget to support O_PATH */
+	f = fdget_raw(fd);
+	if (!f.file)
+		goto error;
+
+	p = d_path(&f.file->f_path, dst, size);
+	if (IS_ERR_OR_NULL(p)) {
+		ret = PTR_ERR(p);
+		goto error;
+	}
+
+	ret = strlen(p);
+	memmove(dst, p, ret);
+	dst[ret] = '\0';
+	goto end;
+
+error:
+	memset(dst, '0', size);
+end:
+	fdput(f);
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_fd2path_proto = {
+	.func       = bpf_fd2path,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type  = ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type  = ARG_CONST_SIZE,
+	.arg3_type  = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -735,6 +773,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 	case BPF_FUNC_send_signal:
 		return &bpf_send_signal_proto;
+	case BPF_FUNC_fd2path:
+		return &bpf_fd2path_proto;
 	default:
 		return NULL;
 	}

tools/include/uapi/linux/bpf.h

@@ -2775,6 +2775,17 @@ union bpf_attr {
  * 		restricted to raw_tracepoint bpf programs.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_fd2path(char *path, u32 size, int fd)
+ *	Description
+ *		Get **file** atrribute from the current task by *fd*, then call
+ *		**d_path** to get it's absolute path and copy it as string into
+ *		*path* of *size*. The **path** also support pseudo filesystems
+ *		(whether or not it can be mounted). The *size* must be strictly
+ *		positive. On success, the helper makes sure that the *path* is
+ *		NUL-terminated. On failure, it is filled with zeroes.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2888,7 +2899,8 @@ union bpf_attr {
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
 	FN(tcp_gen_syncookie),		\
-	FN(skb_output),
+	FN(skb_output),			\
+	FN(fd2path),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call