[PATCH RFC] bpf: Add support for reading user pointers

[Joel Fernandes (Google)]

The eBPF based opensnoop tool fails to read the file path string passed
to the do_sys_open function. This is because it is a pointer to
userspace address and causes an -EFAULT when read with
probe_kernel_read. This is not an issue when running the tool on x86 but
is an issue on arm64. This patch adds a new bpf function call based
which calls the recently proposed probe_user_read function [1].
Using this function call from opensnoop fixes the issue on arm64.

[1] https://lore.kernel.org/patchwork/patch/1051588/

Cc: Michal Gregorczyk <michalgr@xxxxxxxx>
Cc: Adrian Ratiu <adrian.ratiu@xxxxxxxxxxxxx>
Cc: Mohammad Husain <russoue@xxxxxxxxx>
Cc: Qais Yousef <qais.yousef@xxxxxxx>
Cc: Srinivas Ramana <sramana@xxxxxxxxxxxxxx>
Cc: duyuchao <yuchao.du@xxxxxxxxxx>
Cc: Manjo Raja Rao <linux@xxxxxxxxxxxxxxxx>
Cc: Karim Yaghmour <karim.yaghmour@xxxxxxxxxxx>
Cc: Tamir Carmeli <carmeli.tamir@xxxxxxxxx>
Cc: Yonghong Song <yhs@xxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Peter Ziljstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
---
 include/uapi/linux/bpf.h       |  7 ++++++-
 kernel/trace/bpf_trace.c       | 22 ++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 ++++++-
 3 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e99e3e6f8b37..6fec701eaa46 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -539,6 +539,10 @@ union bpf_attr {
  *     @mode: operation mode (enum bpf_adj_room_mode)
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
+ *
+ * int bpf_probe_read_user(void *dst, int size, void *src)
+ *     Read a userspace pointer safely.
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -591,7 +595,8 @@ union bpf_attr {
 	FN(get_socket_uid),		\
 	FN(set_hash),			\
 	FN(setsockopt),			\
-	FN(skb_adjust_room),
+	FN(skb_adjust_room),		\
+	FN(probe_read_user),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index dc498b605d5d..1e1a11d9faa8 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -81,6 +81,26 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void *, unsafe_ptr)
+{
+	int ret;
+
+	ret = probe_user_read(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_proto = {
+	.func		= bpf_probe_read_user,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	   u32, size)
 {
@@ -459,6 +479,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_delete_elem_proto;
 	case BPF_FUNC_probe_read:
 		return &bpf_probe_read_proto;
+	case BPF_FUNC_probe_read_user:
+		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_tail_call:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e99e3e6f8b37..6fec701eaa46 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -539,6 +539,10 @@ union bpf_attr {
  *     @mode: operation mode (enum bpf_adj_room_mode)
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
+ *
+ * int bpf_probe_read_user(void *dst, int size, void *src)
+ *     Read a userspace pointer safely.
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -591,7 +595,8 @@ union bpf_attr {
 	FN(get_socket_uid),		\
 	FN(set_hash),			\
 	FN(setsockopt),			\
-	FN(skb_adjust_room),
+	FN(skb_adjust_room),		\
+	FN(probe_read_user),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
2.21.0.593.g511ec345e18-goog