bpf: Remove trace_printk_lock

Both bpf_trace_printk and bpf_trace_vprintk helpers use static buffer guarded
with trace_printk_lock spin lock.

The spin lock contention causes issues with bpf programs attached to
contention_begin tracepoint [1][2].

Andrii suggested we could get rid of the contention by using trylock, but we
could actually get rid of the spinlock completely by using percpu buffers the
same way as for bin_args in bpf_bprintf_prepare function.

Adding new return 'buf' argument to struct bpf_bprintf_data and making
bpf_bprintf_prepare to return also the buffer for printk helpers.

  [1] https://lore.kernel.org/bpf/CACkBjsakT_yWxnSWr4r-0TpPvbKm9-OBmVUhJb7hV3hY8fdCkw@mail.gmail.com/
  [2] https://lore.kernel.org/bpf/CACkBjsaCsTovQHFfkqJKto6S4Z8d02ud1D7MPESrHa1cVNNTrw@mail.gmail.com/

Reported-by: Hao Sun <sunhao.th@gmail.com>
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221215214430.1336195-4-jolsa@kernel.org

1 files changed, 19 insertions, 12 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9cca02e13f2e..23aa8cf8fd1a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -756,19 +756,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
  * arguments representation.
  */
-#define MAX_BPRINTF_BUF_LEN	512
+#define MAX_BPRINTF_BIN_ARGS	512
 
 /* Support executing three nested bprintf helper calls on a given CPU */
 #define MAX_BPRINTF_NEST_LEVEL	3
 struct bpf_bprintf_buffers {
-	char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN];
+	char bin_args[MAX_BPRINTF_BIN_ARGS];
+	char buf[MAX_BPRINTF_BUF];
 };
-static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs);
+
+static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
 static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
 
-static int try_get_fmt_tmp_buf(char **tmp_buf)
+static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
 {
-	struct bpf_bprintf_buffers *bufs;
 	int nest_level;
 
 	preempt_disable();
@@ -778,15 +779,14 @@ static int try_get_fmt_tmp_buf(char **tmp_buf)
 		preempt_enable();
 		return -EBUSY;
 	}
-	bufs = this_cpu_ptr(&bpf_bprintf_bufs);
-	*tmp_buf = bufs->tmp_bufs[nest_level - 1];
+	*bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]);
 
 	return 0;
 }
 
 void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
 {
-	if (!data->bin_args)
+	if (!data->bin_args && !data->buf)
 		return;
 	if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
 		return;
@@ -811,7 +811,9 @@ void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
 int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 num_args, struct bpf_bprintf_data *data)
 {
+	bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
 	char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end;
+	struct bpf_bprintf_buffers *buffers = NULL;
 	size_t sizeof_cur_arg, sizeof_cur_ip;
 	int err, i, num_spec = 0;
 	u64 cur_arg;
@@ -822,14 +824,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 		return -EINVAL;
 	fmt_size = fmt_end - fmt;
 
-	if (data->get_bin_args) {
-		if (num_args && try_get_fmt_tmp_buf(&tmp_buf))
-			return -EBUSY;
+	if (get_buffers && try_get_buffers(&buffers))
+		return -EBUSY;
 
-		tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN;
+	if (data->get_bin_args) {
+		if (num_args)
+			tmp_buf = buffers->bin_args;
+		tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS;
 		data->bin_args = (u32 *)tmp_buf;
 	}
 
+	if (data->get_buf)
+		data->buf = buffers->buf;
+
 	for (i = 0; i < fmt_size; i++) {
 		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
 			err = -EINVAL;