On 12/14/22 2:04 AM, Jiri Olsa wrote:
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 4 per cpu buffers (1k each) which should be enough for all
possible nesting contexts (normal, softirq, irq, nmi) or possible
(yet unlikely) probe within the printk helpers.
In very unlikely case we'd run out of the nesting levels the printk
will be omitted.
[1] https://lore.kernel.org/bpf/CACkBjsakT_yWxnSWr4r-0TpPvbKm9-OBmVUhJb7hV3hY8fdCkw@xxxxxxxxxxxxxx/
[2] https://lore.kernel.org/bpf/CACkBjsaCsTovQHFfkqJKto6S4Z8d02ud1D7MPESrHa1cVNNTrw@xxxxxxxxxxxxxx/
Reported-by: Hao Sun <sunhao.th@xxxxxxxxx>
Suggested-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
v2 changes:
- changed subject [Yonghong]
- added WARN_ON_ONCE to get_printk_buf [Song]
kernel/trace/bpf_trace.c | 61 +++++++++++++++++++++++++++++++---------
1 file changed, 47 insertions(+), 14 deletions(-)
Ack with a nit below.
Acked-by: Yonghong Song <yhs@xxxxxx>
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3bbd3f0c810c..a992b5a47fd6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -369,33 +369,62 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
return &bpf_probe_write_user_proto;
}
-static DEFINE_RAW_SPINLOCK(trace_printk_lock);
-
#define MAX_TRACE_PRINTK_VARARGS 3
#define BPF_TRACE_PRINTK_SIZE 1024
+#define BPF_TRACE_PRINTK_LEVELS 4
+
+struct trace_printk_buf {
+ char data[BPF_TRACE_PRINTK_LEVELS][BPF_TRACE_PRINTK_SIZE];
+ int level;
+};
+static DEFINE_PER_CPU(struct trace_printk_buf, printk_buf);
+
+static void put_printk_buf(struct trace_printk_buf __percpu *buf)
+{
+ if (WARN_ON_ONCE(this_cpu_read(buf->level) == 0))
+ return;
The above WARN_ON_ONCE is not needed as it never happens based on
implementation. There are a few other similar cases in bpf_trace.c and
none of them has WARN_ON_ONCE.
+ this_cpu_dec(buf->level);
+ preempt_enable();
+}
+
+static bool get_printk_buf(struct trace_printk_buf __percpu *buf, char **data)
+{
+ int level;
+
+ preempt_disable();
+ level = this_cpu_inc_return(buf->level);
+ if (WARN_ON_ONCE(level > BPF_TRACE_PRINTK_LEVELS)) {
+ put_printk_buf(buf);
+ return false;
+ }
+ *data = (char *) this_cpu_ptr(&buf->data[level - 1]);
+ return true;
+}
[...]
