86 lines
3.1 KiB
Diff
86 lines
3.1 KiB
Diff
From 6986d818e6d2c846c001fc7211b5a4153e5ecd11 Mon Sep 17 00:00:00 2001
|
|
From: Shiju Jose <shiju.jose@huawei.com>
|
|
Date: Sat, 4 Feb 2023 19:15:55 +0000
|
|
Subject: [PATCH] rasdaemon: Fix poll() on per_cpu trace_pipe_raw blocks
|
|
indefinitely
|
|
|
|
The error events are not received in the rasdaemon since kernel 6.1-rc6.
|
|
This issue is firstly detected and reported, when testing the CXL error
|
|
events in the rasdaemon.
|
|
|
|
Debugging showed, poll() on trace_pipe_raw in the ras-events.c do not
|
|
return and this issue is seen after the commit
|
|
42fb0a1e84ff525ebe560e2baf9451ab69127e2b ("tracing/ring-buffer: Have
|
|
polling block on watermark").
|
|
|
|
This issue is also verified using a test application for poll()
|
|
and select() on per_cpu trace_pipe_raw.
|
|
|
|
There is also a bug reported on this issue,
|
|
https://lore.kernel.org/all/31eb3b12-3350-90a4-a0d9-d1494db7cf74@oracle.com/
|
|
|
|
This issue occurs for the per_cpu case, which calls the ring_buffer_poll_wait(),
|
|
in kernel/trace/ring_buffer.c, with the buffer_percent > 0 and then wait until
|
|
the percentage of pages are available. The default value set for the
|
|
buffer_percent is 50 in the kernel/trace/trace.c. However poll() does not return
|
|
even met the percentage of pages condition.
|
|
|
|
As a fix, rasdaemon set buffer_percent as 0 through the
|
|
/sys/kernel/debug/tracing/instances/rasdaemon/buffer_percent, then the
|
|
task will wake up as soon as data is added to any of the specific cpu
|
|
buffer and poll() on per_cpu/cpuX/trace_pipe_raw does not block
|
|
indefinitely.
|
|
|
|
Dependency on the kernel fix commit
|
|
3e46d910d8acf94e5360126593b68bf4fee4c4a1("tracing: Fix poll() and select()
|
|
do not work on per_cpu trace_pipe and trace_pipe_raw")
|
|
|
|
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
|
|
---
|
|
ras-events.c | 22 ++++++++++++++++++++++
|
|
1 file changed, 22 insertions(+)
|
|
|
|
diff --git a/ras-events.c b/ras-events.c
|
|
index 39f9ce2..49e4f9a 100644
|
|
--- a/ras-events.c
|
|
+++ b/ras-events.c
|
|
@@ -376,6 +376,8 @@ static int read_ras_event_all_cpus(struct pthread_data *pdata,
|
|
int warnonce[n_cpus];
|
|
char pipe_raw[PATH_MAX];
|
|
int legacy_kernel = 0;
|
|
+ int fd;
|
|
+ char buf[16];
|
|
#if 0
|
|
int need_sleep = 0;
|
|
#endif
|
|
@@ -395,6 +397,26 @@ static int read_ras_event_all_cpus(struct pthread_data *pdata,
|
|
return -ENOMEM;
|
|
}
|
|
|
|
+ /* Fix for poll() on the per_cpu trace_pipe and trace_pipe_raw blocks
|
|
+ * indefinitely with the default buffer_percent in the kernel trace system,
|
|
+ * which is introduced by the following change in the kernel.
|
|
+ * https://lore.kernel.org/all/20221020231427.41be3f26@gandalf.local.home/T/#u.
|
|
+ * Set buffer_percent to 0 so that poll() will return immediately
|
|
+ * when the trace data is available in the ras per_cpu trace pipe_raw
|
|
+ */
|
|
+ fd = open_trace(pdata[0].ras, "buffer_percent", O_WRONLY);
|
|
+ if (fd >= 0) {
|
|
+ /* For the backward compatibility to the old kernels, do not return
|
|
+ * if fail to set the buffer_percent.
|
|
+ */
|
|
+ snprintf(buf, sizeof(buf), "0");
|
|
+ size = write(fd, buf, strlen(buf));
|
|
+ if (size <= 0)
|
|
+ log(TERM, LOG_WARNING, "can't write to buffer_percent\n");
|
|
+ close(fd);
|
|
+ } else
|
|
+ log(TERM, LOG_WARNING, "Can't open buffer_percent\n");
|
|
+
|
|
for (i = 0; i < (n_cpus + 1); i++)
|
|
fds[i].fd = -1;
|
|
|
|
--
|
|
2.25.1
|
|
|