lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

tracing: pass around ring buffer instead of tracer

Browse Source 
The latency tracers (irqsoff and wakeup) can swap trace buffers
on the fly. If an event is happening and has reserved data on one of
the buffers, and the latency tracer swaps the global buffer with the
max buffer, the result is that the event may commit the data to the
wrong buffer.

This patch changes the API to the trace recording to be recieve the
buffer that was used to reserve a commit. Then this buffer can be passed
in to the commit.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
This commit is contained in:
Steven Rostedt
2009-09-02 14:17:06 -04:00
committed by Steven Rostedt
parent f633903af2
commit e77405ad80
12 changed files with 163 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
kernel/trace/trace_events.c
View File

@@ -1438,6 +1438,7 @@ static void
function_test_events_call(unsigned long ip, unsigned long parent_ip)
{
struct ring_buffer_event *event;
struct ring_buffer *buffer;
struct ftrace_entry *entry;
unsigned long flags;
long disabled;
@@ -1455,7 +1456,8 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
local_save_flags(flags);
event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
event = trace_current_buffer_lock_reserve(&buffer,
TRACE_FN, sizeof(*entry),
flags, pc);
if (!event)
goto out;
@@ -1463,7 +1465,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
entry->ip = ip;
entry->parent_ip = parent_ip;
trace_nowake_buffer_unlock_commit(event, flags, pc);
trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
out:
atomic_dec(&per_cpu(test_event_disable, cpu));