From 85550c83da421fb12dc1816c45012e1e638d2b38 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 17 Jun 2021 13:47:25 -0400 Subject: tracing: Do not stop recording cmdlines when tracing is off The saved_cmdlines is used to map pids to the task name, such that the output of the tracing does not just show pids, but also gives a human readable name for the task. If the name is not mapped, the output looks like this: <...>-1316 [005] ...2 132.044039: ... Instead of this: gnome-shell-1316 [005] ...2 132.044039: ... The names are updated when tracing is running, but are skipped if tracing is stopped. Unfortunately, this stops the recording of the names if the top level tracer is stopped, and not if there's other tracers active. The recording of a name only happens when a new event is written into a ring buffer, so there is no need to test if tracing is on or not. If tracing is off, then no event is written and no need to test if tracing is off or not. Remove the check, as it hides the names of tasks for events in the instance buffers. Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9299057feb56..e220b37e29c6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2486,8 +2486,6 @@ static bool tracing_record_taskinfo_skip(int flags) { if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; if (!__this_cpu_read(trace_taskinfo_save)) return true; return false; -- cgit v1.2.3 From 4fdd595e4f9a1ff6d93ec702eaecae451cfc6591 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 17 Jun 2021 14:32:34 -0400 Subject: tracing: Do not stop recording comms if the trace file is being read A while ago, when the "trace" file was opened, tracing was stopped, and code was added to stop recording the comms to saved_cmdlines, for mapping of the pids to the task name. Code has been added that only records the comm if a trace event occurred, and there's no reason to not trace it if the trace file is opened. Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e220b37e29c6..d23a09d3eb37 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -3996,9 +3993,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -4041,9 +4035,6 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } -- cgit v1.2.3 From 89529d8b8f8daf92d9979382b8d2eb39966846ea Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 17 Jun 2021 17:12:35 -0400 Subject: tracing: Do no increment trace_clock_global() by one The trace_clock_global() tries to make sure the events between CPUs is somewhat in order. A global value is used and updated by the latest read of a clock. If one CPU is ahead by a little, and is read by another CPU, a lock is taken, and if the timestamp of the other CPU is behind, it will simply use the other CPUs timestamp. The lock is also only taken with a "trylock" due to tracing, and strange recursions can happen. The lock is not taken at all in NMI context. In the case where the lock is not able to be taken, the non synced timestamp is returned. But it will not be less than the saved global timestamp. The problem arises because when the time goes "backwards" the time returned is the saved timestamp plus 1. If the lock is not taken, and the plus one to the timestamp is returned, there's a small race that can cause the time to go backwards! CPU0 CPU1 ---- ---- trace_clock_global() { ts = clock() [ 1000 ] trylock(clock_lock) [ success ] global_ts = ts; [ 1000 ] trace_clock_global() { ts = clock() [ 999 ] if (ts < global_ts) ts = global_ts + 1 [ 1001 ] trylock(clock_lock) [ fail ] return ts [ 1001] } unlock(clock_lock); return ts; [ 1000 ] } trace_clock_global() { ts = clock() [ 1000 ] if (ts < global_ts) [ false 1000 == 1000 ] trylock(clock_lock) [ success ] global_ts = ts; [ 1000 ] unlock(clock_lock) return ts; [ 1000 ] } The above case shows to reads of trace_clock_global() on the same CPU, but the second read returns one less than the first read. That is, time when backwards, and this is not what is allowed by trace_clock_global(). This was triggered by heavy tracing and the ring buffer checker that tests for the clock going backwards: Ring buffer clock went backwards: 20613921464 -> 20613921463 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 0 at kernel/trace/ring_buffer.c:3412 check_buffer+0x1b9/0x1c0 Modules linked in: [..] [CPU: 2]TIME DOES NOT MATCH expected:20620711698 actual:20620711697 delta:6790234 before:20613921463 after:20613921463 [20613915818] PAGE TIME STAMP [20613915818] delta:0 [20613915819] delta:1 [20613916035] delta:216 [20613916465] delta:430 [20613916575] delta:110 [20613916749] delta:174 [20613917248] delta:499 [20613917333] delta:85 [20613917775] delta:442 [20613917921] delta:146 [20613918321] delta:400 [20613918568] delta:247 [20613918768] delta:200 [20613919306] delta:538 [20613919353] delta:47 [20613919980] delta:627 [20613920296] delta:316 [20613920571] delta:275 [20613920862] delta:291 [20613921152] delta:290 [20613921464] delta:312 [20613921464] delta:0 TIME EXTEND [20613921464] delta:0 This happened more than once, and always for an off by one result. It also started happening after commit aafe104aa9096 was added. Cc: stable@vger.kernel.org Fixes: aafe104aa9096 ("tracing: Restructure trace_clock_global() to never block") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_clock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index c1637f90c8a3..4702efb00ff2 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -115,9 +115,9 @@ u64 notrace trace_clock_global(void) prev_time = READ_ONCE(trace_clock_struct.prev_time); now = sched_clock_cpu(this_cpu); - /* Make sure that now is always greater than prev_time */ + /* Make sure that now is always greater than or equal to prev_time */ if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; /* * If in an NMI context then dont risk lockups and simply return @@ -131,7 +131,7 @@ u64 notrace trace_clock_global(void) /* Reread prev_time in case it was already updated */ prev_time = READ_ONCE(trace_clock_struct.prev_time); if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; trace_clock_struct.prev_time = now; -- cgit v1.2.3