From 5168ae50a66e3ff7184c2b16d661bd6d70367e50 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 3 Jun 2010 09:36:50 -0400 Subject: tracing: Remove ftrace_preempt_disable/enable The ftrace_preempt_disable/enable functions were to address a recursive race caused by the function tracer. The function tracer traces all functions which makes it easily susceptible to recursion. One area was preempt_enable(). This would call the scheduler and the schedulre would call the function tracer and loop. (So was it thought). The ftrace_preempt_disable/enable was made to protect against recursion inside the scheduler by storing the NEED_RESCHED flag. If it was set before the ftrace_preempt_disable() it would not call schedule on ftrace_preempt_enable(), thinking that if it was set before then it would have already scheduled unless it was already in the scheduler. This worked fine except in the case of SMP, where another task would set the NEED_RESCHED flag for a task on another CPU, and then kick off an IPI to trigger it. This could cause the NEED_RESCHED to be saved at ftrace_preempt_disable() but the IPI to arrive in the the preempt disabled section. The ftrace_preempt_enable() would not call the scheduler because the flag was already set before entring the section. This bug would cause a missed preemption check and cause lower latencies. Investigating further, I found that the recusion caused by the function tracer was not due to schedule(), but due to preempt_schedule(). Now that preempt_schedule is completely annotated with notrace, the recusion no longer is an issue. Reported-by: Thomas Gleixner Signed-off-by: Steven Rostedt --- kernel/trace/trace_stack.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace/trace_stack.c') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index f4bc9b27de5f..056468eae7cf 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -110,12 +110,12 @@ static inline void check_stack(void) static void stack_trace_call(unsigned long ip, unsigned long parent_ip) { - int cpu, resched; + int cpu; if (unlikely(!ftrace_enabled || stack_trace_disabled)) return; - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); /* no atomic needed, we only modify this variable by this cpu */ @@ -127,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) out: per_cpu(trace_active, cpu)--; /* prevent recursion in schedule */ - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static struct ftrace_ops trace_ops __read_mostly = -- cgit v1.2.3 From 151772dbfad4dbe81721e40f9b3d588ea77bb7aa Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 25 Aug 2010 11:32:38 +1000 Subject: tracing/trace_stack: Fix stack trace on ppc64 save_stack_trace() stores the instruction pointer, not the function descriptor. On ppc64 the trace stack code currently dereferences the instruction pointer and shows 8 bytes of instructions in our backtraces: # cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (26 entries) ----- ---- -------- 0) 5424 112 0x6000000048000004 1) 5312 160 0x60000000ebad01b0 2) 5152 160 0x2c23000041c20030 3) 4992 240 0x600000007c781b79 4) 4752 160 0xe84100284800000c 5) 4592 192 0x600000002fa30000 6) 4400 256 0x7f1800347b7407e0 7) 4144 208 0xe89f0108f87f0070 8) 3936 272 0xe84100282fa30000 Since we aren't dealing with function descriptors, use %pS instead of %pF to fix it: # cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (26 entries) ----- ---- -------- 0) 5424 112 ftrace_call+0x4/0x8 1) 5312 160 .current_io_context+0x28/0x74 2) 5152 160 .get_io_context+0x48/0xa0 3) 4992 240 .cfq_set_request+0x94/0x4c4 4) 4752 160 .elv_set_request+0x60/0x84 5) 4592 192 .get_request+0x2d4/0x468 6) 4400 256 .get_request_wait+0x7c/0x258 7) 4144 208 .__make_request+0x49c/0x610 8) 3936 272 .generic_make_request+0x390/0x434 Signed-off-by: Anton Blanchard Cc: rostedt@goodmis.org Cc: fweisbec@gmail.com LKML-Reference: <20100825013238.GE28360@kryten> Signed-off-by: Ingo Molnar --- kernel/trace/trace_stack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/trace_stack.c') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 056468eae7cf..a6b7e0e0f3eb 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i) { unsigned long addr = stack_dump_trace[i]; - return seq_printf(m, "%pF\n", (void *)addr); + return seq_printf(m, "%pS\n", (void *)addr); } static void print_disabled(struct seq_file *m) -- cgit v1.2.3