ftrace: Add function names to dangling } in function graph tracer
Steven Rostedt
maintainerIngo,
Please pull the latest tip/tracing/core tree, which can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/tracing/core
Steven Rostedt (1):
ftrace: Add function names to dangling } in function graph tracer
----
kernel/trace/trace_functions_graph.c | 52 ++++++++++++++++++++++++++++------ 1 files changed, 43 insertions(+), 9 deletions(-) --------------------------- commit f1c7f517a5dc23bce07efa5ed55e2c074ed9d4ba Author: Steven Rostedt <[email protected]> Date: Fri Feb 26 17:08:16 2010 -0500
ftrace: Add function names to dangling } in function graph tracer
The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost.
On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'.
Here is how a typical trace output starts:
[tracing] cat trace
# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | }
0) ! 567.961 us | }
0) <========== |
0) ! 579.083 us | _raw_spin_lock_irqsave();
0) 4.694 us | _raw_spin_unlock_irqrestore();
0) ! 594.862 us | }
0) ! 603.361 us | }
0) ! 613.574 us | }
0) ! 623.554 us | }
0) 3.653 us | fget_light();
0) | sock_poll() {
There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to.
This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'.
This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in.
Here is what the above trace will look like after this patch:
[tracing] cat trace
# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | } (irq_exit)
0) ! 567.961 us | } (smp_apic_timer_interrupt)
0) <========== |
0) ! 579.083 us | _raw_spin_lock_irqsave();
0) 4.694 us | _raw_spin_unlock_irqrestore();
0) ! 594.862 us | } (add_wait_queue)
0) ! 603.361 us | } (__pollwait)
0) ! 613.574 us | } (tcp_poll)
0) ! 623.554 us | } (sock_poll)
0) 3.653 us | fget_light();
0) | sock_poll() {
kernel/trace/trace_functions_graph.c +43 -9
@@ -18,6 +18,7 @@ struct fgraph_cpu_data {pid_t last_pid;int depth;int ignore; +unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH ]; };struct fgraph_data {
@@ -670,15 +671,21 @@ print_graph_entry_leaf(struct trace_iterator *iter, duration = graph_ret->rettime - graph_ret->calltime;if (data) { +struct fgraph_cpu_data *cpu_data;int cpu = iter->cpu; -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); + + cpu_data =per_cpu_ptr (data->cpu_data, cpu);/* * Comments display at + 1 to depth. Since * this is a leaf function, keep the comments * equal to this depth. */ - *depth = call->depth -1 ; + cpu_data->depth = call->depth -1 ; + +/* No need to keep this function around for this depth */ +if (call->depth <FTRACE_RETFUNC_DEPTH ) + cpu_data->enter_funcs[call->depth] =0 ; }/* Overhead */
@@ -718,10 +725,15 @@ print_graph_entry_nested(struct trace_iterator *iter,int i;if (data) { +struct fgraph_cpu_data *cpu_data;int cpu = iter->cpu; -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); - *depth = call->depth; + cpu_data =per_cpu_ptr (data->cpu_data, cpu); + cpu_data->depth = call->depth; + +/* Save this function pointer to see if the exit matches */ +if (call->depth <FTRACE_RETFUNC_DEPTH ) + cpu_data->enter_funcs[call->depth] = call->func; }/* No overhead */
@@ -851,18 +863,28 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,struct fgraph_data *data = iter->private;pid_t pid = ent->pid;int cpu = iter->cpu; +int func_match =1 ;int ret;int i;if (data) { -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); +struct fgraph_cpu_data *cpu_data; +int cpu = iter->cpu; + + cpu_data =per_cpu_ptr (data->cpu_data, cpu);/* * Comments display at + 1 to depth. This is the * return from a function, we now want the comments * to display at the same level of the bracket. */ - *depth = trace->depth -1 ; + cpu_data->depth = trace->depth -1 ; + +if (trace->depth <FTRACE_RETFUNC_DEPTH ) { +if (cpu_data->enter_funcs[trace->depth] != trace->func) + func_match =0 ; + cpu_data->enter_funcs[trace->depth] =0 ; + } }if (print_graph_prologue (iter, s,0 ,0 ))
@@ -887,9 +909,21 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,return TRACE_TYPE_PARTIAL_LINE ; } - ret =trace_seq_printf (s,"}\n" ); -if (!ret) -return TRACE_TYPE_PARTIAL_LINE ; +/* +* If the return function does not have a matching entry, +* then the entry was lost. Instead of just printing +* the '}' and letting the user guess what function this +* belongs to, write out the function name. +*/ +if (func_match) { + ret =trace_seq_printf (s,"}\n" ); +if (!ret) +return TRACE_TYPE_PARTIAL_LINE ; + }else { + ret =trace_seq_printf (s,"} (%ps)\n" , (void *)trace->func); +if (!ret) +return TRACE_TYPE_PARTIAL_LINE ; + }/* Overrun */ if (tracer_flags.val &TRACE_GRAPH_PRINT_OVERRUN ) {
Quoted 9 lines · Steven Rostedt
Ingo,
Please pull the latest tip/tracing/core tree, which can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/tracing/core
Quoted 6 lines
Steven Rostedt (1):
ftrace: Add function names to dangling } in function graph tracer----
kernel/trace/trace_functions_graph.c | 52 ++++++++++++++++++++++++++++------ 1 files changed, 43 insertions(+), 9 deletions(-)
Pulled, thanks Steve!
Quoted 8 lines
[tracing] cat trace
# tracer:function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | } (irq_exit)
0) ! 567.961 us | } (smp_apic_timer_interrupt)
0) <========== |
Quoted 8 lines
0) ! 579.083 us |
_raw_spin_lock_irqsave();
0) 4.694 us |_raw_spin_unlock_irqrestore();
0) ! 594.862 us | } (add_wait_queue)
0) ! 603.361 us | } (__pollwait)
0) ! 613.574 us | } (tcp_poll)
0) ! 623.554 us | } (sock_poll)
0) 3.653 us |fget_light();
0) |sock_poll(){
Neat! I think it would read even more C-ish if it was something non-syntactic, like:
Quoted 4 lines
0) ! 594.862 us | } /* add_wait_queue */
0) ! 603.361 us | } /* __pollwait */
0) ! 613.574 us | } /* tcp_poll */
0) ! 623.554 us | } /* sock_poll */hm?
Ingo
Quoted 20 lines · Ingo Molnar
Quoted 8 lines
[tracing] cat trace
# tracer:function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | } (irq_exit)
0) ! 567.961 us | } (smp_apic_timer_interrupt)
0) <========== |Quoted 8 lines
0) ! 579.083 us |
_raw_spin_lock_irqsave();
0) 4.694 us |_raw_spin_unlock_irqrestore();
0) ! 594.862 us | } (add_wait_queue)
0) ! 603.361 us | } (__pollwait)
0) ! 613.574 us | } (tcp_poll)
0) ! 623.554 us | } (sock_poll)
0) 3.653 us |fget_light();
0) |sock_poll(){Neat! I think it would read even more C-ish if it was something non-syntactic, like:
Quoted 6 lines
Quoted 4 lines
0) ! 594.862 us | } /* add_wait_queue */ 0) ! 603.361 us | } /* __pollwait */ 0) ! 613.574 us | } /* tcp_poll */ 0) ! 623.554 us | } /* sock_poll */hm?
Agreed. It won't even be confusing with other events that are printed as comments, since we have the closing brace before.
Quoted 2 lines
Ingo
Steven Rostedt
maintainerQuoted 4 lines · Ingo Molnar
* Steven Rostedt <[email protected]> wrote:
Quoted 8 lines
Neat! I think it would read even more C-ish if it was something non-syntactic, like:
Quoted 4 lines
0) ! 594.862 us | } /* add_wait_queue */ 0) ! 603.361 us | } /* __pollwait */ 0) ! 613.574 us | } /* tcp_poll */ 0) ! 623.554 us | } /* sock_poll */
Yeah, that looks better. I'll write up a patch when I get a chance.
Thanks,
-- Steve
Quoted 48 lines · Steven Rostedt
commit
f1c7f517a5dc23bce07efa5ed55e2c074ed9d4baAuthor: Steven Rostedt <[email protected]> Date: Fri Feb 26 17:08:16 2010 -0500ftrace: Add function names to dangling } in function graph tracer
The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost.
On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'.
Here is how a typical trace output starts:
[tracing] cat trace
# tracer:function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | }
0) ! 567.961 us | }
0) <========== |
0) ! 579.083 us |_raw_spin_lock_irqsave();
0) 4.694 us |_raw_spin_unlock_irqrestore();
0) ! 594.862 us | }
0) ! 603.361 us | }
0) ! 613.574 us | }
0) ! 623.554 us | }
0) 3.653 us |fget_light();
0) |sock_poll(){There are a series of '}' with no matching "
func(){". There's no information to what functions these ending brackets belong to.This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'.
This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in.
Here is what the above trace will look like after this patch:
Quoted 16 lines
[tracing] cat trace
# tracer:function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
0) + 91.897 us | } (irq_exit)
0) ! 567.961 us | } (smp_apic_timer_interrupt)
0) <========== |
0) ! 579.083 us |_raw_spin_lock_irqsave();
0) 4.694 us |_raw_spin_unlock_irqrestore();
0) ! 594.862 us | } (add_wait_queue)
0) ! 603.361 us | } (__pollwait)
0) ! 613.574 us | } (tcp_poll)
0) ! 623.554 us | } (sock_poll)
0) 3.653 us |fget_light();
0) |sock_poll(){
That's a good idea.
Quoted 25 lines
Signed-off-by Steven Rostedt <[email protected]>kernel/trace/trace_functions_graph.c +4
-1@@ -18,6 +18,7 @@ struct fgraph_cpu_data {pid_t last_pid;int depth;int ignore; +unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH ]; };struct fgraph_data {@@ -670,15 +671,21 @@ print_graph_entry_leaf(struct trace_iterator *iter, duration = graph_ret->rettime - graph_ret->calltime;if (data) { +struct fgraph_cpu_data *cpu_data;int cpu = iter->cpu; -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); + + cpu_data =per_cpu_ptr (data->cpu_data, cpu);
kernel/trace/trace_functions_graph.c print_graph_entry_leaf(struct trace_iterator *iter, · line 687
Quoted 10 lines
kernel/trace/trace_functions_graph.c +4
-1/* * Comments display at + 1 to depth. Since * this is a leaf function, keep the comments * equal to this depth. */ - *depth = call->depth -1 ; + cpu_data->depth = call->depth -1 ; + +/* No need to keep this function around for this depth */ +if (call->depth <FTRACE_RETFUNC_DEPTH )
Do you really need to check that? call->depth >= FTRACE_RETFUNC_DEPTH are not recorded.
Quoted 70 lines
kernel/trace/trace_functions_graph.c +28
-7+ cpu_data->enter_funcs[call->depth] =0 ; }/* Overhead */ @@ -718,10 +725,15 @@ print_graph_entry_nested(struct trace_iterator *iter,int i;if (data) { +struct fgraph_cpu_data *cpu_data;int cpu = iter->cpu; -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); - *depth = call->depth; + cpu_data =per_cpu_ptr (data->cpu_data, cpu); + cpu_data->depth = call->depth; + +/* Save this function pointer to see if the exit matches */ +if (call->depth <FTRACE_RETFUNC_DEPTH ) + cpu_data->enter_funcs[call->depth] = call->func; }/* No overhead */ @@ -851,18 +863,28 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,struct fgraph_data *data = iter->private;pid_t pid = ent->pid;int cpu = iter->cpu; +int func_match =1 ;int ret;int i;if (data) { -int *depth = &(per_cpu_ptr (data->cpu_data, cpu)->depth); +struct fgraph_cpu_data *cpu_data; +int cpu = iter->cpu; + + cpu_data =per_cpu_ptr (data->cpu_data, cpu);/* * Comments display at + 1 to depth. This is the * return from a function, we now want the comments * to display at the same level of the bracket. */ - *depth = trace->depth -1 ; + cpu_data->depth = trace->depth -1 ; + +if (trace->depth <FTRACE_RETFUNC_DEPTH ) { +if (cpu_data->enter_funcs[trace->depth] != trace->func) + func_match =0 ; + cpu_data->enter_funcs[trace->depth] =0 ; + } }if (print_graph_prologue (iter, s,0 ,0 ))@@ -887,9 +909,21 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,return TRACE_TYPE_PARTIAL_LINE ; } - ret =trace_seq_printf (s,"}\n" ); -if (!ret) -return TRACE_TYPE_PARTIAL_LINE ; +/* +* If the return function does not have a matching entry, +* then the entry was lost. Instead of just printing +* the '}' and letting the user guess what function this +* belongs to, write out the function name. +*/ +if (func_match) { + ret =trace_seq_printf (s,"}\n" );
kernel/trace/trace_functions_graph.c print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, · line 929
Quoted 10 lines
kernel/trace/trace_functions_graph.c +7
-0+if (!ret) +return TRACE_TYPE_PARTIAL_LINE ; + }else { + ret =trace_seq_printf (s,"} (%ps)\n" , (void *)trace->func); +if (!ret) +return TRACE_TYPE_PARTIAL_LINE ; + }/* Overrun */ if (tracer_flags.val &TRACE_GRAPH_PRINT_OVERRUN ) {
Very nice!
Steven Rostedt
maintainerQuoted 7 lines · Frederic Weisbecker
Quoted 7 lines
kernel/trace/trace_functions_graph.c +1
-1/* * Comments display at + 1 to depth. Since * this is a leaf function, keep the comments * equal to this depth. */ - *depth = call->depth -1 ; + cpu_data->depth = call->depth -1 ;
Quoted 10 lines
kernel/trace/trace_functions_graph.c print_graph_entry_leaf(struct trace_iterator *iter, · line 687
Quoted 3 lines
kernel/trace/trace_functions_graph.c +3
-0+ +/* No need to keep this function around for this depth */ +if (call->depth <FTRACE_RETFUNC_DEPTH )Do you really need to check that?
call->depth>=FTRACE_RETFUNC_DEPTHare not recorded.
Call me paranoid, but working inside the kernel makes me paranoid. If for some reason a trace gets corrupted here, not doing this check can cause a kernel oops.
Quoted 2 lines
kernel/trace/trace_functions_graph.c print_graph_entry_leaf(struct trace_iterator *iter, · line 688
Quoted 2 lines
kernel/trace/trace_functions_graph.c +1
-0+ cpu_data->enter_funcs[call->depth] =0 ;
cpu_data->enter_funcs[102340320211] = 0;
would be bad ;-)
Hmm, I should also make sure depth is not less than zero. I'll send a new patch to do that too.
-- Steve
Quoted 2 lines
Quoted 2 lines
}
Quoted 20 lines · Steven Rostedt
Quoted 7 lines · Frederic Weisbecker
Quoted 7 lines
kernel/trace/trace_functions_graph.c +1
-1/* * Comments display at + 1 to depth. Since * this is a leaf function, keep the comments * equal to this depth. */ - *depth = call->depth -1 ; + cpu_data->depth = call->depth -1 ;Quoted 10 lines
kernel/trace/trace_functions_graph.c print_graph_entry_leaf(struct trace_iterator *iter, · line 687
Quoted 3 lines
kernel/trace/trace_functions_graph.c +3
-0+ +/* No need to keep this function around for this depth */ +if (call->depth <FTRACE_RETFUNC_DEPTH )Do you really need to check that?
call->depth>=FTRACE_RETFUNC_DEPTHare not recorded.
Quoted 3 lines
Call me paranoid, but working inside the kernel makes me paranoid. If for some reason a trace gets corrupted here, not doing this check can cause a kernel oops.
Ok but this may also hide a bug.
Could it be a WARN_ON_ONCE?
Quoted 10 lines
Quoted 2 lines
kernel/trace/trace_functions_graph.c print_graph_entry_leaf(struct trace_iterator *iter, · line 688
Quoted 2 lines
kernel/trace/trace_functions_graph.c +1
-0+ cpu_data->enter_funcs[call->depth] =0 ;cpu_data->enter_funcs[102340320211] = 0;
would be bad ;-)
Hmm, I should also make sure depth is not less than zero. I'll send a new patch to do that too.
With a WARN_ON_ONCE? :)
Thanks.