perf report: Do not process non-JIT BPF ksymbol events
Subsystems (2)
Namhyung Kim
maintainerPATCH 1/1 perf report: Do not process non-JIT BPF ksymbol events
The length of PERF_RECORD_KSYMBOL for BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.
Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
--- tools/perf/util/machine.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/util/machine.c +4 -0
@@ -779,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,if (dump_trace)perf_event__fprintf_ksymbol (event, stdout); +/* no need to process non-JIT BPF as it cannot get samples */ +if (event->ksymbol.len ==0 ) +return 0 ; +if (event->ksymbol.flags &PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER )return machine__process_ksymbol_unregister (machine, event, sample);
Signature · 1 line
2.48.1.711.g2feabab25a-goog
Quoted 12 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Quoted 6 lines
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
Reported-by Kevin Nomura <[email protected]>Cc Song Liu <[email protected]>Signed-off-by Namhyung Kim <[email protected]>
Adrian Hunter
reviewerQuoted 26 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
Reported-by Kevin Nomura <[email protected]>Cc Song Liu <[email protected]>Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/machine.c | 4 ++++ 1 file changed, 4 insertions(+)tools/perf/util/machine.c +0
-0
tools/perf/util/machine.c int machine__process_ksymbol(struct machine *machine __maybe_unused, · line 784
Quoted 6 lines
tools/perf/util/machine.c +3
-0@@ -779,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,if (dump_trace)perf_event__fprintf_ksymbol (event, stdout); +/* no need to process non-JIT BPF as it cannot get samples */ +if (event->ksymbol.len ==0 ) +return 0 ;
Are all ksymbol events BPF? Maybe it is OK
for PERF_RECORD_KSYMBOL_TYPE_OOL also. Perhaps adjust the comment in that case.
Quoted 4 lines
tools/perf/util/machine.c +1
-0+if (event->ksymbol.flags &PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER )return machine__process_ksymbol_unregister (machine, event, sample);
Namhyung Kim
maintainerHello,
Quoted 30 lines · Adrian Hunter
Quoted 29 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
Reported-by Kevin Nomura <[email protected]>Cc Song Liu <[email protected]>Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/machine.c | 4 ++++ 1 file changed, 4 insertions(+)tools/perf/util/machine.c +0
-0@@ -779,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,if (dump_trace)perf_event__fprintf_ksymbol (event, stdout);
Quoted 7 lines
tools/perf/util/machine.c int machine__process_ksymbol(struct machine *machine __maybe_unused, · line 784
Quoted 3 lines
tools/perf/util/machine.c +3
-0+/* no need to process non-JIT BPF as it cannot get samples */ +if (event->ksymbol.len ==0 ) +return 0 ;Are all ksymbol events BPF? Maybe it is OK
forPERF_RECORD_KSYMBOL_TYPE_OOLalso. Perhaps adjust the comment in that case.
Probably, but I didn't see OOL with zero length yet. Is it possible?
Thanks,
Namhyung
Adrian Hunter
reviewerQuoted 41 lines · Namhyung Kim
Hello,
Quoted 30 lines · Adrian Hunter
Quoted 29 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
Reported-by Kevin Nomura <[email protected]>Cc Song Liu <[email protected]>Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/machine.c | 4 ++++ 1 file changed, 4 insertions(+)tools/perf/util/machine.c +0
-0@@ -779,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,if (dump_trace)perf_event__fprintf_ksymbol (event, stdout);Quoted 7 lines
tools/perf/util/machine.c int machine__process_ksymbol(struct machine *machine __maybe_unused, · line 784
Quoted 3 lines
tools/perf/util/machine.c +3
-0+/* no need to process non-JIT BPF as it cannot get samples */ +if (event->ksymbol.len ==0 ) +return 0 ;Are all ksymbol events BPF? Maybe it is OK
forPERF_RECORD_KSYMBOL_TYPE_OOLalso. Perhaps adjust the comment in that case.
Quoted 1 line
Probably, but I didn't see OOL with zero length yet. Is it possible?
Probably not
Namhyung Kim
maintainerQuoted 42 lines · Adrian Hunter
Quoted 41 lines · Namhyung Kim
Hello,
Quoted 37 lines · Adrian Hunter
Quoted 26 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
Probably there's a bug in the kernel map/symbol handling in perf tools. But I think we need to fix this anyway.
Reported-by Kevin Nomura <[email protected]>Cc Song Liu <[email protected]>Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/util/machine.c | 4 ++++ 1 file changed, 4 insertions(+)tools/perf/util/machine.c +0
-0tools/perf/util/machine.c int machine__process_ksymbol(struct machine *machine __maybe_unused, · line 784
Quoted 6 lines
tools/perf/util/machine.c +3
-0@@ -779,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,if (dump_trace)perf_event__fprintf_ksymbol (event, stdout); +/* no need to process non-JIT BPF as it cannot get samples */ +if (event->ksymbol.len ==0 ) +return 0 ;Are all ksymbol events BPF? Maybe it is OK
forPERF_RECORD_KSYMBOL_TYPE_OOLalso. Perhaps adjust the comment in that case.
Quoted 3 lines
Quoted 1 line
Probably, but I didn't see OOL with zero length yet. Is it possible?
Probably not
Then I think it's ok to leave the comment as is.
Thanks,
Namhyung
Quoted 5 lines · Namhyung Kim
The length of
PERF_RECORD_KSYMBOLfor BPF is a size of JITed code so it'd be 0 when it's not JITed. The ksymbol is needed to symbolize the code when it gets samples in the region but non-JITed code cannot get samples. Thus it'd be ok to ignore them.
Quoted 7 lines
Actually it caused a performance issue in the perf tools on old ARM kernels where it can refuse to JIT some BPF codes. It ended up splitting the existing kernel map (kallsyms). And later lookup for a kernel symbol would create a new kernel map from kallsyms and then split it again and again. :(
[...]
Applied to perf-tools-next, thanks!
Best regards,
Namhyung