diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2016-05-16 21:16:54 -0300 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2016-05-16 23:11:54 -0300 |
commit | a29d5c9b8167dbc21a7ca8c0302e3799f9063b4e (patch) | |
tree | 66086a34dd9c788e6ae1b865a56e445361feb492 | |
parent | c85b03349640b34f3545503c8429fc43005e9a92 (diff) | |
download | linux-a29d5c9b8167dbc21a7ca8c0302e3799f9063b4e.tar.bz2 |
perf tools: Separate accounting of contexts and real addresses in a stack trace
The perf_sample->ip_callchain->nr value includes all the entries in the
ip_callchain->ip[] array, real addresses and PERF_CONTEXT_{KERNEL,USER,etc},
while what the user expects is that what is in the kernel.perf_event_max_stack
sysctl or in the upcoming per event perf_event_attr.sample_max_stack knob be
honoured in terms of IP addresses in the stack trace.
So match the kernel support and validate chain->nr taking into account
both kernel.perf_event_max_stack and kernel.perf_event_max_contexts_per_stack.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-mgx0jpzfdq4uq4abfa40byu0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-rw-r--r-- | tools/perf/perf.c | 3 | ||||
-rw-r--r-- | tools/perf/util/machine.c | 26 | ||||
-rw-r--r-- | tools/perf/util/util.c | 3 | ||||
-rw-r--r-- | tools/perf/util/util.h | 3 |
4 files changed, 24 insertions, 11 deletions
diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 797000842d40..15982cee5ef3 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -549,6 +549,9 @@ int main(int argc, const char **argv) if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) sysctl_perf_event_max_stack = value; + if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) + sysctl_perf_event_max_contexts_per_stack = value; + cmd = extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 18dd96bdde05..7ba9fadb68af 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1811,9 +1811,9 @@ static int thread__resolve_callchain_sample(struct thread *thread, { struct branch_stack *branch = sample->branch_stack; struct ip_callchain *chain = sample->callchain; - int chain_nr = min(max_stack, (int)chain->nr); + int chain_nr = chain->nr; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err; + int i, j, err, nr_entries, nr_contexts; int skip_idx = -1; int first_call = 0; @@ -1828,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - if (chain->nr < sysctl_perf_event_max_stack) + if (chain_nr < sysctl_perf_event_max_stack) skip_idx = arch_skip_callchain_idx(thread, chain); /* @@ -1889,12 +1889,8 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) { - pr_warning("corrupted callchain. skipping...\n"); - return 0; - } - - for (i = first_call; i < chain_nr; i++) { + for (i = first_call, nr_entries = 0, nr_contexts = 0; + i < chain_nr && nr_entries < max_stack; i++) { u64 ip; if (callchain_param.order == ORDER_CALLEE) @@ -1908,6 +1904,14 @@ check_calls: #endif ip = chain->ips[j]; + if (ip >= PERF_CONTEXT_MAX) { + if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack) + goto out_corrupted_callchain; + } else { + if (++nr_entries > sysctl_perf_event_max_stack) + goto out_corrupted_callchain; + } + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) @@ -1915,6 +1919,10 @@ check_calls: } return 0; + +out_corrupted_callchain: + pr_warning("corrupted callchain. skipping...\n"); + return 0; } static int unwind_entry(struct unwind_entry *entry, void *arg) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index eab077ad6ca9..23504ad5d6dd 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -33,7 +33,8 @@ struct callchain_param callchain_param = { unsigned int page_size; int cacheline_size; -unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; +int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; +int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; bool test_attr__enabled; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 7651633a8dc7..1e8c3167b9fb 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; -extern unsigned int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_contexts_per_stack; struct parse_tag { char tag; |