summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorArnaldo Carvalho de Melo <acme@redhat.com>2016-04-28 13:16:33 -0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2016-05-30 12:41:44 -0300
commit97c79a38cd454602645f0470ffb444b3b75ce574 (patch)
tree40e427e9c76c5e4e1a5f2da1f3ec81e34223fa9b /kernel
parent480ca357fd7f86a381a5b35a8157aa176eddbed4 (diff)
perf core: Per event callchain limit
Additionally to being able to control the system wide maximum depth via /proc/sys/kernel/perf_event_max_stack, now we are able to ask for different depths per event, using perf_event_attr.sample_max_stack for that. This uses an u16 hole at the end of perf_event_attr, that, when perf_event_attr.sample_type has the PERF_SAMPLE_CALLCHAIN, if sample_max_stack is zero, means use perf_event_max_stack, otherwise it'll be bounds checked under callchain_mutex. 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: Linus Torvalds <torvalds@linux-foundation.org> 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-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/stackmap.c2
-rw-r--r--kernel/events/callchain.c14
-rw-r--r--kernel/events/core.c5
3 files changed, 17 insertions, 4 deletions
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a82d7605db3f..f1de5c1a2af6 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -99,7 +99,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
if (err)
goto free_smap;
- err = get_callchain_buffers();
+ err = get_callchain_buffers(sysctl_perf_event_max_stack);
if (err)
goto free_smap;
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 179ef4640964..e9fdb5203de5 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -104,7 +104,7 @@ fail:
return -ENOMEM;
}
-int get_callchain_buffers(void)
+int get_callchain_buffers(int event_max_stack)
{
int err = 0;
int count;
@@ -121,6 +121,15 @@ int get_callchain_buffers(void)
/* If the allocation failed, give up */
if (!callchain_cpus_entries)
err = -ENOMEM;
+ /*
+ * If requesting per event more than the global cap,
+ * return a different error to help userspace figure
+ * this out.
+ *
+ * And also do it here so that we have &callchain_mutex held.
+ */
+ if (event_max_stack > sysctl_perf_event_max_stack)
+ err = -EOVERFLOW;
goto exit;
}
@@ -174,11 +183,12 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
bool user = !event->attr.exclude_callchain_user;
/* Disallow cross-task user callchains. */
bool crosstask = event->ctx->task && event->ctx->task != current;
+ const u32 max_stack = event->attr.sample_max_stack;
if (!kernel && !user)
return NULL;
- return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
+ return get_perf_callchain(regs, 0, kernel, user, max_stack, crosstask, true);
}
struct perf_callchain_entry *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 050a290c72c7..79363f298445 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8843,7 +8843,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
- err = get_callchain_buffers();
+ err = get_callchain_buffers(attr->sample_max_stack);
if (err)
goto err_addr_filters;
}
@@ -9165,6 +9165,9 @@ SYSCALL_DEFINE5(perf_event_open,
return -EINVAL;
}
+ if (!attr.sample_max_stack)
+ attr.sample_max_stack = sysctl_perf_event_max_stack;
+
/*
* In cgroup mode, the pid argument is used to pass the fd
* opened to the cgroup directory in cgroupfs. The cpu argument