summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2016-05-20 08:19:20 +0200
committerIngo Molnar <mingo@kernel.org>2016-05-20 08:20:14 +0200
commit21f77d231fabd33c5de61fbff31818d93203353e (patch)
tree74bd85f1184b26409605884bf65ae1c1ba5d724c /include
parentb0a434fb7412937d55f15b8897c5646c81497bbe (diff)
parenta29d5c9b8167dbc21a7ca8c0302e3799f9063b4e (diff)
downloadop-kernel-dev-21f77d231fabd33c5de61fbff31818d93203353e.zip
op-kernel-dev-21f77d231fabd33c5de61fbff31818d93203353e.tar.gz
Merge tag 'perf-core-for-mingo-20160516' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: User visible changes: - Honour the kernel.perf_event_max_stack knob more precisely by not counting PERF_CONTEXT_{KERNEL,USER} when deciding when to stop adding entries to the perf_sample->ip_callchain[] array (Arnaldo Carvalho de Melo) - Fix identation of 'stalled-backend-cycles' in 'perf stat' (Namhyung Kim) - Update runtime using 'cpu-clock' event in 'perf stat' (Namhyung Kim) - Use 'cpu-clock' for cpu targets in 'perf stat' (Namhyung Kim) - Avoid fractional digits for integer scales in 'perf stat' (Andi Kleen) - Store vdso buildid unconditionally, as it appears in callchains and we're not checking those when creating the build-id table, so we end up not being able to resolve VDSO symbols when doing analysis on a different machine than the one where recording was done, possibly of a different arch even (arm -> x86_64) (He Kuang) Infrastructure changes: - Generalize max_stack sysctl handler, will be used for configuring multiple kernel knobs related to callchains (Arnaldo Carvalho de Melo) Cleanups: - Introduce DSO__NAME_KALLSYMS and DSO__NAME_KCORE, to stop using open coded strings (Masami Hiramatsu) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/perf_event.h34
-rw-r--r--include/uapi/linux/perf_event.h1
2 files changed, 30 insertions, 5 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9e1c3ad..6b87be9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,6 +61,14 @@ struct perf_callchain_entry {
__u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
+struct perf_callchain_entry_ctx {
+ struct perf_callchain_entry *entry;
+ u32 max_stack;
+ u32 nr;
+ short contexts;
+ bool contexts_maxed;
+};
+
struct perf_raw_record {
u32 size;
void *data;
@@ -1063,20 +1071,36 @@ extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
-extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
- bool crosstask, bool add_mark);
+ u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
+
+static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
+{
+ if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
+ struct perf_callchain_entry *entry = ctx->entry;
+ entry->ip[entry->nr++] = ip;
+ ++ctx->contexts;
+ return 0;
+ } else {
+ ctx->contexts_maxed = true;
+ return -1; /* no more room, stop walking the stack */
+ }
+}
-static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
- if (entry->nr < sysctl_perf_event_max_stack) {
+ if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
+ struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
+ ++ctx->nr;
return 0;
} else {
return -1; /* no more room, stop walking the stack */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 43fc8d2..36ce552 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -862,6 +862,7 @@ enum perf_event_type {
};
#define PERF_MAX_STACK_DEPTH 127
+#define PERF_MAX_CONTEXTS_PER_STACK 8
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
OpenPOWER on IntegriCloud