summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2016-05-20 09:19:20 +0300
committerIngo Molnar <mingo@kernel.org>2016-05-20 09:20:14 +0300
commit21f77d231fabd33c5de61fbff31818d93203353e (patch)
tree74bd85f1184b26409605884bf65ae1c1ba5d724c /kernel
parentb0a434fb7412937d55f15b8897c5646c81497bbe (diff)
parenta29d5c9b8167dbc21a7ca8c0302e3799f9063b4e (diff)
downloadlinux-21f77d231fabd33c5de61fbff31818d93203353e.tar.xz
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 'kernel')
-rw-r--r--kernel/bpf/stackmap.c3
-rw-r--r--kernel/events/callchain.c36
-rw-r--r--kernel/sysctl.c11
3 files changed, 36 insertions, 14 deletions
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index f5a19548be12..a82d7605db3f 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -136,7 +136,8 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
- trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
+ trace = get_perf_callchain(regs, init_nr, kernel, user,
+ sysctl_perf_event_max_stack, false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index b9325e7dcba1..179ef4640964 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -19,11 +19,13 @@ struct callchain_cpus_entries {
};
int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;
static inline size_t perf_callchain_entry__sizeof(void)
{
return (sizeof(struct perf_callchain_entry) +
- sizeof(__u64) * sysctl_perf_event_max_stack);
+ sizeof(__u64) * (sysctl_perf_event_max_stack +
+ sysctl_perf_event_max_contexts_per_stack));
}
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
@@ -32,12 +34,12 @@ static DEFINE_MUTEX(callchain_mutex);
static struct callchain_cpus_entries *callchain_cpus_entries;
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
@@ -176,14 +178,15 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
if (!kernel && !user)
return NULL;
- return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
+ return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
}
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)
{
struct perf_callchain_entry *entry;
+ struct perf_callchain_entry_ctx ctx;
int rctx;
entry = get_callchain_entry(&rctx);
@@ -193,12 +196,16 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
if (!entry)
goto exit_put;
- entry->nr = init_nr;
+ ctx.entry = entry;
+ ctx.max_stack = max_stack;
+ ctx.nr = entry->nr = init_nr;
+ ctx.contexts = 0;
+ ctx.contexts_maxed = false;
if (kernel && !user_mode(regs)) {
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
- perf_callchain_kernel(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL);
+ perf_callchain_kernel(&ctx, regs);
}
if (user) {
@@ -214,8 +221,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
goto exit_put;
if (add_mark)
- perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
+ perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+ perf_callchain_user(&ctx, regs);
}
}
@@ -225,10 +232,15 @@ exit_put:
return entry;
}
+/*
+ * Used for sysctl_perf_event_max_stack and
+ * sysctl_perf_event_max_contexts_per_stack.
+ */
int perf_event_max_stack_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- int new_value = sysctl_perf_event_max_stack, ret;
+ int *value = table->data;
+ int new_value = *value, ret;
struct ctl_table new_table = *table;
new_table.data = &new_value;
@@ -240,7 +252,7 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write,
if (atomic_read(&nr_callchain_events))
ret = -EBUSY;
else
- sysctl_perf_event_max_stack = new_value;
+ *value = new_value;
mutex_unlock(&callchain_mutex);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c8b318663525..bec4c11c47d6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1149,13 +1149,22 @@ static struct ctl_table kern_table[] = {
},
{
.procname = "perf_event_max_stack",
- .data = NULL, /* filled in by handler */
+ .data = &sysctl_perf_event_max_stack,
.maxlen = sizeof(sysctl_perf_event_max_stack),
.mode = 0644,
.proc_handler = perf_event_max_stack_handler,
.extra1 = &zero,
.extra2 = &six_hundred_forty_kb,
},
+ {
+ .procname = "perf_event_max_contexts_per_stack",
+ .data = &sysctl_perf_event_max_contexts_per_stack,
+ .maxlen = sizeof(sysctl_perf_event_max_contexts_per_stack),
+ .mode = 0644,
+ .proc_handler = perf_event_max_stack_handler,
+ .extra1 = &zero,
+ .extra2 = &one_thousand,
+ },
#endif
#ifdef CONFIG_KMEMCHECK
{