summaryrefslogtreecommitdiffstats
path: root/include/linux/perf_counter.h
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@samba.org>2009-01-14 21:00:30 +1100
committerPaul Mackerras <paulus@samba.org>2009-01-14 21:00:30 +1100
commit3b6f9e5cb21964b7ce12bf81076f830885563ec8 (patch)
treee9d5ecffafa66cc3aeb259ade15a2611ad795327 /include/linux/perf_counter.h
parent01d0287f068de2934109ba9b989d8807526cccc2 (diff)
downloadlinux-stable-3b6f9e5cb21964b7ce12bf81076f830885563ec8.tar.gz
linux-stable-3b6f9e5cb21964b7ce12bf81076f830885563ec8.tar.bz2
linux-stable-3b6f9e5cb21964b7ce12bf81076f830885563ec8.zip
perf_counter: Add support for pinned and exclusive counter groups
Impact: New perf_counter features A pinned counter group is one that the user wants to have on the CPU whenever possible, i.e. whenever the associated task is running, for a per-task group, or always for a per-cpu group. If the system cannot satisfy that, it puts the group into an error state where it is not scheduled any more and reads from it return EOF (i.e. 0 bytes read). The group can be released from error state and made readable again using prctl(PR_TASK_PERF_COUNTERS_ENABLE). When we have finer-grained enable/disable controls on counters we'll be able to reset the error state on individual groups. An exclusive group is one that the user wants to be the only group using the CPU performance monitor hardware whenever it is on. The counter group scheduler will not schedule an exclusive group if there are already other groups on the CPU and will not schedule other groups onto the CPU if there is an exclusive group scheduled (that statement does not apply to groups containing only software counters, which can always go on and which do not prevent an exclusive group from going on). With an exclusive group, we will be able to let users program PMU registers at a low level without the concern that those settings will perturb other measurements. Along the way this reorganizes things a little: - is_software_counter() is moved to perf_counter.h. - cpuctx->active_oncpu now records the number of hardware counters on the CPU, i.e. it now excludes software counters. Nothing was reading cpuctx->active_oncpu before, so this change is harmless. - A new cpuctx->exclusive field records whether we currently have an exclusive group on the CPU. - counter_sched_out moves higher up in perf_counter.c and gets called from __perf_counter_remove_from_context and __perf_counter_exit_task, where we used to have essentially the same code. - __perf_counter_sched_in now goes through the counter list twice, doing the pinned counters in the first loop and the non-pinned counters in the second loop, in order to give the pinned counters the best chance to be scheduled in. Note that only a group leader can be exclusive or pinned, and that attribute applies to the whole group. This avoids some awkwardness in some corner cases (e.g. where a group leader is closed and the other group members get added to the context list). If we want to relax that restriction later, we can, and it is easier to relax a restriction than to apply a new one. This doesn't yet handle the case where a pinned counter is inherited and goes into error state in the child - the error state is not propagated up to the parent when the child exits, and arguably it should. Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'include/linux/perf_counter.h')
-rw-r--r--include/linux/perf_counter.h15
1 files changed, 14 insertions, 1 deletions
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index b21d1ea4c054..7ab8e5f96f5b 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -86,7 +86,10 @@ struct perf_counter_hw_event {
nmi : 1, /* NMI sampling */
raw : 1, /* raw event type */
inherit : 1, /* children inherit it */
- __reserved_1 : 28;
+ pinned : 1, /* must always be on PMU */
+ exclusive : 1, /* only counter on PMU */
+
+ __reserved_1 : 26;
u64 __reserved_2;
};
@@ -141,6 +144,7 @@ struct hw_perf_counter_ops {
* enum perf_counter_active_state - the states of a counter
*/
enum perf_counter_active_state {
+ PERF_COUNTER_STATE_ERROR = -2,
PERF_COUNTER_STATE_OFF = -1,
PERF_COUNTER_STATE_INACTIVE = 0,
PERF_COUNTER_STATE_ACTIVE = 1,
@@ -214,6 +218,7 @@ struct perf_cpu_context {
struct perf_counter_context *task_ctx;
int active_oncpu;
int max_pertask;
+ int exclusive;
};
/*
@@ -240,6 +245,14 @@ extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
struct perf_cpu_context *cpuctx,
struct perf_counter_context *ctx, int cpu);
+/*
+ * Return 1 for a software counter, 0 for a hardware counter
+ */
+static inline int is_software_counter(struct perf_counter *counter)
+{
+ return !counter->hw_event.raw && counter->hw_event.type < 0;
+}
+
#else
static inline void
perf_counter_task_sched_in(struct task_struct *task, int cpu) { }