perf, x86: Fix event scheduler for constraints with overlapping counters

The current x86 event scheduler fails to resolve scheduling problems
of certain combinations of events and constraints. This happens if the
counter mask of such an event is not a subset of any other counter
mask of a constraint with an equal or higher weight, e.g. constraints
of the AMD family 15h pmu:

                        counter mask    weight

 amd_f15_PMC30          0x09            2  <--- overlapping counters
 amd_f15_PMC20          0x07            3
 amd_f15_PMC53          0x38            3

The scheduler does not find then an existing solution. Here is an
example:

 event code     counter         failure         possible solution

 0x02E          PMC[3,0]        0               3
 0x043          PMC[2:0]        1               0
 0x045          PMC[2:0]        2               1
 0x046          PMC[2:0]        FAIL            2

The event scheduler may not select the correct counter in the first
cycle because it needs to know which subsequent events will be
scheduled. It may fail to schedule the events then.

To solve this, we now save the scheduler state of events with
overlapping counter counstraints.  If we fail to schedule the events
we rollback to those states and try to use another free counter.

Constraints with overlapping counters are marked with a new introduced
overlap flag. We set the overlap flag for such constraints to give the
scheduler a hint which events to select for counter rescheduling. The
EVENT_CONSTRAINT_OVERLAP() macro can be used for this.

Care must be taken as the rescheduling algorithm is O(n!) which will
increase scheduling cycles for an over-commited system dramatically.
The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter
masks must be kept at a minimum. Thus, the current stack is limited to
2 states to limit the number of loops the algorithm takes in the worst
case.

On systems with no overlapping-counter constraints, this
implementation does not increase the loop count compared to the
previous algorithm.

V2:
* Renamed redo -> overlap.
* Reimplementation using perf scheduling helper functions.

V3:
* Added WARN_ON_ONCE() if out of save states.
* Changed function interface of perf_sched_restore_state() to use bool
  as return value.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 28 insertions, 2 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index b9698d40ac4b..51a985cbc12f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -45,6 +45,7 @@ struct event_constraint {
 	u64	code;
 	u64	cmask;
 	int	weight;
+	int	overlap;
 };
 
 struct amd_nb {
@@ -151,15 +152,40 @@ struct cpu_hw_events {
 	void				*kfree_on_online;
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
 	.cmask = (m),			\
 	.weight = (w),			\
+	.overlap = (o),			\
 }
 
 #define EVENT_CONSTRAINT(c, n, m)	\
-	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+
+/*
+ * The overlap flag marks event constraints with overlapping counter
+ * masks. This is the case if the counter mask of such an event is not
+ * a subset of any other counter mask of a constraint with an equal or
+ * higher weight, e.g.:
+ *
+ *  c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
+ *  c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
+ *  c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
+ *
+ * The event scheduler may not select the correct counter in the first
+ * cycle because it needs to know which subsequent events will be
+ * scheduled. It may fail to schedule the events then. So we set the
+ * overlap flag for such constraints to give the scheduler a hint which
+ * events to select for counter rescheduling.
+ *
+ * Care must be taken as the rescheduling algorithm is O(n!) which
+ * will increase scheduling cycles for an over-commited system
+ * dramatically.  The number of such EVENT_CONSTRAINT_OVERLAP() macros
+ * and its counter masks must be kept at a minimum.
+ */
+#define EVENT_CONSTRAINT_OVERLAP(c, n, m)	\
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1)
 
 /*
  * Constraint on the Event code.