perf/core: Add a 'flags' parameter to the PMU transactional interfaces

Currently, the PMU interface allows reading only one counter at a time.
But some PMUs like the 24x7 counters in Power, support reading several
counters at once. To leveage this functionality, extend the transaction
interface to support a "transaction type".

The first type, PERF_PMU_TXN_ADD, refers to the existing transactions,
i.e. used to _schedule_ all the events on the PMU as a group. A second
transaction type, PERF_PMU_TXN_READ, will be used in a follow-on patch,
by the 24x7 counters to read several counters at once.

Extend the transaction interfaces to the PMU to accept a 'txn_flags'
parameter and use this parameter to ignore any transactions that are
not of type PERF_PMU_TXN_ADD.

Thanks to Peter Zijlstra for his input.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
[peterz: s390 compile fix]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.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>
Link: http://lkml.kernel.org/r/1441336073-22750-3-git-send-email-sukadev@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/cpu/perf_event.c

@@ -1748,9 +1748,21 @@ static inline void x86_pmu_read(struct perf_event *event)
  * Start group events scheduling transaction
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
+ *
+ * We only support PERF_PMU_TXN_ADD transactions. Save the
+ * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD
+ * transactions.
  */
-static void x86_pmu_start_txn(struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON_ONCE(cpuc->txn_flags);		/* txn already in flight */
+
+	cpuc->txn_flags = txn_flags;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_disable(pmu);
 	__this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN);
 	__this_cpu_write(cpu_hw_events.n_txn, 0);
@@ -1763,6 +1775,16 @@ static void x86_pmu_start_txn(struct pmu *pmu)
  */
 static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
+	unsigned int txn_flags;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON_ONCE(!cpuc->txn_flags);	/* no txn in flight */
+
+	txn_flags = cpuc->txn_flags;
+	cpuc->txn_flags = 0;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
 	/*
 	 * Truncate collected array by the number of events added in this
@@ -1786,6 +1808,13 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
 	int assign[X86_PMC_IDX_MAX];
 	int n, ret;
 
+	WARN_ON_ONCE(!cpuc->txn_flags);	/* no txn in flight */
+
+	if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) {
+		cpuc->txn_flags = 0;
+		return 0;
+	}
+
 	n = cpuc->n_events;
 
 	if (!x86_pmu_initialized())
@@ -1802,6 +1831,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	cpuc->txn_flags = 0;
 	perf_pmu_enable(pmu);
 	return 0;
 }

arch/x86/kernel/cpu/perf_event.h

@@ -196,6 +196,7 @@ struct cpu_hw_events {
 	int			n_excl; /* the number of exclusive events */
 
 	unsigned int		group_flag;
+	unsigned int		txn_flags;
 	int			is_fake;
 
 	/*