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>

7 files changed, 153 insertions, 10 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b0382f3f1095..c84074185c80 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -49,6 +49,7 @@ struct cpu_hw_events {
 	unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 
 	unsigned int group_flag;
+	unsigned int txn_flags;
 	int n_txn_start;
 
 	/* BHRB bits */
@@ -1586,11 +1587,21 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags)
  * 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 power_pmu_start_txn(struct pmu *pmu)
+static void power_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
 {
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
+	WARN_ON_ONCE(cpuhw->txn_flags);		/* txn already in flight */
+
+	cpuhw->txn_flags = txn_flags;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
@@ -1604,6 +1615,14 @@ static void power_pmu_start_txn(struct pmu *pmu)
 static void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+	unsigned int txn_flags;
+
+	WARN_ON_ONCE(!cpuhw->txn_flags);	/* no txn in flight */
+
+	txn_flags = cpuhw->txn_flags;
+	cpuhw->txn_flags = 0;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1621,7 +1640,15 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 
 	if (!ppmu)
 		return -EAGAIN;
+
 	cpuhw = this_cpu_ptr(&cpu_hw_events);
+	WARN_ON_ONCE(!cpuhw->txn_flags);	/* no txn in flight */
+
+	if (cpuhw->txn_flags & ~PERF_PMU_TXN_ADD) {
+		cpuhw->txn_flags = 0;
+		return 0;
+	}
+
 	n = cpuhw->n_events;
 	if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
 		return -EAGAIN;
@@ -1633,6 +1660,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	cpuhw->txn_flags = 0;
 	perf_pmu_enable(pmu);
 	return 0;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 56fdad479115..19138be412d6 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -72,6 +72,7 @@ struct cpu_hw_events {
 	atomic_t		ctr_set[CPUMF_CTR_SET_MAX];
 	u64			state, tx_state;
 	unsigned int		flags;
+	unsigned int		txn_flags;
 };
 static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.ctr_set = {
@@ -82,6 +83,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	},
 	.state = 0,
 	.flags = 0,
+	.txn_flags = 0,
 };
 
 static int get_counter_set(u64 event)
@@ -572,11 +574,21 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
 /*
  * Start group events scheduling transaction.
  * Set flags to perform a single test 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 cpumf_pmu_start_txn(struct pmu *pmu)
+static void cpumf_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
 {
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
+	WARN_ON_ONCE(cpuhw->txn_flags);		/* txn already in flight */
+
+	cpuhw->txn_flags = txn_flags;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_disable(pmu);
 	cpuhw->flags |= PERF_EVENT_TXN;
 	cpuhw->tx_state = cpuhw->state;
@@ -589,8 +601,16 @@ static void cpumf_pmu_start_txn(struct pmu *pmu)
  */
 static void cpumf_pmu_cancel_txn(struct pmu *pmu)
 {
+	unsigned int txn_flags;
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
+	WARN_ON_ONCE(!cpuhw->txn_flags);	/* no txn in flight */
+
+	txn_flags = cpuhw->txn_flags;
+	cpuhw->txn_flags = 0;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	WARN_ON(cpuhw->tx_state != cpuhw->state);
 
 	cpuhw->flags &= ~PERF_EVENT_TXN;
@@ -607,6 +627,13 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	u64 state;
 
+	WARN_ON_ONCE(!cpuhw->txn_flags);	/* no txn in flight */
+
+	if (cpuhw->txn_flags & ~PERF_PMU_TXN_ADD) {
+		cpuhw->txn_flags = 0;
+		return 0;
+	}
+
 	/* check if the updated state can be scheduled */
 	state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
 	state >>= CPUMF_LCCTL_ENABLE_SHIFT;
@@ -614,6 +641,7 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
 		return -EPERM;
 
 	cpuhw->flags &= ~PERF_EVENT_TXN;
+	cpuhw->txn_flags = 0;
 	perf_pmu_enable(pmu);
 	return 0;
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index e3f89c7e5062..2c0984d146ec 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -109,6 +109,7 @@ struct cpu_hw_events {
 	int			enabled;
 
 	unsigned int		group_flag;
+	unsigned int		txn_flags;
 };
 static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
 
@@ -1494,10 +1495,16 @@ static int sparc_pmu_event_init(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
 {
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
+	WARN_ON_ONCE(cpuhw->txn_flags);		/* txn already in flight */
+
+	cpuhw->txn_flags = txn_flags;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
@@ -1510,6 +1517,14 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
 static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+	unsigned int txn_flags;
+
+	WARN_ON_ONCE(!cpuhw->txn_flags);	/* no txn in flight */
+
+	txn_flags = cpuhw->txn_flags;
+	cpuhw->txn_flags = 0;
+	if (txn_flags & ~PERF_PMU_TXN_ADD)
+		return;
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1528,6 +1543,13 @@ static int sparc_pmu_commit_txn(struct pmu *pmu)
 	if (!sparc_pmu)
 		return -EINVAL;
 
+	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 (check_excludes(cpuc->event, 0, n))
 		return -EINVAL;
@@ -1535,6 +1557,7 @@ static int sparc_pmu_commit_txn(struct pmu *pmu)
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	cpuc->txn_flags = 0;
 	perf_pmu_enable(pmu);
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 66dd3fe99b82..dc77ef470e0e 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/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;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d868fc1..c99c93b9e348 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/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;
 
 	/*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d61ee4459eee..ea3b5dd21a4c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -201,6 +201,8 @@ struct perf_event;
  */
 #define PERF_EVENT_TXN 0x1
 
+#define PERF_PMU_TXN_ADD  0x1		/* txn to add/schedule event on PMU */
+
 /**
  * pmu::capabilities flags
  */
@@ -331,20 +333,26 @@ struct pmu {
 	 *
 	 * Start the transaction, after this ->add() doesn't need to
 	 * do schedulability tests.
+	 *
+	 * Optional.
 	 */
-	void (*start_txn)		(struct pmu *pmu); /* optional */
+	void (*start_txn)		(struct pmu *pmu, unsigned int txn_flags);
 	/*
 	 * If ->start_txn() disabled the ->add() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
+	 *
+	 * Optional.
 	 */
-	int  (*commit_txn)		(struct pmu *pmu); /* optional */
+	int  (*commit_txn)		(struct pmu *pmu);
 	/*
 	 * Will cancel the transaction, assumes ->del() is called
 	 * for each successful ->add() during the transaction.
+	 *
+	 * Optional.
 	 */
-	void (*cancel_txn)		(struct pmu *pmu); /* optional */
+	void (*cancel_txn)		(struct pmu *pmu);
 
 	/*
 	 * Will return the value for perf_event_mmap_page::index for this event,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 76e64be9bfb5..c80cee82959f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1914,7 +1914,7 @@ group_sched_in(struct perf_event *group_event,
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	pmu->start_txn(pmu);
+	pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
 		pmu->cancel_txn(pmu);
@@ -7267,24 +7267,49 @@ static void perf_pmu_nop_void(struct pmu *pmu)
 {
 }
 
+static void perf_pmu_nop_txn(struct pmu *pmu, unsigned int flags)
+{
+}
+
 static int perf_pmu_nop_int(struct pmu *pmu)
 {
 	return 0;
 }
 
-static void perf_pmu_start_txn(struct pmu *pmu)
+DEFINE_PER_CPU(unsigned int, nop_txn_flags);
+
+static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
 {
+	__this_cpu_write(nop_txn_flags, flags);
+
+	if (flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_disable(pmu);
 }
 
 static int perf_pmu_commit_txn(struct pmu *pmu)
 {
+	unsigned int flags = __this_cpu_read(nop_txn_flags);
+
+	__this_cpu_write(nop_txn_flags, 0);
+
+	if (flags & ~PERF_PMU_TXN_ADD)
+		return 0;
+
 	perf_pmu_enable(pmu);
 	return 0;
 }
 
 static void perf_pmu_cancel_txn(struct pmu *pmu)
 {
+	unsigned int flags =  __this_cpu_read(nop_txn_flags);
+
+	__this_cpu_write(nop_txn_flags, 0);
+
+	if (flags & ~PERF_PMU_TXN_ADD)
+		return;
+
 	perf_pmu_enable(pmu);
 }
 
@@ -7523,7 +7548,7 @@ got_cpu_context:
 			pmu->commit_txn = perf_pmu_commit_txn;
 			pmu->cancel_txn = perf_pmu_cancel_txn;
 		} else {
-			pmu->start_txn  = perf_pmu_nop_void;
+			pmu->start_txn  = perf_pmu_nop_txn;
 			pmu->commit_txn = perf_pmu_nop_int;
 			pmu->cancel_txn = perf_pmu_nop_void;
 		}