[RFC][PATCH 2/7] perf,x86: Ensure perf_sched_cb_{inc,dec}() is only called from pmu::{add,del}()

[Peter Zijlstra <peterz@infradead.org>]

[-- Attachment #1: peterz-perf-move-sched_cb-1.patch --]
[-- Type: text/plain, Size: 7651 bytes --]

Currently perf_sched_cb_{inc,dec}() are called from
pmu::{start,stop}(), which has the problem that this can happen from
NMI context, this is making it hard to optimize perf_pmu_sched_task().

Furthermore, we really only need this accounting on pmu::{add,del}(),
so doing it from pmu::{start,stop}() is doing more work than we really
need.

Introduce x86_pmu::{add,del}() and wire up the LBR and PEBS.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/events/core.c       |   24 ++++++++++++++++++++++--
 arch/x86/events/intel/core.c |   31 ++++++++++++++++++-------------
 arch/x86/events/intel/ds.c   |    8 ++------
 arch/x86/events/intel/lbr.c  |    4 ++--
 arch/x86/events/perf_event.h |   10 ++++++++--
 5 files changed, 52 insertions(+), 25 deletions(-)

--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1197,6 +1197,9 @@ static int x86_pmu_add(struct perf_event
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be performed
 	 * at commit time (->commit_txn) as a whole.
+	 *
+	 * If commit fails, we'll call ->del() on all events
+	 * for which ->add() was called.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
 		goto done_collect;
@@ -1219,6 +1222,14 @@ static int x86_pmu_add(struct perf_event
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
+	if (x86_pmu.add) {
+		/*
+		 * This is before x86_pmu_enable() will call x86_pmu_start(),
+		 * so we enable LBRs before an event needs them etc..
+		 */
+		x86_pmu.add(event);
+	}
+
 	ret = 0;
 out:
 	return ret;
@@ -1342,7 +1353,7 @@ static void x86_pmu_del(struct perf_even
 	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
 
 	/*
-	 * If we're called during a txn, we don't need to do anything.
+	 * If we're called during a txn, we only need to undo x86_pmu.add.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
 	 *
@@ -1350,7 +1361,7 @@ static void x86_pmu_del(struct perf_even
 	 * an event added during that same TXN.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
-		return;
+		goto do_del;
 
 	/*
 	 * Not a TXN, therefore cleanup properly.
@@ -1380,6 +1391,15 @@ static void x86_pmu_del(struct perf_even
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
+
+do_del:
+	if (x86_pmu.del) {
+		/*
+		 * This is after x86_pmu_stop(); so we disable LBRs after any
+		 * event can need them etc..
+		 */
+		x86_pmu.del(event);
+	}
 }
 
 int x86_pmu_handle_irq(struct pt_regs *regs)
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1907,13 +1907,6 @@ static void intel_pmu_disable_event(stru
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	/*
-	 * must disable before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -1925,6 +1918,14 @@ static void intel_pmu_disable_event(stru
 		intel_pmu_pebs_disable(event);
 }
 
+static void intel_pmu_del_event(struct perf_event *event)
+{
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_del(event);
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_del(event);
+}
+
 static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
@@ -1968,12 +1969,6 @@ static void intel_pmu_enable_event(struc
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
-	/*
-	 * must enabled before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1994,6 +1989,14 @@ static void intel_pmu_enable_event(struc
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
+static void intel_pmu_add_event(struct perf_event *event)
+{
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_add(event);
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_add(event);
+}
+
 /*
  * Save and restart an expired event. Called by NMI contexts,
  * so it has to be careful about preempting normal event ops:
@@ -3290,6 +3293,8 @@ static __initconst const struct x86_pmu
 	.enable_all		= intel_pmu_enable_all,
 	.enable			= intel_pmu_enable_event,
 	.disable		= intel_pmu_disable_event,
+	.add			= intel_pmu_add_event,
+	.del			= intel_pmu_del_event,
 	.hw_config		= intel_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -831,7 +831,7 @@ static inline void pebs_update_threshold
 	ds->pebs_interrupt_threshold = threshold;
 }
 
-static void intel_pmu_pebs_add(struct perf_event *event)
+void intel_pmu_pebs_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
@@ -853,8 +853,6 @@ void intel_pmu_pebs_enable(struct perf_e
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
 
-	intel_pmu_pebs_add(event);
-
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
@@ -874,7 +872,7 @@ void intel_pmu_pebs_enable(struct perf_e
 	}
 }
 
-static void intel_pmu_pebs_del(struct perf_event *event)
+void intel_pmu_pebs_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
@@ -910,8 +908,6 @@ void intel_pmu_pebs_disable(struct perf_
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
-
-	intel_pmu_pebs_del(event);
 }
 
 void intel_pmu_pebs_enable_all(void)
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -422,7 +422,7 @@ static inline bool branch_user_callstack
 	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
 }
 
-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
@@ -450,7 +450,7 @@ void intel_pmu_lbr_enable(struct perf_ev
 	perf_sched_cb_inc(event->ctx->pmu);
 }
 
-void intel_pmu_lbr_disable(struct perf_event *event)
+void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -510,6 +510,8 @@ struct x86_pmu {
 	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	void		(*add)(struct perf_event *);
+	void		(*del)(struct perf_event *);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
@@ -890,6 +892,10 @@ extern struct event_constraint intel_skl
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
+void intel_pmu_pebs_add(struct perf_event *event);
+
+void intel_pmu_pebs_del(struct perf_event *event);
+
 void intel_pmu_pebs_enable(struct perf_event *event);
 
 void intel_pmu_pebs_disable(struct perf_event *event);
@@ -908,9 +914,9 @@ u64 lbr_from_signext_quirk_wr(u64 val);
 
 void intel_pmu_lbr_reset(void);
 
-void intel_pmu_lbr_enable(struct perf_event *event);
+void intel_pmu_lbr_add(struct perf_event *event);
 
-void intel_pmu_lbr_disable(struct perf_event *event);
+void intel_pmu_lbr_del(struct perf_event *event);
 
 void intel_pmu_lbr_enable_all(bool pmi);