Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf update from Thomas Gleixner:
 "The perf crowd presents:

  Kernel updates:

   - Removal of jprobes

   - Cleanup and consolidatation the handling of kprobes

   - Cleanup and consolidation of hardware breakpoints

   - The usual pile of fixes and updates to PMUs and event descriptors

  Tooling updates:

   - Updates and improvements all over the place. Nothing outstanding,
     just the (good) boring incremental grump work"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  perf trace: Do not require --no-syscalls to suppress strace like output
  perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h
  perf tools: Allow overriding MAX_NR_CPUS at compile time
  perf bpf: Show better message when failing to load an object
  perf list: Unify metric group description format with PMU event description
  perf vendor events arm64: Update ThunderX2 implementation defined pmu core events
  perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet
  perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON packet
  perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet
  perf cs-etm: Fix start tracing packet handling
  perf build: Fix installation directory for eBPF
  perf c2c report: Fix crash for empty browser
  perf tests: Fix indexing when invoking subtests
  perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
  perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg
  perf trace beauty: Do not print NULL strarray entries
  perf beauty: Add a generator for IPPROTO_ socket's protocol constants
  tools include uapi: Grab a copy of linux/in.h
  perf tests: Fix complex event name parsing
  perf evlist: Fix error out while applying initial delay and LBR
  ...

1 files changed, 34 insertions, 15 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8dbba77e0518..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_glp_pebs_event_constraints[] = {
-	/* Allow all events as PEBS with no flags */
-	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
-	EVENT_CONSTRAINT_END
-};
-
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -871,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * Extended PEBS support
+	 * Makes the PEBS code search the normal constraints.
+	 */
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		return NULL;
+
 	return &emptyconstraint;
 }
 
@@ -896,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	u64 threshold;
+	int reserved;
+
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+	else
+		reserved = x86_pmu.max_pebs_events;
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+			reserved * x86_pmu.pebs_record_size;
 	} else {
 		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 	}
@@ -963,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		ds->pebs_event_reset[hwc->idx] =
+		unsigned int idx = hwc->idx;
+
+		if (idx >= INTEL_PMC_IDX_FIXED)
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
@@ -1481,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	short counts[MAX_PEBS_EVENTS] = {};
-	short error[MAX_PEBS_EVENTS] = {};
-	int bit, i;
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int bit, i, size;
+	u64 mask;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1493,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
+	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+	size = x86_pmu.max_pebs_events;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+	}
+
 	if (unlikely(base >= top)) {
 		/*
 		 * The drain_pebs() could be called twice in a short period
@@ -1502,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * update the event->count for this case.
 		 */
 		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 x86_pmu.max_pebs_events) {
+				 size) {
 			event = cpuc->events[bit];
 			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 				intel_pmu_save_and_restart_reload(event, 0);
@@ -1515,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		u64 pebs_status;
 
 		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+		pebs_status &= mask;
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
 			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+					 size)
 				counts[bit]++;
 
 			continue;
@@ -1568,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+	for (bit = 0; bit < size; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;