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
  ...

4 files changed, 107 insertions, 35 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 86f0c15dcc2d..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
-
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
 		x86_perf_event_update(event);
 }
 
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
+	u64 ctrl_val, mask, bits = 0;
 
 	/*
-	 * Enable IRQ generation (0x8),
+	 * Enable IRQ generation (0x8), if not PEBS,
 	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
 	 * if requested:
 	 */
-	bits = 0x8ULL;
+	if (!event->attr.precise_ip)
+		bits |= 0x8;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event_is_checkpointed(event)))
 		cpuc->intel_cp_status |= (1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc);
+		intel_pmu_enable_fixed(event);
 		return;
 	}
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
-
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
@@ -2280,7 +2282,10 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		status &= ~cpuc->pebs_enabled;
+	else
+		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -4072,7 +4077,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_skl();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_glm_extra_regs;
 		/*
 		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4082,6 +4086,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
 		x86_pmu.cpu_events = glm_events_attrs;
 		/* Goldmont Plus has 4-wide pipeline */
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;
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
 
 void intel_pmu_lbr_reset(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
 	if (!x86_pmu.lbr_nr)
 		return;
 
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
+
+	cpuc->last_task_ctx = NULL;
+	cpuc->last_log_id = 0;
 }
 
 /*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
 
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
@@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		return;
 	}
 
-	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
-	for (i = 0; i < tos; i++) {
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Did not enter C6
+	 */
+	if ((task_ctx == cpuc->last_task_ctx) &&
+	    (task_ctx->log_id == cpuc->last_log_id) &&
+	    rdlbr_from(tos)) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
 		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+
+	for (; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrlbr_from(lbr_idx, 0);
+		wrlbr_to(lbr_idx, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+	}
+
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned lbr_idx, mask;
-	u64 tos;
+	u64 tos, from;
 	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
@@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		from = rdlbr_from(lbr_idx);
+		if (!from)
+			break;
+		task_ctx->lbr_from[i] = from;
 		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = task_ctx;
+	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
@@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
-	bool need_info = false;
+	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	if (cpuc->lbr_sel) {
 		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
 		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-			num = tos;
+			call_stack = true;
 	}
 
 	for (i = 0; i < num; i++) {
@@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		from = rdlbr_from(lbr_idx);
 		to   = rdlbr_to(lbr_idx);
 
+		/*
+		 * Read LBR call stack entries
+		 * until invalid entry (0s) is detected.
+		 */
+		if (call_stack && !from)
+			break;
+
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9f3711470ec1..156286335351 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -163,6 +163,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
+struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
@@ -214,6 +215,8 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
 	u64				br_sel;
+	struct x86_perf_task_context	*last_task_ctx;
+	int				last_log_id;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -648,8 +651,10 @@ struct x86_perf_task_context {
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
 	int tos;
+	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
+	int log_id;
 };
 
 #define x86_add_quirk(func_)						\
@@ -668,6 +673,7 @@ do {									\
 #define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
 #define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr