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, 49 insertions, 7 deletions

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;