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

Pull perf updates from Ingo Molnar:
 "The main kernel side changes in this cycle were:

   - Various Intel-PT updates and optimizations (Alexander Shishkin)

   - Prohibit kprobes on Xen/KVM emulate prefixes (Masami Hiramatsu)

   - Add support for LSM and SELinux checks to control access to the
     perf syscall (Joel Fernandes)

   - Misc other changes, optimizations, fixes and cleanups - see the
     shortlog for details.

  There were numerous tooling changes as well - 254 non-merge commits.
  Here are the main changes - too many to list in detail:

   - Enhancements to core tooling infrastructure, perf.data, libperf,
     libtraceevent, event parsing, vendor events, Intel PT, callchains,
     BPF support and instruction decoding.

   - There were updates to the following tools:

        perf annotate
        perf diff
        perf inject
        perf kvm
        perf list
        perf maps
        perf parse
        perf probe
        perf record
        perf report
        perf script
        perf stat
        perf test
        perf trace

   - And a lot of other changes: please see the shortlog and Git log for
     more details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (279 commits)
  perf parse: Fix potential memory leak when handling tracepoint errors
  perf probe: Fix spelling mistake "addrees" -> "address"
  libtraceevent: Fix memory leakage in copy_filter_type
  libtraceevent: Fix header installation
  perf intel-bts: Does not support AUX area sampling
  perf intel-pt: Add support for decoding AUX area samples
  perf intel-pt: Add support for recording AUX area samples
  perf pmu: When using default config, record which bits of config were changed by the user
  perf auxtrace: Add support for queuing AUX area samples
  perf session: Add facility to peek at all events
  perf auxtrace: Add support for dumping AUX area samples
  perf inject: Cut AUX area samples
  perf record: Add aux-sample-size config term
  perf record: Add support for AUX area sampling
  perf auxtrace: Add support for AUX area sample recording
  perf auxtrace: Move perf_evsel__find_pmu()
  perf record: Add a function to test for kernel support for AUX area sampling
  perf tools: Add kernel AUX area sampling definitions
  perf/core: Make the mlock accounting simple again
  perf report: Jump to symbol source view from total cycles view
  ...

Author: torvalds

MAINTAINERS

@@ -12846,6 +12846,13 @@ F:	arch/*/events/*
 F:	arch/*/events/*/*
 F:	tools/perf/
 
+PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS
+R:	John Garry <[email protected]>
+R:	Will Deacon <[email protected]>
+L:	[email protected] (moderated for non-subscribers)
+S:	Supported
+F:	tools/perf/pmu-events/arch/arm64/
+
 PERSONALITY HANDLING
 M:	Christoph Hellwig <[email protected]>
 L:	[email protected]

arch/powerpc/perf/core-book3s.c

@@ -96,7 +96,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
 {
 	return 0;
 }
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { }
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { }
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	return 0;
@@ -127,7 +127,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
 static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
-static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
+static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
 
@@ -179,7 +179,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
  * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the
  * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER.
  */
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp)
 {
 	unsigned long mmcra = regs->dsisr;
 	bool sdar_valid;
@@ -204,8 +204,7 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 
-	if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-		is_kernel_addr(mfspr(SPRN_SDAR)))
+	if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
 		*addrp = 0;
 }
 
@@ -444,7 +443,7 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 }
 
 /* Processing BHRB entries */
-static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw)
 {
 	u64 val;
 	u64 addr;
@@ -472,8 +471,7 @@ static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
 			 * exporting it to userspace (avoid exposure of regions
 			 * where we could have speculative execution)
 			 */
-			if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-				is_kernel_addr(addr))
+			if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is
@@ -2087,12 +2085,12 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (event->attr.sample_type &
 		    (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
-			perf_get_data_addr(regs, &data.addr);
+			perf_get_data_addr(event, regs, &data.addr);
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
-			power_pmu_bhrb_read(cpuhw);
+			power_pmu_bhrb_read(event, cpuhw);
 			data.br_stack = &cpuhw->bhrb_stack;
 		}
 

arch/x86/events/amd/core.c

@@ -652,15 +652,7 @@ static void amd_pmu_disable_event(struct perf_event *event)
  */
 static int amd_pmu_handle_irq(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int active, handled;
-
-	/*
-	 * Obtain the active count before calling x86_pmu_handle_irq() since
-	 * it is possible that x86_pmu_handle_irq() may make a counter
-	 * inactive (through x86_pmu_stop).
-	 */
-	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+	int handled;
 
 	/* Process any counter overflows */
 	handled = x86_pmu_handle_irq(regs);
@@ -670,8 +662,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	 * NMIs will be claimed if arriving within that window.
 	 */
 	if (handled) {
-		this_cpu_write(perf_nmi_tstamp,
-			       jiffies + perf_nmi_window);
+		this_cpu_write(perf_nmi_tstamp, jiffies + perf_nmi_window);
 
 		return handled;
 	}

arch/x86/events/core.c

@@ -2243,6 +2243,13 @@ static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 		x86_pmu.sched_task(ctx, sched_in);
 }
 
+static void x86_pmu_swap_task_ctx(struct perf_event_context *prev,
+				  struct perf_event_context *next)
+{
+	if (x86_pmu.swap_task_ctx)
+		x86_pmu.swap_task_ctx(prev, next);
+}
+
 void perf_check_microcode(void)
 {
 	if (x86_pmu.check_microcode)
@@ -2297,6 +2304,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
 	.aux_output_match	= x86_pmu_aux_output_match,

arch/x86/events/intel/bts.c

@@ -549,9 +549,11 @@ static int bts_event_init(struct perf_event *event)
 	 * Note that the default paranoia setting permits unprivileged
 	 * users to profile the kernel.
 	 */
-	if (event->attr.exclude_kernel && perf_paranoid_kernel() &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if (event->attr.exclude_kernel) {
+		ret = perf_allow_kernel(&event->attr);
+		if (ret)
+			return ret;
+	}
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;

arch/x86/events/intel/core.c

@@ -3315,8 +3315,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (x86_pmu.version < 3)
 		return -EINVAL;
 
-	if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	ret = perf_allow_cpu(&event->attr);
+	if (ret)
+		return ret;
 
 	event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
 
@@ -3830,6 +3831,12 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static void intel_pmu_swap_task_ctx(struct perf_event_context *prev,
+				    struct perf_event_context *next)
+{
+	intel_pmu_lbr_swap_task_ctx(prev, next);
+}
+
 static int intel_pmu_check_period(struct perf_event *event, u64 value)
 {
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
@@ -3965,6 +3972,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+	.swap_task_ctx		= intel_pmu_swap_task_ctx,
 
 	.check_period		= intel_pmu_check_period,
 

arch/x86/events/intel/lbr.c

@@ -417,6 +417,29 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
+void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
+				 struct perf_event_context *next)
+{
+	struct x86_perf_task_context *prev_ctx_data, *next_ctx_data;
+
+	swap(prev->task_ctx_data, next->task_ctx_data);
+
+	/*
+	 * Architecture specific synchronization makes sense in
+	 * case both prev->task_ctx_data and next->task_ctx_data
+	 * pointers are allocated.
+	 */
+
+	prev_ctx_data = next->task_ctx_data;
+	next_ctx_data = prev->task_ctx_data;
+
+	if (!prev_ctx_data || !next_ctx_data)
+		return;
+
+	swap(prev_ctx_data->lbr_callstack_users,
+	     next_ctx_data->lbr_callstack_users);
+}
+
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

arch/x86/events/intel/p4.c

@@ -776,8 +776,9 @@ static int p4_validate_raw_event(struct perf_event *event)
 	 * the user needs special permissions to be able to use it
 	 */
 	if (p4_ht_active() && p4_event_bind_map[v].shared) {
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		v = perf_allow_cpu(&event->attr);
+		if (v)
+			return v;
 	}
 
 	/* ESCR EventMask bits may be invalid */