Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Misc race fixes uncovered by fuzzing efforts, a Sparse fix, two PMU
  driver fixes, plus miscellanous tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86: Reject non sampling events with precise_ip
  perf/x86/intel: Account interrupts for PEBS errors
  perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race
  perf/core: Fix sys_perf_event_open() vs. hotplug
  perf/x86/intel: Use ULL constant to prevent undefined shift behaviour
  perf/x86/intel/uncore: Fix hardcoded socket 0 assumption in the Haswell init code
  perf/x86: Set pmu->module in Intel PMU modules
  perf probe: Fix to probe on gcc generated symbols for offline kernel
  perf probe: Fix --funcs to show correct symbols for offline module
  perf symbols: Robustify reading of build-id from sysfs
  perf tools: Install tools/lib/traceevent plugins with install-bin
  tools lib traceevent: Fix prev/next_prio for deadline tasks
  perf record: Fix --switch-output documentation and comment
  perf record: Make __record_options static
  tools lib subcmd: Add OPT_STRING_OPTARG_SET option
  perf probe: Fix to get correct modname from elf header
  samples/bpf trace_output_user: Remove duplicate sys/ioctl.h include
  samples/bpf sock_example: Avoid getting ethhdr from two includes
  perf sched timehist: Show total scheduling time

arch/x86/events/core.c

@@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+
+		/* There's no sense in having PEBS for non sampling events: */
+		if (!is_sampling_event(event))
+			return -EINVAL;
 	}
 	/*
 	 * check that PEBS LBR correction does not conflict with

arch/x86/events/intel/core.c

@@ -3987,7 +3987,7 @@ __init int intel_pmu_init(void)
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
 		x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
 	}
-	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
 
 	if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",

arch/x86/events/intel/cstate.c

@@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static struct pmu cstate_pkg_pmu = {
@@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static const struct cstate_model nhm_cstates __initconst = {

arch/x86/events/intel/ds.c

@@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		/* log dropped samples number */
-		if (error[bit])
+		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
+			if (perf_event_account_interrupt(event))
+				x86_pmu_stop(event, 0);
+		}
+
 		if (counts[bit]) {
 			__intel_pmu_pebs_event(event, iregs, base,
 					       top, bit, counts[bit]);

arch/x86/events/intel/rapl.c

@@ -697,6 +697,7 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.module		= THIS_MODULE;
 	return 0;
 }
 

arch/x86/events/intel/uncore.c

@@ -733,6 +733,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.start		= uncore_pmu_event_start,
 			.stop		= uncore_pmu_event_stop,
 			.read		= uncore_pmu_event_read,
+			.module		= THIS_MODULE,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;

arch/x86/events/intel/uncore_snbep.c

@@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = boot_cpu_data.logical_proc_id;
 
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;

include/linux/perf_event.h

@@ -1259,6 +1259,7 @@ extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
 extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
+extern int perf_event_account_interrupt(struct perf_event *event);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,

kernel/events/core.c

@@ -2249,35 +2249,34 @@ static int  __perf_install_in_context(void *info)
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
-	bool activate = true;
+	bool reprogram = true;
 	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
 	if (ctx->task) {
 		raw_spin_lock(&ctx->lock);
 		task_ctx = ctx;
 
-		/* If we're on the wrong CPU, try again */
-		if (task_cpu(ctx->task) != smp_processor_id()) {
-			ret = -ESRCH;
-			goto unlock;
-		}
+		reprogram = (ctx->task == current);
 
 		/*
-		 * If we're on the right CPU, see if the task we target is
-		 * current, if not we don't have to activate the ctx, a future
-		 * context switch will do that for us.
+		 * If the task is running, it must be running on this CPU,
+		 * otherwise we cannot reprogram things.
+		 *
+		 * If its not running, we don't care, ctx->lock will
+		 * serialize against it becoming runnable.
 		 */
-		if (ctx->task != current)
-			activate = false;
-		else
-			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+		if (task_curr(ctx->task) && !reprogram) {
+			ret = -ESRCH;
+			goto unlock;
+		}
 
+		WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx);
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	if (activate) {
+	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
 		ctx_resched(cpuctx, task_ctx);
@@ -2328,13 +2327,36 @@ perf_install_in_context(struct perf_event_context *ctx,
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
+	 *
+	 * Instead we use task_curr(), which tells us if the task is running.
+	 * However, since we use task_curr() outside of rq::lock, we can race
+	 * against the actual state. This means the result can be wrong.
+	 *
+	 * If we get a false positive, we retry, this is harmless.
+	 *
+	 * If we get a false negative, things are complicated. If we are after
+	 * perf_event_context_sched_in() ctx::lock will serialize us, and the
+	 * value must be correct. If we're before, it doesn't matter since
+	 * perf_event_context_sched_in() will program the counter.
+	 *
+	 * However, this hinges on the remote context switch having observed
+	 * our task->perf_event_ctxp[] store, such that it will in fact take
+	 * ctx::lock in perf_event_context_sched_in().
+	 *
+	 * We do this by task_function_call(), if the IPI fails to hit the task
+	 * we know any future context switch of task must see the
+	 * perf_event_ctpx[] store.
 	 */
-again:
+
 	/*
-	 * Cannot use task_function_call() because we need to run on the task's
-	 * CPU regardless of whether its current or not.
+	 * This smp_mb() orders the task->perf_event_ctxp[] store with the
+	 * task_cpu() load, such that if the IPI then does not find the task
+	 * running, a future context switch of that task must observe the
+	 * store.
 	 */
-	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+	smp_mb();
+again:
+	if (!task_function_call(task, __perf_install_in_context, event))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -2348,12 +2370,16 @@ perf_install_in_context(struct perf_event_context *ctx,
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Since !ctx->is_active doesn't mean anything, we must IPI
-	 * unconditionally.
+	 * If the task is not running, ctx->lock will avoid it becoming so,
+	 * thus we can safely install the event.
 	 */
-	goto again;
+	if (task_curr(task)) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	add_event_to_ctx(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
@@ -7034,25 +7060,12 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
-/*
- * Generic event overflow handling, sampling.
- */
-
-static int __perf_event_overflow(struct perf_event *event,
-				   int throttle, struct perf_sample_data *data,
-				   struct pt_regs *regs)
+static int
+__perf_event_account_interrupt(struct perf_event *event, int throttle)
 {
-	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
-	u64 seq;
 	int ret = 0;
-
-	/*
-	 * Non-sampling counters might still use the PMI to fold short
-	 * hardware counters, ignore those.
-	 */
-	if (unlikely(!is_sampling_event(event)))
-		return 0;
+	u64 seq;
 
 	seq = __this_cpu_read(perf_throttled_seq);
 	if (seq != hwc->interrupts_seq) {
@@ -7080,6 +7093,34 @@ static int __perf_event_overflow(struct perf_event *event,
 			perf_adjust_period(event, delta, hwc->last_period, true);
 	}
 
+	return ret;
+}
+
+int perf_event_account_interrupt(struct perf_event *event)
+{
+	return __perf_event_account_interrupt(event, 1);
+}
+
+/*
+ * Generic event overflow handling, sampling.
+ */
+
+static int __perf_event_overflow(struct perf_event *event,
+				   int throttle, struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	int events = atomic_read(&event->event_limit);
+	int ret = 0;
+
+	/*
+	 * Non-sampling counters might still use the PMI to fold short
+	 * hardware counters, ignore those.
+	 */
+	if (unlikely(!is_sampling_event(event)))
+		return 0;
+
+	ret = __perf_event_account_interrupt(event, throttle);
+
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
@@ -9503,6 +9544,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -9746,12 +9818,31 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
 		if (gctx->task == TASK_TOMBSTONE) {
 			err = -ESRCH;
 			goto err_locked;
 		}
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -9853,7 +9944,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
@@ -9879,7 +9970,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);

samples/bpf/sock_example.h

@@ -4,7 +4,7 @@
 #include <unistd.h>
 #include <string.h>
 #include <errno.h>
-#include <net/ethernet.h>
+#include <linux/if_ether.h>
 #include <net/if.h>
 #include <linux/if_packet.h>
 #include <arpa/inet.h>

samples/bpf/trace_output_user.c

@@ -9,7 +9,6 @@
 #include <string.h>
 #include <fcntl.h>
 #include <poll.h>
-#include <sys/ioctl.h>
 #include <linux/perf_event.h>
 #include <linux/bpf.h>
 #include <errno.h>

tools/lib/subcmd/parse-options.c

@@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 		else
 			err = get_arg(p, opt, flags, (const char **)opt->value);
 
+		if (opt->set)
+			*(bool *)opt->set = true;
+
 		/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
 		if (opt->flags & PARSE_OPT_NOEMPTY) {
 			const char *val = *(const char **)opt->value;

tools/lib/subcmd/parse-options.h

@@ -137,6 +137,11 @@ struct option {
 	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
 	  .value = check_vtype(v, const char **), (a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+	{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+	  .set = check_vtype(os, bool *)}
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }