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

…linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Mostly tooling fixes, but also an uncore PMU driver fix and an uncore
  PMU driver hardware-enablement addition"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf probe: Fix segfault if passed with ''.
  perf report: Fix -T/--threads option to work again
  perf bench numa: Fix immediate meeting of convergence condition
  perf bench numa: Fixes of --quiet argument
  perf bench futex: Fix hung wakeup tasks after requeueing
  perf probe: Fix bug with global variables handling
  perf top: Fix a segfault when kernel map is restricted.
  tools lib traceevent: Fix build failure on 32-bit arch
  perf kmem: Fix compiles on RHEL6/OL6
  tools lib api: Undefine _FORTIFY_SOURCE before setting it
  perf kmem: Consistently use PRIu64 for printing u64 values
  perf trace: Disable events and drain events when forked workload ends
  perf trace: Enable events when doing system wide tracing and starting a workload
  perf/x86/intel/uncore: Move PCI IDs for IMC to uncore driver
  perf/x86/intel/uncore: Add support for Intel Haswell ULT (lower power Mobile Processor) IMC uncore PMUs
  perf/x86/intel: Add cpu_(prepare|starting|dying) for core_pmu

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2533,34 +2533,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2743,6 +2715,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,

arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c

@@ -1,6 +1,13 @@
 /* Nehalem/SandBridge/Haswell uncore support */
 #include "perf_event_intel_uncore.h"
 
+/* Uncore IMC PCI IDs */
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
 #define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
@@ -472,6 +479,10 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -502,6 +513,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	{  /* end marker */ }
 };
 

include/linux/pci_ids.h

@@ -2541,10 +2541,6 @@
 
 #define PCI_VENDOR_ID_INTEL		0x8086
 #define PCI_DEVICE_ID_INTEL_EESSC	0x0008
-#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
-#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
-#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
-#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0	0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1	0x0321
 #define PCI_DEVICE_ID_INTEL_PXH_0	0x0329

tools/lib/api/Makefile

@@ -16,7 +16,7 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 RM = rm -f

tools/lib/traceevent/event-parse.c

@@ -3865,7 +3865,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			} else if (el_size == 4) {
 				trace_seq_printf(s, "%u", *(uint32_t *)num);
 			} else if (el_size == 8) {
-				trace_seq_printf(s, "%lu", *(uint64_t *)num);
+				trace_seq_printf(s, "%"PRIu64, *(uint64_t *)num);
 			} else {
 				trace_seq_printf(s, "BAD SIZE:%d 0x%x",
 						 el_size, *(uint8_t *)num);

tools/perf/bench/futex-requeue.c

@@ -132,6 +132,9 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
+	if (nrequeue > nthreads)
+		nrequeue = nthreads;
+
 	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
 	       "%d at a time.\n\n",  getpid(), nthreads,
 	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
@@ -161,20 +164,18 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
+		while (nrequeued < nthreads) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0,
-					  nrequeue, futex_flag);
+			nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
+						       nrequeue, futex_flag);
 		}
+
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
-		if (nrequeued > nthreads)
-			nrequeued = nthreads;
-
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
+		nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 

tools/perf/bench/numa.c

@@ -180,7 +180,7 @@ static const struct option options[] = {
 	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
 	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
 	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
-	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"quiet mode"),
 	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
 
 	/* Special option string parsing callbacks: */
@@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
+		if (node < 0) /* curr_cpu was likely still -1 */
+			return 0;
+
 		node_present[node] = 1;
 	}
 
@@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong)
 	for (p = 0; p < g->p.nr_proc; p++) {
 		unsigned int nodes = count_process_nodes(p);
 
+		if (!nodes) {
+			*strong = 0;
+			return;
+		}
+
 		nodes_min = min(nodes, nodes_min);
 		nodes_max = max(nodes, nodes_max);
 	}
@@ -1395,7 +1403,7 @@ static void print_res(const char *name, double val,
 	if (!name)
 		name = "main,";
 
-	if (g->p.show_quiet)
+	if (!g->p.show_quiet)
 		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
 	else
 		printf(" %14.3f %s\n", val, txt_long);

tools/perf/builtin-kmem.c

@@ -319,7 +319,7 @@ static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
 	return 0;
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create)
+static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;
@@ -331,7 +331,7 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = page_stat_cmp(data, stat);
+		cmp = page_stat_cmp(data, pstat);
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -345,10 +345,10 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 
 	data = zalloc(sizeof(*data));
 	if (data != NULL) {
-		data->page = stat->page;
-		data->order = stat->order;
-		data->gfp_flags = stat->gfp_flags;
-		data->migrate_type = stat->migrate_type;
+		data->page = pstat->page;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
 
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &page_alloc_tree);
@@ -375,7 +375,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 		.gfp_flags = gfp_flags,
@@ -401,21 +401,21 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	stat = search_page(page, true);
-	if (stat == NULL)
+	pstat = search_page(page, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->order = order;
-	stat->gfp_flags = gfp_flags;
-	stat->migrate_type = migrate_type;
+	pstat->order = order;
+	pstat->gfp_flags = gfp_flags;
+	pstat->migrate_type = migrate_type;
 
 	this.page = page;
-	stat = search_page_alloc_stat(&this, true);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->nr_alloc++;
-	stat->alloc_bytes += bytes;
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
 
 	order_stats[order][migrate_type]++;
 
@@ -428,7 +428,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	u64 page;
 	unsigned int order = perf_evsel__intval(evsel, sample, "order");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 	};
@@ -441,8 +441,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	stat = search_page(page, false);
-	if (stat == NULL) {
+	pstat = search_page(page, false);
+	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);
 
@@ -453,18 +453,18 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	}
 
 	this.page = page;
-	this.gfp_flags = stat->gfp_flags;
-	this.migrate_type = stat->migrate_type;
+	this.gfp_flags = pstat->gfp_flags;
+	this.migrate_type = pstat->migrate_type;
 
-	rb_erase(&stat->node, &page_tree);
-	free(stat);
+	rb_erase(&pstat->node, &page_tree);
+	free(pstat);
 
-	stat = search_page_alloc_stat(&this, false);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, false);
+	if (pstat == NULL)
 		return -ENOENT;
 
-	stat->nr_free++;
-	stat->free_bytes += bytes;
+	pstat->nr_free++;
+	pstat->free_bytes += bytes;
 
 	return 0;
 }
@@ -640,9 +640,9 @@ static void print_page_summary(void)
 	       nr_page_frees, total_page_free_bytes / 1024);
 	printf("\n");
 
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
 	       nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
 	       nr_page_allocs - nr_alloc_freed,
 	       (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
 	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total free-only requests",

tools/perf/builtin-report.c

@@ -329,7 +329,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == default_sort_order &&
+	if (sort_order == NULL &&
 	    parent_pattern == default_parent_pattern) {
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 

tools/perf/builtin-top.c

@@ -733,7 +733,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
-			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);