perf fixes

index a6fd4dbcf820..5210eaa4aa62 100644
@@ -3708,7 +3708,7 @@ __init int intel_pmu_init(void)
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
 			c->idxmsk64 &=
-				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
 			c->weight = hweight64(c->idxmsk64);
 		}
 	}

index 09a77dbc73c9..7377814de30b 100644
@@ -709,6 +709,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
 	/* how many pages till the STOP marker */

@@ -733,6 +734,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
 
 	return 0;

index ab2bcaaebe38..b2625867ebd1 100644
@@ -219,6 +219,9 @@
 #define KNL_CHA_MSR_PMON_BOX_FILTER_TID		0x1ff
 #define KNL_CHA_MSR_PMON_BOX_FILTER_STATE	(7 << 18)
 #define KNL_CHA_MSR_PMON_BOX_FILTER_OP		(0xfffffe2aULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE	(0x1ULL << 32)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE	(0x1ULL << 33)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_NNC		(0x1ULL << 37)
 
 /* KNL EDC/MC UCLK */
 #define KNL_UCLK_MSR_PMON_CTR0_LOW		0x400

@@ -1902,6 +1905,10 @@ static int knl_cha_hw_config(struct intel_uncore_box *box,
 		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
 			    KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx;
 		reg1->config = event->attr.config1 & knl_cha_filter_mask(idx);
+
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE;
+		reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_NNC;
 		reg1->idx = idx;
 	}
 	return 0;

index ec863b9a9f78..8bef19f098d4 100644
@@ -166,7 +166,7 @@ static void msr_event_update(struct perf_event *event)
 	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
 		delta = sign_extend64(delta, 31);
 
-	local64_add(now - prev, &event->count);
+	local64_add(delta, &event->count);
 }
 
 static void msr_event_start(struct perf_event *event, int flags)

index c61f0cbd308b..7611d0f66cf8 100644
@@ -347,6 +347,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 			 bool truncated)
 {
 	struct ring_buffer *rb = handle->rb;
+	bool wakeup = truncated;
 	unsigned long aux_head;
 	u64 flags = 0;
 

@@ -375,9 +376,16 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
 
 	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
-		perf_output_wakeup(handle);
+		wakeup = true;
 		local_add(rb->aux_watermark, &rb->aux_wakeup);
 	}
+
+	if (wakeup) {
+		if (truncated)
+			handle->event->pending_disable = 1;
+		perf_output_wakeup(handle);
+	}
+
 	handle->event = NULL;
 
 	local_set(&rb->aux_nest, 0);

index e499a36c1e4a..a282e8cb84f3 100644
@@ -41,6 +41,10 @@
 # include "test-dwarf.c"
 #undef main
 
+#define main main_test_dwarf_getlocations
+# include "test-dwarf_getlocations.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main

@@ -143,6 +147,7 @@ int main(int argc, char *argv[])
 	main_test_libelf_mmap();
 	main_test_glibc();
 	main_test_dwarf();
+	main_test_dwarf_getlocations();
 	main_test_libelf_getphdrnum();
 	main_test_libunwind();
 	main_test_libaudit();

new file mode 100644
index 000000000000..70162699dd43
@@ -0,0 +1,12 @@
+#include <stdlib.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+	Dwarf_Addr base, start, end;
+	Dwarf_Attribute attr;
+	Dwarf_Op *op;
+        size_t nops;
+	ptrdiff_t offset = 0;
+        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}

index 0144b3d1bb77..88cccea3ca99 100644
@@ -1164,11 +1164,11 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		current_op = current_exp;
 
 	ret = collapse_tree(current_op, parg, error_str);
+	/* collapse_tree() may free current_op, and updates parg accordingly */
+	current_op = NULL;
 	if (ret < 0)
 		goto fail;
 
-	*parg = current_op;
-
 	free(token);
 	return 0;
 

index 9223c164e545..1f86ee8fb831 100644
@@ -63,6 +63,8 @@ struct pt_regs_offset {
 # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
 #endif
 
+/* TODO: switching by dwarf address size */
+#ifndef __x86_64__
 static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_NAME_32("%ax",	eax),
 	REG_OFFSET_NAME_32("%cx",	ecx),

@@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
+#define regoffset_table x86_32_regoffset_table
+#else
 static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_NAME_64("%ax",	rax),
 	REG_OFFSET_NAME_64("%dx",	rdx),

@@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
 #define regoffset_table x86_64_regoffset_table
-#else
-#define regoffset_table x86_32_regoffset_table
 #endif
 
 /* Minus 1 for the ending REG_OFFSET_END */

141 lines not on this page · raw message

index 1f19f2f999c8..307e8a1a003c 100644
@@ -528,6 +528,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		perf_evlist__set_leader(evsel_list);
 
 	evlist__for_each(evsel_list, counter) {
+try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37

@@ -544,7 +545,11 @@ static int __run_perf_stat(int argc, const char **argv)
 				if ((counter->leader != counter) ||
 				    !(counter->leader->nr_members > 1))
 					continue;
-			}
+			} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+                                if (verbose)
+                                        ui__warning("%s\n", msg);
+                                goto try_again;
+                        }
 
 			perf_evsel__open_strerror(counter, &target,
 						  errno, msg, sizeof(msg));

index 577e600c8eb1..aea189b41cc8 100644
@@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return 0;
 }
 
+#ifdef HAVE_DWARF_GETLOCATIONS
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE

@@ -1080,3 +1081,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 
 	return ret;
 }
+#else
+int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+		      Dwarf_Die *vr_die __maybe_unused,
+		      struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif

index dad55d04ffdd..edcf4ed4e99c 100644
@@ -433,7 +433,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	pid_t tgid, ppid;
 	int rc = 0;
 

@@ -462,11 +462,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		return 0;
 	}
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
+	while ((dirent = readdir(tasks)) != NULL) {
 		char *end;
 		pid_t _pid;
 
-		_pid = strtol(dirent.d_name, &end, 10);
+		_pid = strtol(dirent->d_name, &end, 10);
 		if (*end)
 			continue;
 

@@ -575,7 +575,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 

@@ -600,9 +600,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (proc == NULL)
 		goto out_free_fork;
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;

index 738ce226002b..645dc1828836 100644
@@ -2345,6 +2345,8 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
+	int paranoid;
+
 	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
 	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {

@@ -2364,6 +2366,22 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 
 		zfree(&evsel->name);
 		return true;
+	} else if (err == EACCES && !evsel->attr.exclude_kernel &&
+		   (paranoid = perf_event_paranoid()) > 1) {
+		const char *name = perf_evsel__name(evsel);
+		char *new_name;
+
+		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+			return false;
+
+		if (evsel->name)
+			free(evsel->name);
+		evsel->name = new_name;
+		scnprintf(msg, msgsize,
+"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
+		evsel->attr.exclude_kernel = 1;
+
+		return true;
 	}
 
 	return false;

@@ -2382,12 +2400,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
 		 "which controls use of the performance events system by\n"
 		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
-		 "The default value is 1:\n\n"
+		 "The current value is %d:\n\n"
 		 "  -1: Allow use of (almost) all events by all users\n"
 		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
 		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
 		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
-				 target->system_wide ? "system-wide " : "");
+				 target->system_wide ? "system-wide " : "",
+				 perf_event_paranoid());
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",
 				 perf_evsel__name(evsel));

145 lines not on this page · raw message

index 47966a1618c7..f5ba111cd9fb 100644
@@ -2445,6 +2445,9 @@ static char *prefix_if_not_in(const char *pre, char *str)
 
 static char *setup_overhead(char *keys)
 {
+	if (sort__mode == SORT_MODE__DIFF)
+		return keys;
+
 	keys = prefix_if_not_in("overhead", keys);
 
 	if (symbol_conf.cumulate_callchain)

index 08afc6909953..267112b4e3db 100644
@@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	DIR *proc;
 	int max_threads = 32, items, i;
 	char path[256];
-	struct dirent dirent, *next, **namelist = NULL;
+	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)

@@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	threads->nr = 0;
 	atomic_set(&threads->refcnt, 1);
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
 		struct stat st;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
 		if (stat(path, &st) != 0)
 			continue;