BackMerge v5.1-rc5 into drm-next

Need rc5 for udl fix to add udl cleanups on top.

Signed-off-by: Dave Airlie <airlied@redhat.com>

7 files changed, 98 insertions, 68 deletions

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index ba4c623cd8de..39fe21e1cf93 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ec78e93085de..6689378ee577 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dcb68f34d2cd..6a94785b9100 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7835e05f0c0a..66d066f18b5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (!precise)
 		goto new_event;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ new_event:
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/*
+		 * Do quick precise_ip fallback if:
+		 *  - there is precise_ip set in perf_event_attr
+		 *  - maximum precise is requested
+		 *  - sys_perf_event_open failed with ENOTSUP error,
+		 *    which is associated with wrong precise_ip
+		 */
+		if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->attr.precise_ip) {
+			evsel->attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+		display_attr(&evsel->attr);
+	}
+
+	return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads)
 {
@@ -1824,12 +1878,7 @@ retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1890,10 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6e03db142091..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61959aba7e27..3c520baa198c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, addr, ~0ULL);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6199a3174ab9..e0429f4ef335 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
+
+			/*
+			 * uncore alias may be from different PMU
+			 * with common prefix
+			 */
+			if (pmu_is_uncore(name) &&
+			    !strncmp(pname, name, strlen(pname)))
+				goto new_alias;
+
 			if (strcmp(pname, name))
 				continue;
 		}
 
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,