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 event groups fix, two PMU driver
  fixes and a CPU model variant addition"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Tighten (and fix) the grouping condition
  perf/x86/intel: Add model number for Airmont
  perf/rapl: Fix crash in rapl_scale()
  perf/x86/intel/uncore: Move uncore_box_init() out of driver initialization
  perf probe: Fix probing kretprobes
  perf symbols: Introduce 'for' method to iterate over the symbols with a given name
  perf probe: Do not rely on map__load() filter to find symbols
  perf symbols: Introduce method to iterate symbols ordered by name
  perf symbols: Return the first entry with a given name in find_by_name method
  perf annotate: Fix memory leaks in LOCK handling
  perf annotate: Handle ins parsing failures
  perf scripting perl: Force to use stdbool
  perf evlist: Remove extraneous 'was' on error message

13 files changed, 107 insertions, 51 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf01..498b6d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 6e434f8..c4bb8b8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -142,7 +142,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 10b8d3e..c635b8b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
-	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0) {
-				uncore_box_init(box);
+			if (box && box->phys_id >= 0)
 				continue;
-			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box) {
+			if (box)
 				box->phys_id = phys_id;
-				uncore_box_init(box);
-			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 863d9b0..6c8c1e7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
+	uncore_box_init(box);
+
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61c..664de5a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -450,11 +450,6 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-	task_context,
-	cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -462,7 +457,6 @@ enum perf_event_context_type {
  */
 struct perf_event_context {
 	struct pmu			*pmu;
-	enum perf_event_context_type	type;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835..19efcf1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@ skip_type:
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7420,7 +7419,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 790ceba..28431d1 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -5,7 +5,10 @@
  *	ANY CHANGES MADE HERE WILL BE LOST! 
  *
  */
-
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
 #line 1 "Context.xs"
 /*
  * Context.xs.  XS interfaces for perf script.
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79999ce..01bc4e2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -177,14 +177,17 @@ static int lock__parse(struct ins_operands *ops)
 		goto out_free_ops;
 
 	ops->locked.ins = ins__find(name);
+	free(name);
+
 	if (ops->locked.ins == NULL)
 		goto out_free_ops;
 
 	if (!ops->locked.ins->ops)
 		return 0;
 
-	if (ops->locked.ins->ops->parse)
-		ops->locked.ins->ops->parse(ops->locked.ops);
+	if (ops->locked.ins->ops->parse &&
+	    ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+		goto out_free_ops;
 
 	return 0;
 
@@ -208,6 +211,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void lock__delete(struct ins_operands *ops)
 {
+	struct ins *ins = ops->locked.ins;
+
+	if (ins && ins->ops->free)
+		ins->ops->free(ops->locked.ops);
+	else
+		ins__delete(ops->locked.ops);
+
 	zfree(&ops->locked.ops);
 	zfree(&ops->target.raw);
 	zfree(&ops->target.name);
@@ -531,8 +541,8 @@ static void disasm_line__init_ins(struct disasm_line *dl)
 	if (!dl->ins->ops)
 		return;
 
-	if (dl->ins->ops->parse)
-		dl->ins->ops->parse(&dl->ops);
+	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+		dl->ins = NULL;
 }
 
 static int disasm_line__parse(char *line, char **namep, char **rawp)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cbab1fb..2e507b5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1445,7 +1445,7 @@ int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
 	case ENOENT:
 		scnprintf(buf, size, "%s",
 			  "Error:\tUnable to find debugfs\n"
-			  "Hint:\tWas your kernel was compiled with debugfs support?\n"
+			  "Hint:\tWas your kernel compiled with debugfs support?\n"
 			  "Hint:\tIs the debugfs filesystem mounted?\n"
 			  "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
 		break;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 6951a9d..0e42438 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -116,6 +116,22 @@ struct thread;
 #define map__for_each_symbol(map, pos, n)	\
 	dso__for_each_symbol(map->dso, pos, n, map->type)
 
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ *                                  that have the given name
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @filter: to use when loading the DSO
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
+	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
+	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos = symbol__next_by_name(pos))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos)		\
+	__map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 94a717b..919937e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address) {
+		if (tevs[i].point.address && !tevs[i].point.retprobe) {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
@@ -2193,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	return ret;
 }
 
-static char *looking_function_name;
-static int num_matched_functions;
-
-static int probe_function_filter(struct map *map __maybe_unused,
-				      struct symbol *sym)
+static int find_probe_functions(struct map *map, char *name)
 {
-	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
-	    strcmp(looking_function_name, sym->name) == 0) {
-		num_matched_functions++;
-		return 0;
+	int found = 0;
+	struct symbol *sym;
+
+	map__for_each_symbol_by_name(map, name, sym) {
+		if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
+			found++;
 	}
-	return 1;
+
+	return found;
 }
 
 #define strdup_or_goto(str, label)	\
@@ -2222,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	struct kmap *kmap = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
-	struct rb_node *nd;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
+	int num_matched_functions;
 	int ret, i;
 
 	/* Init maps of given executable or kernel */
@@ -2242,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = 0;
-	looking_function_name = pp->function;
-	ret = map__load(map, probe_function_filter);
-	if (ret || num_matched_functions == 0) {
+	num_matched_functions = find_probe_functions(map, pp->function);
+	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
 			target ? : "kernel");
 		ret = -ENOENT;
@@ -2257,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		goto out;
 	}
 
-	if (!pev->uprobes) {
+	if (!pev->uprobes && !pp->retprobe) {
 		kmap = map__kmap(map);
 		reloc_sym = kmap->ref_reloc_sym;
 		if (!reloc_sym) {
@@ -2275,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	map__for_each_symbol(map, sym, nd) {
+
+	map__for_each_symbol_by_name(map, pp->function, sym) {
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c24c5b8..a194702 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -396,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
+	struct symbol_name_rb_node *s;
 
 	if (symbols == NULL)
 		return NULL;
@@ -403,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 	n = symbols->rb_node;
 
 	while (n) {
-		struct symbol_name_rb_node *s;
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
@@ -414,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		else if (cmp > 0)
 			n = n->rb_right;
 		else
-			return &s->sym;
+			break;
 	}
 
-	return NULL;
+	if (n == NULL)
+		return NULL;
+
+	/* return first symbol that has same name (if any) */
+	for (n = rb_prev(n); n; n = rb_prev(n)) {
+		struct symbol_name_rb_node *tmp;
+
+		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
+		if (strcmp(tmp->sym.name, s->sym.name))
+			break;
+
+		s = tmp;
+	}
+
+	return &s->sym;
 }
 
 struct symbol *dso__find_symbol(struct dso *dso,
@@ -436,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym)
 	return symbols__next(sym);
 }
 
+struct symbol *symbol__next_by_name(struct symbol *sym)
+{
+	struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
+	struct rb_node *n = rb_next(&s->rb_node);
+
+	return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+}
+
+ /*
+  * Teturns first symbol that matched with @name.
+  */
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9d602e9..1650dcb 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -231,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
+struct symbol *symbol__next_by_name(struct symbol *sym);
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);