perf/core improvements

index a59281d64368..e7a4b31a84fb 100644
@@ -1795,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
 
 	return true;
 }
+
+/*
+ * Events in data file are not collect in groups, but we still want
+ * the group display. Set the artificial group and set the leader's
+ * forced_leader flag to notify the display code.
+ */
+void perf_evlist__force_leader(struct perf_evlist *evlist)
+{
+	if (!evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(evlist);
+
+		perf_evlist__set_leader(evlist);
+		leader->forced_leader = true;
+	}
+}

index 6c41b2f78713..dc66436add98 100644
@@ -309,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
 
 bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
+
+void perf_evlist__force_leader(struct perf_evlist *evlist);
+
 #endif /* __PERF_EVLIST_H */

index 4c931afb2e80..ad978e3ee2b8 100644
@@ -194,20 +194,11 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 	return err;
 }
 
-/*
- * Events in data file are not collect in groups, but we still want
- * the group display. Set the artificial group and set the leader's
- * forced_leader flag to notify the display code.
- */
 static void setup_forced_leader(struct report *report,
 				struct perf_evlist *evlist)
 {
-	if (report->group_set && !evlist->nr_groups) {
-		struct perf_evsel *leader = perf_evlist__first(evlist);
-
-		perf_evlist__set_leader(evlist);
-		leader->forced_leader = true;
-	}
+	if (report->group_set)
+		perf_evlist__force_leader(evlist);
 }
 
 static int process_feature_event(struct perf_tool *tool,

index 6e5d9f718154..da5704240239 100644
@@ -45,6 +45,7 @@ struct perf_annotate {
 	bool	   print_line;
 	bool	   skip_missing;
 	bool	   has_br_stack;
+	bool	   group_set;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);

@@ -508,6 +509,9 @@ int cmd_annotate(int argc, const char **argv)
 		    "Don't shorten the displayed pathnames"),
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
+	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group,
+			&annotate.group_set,
+			"Show event group information together"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
 	OPT_CALLBACK(0, "symfs", NULL, "directory",
 		     "Look for files with symbols relative to this directory",

@@ -570,6 +574,9 @@ int cmd_annotate(int argc, const char **argv)
 	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
 						      HEADER_BRANCH_STACK);
 
+	if (annotate.group_set)
+		perf_evlist__force_leader(annotate.session->evlist);
+
 	ret = symbol__annotation_init();
 	if (ret < 0)
 		goto out_delete;

index 319fb0a0d05e..59f38c7693f8 100644
@@ -106,11 +106,24 @@ static int perf_env__read_arch(struct perf_env *env)
 	return env->arch ? 0 : -ENOMEM;
 }
 
+static int perf_env__read_nr_cpus_avail(struct perf_env *env)
+{
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = cpu__max_present_cpu();
+
+	return env->nr_cpus_avail ? 0 : -ENOENT;
+}
+
 const char *perf_env__raw_arch(struct perf_env *env)
 {
 	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
 }
 
+int perf_env__nr_cpus_avail(struct perf_env *env)
+{
+	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);

index 62e193948608..1f3ccc368530 100644
@@ -77,5 +77,6 @@ void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
 
 #endif /* __PERF_ENV_H */

index e011a7160380..f62ecd9c36e8 100644
@@ -2305,6 +2305,11 @@ bool machine__is(struct machine *machine, const char *arch)
 	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
 }
 
+int machine__nr_cpus_avail(struct machine *machine)
+{
+	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);

index b31d33b5aa2a..2d2b092ba753 100644
@@ -189,6 +189,7 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 bool machine__is(struct machine *machine, const char *arch);
+int machine__nr_cpus_avail(struct machine *machine);
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);

index f62ecd9c36e8..db695603873b 100644
@@ -851,6 +851,102 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+	u64 start;
+	u64 end;
+	u64 pgoff;
+};
+
+static int machine__create_extra_kernel_map(struct machine *machine,
+					    struct dso *kernel,
+					    struct extra_kernel_map *xm)
+{
+	struct kmap *kmap;
+	struct map *map;
+
+	map = map__new2(xm->start, kernel);
+	if (!map)
+		return -1;
+
+	map->end   = xm->end;
+	map->pgoff = xm->pgoff;
+
+	kmap = map__kmap(map);
+
+	kmap->kmaps = &machine->kmaps;
+
+	map_groups__insert(&machine->kmaps, map);
+
+	pr_debug2("Added extra kernel map %" PRIx64 "-%" PRIx64 "\n",
+		  map->start, map->end);
+
+	map__put(map);
+
+	return 0;
+}
+
+static u64 find_entry_trampoline(struct dso *dso)
+{
+	/* Duplicates are removed so lookup all aliases */
+	const char *syms[] = {
+		"_entry_trampoline",
+		"__entry_trampoline_start",
+		"entry_SYSCALL_64_trampoline",
+	};
+	struct symbol *sym = dso__first_symbol(dso);
+	unsigned int i;
+
+	for (; sym; sym = dso__next_symbol(sym)) {
+		if (sym->binding != STB_GLOBAL)
+			continue;
+		for (i = 0; i < ARRAY_SIZE(syms); i++) {
+			if (!strcmp(sym->name, syms[i]))
+				return sym->start;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * These values can be used for kernels that do not have symbols for the entry
+ * trampolines in kallsyms.
+ */
+#define X86_64_CPU_ENTRY_AREA_PER_CPU	0xfffffe0000000000ULL
+#define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
+#define X86_64_ENTRY_TRAMPOLINE		0x6000
+
+/* Map x86_64 PTI entry trampolines */
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel)
+{
+	u64 pgoff = find_entry_trampoline(kernel);
+	int nr_cpus_avail, cpu;
+
+	if (!pgoff)
+		return 0;
+
+	nr_cpus_avail = machine__nr_cpus_avail(machine);
+
+	/* Add a 1 page map for each CPU's entry trampoline */
+	for (cpu = 0; cpu < nr_cpus_avail; cpu++) {
+		u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU +
+			 cpu * X86_64_CPU_ENTRY_AREA_SIZE +
+			 X86_64_ENTRY_TRAMPOLINE;
+		struct extra_kernel_map xm = {
+			.start = va,
+			.end   = va + page_size,
+			.pgoff = pgoff,
+		};
+
+		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+			return -1;
+	}
+
+	return 0;
+}
+
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {

index 2d2b092ba753..b6a1c3eb3d65 100644
@@ -268,4 +268,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel);
+
 #endif /* __PERF_MACHINE_H */

index 4a39f4d0a174..701144094183 100644
@@ -1490,20 +1490,22 @@ int dso__load(struct dso *dso, struct map *map)
 		goto out;
 	}
 
+	if (map->groups && map->groups->machine)
+		machine = map->groups->machine;
+	else
+		machine = NULL;
+
 	if (dso->kernel) {
 		if (dso->kernel == DSO_TYPE_KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
 		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 			ret = dso__load_guest_kernel_sym(dso, map);
 
+		if (machine__is(machine, "x86_64"))
+			machine__map_x86_64_entry_trampolines(machine, dso);
 		goto out;
 	}
 
-	if (map->groups && map->groups->machine)
-		machine = map->groups->machine;
-	else
-		machine = NULL;
-
 	dso->adjust_symbols = 0;
 
 	if (perfmap) {

index f1afe1ab6ff7..fafcc375ed37 100644
@@ -8,6 +8,7 @@
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <stdio.h>
+#include <string.h>
 #include <stdbool.h>
 #include <linux/types.h>
 #include "rwsem.h"

@@ -239,4 +240,11 @@ static inline bool __map__is_kmodule(const struct map *map)
 
 bool map__has_symbols(const struct map *map);
 
+#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
+
+static inline bool is_entry_trampoline(const char *name)
+{
+	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
+}
+
 #endif /* __PERF_MAP_H */

index 701144094183..929058da6727 100644
@@ -737,12 +737,15 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso,
 	struct rb_root *root = &dso->symbols;
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
+	bool x86_64;
 
 	if (!kmaps)
 		return -1;
 
 	machine = kmaps->machine;
 
+	x86_64 = machine__is(machine, "x86_64");
+
 	while (next) {
 		char *module;
 

@@ -790,6 +793,16 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso,
 			 */
 			pos->start = curr_map->map_ip(curr_map, pos->start);
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
+		} else if (x86_64 && is_entry_trampoline(pos->name)) {
+			/*
+			 * These symbols are not needed anymore since the
+			 * trampoline maps refer to the text section and it's
+			 * symbols instead. Avoid having to deal with
+			 * relocations, and the assumption that the first symbol
+			 * is the start of kernel text, by simply removing the
+			 * symbols at this point.
+			 */
+			goto discard_symbol;
 		} else if (curr_map != initial_map) {
 			char dso_name[PATH_MAX];
 			struct dso *ndso;

index 244135b5ea43..aafa9878465f 100644
@@ -487,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
 
-		if (__map__is_kernel(pos))
+		if (!__map__is_kmodule(pos))
 			continue;
 
 		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));

index db695603873b..355d23bcd443 100644
@@ -856,6 +856,7 @@ struct extra_kernel_map {
 	u64 start;
 	u64 end;
 	u64 pgoff;
+	char name[KMAP_NAME_LEN];
 };
 
 static int machine__create_extra_kernel_map(struct machine *machine,

@@ -875,11 +876,12 @@ static int machine__create_extra_kernel_map(struct machine *machine,
 	kmap = map__kmap(map);
 
 	kmap->kmaps = &machine->kmaps;
+	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
 	map_groups__insert(&machine->kmaps, map);
 
-	pr_debug2("Added extra kernel map %" PRIx64 "-%" PRIx64 "\n",
-		  map->start, map->end);
+	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
+		  kmap->name, map->start, map->end);
 
 	map__put(map);
 

@@ -940,6 +942,8 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine,
 			.pgoff = pgoff,
 		};
 
+		strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN);
+
 		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
 			return -1;
 	}

index c8fe836e4c3c..6ae97eda370b 100644
@@ -252,6 +252,13 @@ bool __map__is_kernel(const struct map *map)
 	return machine__kernel_map(map->groups->machine) == map;
 }
 
+bool __map__is_extra_kernel_map(const struct map *map)
+{
+	struct kmap *kmap = __map__kmap((struct map *)map);
+
+	return kmap && kmap->name[0];
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);

@@ -846,15 +853,22 @@ struct map *map__next(struct map *map)
 	return NULL;
 }
 
-struct kmap *map__kmap(struct map *map)
+struct kmap *__map__kmap(struct map *map)
 {
-	if (!map->dso || !map->dso->kernel) {
-		pr_err("Internal error: map__kmap with a non-kernel map\n");
+	if (!map->dso || !map->dso->kernel)
 		return NULL;
-	}
 	return (struct kmap *)(map + 1);
 }
 
+struct kmap *map__kmap(struct map *map)
+{
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap)
+		pr_err("Internal error: map__kmap with a non-kernel map\n");
+	return kmap;
+}
+
 struct map_groups *map__kmaps(struct map *map)
 {
 	struct kmap *kmap = map__kmap(map);

index fafcc375ed37..97e2a063bd65 100644
@@ -47,9 +47,12 @@ struct map {
 	refcount_t		refcnt;
 };
 
+#define KMAP_NAME_LEN 256
+
 struct kmap {
 	struct ref_reloc_sym	*ref_reloc_sym;
 	struct map_groups	*kmaps;
+	char			name[KMAP_NAME_LEN];
 };
 
 struct maps {

@@ -76,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg);
 
+struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct map_groups *map__kmaps(struct map *map);
 

@@ -232,10 +236,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
 
 bool __map__is_kernel(const struct map *map);
+bool __map__is_extra_kernel_map(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
 }
 
 bool map__has_symbols(const struct map *map);

index 929058da6727..cdddae67f40c 100644
@@ -1030,7 +1030,7 @@ struct map *map_groups__first(struct map_groups *mg)
 	return maps__first(&mg->maps);
 }
 
-static int do_validate_kcore_modules(const char *filename, struct map *map,
+static int do_validate_kcore_modules(const char *filename,
 				  struct map_groups *kmaps)
 {
 	struct rb_root modules = RB_ROOT;

@@ -1046,8 +1046,7 @@ static int do_validate_kcore_modules(const char *filename, struct map *map,
 		struct map *next = map_groups__next(old_map);
 		struct module_info *mi;
 
-		if (old_map == map || old_map->start == map->start) {
-			/* The kernel map */
+		if (!__map__is_kmodule(old_map)) {
 			old_map = next;
 			continue;
 		}

@@ -1104,7 +1103,7 @@ static int validate_kcore_modules(const char *kallsyms_filename,
 					     kallsyms_filename))
 		return -EINVAL;
 
-	if (do_validate_kcore_modules(modules_filename, map, kmaps))
+	if (do_validate_kcore_modules(modules_filename, kmaps))
 		return -EINVAL;
 
 	return 0;

103 lines not on this page · raw message

115 lines not on this page · raw message

index b6a1c3eb3d65..1de7660d93e9 100644
@@ -56,6 +56,7 @@ struct machine {
 		void	  *priv;
 		u64	  db_id;
 	};
+	bool		  trampolines_mapped;
 };
 
 static inline struct threads *machine__threads(struct machine *machine, pid_t tid)

@@ -268,6 +269,24 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz);
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel);
+
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+	u64 start;
+	u64 end;
+	u64 pgoff;
+	char name[KMAP_NAME_LEN];
+};
+
+int machine__create_extra_kernel_map(struct machine *machine,
+				     struct dso *kernel,
+				     struct extra_kernel_map *xm);
+
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel);
 

index cdddae67f40c..8c84437f2a10 100644
@@ -1158,6 +1158,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	struct map_groups *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
 	struct map *old_map, *new_map, *replacement_map = NULL;
+	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
 	char kcore_filename[PATH_MAX];

@@ -1166,6 +1167,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	if (!kmaps)
 		return -EINVAL;
 
+	machine = kmaps->machine;
+
 	/* This function requires that the map is the kernel map */
 	if (!__map__is_kernel(map))
 		return -EINVAL;

@@ -1209,6 +1212,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			map_groups__remove(kmaps, old_map);
 		old_map = next;
 	}
+	machine->trampolines_mapped = false;
 
 	/* Find the kernel map using the '_stext' symbol */
 	if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) {

@@ -1245,6 +1249,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		map__put(new_map);
 	}
 
+	if (machine__is(machine, "x86_64")) {
+		u64 addr;
+
+		/*
+		 * If one of the corresponding symbols is there, assume the
+		 * entry trampoline maps are too.
+		 */
+		if (!kallsyms__get_function_start(kallsyms_filename,
+						  ENTRY_TRAMPOLINE_NAME,
+						  &addr))
+			machine->trampolines_mapped = true;
+	}
+
 	/*
 	 * Set the data type and long name so that kcore can be read via
 	 * dso__data_read_addr().

76 lines not on this page · raw message

index aafa9878465f..0c8ecf0c78a4 100644
@@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id)
 	return perf_ns__names[id];
 }
 
-static int perf_tool__process_synth_event(struct perf_tool *tool,
-					  union perf_event *event,
-					  struct machine *machine,
-					  perf_event__handler_t process)
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process)
 {
 	struct perf_sample synth_sample = {
 	.pid	   = -1,

@@ -888,9 +888,16 @@ int kallsyms__get_function_start(const char *kallsyms_filename,
 	return 0;
 }
 
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+					      perf_event__handler_t process __maybe_unused,
+					      struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+						perf_event__handler_t process,
+						struct machine *machine)
 {
 	size_t size;
 	struct map *map = machine__kernel_map(machine);

@@ -943,6 +950,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int err;
+
+	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+	if (err < 0)
+		return err;
+
+	return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
 int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,

index 0f794744919c..bfa60bcafbde 100644
@@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,

@@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       bool mmap_data,
 				       unsigned int proc_map_timeout);
 
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);

index dd7ab0731167..e7b4a8b513f2 100644
@@ -1387,6 +1387,32 @@ static bool machine__uses_kcore(struct machine *machine)
 	return false;
 }
 
+static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
+					     union perf_event *event)
+{
+	return machine__is(machine, "x86_64") &&
+	       is_entry_trampoline(event->mmap.filename);
+}
+
+static int machine__process_extra_kernel_map(struct machine *machine,
+					     union perf_event *event)
+{
+	struct map *kernel_map = machine__kernel_map(machine);
+	struct dso *kernel = kernel_map ? kernel_map->dso : NULL;
+	struct extra_kernel_map xm = {
+		.start = event->mmap.start,
+		.end   = event->mmap.start + event->mmap.len,
+		.pgoff = event->mmap.pgoff,
+	};
+
+	if (kernel == NULL)
+		return -1;
+
+	strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+
+	return machine__create_extra_kernel_map(machine, kernel, &xm);
+}
+
 static int machine__process_kernel_mmap_event(struct machine *machine,
 					      union perf_event *event)
 {

@@ -1490,6 +1516,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			 */
 			dso__load(kernel, machine__kernel_map(machine));
 		}
+	} else if (perf_event__is_extra_kernel_mmap(machine, event)) {
+		return machine__process_extra_kernel_map(machine, event);
 	}
 	return 0;
 out_problem:

index 6612c7f90af4..71897689dacf 100644
@@ -1965,6 +1965,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	u64 len;
 	int width = symbol_conf.show_total_period ? 12 : 8;
 	int graph_dotted_len;
+	char buf[512];
 
 	filename = strdup(dso->long_name);
 	if (!filename)

@@ -1977,8 +1978,11 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 	len = symbol__size(sym);
 
-	if (perf_evsel__is_group_event(evsel))
+	if (perf_evsel__is_group_event(evsel)) {
 		width *= evsel->nr_members;
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		evsel_name = buf;
+	}
 
 	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
 				  width, width, symbol_conf.show_total_period ? "Period" :

index 48943b834f11..b13873a6f368 100644
@@ -1388,6 +1388,7 @@ struct phdr_data {
 	off_t offset;
 	u64 addr;
 	u64 len;
+	struct list_head node;
 };
 
 struct kcore_copy_info {

@@ -1399,6 +1400,7 @@ struct kcore_copy_info {
 	u64 last_module_symbol;
 	struct phdr_data kernel_map;
 	struct phdr_data modules_map;
+	struct list_head phdrs;
 };
 
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,

@@ -1510,6 +1512,11 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
 		return -1;
 
+	if (kci->kernel_map.len)
+		list_add_tail(&kci->kernel_map.node, &kci->phdrs);
+	if (kci->modules_map.len)
+		list_add_tail(&kci->modules_map.node, &kci->phdrs);
+
 	return 0;
 }
 

@@ -1678,6 +1685,8 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	char kcore_filename[PATH_MAX];
 	char extract_filename[PATH_MAX];
 
+	INIT_LIST_HEAD(&kci.phdrs);
+
 	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
 		return -1;
 

index b13873a6f368..4e7b71e8ac0e 100644
@@ -1398,6 +1398,7 @@ struct kcore_copy_info {
 	u64 last_symbol;
 	u64 first_module;
 	u64 last_module_symbol;
+	size_t phnum;
 	struct phdr_data kernel_map;
 	struct phdr_data modules_map;
 	struct list_head phdrs;

@@ -1517,6 +1518,8 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	if (kci->modules_map.len)
 		list_add_tail(&kci->modules_map.node, &kci->phdrs);
 
+	kci->phnum = !!kci->kernel_map.len + !!kci->modules_map.len;
+
 	return 0;
 }
 

@@ -1678,7 +1681,6 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 {
 	struct kcore kcore;
 	struct kcore extract;
-	size_t count = 2;
 	int idx = 0, err = -1;
 	off_t offset = page_size, sz, modules_offset = 0;
 	struct kcore_copy_info kci = { .stext = 0, };

@@ -1705,10 +1707,7 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
 		goto out_kcore_close;
 
-	if (!kci.modules_map.addr)
-		count -= 1;
-
-	if (kcore__copy_hdr(&kcore, &extract, count))
+	if (kcore__copy_hdr(&kcore, &extract, kci.phnum))
 		goto out_extract_close;
 
 	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,

index 4e7b71e8ac0e..4aec12102e19 100644
@@ -1682,7 +1682,7 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	struct kcore kcore;
 	struct kcore extract;
 	int idx = 0, err = -1;
-	off_t offset = page_size, sz, modules_offset = 0;
+	off_t offset, sz, modules_offset = 0;
 	struct kcore_copy_info kci = { .stext = 0, };
 	char kcore_filename[PATH_MAX];
 	char extract_filename[PATH_MAX];

@@ -1710,6 +1710,10 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (kcore__copy_hdr(&kcore, &extract, kci.phnum))
 		goto out_extract_close;
 
+	offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) +
+		 gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT);
+	offset = round_up(offset, page_size);
+
 	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
 			    kci.kernel_map.len))
 		goto out_extract_close;

index 4aec12102e19..3e76a0efd15c 100644
@@ -1386,6 +1386,7 @@ static off_t kcore__write(struct kcore *kcore)
 
 struct phdr_data {
 	off_t offset;
+	off_t rel;
 	u64 addr;
 	u64 len;
 	struct list_head node;

@@ -1404,6 +1405,9 @@ struct kcore_copy_info {
 	struct list_head phdrs;
 };
 
+#define kcore_copy__for_each_phdr(k, p) \
+	list_for_each_entry((p), &(k)->phdrs, node)
+
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 					u64 start)
 {

@@ -1518,11 +1522,21 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	if (kci->modules_map.len)
 		list_add_tail(&kci->modules_map.node, &kci->phdrs);
 
-	kci->phnum = !!kci->kernel_map.len + !!kci->modules_map.len;
-
 	return 0;
 }
 
+static void kcore_copy__layout(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p;
+	off_t rel = 0;
+
+	kcore_copy__for_each_phdr(kci, p) {
+		p->rel = rel;
+		rel += p->len;
+		kci->phnum += 1;
+	}
+}
+
 static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 				 Elf *elf)
 {

@@ -1558,7 +1572,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 	if (kci->first_module && !kci->last_module_symbol)
 		return -1;
 
-	return kcore_copy__read_maps(kci, elf);
+	if (kcore_copy__read_maps(kci, elf))
+		return -1;
+
+	kcore_copy__layout(kci);
+
+	return 0;
 }
 
 static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,

index 3e76a0efd15c..91b8cfb045ec 100644
@@ -1701,10 +1701,11 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	struct kcore kcore;
 	struct kcore extract;
 	int idx = 0, err = -1;
-	off_t offset, sz, modules_offset = 0;
+	off_t offset, sz;
 	struct kcore_copy_info kci = { .stext = 0, };
 	char kcore_filename[PATH_MAX];
 	char extract_filename[PATH_MAX];
+	struct phdr_data *p;
 
 	INIT_LIST_HEAD(&kci.phdrs);
 

@@ -1733,14 +1734,10 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 		 gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT);
 	offset = round_up(offset, page_size);
 
-	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
-			    kci.kernel_map.len))
-		goto out_extract_close;
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
 
-	if (kci.modules_map.addr) {
-		modules_offset = offset + kci.kernel_map.len;
-		if (kcore__add_phdr(&extract, idx, modules_offset,
-				    kci.modules_map.addr, kci.modules_map.len))
+		if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len))
 			goto out_extract_close;
 	}
 

@@ -1748,14 +1745,12 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (sz < 0 || sz > offset)
 		goto out_extract_close;
 
-	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
-		       kci.kernel_map.len))
-		goto out_extract_close;
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
 
-	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
-					 extract.fd, modules_offset,
-					 kci.modules_map.len))
-		goto out_extract_close;
+		if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len))
+			goto out_extract_close;
+	}
 
 	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
 		goto out_extract_close;

index 91b8cfb045ec..37d9324c277c 100644
@@ -1400,14 +1400,47 @@ struct kcore_copy_info {
 	u64 first_module;
 	u64 last_module_symbol;
 	size_t phnum;
-	struct phdr_data kernel_map;
-	struct phdr_data modules_map;
 	struct list_head phdrs;
 };
 
 #define kcore_copy__for_each_phdr(k, p) \
 	list_for_each_entry((p), &(k)->phdrs, node)
 
+static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset)
+{
+	struct phdr_data *p = zalloc(sizeof(*p));
+
+	if (p) {
+		p->addr   = addr;
+		p->len    = len;
+		p->offset = offset;
+	}
+
+	return p;
+}
+
+static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci,
+						 u64 addr, u64 len,
+						 off_t offset)
+{
+	struct phdr_data *p = phdr_data__new(addr, len, offset);
+
+	if (p)
+		list_add_tail(&p->node, &kci->phdrs);
+
+	return p;
+}
+
+static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *tmp;
+
+	list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
+		list_del(&p->node);
+		free(p);
+	}
+}
+
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 					u64 start)
 {

@@ -1487,15 +1520,18 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
 	return 0;
 }
 
-static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
-			    u64 s, u64 e)
+static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end,
+			   u64 pgoff, u64 s, u64 e)
 {
-	if (p->addr || s < start || s >= end)
-		return;
+	u64 len, offset;
+
+	if (s < start || s >= end)
+		return 0;
 
-	p->addr = s;
-	p->offset = (s - start) + pgoff;
-	p->len = e < end ? e - s : end - s;
+	offset = (s - start) + pgoff;
+	len = e < end ? e - s : end - s;
+
+	return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1;
 }
 
 static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)

@@ -1503,11 +1539,12 @@ static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
 	struct kcore_copy_info *kci = data;
 	u64 end = start + len;
 
-	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
-			kci->etext);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext))
+		return -1;
 
-	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
-			kci->last_module_symbol);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->first_module,
+			    kci->last_module_symbol))
+		return -1;
 
 	return 0;
 }

@@ -1517,11 +1554,6 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
 		return -1;
 
-	if (kci->kernel_map.len)
-		list_add_tail(&kci->kernel_map.node, &kci->phdrs);
-	if (kci->modules_map.len)
-		list_add_tail(&kci->modules_map.node, &kci->phdrs);
-
 	return 0;
 }
 

@@ -1773,6 +1805,8 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (err)
 		kcore_copy__unlink(to_dir, "kallsyms");
 
+	kcore_copy__free_phdrs(&kci);
+
 	return err;
 }
 

index 37d9324c277c..584966913aeb 100644
@@ -1392,6 +1392,11 @@ struct phdr_data {
 	struct list_head node;
 };
 
+struct sym_data {
+	u64 addr;
+	struct list_head node;
+};
+
 struct kcore_copy_info {
 	u64 stext;
 	u64 etext;

@@ -1401,6 +1406,7 @@ struct kcore_copy_info {
 	u64 last_module_symbol;
 	size_t phnum;
 	struct list_head phdrs;
+	struct list_head syms;
 };
 
 #define kcore_copy__for_each_phdr(k, p) \

@@ -1441,6 +1447,29 @@ static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
 	}
 }
 
+static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci,
+					    u64 addr)
+{
+	struct sym_data *s = zalloc(sizeof(*s));
+
+	if (s) {
+		s->addr = addr;
+		list_add_tail(&s->node, &kci->syms);
+	}
+
+	return s;
+}
+
+static void kcore_copy__free_syms(struct kcore_copy_info *kci)
+{
+	struct sym_data *s, *tmp;
+
+	list_for_each_entry_safe(s, tmp, &kci->syms, node) {
+		list_del(&s->node);
+		free(s);
+	}
+}
+
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 					u64 start)
 {

@@ -1471,6 +1500,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 	}
 
+	if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start))
+		return -1;
+
 	return 0;
 }
 

@@ -1538,6 +1570,7 @@ static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
 {
 	struct kcore_copy_info *kci = data;
 	u64 end = start + len;
+	struct sym_data *sdat;
 
 	if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext))
 		return -1;

@@ -1546,6 +1579,13 @@ static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
 			    kci->last_module_symbol))
 		return -1;
 
+	list_for_each_entry(sdat, &kci->syms, node) {
+		u64 s = round_down(sdat->addr, page_size);
+
+		if (kcore_copy__map(kci, start, end, pgoff, s, s + len))
+			return -1;
+	}
+
 	return 0;
 }
 

@@ -1740,6 +1780,7 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	struct phdr_data *p;
 
 	INIT_LIST_HEAD(&kci.phdrs);
+	INIT_LIST_HEAD(&kci.syms);
 
 	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
 		return -1;

@@ -1806,6 +1847,7 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 		kcore_copy__unlink(to_dir, "kallsyms");
 
 	kcore_copy__free_phdrs(&kci);
+	kcore_copy__free_syms(&kci);
 
 	return err;
 }

index 584966913aeb..29770ea61768 100644
@@ -1390,6 +1390,7 @@ struct phdr_data {
 	u64 addr;
 	u64 len;
 	struct list_head node;
+	struct phdr_data *remaps;
 };
 
 struct sym_data {

@@ -1597,16 +1598,62 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	return 0;
 }
 
+static void kcore_copy__find_remaps(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *k = NULL;
+	u64 kend;
+
+	if (!kci->stext)
+		return;
+
+	/* Find phdr that corresponds to the kernel map (contains stext) */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->addr + p->len - 1;
+
+		if (p->addr <= kci->stext && pend >= kci->stext) {
+			k = p;
+			break;
+		}
+	}
+
+	if (!k)
+		return;
+
+	kend = k->offset + k->len;
+
+	/* Find phdrs that remap the kernel */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->offset + p->len;
+
+		if (p == k)
+			continue;
+
+		if (p->offset >= k->offset && pend <= kend)
+			p->remaps = k;
+	}
+}
+
 static void kcore_copy__layout(struct kcore_copy_info *kci)
 {
 	struct phdr_data *p;
 	off_t rel = 0;
 
+	kcore_copy__find_remaps(kci);
+
 	kcore_copy__for_each_phdr(kci, p) {
-		p->rel = rel;
-		rel += p->len;
+		if (!p->remaps) {
+			p->rel = rel;
+			rel += p->len;
+		}
 		kci->phnum += 1;
 	}
+
+	kcore_copy__for_each_phdr(kci, p) {
+		struct phdr_data *k = p->remaps;
+
+		if (k)
+			p->rel = p->offset - k->offset + k->rel;
+	}
 }
 
 static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,

@@ -1821,6 +1868,8 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	kcore_copy__for_each_phdr(&kci, p) {
 		off_t offs = p->rel + offset;
 
+		if (p->remaps)
+			continue;
 		if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len))
 			goto out_extract_close;
 	}