Merge tag 'perf-core-for-mingo-4.18-20180523' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements from Arnaldo Carvalho de Melo:

- Create extra kernel maps to help in decoding samples in x86 PTI entry
  trampolines (Adrian Hunter)

- Copy x86 PTI entry trampoline sections in the kcore copy used for
  annotation and intel_pt CPU traces decoding (Adrian Hunter)

- Support 'perf annotate --group' for non-explicit recorded event
  "groups", showing multiple columns, one for each event, just like
  when dealing with explicit event groups (those enclosed with {}) (Jin Yao)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 711 insertions, 75 deletions

diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index f95e6f46ef0d..844b8f335532 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -4,6 +4,8 @@ libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
 libperf-y += group.o
+libperf-y += machine.o
+libperf-y += event.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
new file mode 100644
index 000000000000..675a0213044d
--- /dev/null
+++ b/tools/perf/arch/x86/util/event.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include "../../util/machine.h"
+#include "../../util/tool.h"
+#include "../../util/map.h"
+#include "../../util/util.h"
+#include "../../util/debug.h"
+
+#if defined(__x86_64__)
+
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc = 0;
+	struct map *pos;
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	union perf_event *event = zalloc(sizeof(event->mmap) +
+					 machine->id_hdr_size);
+
+	if (!event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
+	}
+
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		struct kmap *kmap;
+		size_t size;
+
+		if (!__map__is_extra_kernel_map(pos))
+			continue;
+
+		kmap = map__kmap(pos);
+
+		size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		       PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		       machine->id_hdr_size;
+
+		memset(event, 0, size);
+
+		event->mmap.header.type = PERF_RECORD_MMAP;
+
+		/*
+		 * kernel uses 0 for user space maps, see kernel/perf_event.c
+		 * __perf_event_mmap
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_KERNEL;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+		event->mmap.header.size = size;
+
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pgoff = pos->pgoff;
+		event->mmap.pid   = machine->pid;
+
+		strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+		if (perf_tool__process_synth_event(tool, event, machine,
+						   process) != 0) {
+			rc = -1;
+			break;
+		}
+	}
+
+	free(event);
+	return rc;
+}
+
+#endif
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
new file mode 100644
index 000000000000..4520ac53caa9
--- /dev/null
+++ b/tools/perf/arch/x86/util/machine.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+#include "../../util/map.h"
+#include "../../util/symbol.h"
+#include "../../util/sane_ctype.h"
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+	int cnt;
+	int max_cnt;
+	struct extra_kernel_map *maps;
+	bool get_entry_trampolines;
+	u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+				u64 end, u64 pgoff, const char *name)
+{
+	if (mi->cnt >= mi->max_cnt) {
+		void *buf;
+		size_t sz;
+
+		mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+		sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+		buf = realloc(mi->maps, sz);
+		if (!buf)
+			return -1;
+		mi->maps = buf;
+	}
+
+	mi->maps[mi->cnt].start = start;
+	mi->maps[mi->cnt].end   = end;
+	mi->maps[mi->cnt].pgoff = pgoff;
+	strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+	mi->cnt += 1;
+
+	return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+				  u64 start)
+{
+	struct extra_kernel_map_info *mi = arg;
+
+	if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+	    !strcmp(name, "_entry_trampoline")) {
+		mi->entry_trampoline = start;
+		return 0;
+	}
+
+	if (is_entry_trampoline(name)) {
+		u64 end = start + page_size;
+
+		return add_extra_kernel_map(mi, start, end, 0, name);
+	}
+
+	return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel)
+{
+	struct extra_kernel_map_info mi = { .cnt = 0, };
+	char filename[PATH_MAX];
+	int ret;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+	if (ret)
+		goto out_free;
+
+	if (!mi.entry_trampoline)
+		goto out_free;
+
+	for (i = 0; i < mi.cnt; i++) {
+		struct extra_kernel_map *xm = &mi.maps[i];
+
+		xm->pgoff = mi.entry_trampoline;
+		ret = machine__create_extra_kernel_map(machine, kernel, xm);
+		if (ret)
+			goto out_free;
+	}
+
+	machine->trampolines_mapped = mi.cnt;
+out_free:
+	free(mi.maps);
+	return ret;
+}
+
+#endif
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6e5d9f718154..da5704240239 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -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;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4c931afb2e80..ad978e3ee2b8 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -194,20 +194,11 @@ out:
 	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,
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 6612c7f90af4..71897689dacf 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -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" :
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 319fb0a0d05e..59f38c7693f8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -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);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 62e193948608..1f3ccc368530 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -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 */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 244135b5ea43..0c8ecf0c78a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -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,
@@ -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));
@@ -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,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0f794744919c..bfa60bcafbde 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -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);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59281d64368..e7a4b31a84fb 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -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;
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6c41b2f78713..dc66436add98 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -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 */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e011a7160380..e7b4a8b513f2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -807,8 +807,8 @@ struct process_args {
 	u64 start;
 };
 
-static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
-					   size_t bufsz)
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz)
 {
 	if (machine__is_default_guest(machine))
 		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
@@ -851,6 +851,130 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
+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;
+	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
+
+	map_groups__insert(&machine->kmaps, map);
+
+	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
+		  kmap->name, 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)
+{
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	int nr_cpus_avail, cpu;
+	bool found = false;
+	struct map *map;
+	u64 pgoff;
+
+	/*
+	 * In the vmlinux case, pgoff is a virtual address which must now be
+	 * mapped to a vmlinux offset.
+	 */
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct kmap *kmap = __map__kmap(map);
+		struct map *dest_map;
+
+		if (!kmap || !is_entry_trampoline(kmap->name))
+			continue;
+
+		dest_map = map_groups__find(kmaps, map->pgoff);
+		if (dest_map != map)
+			map->pgoff = dest_map->map_ip(dest_map, map->pgoff);
+		found = true;
+	}
+	if (found || machine->trampolines_mapped)
+		return 0;
+
+	pgoff = find_entry_trampoline(kernel);
+	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,
+		};
+
+		strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN);
+
+		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+			return -1;
+	}
+
+	machine->trampolines_mapped = nr_cpus_avail;
+
+	return 0;
+}
+
+int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused,
+					     struct dso *kernel __maybe_unused)
+{
+	return 0;
+}
+
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
@@ -1206,9 +1330,8 @@ int machine__create_kernel_maps(struct machine *machine)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
-	dso__put(kernel);
 	if (ret < 0)
-		return -1;
+		goto out_put;
 
 	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
 		if (machine__is_host(machine))
@@ -1223,7 +1346,8 @@ int machine__create_kernel_maps(struct machine *machine)
 		if (name &&
 		    map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) {
 			machine__destroy_kernel_maps(machine);
-			return -1;
+			ret = -1;
+			goto out_put;
 		}
 
 		/* we have a real start address now, so re-order the kmaps */
@@ -1239,12 +1363,16 @@ int machine__create_kernel_maps(struct machine *machine)
 		map__put(map);
 	}
 
+	if (machine__create_extra_kernel_maps(machine, kernel))
+		pr_debug("Problems creating extra kernel maps, continuing anyway...\n");
+
 	/* update end address of the kernel map using adjacent module address */
 	map = map__next(machine__kernel_map(machine));
 	if (map)
 		machine__set_kernel_mmap(machine, addr, map->start);
-
-	return 0;
+out_put:
+	dso__put(kernel);
+	return ret;
 }
 
 static bool machine__uses_kcore(struct machine *machine)
@@ -1259,6 +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)
 {
@@ -1362,6 +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:
@@ -2305,6 +2461,11 @@ 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);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b31d33b5aa2a..1de7660d93e9 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -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)
@@ -189,6 +190,7 @@ 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);
@@ -267,4 +269,25 @@ 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);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index c8fe836e4c3c..6ae97eda370b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -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);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f1afe1ab6ff7..97e2a063bd65 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -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"
@@ -46,9 +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 {
@@ -75,6 +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);
 
@@ -231,12 +236,20 @@ 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);
 
+#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 */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 48943b834f11..29770ea61768 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1386,8 +1386,16 @@ 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;
+	struct phdr_data *remaps;
+};
+
+struct sym_data {
+	u64 addr;
+	struct list_head node;
 };
 
 struct kcore_copy_info {
@@ -1397,10 +1405,72 @@ struct kcore_copy_info {
 	u64 last_symbol;
 	u64 first_module;
 	u64 last_module_symbol;
-	struct phdr_data kernel_map;
-	struct phdr_data modules_map;
+	size_t phnum;
+	struct list_head phdrs;
+	struct list_head syms;
 };
 
+#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 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)
 {
@@ -1431,6 +1501,9 @@ 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;
 }
 
@@ -1480,27 +1553,39 @@ 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)
 {
 	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;
+
+	if (kcore_copy__map(kci, start, end, pgoff, kci->first_module,
+			    kci->last_module_symbol))
+		return -1;
 
-	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
-			kci->etext);
+	list_for_each_entry(sdat, &kci->syms, node) {
+		u64 s = round_down(sdat->addr, page_size);
 
-	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
-			kci->last_module_symbol);
+		if (kcore_copy__map(kci, start, end, pgoff, s, s + len))
+			return -1;
+	}
 
 	return 0;
 }
@@ -1513,6 +1598,64 @@ 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) {
+		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,
 				 Elf *elf)
 {
@@ -1548,7 +1691,12 @@ 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,
@@ -1671,12 +1819,15 @@ 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;
+	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);
+	INIT_LIST_HEAD(&kci.syms);
 
 	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
 		return -1;
@@ -1696,20 +1847,17 @@ 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,
-			    kci.kernel_map.len))
-		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 (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))
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
+
+		if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len))
 			goto out_extract_close;
 	}
 
@@ -1717,14 +1865,14 @@ 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 (p->remaps)
+			continue;
+		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;
@@ -1747,6 +1895,9 @@ out_unlink_kallsyms:
 	if (err)
 		kcore_copy__unlink(to_dir, "kallsyms");
 
+	kcore_copy__free_phdrs(&kci);
+	kcore_copy__free_syms(&kci);
+
 	return err;
 }
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 4a39f4d0a174..8c84437f2a10 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -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;
@@ -1017,7 +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;
@@ -1033,8 +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;
 		}
@@ -1091,7 +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;
@@ -1146,6 +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];
@@ -1154,6 +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;
@@ -1197,6 +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)) {
@@ -1233,6 +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().
@@ -1490,20 +1519,22 @@ 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) {