Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The biggest changes are Intel Nehalem-EX PMU uncore support, uprobes
  updates/cleanups/fixes from Oleg and diverse tooling updates (mostly
  fixes) now that Arnaldo is back from vacation."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  uprobes: __replace_page() needs munlock_vma_page()
  uprobes: Rename vma_address() and make it return "unsigned long"
  uprobes: Fix register_for_each_vma()->vma_address() check
  uprobes: Introduce vaddr_to_offset(vma, vaddr)
  uprobes: Teach build_probe_list() to consider the range
  uprobes: Remove insert_vm_struct()->uprobe_mmap()
  uprobes: Remove copy_vma()->uprobe_mmap()
  uprobes: Fix overflow in vma_address()/find_active_uprobe()
  uprobes: Suppress uprobe_munmap() from mmput()
  uprobes: Uprobe_mmap/munmap needs list_for_each_entry_safe()
  uprobes: Clean up and document write_opcode()->lock_page(old_page)
  uprobes: Kill write_opcode()->lock_page(new_page)
  uprobes: __replace_page() should not use page_address_in_vma()
  uprobes: Don't recheck vma/f_mapping in write_opcode()
  perf/x86: Fix missing struct before structure name
  perf/x86: Fix format definition of SNB-EP uncore QPI box
  perf/x86: Make bitfield unsigned
  perf/x86: Fix LLC-* and node-* events on Intel SandyBridge
  perf/x86: Add Intel Nehalem-EX uncore support
  perf/x86: Fix typo in format definition of uncore PCU filter
  ...

18 files changed, 657 insertions, 116 deletions

diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore
new file mode 100644
index 00000000000..35f56be5a4c
--- /dev/null
+++ b/tools/lib/traceevent/.gitignore
@@ -0,0 +1 @@
+TRACEEVENT-CFLAGS
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 46c2f6b7b12..14131cb0522 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -207,7 +207,7 @@ libtraceevent.so: $(PEVENT_LIB_OBJS)
 libtraceevent.a: $(PEVENT_LIB_OBJS)
 	$(Q)$(do_build_static_lib)
 
-$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
 	$(Q)$(do_fpic_compile)
 
 define make_version.h
@@ -272,6 +272,16 @@ ifneq ($(dep_includes),)
  include $(dep_includes)
 endif
 
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+TRACEEVENT-CFLAGS: force
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "    * new build flags or cross compiler"; \
+		echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
+            fi
+
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
@@ -297,7 +307,7 @@ install: install_lib
 
 clean:
 	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
-	$(RM) tags TAGS
+	$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 endif # skip-makefile
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 75d74e5db8d..77f124fe57a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -354,6 +354,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/dso-test-data.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
@@ -803,6 +804,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $<
+
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 5ce30305462..d909eb74a0e 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -1142,6 +1142,10 @@ static struct test {
 		.func = test__perf_pmu,
 	},
 	{
+		.desc = "Test dso data interface",
+		.func = dso__test_data,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e3cab5f088f..35e86c6df71 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -125,7 +125,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		pr_err("Can't annotate %s: No vmlinux file was found in the "
 		       "path\n", sym->name);
 		sleep(1);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 482f0517b61..413bd62eedb 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -978,8 +978,8 @@ static int hist_browser__dump(struct hist_browser *browser)
 	fp = fopen(filename, "w");
 	if (fp == NULL) {
 		char bf[64];
-		strerror_r(errno, bf, sizeof(bf));
-		ui_helpline__fpush("Couldn't write to %s: %s", filename, bf);
+		const char *err = strerror_r(errno, bf, sizeof(bf));
+		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
 		return -1;
 	}
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8069dfb5ba7..3a282c0057d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -426,7 +426,18 @@ int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	const size_t size = symbol__size(sym);
-	size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+	size_t sizeof_sym_hist;
+
+	/* Check for overflow when calculating sizeof_sym_hist */
+	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+		return -1;
+
+	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+
+	/* Check for overflow in zalloc argument */
+	if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
+				/ symbol_conf.nr_events)
+		return -1;
 
 	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
 	if (notes->src == NULL)
@@ -777,7 +788,7 @@ fallback:
 		free_filename = false;
 	}
 
-	if (dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
 		char *build_id_msg = NULL;
 
diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/util/dso-test-data.c
new file mode 100644
index 00000000000..541cdc72c7d
--- /dev/null
+++ b/tools/perf/util/dso-test-data.c
@@ -0,0 +1,153 @@
+#include "util.h"
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "symbol.h"
+
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!(cond)) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static char *test_file(int size)
+{
+	static char buf_templ[] = "/tmp/test-XXXXXX";
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC);
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data_offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data_offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+int dso__test_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	size_t i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		struct test_data_offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < (size_t)size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f74e9560350..3edfd348381 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -214,7 +214,7 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
 		attrs[i].type	       = PERF_TYPE_TRACEPOINT;
 		attrs[i].config	       = err;
 	        attrs[i].sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
-					  PERF_SAMPLE_CPU);
+					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD);
 		attrs[i].sample_period = 1;
 	}
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 5a47aba4675..3a6d2044333 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1212,6 +1212,12 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 				attr.exclude_user,
 				attr.exclude_kernel);
 
+		fprintf(fp, ", excl_host = %d, excl_guest = %d",
+				attr.exclude_host,
+				attr.exclude_guest);
+
+		fprintf(fp, ", precise_ip = %d", attr.precise_ip);
+
 		if (nr)
 			fprintf(fp, ", id = {");
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 514e2a4b367..f247ef2789a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -708,7 +708,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	bool printed = false;
 	struct rb_node *node;
 	int i = 0;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * If have one single callchain root, don't bother printing
@@ -747,8 +747,11 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
-	return __callchain__fprintf_graph(fp, root, total_samples,
+	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
+	ret += fprintf(fp, "\n");
+
+	return ret;
 }
 
 static size_t __callchain__fprintf_flat(FILE *fp,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a1f4e366914..cc33486ad9e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -7,6 +7,8 @@
 #include <stdio.h>
 #include <unistd.h>
 #include "map.h"
+#include "thread.h"
+#include "strlist.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -585,7 +587,21 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid)
 	self->kmaps.machine = self;
 	self->pid	    = pid;
 	self->root_dir      = strdup(root_dir);
-	return self->root_dir == NULL ? -ENOMEM : 0;
+	if (self->root_dir == NULL)
+		return -ENOMEM;
+
+	if (pid != HOST_KERNEL_ID) {
+		struct thread *thread = machine__findnew_thread(self, pid);
+		char comm[64];
+
+		if (thread == NULL)
+			return -ENOMEM;
+
+		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+		thread__set_comm(thread, comm);
+	}
+
+	return 0;
 }
 
 static void dsos__delete(struct list_head *self)
@@ -680,7 +696,15 @@ struct machine *machines__findnew(struct rb_root *self, pid_t pid)
 	    (symbol_conf.guestmount)) {
 		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
 		if (access(path, R_OK)) {
-			pr_err("Can't access file %s\n", path);
+			static struct strlist *seen;
+
+			if (!seen)
+				seen = strlist__new(true, NULL);
+
+			if (!strlist__has_entry(seen, path)) {
+				pr_err("Can't access file %s\n", path);
+				strlist__add(seen, path);
+			}
 			machine = NULL;
 			goto out;
 		}
@@ -714,3 +738,16 @@ char *machine__mmap_name(struct machine *self, char *bf, size_t size)
 
 	return bf;
 }
+
+void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
+{
+	struct rb_node *node;
+	struct machine *machine;
+
+	for (node = rb_first(machines); node; node = rb_next(node)) {
+		machine = rb_entry(node, struct machine, rb_node);
+		machine->id_hdr_size = id_hdr_size;
+	}
+
+	return;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index c14c665d9a2..03a1e9b08b2 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -151,6 +151,7 @@ struct machine *machines__add(struct rb_root *self, pid_t pid,
 struct machine *machines__find_host(struct rb_root *self);
 struct machine *machines__find(struct rb_root *self, pid_t pid);
 struct machine *machines__findnew(struct rb_root *self, pid_t pid);
+void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *self, char *bf, size_t size);
 int machine__init(struct machine *self, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *self);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1aa721d7c10..74a5af4d33e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -377,6 +377,7 @@ static int add_tracepoint(struct list_head **list, int *idx,
 	attr.sample_type |= PERF_SAMPLE_RAW;
 	attr.sample_type |= PERF_SAMPLE_TIME;
 	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_type |= PERF_SAMPLE_PERIOD;
 	attr.sample_period = 1;
 
 	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
@@ -489,6 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.sample_period = 1;
 
 	return add_event(list, idx, &attr, NULL);
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8e485592ca2..8e4f0755d2a 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -87,6 +87,7 @@ void perf_session__update_sample_type(struct perf_session *self)
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
 	self->host_machine.id_hdr_size = self->id_hdr_size;
+	machines__set_id_hdr_size(&self->machines, self->id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -918,7 +919,9 @@ static struct machine *
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+	if (perf_guest &&
+	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
 		if (event->header.type == PERF_RECORD_MMAP)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 50958bbeb26..fdad4eeeb42 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,6 +29,7 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
+static void dso_cache__free(struct rb_root *root);
 static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
@@ -48,6 +49,31 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
+static enum dso_binary_type binary_type_symtab[] = {
+	DSO_BINARY_TYPE__KALLSYMS,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab)
+
+static enum dso_binary_type binary_type_data[] = {
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__DATA_CNT sizeof(binary_type_data)
+
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -318,7 +344,9 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->cache = RB_ROOT;
+		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
@@ -352,6 +380,7 @@ void dso__delete(struct dso *dso)
 		free((char *)dso->short_name);
 	if (dso->lname_alloc)
 		free(dso->long_name);
+	dso_cache__free(&dso->cache);
 	free(dso);
 }
 
@@ -806,9 +835,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	symbols__fixup_end(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 	else
-		dso->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	return dso__split_kallsyms(dso, map, filter);
 }
@@ -1660,32 +1689,110 @@ out:
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
-		[SYMTAB__KALLSYMS]	      = 'k',
-		[SYMTAB__JAVA_JIT]	      = 'j',
-		[SYMTAB__DEBUGLINK]           = 'l',
-		[SYMTAB__BUILD_ID_CACHE]      = 'B',
-		[SYMTAB__FEDORA_DEBUGINFO]    = 'f',
-		[SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
-		[SYMTAB__BUILDID_DEBUGINFO]   = 'b',
-		[SYMTAB__SYSTEM_PATH_DSO]     = 'd',
-		[SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
-		[SYMTAB__GUEST_KALLSYMS]      =  'g',
-		[SYMTAB__GUEST_KMODULE]	      =  'G',
+		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
+		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
+		[DSO_BINARY_TYPE__DEBUGLINK]		= 'l',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
 	};
 
-	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
 		return '!';
 	return origin[dso->symtab_type];
 }
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size)
+{
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	int ret = 0;
+
+	switch (type) {
+	case DSO_BINARY_TYPE__DEBUGLINK: {
+		char *debuglink;
+
+		strncpy(file, dso->long_name, size);
+		debuglink = file + dso->long_name_len;
+		while (debuglink != file && *debuglink != '/')
+			debuglink--;
+		if (*debuglink == '/')
+			debuglink++;
+		filename__read_debuglink(dso->long_name, debuglink,
+					 size - (debuglink - file));
+		}
+		break;
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		/* skip the locally configured cache if a symfs is given */
+		if (symbol_conf.symfs[0] ||
+		    (dso__build_id_filename(dso, file, size) == NULL))
+			ret = -1;
+		break;
+
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+		if (!dso->has_build_id) {
+			ret = -1;
+			break;
+		}
+
+		build_id__sprintf(dso->build_id,
+				  sizeof(dso->build_id),
+				  build_id_hex);
+		snprintf(file, size,
+			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+		snprintf(file, size, "%s%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+			 root_dir, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		snprintf(file, size, "%s%s", symbol_conf.symfs,
+			 dso->long_name);
+		break;
+
+	default:
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__NOT_FOUND:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
-	int size = PATH_MAX;
 	char *name;
 	int ret = -1;
 	int fd;
+	u_int i;
 	struct machine *machine;
-	const char *root_dir;
+	char *root_dir = (char *) "";
 	int want_symtab;
 
 	dso__set_loaded(dso, map->type);
@@ -1700,7 +1807,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	else
 		machine = NULL;
 
-	name = malloc(size);
+	name = malloc(PATH_MAX);
 	if (!name)
 		return -1;
 
@@ -1719,81 +1826,27 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
-		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
-					      SYMTAB__NOT_FOUND;
+		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
+					     DSO_BINARY_TYPE__NOT_FOUND;
 		return ret;
 	}
 
+	if (machine)
+		root_dir = machine->root_dir;
+
 	/* Iterate over candidate debug images.
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
 	want_symtab = 1;
 restart:
-	for (dso->symtab_type = SYMTAB__DEBUGLINK;
-	     dso->symtab_type != SYMTAB__NOT_FOUND;
-	     dso->symtab_type++) {
-		switch (dso->symtab_type) {
-		case SYMTAB__DEBUGLINK: {
-			char *debuglink;
-			strncpy(name, dso->long_name, size);
-			debuglink = name + dso->long_name_len;
-			while (debuglink != name && *debuglink != '/')
-				debuglink--;
-			if (*debuglink == '/')
-				debuglink++;
-			filename__read_debuglink(dso->long_name, debuglink,
-						 size - (debuglink - name));
-			}
-			break;
-		case SYMTAB__BUILD_ID_CACHE:
-			/* skip the locally configured cache if a symfs is given */
-			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(dso, name, size) == NULL)) {
-				continue;
-			}
-			break;
-		case SYMTAB__FEDORA_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__UBUNTU_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__BUILDID_DEBUGINFO: {
-			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
 
-			if (!dso->has_build_id)
-				continue;
+		dso->symtab_type = binary_type_symtab[i];
 
-			build_id__sprintf(dso->build_id,
-					  sizeof(dso->build_id),
-					  build_id_hex);
-			snprintf(name, size,
-				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
-			}
-			break;
-		case SYMTAB__SYSTEM_PATH_DSO:
-			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__GUEST_KMODULE:
-			if (map->groups && machine)
-				root_dir = machine->root_dir;
-			else
-				root_dir = "";
-			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, dso->long_name);
-			break;
-
-		case SYMTAB__SYSTEM_PATH_KMODULE:
-			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 dso->long_name);
-			break;
-		default:;
-		}
+		if (dso__binary_type_file(dso, dso->symtab_type,
+					  root_dir, name, PATH_MAX))
+			continue;
 
 		/* Name is now the name of the next image to try */
 		fd = open(name, O_RDONLY);
@@ -2010,9 +2063,9 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		return NULL;
 
 	if (machine__is_host(machine))
-		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
-		dso->symtab_type = SYMTAB__GUEST_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
@@ -2564,8 +2617,15 @@ int machine__create_kernel_maps(struct machine *machine)
 	    __machine__create_kernel_maps(machine, kernel) < 0)
 		return -1;
 
-	if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
 	/*
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
@@ -2905,3 +2965,218 @@ struct map *dso__new_map(const char *name)
 
 	return map;
 }
+
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	char *root_dir = (char *) "";
+	char *name;
+	int fd;
+
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -ENOMEM;
+
+	if (machine)
+		root_dir = machine->root_dir;
+
+	if (dso__binary_type_file(dso, dso->data_type,
+				  root_dir, name, PATH_MAX)) {
+		free(name);
+		return -EINVAL;
+	}
+
+	fd = open(name, O_RDONLY);
+	free(name);
+	return fd;
+}
+
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int i = 0;
+
+	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+		return open_dso(dso, machine);
+
+	do {
+		int fd;
+
+		dso->data_type = binary_type_data[i++];
+
+		fd = open_dso(dso, machine);
+		if (fd >= 0)
+			return fd;
+
+	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+
+	return -EINVAL;
+}
+
+static void
+dso_cache__free(struct rb_root *root)
+{
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct dso_cache *cache;
+
+		cache = rb_entry(next, struct dso_cache, rb_node);
+		next = rb_next(&cache->rb_node);
+		rb_erase(&cache->rb_node, root);
+		free(cache);
+	}
+}
+
+static struct dso_cache*
+dso_cache__find(struct rb_root *root, u64 offset)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+		else
+			return cache;
+	}
+	return NULL;
+}
+
+static void
+dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+	u64 offset = new->offset;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+}
+
+static ssize_t
+dso_cache__memcpy(struct dso_cache *cache, u64 offset,
+		  u8 *data, u64 size)
+{
+	u64 cache_offset = offset - cache->offset;
+	u64 cache_size   = min(cache->size - cache_offset, size);
+
+	memcpy(data, cache->data + cache_offset, cache_size);
+	return cache_size;
+}
+
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+		 u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+	ssize_t ret;
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return -1;
+
+	do {
+		u64 cache_offset;
+
+		ret = -ENOMEM;
+
+		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+		if (!cache)
+			break;
+
+		cache_offset = offset & DSO__DATA_CACHE_MASK;
+		ret = -EINVAL;
+
+		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+			break;
+
+		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		if (ret <= 0)
+			break;
+
+		cache->offset = cache_offset;
+		cache->size   = ret;
+		dso_cache__insert(&dso->cache, cache);
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+
+	} while (0);
+
+	if (ret <= 0)
+		free(cache);
+
+	close(fd);
+	return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+
+	cache = dso_cache__find(&dso->cache, offset);
+	if (cache)
+		return dso_cache__memcpy(cache, offset, data, size);
+	else
+		return dso_cache__read(dso, machine, offset, data, size);
+}
+
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	ssize_t r = 0;
+	u8 *p = data;
+
+	do {
+		ssize_t ret;
+
+		ret = dso_cache_read(dso, machine, offset, p, size);
+		if (ret < 0)
+			return ret;
+
+		/* Reached EOF, return what we have. */
+		if (!ret)
+			break;
+
+		BUG_ON(ret > size);
+
+		r      += ret;
+		p      += ret;
+		offset += ret;
+		size   -= ret;
+
+	} while (size);
+
+	return r;
+}
+
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size)
+{
+	u64 offset = map->map_ip(map, addr);
+	return dso__data_read_offset(dso, machine, offset, data, size);
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index a884b99017f..1fe733a1e21 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -155,6 +155,21 @@ struct addr_location {
 	s32	      cpu;
 };
 
+enum dso_binary_type {
+	DSO_BINARY_TYPE__KALLSYMS = 0,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
 enum dso_kernel_type {
 	DSO_TYPE_USER = 0,
 	DSO_TYPE_KERNEL,
@@ -167,19 +182,31 @@ enum dso_swap_type {
 	DSO_SWAP__YES,
 };
 
+#define DSO__DATA_CACHE_SIZE 4096
+#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
+
+struct dso_cache {
+	struct rb_node	rb_node;
+	u64 offset;
+	u64 size;
+	char data[0];
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 cache;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
+	enum dso_binary_type	symtab_type;
+	enum dso_binary_type	data_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
 	u8		 lname_alloc:1;
-	unsigned char	 symtab_type;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
@@ -253,21 +280,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 				    enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
-enum symtab_type {
-	SYMTAB__KALLSYMS = 0,
-	SYMTAB__GUEST_KALLSYMS,
-	SYMTAB__JAVA_JIT,
-	SYMTAB__DEBUGLINK,
-	SYMTAB__BUILD_ID_CACHE,
-	SYMTAB__FEDORA_DEBUGINFO,
-	SYMTAB__UBUNTU_DEBUGINFO,
-	SYMTAB__BUILDID_DEBUGINFO,
-	SYMTAB__SYSTEM_PATH_DSO,
-	SYMTAB__GUEST_KMODULE,
-	SYMTAB__SYSTEM_PATH_KMODULE,
-	SYMTAB__NOT_FOUND,
-};
-
 char dso__symtab_origin(const struct dso *dso);
 void dso__set_long_name(struct dso *dso, char *name);
 void dso__set_build_id(struct dso *dso, void *build_id);
@@ -304,4 +316,14 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size);
+
+int dso__data_fd(struct dso *dso, struct machine *machine);
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size);
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size);
+int dso__test_data(void);
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 1064d5b148a..3f59c496e64 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -110,8 +110,17 @@ int perf_target__strerror(struct perf_target *target, int errnum,
 	int idx;
 	const char *msg;
 
+	BUG_ON(buflen > 0);
+
 	if (errnum >= 0) {
-		strerror_r(errnum, buf, buflen);
+		const char *err = strerror_r(errnum, buf, buflen);
+
+		if (err != buf) {
+			size_t len = strlen(err);
+			char *c = mempcpy(buf, err, min(buflen - 1, len));
+			*c = '\0';
+		}
+
 		return 0;
 	}