25 files changed, 1178 insertions, 129 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9a42382b3921..48b6d3f50012 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -616,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 	if (sample->callchain == NULL)
 		return 0;
 
-	if (symbol_conf.use_callchain || sort__has_parent) {
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+	    sort__has_parent) {
 		return machine__resolve_callchain(al->machine, evsel, al->thread,
 						  sample, parent, al, max_stack);
 	}
@@ -629,3 +630,45 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
 		return 0;
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved)
+{
+	al->map = node->map;
+	al->sym = node->sym;
+	if (node->map)
+		al->addr = node->map->map_ip(node->map, node->ip);
+	else
+		al->addr = node->ip;
+
+	if (al->sym == NULL) {
+		if (hide_unresolved)
+			return 0;
+		if (al->map == NULL)
+			goto out;
+	}
+
+	if (al->map->groups == &al->machine->kmaps) {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_KERNEL;
+			al->level = 'k';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+			al->level = 'g';
+		}
+	} else {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_USER;
+			al->level = '.';
+		} else if (perf_guest) {
+			al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+			al->level = 'u';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+			al->level = 'H';
+		}
+	}
+
+out:
+	return 1;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index bde2b0cc24cf..8f84423a75da 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -162,7 +162,18 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 			      struct perf_evsel *evsel, struct addr_location *al,
 			      int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved);
 
 extern const char record_callchain_help[];
 int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+					     struct callchain_cursor *src)
+{
+	*dest = *src;
+
+	dest->first = src->curr;
+	dest->nr -= src->pos;
+}
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d63b971..819f10414f08 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+	list_del(&dso->data.open_entry);
+	WARN_ONCE(dso__data_open_cnt <= 0,
+		  "DSO data fd counter out of bounds.");
+	dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+	int fd;
+
+	do {
+		fd = open(name, O_RDONLY);
+		if (fd >= 0)
+			return fd;
+
+		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		if (!dso__data_open_cnt || errno != EMFILE)
+			break;
+
+		close_first_dso();
+	} while (1);
+
+	return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd;
 	char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
-	fd = open(name, O_RDONLY);
+	fd = do_open(name);
 	free(name);
 	return fd;
 }
 
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd = __open_dso(dso, machine);
+
+	if (fd > 0) {
+		dso__list_add(dso);
+		/*
+		 * Check if we crossed the allowed number
+		 * of opened DSOs and close one if needed.
+		 */
+		check_data_close();
+	}
+
+	return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+	if (dso->data.fd >= 0) {
+		close(dso->data.fd);
+		dso->data.fd = -1;
+		dso->data.file_size = 0;
+		dso__list_del(dso);
+	}
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+	close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+	struct dso *dso;
+
+	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+	struct rlimit l;
+	rlim_t limit = 0;
+
+	/* Allow half of the current open fd limit. */
+	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+		if (l.rlim_cur == RLIM_INFINITY)
+			limit = l.rlim_cur;
+		else
+			limit = l.rlim_cur / 2;
+	} else {
+		pr_err("failed to get fd limit\n");
+		limit = 1;
+	}
+
+	return limit;
+}
+
+static bool may_cache_fd(void)
+{
+	static rlim_t limit;
+
+	if (!limit)
+		limit = get_fd_limit();
+
+	if (limit == RLIM_INFINITY)
+		return true;
+
+	return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+	bool cache_fd = may_cache_fd();
+
+	if (!cache_fd)
+		close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+	close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
@@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
-		return open_dso(dso, machine);
+	if (dso->data.fd >= 0)
+		return dso->data.fd;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->data.fd = open_dso(dso, machine);
+		return dso->data.fd;
+	}
 
 	do {
 		int fd;
@@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 
 		fd = open_dso(dso, machine);
 		if (fd >= 0)
-			return fd;
+			return dso->data.fd = fd;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
@@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-		 u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, 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;
@@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 		ret = -EINVAL;
 
-		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
 			break;
 
-		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
 		if (ret <= 0)
 			break;
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->cache, cache);
+		dso_cache__insert(&dso->data.cache, cache);
 
 		ret = dso_cache__memcpy(cache, offset, data, size);
 
@@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 	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)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+			      u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->cache, offset);
+	cache = dso_cache__find(&dso->data.cache, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, machine, offset, data, size);
+		return dso_cache__read(dso, offset, data, size);
 }
 
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, machine, offset, p, size);
+		ret = dso_cache_read(dso, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	return r;
 }
 
+static int data_file_size(struct dso *dso)
+{
+	struct stat st;
+
+	if (!dso->data.file_size) {
+		if (fstat(dso->data.fd, &st)) {
+			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			return -1;
+		}
+		dso->data.file_size = st.st_size;
+	}
+
+	return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+				u8 *data, ssize_t size)
+{
+	if (data_file_size(dso))
+		return -1;
+
+	/* Check the offset sanity. */
+	if (offset > dso->data.file_size)
+		return -1;
+
+	if (offset + size < offset)
+		return -1;
+
+	return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso__data_fd(dso, machine) < 0)
+		return -1;
+
+	return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size)
@@ -473,7 +699,8 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->cache = RB_ROOT;
+		dso->data.cache = RB_ROOT;
+		dso->data.fd = -1;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
@@ -485,6 +712,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
+		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
 
 	return dso;
@@ -506,7 +734,8 @@ void dso__delete(struct dso *dso)
 		dso->long_name_allocated = false;
 	}
 
-	dso_cache__free(&dso->cache);
+	dso__data_close(dso);
+	dso_cache__free(&dso->data.cache);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
 	free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 38efe95a7fdd..ad553ba257bf 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -76,7 +76,6 @@ 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;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -99,6 +98,15 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+
+	/* dso data file */
+	struct {
+		struct rb_root	 cache;
+		int		 fd;
+		size_t		 file_size;
+		struct list_head open_entry;
+	} data;
+
 	char		 name[0];
 };
 
@@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
 int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
 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,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 65795b835b39..d0281bdfa582 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <sys/mman.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP;
+	event->header.type = PERF_RECORD_MMAP2;
 
 	while (1) {
 		char bf[BUFSIZ];
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
 		ssize_t n;
 
@@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-		       &event->mmap.start, &event->mmap.len, prot,
-		       &event->mmap.pgoff,
-		       execname);
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
 		/*
  		 * Anon maps don't have the execname.
  		 */
-		if (n < 4)
+		if (n < 7)
 			continue;
+
+		event->mmap2.ino = (u64)ino;
+
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 		 */
@@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
 		if (prot[2] != 'x') {
 			if (!mmap_data || prot[0] != 'r')
 				continue;
@@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap.filename, execname, size);
+		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap.len -= event->mmap.start;
-		event->mmap.header.size = (sizeof(event->mmap) -
-					(sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.pid = tgid;
-		event->mmap.tid = pid;
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
@@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
 		       event->mmap2.ino_generation,
-		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+		       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+		       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+		       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
 		       event->mmap2.filename);
 }
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d970232cb270..e5dd40addb30 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
 #include "../perf.h"
 #include "map.h"
 #include "build-id.h"
+#include "perf_regs.h"
 
 struct mmap_event {
 	struct perf_event_header header;
@@ -27,6 +28,8 @@ struct mmap2_event {
 	u32 min;
 	u64 ino;
 	u64 ino_generation;
+	u32 prot;
+	u32 flags;
 	char filename[PATH_MAX];
 };
 
@@ -87,6 +90,10 @@ struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
+
+	/* Cached values/mask filled by first register access. */
+	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_mask;
 };
 
 struct stack_dump {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82b76c4..8606175fe1e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 
 	/*
-	 * We default some events to a 1 default interval. But keep
+	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
 			perf_evsel__set_sample_bit(evsel, PERIOD);
@@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
 	if (opts->sample_transaction)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b262b44b7a65..30df6187ee02 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -127,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
@@ -231,6 +234,8 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 		return true;
 
 	he_stat__decay(&he->stat);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__decay(he->stat_acc);
 
 	diff = prev_period - he->stat.period;
 
@@ -276,14 +281,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+		callchain_size = sizeof(struct callchain_root);
+
+	he = zalloc(sizeof(*he) + callchain_size);
 
 	if (he != NULL) {
 		*he = *template;
 
+		if (symbol_conf.cumulate_callchain) {
+			he->stat_acc = malloc(sizeof(he->stat));
+			if (he->stat_acc == NULL) {
+				free(he);
+				return NULL;
+			}
+			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
+		}
+
 		if (he->ms.map)
 			he->ms.map->referenced = true;
 
@@ -295,6 +317,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				free(he->stat_acc);
 				free(he);
 				return NULL;
 			}
@@ -333,7 +356,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
 					 struct hist_entry *entry,
-					 struct addr_location *al)
+					 struct addr_location *al,
+					 bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -357,7 +381,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period, weight);
+			if (sample_self)
+				he_stat__add_period(&he->stat, period, weight);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_period(he->stat_acc, period, weight);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -385,14 +412,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
 		return NULL;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (sample_self)
+		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
 	return he;
 }
 
@@ -401,7 +431,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction)
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -410,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
 			.period	= period,
@@ -426,7 +458,429 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al);
+	return add_hist_entry(hists, &entry, al, sample_self);
+}
+
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
+
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	iter->priv = mi;
+	return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
+
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0, true);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
+
+	iter->he = NULL;
+	return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
+
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
+
+	iter->priv = bi;
+	return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	/* to avoid calling callback function */
+	iter->he = NULL;
+
+	return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
+
+	if (bi == NULL)
+		return 0;
+
+	if (iter->curr >= iter->total)
+		return 0;
+
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
+
+	bi = iter->priv;
+
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 */
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+				1, 1, 0, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+
+	if (he == NULL)
+		return 0;
+
+	iter->he = NULL;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+			      struct addr_location *al __maybe_unused)
+{
+	struct hist_entry **he_cache;
+
+	callchain_cursor_commit(&callchain_cursor);
+
+	/*
+	 * This is for detecting cycles or recursions so that they're
+	 * cumulated only one time to prevent entries more than 100%
+	 * overhead.
+	 */
+	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	if (he_cache == NULL)
+		return -ENOMEM;
+
+	iter->priv = he_cache;
+	iter->curr = 0;
+
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+	/*
+	 * We need to re-initialize the cursor since callchain_append()
+	 * advanced the cursor to the end.
+	 */
+	callchain_cursor_commit(&callchain_cursor);
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
+{
+	struct callchain_cursor_node *node;
+
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
+
+	return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+			       struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	struct hist_entry he_tmp = {
+		.cpu = al->cpu,
+		.thread = al->thread,
+		.comm = thread__comm(al->thread),
+		.ip = al->addr,
+		.ms = {
+			.map = al->map,
+			.sym = al->sym,
+		},
+		.parent = iter->parent,
+	};
+	int i;
+	struct callchain_cursor cursor;
+
+	callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+	callchain_cursor_advance(&callchain_cursor);
+
+	/*
+	 * Check if there's duplicate entries in the callchain.
+	 * It's possible that it has cycles or recursive calls.
+	 */
+	for (i = 0; i < iter->curr; i++) {
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
+			return 0;
+		}
+	}
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &cursor, sample->period);
+	return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return 0;
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
+
+	iter->evsel = evsel;
+	iter->sample = sample;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
+
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
+
+	return err;
 }
 
 int64_t
@@ -469,6 +923,7 @@ void hist_entry__free(struct hist_entry *he)
 {
 	zfree(&he->branch_info);
 	zfree(&he->mem_info);
+	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free(he);
 }
@@ -494,6 +949,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 		if (!cmp) {
 			he_stat__add_stat(&iter->stat, &he->stat);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
@@ -800,6 +1257,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
 	events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
@@ -831,7 +1295,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(pair);
+	he = hist_entry__new(pair, true);
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a8418d19808d..742f49a85725 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -72,6 +72,7 @@ enum hist_column {
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
 	HISTC_MEM_SNOOP,
+	HISTC_MEM_DCACHELINE,
 	HISTC_TRANSACTION,
 	HISTC_NR_COLS, /* Last entry */
 };
@@ -96,12 +97,50 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+	/* user-defined callback function (optional) */
+	int (*add_entry_cb)(struct hist_entry_iter *iter,
+			    struct addr_location *al, bool single, void *arg);
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction);
+				      u64 weight, u64 transaction,
+				      bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg);
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
@@ -119,6 +158,7 @@ u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
@@ -166,6 +206,7 @@ struct perf_hpp_fmt {
 
 	struct list_head list;
 	struct list_head sort_list;
+	bool elide;
 };
 
 extern struct list_head perf_hpp__list;
@@ -192,6 +233,7 @@ enum {
 	PERF_HPP__OVERHEAD_US,
 	PERF_HPP__OVERHEAD_GUEST_SYS,
 	PERF_HPP__OVERHEAD_GUEST_US,
+	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
 
@@ -200,7 +242,11 @@ enum {
 
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
 void perf_hpp__setup_output_field(void);
 void perf_hpp__reset_output_field(void);
@@ -208,7 +254,12 @@ void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
-bool perf_hpp__should_skip(struct perf_hpp_fmt *format);
+
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+{
+	return format->elide;
+}
+
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
@@ -218,6 +269,9 @@ typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	       hpp_field_fn get_field, const char *fmt,
 	       hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7409ac8de51c..0e5fea95d596 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1060,6 +1060,8 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.pid, event->mmap2.maj,
 			event->mmap2.min, event->mmap2.ino,
 			event->mmap2.ino_generation,
+			event->mmap2.prot,
+			event->mmap2.flags,
 			event->mmap2.filename, type);
 
 	if (map == NULL)
@@ -1105,7 +1107,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
 	map = map__new(&machine->user_dsos, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			event->mmap.pid, 0, 0, 0, 0,
+			event->mmap.pid, 0, 0, 0, 0, 0, 0,
 			event->mmap.filename,
 			type);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8ccbb32eda25..25c571f4cba6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -138,7 +138,7 @@ void map__init(struct map *map, enum map_type type,
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen, char *filename,
+		     u64 ino_gen, u32 prot, u32 flags, char *filename,
 		     enum map_type type)
 {
 	struct map *map = malloc(sizeof(*map));
@@ -157,6 +157,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->min = d_min;
 		map->ino = ino;
 		map->ino_generation = ino_gen;
+		map->prot = prot;
+		map->flags = flags;
 
 		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ae2d45110588..7758c72522ef 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -35,6 +35,8 @@ struct map {
 	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
+	u32			prot;
+	u32			flags;
 	u64			pgoff;
 	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
@@ -118,7 +120,7 @@ void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen,
+		     u64 ino_gen, u32 prot, u32 flags,
 		     char *filename, enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef30b15..43168fb0d9a2 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
 #include <errno.h>
 #include "perf_regs.h"
+#include "event.h"
 
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if (regs->cache_mask & (1 << id))
+		goto out;
+
 	if (!(mask & (1 << id)))
 		return -EINVAL;
 
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 			idx++;
 	}
 
-	*valp = regs->regs[idx];
+	regs->cache_mask |= (1 << id);
+	regs->cache_regs[id] = regs->regs[idx];
+
+out:
+	*valp = regs->cache_regs[id];
 	return 0;
 }
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 79c78f74e0cf..980dbf76bc98 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,7 +2,8 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
-#include "event.h"
+
+struct regs_dump;
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK	0
+#define PERF_REGS_MAX	0
 
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0d1542f33d87..9a0a1839a377 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
-	if (ret == 0) {
+	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
 	} else if (ret < 0) {
-		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		pr_warning("Debuginfo analysis failed.\n");
 		return ret;
 	}
 
@@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
 	free(tmp);	/* Free old path */
 	if (ret < 0) {
-		pr_warning("Failed to find source file. (%d)\n", ret);
+		pr_warning("Failed to find source file path.\n");
 		return ret;
 	}
 
@@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
 						max_vls, externs);
 	if (ret <= 0) {
-		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+		if (ret == 0 || ret == -ENOENT) {
+			pr_err("Failed to find the address of %s\n", buf);
+			ret = -ENOENT;
+		} else
+			pr_warning("Debuginfo analysis failed.\n");
 		goto end;
 	}
+
 	/* Some variables are found */
 	fprintf(stdout, "Available variables at %s\n", buf);
 	for (i = 0; i < ret; i++) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 9d8eb26f0533..98e304766416 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -573,14 +573,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+			pr_warning("Failed to find '%s' in this function.\n",
+				   pf->pvar->var);
 			ret = -ENOENT;
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
-	if (ret < 0)
-		pr_warning("Failed to find '%s' in this function.\n",
-			   pf->pvar->var);
 	return ret;
 }
 
@@ -1281,7 +1280,11 @@ out:
 	return ret;
 }
 
-/* Find available variables at given probe point */
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
 				      struct variable_list **vls,
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207c5de0..af7da565a750 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
+	case PRINT_BITMASK:
 		break;
 	case PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cd9774df3750..1c419321f707 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_FUNC:
+	case PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			fprintf(ofp, "%s=", f->name);
 			if (f->flags & FIELD_IS_STRING ||
 			    f->flags & FIELD_IS_FLAG ||
+			    f->flags & FIELD_IS_ARRAY ||
 			    f->flags & FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
 			else if (f->flags & FIELD_IS_SIGNED)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 901b9bece2ee..1ec57dd82284 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,3 +1,4 @@
+#include <sys/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
+static inline  u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 l, r;
+	struct map *l_map, *r_map;
+
+	if (!left->mem_info)  return -1;
+	if (!right->mem_info) return 1;
+
+	/* group event types together */
+	if (left->cpumode > right->cpumode) return -1;
+	if (left->cpumode < right->cpumode) return 1;
+
+	l_map = left->mem_info->daddr.map;
+	r_map = right->mem_info->daddr.map;
+
+	/* if both are NULL, jump to sort on al_addr instead */
+	if (!l_map && !r_map)
+		goto addr;
+
+	if (!l_map) return -1;
+	if (!r_map) return 1;
+
+	if (l_map->maj > r_map->maj) return -1;
+	if (l_map->maj < r_map->maj) return 1;
+
+	if (l_map->min > r_map->min) return -1;
+	if (l_map->min < r_map->min) return 1;
+
+	if (l_map->ino > r_map->ino) return -1;
+	if (l_map->ino < r_map->ino) return 1;
+
+	if (l_map->ino_generation > r_map->ino_generation) return -1;
+	if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+	/*
+	 * Addresses with no major/minor numbers are assumed to be
+	 * anonymous in userspace.  Sort those on pid then address.
+	 *
+	 * The kernel and non-zero major/minor mapped areas are
+	 * assumed to be unity mapped.  Sort those on address.
+	 */
+
+	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
+	    (!(l_map->flags & MAP_SHARED)) &&
+	    !l_map->maj && !l_map->min && !l_map->ino &&
+	    !l_map->ino_generation) {
+		/* userspace anonymous */
+
+		if (left->thread->pid_ > right->thread->pid_) return -1;
+		if (left->thread->pid_ < right->thread->pid_) return 1;
+	}
+
+addr:
+	/* al_addr does all the right addr - start + offset calculations */
+	l = cl_address(left->mem_info->daddr.al_addr);
+	r = cl_address(right->mem_info->daddr.al_addr);
+
+	if (l > r) return -1;
+	if (l < r) return 1;
+
+	return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+	char level = he->level;
+
+	if (he->mem_info) {
+		addr = cl_address(he->mem_info->daddr.al_addr);
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+
+		/* print [s] for shared data mmaps */
+		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+		     map && (map->type == MAP__VARIABLE) &&
+		    (map->flags & MAP_SHARED) &&
+		    (map->maj || map->min || map->ino ||
+		     map->ino_generation))
+			level = 's';
+		else if (!map)
+			level = 'X';
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+					 width);
+}
+
 struct sort_entry sort_mispredict = {
 	.se_header	= "Branch Mispredicted",
 	.se_cmp		= sort__mispredict_cmp,
@@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = {
 	.se_width_idx	= HISTC_MEM_SNOOP,
 };
 
+struct sort_entry sort_mem_dcacheline = {
+	.se_header	= "Data Cacheline",
+	.se_cmp		= sort__dcacheline_cmp,
+	.se_snprintf	= hist_entry__dcacheline_snprintf,
+	.se_width_idx	= HISTC_MEM_DCACHELINE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
 	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
 	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 };
 
 #undef DIM
@@ -1061,6 +1168,7 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
 };
@@ -1156,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
+	hse->hpp.elide = false;
 
 	return hse;
 }
@@ -1363,27 +1472,64 @@ static int __setup_sorting(void)
 	return ret;
 }
 
-bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+void perf_hpp__set_elide(int idx, bool elide)
 {
-	if (perf_hpp__is_sort_entry(format)) {
-		struct hpp_sort_entry *hse;
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
 
-		hse = container_of(format, struct hpp_sort_entry, hpp);
-		return hse->se->elide;
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_width_idx == idx) {
+			fmt->elide = elide;
+			break;
+		}
 	}
-	return false;
 }
 
-static void sort_entry__setup_elide(struct sort_entry *se,
-				    struct strlist *list,
-				    const char *list_name, FILE *fp)
+static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp)
 {
 	if (list && strlist__nr_entries(list) == 1) {
 		if (fp != NULL)
 			fprintf(fp, "# %s: %s\n", list_name,
 				strlist__entry(list, 0)->s);
-		se->elide = true;
+		return true;
 	}
+	return false;
+}
+
+static bool get_elide(int idx, FILE *output)
+{
+	switch (idx) {
+	case HISTC_SYMBOL:
+		return __get_elide(symbol_conf.sym_list, "symbol", output);
+	case HISTC_DSO:
+		return __get_elide(symbol_conf.dso_list, "dso", output);
+	case HISTC_COMM:
+		return __get_elide(symbol_conf.comm_list, "comm", output);
+	default:
+		break;
+	}
+
+	if (sort__mode != SORT_MODE__BRANCH)
+		return false;
+
+	switch (idx) {
+	case HISTC_SYMBOL_FROM:
+		return __get_elide(symbol_conf.sym_from_list, "sym_from", output);
+	case HISTC_SYMBOL_TO:
+		return __get_elide(symbol_conf.sym_to_list, "sym_to", output);
+	case HISTC_DSO_FROM:
+		return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
+	case HISTC_DSO_TO:
+		return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+	default:
+		break;
+	}
+
+	return false;
 }
 
 void sort__setup_elide(FILE *output)
@@ -1391,39 +1537,12 @@ void sort__setup_elide(FILE *output)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-				"dso", output);
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
-				"comm", output);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
-				"symbol", output);
-
-	if (sort__mode == SORT_MODE__BRANCH) {
-		sort_entry__setup_elide(&sort_dso_from,
-					symbol_conf.dso_from_list,
-					"dso_from", output);
-		sort_entry__setup_elide(&sort_dso_to,
-					symbol_conf.dso_to_list,
-					"dso_to", output);
-		sort_entry__setup_elide(&sort_sym_from,
-					symbol_conf.sym_from_list,
-					"sym_from", output);
-		sort_entry__setup_elide(&sort_sym_to,
-					symbol_conf.sym_to_list,
-					"sym_to", output);
-	} else if (sort__mode == SORT_MODE__MEMORY) {
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"symbol_daddr", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"dso_daddr", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"mem", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"local_weight", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"tlb", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"snoop", output);
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		fmt->elide = get_elide(hse->se->se_width_idx, output);
 	}
 
 	/*
@@ -1434,8 +1553,7 @@ void sort__setup_elide(FILE *output)
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
-		hse = container_of(fmt, struct hpp_sort_entry, hpp);
-		if (!hse->se->elide)
+		if (!fmt->elide)
 			return;
 	}
 
@@ -1443,8 +1561,7 @@ void sort__setup_elide(FILE *output)
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
-		hse = container_of(fmt, struct hpp_sort_entry, hpp);
-		hse->se->elide = false;
+		fmt->elide = false;
 	}
 }
 
@@ -1581,6 +1698,9 @@ void reset_output_field(void)
 	sort__has_sym = 0;
 	sort__has_dso = 0;
 
+	field_order = NULL;
+	sort_order = NULL;
+
 	reset_dimensions();
 	perf_hpp__reset_output_field();
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5f38d925e92f..041f0c9cea2b 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -20,7 +20,7 @@
 
 #include "parse-options.h"
 #include "parse-events.h"
-
+#include "hist.h"
 #include "thread.h"
 
 extern regex_t parent_regex;
@@ -82,12 +82,14 @@ struct hist_entry {
 		struct list_head head;
 	} pairs;
 	struct he_stat		stat;
+	struct he_stat		*stat_acc;
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
 	u64			ip;
 	u64			transaction;
 	s32			cpu;
+	u8			cpumode;
 
 	struct hist_entry_diff	diff;
 
@@ -130,6 +132,21 @@ static inline void hist_entry__add_pair(struct hist_entry *pair,
 	list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
+
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
@@ -169,6 +186,7 @@ enum sort_type {
 	SORT_MEM_TLB,
 	SORT_MEM_LVL,
 	SORT_MEM_SNOOP,
+	SORT_MEM_DCACHELINE,
 };
 
 /*
@@ -186,7 +204,6 @@ struct sort_entry {
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
 	u8	se_width_idx;
-	bool	elide;
 };
 
 extern struct sort_entry sort_thread;
@@ -197,6 +214,7 @@ int setup_output_field(void);
 void reset_output_field(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
+void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 95e249779931..7b9096f29cdb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,11 +29,12 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
-	.use_modules	  = true,
-	.try_vmlinux_path = true,
-	.annotate_src	  = true,
-	.demangle	  = true,
-	.symfs            = "",
+	.use_modules		= true,
+	.try_vmlinux_path	= true,
+	.annotate_src		= true,
+	.demangle		= true,
+	.cumulate_callchain	= true,
+	.symfs			= "",
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 33ede53fa6b9..615c752dd767 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -109,6 +109,7 @@ struct symbol_conf {
 			show_nr_samples,
 			show_total_period,
 			use_callchain,
+			cumulate_callchain,
 			exclude_other,
 			show_cpu_utilization,
 			initialized,
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d74f01..25578b98f5c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 
 	/* Check the .eh_frame section for unwinding info */
 	offset = elf_section_offset(fd, ".eh_frame_hdr");
-	close(fd);
 
 	if (offset)
 		ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 
 	/* Check the .debug_frame section for unwinding info */
 	*offset = elf_section_offset(fd, ".debug_frame");
-	close(fd);
 
 	if (*offset)
 		return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7fff6be07f07..95aefa78bb07 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,7 @@
  * XXX We need to find a better place for these things...
  */
 unsigned int page_size;
+int cacheline_size;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b03da44e94e4..66864364ccb4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -304,6 +304,7 @@ char *rtrim(char *s);
 void dump_stack(void);
 
 extern unsigned int page_size;
+extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);