Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:
	drivers/power/wm97xx_battery.c

1 files changed, 784 insertions, 639 deletions

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5eb5566f0c9..19669c20088 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -10,38 +10,45 @@
 #include "util/util.h"
 
 #include "util/color.h"
-#include "util/list.h"
+#include <linux/list.h>
 #include "util/cache.h"
-#include "util/rbtree.h"
+#include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/string.h"
+#include "util/callchain.h"
+#include "util/strlist.h"
+#include "util/values.h"
 
 #include "perf.h"
+#include "util/debug.h"
+#include "util/header.h"
 
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 
-#define SHOW_KERNEL	1
-#define SHOW_USER	2
-#define SHOW_HV		4
+#include "util/thread.h"
 
 static char		const *input_name = "perf.data";
-static char		*vmlinux = NULL;
 
-static char		default_sort_order[] = "comm,dso";
+static char		default_sort_order[] = "comm,dso,symbol";
 static char		*sort_order = default_sort_order;
+static char		*dso_list_str, *comm_list_str, *sym_list_str,
+			*col_width_list_str;
+static struct strlist	*dso_list, *comm_list, *sym_list;
+static char		*field_sep;
 
+static int		force;
 static int		input;
 static int		show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV;
 
-static int		dump_trace = 0;
-#define dprintf(x...)	do { if (dump_trace) printf(x); } while (0)
-#define cdprintf(x...)	do { if (dump_trace) color_fprintf(stdout, color, x); } while (0)
+static int		full_paths;
+static int		show_nr_samples;
 
-static int		verbose;
-#define eprintf(x...)	do { if (verbose) fprintf(stderr, x); } while (0)
+static int		show_threads;
+static struct perf_read_values	show_threads_values;
 
-static int		full_paths;
+static char		default_pretty_printing_style[] = "normal";
+static char		*pretty_printing_style = default_pretty_printing_style;
 
 static unsigned long	page_size;
 static unsigned long	mmap_window = 32;
@@ -52,410 +59,58 @@ static regex_t		parent_regex;
 
 static int		exclude_other = 1;
 
-struct ip_event {
-	struct perf_event_header header;
-	u64 ip;
-	u32 pid, tid;
-	unsigned char __more_data[];
-};
-
-struct ip_callchain {
-	u64 nr;
-	u64 ips[0];
-};
-
-struct mmap_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	u64 start;
-	u64 len;
-	u64 pgoff;
-	char filename[PATH_MAX];
-};
-
-struct comm_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	char comm[16];
-};
-
-struct fork_event {
-	struct perf_event_header header;
-	u32 pid, ppid;
-};
-
-struct period_event {
-	struct perf_event_header header;
-	u64 time;
-	u64 id;
-	u64 sample_period;
-};
-
-struct lost_event {
-	struct perf_event_header header;
-	u64 id;
-	u64 lost;
-};
-
-typedef union event_union {
-	struct perf_event_header	header;
-	struct ip_event			ip;
-	struct mmap_event		mmap;
-	struct comm_event		comm;
-	struct fork_event		fork;
-	struct period_event		period;
-	struct lost_event		lost;
-} event_t;
-
-static LIST_HEAD(dsos);
-static struct dso *kernel_dso;
-static struct dso *vdso;
-
-static void dsos__add(struct dso *dso)
-{
-	list_add_tail(&dso->node, &dsos);
-}
-
-static struct dso *dsos__find(const char *name)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, &dsos, node)
-		if (strcmp(pos->name, name) == 0)
-			return pos;
-	return NULL;
-}
-
-static struct dso *dsos__findnew(const char *name)
-{
-	struct dso *dso = dsos__find(name);
-	int nr;
-
-	if (dso)
-		return dso;
-
-	dso = dso__new(name, 0);
-	if (!dso)
-		goto out_delete_dso;
-
-	nr = dso__load(dso, NULL, verbose);
-	if (nr < 0) {
-		eprintf("Failed to open: %s\n", name);
-		goto out_delete_dso;
-	}
-	if (!nr)
-		eprintf("No symbols found in: %s, maybe install a debug package?\n", name);
-
-	dsos__add(dso);
-
-	return dso;
-
-out_delete_dso:
-	dso__delete(dso);
-	return NULL;
-}
-
-static void dsos__fprintf(FILE *fp)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, &dsos, node)
-		dso__fprintf(pos, fp);
-}
-
-static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip)
-{
-	return dso__find_symbol(kernel_dso, ip);
-}
-
-static int load_kernel(void)
-{
-	int err;
-
-	kernel_dso = dso__new("[kernel]", 0);
-	if (!kernel_dso)
-		return -1;
-
-	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose);
-	if (err) {
-		dso__delete(kernel_dso);
-		kernel_dso = NULL;
-	} else
-		dsos__add(kernel_dso);
-
-	vdso = dso__new("[vdso]", 0);
-	if (!vdso)
-		return -1;
+static char		callchain_default_opt[] = "fractal,0.5";
 
-	vdso->find_symbol = vdso__find_symbol;
+static int		callchain;
 
-	dsos__add(vdso);
+static char		__cwd[PATH_MAX];
+static char		*cwd = __cwd;
+static int		cwdlen;
 
-	return err;
-}
-
-static char __cwd[PATH_MAX];
-static char *cwd = __cwd;
-static int cwdlen;
-
-static int strcommon(const char *pathname)
-{
-	int n = 0;
+static struct rb_root	threads;
+static struct thread	*last_match;
 
-	while (pathname[n] == cwd[n] && n < cwdlen)
-		++n;
-
-	return n;
-}
+static struct perf_header *header;
 
-struct map {
-	struct list_head node;
-	u64	 start;
-	u64	 end;
-	u64	 pgoff;
-	u64	 (*map_ip)(struct map *, u64);
-	struct dso	 *dso;
+static
+struct callchain_param	callchain_param = {
+	.mode	= CHAIN_GRAPH_REL,
+	.min_percent = 0.5
 };
 
-static u64 map__map_ip(struct map *map, u64 ip)
-{
-	return ip - map->start + map->pgoff;
-}
-
-static u64 vdso__map_ip(struct map *map, u64 ip)
-{
-	return ip;
-}
-
-static inline int is_anon_memory(const char *filename)
-{
-     return strcmp(filename, "//anon") == 0;
-}
+static u64		sample_type;
 
-static struct map *map__new(struct mmap_event *event)
+static int repsep_fprintf(FILE *fp, const char *fmt, ...)
 {
-	struct map *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		const char *filename = event->filename;
-		char newfilename[PATH_MAX];
-		int anon;
-
-		if (cwd) {
-			int n = strcommon(filename);
-
-			if (n == cwdlen) {
-				snprintf(newfilename, sizeof(newfilename),
-					 ".%s", filename + n);
-				filename = newfilename;
+	int n;
+	va_list ap;
+
+	va_start(ap, fmt);
+	if (!field_sep)
+		n = vfprintf(fp, fmt, ap);
+	else {
+		char *bf = NULL;
+		n = vasprintf(&bf, fmt, ap);
+		if (n > 0) {
+			char *sep = bf;
+
+			while (1) {
+				sep = strchr(sep, *field_sep);
+				if (sep == NULL)
+					break;
+				*sep = '.';
 			}
 		}
-
-		anon = is_anon_memory(filename);
-
-		if (anon) {
-			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid);
-			filename = newfilename;
-		}
-
-		self->start = event->start;
-		self->end   = event->start + event->len;
-		self->pgoff = event->pgoff;
-
-		self->dso = dsos__findnew(filename);
-		if (self->dso == NULL)
-			goto out_delete;
-
-		if (self->dso == vdso || anon)
-			self->map_ip = vdso__map_ip;
-		else
-			self->map_ip = map__map_ip;
-	}
-	return self;
-out_delete:
-	free(self);
-	return NULL;
-}
-
-static struct map *map__clone(struct map *self)
-{
-	struct map *map = malloc(sizeof(*self));
-
-	if (!map)
-		return NULL;
-
-	memcpy(map, self, sizeof(*self));
-
-	return map;
-}
-
-static int map__overlap(struct map *l, struct map *r)
-{
-	if (l->start > r->start) {
-		struct map *t = l;
-		l = r;
-		r = t;
-	}
-
-	if (l->end > r->start)
-		return 1;
-
-	return 0;
-}
-
-static size_t map__fprintf(struct map *self, FILE *fp)
-{
-	return fprintf(fp, " %Lx-%Lx %Lx %s\n",
-		       self->start, self->end, self->pgoff, self->dso->name);
-}
-
-
-struct thread {
-	struct rb_node	 rb_node;
-	struct list_head maps;
-	pid_t		 pid;
-	char		 *comm;
-};
-
-static struct thread *thread__new(pid_t pid)
-{
-	struct thread *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		self->pid = pid;
-		self->comm = malloc(32);
-		if (self->comm)
-			snprintf(self->comm, 32, ":%d", self->pid);
-		INIT_LIST_HEAD(&self->maps);
+		fputs(bf, fp);
+		free(bf);
 	}
-
-	return self;
-}
-
-static int thread__set_comm(struct thread *self, const char *comm)
-{
-	if (self->comm)
-		free(self->comm);
-	self->comm = strdup(comm);
-	return self->comm ? 0 : -ENOMEM;
-}
-
-static size_t thread__fprintf(struct thread *self, FILE *fp)
-{
-	struct map *pos;
-	size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm);
-
-	list_for_each_entry(pos, &self->maps, node)
-		ret += map__fprintf(pos, fp);
-
-	return ret;
-}
-
-
-static struct rb_root threads;
-static struct thread *last_match;
-
-static struct thread *threads__findnew(pid_t pid)
-{
-	struct rb_node **p = &threads.rb_node;
-	struct rb_node *parent = NULL;
-	struct thread *th;
-
-	/*
-	 * Font-end cache - PID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
-	if (last_match && last_match->pid == pid)
-		return last_match;
-
-	while (*p != NULL) {
-		parent = *p;
-		th = rb_entry(parent, struct thread, rb_node);
-
-		if (th->pid == pid) {
-			last_match = th;
-			return th;
-		}
-
-		if (pid < th->pid)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	th = thread__new(pid);
-	if (th != NULL) {
-		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &threads);
-		last_match = th;
-	}
-
-	return th;
-}
-
-static void thread__insert_map(struct thread *self, struct map *map)
-{
-	struct map *pos, *tmp;
-
-	list_for_each_entry_safe(pos, tmp, &self->maps, node) {
-		if (map__overlap(pos, map)) {
-			list_del_init(&pos->node);
-			/* XXX leaks dsos */
-			free(pos);
-		}
-	}
-
-	list_add_tail(&map->node, &self->maps);
-}
-
-static int thread__fork(struct thread *self, struct thread *parent)
-{
-	struct map *map;
-
-	if (self->comm)
-		free(self->comm);
-	self->comm = strdup(parent->comm);
-	if (!self->comm)
-		return -ENOMEM;
-
-	list_for_each_entry(map, &parent->maps, node) {
-		struct map *new = map__clone(map);
-		if (!new)
-			return -ENOMEM;
-		thread__insert_map(self, new);
-	}
-
-	return 0;
-}
-
-static struct map *thread__find_map(struct thread *self, u64 ip)
-{
-	struct map *pos;
-
-	if (self == NULL)
-		return NULL;
-
-	list_for_each_entry(pos, &self->maps, node)
-		if (ip >= pos->start && ip <= pos->end)
-			return pos;
-
-	return NULL;
+	va_end(ap);
+	return n;
 }
 
-static size_t threads__fprintf(FILE *fp)
-{
-	size_t ret = 0;
-	struct rb_node *nd;
-
-	for (nd = rb_first(&threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
-
-		ret += thread__fprintf(pos, fp);
-	}
-
-	return ret;
-}
+static unsigned int dsos__col_width,
+		    comms__col_width,
+		    threads__col_width;
 
 /*
  * histogram, sorted on item, collects counts
@@ -464,17 +119,19 @@ static size_t threads__fprintf(FILE *fp)
 static struct rb_root hist;
 
 struct hist_entry {
-	struct rb_node	 rb_node;
-
-	struct thread	 *thread;
-	struct map	 *map;
-	struct dso	 *dso;
-	struct symbol	 *sym;
-	struct symbol	 *parent;
-	u64		 ip;
-	char		 level;
-
-	u64		 count;
+	struct rb_node		rb_node;
+
+	struct thread		*thread;
+	struct map		*map;
+	struct dso		*dso;
+	struct symbol		*sym;
+	struct symbol		*parent;
+	u64			ip;
+	char			level;
+	struct callchain_node	callchain;
+	struct rb_root		sorted_chain;
+
+	u64			count;
 };
 
 /*
@@ -484,11 +141,13 @@ struct hist_entry {
 struct sort_entry {
 	struct list_head list;
 
-	char *header;
+	const char *header;
 
 	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
 	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
-	size_t	(*print)(FILE *fp, struct hist_entry *);
+	size_t	(*print)(FILE *fp, struct hist_entry *, unsigned int width);
+	unsigned int *width;
+	bool	elide;
 };
 
 static int64_t cmp_null(void *l, void *r)
@@ -510,15 +169,17 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static size_t
-sort__thread_print(FILE *fp, struct hist_entry *self)
+sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width)
 {
-	return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid);
+	return repsep_fprintf(fp, "%*s:%5d", width - 6,
+			      self->thread->comm ?: "", self->thread->pid);
 }
 
 static struct sort_entry sort_thread = {
-	.header = "         Command:  Pid",
+	.header = "Command:  Pid",
 	.cmp	= sort__thread_cmp,
 	.print	= sort__thread_print,
+	.width	= &threads__col_width,
 };
 
 /* --sort comm */
@@ -542,16 +203,17 @@ sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 }
 
 static size_t
-sort__comm_print(FILE *fp, struct hist_entry *self)
+sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
 {
-	return fprintf(fp, "%16s", self->thread->comm);
+	return repsep_fprintf(fp, "%*s", width, self->thread->comm);
 }
 
 static struct sort_entry sort_comm = {
-	.header		= "         Command",
+	.header		= "Command",
 	.cmp		= sort__comm_cmp,
 	.collapse	= sort__comm_collapse,
 	.print		= sort__comm_print,
+	.width		= &comms__col_width,
 };
 
 /* --sort dso */
@@ -569,18 +231,19 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static size_t
-sort__dso_print(FILE *fp, struct hist_entry *self)
+sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width)
 {
 	if (self->dso)
-		return fprintf(fp, "%-25s", self->dso->name);
+		return repsep_fprintf(fp, "%-*s", width, self->dso->name);
 
-	return fprintf(fp, "%016llx         ", (u64)self->ip);
+	return repsep_fprintf(fp, "%*llx", width, (u64)self->ip);
 }
 
 static struct sort_entry sort_dso = {
-	.header = "Shared Object            ",
+	.header = "Shared Object",
 	.cmp	= sort__dso_cmp,
 	.print	= sort__dso_print,
+	.width	= &dsos__col_width,
 };
 
 /* --sort symbol */
@@ -600,18 +263,23 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static size_t
-sort__sym_print(FILE *fp, struct hist_entry *self)
+sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used)
 {
 	size_t ret = 0;
 
 	if (verbose)
-		ret += fprintf(fp, "%#018llx  ", (u64)self->ip);
+		ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip,
+				      dso__symtab_origin(self->dso));
 
+	ret += repsep_fprintf(fp, "[%c] ", self->level);
 	if (self->sym) {
-		ret += fprintf(fp, "[%c] %s",
-			self->dso == kernel_dso ? 'k' : '.', self->sym->name);
+		ret += repsep_fprintf(fp, "%s", self->sym->name);
+
+		if (self->sym->module)
+			ret += repsep_fprintf(fp, "\t[%s]",
+					     self->sym->module->name);
 	} else {
-		ret += fprintf(fp, "%#016llx", (u64)self->ip);
+		ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip);
 	}
 
 	return ret;
@@ -638,26 +306,26 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static size_t
-sort__parent_print(FILE *fp, struct hist_entry *self)
+sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width)
 {
-	size_t ret = 0;
-
-	ret += fprintf(fp, "%-20s", self->parent ? self->parent->name : "[other]");
-
-	return ret;
+	return repsep_fprintf(fp, "%-*s", width,
+			      self->parent ? self->parent->name : "[other]");
 }
 
+static unsigned int parent_symbol__col_width;
+
 static struct sort_entry sort_parent = {
-	.header = "Parent symbol       ",
+	.header = "Parent symbol",
 	.cmp	= sort__parent_cmp,
 	.print	= sort__parent_print,
+	.width	= &parent_symbol__col_width,
 };
 
 static int sort__need_collapse = 0;
 static int sort__has_parent = 0;
 
 struct sort_dimension {
-	char			*name;
+	const char		*name;
 	struct sort_entry	*entry;
 	int			taken;
 };
@@ -672,9 +340,9 @@ static struct sort_dimension sort_dimensions[] = {
 
 static LIST_HEAD(hist_entry__sort_list);
 
-static int sort_dimension__add(char *tok)
+static int sort_dimension__add(const char *tok)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
 		struct sort_dimension *sd = &sort_dimensions[i];
@@ -744,6 +412,205 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	return cmp;
 }
 
+static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask)
+{
+	int i;
+	size_t ret = 0;
+
+	ret += fprintf(fp, "%s", "                ");
+
+	for (i = 0; i < depth; i++)
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|          ");
+		else
+			ret += fprintf(fp, "           ");
+
+	ret += fprintf(fp, "\n");
+
+	return ret;
+}
+static size_t
+ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
+		       int depth_mask, int count, u64 total_samples,
+		       int hits)
+{
+	int i;
+	size_t ret = 0;
+
+	ret += fprintf(fp, "%s", "                ");
+	for (i = 0; i < depth; i++) {
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|");
+		else
+			ret += fprintf(fp, " ");
+		if (!count && i == depth - 1) {
+			double percent;
+
+			percent = hits * 100.0 / total_samples;
+			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+		} else
+			ret += fprintf(fp, "%s", "          ");
+	}
+	if (chain->sym)
+		ret += fprintf(fp, "%s\n", chain->sym->name);
+	else
+		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
+
+	return ret;
+}
+
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+	if (!rem_sq_bracket) {
+		fprintf(stderr, "Not enough memory to display remaining hits\n");
+		return;
+	}
+
+	strcpy(rem_sq_bracket->name, "[...]");
+	rem_hits.sym = rem_sq_bracket;
+}
+
+static size_t
+callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+			u64 total_samples, int depth, int depth_mask)
+{
+	struct rb_node *node, *next;
+	struct callchain_node *child;
+	struct callchain_list *chain;
+	int new_depth_mask = depth_mask;
+	u64 new_total;
+	u64 remaining;
+	size_t ret = 0;
+	int i;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = self->children_hit;
+	else
+		new_total = total_samples;
+
+	remaining = new_total;
+
+	node = rb_first(&self->rb_root);
+	while (node) {
+		u64 cumul;
+
+		child = rb_entry(node, struct callchain_node, rb_node);
+		cumul = cumul_hits(child);
+		remaining -= cumul;
+
+		/*
+		 * The depth mask manages the output of pipes that show
+		 * the depth. We don't want to keep the pipes of the current
+		 * level for the last child of this depth.
+		 * Except if we have remaining filtered hits. They will
+		 * supersede the last child
+		 */
+		next = rb_next(node);
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
+			new_depth_mask &= ~(1 << (depth - 1));
+
+		/*
+		 * But we keep the older depth mask for the line seperator
+		 * to keep the level link until we reach the last child
+		 */
+		ret += ipchain__fprintf_graph_line(fp, depth, depth_mask);
+		i = 0;
+		list_for_each_entry(chain, &child->val, list) {
+			if (chain->ip >= PERF_CONTEXT_MAX)
+				continue;
+			ret += ipchain__fprintf_graph(fp, chain, depth,
+						      new_depth_mask, i++,
+						      new_total,
+						      cumul);
+		}
+		ret += callchain__fprintf_graph(fp, child, new_total,
+						depth + 1,
+						new_depth_mask | (1 << depth));
+		node = next;
+	}
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL &&
+		remaining && remaining != new_total) {
+
+		if (!rem_sq_bracket)
+			return ret;
+
+		new_depth_mask &= ~(1 << (depth - 1));
+
+		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+					      new_depth_mask, 0, new_total,
+					      remaining);
+	}
+
+	return ret;
+}
+
+static size_t
+callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
+			u64 total_samples)
+{
+	struct callchain_list *chain;
+	size_t ret = 0;
+
+	if (!self)
+		return 0;
+
+	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
+
+
+	list_for_each_entry(chain, &self->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->sym)
+			ret += fprintf(fp, "                %s\n", chain->sym->name);
+		else
+			ret += fprintf(fp, "                %p\n",
+					(void *)(long)chain->ip);
+	}
+
+	return ret;
+}
+
+static size_t
+hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
+			      u64 total_samples)
+{
+	struct rb_node *rb_node;
+	struct callchain_node *chain;
+	size_t ret = 0;
+
+	rb_node = rb_first(&self->sorted_chain);
+	while (rb_node) {
+		double percent;
+
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		percent = chain->hit * 100.0 / total_samples;
+		switch (callchain_param.mode) {
+		case CHAIN_FLAT:
+			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
+						     percent);
+			ret += callchain__fprintf_flat(fp, chain, total_samples);
+			break;
+		case CHAIN_GRAPH_ABS: /* Falldown */
+		case CHAIN_GRAPH_REL:
+			ret += callchain__fprintf_graph(fp, chain,
+							total_samples, 1, 1);
+		case CHAIN_NONE:
+		default:
+			break;
+		}
+		ret += fprintf(fp, "\n");
+		rb_node = rb_next(rb_node);
+	}
+
+	return ret;
+}
+
+
 static size_t
 hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples)
 {
@@ -753,37 +620,33 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples)
 	if (exclude_other && !self->parent)
 		return 0;
 
-	if (total_samples) {
-		double percent = self->count * 100.0 / total_samples;
-		char *color = PERF_COLOR_NORMAL;
-
-		/*
-		 * We color high-overhead entries in red, mid-overhead
-		 * entries in green - and keep the low overhead places
-		 * normal:
-		 */
-		if (percent >= 5.0) {
-			color = PERF_COLOR_RED;
-		} else {
-			if (percent >= 0.5)
-				color = PERF_COLOR_GREEN;
-		}
+	if (total_samples)
+		ret = percent_color_fprintf(fp,
+					    field_sep ? "%.2f" : "   %6.2f%%",
+					(self->count * 100.0) / total_samples);
+	else
+		ret = fprintf(fp, field_sep ? "%lld" : "%12lld ", self->count);
 
-		ret = color_fprintf(fp, color, "   %6.2f%%",
-				(self->count * 100.0) / total_samples);
-	} else
-		ret = fprintf(fp, "%12Ld ", self->count);
+	if (show_nr_samples) {
+		if (field_sep)
+			fprintf(fp, "%c%lld", *field_sep, self->count);
+		else
+			fprintf(fp, "%11lld", self->count);
+	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (exclude_other && (se == &sort_parent))
+		if (se->elide)
 			continue;
 
-		fprintf(fp, "  ");
-		ret += se->print(fp, self);
+		fprintf(fp, "%s", field_sep ?: "  ");
+		ret += se->print(fp, self, se->width ? *se->width : 0);
 	}
 
 	ret += fprintf(fp, "\n");
 
+	if (callchain)
+		hist_entry_callchain__fprintf(fp, self, total_samples);
+
 	return ret;
 }
 
@@ -791,13 +654,53 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples)
  *
  */
 
+static void dso__calc_col_width(struct dso *self)
+{
+	if (!col_width_list_str && !field_sep &&
+	    (!dso_list || strlist__has_entry(dso_list, self->name))) {
+		unsigned int slen = strlen(self->name);
+		if (slen > dsos__col_width)
+			dsos__col_width = slen;
+	}
+
+	self->slen_calculated = 1;
+}
+
+static void thread__comm_adjust(struct thread *self)
+{
+	char *comm = self->comm;
+
+	if (!col_width_list_str && !field_sep &&
+	    (!comm_list || strlist__has_entry(comm_list, comm))) {
+		unsigned int slen = strlen(comm);
+
+		if (slen > comms__col_width) {
+			comms__col_width = slen;
+			threads__col_width = slen + 6;
+		}
+	}
+}
+
+static int thread__set_comm_adjust(struct thread *self, const char *comm)
+{
+	int ret = thread__set_comm(self, comm);
+
+	if (ret)
+		return ret;
+
+	thread__comm_adjust(self);
+
+	return 0;
+}
+
+
 static struct symbol *
 resolve_symbol(struct thread *thread, struct map **mapp,
 	       struct dso **dsop, u64 *ipp)
 {
 	struct dso *dso = dsop ? *dsop : NULL;
 	struct map *map = mapp ? *mapp : NULL;
-	uint64_t ip = *ipp;
+	u64 ip = *ipp;
 
 	if (!thread)
 		return NULL;
@@ -810,11 +713,18 @@ resolve_symbol(struct thread *thread, struct map **mapp,
 
 	map = thread__find_map(thread, ip);
 	if (map != NULL) {
+		/*
+		 * We have to do this here as we may have a dso
+		 * with no symbol hit that has a name longer than
+		 * the ones with symbols sampled.
+		 */
+		if (!sort_dso.elide && !map->dso->slen_calculated)
+			dso__calc_col_width(map->dso);
+
 		if (mapp)
 			*mapp = map;
 got_map:
 		ip = map->map_ip(map, ip);
-		*ipp  = ip;
 
 		dso = map->dso;
 	} else {
@@ -827,7 +737,9 @@ got_map:
 		if ((long long)ip < 0)
 		dso = kernel_dso;
 	}
-	dprintf(" ...... dso: %s\n", dso ? dso->name : "<not found>");
+	dump_printf(" ...... dso: %s\n", dso ? dso->name : "<not found>");
+	dump_printf(" ...... map: %Lx -> %Lx\n", *ipp, ip);
+	*ipp  = ip;
 
 	if (dsop)
 		*dsop = dso;
@@ -846,6 +758,58 @@ static int call__match(struct symbol *sym)
 	return 0;
 }
 
+static struct symbol **
+resolve_callchain(struct thread *thread, struct map *map __used,
+		    struct ip_callchain *chain, struct hist_entry *entry)
+{
+	u64 context = PERF_CONTEXT_MAX;
+	struct symbol **syms = NULL;
+	unsigned int i;
+
+	if (callchain) {
+		syms = calloc(chain->nr, sizeof(*syms));
+		if (!syms) {
+			fprintf(stderr, "Can't allocate memory for symbols\n");
+			exit(-1);
+		}
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip = chain->ips[i];
+		struct dso *dso = NULL;
+		struct symbol *sym;
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			context = ip;
+			continue;
+		}
+
+		switch (context) {
+		case PERF_CONTEXT_HV:
+			dso = hypervisor_dso;
+			break;
+		case PERF_CONTEXT_KERNEL:
+			dso = kernel_dso;
+			break;
+		default:
+			break;
+		}
+
+		sym = resolve_symbol(thread, NULL, &dso, &ip);
+
+		if (sym) {
+			if (sort__has_parent && call__match(sym) &&
+			    !entry->parent)
+				entry->parent = sym;
+			if (!callchain)
+				break;
+			syms[i] = sym;
+		}
+	}
+
+	return syms;
+}
+
 /*
  * collect histogram counts
  */
@@ -858,6 +822,7 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 	struct rb_node **p = &hist.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
+	struct symbol **syms = NULL;
 	struct hist_entry entry = {
 		.thread	= thread,
 		.map	= map,
@@ -867,39 +832,12 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 		.level	= level,
 		.count	= count,
 		.parent = NULL,
+		.sorted_chain = RB_ROOT
 	};
 	int cmp;
 
-	if (sort__has_parent && chain) {
-		u64 context = PERF_CONTEXT_MAX;
-		int i;
-
-		for (i = 0; i < chain->nr; i++) {
-			u64 ip = chain->ips[i];
-			struct dso *dso = NULL;
-			struct symbol *sym;
-
-			if (ip >= PERF_CONTEXT_MAX) {
-				context = ip;
-				continue;
-			}
-
-			switch (context) {
-			case PERF_CONTEXT_KERNEL:
-				dso = kernel_dso;
-				break;
-			default:
-				break;
-			}
-
-			sym = resolve_symbol(thread, NULL, &dso, &ip);
-
-			if (sym && call__match(sym)) {
-				entry.parent = sym;
-				break;
-			}
-		}
-	}
+	if ((sort__has_parent || callchain) && chain)
+		syms = resolve_callchain(thread, map, chain, &entry);
 
 	while (*p != NULL) {
 		parent = *p;
@@ -909,6 +847,10 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 
 		if (!cmp) {
 			he->count += count;
+			if (callchain) {
+				append_chain(&he->callchain, chain, syms);
+				free(syms);
+			}
 			return 0;
 		}
 
@@ -922,6 +864,11 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 	if (!he)
 		return -ENOMEM;
 	*he = entry;
+	if (callchain) {
+		callchain_init(&he->callchain);
+		append_chain(&he->callchain, chain, syms);
+		free(syms);
+	}
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, &hist);
 
@@ -992,12 +939,16 @@ static void collapse__resort(void)
 
 static struct rb_root output_hists;
 
-static void output__insert_entry(struct hist_entry *he)
+static void output__insert_entry(struct hist_entry *he, u64 min_callchain_hits)
 {
 	struct rb_node **p = &output_hists.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 
+	if (callchain)
+		callchain_param.sort(&he->sorted_chain, &he->callchain,
+				      min_callchain_hits, &callchain_param);
+
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
@@ -1012,11 +963,14 @@ static void output__insert_entry(struct hist_entry *he)
 	rb_insert_color(&he->rb_node, &output_hists);
 }
 
-static void output__resort(void)
+static void output__resort(u64 total_samples)
 {
 	struct rb_node *next;
 	struct hist_entry *n;
 	struct rb_root *tree = &hist;
+	u64 min_callchain_hits;
+
+	min_callchain_hits = total_samples * (callchain_param.min_percent / 100);
 
 	if (sort__need_collapse)
 		tree = &collapse_hists;
@@ -1028,7 +982,7 @@ static void output__resort(void)
 		next = rb_next(&n->rb_node);
 
 		rb_erase(&n->rb_node, tree);
-		output__insert_entry(n);
+		output__insert_entry(n, min_callchain_hits);
 	}
 }
 
@@ -1038,35 +992,72 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	struct sort_entry *se;
 	struct rb_node *nd;
 	size_t ret = 0;
+	unsigned int width;
+	char *col_width = col_width_list_str;
+	int raw_printing_style;
 
-	fprintf(fp, "\n");
-	fprintf(fp, "#\n");
-	fprintf(fp, "# (%Ld samples)\n", (u64)total_samples);
+	raw_printing_style = !strcmp(pretty_printing_style, "raw");
+
+	init_rem_hits();
+
+	fprintf(fp, "# Samples: %Ld\n", (u64)total_samples);
 	fprintf(fp, "#\n");
 
 	fprintf(fp, "# Overhead");
+	if (show_nr_samples) {
+		if (field_sep)
+			fprintf(fp, "%cSamples", *field_sep);
+		else
+			fputs("  Samples  ", fp);
+	}
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (exclude_other && (se == &sort_parent))
+		if (se->elide)
+			continue;
+		if (field_sep) {
+			fprintf(fp, "%c%s", *field_sep, se->header);
 			continue;
-		fprintf(fp, "  %s", se->header);
+		}
+		width = strlen(se->header);
+		if (se->width) {
+			if (col_width_list_str) {
+				if (col_width) {
+					*se->width = atoi(col_width);
+					col_width = strchr(col_width, ',');
+					if (col_width)
+						++col_width;
+				}
+			}
+			width = *se->width = max(*se->width, width);
+		}
+		fprintf(fp, "  %*s", width, se->header);
 	}
 	fprintf(fp, "\n");
 
+	if (field_sep)
+		goto print_entries;
+
 	fprintf(fp, "# ........");
+	if (show_nr_samples)
+		fprintf(fp, " ..........");
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		int i;
+		unsigned int i;
 
-		if (exclude_other && (se == &sort_parent))
+		if (se->elide)
 			continue;
 
 		fprintf(fp, "  ");
-		for (i = 0; i < strlen(se->header); i++)
+		if (se->width)
+			width = *se->width;
+		else
+			width = strlen(se->header);
+		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
 	fprintf(fp, "\n");
 
 	fprintf(fp, "#\n");
 
+print_entries:
 	for (nd = rb_first(&output_hists); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct hist_entry, rb_node);
 		ret += hist_entry__fprintf(fp, pos, total_samples);
@@ -1075,23 +1066,18 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	if (sort_order == default_sort_order &&
 			parent_pattern == default_parent_pattern) {
 		fprintf(fp, "#\n");
-		fprintf(fp, "# (For more details, try: perf report --sort comm,dso,symbol)\n");
+		fprintf(fp, "# (For a higher level overview, try: perf report --sort comm,dso)\n");
 		fprintf(fp, "#\n");
 	}
 	fprintf(fp, "\n");
 
-	return ret;
-}
+	free(rem_sq_bracket);
 
-static void register_idle_thread(void)
-{
-	struct thread *thread = threads__findnew(0);
+	if (show_threads)
+		perf_read_values_display(fp, &show_threads_values,
+					 raw_printing_style);
 
-	if (thread == NULL ||
-			thread__set_comm(thread, "[idle]")) {
-		fprintf(stderr, "problem inserting idle task.\n");
-		exit(-1);
-	}
+	return ret;
 }
 
 static unsigned long total = 0,
@@ -1115,37 +1101,40 @@ static int validate_chain(struct ip_callchain *chain, event_t *event)
 }
 
 static int
-process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
+process_sample_event(event_t *event, unsigned long offset, unsigned long head)
 {
 	char level;
 	int show = 0;
 	struct dso *dso = NULL;
-	struct thread *thread = threads__findnew(event->ip.pid);
+	struct thread *thread;
 	u64 ip = event->ip.ip;
 	u64 period = 1;
 	struct map *map = NULL;
 	void *more_data = event->ip.__more_data;
 	struct ip_callchain *chain = NULL;
+	int cpumode;
 
-	if (event->header.type & PERF_SAMPLE_PERIOD) {
+	thread = threads__findnew(event->ip.pid, &threads, &last_match);
+
+	if (sample_type & PERF_SAMPLE_PERIOD) {
 		period = *(u64 *)more_data;
 		more_data += sizeof(u64);
 	}
 
-	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n",
+	dump_printf("%p [%p]: PERF_RECORD_SAMPLE (IP, %d): %d/%d: %p period: %Ld\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
 		event->header.misc,
-		event->ip.pid,
+		event->ip.pid, event->ip.tid,
 		(void *)(long)ip,
 		(long long)period);
 
-	if (event->header.type & PERF_SAMPLE_CALLCHAIN) {
-		int i;
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		unsigned int i;
 
 		chain = (void *)more_data;
 
-		dprintf("... chain: nr:%Lu\n", chain->nr);
+		dump_printf("... chain: nr:%Lu\n", chain->nr);
 
 		if (validate_chain(chain, event) < 0) {
 			eprintf("call-chain problem with event, skipping it.\n");
@@ -1154,11 +1143,11 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 
 		if (dump_trace) {
 			for (i = 0; i < chain->nr; i++)
-				dprintf("..... %2d: %016Lx\n", i, chain->ips[i]);
+				dump_printf("..... %2d: %016Lx\n", i, chain->ips[i]);
 		}
 	}
 
-	dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
 	if (thread == NULL) {
 		eprintf("problem processing %d event, skipping it.\n",
@@ -1166,15 +1155,20 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 		return -1;
 	}
 
-	if (event->header.misc & PERF_EVENT_MISC_KERNEL) {
+	if (comm_list && !strlist__has_entry(comm_list, thread->comm))
+		return 0;
+
+	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	if (cpumode == PERF_RECORD_MISC_KERNEL) {
 		show = SHOW_KERNEL;
 		level = 'k';
 
 		dso = kernel_dso;
 
-		dprintf(" ...... dso: %s\n", dso->name);
+		dump_printf(" ...... dso: %s\n", dso->name);
 
-	} else if (event->header.misc & PERF_EVENT_MISC_USER) {
+	} else if (cpumode == PERF_RECORD_MISC_USER) {
 
 		show = SHOW_USER;
 		level = '.';
@@ -1182,12 +1176,22 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 	} else {
 		show = SHOW_HV;
 		level = 'H';
-		dprintf(" ...... dso: [hypervisor]\n");
+
+		dso = hypervisor_dso;
+
+		dump_printf(" ...... dso: [hypervisor]\n");
 	}
 
 	if (show & show_mask) {
 		struct symbol *sym = resolve_symbol(thread, &map, &dso, &ip);
 
+		if (dso_list && (!dso || !dso->name ||
+				 !strlist__has_entry(dso_list, dso->name)))
+			return 0;
+
+		if (sym_list && (!sym || !strlist__has_entry(sym_list, sym->name)))
+			return 0;
+
 		if (hist_entry__add(thread, map, dso, sym, ip, chain, level, period)) {
 			eprintf("problem incrementing symbol count, skipping event\n");
 			return -1;
@@ -1201,20 +1205,23 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 static int
 process_mmap_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	struct thread *thread = threads__findnew(event->mmap.pid);
-	struct map *map = map__new(&event->mmap);
+	struct thread *thread;
+	struct map *map = map__new(&event->mmap, cwd, cwdlen);
+
+	thread = threads__findnew(event->mmap.pid, &threads, &last_match);
 
-	dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n",
+	dump_printf("%p [%p]: PERF_RECORD_MMAP %d/%d: [%p(%p) @ %p]: %s\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
 		event->mmap.pid,
+		event->mmap.tid,
 		(void *)(long)event->mmap.start,
 		(void *)(long)event->mmap.len,
 		(void *)(long)event->mmap.pgoff,
 		event->mmap.filename);
 
 	if (thread == NULL || map == NULL) {
-		dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n");
+		dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
 		return 0;
 	}
 
@@ -1227,16 +1234,18 @@ process_mmap_event(event_t *event, unsigned long offset, unsigned long head)
 static int
 process_comm_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	struct thread *thread = threads__findnew(event->comm.pid);
+	struct thread *thread;
 
-	dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n",
+	thread = threads__findnew(event->comm.pid, &threads, &last_match);
+
+	dump_printf("%p [%p]: PERF_RECORD_COMM: %s:%d\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
 		event->comm.comm, event->comm.pid);
 
 	if (thread == NULL ||
-	    thread__set_comm(thread, event->comm.comm)) {
-		dprintf("problem processing PERF_EVENT_COMM, skipping event.\n");
+	    thread__set_comm_adjust(thread, event->comm.comm)) {
+		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
 	total_comm++;
@@ -1245,18 +1254,33 @@ process_comm_event(event_t *event, unsigned long offset, unsigned long head)
 }
 
 static int
-process_fork_event(event_t *event, unsigned long offset, unsigned long head)
+process_task_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	struct thread *thread = threads__findnew(event->fork.pid);
-	struct thread *parent = threads__findnew(event->fork.ppid);
+	struct thread *thread;
+	struct thread *parent;
+
+	thread = threads__findnew(event->fork.pid, &threads, &last_match);
+	parent = threads__findnew(event->fork.ppid, &threads, &last_match);
 
-	dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n",
+	dump_printf("%p [%p]: PERF_RECORD_%s: (%d:%d):(%d:%d)\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
-		event->fork.pid, event->fork.ppid);
+		event->header.type == PERF_RECORD_FORK ? "FORK" : "EXIT",
+		event->fork.pid, event->fork.tid,
+		event->fork.ppid, event->fork.ptid);
+
+	/*
+	 * A thread clone will have the same PID for both
+	 * parent and child.
+	 */
+	if (thread == parent)
+		return 0;
+
+	if (event->header.type == PERF_RECORD_EXIT)
+		return 0;
 
 	if (!thread || !parent || thread__fork(thread, parent)) {
-		dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
+		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		return -1;
 	}
 	total_fork++;
@@ -1265,22 +1289,9 @@ process_fork_event(event_t *event, unsigned long offset, unsigned long head)
 }
 
 static int
-process_period_event(event_t *event, unsigned long offset, unsigned long head)
-{
-	dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n",
-		(void *)(offset + head),
-		(void *)(long)(event->header.size),
-		event->period.time,
-		event->period.id,
-		event->period.sample_period);
-
-	return 0;
-}
-
-static int
 process_lost_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	dprintf("%p [%p]: PERF_EVENT_LOST: id:%Ld: lost:%Ld\n",
+	dump_printf("%p [%p]: PERF_RECORD_LOST: id:%Ld: lost:%Ld\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
 		event->lost.id,
@@ -1291,40 +1302,33 @@ process_lost_event(event_t *event, unsigned long offset, unsigned long head)
 	return 0;
 }
 
-static void trace_event(event_t *event)
+static int
+process_read_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	unsigned char *raw_event = (void *)event;
-	char *color = PERF_COLOR_BLUE;
-	int i, j;
-
-	if (!dump_trace)
-		return;
-
-	dprintf(".");
-	cdprintf("\n. ... raw event: size %d bytes\n", event->header.size);
+	struct perf_event_attr *attr;
+
+	attr = perf_header__find_attr(event->read.id, header);
+
+	if (show_threads) {
+		const char *name = attr ? __event_name(attr->type, attr->config)
+				   : "unknown";
+		perf_read_values_add_value(&show_threads_values,
+					   event->read.pid, event->read.tid,
+					   event->read.id,
+					   name,
+					   event->read.value);
+	}
 
-	for (i = 0; i < event->header.size; i++) {
-		if ((i & 15) == 0) {
-			dprintf(".");
-			cdprintf("  %04x: ", i);
-		}
+	dump_printf("%p [%p]: PERF_RECORD_READ: %d %d %s %Lu\n",
+			(void *)(offset + head),
+			(void *)(long)(event->header.size),
+			event->read.pid,
+			event->read.tid,
+			attr ? __event_name(attr->type, attr->config)
+			     : "FAIL",
+			event->read.value);
 
-		cdprintf(" %02x", raw_event[i]);
-
-		if (((i & 15) == 15) || i == event->header.size-1) {
-			cdprintf("  ");
-			for (j = 0; j < 15-(i & 15); j++)
-				cdprintf("   ");
-			for (j = 0; j < (i & 15); j++) {
-				if (isprint(raw_event[i-15+j]))
-					cdprintf("%c", raw_event[i-15+j]);
-				else
-					cdprintf(".");
-			}
-			cdprintf("\n");
-		}
-	}
-	dprintf(".\n");
+	return 0;
 }
 
 static int
@@ -1332,31 +1336,32 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 {
 	trace_event(event);
 
-	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW)
-		return process_overflow_event(event, offset, head);
-
 	switch (event->header.type) {
-	case PERF_EVENT_MMAP:
+	case PERF_RECORD_SAMPLE:
+		return process_sample_event(event, offset, head);
+
+	case PERF_RECORD_MMAP:
 		return process_mmap_event(event, offset, head);
 
-	case PERF_EVENT_COMM:
+	case PERF_RECORD_COMM:
 		return process_comm_event(event, offset, head);
 
-	case PERF_EVENT_FORK:
-		return process_fork_event(event, offset, head);
-
-	case PERF_EVENT_PERIOD:
-		return process_period_event(event, offset, head);
+	case PERF_RECORD_FORK:
+	case PERF_RECORD_EXIT:
+		return process_task_event(event, offset, head);
 
-	case PERF_EVENT_LOST:
+	case PERF_RECORD_LOST:
 		return process_lost_event(event, offset, head);
 
+	case PERF_RECORD_READ:
+		return process_read_event(event, offset, head);
+
 	/*
 	 * We dont process them right now but they are fine:
 	 */
 
-	case PERF_EVENT_THROTTLE:
-	case PERF_EVENT_UNTHROTTLE:
+	case PERF_RECORD_THROTTLE:
+	case PERF_RECORD_UNTHROTTLE:
 		return 0;
 
 	default:
@@ -1366,19 +1371,22 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 	return 0;
 }
 
-static struct perf_file_header		file_header;
-
 static int __cmd_report(void)
 {
 	int ret, rc = EXIT_FAILURE;
 	unsigned long offset = 0;
-	unsigned long head = sizeof(file_header);
-	struct stat stat;
+	unsigned long head, shift;
+	struct stat input_stat;
+	struct thread *idle;
 	event_t *event;
 	uint32_t size;
 	char *buf;
 
-	register_idle_thread();
+	idle = register_idle_thread(&threads, &last_match);
+	thread__comm_adjust(idle);
+
+	if (show_threads)
+		perf_read_values_init(&show_threads_values);
 
 	input = open(input_name, O_RDONLY);
 	if (input < 0) {
@@ -1389,26 +1397,47 @@ static int __cmd_report(void)
 		exit(-1);
 	}
 
-	ret = fstat(input, &stat);
+	ret = fstat(input, &input_stat);
 	if (ret < 0) {
 		perror("failed to stat file");
 		exit(-1);
 	}
 
-	if (!stat.st_size) {
+	if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) {
+		fprintf(stderr, "file: %s not owned by current user or root\n", input_name);
+		exit(-1);
+	}
+
+	if (!input_stat.st_size) {
 		fprintf(stderr, "zero-sized file, nothing to do!\n");
 		exit(0);
 	}
 
-	if (read(input, &file_header, sizeof(file_header)) == -1) {
-		perror("failed to read file headers");
-		exit(-1);
-	}
+	header = perf_header__read(input);
+	head = header->data_offset;
 
-	if (sort__has_parent &&
-	    !(file_header.sample_type & PERF_SAMPLE_CALLCHAIN)) {
-		fprintf(stderr, "selected --sort parent, but no callchain data\n");
-		exit(-1);
+	sample_type = perf_header__sample_type(header);
+
+	if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+		if (sort__has_parent) {
+			fprintf(stderr, "selected --sort parent, but no"
+					" callchain data. Did you call"
+					" perf record without -g?\n");
+			exit(-1);
+		}
+		if (callchain) {
+			fprintf(stderr, "selected -g but no callchain data."
+					" Did you call perf record without"
+					" -g?\n");
+			exit(-1);
+		}
+	} else if (callchain_param.mode != CHAIN_NONE && !callchain) {
+			callchain = 1;
+			if (register_callchain_param(&callchain_param) < 0) {
+				fprintf(stderr, "Can't register callchain"
+						" params\n");
+				exit(-1);
+			}
 	}
 
 	if (load_kernel() < 0) {
@@ -1426,6 +1455,11 @@ static int __cmd_report(void)
 		cwd = NULL;
 		cwdlen = 0;
 	}
+
+	shift = page_size * (head / page_size);
+	offset += shift;
+	head -= shift;
+
 remap:
 	buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ,
 			   MAP_SHARED, input, offset);
@@ -1442,11 +1476,12 @@ more:
 		size = 8;
 
 	if (head + event->header.size >= page_size * mmap_window) {
-		unsigned long shift = page_size * (head / page_size);
-		int ret;
+		int munmap_ret;
 
-		ret = munmap(buf, page_size * mmap_window);
-		assert(ret == 0);
+		shift = page_size * (head / page_size);
+
+		munmap_ret = munmap(buf, page_size * mmap_window);
+		assert(munmap_ret == 0);
 
 		offset += shift;
 		head -= shift;
@@ -1455,14 +1490,14 @@ more:
 
 	size = event->header.size;
 
-	dprintf("\n%p [%p]: event: %d\n",
+	dump_printf("\n%p [%p]: event: %d\n",
 			(void *)(offset + head),
 			(void *)(long)event->header.size,
 			event->header.type);
 
 	if (!size || process_event(event, offset, head) < 0) {
 
-		dprintf("%p [%p]: skipping unknown header type: %d\n",
+		dump_printf("%p [%p]: skipping unknown header type: %d\n",
 			(void *)(offset + head),
 			(void *)(long)(event->header.size),
 			event->header.type);
@@ -1482,39 +1517,95 @@ more:
 
 	head += size;
 
-	if (offset + head >= sizeof(file_header) + file_header.data_size)
+	if (offset + head >= header->data_offset + header->data_size)
 		goto done;
 
-	if (offset + head < stat.st_size)
+	if (offset + head < (unsigned long)input_stat.st_size)
 		goto more;
 
 done:
 	rc = EXIT_SUCCESS;
 	close(input);
 
-	dprintf("      IP events: %10ld\n", total);
-	dprintf("    mmap events: %10ld\n", total_mmap);
-	dprintf("    comm events: %10ld\n", total_comm);
-	dprintf("    fork events: %10ld\n", total_fork);
-	dprintf("    lost events: %10ld\n", total_lost);
-	dprintf(" unknown events: %10ld\n", total_unknown);
+	dump_printf("      IP events: %10ld\n", total);
+	dump_printf("    mmap events: %10ld\n", total_mmap);
+	dump_printf("    comm events: %10ld\n", total_comm);
+	dump_printf("    fork events: %10ld\n", total_fork);
+	dump_printf("    lost events: %10ld\n", total_lost);
+	dump_printf(" unknown events: %10ld\n", total_unknown);
 
 	if (dump_trace)
 		return 0;
 
 	if (verbose >= 3)
-		threads__fprintf(stdout);
+		threads__fprintf(stdout, &threads);
 
 	if (verbose >= 2)
 		dsos__fprintf(stdout);
 
 	collapse__resort();
-	output__resort();
+	output__resort(total);
 	output__fprintf(stdout, total);
 
+	if (show_threads)
+		perf_read_values_destroy(&show_threads_values);
+
 	return rc;
 }
 
+static int
+parse_callchain_opt(const struct option *opt __used, const char *arg,
+		    int unset __used)
+{
+	char *tok;
+	char *endptr;
+
+	callchain = 1;
+
+	if (!arg)
+		return 0;
+
+	tok = strtok((char *)arg, ",");
+	if (!tok)
+		return -1;
+
+	/* get the output mode */
+	if (!strncmp(tok, "graph", strlen(arg)))
+		callchain_param.mode = CHAIN_GRAPH_ABS;
+
+	else if (!strncmp(tok, "flat", strlen(arg)))
+		callchain_param.mode = CHAIN_FLAT;
+
+	else if (!strncmp(tok, "fractal", strlen(arg)))
+		callchain_param.mode = CHAIN_GRAPH_REL;
+
+	else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		callchain = 0;
+
+		return 0;
+	}
+
+	else
+		return -1;
+
+	/* get the min percentage */
+	tok = strtok(NULL, ",");
+	if (!tok)
+		goto setup;
+
+	callchain_param.min_percent = strtod(tok, &endptr);
+	if (tok == endptr)
+		return -1;
+
+setup:
+	if (register_callchain_param(&callchain_param) < 0) {
+		fprintf(stderr, "Can't register callchain params\n");
+		return -1;
+	}
+	return 0;
+}
+
 static const char * const report_usage[] = {
 	"perf report [<options>] <command>",
 	NULL
@@ -1527,7 +1618,16 @@ static const struct option options[] = {
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
-	OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
+	OPT_STRING('k', "vmlinux", &vmlinux_name, "file", "vmlinux pathname"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('m', "modules", &modules,
+		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
+	OPT_BOOLEAN('n', "show-nr-samples", &show_nr_samples,
+		    "Show a column with the number of samples"),
+	OPT_BOOLEAN('T', "threads", &show_threads,
+		    "Show per-thread event counters"),
+	OPT_STRING(0, "pretty", &pretty_printing_style, "key",
+		   "pretty printing style key: normal raw"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN('P', "full-paths", &full_paths,
@@ -1536,6 +1636,21 @@ static const struct option options[] = {
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &exclude_other,
 		    "Only display entries with parent-match"),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
+		     "Display callchains using output_type and min percent threshold. "
+		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
+	OPT_STRING('d', "dsos", &dso_list_str, "dso[,dso...]",
+		   "only consider symbols in these dsos"),
+	OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]",
+		   "only consider symbols in these comms"),
+	OPT_STRING('S', "symbols", &sym_list_str, "symbol[,symbol...]",
+		   "only consider these symbols"),
+	OPT_STRING('w', "column-widths", &col_width_list_str,
+		   "width[,width...]",
+		   "don't try to adjust column width, use these fixed values"),
+	OPT_STRING('t', "field-separator", &field_sep, "separator",
+		   "separator for columns, no spaces will be added between "
+		   "columns '.' is reserved."),
 	OPT_END()
 };
 
@@ -1554,7 +1669,26 @@ static void setup_sorting(void)
 	free(str);
 }
 
-int cmd_report(int argc, const char **argv, const char *prefix)
+static void setup_list(struct strlist **list, const char *list_str,
+		       struct sort_entry *se, const char *list_name,
+		       FILE *fp)
+{
+	if (list_str) {
+		*list = strlist__new(true, list_str);
+		if (!*list) {
+			fprintf(stderr, "problems parsing %s list\n",
+				list_name);
+			exit(129);
+		}
+		if (strlist__nr_entries(*list) == 1) {
+			fprintf(fp, "# %s: %s\n", list_name,
+				strlist__entry(*list, 0)->s);
+			se->elide = true;
+		}
+	}
+}
+
+int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
 	symbol__init();
 
@@ -1564,9 +1698,10 @@ int cmd_report(int argc, const char **argv, const char *prefix)
 
 	setup_sorting();
 
-	if (parent_pattern != default_parent_pattern)
+	if (parent_pattern != default_parent_pattern) {
 		sort_dimension__add("parent");
-	else
+		sort_parent.elide = 1;
+	} else
 		exclude_other = 0;
 
 	/*
@@ -1577,5 +1712,15 @@ int cmd_report(int argc, const char **argv, const char *prefix)
 
 	setup_pager();
 
+	setup_list(&dso_list, dso_list_str, &sort_dso, "dso", stdout);
+	setup_list(&comm_list, comm_list_str, &sort_comm, "comm", stdout);
+	setup_list(&sym_list, sym_list_str, &sort_sym, "symbol", stdout);
+
+	if (field_sep && *field_sep == '.') {
+		fputs("'.' is the only non valid --field-separator argument\n",
+		      stderr);
+		exit(129);
+	}
+
 	return __cmd_report();
 }