Merge branch 'perfcounters-fixes-for-linus' of...

Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (27 commits)
  perf_counter: Zero dead bytes from ftrace raw samples size alignment
  perf_counter: Subtract the buffer size field from the event record size
  perf_counter: Require CAP_SYS_ADMIN for raw tracepoint data
  perf_counter: Correct PERF_SAMPLE_RAW output
  perf tools: callchain: Fix bad rounding of minimum rate
  perf_counter tools: Fix libbfd detection for systems with libz dependency
  perf: "Longum est iter per praecepta, breve et efficax per exempla"
  perf_counter: Fix a race on perf_counter_ctx
  perf_counter: Fix tracepoint sampling to be part of generic sampling
  perf_counter: Work around gcc warning by initializing tracepoint record unconditionally
  perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode
  perf tools: callchain: Fix 'perf report' display to be callchain by default
  perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains
  perf record: Fix the -A UI for empty or non-existent perf.data
  perf util: Fix do_read() to fail on EOF instead of busy-looping
  perf list: Fix the output to not include tracepoints without an id
  perf_counter/powerpc: Fix oops on cpus without perf_counter hardware support
  perf stat: Fix tool option consistency: rename -S/--scale to -c/--scale
  perf report: Add debug help for the finding of symbol bugs - show the symtab origin (DSO, build-id, kernel, etc)
  perf report: Fix per task mult-counter stat reporting
  ...

arch/powerpc/kernel/perf_counter.c

@@ -518,6 +518,8 @@ void hw_perf_disable(void)
 	struct cpu_hw_counters *cpuhw;
 	unsigned long flags;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 
@@ -572,6 +574,8 @@ void hw_perf_enable(void)
 	int n_lim;
 	int idx;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	if (!cpuhw->disabled) {
@@ -737,6 +741,8 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader,
 	long i, n, n0;
 	struct perf_counter *sub;
 
+	if (!ppmu)
+		return 0;
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	n0 = cpuhw->n_counters;
 	n = collect_events(group_leader, ppmu->n_counter - n0,
@@ -1281,6 +1287,8 @@ void hw_perf_counter_setup(int cpu)
 {
 	struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
 
+	if (!ppmu)
+		return;
 	memset(cpuhw, 0, sizeof(*cpuhw));
 	cpuhw->mmcr[0] = MMCR0_FC;
 }

include/linux/perf_counter.h

@@ -121,7 +121,7 @@ enum perf_counter_sample_format {
 	PERF_SAMPLE_CPU				= 1U << 7,
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
-	PERF_SAMPLE_TP_RECORD			= 1U << 10,
+	PERF_SAMPLE_RAW				= 1U << 10,
 
 	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
 };
@@ -369,6 +369,8 @@ enum perf_event_type {
 	 *
 	 *	{ u64			nr,
 	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 * };
 	 */
 	PERF_EVENT_SAMPLE		= 9,
@@ -414,9 +416,9 @@ struct perf_callchain_entry {
 	__u64				ip[PERF_MAX_STACK_DEPTH];
 };
 
-struct perf_tracepoint_record {
-	int				size;
-	char				*record;
+struct perf_raw_record {
+	u32				size;
+	void				*data;
 };
 
 struct task_struct;
@@ -687,7 +689,7 @@ struct perf_sample_data {
 	struct pt_regs			*regs;
 	u64				addr;
 	u64				period;
-	void				*private;
+	struct perf_raw_record		*raw;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,

include/trace/ftrace.h

@@ -637,12 +637,20 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *	pc = preempt_count();
  *
  *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *	__entry_size = __data_size + sizeof(*entry);
+ *
+ *	// Below we want to get the aligned size by taking into account
+ *	// the u32 field that will later store the buffer size
+ *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *			     sizeof(u64));
+ *	__entry_size -= sizeof(u32);
  *
  *	do {
  *		char raw_data[__entry_size]; <- allocate our sample in the stack
  *		struct trace_entry *ent;
  *
+ *		zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
  *		entry = (struct ftrace_raw_<call> *)raw_data;
  *		ent = &entry->ent;
  *		tracing_generic_entry_update(ent, irq_flags, pc);
@@ -685,12 +693,15 @@ static void ftrace_profile_##call(proto)				\
 	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
-	__entry_size = ALIGN(__data_size + sizeof(*entry), sizeof(u64));\
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
+	__entry_size -= sizeof(u32);					\
 									\
 	do {								\
 		char raw_data[__entry_size];				\
 		struct trace_entry *ent;				\
 									\
+		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;	\
 		entry = (struct ftrace_raw_##call *)raw_data;		\
 		ent = &entry->ent;					\
 		tracing_generic_entry_update(ent, irq_flags, pc);	\

tools/perf/Documentation/perf-examples.txt

+
+		------------------------------
+		****** perf by examples ******
+		------------------------------
+
+[ From an e-mail by Ingo Molnar, http://lkml.org/lkml/2009/8/4/346 ]
+
+
+First, discovery/enumeration of available counters can be done via
+'perf list':
+
+titan:~> perf list
+  [...]
+  kmem:kmalloc                             [Tracepoint event]
+  kmem:kmem_cache_alloc                    [Tracepoint event]
+  kmem:kmalloc_node                        [Tracepoint event]
+  kmem:kmem_cache_alloc_node               [Tracepoint event]
+  kmem:kfree                               [Tracepoint event]
+  kmem:kmem_cache_free                     [Tracepoint event]
+  kmem:mm_page_free_direct                 [Tracepoint event]
+  kmem:mm_pagevec_free                     [Tracepoint event]
+  kmem:mm_page_alloc                       [Tracepoint event]
+  kmem:mm_page_alloc_zone_locked           [Tracepoint event]
+  kmem:mm_page_pcpu_drain                  [Tracepoint event]
+  kmem:mm_page_alloc_extfrag               [Tracepoint event]
+
+Then any (or all) of the above event sources can be activated and
+measured. For example the page alloc/free properties of a 'hackbench
+run' are:
+
+ titan:~> perf stat -e kmem:mm_page_pcpu_drain -e kmem:mm_page_alloc
+ -e kmem:mm_pagevec_free -e kmem:mm_page_free_direct ./hackbench 10
+ Time: 0.575
+
+ Performance counter stats for './hackbench 10':
+
+          13857  kmem:mm_page_pcpu_drain
+          27576  kmem:mm_page_alloc
+           6025  kmem:mm_pagevec_free
+          20934  kmem:mm_page_free_direct
+
+    0.613972165  seconds time elapsed
+
+You can observe the statistical properties as well, by using the
+'repeat the workload N times' feature of perf stat:
+
+ titan:~> perf stat --repeat 5 -e kmem:mm_page_pcpu_drain -e
+   kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
+   kmem:mm_page_free_direct ./hackbench 10
+ Time: 0.627
+ Time: 0.644
+ Time: 0.564
+ Time: 0.559
+ Time: 0.626
+
+ Performance counter stats for './hackbench 10' (5 runs):
+
+          12920  kmem:mm_page_pcpu_drain    ( +-   3.359% )
+          25035  kmem:mm_page_alloc         ( +-   3.783% )
+           6104  kmem:mm_pagevec_free       ( +-   0.934% )
+          18376  kmem:mm_page_free_direct   ( +-   4.941% )
+
+    0.643954516  seconds time elapsed   ( +-   2.363% )
+
+Furthermore, these tracepoints can be used to sample the workload as
+well. For example the page allocations done by a 'git gc' can be
+captured the following way:
+
+ titan:~/git> perf record -f -e kmem:mm_page_alloc -c 1 ./git gc
+ Counting objects: 1148, done.
+ Delta compression using up to 2 threads.
+ Compressing objects: 100% (450/450), done.
+ Writing objects: 100% (1148/1148), done.
+ Total 1148 (delta 690), reused 1148 (delta 690)
+ [ perf record: Captured and wrote 0.267 MB perf.data (~11679 samples) ]
+
+To check which functions generated page allocations:
+
+ titan:~/git> perf report
+ # Samples: 10646
+ #
+ # Overhead          Command               Shared Object
+ # ........  ...............  ..........................
+ #
+    23.57%       git-repack  /lib64/libc-2.5.so
+    21.81%              git  /lib64/libc-2.5.so
+    14.59%              git  ./git
+    11.79%       git-repack  ./git
+     7.12%              git  /lib64/ld-2.5.so
+     3.16%       git-repack  /lib64/libpthread-2.5.so
+     2.09%       git-repack  /bin/bash
+     1.97%               rm  /lib64/libc-2.5.so
+     1.39%               mv  /lib64/ld-2.5.so
+     1.37%               mv  /lib64/libc-2.5.so
+     1.12%       git-repack  /lib64/ld-2.5.so
+     0.95%               rm  /lib64/ld-2.5.so
+     0.90%  git-update-serv  /lib64/libc-2.5.so
+     0.73%  git-update-serv  /lib64/ld-2.5.so
+     0.68%             perf  /lib64/libpthread-2.5.so
+     0.64%       git-repack  /usr/lib64/libz.so.1.2.3
+
+Or to see it on a more finegrained level:
+
+titan:~/git> perf report --sort comm,dso,symbol
+# Samples: 10646
+#
+# Overhead          Command               Shared Object  Symbol
+# ........  ...............  ..........................  ......
+#
+     9.35%       git-repack  ./git                       [.] insert_obj_hash
+     9.12%              git  ./git                       [.] insert_obj_hash
+     7.31%              git  /lib64/libc-2.5.so          [.] memcpy
+     6.34%       git-repack  /lib64/libc-2.5.so          [.] _int_malloc
+     6.24%       git-repack  /lib64/libc-2.5.so          [.] memcpy
+     5.82%       git-repack  /lib64/libc-2.5.so          [.] __GI___fork
+     5.47%              git  /lib64/libc-2.5.so          [.] _int_malloc
+     2.99%              git  /lib64/libc-2.5.so          [.] memset
+
+Furthermore, call-graph sampling can be done too, of page
+allocations - to see precisely what kind of page allocations there
+are:
+
+ titan:~/git> perf record -f -g -e kmem:mm_page_alloc -c 1 ./git gc
+ Counting objects: 1148, done.
+ Delta compression using up to 2 threads.
+ Compressing objects: 100% (450/450), done.
+ Writing objects: 100% (1148/1148), done.
+ Total 1148 (delta 690), reused 1148 (delta 690)
+ [ perf record: Captured and wrote 0.963 MB perf.data (~42069 samples) ]
+
+ titan:~/git> perf report -g
+ # Samples: 10686
+ #
+ # Overhead          Command               Shared Object
+ # ........  ...............  ..........................
+ #
+    23.25%       git-repack  /lib64/libc-2.5.so
+                |
+                |--50.00%-- _int_free
+                |
+                |--37.50%-- __GI___fork
+                |          make_child
+                |
+                |--12.50%-- ptmalloc_unlock_all2
+                |          make_child
+                |
+                 --6.25%-- __GI_strcpy
+    21.61%              git  /lib64/libc-2.5.so
+                |
+                |--30.00%-- __GI_read
+                |          |
+                |           --83.33%-- git_config_from_file
+                |                     git_config
+                |                     |
+   [...]
+
+Or you can observe the whole system's page allocations for 10
+seconds:
+
+titan:~/git> perf stat -a -e kmem:mm_page_pcpu_drain -e
+kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
+kmem:mm_page_free_direct sleep 10
+
+ Performance counter stats for 'sleep 10':
+
+         171585  kmem:mm_page_pcpu_drain
+         322114  kmem:mm_page_alloc
+          73623  kmem:mm_pagevec_free
+         254115  kmem:mm_page_free_direct
+
+   10.000591410  seconds time elapsed
+
+Or observe how fluctuating the page allocations are, via statistical
+analysis done over ten 1-second intervals:
+
+ titan:~/git> perf stat --repeat 10 -a -e kmem:mm_page_pcpu_drain -e
+   kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
+   kmem:mm_page_free_direct sleep 1
+
+ Performance counter stats for 'sleep 1' (10 runs):
+
+          17254  kmem:mm_page_pcpu_drain    ( +-   3.709% )
+          34394  kmem:mm_page_alloc         ( +-   4.617% )
+           7509  kmem:mm_pagevec_free       ( +-   4.820% )
+          25653  kmem:mm_page_free_direct   ( +-   3.672% )
+
+    1.058135029  seconds time elapsed   ( +-   3.089% )
+
+Or you can annotate the recorded 'git gc' run on a per symbol basis
+and check which instructions/source-code generated page allocations:
+
+ titan:~/git> perf annotate __GI___fork
+ ------------------------------------------------
+  Percent |      Source code & Disassembly of libc-2.5.so
+ ------------------------------------------------
+          :
+          :
+          :      Disassembly of section .plt:
+          :      Disassembly of section .text:
+          :
+          :      00000031a2e95560 <__fork>:
+ [...]
+     0.00 :        31a2e95602:   b8 38 00 00 00          mov    $0x38,%eax
+     0.00 :        31a2e95607:   0f 05                   syscall
+    83.42 :        31a2e95609:   48 3d 00 f0 ff ff       cmp    $0xfffffffffffff000,%rax
+     0.00 :        31a2e9560f:   0f 87 4d 01 00 00       ja     31a2e95762 <__fork+0x202>
+     0.00 :        31a2e95615:   85 c0                   test   %eax,%eax
+
+( this shows that 83.42% of __GI___fork's page allocations come from
+  the 0x38 system call it performs. )
+
+etc. etc. - a lot more is possible. I could list a dozen of
+other different usecases straight away - neither of which is
+possible via /proc/vmstat.
+
+/proc/vmstat is not in the same league really, in terms of
+expressive power of system analysis and performance
+analysis.
+
+All that the above results needed were those new tracepoints
+in include/tracing/events/kmem.h.
+
+	Ingo
+
+

tools/perf/Documentation/perf-stat.txt

@@ -40,7 +40,7 @@ OPTIONS
 -a::
         system-wide collection
 
--S::
+-c::
         scale counter values
 
 EXAMPLES

tools/perf/Documentation/perf-top.txt

@@ -3,36 +3,122 @@ perf-top(1)
 
 NAME
 ----
-perf-top - Run a command and profile it
+perf-top - System profiling tool.
 
 SYNOPSIS
 --------
 [verse]
-'perf top' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
+'perf top' [-e <EVENT> | --event=EVENT] [<options>]
 
 DESCRIPTION
 -----------
-This command runs a command and gathers a performance counter profile
-from it.
+This command generates and displays a performance counter profile in realtime.
 
 
 OPTIONS
 -------
-<command>...::
-	Any command you can specify in a shell.
+-a::
+--all-cpus::
+        System-wide collection.  (default)
+
+-c <count>::
+--count=<count>::
+	Event period to sample.
+
+-C <cpu>::
+--CPU=<cpu>::
+	CPU to profile.
+
+-d <seconds>::
+--delay=<seconds>::
+	Number of seconds to delay between refreshes.
 
--e::
---event=::
+-e <event>::
+--event=<event>::
 	Select the PMU event. Selection can be a symbolic event name
 	(use 'perf list' to list all events) or a raw PMU
 	event (eventsel+umask) in the form of rNNN where NNN is a
-	 hexadecimal event descriptor.
+	hexadecimal event descriptor.
 
--a::
-        system-wide collection
+-E <entries>::
+--entries=<entries>::
+	Display this many functions.
+
+-f <count>::
+--count-filter=<count>::
+	Only display functions with more events than this.
+
+-F <freq>::
+--freq=<freq>::
+	Profile at this frequency.
+
+-i::
+--inherit::
+	Child tasks inherit counters, only makes sens with -p option.
+
+-k <path>::
+--vmlinux=<path>::
+	Path to vmlinux.  Required for annotation functionality.
+
+-m <pages>::
+--mmap-pages=<pages>::
+	Number of mmapped data pages.
+
+-p <pid>::
+--pid=<pid>::
+	Profile events on existing pid.
+
+-r <priority>::
+--realtime=<priority>::
+	Collect data with this RT SCHED_FIFO priority.
+
+-s <symbol>::
+--sym-annotate=<symbol>::
+        Annotate this symbol.  Requires -k option.
+
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
+
+-z::
+--zero::
+	Zero history across display updates.
+
+INTERACTIVE PROMPTING KEYS
+--------------------------
+
+[d]::
+	Display refresh delay.
+
+[e]::
+	Number of entries to display.
+
+[E]::
+	Event to display when multiple counters are active.
+
+[f]::
+	Profile display filter (>= hit count).
+
+[F]::
+	Annotation display filter (>= % of total).
+
+[s]::
+	Annotate symbol.
+
+[S]::
+	Stop annotation, return to full profile display.
+
+[w]::
+	Toggle between weighted sum and individual count[E]r profile.
+
+[z]::
+	Toggle event count zeroing across display updates.
+
+[qQ]::
+	Quit.
+
+Pressing any unmapped key displays a menu, and prompts for input.
 
--l::
-        scale counter values
 
 SEE ALSO
 --------

tools/perf/Makefile

@@ -387,10 +387,14 @@ else
 
 	has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty > /dev/null 2>&1 && echo y")
 
+	has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty -lz > /dev/null 2>&1 && echo y")
+
 	ifeq ($(has_bfd),y)
 		EXTLIBS += -lbfd
 	else ifeq ($(has_bfd_iberty),y)
 		EXTLIBS += -lbfd -liberty
+	else ifeq ($(has_bfd_iberty_z),y)
+		EXTLIBS += -lbfd -liberty -lz
 	else
 		msg := $(warning No bfd.h/libbfd found, install binutils-dev[el] to gain symbol demangling)
 		BASIC_CFLAGS += -DNO_DEMANGLE

tools/perf/builtin-record.c

@@ -525,10 +525,14 @@ static int __cmd_record(int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 
-	if (!stat(output_name, &st) && !force && !append_file) {
-		fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n",
-				output_name);
-		exit(-1);
+	if (!stat(output_name, &st) && st.st_size) {
+		if (!force && !append_file) {
+			fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n",
+					output_name);
+			exit(-1);
+		}
+	} else {
+		append_file = 0;
 	}
 
 	flags = O_CREAT|O_RDWR;

tools/perf/builtin-report.c

@@ -68,7 +68,7 @@ static int		callchain;
 
 static
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
+	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5
 };
 
@@ -112,7 +112,9 @@ struct read_event {
 	struct perf_event_header header;
 	u32 pid,tid;
 	u64 value;
-	u64 format[3];
+	u64 time_enabled;
+	u64 time_running;
+	u64 id;
 };
 
 typedef union event_union {
@@ -698,7 +700,8 @@ sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used)
 	size_t ret = 0;
 
 	if (verbose)
-		ret += repsep_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) {
@@ -888,6 +891,21 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
 	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)
@@ -897,25 +915,34 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	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->cumul_hit;
+		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
+		 * 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)
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
 			new_depth_mask &= ~(1 << (depth - 1));
 
 		/*
@@ -930,7 +957,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
-						      child->cumul_hit);
+						      cumul);
 		}
 		ret += callchain__fprintf_graph(fp, child, new_total,
 						depth + 1,
@@ -938,6 +965,19 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		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;
 }
 
@@ -1358,6 +1398,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	unsigned int width;
 	char *col_width = col_width_list_str;
 
+	init_rem_hits();
+
 	fprintf(fp, "# Samples: %Ld\n", (u64)total_samples);
 	fprintf(fp, "#\n");
 
@@ -1429,6 +1471,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	}
 	fprintf(fp, "\n");
 
+	free(rem_sq_bracket);
+
 	return ret;
 }
 
@@ -1690,14 +1734,37 @@ static void trace_event(event_t *event)
 	dprintf(".\n");
 }
 
+static struct perf_header	*header;
+
+static struct perf_counter_attr *perf_header__find_attr(u64 id)
+{
+	int i;
+
+	for (i = 0; i < header->attrs; i++) {
+		struct perf_header_attr *attr = header->attr[i];
+		int j;
+
+		for (j = 0; j < attr->ids; j++) {
+			if (attr->id[j] == id)
+				return &attr->attr;
+		}
+	}
+
+	return NULL;
+}
+
 static int
 process_read_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	dprintf("%p [%p]: PERF_EVENT_READ: %d %d %Lu\n",
+	struct perf_counter_attr *attr = perf_header__find_attr(event->read.id);
+
+	dprintf("%p [%p]: PERF_EVENT_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);
 
 	return 0;
@@ -1743,8 +1810,6 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 	return 0;
 }
 
-static struct perf_header	*header;
-
 static u64 perf_header__sample_type(void)
 {
 	u64 sample_type = 0;
@@ -1812,6 +1877,13 @@ static int __cmd_report(void)
 					" -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) {
@@ -1950,6 +2022,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	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;
 

tools/perf/builtin-stat.c

@@ -496,7 +496,7 @@ static const struct option options[] = {
 		    "stat events on existing pid"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('S', "scale", &scale,
+	OPT_BOOLEAN('c', "scale", &scale,
 		    "scale/normalize counters"),
 	OPT_BOOLEAN('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),

tools/perf/util/callchain.c

@@ -13,6 +13,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <errno.h>
+#include <math.h>
 
 #include "callchain.h"
 
@@ -26,10 +27,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct callchain_node *rnode;
+	u64 chain_cumul = cumul_hits(chain);
 
 	while (*p) {
+		u64 rnode_cumul;
+
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node);
+		rnode_cumul = cumul_hits(rnode);
 
 		switch (mode) {
 		case CHAIN_FLAT:
@@ -40,7 +45,7 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 			break;
 		case CHAIN_GRAPH_ABS: /* Falldown */
 		case CHAIN_GRAPH_REL:
-			if (rnode->cumul_hit < chain->cumul_hit)
+			if (rnode_cumul < chain_cumul)
 				p = &(*p)->rb_left;
 			else
 				p = &(*p)->rb_right;
@@ -87,7 +92,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node,
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_abs(child, min_hit);
-		if (child->cumul_hit >= min_hit)
+		if (cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_ABS);
 	}
@@ -108,11 +113,11 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 	u64 min_hit;
 
 	node->rb_root = RB_ROOT;
-	min_hit = node->cumul_hit * min_percent / 100.0;
+	min_hit = ceil(node->children_hit * min_percent);
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_rel(child, min_percent);
-		if (child->cumul_hit >= min_hit)
+		if (cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_REL);
 	}
@@ -122,7 +127,7 @@ static void
 sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
 		     u64 min_hit __used, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent);
+	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
 	rb_root->rb_node = chain_root->rb_root.rb_node;
 }
 
@@ -211,7 +216,8 @@ add_child(struct callchain_node *parent, struct ip_callchain *chain,
 	new = create_child(parent, false);
 	fill_node(new, chain, start, syms);
 
-	new->cumul_hit = new->hit = 1;
+	new->children_hit = 0;
+	new->hit = 1;
 }
 
 /*
@@ -241,7 +247,8 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 
 	/* split the hits */
 	new->hit = parent->hit;
-	new->cumul_hit = parent->cumul_hit;
+	new->children_hit = parent->children_hit;
+	parent->children_hit = cumul_hits(new);
 	new->val_nr = parent->val_nr - idx_local;
 	parent->val_nr = idx_local;
 
@@ -249,6 +256,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
 		add_child(parent, chain, idx_total, syms);
+		parent->children_hit++;
 	} else {
 		parent->hit = 1;
 	}
@@ -269,13 +277,13 @@ __append_chain_children(struct callchain_node *root, struct ip_callchain *chain,
 		unsigned int ret = __append_chain(rnode, chain, start, syms);
 
 		if (!ret)
-			goto cumul;
+			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
 	add_child(root, chain, start, syms);
 
-cumul:
-	root->cumul_hit++;
+inc_children_hit:
+	root->children_hit++;
 }
 
 static int
@@ -317,8 +325,6 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	/* we match 100% of the path, increment the hit */
 	if (i - start == root->val_nr && i == chain->nr) {
 		root->hit++;
-		root->cumul_hit++;
-
 		return 0;
 	}
 
@@ -331,5 +337,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 void append_chain(struct callchain_node *root, struct ip_callchain *chain,
 		  struct symbol **syms)
 {
+	if (!chain->nr)
+		return;
 	__append_chain_children(root, chain, syms, 0);
 }

tools/perf/util/callchain.h

@@ -7,6 +7,7 @@
 #include "symbol.h"
 
 enum chain_mode {
+	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
 	CHAIN_GRAPH_REL
@@ -21,7 +22,7 @@ struct callchain_node {
 	struct rb_root		rb_root; /* sorted tree of children */
 	unsigned int		val_nr;
 	u64			hit;
-	u64			cumul_hit; /* hit + hits of children */
+	u64			children_hit;
 };
 
 struct callchain_param;
@@ -48,6 +49,11 @@ static inline void callchain_init(struct callchain_node *node)
 	INIT_LIST_HEAD(&node->val);
 }
 
+static inline u64 cumul_hits(struct callchain_node *node)
+{
+	return node->hit + node->children_hit;
+}
+
 int register_callchain_param(struct callchain_param *param);
 void append_chain(struct callchain_node *root, struct ip_callchain *chain,
 		  struct symbol **syms);

tools/perf/util/header.c

@@ -185,6 +185,8 @@ static void do_read(int fd, void *buf, size_t size)
 
 		if (ret < 0)
 			die("failed to read");
+		if (ret == 0)
+			die("failed to read: missing data");
 
 		size -= ret;
 		buf += ret;
@@ -213,9 +215,10 @@ struct perf_header *perf_header__read(int fd)
 
 	for (i = 0; i < nr_attrs; i++) {
 		struct perf_header_attr *attr;
-		off_t tmp = lseek(fd, 0, SEEK_CUR);
+		off_t tmp;
 
 		do_read(fd, &f_attr, sizeof(f_attr));
+		tmp = lseek(fd, 0, SEEK_CUR);
 
 		attr = perf_header_attr__new(&f_attr.attr);
 

tools/perf/util/parse-events.c

@@ -121,13 +121,29 @@ static unsigned long hw_cache_stat[C(MAX)] = {
 	   (strcmp(sys_dirent.d_name, ".")) &&				       \
 	   (strcmp(sys_dirent.d_name, "..")))
 
+static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
+{
+	char evt_path[MAXPATHLEN];
+	int fd;
+
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
+			sys_dir->d_name, evt_dir->d_name);
+	fd = open(evt_path, O_RDONLY);
+	if (fd < 0)
+		return -EINVAL;
+	close(fd);
+
+	return 0;
+}
+
 #define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next, file, st)    \
 	while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next)        \
 	if (snprintf(file, MAXPATHLEN, "%s/%s/%s", debugfs_path,	       \
 		     sys_dirent.d_name, evt_dirent.d_name) &&		       \
 	   (!stat(file, &st)) && (S_ISDIR(st.st_mode)) &&		       \
 	   (strcmp(evt_dirent.d_name, ".")) &&				       \
-	   (strcmp(evt_dirent.d_name, "..")))
+	   (strcmp(evt_dirent.d_name, "..")) &&				       \
+	   (!tp_event_has_id(&sys_dirent, &evt_dirent)))
 
 #define MAX_EVENT_LENGTH 30
 
@@ -223,9 +239,15 @@ char *event_name(int counter)
 {
 	u64 config = attrs[counter].config;
 	int type = attrs[counter].type;
+
+	return __event_name(type, config);
+}
+
+char *__event_name(int type, u64 config)
+{
 	static char buf[32];
 
-	if (attrs[counter].type == PERF_TYPE_RAW) {
+	if (type == PERF_TYPE_RAW) {
 		sprintf(buf, "raw 0x%llx", config);
 		return buf;
 	}

tools/perf/util/parse-events.h

@@ -10,6 +10,7 @@ extern int			nr_counters;
 extern struct perf_counter_attr attrs[MAX_COUNTERS];
 
 extern char *event_name(int ctr);
+extern char *__event_name(int type, u64 config);
 
 extern int parse_events(const struct option *opt, const char *str, int unset);
 

tools/perf/util/symbol.c

@@ -24,6 +24,16 @@ const char *sym_hist_filter;
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+enum dso_origin {
+	DSO__ORIG_KERNEL = 0,
+	DSO__ORIG_JAVA_JIT,
+	DSO__ORIG_FEDORA,
+	DSO__ORIG_UBUNTU,
+	DSO__ORIG_BUILDID,
+	DSO__ORIG_DSO,
+	DSO__ORIG_NOT_FOUND,
+};
+
 static struct symbol *symbol__new(u64 start, u64 len,
 				  const char *name, unsigned int priv_size,
 				  u64 obj_start, int verbose)
@@ -81,6 +91,7 @@ struct dso *dso__new(const char *name, unsigned int sym_priv_size)
 		self->sym_priv_size = sym_priv_size;
 		self->find_symbol = dso__find_symbol;
 		self->slen_calculated = 0;
+		self->origin = DSO__ORIG_NOT_FOUND;
 	}
 
 	return self;
@@ -710,7 +721,7 @@ static char *dso__read_build_id(struct dso *self, int verbose)
 		++raw;
 		bid += 2;
 	}
-	if (verbose)
+	if (verbose >= 2)
 		printf("%s(%s): %s\n", __func__, self->name, build_id);
 out_elf_end:
 	elf_end(elf);
@@ -720,11 +731,26 @@ static char *dso__read_build_id(struct dso *self, int verbose)
 	return build_id;
 }
 
+char dso__symtab_origin(const struct dso *self)
+{
+	static const char origin[] = {
+		[DSO__ORIG_KERNEL] =   'k',
+		[DSO__ORIG_JAVA_JIT] = 'j',
+		[DSO__ORIG_FEDORA] =   'f',
+		[DSO__ORIG_UBUNTU] =   'u',
+		[DSO__ORIG_BUILDID] =  'b',
+		[DSO__ORIG_DSO] =      'd',
+	};
+
+	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
+		return '!';
+	return origin[self->origin];
+}
+
 int dso__load(struct dso *self, symbol_filter_t filter, int verbose)
 {
 	int size = PATH_MAX;
 	char *name = malloc(size), *build_id = NULL;
-	int variant = 0;
 	int ret = -1;
 	int fd;
 
@@ -733,19 +759,26 @@ int dso__load(struct dso *self, symbol_filter_t filter, int verbose)
 
 	self->adjust_symbols = 0;
 
-	if (strncmp(self->name, "/tmp/perf-", 10) == 0)
-		return dso__load_perf_map(self, filter, verbose);
+	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
+		ret = dso__load_perf_map(self, filter, verbose);
+		self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT :
+					 DSO__ORIG_NOT_FOUND;
+		return ret;
+	}
+
+	self->origin = DSO__ORIG_FEDORA - 1;
 
 more:
 	do {
-		switch (variant) {
-		case 0: /* Fedora */
+		self->origin++;
+		switch (self->origin) {
+		case DSO__ORIG_FEDORA:
 			snprintf(name, size, "/usr/lib/debug%s.debug", self->name);
 			break;
-		case 1: /* Ubuntu */
+		case DSO__ORIG_UBUNTU:
 			snprintf(name, size, "/usr/lib/debug%s", self->name);
 			break;
-		case 2:
+		case DSO__ORIG_BUILDID:
 			build_id = dso__read_build_id(self, verbose);
 			if (build_id != NULL) {
 				snprintf(name, size,
@@ -754,16 +787,15 @@ int dso__load(struct dso *self, symbol_filter_t filter, int verbose)
 				free(build_id);
 				break;
 			}
-			variant++;
+			self->origin++;
 			/* Fall thru */
-		case 3: /* Sane people */
+		case DSO__ORIG_DSO:
 			snprintf(name, size, "%s", self->name);
 			break;
 
 		default:
 			goto out;
 		}
-		variant++;
 
 		fd = open(name, O_RDONLY);
 	} while (fd < 0);
@@ -899,6 +931,9 @@ int dso__load_kernel(struct dso *self, const char *vmlinux,
 	if (err <= 0)
 		err = dso__load_kallsyms(self, filter, verbose);
 
+	if (err > 0)
+		self->origin = DSO__ORIG_KERNEL;
+
 	return err;
 }
 

tools/perf/util/symbol.h

@@ -26,6 +26,7 @@ struct dso {
 	unsigned int	 sym_priv_size;
 	unsigned char	 adjust_symbols;
 	unsigned char	 slen_calculated;
+	unsigned char	 origin;
 	char		 name[0];
 };
 
@@ -49,6 +50,7 @@ int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose);
 int dso__load(struct dso *self, symbol_filter_t filter, int verbose);
 
 size_t dso__fprintf(struct dso *self, FILE *fp);
+char dso__symtab_origin(const struct dso *self);
 
 void symbol__init(void);
 #endif /* _PERF_SYMBOL_ */