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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (121 commits)
  perf symbols: Increase symbol KSYM_NAME_LEN size
  perf hists browser: Refuse 'a' hotkey on non symbolic views
  perf ui browser: Use libslang to read keys
  perf tools: Fix tracing info recording
  perf hists browser: Elide DSO column when it is set to just one DSO, ditto for threads
  perf hists: Don't consider filtered entries when calculating column widths
  perf hists: Don't decay total_period for filtered entries
  perf hists browser: Honour symbol_conf.show_{nr_samples,total_period}
  perf hists browser: Do not exit on tab key with single event
  perf annotate browser: Don't change selection line when returning from callq
  perf tools: handle endianness of feature bitmap
  perf tools: Add prelink suggestion to dso update message
  perf script: Fix unknown feature comment
  perf hists browser: Apply the dso and thread filters when merging new batches
  perf hists: Move the dso and thread filters from hist_browser
  perf ui browser: Honour the xterm colors
  perf top tui: Give color hints just on the percentage, like on --stdio
  perf ui browser: Make the colors configurable and change the defaults
  perf tui: Remove unneeded call to newtCls on startup
  perf hists: Don't format the percentage on hist_entry__snprintf
  ...

Fix up conflicts in arch/x86/kernel/kprobes.c manually.

Ingo's tree did the insane "add volatile to const array", which just
doesn't make sense ("volatile const"?).  But we could remove the const
*and* make the array volatile to make doubly sure that gcc doesn't
optimize it away..

Also fix up kernel/trace/ring_buffer.c non-data-conflicts manually: the
reader_lock has been turned into a raw lock by the core locking merge,
and there was a new user of it introduced in this perf core merge.  Make
sure that new use also uses the raw accessor functions.

60 files changed, 3447 insertions, 1209 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 85c5f026930..fe6762ed56b 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -72,6 +72,19 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 5eaac6f26d5..cc22325ffd1 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -16,6 +16,9 @@ This command displays the buildids found in a perf.data file, so that other
 tools can be used to fetch packages with matching symbol tables for use by
 perf report.
 
+It can also be used to show the build id of the running kernel or in an ELF
+file using -i/--input.
+
 OPTIONS
 -------
 -H::
@@ -27,6 +30,9 @@ OPTIONS
 -f::
 --force::
 	Don't do ownership validation.
+-k::
+--kernel::
+	Show running kernel build id.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 04253c07d19..212f24d672e 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -134,6 +134,24 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+--show-total-period:: Show a column with the sum of periods.
+
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+
 SEE ALSO
 --------
-linkperf:perf-stat[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 46822d5fde1..5b212b57f70 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,7 +8,7 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|map|replay|trace}
+'perf sched' {record|latency|map|replay|script}
 
 DESCRIPTION
 -----------
@@ -20,8 +20,8 @@ There are five variants of perf sched:
   'perf sched latency' to report the per task scheduling latencies
   and other scheduling properties of the workload.
 
-  'perf sched trace' to see a detailed trace of the workload that
-  was recorded.
+  'perf sched script' to see a detailed trace of the workload that
+   was recorded (aliased to 'perf script' for now).
 
   'perf sched replay' to simulate the workload that was recorded
   via perf sched record. (this is done by starting up mockup threads
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index db017867d9e..dec87ecb530 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -188,6 +188,13 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+	It can only be used with the perf script report mode.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 918cc38ee6d..8966b9ab201 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -94,6 +94,22 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
 corresponding events, i.e., they always refer to events defined earlier on the command
 line.
 
+-o file::
+--output file::
+Print the output into the designated file.
+
+--append::
+Append to the output file designated with the -o option. Ignored if -o is not specified.
+
+--log-fd::
+
+Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
+with it.  --append may be used here.  Examples:
+     3>results  perf stat --log-fd 3          -- $cmd
+     3>>results perf stat --log-fd 3 --append -- $cmd
+
+
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index f6eb1cdafb7..b1a5bbbfebe 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -106,6 +106,51 @@ Default is to monitor all CPUS.
 --zero::
 	Zero history across display updates.
 
+-s::
+--sort::
+	Sort by key(s): pid, comm, dso, symbol, parent
+
+-n::
+--show-nr-samples::
+	Show a column with the number of samples.
+
+--show-total-period::
+	Show a column with the sum of periods.
+
+--dsos::
+	Only consider symbols in these dsos.
+
+--comms::
+	Only consider symbols in these comms.
+
+--symbols::
+	Only consider these symbols.
+
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+-G [type,min,order]::
+--call-graph::
+        Display call chains using type, min percent threshold and order.
+	type can be either:
+	- flat: single column, linear exposure of call chains.
+	- graph: use a graph tree, displaying absolute overhead rates.
+	- fractal: like graph, but displays relative rates. Each branch of
+		 the tree is considered as a new profiled object.
+
+	order can be either:
+	- callee: callee based call graph.
+	- caller: inverted caller based call graph.
+
+	Default: fractal,0.5,callee.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
@@ -130,9 +175,6 @@ INTERACTIVE PROMPTING KEYS
 [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.
 
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
new file mode 100644
index 00000000000..d1448668f4d
--- /dev/null
+++ b/tools/perf/Documentation/perfconfig.example
@@ -0,0 +1,20 @@
+[colors]
+
+	# These were the old defaults
+	top = red, lightgray
+	medium = green, lightgray
+	normal = black, lightgray
+	selected = lightgray, magenta
+	code = blue, lightgray
+
+[tui]
+
+	# Defaults if linked with libslang
+	report = on
+	annotate = on
+	top = on
+
+[buildid]
+
+	# Default, disable using /dev/null
+	dir = /root/.debug
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index e9d5c271db6..b98e3075646 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -466,13 +466,13 @@ else
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o
-		LIB_OBJS += $(OUTPUT)util/ui/browsers/top.o
 		LIB_OBJS += $(OUTPUT)util/ui/helpline.o
 		LIB_OBJS += $(OUTPUT)util/ui/progress.o
 		LIB_OBJS += $(OUTPUT)util/ui/util.o
 		LIB_H += util/ui/browser.h
 		LIB_H += util/ui/browsers/map.h
 		LIB_H += util/ui/helpline.h
+		LIB_H += util/ui/keysyms.h
 		LIB_H += util/ui/libslang.h
 		LIB_H += util/ui/progress.h
 		LIB_H += util/ui/util.h
@@ -729,9 +729,6 @@ $(OUTPUT)util/ui/browser.o: util/ui/browser.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
-$(OUTPUT)util/ui/browsers/top.o: util/ui/browsers/top.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
 $(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 15130b50dfe..744e629797b 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
new file mode 100644
index 00000000000..eba80c29294
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -0,0 +1,36 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+#define __stringify_1(x)        #x
+#define __stringify(x)          __stringify_1(x)
+
+#define mfspr(rn)       ({unsigned long rval; \
+			 asm volatile("mfspr %0," __stringify(rn) \
+				      : "=r" (rval)); rval; })
+
+#define SPRN_PVR        0x11F	/* Processor Version Register */
+#define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
+#define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned long pvr;
+	int nb;
+
+	pvr = mfspr(SPRN_PVR);
+
+	nb = snprintf(buffer, sz, "%lu,%lu$", PVR_VER(pvr), PVR_REV(pvr));
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 15130b50dfe..744e629797b 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
new file mode 100644
index 00000000000..f94006068d2
--- /dev/null
+++ b/tools/perf/arch/x86/util/header.c
@@ -0,0 +1,59 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+static inline void
+cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
+      unsigned int *d)
+{
+	__asm__ __volatile__ (".byte 0x53\n\tcpuid\n\t"
+			      "movl %%ebx, %%esi\n\t.byte 0x5b"
+			: "=a" (*a),
+			"=S" (*b),
+			"=c" (*c),
+			"=d" (*d)
+			: "a" (op));
+}
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned int a, b, c, d, lvl;
+	int family = -1, model = -1, step = -1;
+	int nb;
+	char vendor[16];
+
+	cpuid(0, &lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
+
+	if (lvl >= 1) {
+		cpuid(1, &a, &b, &c, &d);
+
+		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
+		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
+		step   = a & 0xf;
+
+		/* extended family */
+		if (family == 0xf)
+			family += (a >> 20) & 0xff;
+
+		/* extended model */
+		if (family >= 0x6)
+			model += ((a >> 16) & 0xf) << 4;
+	}
+	nb = snprintf(buffer, sz, "%s,%u,%u,%u$", vendor, family, model, step);
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 555aefd7fe0..46b4c24f338 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -114,10 +114,11 @@ static int hist_entry__tty_annotate(struct hist_entry *he, int evidx)
 				    print_line, full_paths, 0, 0);
 }
 
-static void hists__find_annotations(struct hists *self, int evidx)
+static void hists__find_annotations(struct hists *self, int evidx,
+				    int nr_events)
 {
 	struct rb_node *nd = rb_first(&self->entries), *next;
-	int key = KEY_RIGHT;
+	int key = K_RIGHT;
 
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
@@ -129,7 +130,7 @@ static void hists__find_annotations(struct hists *self, int evidx)
 		notes = symbol__annotation(he->ms.sym);
 		if (notes->src == NULL) {
 find_next:
-			if (key == KEY_LEFT)
+			if (key == K_LEFT)
 				nd = rb_prev(nd);
 			else
 				nd = rb_next(nd);
@@ -137,12 +138,13 @@ find_next:
 		}
 
 		if (use_browser > 0) {
-			key = hist_entry__tui_annotate(he, evidx);
+			key = hist_entry__tui_annotate(he, evidx, nr_events,
+						       NULL, NULL, 0);
 			switch (key) {
-			case KEY_RIGHT:
+			case K_RIGHT:
 				next = rb_next(nd);
 				break;
-			case KEY_LEFT:
+			case K_LEFT:
 				next = rb_prev(nd);
 				break;
 			default:
@@ -215,7 +217,8 @@ static int __cmd_annotate(void)
 			total_nr_samples += nr_samples;
 			hists__collapse_resort(hists);
 			hists__output_resort(hists);
-			hists__find_annotations(hists, pos->idx);
+			hists__find_annotations(hists, pos->idx,
+						session->evlist->nr_entries);
 		}
 	}
 
@@ -267,6 +270,14 @@ static const struct option options[] = {
 	OPT_BOOLEAN('P', "full-paths", &full_paths,
 		    "Don't shorten the displayed pathnames"),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		   "Look for files with symbols relative to this directory"),
+	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5af32ae9031..cb690a65bf0 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,7 +1,8 @@
 /*
  * builtin-buildid-list.c
  *
- * Builtin buildid-list command: list buildids in perf.data
+ * Builtin buildid-list command: list buildids in perf.data, in the running
+ * kernel and in ELF files.
  *
  * Copyright (C) 2009, Red Hat Inc.
  * Copyright (C) 2009, Arnaldo Carvalho de Melo <acme@redhat.com>
@@ -15,8 +16,11 @@
 #include "util/session.h"
 #include "util/symbol.h"
 
+#include <libelf.h>
+
 static char const *input_name = "perf.data";
 static bool force;
+static bool show_kernel;
 static bool with_hits;
 
 static const char * const buildid_list_usage[] = {
@@ -29,12 +33,13 @@ static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose"),
 	OPT_END()
 };
 
-static int __cmd_buildid_list(void)
+static int perf_session__list_build_ids(void)
 {
 	struct perf_session *session;
 
@@ -52,6 +57,49 @@ static int __cmd_buildid_list(void)
 	return 0;
 }
 
+static int sysfs__fprintf_build_id(FILE *fp)
+{
+	u8 kallsyms_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
+				 sizeof(kallsyms_build_id)) != 0)
+		return -1;
+
+	build_id__sprintf(kallsyms_build_id, sizeof(kallsyms_build_id),
+			  sbuild_id);
+	fprintf(fp, "%s\n", sbuild_id);
+	return 0;
+}
+
+static int filename__fprintf_build_id(const char *name, FILE *fp)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (filename__read_build_id(name, build_id,
+				    sizeof(build_id)) != sizeof(build_id))
+		return 0;
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	return fprintf(fp, "%s\n", sbuild_id);
+}
+
+static int __cmd_buildid_list(void)
+{
+	if (show_kernel)
+		return sysfs__fprintf_build_id(stdout);
+
+	elf_version(EV_CURRENT);
+	/*
+ 	 * See if this is an ELF file first:
+ 	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		return 0;
+
+	return perf_session__list_build_ids();
+}