Initial commit; kernel source import

tools/Makefile

@@ -0,0 +1,91 @@
+include scripts/Makefile.include
+
+help:
+	@echo 'Possible targets:'
+	@echo ''
+	@echo '  cgroup     - cgroup tools'
+	@echo '  cpupower   - a tool for all things x86 CPU power'
+	@echo '  firewire   - the userspace part of nosy, an IEEE-1394 traffic sniffer'
+	@echo '  lguest     - a minimal 32-bit x86 hypervisor'
+	@echo '  perf       - Linux performance measurement and analysis tool'
+	@echo '  selftests  - various kernel selftests'
+	@echo '  turbostat  - Intel CPU idle stats and freq reporting tool'
+	@echo '  usb        - USB testing tools'
+	@echo '  virtio     - vhost test module'
+	@echo '  net        - misc networking tools'
+	@echo '  vm         - misc vm tools'
+	@echo '  x86_energy_perf_policy - Intel energy policy tool'
+	@echo ''
+	@echo 'You can do:'
+	@echo ' $$ make -C tools/ <tool>_install'
+	@echo ''
+	@echo '  from the kernel command line to build and install one of'
+	@echo '  the tools above'
+	@echo ''
+	@echo '  $$ make tools/install'
+	@echo ''
+	@echo '  installs all tools.'
+	@echo ''
+	@echo 'Cleaning targets:'
+	@echo ''
+	@echo '  all of the above with the "_clean" string appended cleans'
+	@echo '    the respective build directory.'
+	@echo '  clean: a summary clean target to clean _all_ folders'
+
+cpupower: FORCE
+	$(call descend,power/$@)
+
+cgroup firewire guest usb virtio vm net: FORCE
+	$(call descend,$@)
+
+liblk: FORCE
+	$(call descend,lib/lk)
+
+perf: liblk FORCE
+	$(call descend,$@)
+
+selftests: FORCE
+	$(call descend,testing/$@)
+
+turbostat x86_energy_perf_policy: FORCE
+	$(call descend,power/x86/$@)
+
+cpupower_install:
+	$(call descend,power/$(@:_install=),install)
+
+cgroup_install firewire_install lguest_install perf_install usb_install virtio_install vm_install net_install:
+	$(call descend,$(@:_install=),install)
+
+selftests_install:
+	$(call descend,testing/$(@:_clean=),install)
+
+turbostat_install x86_energy_perf_policy_install:
+	$(call descend,power/x86/$(@:_install=),install)
+
+install: cgroup_install cpupower_install firewire_install lguest_install \
+		perf_install selftests_install turbostat_install usb_install \
+		virtio_install vm_install net_install x86_energy_perf_policy_install
+
+cpupower_clean:
+	$(call descend,power/cpupower,clean)
+
+cgroup_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
+	$(call descend,$(@:_clean=),clean)
+
+liblk_clean:
+	$(call descend,lib/lk,clean)
+
+perf_clean: liblk_clean
+	$(call descend,$(@:_clean=),clean)
+
+selftests_clean:
+	$(call descend,testing/$(@:_clean=),clean)
+
+turbostat_clean x86_energy_perf_policy_clean:
+	$(call descend,power/x86/$(@:_clean=),clean)
+
+clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \
+		selftests_clean turbostat_clean usb_clean virtio_clean \
+		vm_clean net_clean x86_energy_perf_policy_clean
+
+.PHONY: FORCE

tools/cgroup/.gitignore

@@ -0,0 +1 @@
+cgroup_event_listener

tools/cgroup/Makefile

@@ -0,0 +1,11 @@
+# Makefile for cgroup tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: cgroup_event_listener
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+clean:
+	$(RM) cgroup_event_listener

tools/cgroup/cgroup_event_listener.c

@@ -0,0 +1,82 @@
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>"
+
+int main(int argc, char **argv)
+{
+	int efd = -1;
+	int cfd = -1;
+	int event_control = -1;
+	char event_control_path[PATH_MAX];
+	char line[LINE_MAX];
+	int ret;
+
+	if (argc != 3)
+		errx(1, "%s", USAGE_STR);
+
+	cfd = open(argv[1], O_RDONLY);
+	if (cfd == -1)
+		err(1, "Cannot open %s", argv[1]);
+
+	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+			dirname(argv[1]));
+	if (ret >= PATH_MAX)
+		errx(1, "Path to cgroup.event_control is too long");
+
+	event_control = open(event_control_path, O_WRONLY);
+	if (event_control == -1)
+		err(1, "Cannot open %s", event_control_path);
+
+	efd = eventfd(0, 0);
+	if (efd == -1)
+		err(1, "eventfd() failed");
+
+	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+	if (ret >= LINE_MAX)
+		errx(1, "Arguments string is too long");
+
+	ret = write(event_control, line, strlen(line) + 1);
+	if (ret == -1)
+		err(1, "Cannot write to cgroup.event_control");
+
+	while (1) {
+		uint64_t result;
+
+		ret = read(efd, &result, sizeof(result));
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+			err(1, "Cannot read from eventfd");
+		}
+		assert(ret == sizeof(result));
+
+		ret = access(event_control_path, W_OK);
+		if ((ret == -1) && (errno == ENOENT)) {
+			puts("The cgroup seems to have removed.");
+			break;
+		}
+
+		if (ret == -1)
+			err(1, "cgroup.event_control is not accessible any more");
+
+		printf("%s %s: crossed\n", argv[1], argv[2]);
+	}
+
+	return 0;
+}

tools/firewire/Makefile

@@ -0,0 +1,19 @@
+prefix = /usr
+nosy-dump-version = 0.4
+
+CC = gcc
+
+all : nosy-dump
+
+nosy-dump : CFLAGS = -Wall -O2 -g
+nosy-dump : CPPFLAGS = -DVERSION=\"$(nosy-dump-version)\" -I../../drivers/firewire
+nosy-dump : LDFLAGS = -g
+nosy-dump : LDLIBS = -lpopt
+
+nosy-dump : nosy-dump.o decode-fcp.o
+
+clean :
+	rm -rf *.o nosy-dump
+
+install :
+	install nosy-dump $(prefix)/bin/nosy-dump

tools/firewire/decode-fcp.c

@@ -0,0 +1,213 @@
+#include <linux/firewire-constants.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "list.h"
+#include "nosy-dump.h"
+
+#define CSR_FCP_COMMAND			0xfffff0000b00ull
+#define CSR_FCP_RESPONSE		0xfffff0000d00ull
+
+static const char * const ctype_names[] = {
+	[0x0] = "control",		[0x8] = "not implemented",
+	[0x1] = "status",		[0x9] = "accepted",
+	[0x2] = "specific inquiry",	[0xa] = "rejected",
+	[0x3] = "notify",		[0xb] = "in transition",
+	[0x4] = "general inquiry",	[0xc] = "stable",
+	[0x5] = "(reserved 0x05)",	[0xd] = "changed",
+	[0x6] = "(reserved 0x06)",	[0xe] = "(reserved 0x0e)",
+	[0x7] = "(reserved 0x07)",	[0xf] = "interim",
+};
+
+static const char * const subunit_type_names[] = {
+	[0x00] = "monitor",		[0x10] = "(reserved 0x10)",
+	[0x01] = "audio",		[0x11] = "(reserved 0x11)",
+	[0x02] = "printer",		[0x12] = "(reserved 0x12)",
+	[0x03] = "disc",		[0x13] = "(reserved 0x13)",
+	[0x04] = "tape recorder/player",[0x14] = "(reserved 0x14)",
+	[0x05] = "tuner",		[0x15] = "(reserved 0x15)",
+	[0x06] = "ca",			[0x16] = "(reserved 0x16)",
+	[0x07] = "camera",		[0x17] = "(reserved 0x17)",
+	[0x08] = "(reserved 0x08)",	[0x18] = "(reserved 0x18)",
+	[0x09] = "panel",		[0x19] = "(reserved 0x19)",
+	[0x0a] = "bulletin board",	[0x1a] = "(reserved 0x1a)",
+	[0x0b] = "camera storage",	[0x1b] = "(reserved 0x1b)",
+	[0x0c] = "(reserved 0x0c)",	[0x1c] = "vendor unique",
+	[0x0d] = "(reserved 0x0d)",	[0x1d] = "all subunit types",
+	[0x0e] = "(reserved 0x0e)",	[0x1e] = "subunit_type extended to next byte",
+	[0x0f] = "(reserved 0x0f)",	[0x1f] = "unit",
+};
+
+struct avc_enum {
+	int value;
+	const char *name;
+};
+
+struct avc_field {
+	const char *name;	/* Short name for field. */
+	int offset;		/* Location of field, specified in bits; */
+				/* negative means from end of packet.    */
+	int width;		/* Width of field, 0 means use data_length. */
+	struct avc_enum *names;
+};
+
+struct avc_opcode_info {
+	const char *name;
+	struct avc_field fields[8];
+};
+
+struct avc_enum power_field_names[] = {
+	{ 0x70, "on" },
+	{ 0x60, "off" },
+	{ }
+};
+
+static const struct avc_opcode_info opcode_info[256] = {
+
+	/* TA Document 1999026 */
+	/* AV/C Digital Interface Command Set General Specification 4.0 */
+	[0xb2] = { "power", {
+			{ "state", 0, 8, power_field_names }
+		}
+	},
+	[0x30] = { "unit info", {
+			{ "foo", 0, 8 },
+			{ "unit_type", 8, 5 },
+			{ "unit", 13, 3 },
+			{ "company id", 16, 24 },
+		}
+	},
+	[0x31] = { "subunit info" },
+	[0x01] = { "reserve" },
+	[0xb0] = { "version" },
+	[0x00] = { "vendor dependent" },
+	[0x02] = { "plug info" },
+	[0x12] = { "channel usage" },
+	[0x24] = { "connect" },
+	[0x20] = { "connect av" },
+	[0x22] = { "connections" },
+	[0x11] = { "digital input" },
+	[0x10] = { "digital output" },
+	[0x25] = { "disconnect" },
+	[0x21] = { "disconnect av" },
+	[0x19] = { "input plug signal format" },
+	[0x18] = { "output plug signal format" },
+	[0x1f] = { "general bus setup" },
+
+	/* TA Document 1999025 */
+	/* AV/C Descriptor Mechanism Specification Version 1.0 */
+	[0x0c] = { "create descriptor" },
+	[0x08] = { "open descriptor" },
+	[0x09] = { "read descriptor" },
+	[0x0a] = { "write descriptor" },
+	[0x05] = { "open info block" },
+	[0x06] = { "read info block" },
+	[0x07] = { "write info block" },
+	[0x0b] = { "search descriptor" },
+	[0x0d] = { "object number select" },
+
+	/* TA Document 1999015 */
+	/* AV/C Command Set for Rate Control of Isochronous Data Flow 1.0 */
+	[0xb3] = { "rate", {
+			{ "subfunction", 0, 8 },
+			{ "result", 8, 8 },
+			{ "plug_type", 16, 8 },
+			{ "plug_id", 16, 8 },
+		}
+	},
+
+	/* TA Document 1999008 */
+	/* AV/C Audio Subunit Specification 1.0 */
+	[0xb8] = { "function block" },
+
+	/* TA Document 2001001 */
+	/* AV/C Panel Subunit Specification 1.1 */
+	[0x7d] = { "gui update" },
+	[0x7e] = { "push gui data" },
+	[0x7f] = { "user action" },
+	[0x7c] = { "pass through" },
+
+	/* */
+	[0x26] = { "asynchronous connection" },
+};
+
+struct avc_frame {
+	uint32_t operand0:8;
+	uint32_t opcode:8;
+	uint32_t subunit_id:3;
+	uint32_t subunit_type:5;
+	uint32_t ctype:4;
+	uint32_t cts:4;
+};
+
+static void
+decode_avc(struct link_transaction *t)
+{
+	struct avc_frame *frame =
+	    (struct avc_frame *) t->request->packet.write_block.data;
+	const struct avc_opcode_info *info;
+	const char *name;
+	char buffer[32];
+	int i;
+
+	info = &opcode_info[frame->opcode];
+	if (info->name == NULL) {
+		snprintf(buffer, sizeof(buffer),
+			 "(unknown opcode 0x%02x)", frame->opcode);
+		name = buffer;
+	} else {
+		name = info->name;
+	}
+
+	printf("av/c %s, subunit_type=%s, subunit_id=%d, opcode=%s",
+	    ctype_names[frame->ctype], subunit_type_names[frame->subunit_type],
+	    frame->subunit_id, name);
+
+	for (i = 0; info->fields[i].name != NULL; i++)
+		printf(", %s", info->fields[i].name);
+
+	printf("\n");
+}
+
+int
+decode_fcp(struct link_transaction *t)
+{
+	struct avc_frame *frame =
+	    (struct avc_frame *) t->request->packet.write_block.data;
+	unsigned long long offset =
+	    ((unsigned long long) t->request->packet.common.offset_high << 32) |
+	    t->request->packet.common.offset_low;
+
+	if (t->request->packet.common.tcode != TCODE_WRITE_BLOCK_REQUEST)
+		return 0;
+
+	if (offset == CSR_FCP_COMMAND || offset == CSR_FCP_RESPONSE) {
+		switch (frame->cts) {
+		case 0x00:
+			decode_avc(t);
+			break;
+		case 0x01:
+			printf("cal fcp frame (cts=0x01)\n");
+			break;
+		case 0x02:
+			printf("ehs fcp frame (cts=0x02)\n");
+			break;
+		case 0x03:
+			printf("havi fcp frame (cts=0x03)\n");
+			break;
+		case 0x0e:
+			printf("vendor specific fcp frame (cts=0x0e)\n");
+			break;
+		case 0x0f:
+			printf("extended cts\n");
+			break;
+		default:
+			printf("reserved fcp frame (ctx=0x%02x)\n", frame->cts);
+			break;
+		}
+		return 1;
+	}
+
+	return 0;
+}
+

tools/firewire/list.h

@@ -0,0 +1,62 @@
+struct list {
+	struct list *next, *prev;
+};
+
+static inline void
+list_init(struct list *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+static inline int
+list_empty(struct list *list)
+{
+	return list->next == list;
+}
+
+static inline void
+list_insert(struct list *link, struct list *new_link)
+{
+	new_link->prev		= link->prev;
+	new_link->next		= link;
+	new_link->prev->next	= new_link;
+	new_link->next->prev	= new_link;
+}
+
+static inline void
+list_append(struct list *list, struct list *new_link)
+{
+	list_insert((struct list *)list, new_link);
+}
+
+static inline void
+list_prepend(struct list *list, struct list *new_link)
+{
+	list_insert(list->next, new_link);
+}
+
+static inline void
+list_remove(struct list *link)
+{
+	link->prev->next = link->next;
+	link->next->prev = link->prev;
+}
+
+#define list_entry(link, type, member) \
+	((type *)((char *)(link)-(unsigned long)(&((type *)0)->member)))
+
+#define list_head(list, type, member)		\
+	list_entry((list)->next, type, member)
+
+#define list_tail(list, type, member)		\
+	list_entry((list)->prev, type, member)
+
+#define list_next(elm, member)					\
+	list_entry((elm)->member.next, typeof(*elm), member)
+
+#define list_for_each_entry(pos, list, member)			\
+	for (pos = list_head(list, typeof(*pos), member);	\
+	     &pos->member != (list);				\
+	     pos = list_next(pos, member))
+

tools/firewire/nosy-dump.h

@@ -0,0 +1,173 @@
+#ifndef __nosy_dump_h__
+#define __nosy_dump_h__
+
+#define array_length(array) (sizeof(array) / sizeof(array[0]))
+
+#define ACK_NO_ACK   0x0
+#define ACK_DONE(a)  ((a >> 2) == 0)
+#define ACK_BUSY(a)  ((a >> 2) == 1)
+#define ACK_ERROR(a) ((a >> 2) == 3)
+
+#include <stdint.h>
+
+struct phy_packet {
+	uint32_t timestamp;
+	union {
+		struct {
+			uint32_t zero:24;
+			uint32_t phy_id:6;
+			uint32_t identifier:2;
+		} common, link_on;
+
+		struct {
+			uint32_t zero:16;
+			uint32_t gap_count:6;
+			uint32_t set_gap_count:1;
+			uint32_t set_root:1;
+			uint32_t root_id:6;
+			uint32_t identifier:2;
+		} phy_config;
+
+		struct {
+			uint32_t more_packets:1;
+			uint32_t initiated_reset:1;
+			uint32_t port2:2;
+			uint32_t port1:2;
+			uint32_t port0:2;
+			uint32_t power_class:3;
+			uint32_t contender:1;
+			uint32_t phy_delay:2;
+			uint32_t phy_speed:2;
+			uint32_t gap_count:6;
+			uint32_t link_active:1;
+			uint32_t extended:1;
+			uint32_t phy_id:6;
+			uint32_t identifier:2;
+		} self_id;
+
+		struct {
+			uint32_t more_packets:1;
+			uint32_t reserved1:1;
+			uint32_t porth:2;
+			uint32_t portg:2;
+			uint32_t portf:2;
+			uint32_t porte:2;
+			uint32_t portd:2;
+			uint32_t portc:2;
+			uint32_t portb:2;
+			uint32_t porta:2;
+			uint32_t reserved0:2;
+			uint32_t sequence:3;
+			uint32_t extended:1;
+			uint32_t phy_id:6;
+			uint32_t identifier:2;
+		} ext_self_id;
+	};
+	uint32_t inverted;
+	uint32_t ack;
+};
+
+#define TCODE_PHY_PACKET 0x10
+
+#define PHY_PACKET_CONFIGURATION 0x00
+#define PHY_PACKET_LINK_ON 0x01
+#define PHY_PACKET_SELF_ID 0x02
+
+struct link_packet {
+	uint32_t timestamp;
+	union {
+		struct {
+			uint32_t priority:4;
+			uint32_t tcode:4;
+			uint32_t rt:2;
+			uint32_t tlabel:6;
+			uint32_t destination:16;
+
+			uint32_t offset_high:16;
+			uint32_t source:16;
+
+			uint32_t offset_low;
+		} common;
+
+		struct {
+			uint32_t common[3];
+			uint32_t crc;
+		} read_quadlet;
+
+		struct {
+			uint32_t common[3];
+			uint32_t data;
+			uint32_t crc;
+		} read_quadlet_response;
+
+		struct {
+			uint32_t common[3];
+			uint32_t extended_tcode:16;
+			uint32_t data_length:16;
+			uint32_t crc;
+		} read_block;
+
+		struct {
+			uint32_t common[3];
+			uint32_t extended_tcode:16;
+			uint32_t data_length:16;
+			uint32_t crc;
+			uint32_t data[0];
+			/* crc and ack follows. */
+		} read_block_response;
+
+		struct {
+			uint32_t common[3];
+			uint32_t data;
+			uint32_t crc;
+		} write_quadlet;
+
+		struct {
+			uint32_t common[3];
+			uint32_t extended_tcode:16;
+			uint32_t data_length:16;
+			uint32_t crc;
+			uint32_t data[0];
+			/* crc and ack follows. */
+		} write_block;
+
+		struct {
+			uint32_t common[3];
+			uint32_t crc;
+		} write_response;
+
+		struct {
+			uint32_t common[3];
+			uint32_t data;
+			uint32_t crc;
+		} cycle_start;
+
+		struct {
+			uint32_t sy:4;
+			uint32_t tcode:4;
+			uint32_t channel:6;
+			uint32_t tag:2;
+			uint32_t data_length:16;
+
+			uint32_t crc;
+		} iso_data;
+	};
+};
+
+struct subaction {
+	uint32_t ack;
+	size_t length;
+	struct list link;
+	struct link_packet packet;
+};
+
+struct link_transaction {
+	int request_node, response_node, tlabel;
+	struct subaction *request, *response;
+	struct list request_list, response_list;
+	struct list link;
+};
+
+int decode_fcp(struct link_transaction *t);
+
+#endif /* __nosy_dump_h__ */

tools/hv/hv_get_dhcp_info.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+# This example script retrieves the DHCP state of a given interface.
+# In the interest of keeping the KVP daemon code free of distro specific
+# information; the kvp daemon code invokes this external script to gather
+# DHCP setting for the specific interface.
+#
+# Input: Name of the interface
+#
+# Output: The script prints the string "Enabled" to stdout to indicate
+#	that DHCP is enabled on the interface. If DHCP is not enabled,
+#	the script prints the string "Disabled" to stdout.
+#
+# Each Distro is expected to implement this script in a distro specific
+# fashion. For instance on Distros that ship with Network Manager enabled,
+# this script can be based on the Network Manager APIs for retrieving DHCP
+# information.
+
+if_file="/etc/sysconfig/network-scripts/ifcfg-"$1
+
+dhcp=$(grep "dhcp" $if_file 2>/dev/null)
+
+if [ "$dhcp" != "" ];
+then
+echo "Enabled"
+else
+echo "Disabled"
+fi

tools/hv/hv_get_dns_info.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+# This example script parses /etc/resolv.conf to retrive DNS information.
+# In the interest of keeping the KVP daemon code free of distro specific
+# information; the kvp daemon code invokes this external script to gather
+# DNS information.
+# This script is expected to print the nameserver values to stdout.
+# Each Distro is expected to implement this script in a distro specific
+# fashion. For instance on Distros that ship with Network Manager enabled,
+# this script can be based on the Network Manager APIs for retrieving DNS
+# entries.
+
+cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }'

tools/hv/hv_set_ifconfig.sh

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+# This example script activates an interface based on the specified
+# configuration.
+#
+# In the interest of keeping the KVP daemon code free of distro specific
+# information; the kvp daemon code invokes this external script to configure
+# the interface.
+#
+# The only argument to this script is the configuration file that is to
+# be used to configure the interface.
+#
+# Each Distro is expected to implement this script in a distro specific
+# fashion. For instance on Distros that ship with Network Manager enabled,
+# this script can be based on the Network Manager APIs for configuring the
+# interface.
+#
+# This example script is based on a RHEL environment.
+#
+# Here is the format of the ip configuration file:
+#
+# HWADDR=macaddr
+# DEVICE=interface name
+# BOOTPROTO=<protocol> (where <protocol> is "dhcp" if DHCP is configured
+#                       or "none" if no boot-time protocol should be used)
+#
+# IPADDR0=ipaddr1
+# IPADDR1=ipaddr2
+# IPADDRx=ipaddry (where y = x + 1)
+#
+# NETMASK0=netmask1
+# NETMASKx=netmasky (where y = x + 1)
+#
+# GATEWAY=ipaddr1
+# GATEWAYx=ipaddry (where y = x + 1)
+#
+# DNSx=ipaddrx (where first DNS address is tagged as DNS1 etc)
+#
+# IPV6 addresses will be tagged as IPV6ADDR, IPV6 gateway will be
+# tagged as IPV6_DEFAULTGW and IPV6 NETMASK will be tagged as
+# IPV6NETMASK.
+#
+# The host can specify multiple ipv4 and ipv6 addresses to be
+# configured for the interface. Furthermore, the configuration
+# needs to be persistent. A subsequent GET call on the interface
+# is expected to return the configuration that is set via the SET
+# call.
+#
+
+
+
+echo "IPV6INIT=yes" >> $1
+echo "NM_CONTROLLED=no" >> $1
+echo "PEERDNS=yes" >> $1
+echo "ONBOOT=yes" >> $1
+
+
+cp $1 /etc/sysconfig/network-scripts/
+
+
+interface=$(echo $1 | awk -F - '{ print $2 }')
+
+/sbin/ifdown $interface 2>/dev/null
+/sbin/ifup $interface 2>/dev/null

tools/hv/hv_vss_daemon.c

@@ -0,0 +1,249 @@
+/*
+ * An implementation of the host initiated guest snapshot for Hyper-V.
+ *
+ *
+ * Copyright (C) 2013, Microsoft, Inc.
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <sys/ioctl.h>
+#include <linux/types.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <mntent.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <ctype.h>
+#include <errno.h>
+#include <arpa/inet.h>
+#include <linux/fs.h>
+#include <linux/connector.h>
+#include <linux/hyperv.h>
+#include <linux/netlink.h>
+#include <syslog.h>
+
+static char vss_recv_buffer[4096];
+static char vss_send_buffer[4096];
+static struct sockaddr_nl addr;
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+
+static int vss_do_freeze(char *dir, unsigned int cmd, char *fs_op)
+{
+	int ret, fd = open(dir, O_RDONLY);
+
+	if (fd < 0)
+		return 1;
+	ret = ioctl(fd, cmd, 0);
+	syslog(LOG_INFO, "VSS: %s of %s: %s\n", fs_op, dir, strerror(errno));
+	close(fd);
+	return !!ret;
+}
+
+static int vss_operate(int operation)
+{
+	char *fs_op;
+	char match[] = "/dev/";
+	FILE *mounts;
+	struct mntent *ent;
+	unsigned int cmd;
+	int error = 0, root_seen = 0;
+
+	switch (operation) {
+	case VSS_OP_FREEZE:
+		cmd = FIFREEZE;
+		fs_op = "freeze";
+		break;
+	case VSS_OP_THAW:
+		cmd = FITHAW;
+		fs_op = "thaw";
+		break;
+	default:
+		return -1;
+	}
+
+	mounts = setmntent("/proc/mounts", "r");
+	if (mounts == NULL)
+		return -1;
+
+	while ((ent = getmntent(mounts))) {
+		if (strncmp(ent->mnt_fsname, match, strlen(match)))
+			continue;
+		if (strcmp(ent->mnt_type, "iso9660") == 0)
+			continue;
+		if (strcmp(ent->mnt_dir, "/") == 0) {
+			root_seen = 1;
+			continue;
+		}
+		error |= vss_do_freeze(ent->mnt_dir, cmd, fs_op);
+	}
+	endmntent(mounts);
+
+	if (root_seen) {
+		error |= vss_do_freeze("/", cmd, fs_op);
+	}
+
+	return error;
+}
+
+static int netlink_send(int fd, struct cn_msg *msg)
+{
+	struct nlmsghdr *nlh;
+	unsigned int size;
+	struct msghdr message;
+	char buffer[64];
+	struct iovec iov[2];
+
+	size = NLMSG_SPACE(sizeof(struct cn_msg) + msg->len);
+
+	nlh = (struct nlmsghdr *)buffer;
+	nlh->nlmsg_seq = 0;
+	nlh->nlmsg_pid = getpid();
+	nlh->nlmsg_type = NLMSG_DONE;
+	nlh->nlmsg_len = NLMSG_LENGTH(size - sizeof(*nlh));
+	nlh->nlmsg_flags = 0;
+
+	iov[0].iov_base = nlh;
+	iov[0].iov_len = sizeof(*nlh);
+
+	iov[1].iov_base = msg;
+	iov[1].iov_len = size;
+
+	memset(&message, 0, sizeof(message));
+	message.msg_name = &addr;
+	message.msg_namelen = sizeof(addr);
+	message.msg_iov = iov;
+	message.msg_iovlen = 2;
+
+	return sendmsg(fd, &message, 0);
+}
+
+int main(void)
+{
+	int fd, len, nl_group;
+	int error;
+	struct cn_msg *message;
+	struct pollfd pfd;
+	struct nlmsghdr *incoming_msg;
+	struct cn_msg	*incoming_cn_msg;
+	int	op;
+	struct hv_vss_msg *vss_msg;
+
+	if (daemon(1, 0))
+		return 1;
+
+	openlog("Hyper-V VSS", 0, LOG_USER);
+	syslog(LOG_INFO, "VSS starting; pid is:%d", getpid());
+
+	fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+	if (fd < 0) {
+		syslog(LOG_ERR, "netlink socket creation failed; error:%d", fd);
+		exit(EXIT_FAILURE);
+	}
+	addr.nl_family = AF_NETLINK;
+	addr.nl_pad = 0;
+	addr.nl_pid = 0;
+	addr.nl_groups = 0;
+
+
+	error = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+	if (error < 0) {
+		syslog(LOG_ERR, "bind failed; error:%d", error);
+		close(fd);
+		exit(EXIT_FAILURE);
+	}
+	nl_group = CN_VSS_IDX;
+	setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &nl_group, sizeof(nl_group));
+	/*
+	 * Register ourselves with the kernel.
+	 */
+	message = (struct cn_msg *)vss_send_buffer;
+	message->id.idx = CN_VSS_IDX;
+	message->id.val = CN_VSS_VAL;
+	message->ack = 0;
+	vss_msg = (struct hv_vss_msg *)message->data;
+	vss_msg->vss_hdr.operation = VSS_OP_REGISTER;
+
+	message->len = sizeof(struct hv_vss_msg);
+
+	len = netlink_send(fd, message);
+	if (len < 0) {
+		syslog(LOG_ERR, "netlink_send failed; error:%d", len);
+		close(fd);
+		exit(EXIT_FAILURE);
+	}
+
+	pfd.fd = fd;
+
+	while (1) {
+		struct sockaddr *addr_p = (struct sockaddr *) &addr;
+		socklen_t addr_l = sizeof(addr);
+		pfd.events = POLLIN;
+		pfd.revents = 0;
+		poll(&pfd, 1, -1);
+
+		len = recvfrom(fd, vss_recv_buffer, sizeof(vss_recv_buffer), 0,
+				addr_p, &addr_l);
+
+		if (len < 0) {
+			syslog(LOG_ERR, "recvfrom failed; pid:%u error:%d %s",
+					addr.nl_pid, errno, strerror(errno));
+			close(fd);
+			return -1;
+		}
+
+		if (addr.nl_pid) {
+			syslog(LOG_WARNING,
+				"Received packet from untrusted pid:%u",
+				addr.nl_pid);
+			continue;
+		}
+
+		incoming_msg = (struct nlmsghdr *)vss_recv_buffer;
+
+		if (incoming_msg->nlmsg_type != NLMSG_DONE)
+			continue;
+
+		incoming_cn_msg = (struct cn_msg *)NLMSG_DATA(incoming_msg);
+		vss_msg = (struct hv_vss_msg *)incoming_cn_msg->data;
+		op = vss_msg->vss_hdr.operation;
+		error =  HV_S_OK;
+
+		switch (op) {
+		case VSS_OP_FREEZE:
+		case VSS_OP_THAW:
+			error = vss_operate(op);
+			if (error)
+				error = HV_E_FAIL;
+			break;
+		default:
+			syslog(LOG_ERR, "Illegal op:%d\n", op);
+		}
+		vss_msg->error = error;
+		len = netlink_send(fd, incoming_cn_msg);
+		if (len < 0) {
+			syslog(LOG_ERR, "net_link send failed; error:%d", len);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+}

tools/include/tools/be_byteshift.h

@@ -0,0 +1,70 @@
+#ifndef _TOOLS_BE_BYTESHIFT_H
+#define _TOOLS_BE_BYTESHIFT_H
+
+#include <linux/types.h>
+
+static inline __u16 __get_unaligned_be16(const __u8 *p)
+{
+	return p[0] << 8 | p[1];
+}
+
+static inline __u32 __get_unaligned_be32(const __u8 *p)
+{
+	return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3];
+}
+
+static inline __u64 __get_unaligned_be64(const __u8 *p)
+{
+	return (__u64)__get_unaligned_be32(p) << 32 |
+	       __get_unaligned_be32(p + 4);
+}
+
+static inline void __put_unaligned_be16(__u16 val, __u8 *p)
+{
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void __put_unaligned_be32(__u32 val, __u8 *p)
+{
+	__put_unaligned_be16(val >> 16, p);
+	__put_unaligned_be16(val, p + 2);
+}
+
+static inline void __put_unaligned_be64(__u64 val, __u8 *p)
+{
+	__put_unaligned_be32(val >> 32, p);
+	__put_unaligned_be32(val, p + 4);
+}
+
+static inline __u16 get_unaligned_be16(const void *p)
+{
+	return __get_unaligned_be16((const __u8 *)p);
+}
+
+static inline __u32 get_unaligned_be32(const void *p)
+{
+	return __get_unaligned_be32((const __u8 *)p);
+}
+
+static inline __u64 get_unaligned_be64(const void *p)
+{
+	return __get_unaligned_be64((const __u8 *)p);
+}
+
+static inline void put_unaligned_be16(__u16 val, void *p)
+{
+	__put_unaligned_be16(val, p);
+}
+
+static inline void put_unaligned_be32(__u32 val, void *p)
+{
+	__put_unaligned_be32(val, p);
+}
+
+static inline void put_unaligned_be64(__u64 val, void *p)
+{
+	__put_unaligned_be64(val, p);
+}
+
+#endif /* _TOOLS_BE_BYTESHIFT_H */

tools/include/tools/le_byteshift.h

@@ -0,0 +1,70 @@
+#ifndef _TOOLS_LE_BYTESHIFT_H
+#define _TOOLS_LE_BYTESHIFT_H
+
+#include <linux/types.h>
+
+static inline __u16 __get_unaligned_le16(const __u8 *p)
+{
+	return p[0] | p[1] << 8;
+}
+
+static inline __u32 __get_unaligned_le32(const __u8 *p)
+{
+	return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24;
+}
+
+static inline __u64 __get_unaligned_le64(const __u8 *p)
+{
+	return (__u64)__get_unaligned_le32(p + 4) << 32 |
+	       __get_unaligned_le32(p);
+}
+
+static inline void __put_unaligned_le16(__u16 val, __u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+}
+
+static inline void __put_unaligned_le32(__u32 val, __u8 *p)
+{
+	__put_unaligned_le16(val >> 16, p + 2);
+	__put_unaligned_le16(val, p);
+}
+
+static inline void __put_unaligned_le64(__u64 val, __u8 *p)
+{
+	__put_unaligned_le32(val >> 32, p + 4);
+	__put_unaligned_le32(val, p);
+}
+
+static inline __u16 get_unaligned_le16(const void *p)
+{
+	return __get_unaligned_le16((const __u8 *)p);
+}
+
+static inline __u32 get_unaligned_le32(const void *p)
+{
+	return __get_unaligned_le32((const __u8 *)p);
+}
+
+static inline __u64 get_unaligned_le64(const void *p)
+{
+	return __get_unaligned_le64((const __u8 *)p);
+}
+
+static inline void put_unaligned_le16(__u16 val, void *p)
+{
+	__put_unaligned_le16(val, p);
+}
+
+static inline void put_unaligned_le32(__u32 val, void *p)
+{
+	__put_unaligned_le32(val, p);
+}
+
+static inline void put_unaligned_le64(__u64 val, void *p)
+{
+	__put_unaligned_le64(val, p);
+}
+
+#endif /* _TOOLS_LE_BYTESHIFT_H */

tools/lguest/.gitignore

@@ -0,0 +1 @@
+lguest

tools/lguest/Makefile

@@ -0,0 +1,8 @@
+# This creates the demonstration utility "lguest" which runs a Linux guest.
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
+
+all: lguest
+
+clean:
+	rm -f lguest

tools/lguest/extract

@@ -0,0 +1,58 @@
+#! /bin/sh
+
+set -e
+
+PREFIX=$1
+shift
+
+trap 'rm -r $TMPDIR' 0
+TMPDIR=`mktemp -d`
+
+exec 3>/dev/null
+for f; do
+    while IFS="
+" read -r LINE; do
+	case "$LINE" in
+	    *$PREFIX:[0-9]*:\**)
+		NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
+		if [ -f $TMPDIR/$NUM ]; then
+		    echo "$TMPDIR/$NUM already exits prior to $f"
+		    exit 1
+		fi
+		exec 3>>$TMPDIR/$NUM
+		echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
+		/bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3
+		;;
+	    *$PREFIX:[0-9]*)
+		NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
+		if [ -f $TMPDIR/$NUM ]; then
+		    echo "$TMPDIR/$NUM already exits prior to $f"
+		    exit 1
+		fi
+		exec 3>>$TMPDIR/$NUM
+		echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
+		/bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3
+		;;
+	    *:\**)
+		/bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3
+		echo >&3
+		exec 3>/dev/null
+		;;
+	    *)
+		/bin/echo "$LINE" >&3
+		;;
+	esac
+    done < $f
+    echo >&3
+    exec 3>/dev/null
+done
+
+LASTFILE=""
+for f in $TMPDIR/*; do
+    if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then
+	LASTFILE=$(cat $TMPDIR/.$(basename $f) )
+	echo "[ $LASTFILE ]"
+    fi
+    cat $f
+done
+

tools/lguest/lguest.txt

@@ -0,0 +1,125 @@
+      __
+ (___()'`;  Rusty's Remarkably Unreliable Guide to Lguest
+ /,    /`      - or, A Young Coder's Illustrated Hypervisor
+ \\"--\\    http://lguest.ozlabs.org
+
+Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel,
+for Linux developers and users to experiment with virtualization with the
+minimum of complexity.  Nonetheless, it should have sufficient features to
+make it useful for specific tasks, and, of course, you are encouraged to fork
+and enhance it (see drivers/lguest/README).
+
+Features:
+
+- Kernel module which runs in a normal kernel.
+- Simple I/O model for communication.
+- Simple program to create new guests.
+- Logo contains cute puppies: http://lguest.ozlabs.org
+
+Developer features:
+
+- Fun to hack on.
+- No ABI: being tied to a specific kernel anyway, you can change anything.
+- Many opportunities for improvement or feature implementation.
+
+Running Lguest:
+
+- The easiest way to run lguest is to use same kernel as guest and host.
+  You can configure them differently, but usually it's easiest not to.
+
+  You will need to configure your kernel with the following options:
+
+  "Processor type and features":
+     "Paravirtualized guest support" = Y
+        "Lguest guest support" = Y
+     "High Memory Support" = off/4GB
+     "Alignment value to which kernel should be aligned" = 0x100000
+        (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and
+         CONFIG_PHYSICAL_ALIGN=0x100000)
+
+  "Device Drivers":
+     "Block devices"
+        "Virtio block driver" = M/Y
+     "Network device support"
+        "Universal TUN/TAP device driver support" = M/Y
+        "Virtio network driver" = M/Y
+           (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m)
+
+  "Virtualization"
+     "Linux hypervisor example code" = M/Y
+        (CONFIG_LGUEST=m)
+
+- A tool called "lguest" is available in this directory: type "make"
+  to build it.  If you didn't build your kernel in-tree, use "make
+  O=<builddir>".
+
+- Create or find a root disk image.  There are several useful ones
+  around, such as the xm-test tiny root image at
+	  http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img
+
+  For more serious work, I usually use a distribution ISO image and
+  install it under qemu, then make multiple copies:
+
+	  dd if=/dev/zero of=rootfile bs=1M count=2048
+	  qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d
+
+  Make sure that you install a getty on /dev/hvc0 if you want to log in on the
+  console!
+
+- "modprobe lg" if you built it as a module.
+
+- Run an lguest as root:
+
+      tools/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
+        --block=rootfile root=/dev/vda
+
+   Explanation:
+    64: the amount of memory to use, in MB.
+
+    vmlinux: the kernel image found in the top of your build directory.  You
+       can also use a standard bzImage.
+
+    --tunnet=192.168.19.1: configures a "tap" device for networking with this
+       IP address.
+
+    --block=rootfile: a file or block device which becomes /dev/vda
+       inside the guest.
+
+    root=/dev/vda: this (and anything else on the command line) are
+       kernel boot parameters.
+
+- Configuring networking.  I usually have the host masquerade, using
+  "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 >
+  /proc/sys/net/ipv4/ip_forward".  In this example, I would configure
+  eth0 inside the guest at 192.168.19.2.
+
+  Another method is to bridge the tap device to an external interface
+  using --tunnet=bridge:<bridgename>, and perhaps run dhcp on the guest
+  to obtain an IP address.  The bridge needs to be configured first:
+  this option simply adds the tap interface to it.
+
+  A simple example on my system:
+
+    ifconfig eth0 0.0.0.0
+    brctl addbr lg0
+    ifconfig lg0 up
+    brctl addif lg0 eth0
+    dhclient lg0
+
+  Then use --tunnet=bridge:lg0 when launching the guest.
+
+  See:
+  
+    http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
+    
+  for general information on how to get bridging to work.
+
+- Random number generation. Using the --rng option will provide a
+  /dev/hwrng in the guest that will read from the host's /dev/random.
+  Use this option in conjunction with rng-tools (see ../hw_random.txt)
+  to provide entropy to the guest kernel's /dev/random.
+
+There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest
+
+Good luck!
+Rusty Russell rusty@rustcorp.com.au.

tools/lib/lk/Makefile

@@ -0,0 +1,35 @@
+include ../../scripts/Makefile.include
+
+# guard against environment variables
+LIB_H=
+LIB_OBJS=
+
+LIB_H += debugfs.h
+
+LIB_OBJS += $(OUTPUT)debugfs.o
+
+LIBFILE = liblk.a
+
+CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
+EXTLIBS = -lpthread -lrt -lelf -lm
+ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_LDFLAGS = $(LDFLAGS)
+
+RM = rm -f
+
+$(LIBFILE): $(LIB_OBJS)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $(OUTPUT)$@ $(LIB_OBJS)
+
+$(LIB_OBJS): $(LIB_H)
+
+$(OUTPUT)%.o: %.c
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.c
+	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+$(OUTPUT)%.o: %.S
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+
+clean:
+	$(RM) $(LIB_OBJS) $(LIBFILE)
+
+.PHONY: clean

tools/lib/lk/debugfs.c

@@ -0,0 +1,100 @@
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <sys/vfs.h>
+#include <sys/mount.h>
+#include <linux/kernel.h>
+
+#include "debugfs.h"
+
+char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
+
+static const char * const debugfs_known_mountpoints[] = {
+	"/sys/kernel/debug/",
+	"/debug/",
+	0,
+};
+
+static bool debugfs_found;
+
+/* find the path to the mounted debugfs */
+const char *debugfs_find_mountpoint(void)
+{
+	const char * const *ptr;
+	char type[100];
+	FILE *fp;
+
+	if (debugfs_found)
+		return (const char *)debugfs_mountpoint;
+
+	ptr = debugfs_known_mountpoints;
+	while (*ptr) {
+		if (debugfs_valid_mountpoint(*ptr) == 0) {
+			debugfs_found = true;
+			strcpy(debugfs_mountpoint, *ptr);
+			return debugfs_mountpoint;
+		}
+		ptr++;
+	}
+
+	/* give up and parse /proc/mounts */
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		return NULL;
+
+	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+		      debugfs_mountpoint, type) == 2) {
+		if (strcmp(type, "debugfs") == 0)
+			break;
+	}
+	fclose(fp);
+
+	if (strcmp(type, "debugfs") != 0)
+		return NULL;
+
+	debugfs_found = true;
+
+	return debugfs_mountpoint;
+}
+
+/* verify that a mountpoint is actually a debugfs instance */
+
+int debugfs_valid_mountpoint(const char *debugfs)
+{
+	struct statfs st_fs;
+
+	if (statfs(debugfs, &st_fs) < 0)
+		return -ENOENT;
+	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+		return -ENOENT;
+
+	return 0;
+}
+
+/* mount the debugfs somewhere if it's not mounted */
+char *debugfs_mount(const char *mountpoint)
+{
+	/* see if it's already mounted */
+	if (debugfs_find_mountpoint())
+		goto out;
+
+	/* if not mounted and no argument */
+	if (mountpoint == NULL) {
+		/* see if environment variable set */
+		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
+		/* if no environment variable, use default */
+		if (mountpoint == NULL)
+			mountpoint = "/sys/kernel/debug";
+	}
+
+	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
+		return NULL;
+
+	/* save the mountpoint */
+	debugfs_found = true;
+	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
+out:
+	return debugfs_mountpoint;
+}

tools/lib/lk/debugfs.h

@@ -0,0 +1,29 @@
+#ifndef __LK_DEBUGFS_H__
+#define __LK_DEBUGFS_H__
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef PERF_DEBUGFS_ENVIRONMENT
+#define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
+#endif
+
+const char *debugfs_find_mountpoint(void);
+int debugfs_valid_mountpoint(const char *debugfs);
+char *debugfs_mount(const char *mountpoint);
+
+extern char debugfs_mountpoint[];
+
+#endif /* __LK_DEBUGFS_H__ */

tools/lib/traceevent/.gitignore

@@ -0,0 +1 @@
+TRACEEVENT-CFLAGS

tools/lib/traceevent/Makefile

@@ -0,0 +1,319 @@
+# trace-cmd version
+EP_VERSION = 1
+EP_PATCHLEVEL = 1
+EP_EXTRAVERSION = 0
+
+# file format version
+FILE_VERSION = 6
+
+MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
+EXT = -std=gnu99
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+prefix ?= /usr/local
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+man_dir = $(prefix)/share/man
+man_dir_SQ = '$(subst ','\'',$(man_dir))'
+html_install = $(prefix)/share/kernelshark/html
+html_install_SQ = '$(subst ','\'',$(html_install))'
+img_install = $(prefix)/share/kernelshark/html/images
+img_install_SQ = '$(subst ','\'',$(img_install))'
+
+export man_dir man_dir_SQ html_install html_install_SQ INSTALL
+export img_install img_install_SQ
+export DESTDIR DESTDIR_SQ
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ("$(origin O)", "command line")
+  BUILD_OUTPUT := $(O)
+endif
+
+ifeq ($(BUILD_SRC),)
+ifneq ($(BUILD_OUTPUT),)
+
+define build_output
+	$(if $(VERBOSE:1=),@)$(MAKE) -C $(BUILD_OUTPUT) 	\
+	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+endef
+
+saved-output := $(BUILD_OUTPUT)
+BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
+$(if $(BUILD_OUTPUT),, \
+     $(error output directory "$(saved-output)" does not exist))
+
+all: sub-make
+
+gui: force
+	$(call build_output, all_cmd)
+
+$(filter-out gui,$(MAKECMDGOALS)): sub-make
+
+sub-make: force
+	$(call build_output, $(MAKECMDGOALS))
+
+
+# Leave processing to above invocation of make
+skip-makefile := 1
+
+endif # BUILD_OUTPUT
+endif # BUILD_SRC
+
+# We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(skip-makefile),)
+
+srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
+objtree		:= $(CURDIR)
+src		:= $(srctree)
+obj		:= $(objtree)
+
+export prefix bindir src obj
+
+# Shell quotes
+bindir_SQ = $(subst ','\'',$(bindir))
+bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+
+LIB_FILE = libtraceevent.a libtraceevent.so
+
+CONFIG_INCLUDES = 
+CONFIG_LIBS	=
+CONFIG_FLAGS	=
+
+VERSION		= $(EP_VERSION)
+PATCHLEVEL	= $(EP_PATCHLEVEL)
+EXTRAVERSION	= $(EP_EXTRAVERSION)
+
+OBJ		= $@
+N		=
+
+export Q VERBOSE
+
+EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
+
+INCLUDES = -I. $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS if not set elsewhere
+CFLAGS ?= -g -Wall
+
+# Append required CFLAGS
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
+
+ifeq ($(VERBOSE),1)
+  Q =
+  print_compile =
+  print_app_build =
+  print_fpic_compile =
+  print_shared_lib_compile =
+  print_plugin_obj_compile =
+  print_plugin_build =
+  print_install =
+else
+  Q = @
+  print_compile =		echo '  CC                 '$(OBJ);
+  print_app_build =		echo '  BUILD              '$(OBJ);
+  print_fpic_compile =		echo '  CC FPIC            '$(OBJ);
+  print_shared_lib_compile =	echo '  BUILD SHARED LIB   '$(OBJ);
+  print_plugin_obj_compile =	echo '  CC PLUGIN OBJ      '$(OBJ);
+  print_plugin_build =		echo '  CC PLUGI           '$(OBJ);
+  print_static_lib_build =	echo '  BUILD STATIC LIB   '$(OBJ);
+  print_install =		echo '  INSTALL     '$1'	to	$(DESTDIR_SQ)$2';
+endif
+
+do_fpic_compile =					\
+	($(print_fpic_compile)				\
+	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
+
+do_app_build =						\
+	($(print_app_build)				\
+	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
+
+do_compile_shared_library =			\
+	($(print_shared_lib_compile)		\
+	$(CC) --shared $^ -o $@)
+
+do_compile_plugin_obj =				\
+	($(print_plugin_obj_compile)		\
+	$(CC) -c $(CFLAGS) -fPIC -o $@ $<)
+
+do_plugin_build =				\
+	($(print_plugin_build)			\
+	$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<)
+
+do_build_static_lib =				\
+	($(print_static_lib_build)		\
+	$(RM) $@;  $(AR) rcs $@ $^)
+
+
+define do_compile
+	$(print_compile)						\
+	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
+endef
+
+$(obj)/%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+PEVENT_LIB_OBJS = event-parse.o trace-seq.o parse-filter.o parse-utils.o
+
+ALL_OBJS = $(PEVENT_LIB_OBJS)
+
+CMD_TARGETS = $(LIB_FILE)
+
+TARGETS = $(CMD_TARGETS)
+
+
+all: all_cmd
+
+all_cmd: $(CMD_TARGETS)
+
+libtraceevent.so: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_compile_shared_library)
+
+libtraceevent.a: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_build_static_lib)
+
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
+	$(Q)$(do_fpic_compile)
+
+define make_version.h
+	(echo '/* This file is automatically generated. Do not modify. */';		\
+	echo \#define VERSION_CODE $(shell						\
+	expr $(VERSION) \* 256 + $(PATCHLEVEL));					\
+	echo '#define EXTRAVERSION ' $(EXTRAVERSION);					\
+	echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';	\
+	echo '#define FILE_VERSION '$(FILE_VERSION);					\
+	) > $1
+endef
+
+define update_version.h
+	($(call make_version.h, $@.tmp);		\
+	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
+		rm -f $@.tmp;				\
+	else						\
+		echo '  UPDATE                 $@';	\
+		mv -f $@.tmp $@;			\
+	fi);
+endef
+
+ep_version.h: force
+	$(Q)$(N)$(call update_version.h)
+
+VERSION_FILES = ep_version.h
+
+define update_dir
+	(echo $1 > $@.tmp;	\
+	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
+		rm -f $@.tmp;				\
+	else						\
+		echo '  UPDATE                 $@';	\
+		mv -f $@.tmp $@;			\
+	fi);
+endef
+
+## make deps
+
+all_objs := $(sort $(ALL_OBJS))
+all_deps := $(all_objs:%.o=.%.d)
+
+# let .d file also depends on the source and header files
+define check_deps
+		@set -e; $(RM) $@; \
+		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+		$(RM) $@.$$$$
+endef
+
+$(gui_deps): ks_version.h
+$(non_gui_deps): tc_version.h
+
+$(all_deps): .%.d: $(src)/%.c
+	$(Q)$(call check_deps)
+
+$(all_objs) : %.o : .%.d
+
+dep_includes := $(wildcard $(all_deps))
+
+ifneq ($(dep_includes),)
+ include $(dep_includes)
+endif
+
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+TRACEEVENT-CFLAGS: force
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "    * new build flags or cross compiler"; \
+		echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
+            fi
+
+tags:	force
+	$(RM) tags
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+
+TAGS:	force
+	$(RM) TAGS
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+
+define do_install
+	$(print_install)				\
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd install_plugins install_python
+	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
+
+install: install_lib
+
+clean:
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) TRACEEVENT-CFLAGS tags TAGS
+
+endif # skip-makefile
+
+PHONY += force
+force:
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)

tools/lib/traceevent/event-parse.h

@@ -0,0 +1,844 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef _PARSE_EVENTS_H
+#define _PARSE_EVENTS_H
+
+#include <stdarg.h>
+#include <regex.h>
+
+#ifndef __maybe_unused
+#define __maybe_unused __attribute__((unused))
+#endif
+
+/* ----------------------- trace_seq ----------------------- */
+
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+#ifndef DEBUG_RECORD
+#define DEBUG_RECORD 0
+#endif
+
+struct pevent_record {
+	unsigned long long	ts;
+	unsigned long long	offset;
+	long long		missed_events;	/* buffer dropped events before */
+	int			record_size;	/* size of binary record */
+	int			size;		/* size of data */
+	void			*data;
+	int			cpu;
+	int			ref_count;
+	int			locked;		/* Do not free, even if ref_count is zero */
+	void			*priv;
+#if DEBUG_RECORD
+	struct pevent_record	*prev;
+	struct pevent_record	*next;
+	long			alloc_addr;
+#endif
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+	char			*buffer;
+	unsigned int		buffer_size;
+	unsigned int		len;
+	unsigned int		readpos;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+
+/* ----------------------- pevent ----------------------- */
+
+struct pevent;
+struct event_format;
+
+typedef int (*pevent_event_handler_func)(struct trace_seq *s,
+					 struct pevent_record *record,
+					 struct event_format *event,
+					 void *context);
+
+typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
+typedef int (*pevent_plugin_unload_func)(void);
+
+struct plugin_option {
+	struct plugin_option		*next;
+	void				*handle;
+	char				*file;
+	char				*name;
+	char				*plugin_alias;
+	char				*description;
+	char				*value;
+	void				*priv;
+	int				set;
+};
+
+/*
+ * Plugin hooks that can be called:
+ *
+ * PEVENT_PLUGIN_LOADER:  (required)
+ *   The function name to initialized the plugin.
+ *
+ *   int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+ *
+ * PEVENT_PLUGIN_UNLOADER:  (optional)
+ *   The function called just before unloading
+ *
+ *   int PEVENT_PLUGIN_UNLOADER(void)
+ *
+ * PEVENT_PLUGIN_OPTIONS:  (optional)
+ *   Plugin options that can be set before loading
+ *
+ *   struct plugin_option PEVENT_PLUGIN_OPTIONS[] = {
+ *	{
+ *		.name = "option-name",
+ *		.plugin_alias = "overide-file-name", (optional)
+ *		.description = "description of option to show users",
+ *	},
+ *	{
+ *		.name = NULL,
+ *	},
+ *   };
+ *
+ *   Array must end with .name = NULL;
+ *
+ *
+ *   .plugin_alias is used to give a shorter name to access
+ *   the vairable. Useful if a plugin handles more than one event.
+ *
+ * PEVENT_PLUGIN_ALIAS: (optional)
+ *   The name to use for finding options (uses filename if not defined)
+ */
+#define PEVENT_PLUGIN_LOADER pevent_plugin_loader
+#define PEVENT_PLUGIN_UNLOADER pevent_plugin_unloader
+#define PEVENT_PLUGIN_OPTIONS pevent_plugin_options
+#define PEVENT_PLUGIN_ALIAS pevent_plugin_alias
+#define _MAKE_STR(x)	#x
+#define MAKE_STR(x)	_MAKE_STR(x)
+#define PEVENT_PLUGIN_LOADER_NAME MAKE_STR(PEVENT_PLUGIN_LOADER)
+#define PEVENT_PLUGIN_UNLOADER_NAME MAKE_STR(PEVENT_PLUGIN_UNLOADER)
+#define PEVENT_PLUGIN_OPTIONS_NAME MAKE_STR(PEVENT_PLUGIN_OPTIONS)
+#define PEVENT_PLUGIN_ALIAS_NAME MAKE_STR(PEVENT_PLUGIN_ALIAS)
+
+#define NSECS_PER_SEC		1000000000ULL
+#define NSECS_PER_USEC		1000ULL
+
+enum format_flags {
+	FIELD_IS_ARRAY		= 1,
+	FIELD_IS_POINTER	= 2,
+	FIELD_IS_SIGNED		= 4,
+	FIELD_IS_STRING		= 8,
+	FIELD_IS_DYNAMIC	= 16,
+	FIELD_IS_LONG		= 32,
+	FIELD_IS_FLAG		= 64,
+	FIELD_IS_SYMBOLIC	= 128,
+};
+
+struct format_field {
+	struct format_field	*next;
+	struct event_format	*event;
+	char			*type;
+	char			*name;
+	int			offset;
+	int			size;
+	unsigned int		arraylen;
+	unsigned int		elementsize;
+	unsigned long		flags;
+};
+
+struct format {
+	int			nr_common;
+	int			nr_fields;
+	struct format_field	*common_fields;
+	struct format_field	*fields;
+};
+
+struct print_arg_atom {
+	char			*atom;
+};
+
+struct print_arg_string {
+	char			*string;
+	int			offset;
+};
+
+struct print_arg_field {
+	char			*name;
+	struct format_field	*field;
+};
+
+struct print_flag_sym {
+	struct print_flag_sym	*next;
+	char			*value;
+	char			*str;
+};
+
+struct print_arg_typecast {
+	char 			*type;
+	struct print_arg	*item;
+};
+
+struct print_arg_flags {
+	struct print_arg	*field;
+	char			*delim;
+	struct print_flag_sym	*flags;
+};
+
+struct print_arg_symbol {
+	struct print_arg	*field;
+	struct print_flag_sym	*symbols;
+};
+
+struct print_arg_hex {
+	struct print_arg	*field;
+	struct print_arg	*size;
+};
+
+struct print_arg_dynarray {
+	struct format_field	*field;
+	struct print_arg	*index;
+};
+
+struct print_arg;
+
+struct print_arg_op {
+	char			*op;
+	int			prio;
+	struct print_arg	*left;
+	struct print_arg	*right;
+};
+
+struct pevent_function_handler;
+
+struct print_arg_func {
+	struct pevent_function_handler	*func;
+	struct print_arg		*args;
+};
+
+enum print_arg_type {
+	PRINT_NULL,
+	PRINT_ATOM,
+	PRINT_FIELD,
+	PRINT_FLAGS,
+	PRINT_SYMBOL,
+	PRINT_HEX,
+	PRINT_TYPE,
+	PRINT_STRING,
+	PRINT_BSTRING,
+	PRINT_DYNAMIC_ARRAY,
+	PRINT_OP,
+	PRINT_FUNC,
+};
+
+struct print_arg {
+	struct print_arg		*next;
+	enum print_arg_type		type;
+	union {
+		struct print_arg_atom		atom;
+		struct print_arg_field		field;
+		struct print_arg_typecast	typecast;
+		struct print_arg_flags		flags;
+		struct print_arg_symbol		symbol;
+		struct print_arg_hex		hex;
+		struct print_arg_func		func;
+		struct print_arg_string		string;
+		struct print_arg_op		op;
+		struct print_arg_dynarray	dynarray;
+	};
+};
+
+struct print_fmt {
+	char			*format;
+	struct print_arg	*args;
+};
+
+struct event_format {
+	struct pevent		*pevent;
+	char			*name;
+	int			id;
+	int			flags;
+	struct format		format;
+	struct print_fmt	print_fmt;
+	char			*system;
+	pevent_event_handler_func handler;
+	void			*context;
+};
+
+enum {
+	EVENT_FL_ISFTRACE	= 0x01,
+	EVENT_FL_ISPRINT	= 0x02,
+	EVENT_FL_ISBPRINT	= 0x04,
+	EVENT_FL_ISFUNCENT	= 0x10,
+	EVENT_FL_ISFUNCRET	= 0x20,
+
+	EVENT_FL_FAILED		= 0x80000000
+};
+
+enum event_sort_type {
+	EVENT_SORT_ID,
+	EVENT_SORT_NAME,
+	EVENT_SORT_SYSTEM,
+};
+
+enum event_type {
+	EVENT_ERROR,
+	EVENT_NONE,
+	EVENT_SPACE,
+	EVENT_NEWLINE,
+	EVENT_OP,
+	EVENT_DELIM,
+	EVENT_ITEM,
+	EVENT_DQUOTE,
+	EVENT_SQUOTE,
+};
+
+typedef unsigned long long (*pevent_func_handler)(struct trace_seq *s,
+					     unsigned long long *args);
+
+enum pevent_func_arg_type {
+	PEVENT_FUNC_ARG_VOID,
+	PEVENT_FUNC_ARG_INT,
+	PEVENT_FUNC_ARG_LONG,
+	PEVENT_FUNC_ARG_STRING,
+	PEVENT_FUNC_ARG_PTR,
+	PEVENT_FUNC_ARG_MAX_TYPES
+};
+
+enum pevent_flag {
+	PEVENT_NSEC_OUTPUT		= 1,	/* output in NSECS */
+};
+
+#define PEVENT_ERRORS 							      \
+	_PE(MEM_ALLOC_FAILED,	"failed to allocate memory"),		      \
+	_PE(PARSE_EVENT_FAILED,	"failed to parse event"),		      \
+	_PE(READ_ID_FAILED,	"failed to read event id"),		      \
+	_PE(READ_FORMAT_FAILED,	"failed to read event format"),		      \
+	_PE(READ_PRINT_FAILED,	"failed to read event print fmt"), 	      \
+	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
+	_PE(INVALID_ARG_TYPE,	"invalid argument type")
+
+#undef _PE
+#define _PE(__code, __str) PEVENT_ERRNO__ ## __code
+enum pevent_errno {
+	PEVENT_ERRNO__SUCCESS			= 0,
+
+	/*
+	 * Choose an arbitrary negative big number not to clash with standard
+	 * errno since SUS requires the errno has distinct positive values.
+	 * See 'Issue 6' in the link below.
+	 *
+	 * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+	 */
+	__PEVENT_ERRNO__START			= -100000,
+
+	PEVENT_ERRORS,
+
+	__PEVENT_ERRNO__END,
+};
+#undef _PE
+
+struct cmdline;
+struct cmdline_list;
+struct func_map;
+struct func_list;
+struct event_handler;
+
+struct pevent {
+	int ref_count;
+
+	int header_page_ts_offset;
+	int header_page_ts_size;
+	int header_page_size_offset;
+	int header_page_size_size;
+	int header_page_data_offset;
+	int header_page_data_size;
+	int header_page_overwrite;
+
+	int file_bigendian;
+	int host_bigendian;
+
+	int latency_format;
+
+	int old_format;
+
+	int cpus;
+	int long_size;
+
+	struct cmdline *cmdlines;
+	struct cmdline_list *cmdlist;
+	int cmdline_count;
+
+	struct func_map *func_map;
+	struct func_list *funclist;
+	unsigned int func_count;
+
+	struct printk_map *printk_map;
+	struct printk_list *printklist;
+	unsigned int printk_count;
+
+
+	struct event_format **events;
+	int nr_events;
+	struct event_format **sort_events;
+	enum event_sort_type last_type;
+
+	int type_offset;
+	int type_size;
+
+	int pid_offset;
+	int pid_size;
+
+ 	int pc_offset;
+	int pc_size;
+
+	int flags_offset;
+	int flags_size;
+
+	int ld_offset;
+	int ld_size;
+
+	int print_raw;
+
+	int test_filters;
+
+	int flags;
+
+	struct format_field *bprint_ip_field;
+	struct format_field *bprint_fmt_field;
+	struct format_field *bprint_buf_field;
+
+	struct event_handler *handlers;
+	struct pevent_function_handler *func_handlers;
+
+	/* cache */
+	struct event_format *last_event;
+};
+
+static inline void pevent_set_flag(struct pevent *pevent, int flag)
+{
+	pevent->flags |= flag;
+}
+
+static inline unsigned short
+__data2host2(struct pevent *pevent, unsigned short data)
+{
+	unsigned short swap;
+
+	if (pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 8) |
+		((data & (0xffULL << 8)) >> 8);
+
+	return swap;
+}
+
+static inline unsigned int
+__data2host4(struct pevent *pevent, unsigned int data)
+{
+	unsigned int swap;
+
+	if (pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 24) |
+		((data & (0xffULL << 8)) << 8) |
+		((data & (0xffULL << 16)) >> 8) |
+		((data & (0xffULL << 24)) >> 24);
+
+	return swap;
+}
+
+static inline unsigned long long
+__data2host8(struct pevent *pevent, unsigned long long data)
+{
+	unsigned long long swap;
+
+	if (pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 56) |
+		((data & (0xffULL << 8)) << 40) |
+		((data & (0xffULL << 16)) << 24) |
+		((data & (0xffULL << 24)) << 8) |
+		((data & (0xffULL << 32)) >> 8) |
+		((data & (0xffULL << 40)) >> 24) |
+		((data & (0xffULL << 48)) >> 40) |
+		((data & (0xffULL << 56)) >> 56);
+
+	return swap;
+}
+
+#define data2host2(pevent, ptr)		__data2host2(pevent, *(unsigned short *)(ptr))
+#define data2host4(pevent, ptr)		__data2host4(pevent, *(unsigned int *)(ptr))
+#define data2host8(pevent, ptr)					\
+({								\
+	unsigned long long __val;				\
+								\
+	memcpy(&__val, (ptr), sizeof(unsigned long long));	\
+	__data2host8(pevent, __val);				\
+})
+
+/* taken from kernel/trace/trace.h */
+enum trace_flag_type {
+	TRACE_FLAG_IRQS_OFF		= 0x01,
+	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
+	TRACE_FLAG_NEED_RESCHED		= 0x04,
+	TRACE_FLAG_HARDIRQ		= 0x08,
+	TRACE_FLAG_SOFTIRQ		= 0x10,
+};
+
+int pevent_register_comm(struct pevent *pevent, const char *comm, int pid);
+int pevent_register_function(struct pevent *pevent, char *name,
+			     unsigned long long addr, char *mod);
+int pevent_register_print_string(struct pevent *pevent, char *fmt,
+				 unsigned long long addr);
+int pevent_pid_is_registered(struct pevent *pevent, int pid);
+
+void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
+			struct pevent_record *record);
+
+int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long size,
+			     int long_size);
+
+enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
+				     unsigned long size, const char *sys);
+enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+				      unsigned long size, const char *sys);
+void pevent_free_format(struct event_format *event);
+
+void *pevent_get_field_raw(struct trace_seq *s, struct event_format *event,
+			   const char *name, struct pevent_record *record,
+			   int *len, int err);
+
+int pevent_get_field_val(struct trace_seq *s, struct event_format *event,
+			 const char *name, struct pevent_record *record,
+			 unsigned long long *val, int err);
+int pevent_get_common_field_val(struct trace_seq *s, struct event_format *event,
+				const char *name, struct pevent_record *record,
+				unsigned long long *val, int err);
+int pevent_get_any_field_val(struct trace_seq *s, struct event_format *event,
+			     const char *name, struct pevent_record *record,
+			     unsigned long long *val, int err);
+
+int pevent_print_num_field(struct trace_seq *s, const char *fmt,
+			   struct event_format *event, const char *name,
+			   struct pevent_record *record, int err);
+
+int pevent_register_event_handler(struct pevent *pevent, int id, char *sys_name, char *event_name,
+				  pevent_event_handler_func func, void *context);
+int pevent_register_print_function(struct pevent *pevent,
+				   pevent_func_handler func,
+				   enum pevent_func_arg_type ret_type,
+				   char *name, ...);
+
+struct format_field *pevent_find_common_field(struct event_format *event, const char *name);
+struct format_field *pevent_find_field(struct event_format *event, const char *name);
+struct format_field *pevent_find_any_field(struct event_format *event, const char *name);
+
+const char *pevent_find_function(struct pevent *pevent, unsigned long long addr);
+unsigned long long
+pevent_find_function_address(struct pevent *pevent, unsigned long long addr);
+unsigned long long pevent_read_number(struct pevent *pevent, const void *ptr, int size);
+int pevent_read_number_field(struct format_field *field, const void *data,
+			     unsigned long long *value);
+
+struct event_format *pevent_find_event(struct pevent *pevent, int id);
+
+struct event_format *
+pevent_find_event_by_name(struct pevent *pevent, const char *sys, const char *name);
+
+void pevent_data_lat_fmt(struct pevent *pevent,
+			 struct trace_seq *s, struct pevent_record *record);
+int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
+struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
+int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
+const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
+void pevent_event_info(struct trace_seq *s, struct event_format *event,
+		       struct pevent_record *record);
+int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
+		    char *buf, size_t buflen);
+
+struct event_format **pevent_list_events(struct pevent *pevent, enum event_sort_type);
+struct format_field **pevent_event_common_fields(struct event_format *event);
+struct format_field **pevent_event_fields(struct event_format *event);
+
+static inline int pevent_get_cpus(struct pevent *pevent)
+{
+	return pevent->cpus;
+}
+
+static inline void pevent_set_cpus(struct pevent *pevent, int cpus)
+{
+	pevent->cpus = cpus;
+}
+
+static inline int pevent_get_long_size(struct pevent *pevent)
+{
+	return pevent->long_size;
+}
+
+static inline void pevent_set_long_size(struct pevent *pevent, int long_size)
+{
+	pevent->long_size = long_size;
+}
+
+static inline int pevent_is_file_bigendian(struct pevent *pevent)
+{
+	return pevent->file_bigendian;
+}
+
+static inline void pevent_set_file_bigendian(struct pevent *pevent, int endian)
+{
+	pevent->file_bigendian = endian;
+}
+
+static inline int pevent_is_host_bigendian(struct pevent *pevent)
+{
+	return pevent->host_bigendian;
+}
+
+static inline void pevent_set_host_bigendian(struct pevent *pevent, int endian)
+{
+	pevent->host_bigendian = endian;
+}
+
+static inline int pevent_is_latency_format(struct pevent *pevent)
+{
+	return pevent->latency_format;
+}
+
+static inline void pevent_set_latency_format(struct pevent *pevent, int lat)
+{
+	pevent->latency_format = lat;
+}
+
+struct pevent *pevent_alloc(void);
+void pevent_free(struct pevent *pevent);
+void pevent_ref(struct pevent *pevent);
+void pevent_unref(struct pevent *pevent);
+
+/* access to the internal parser */
+void pevent_buffer_init(const char *buf, unsigned long long size);
+enum event_type pevent_read_token(char **tok);
+void pevent_free_token(char *token);
+int pevent_peek_char(void);
+const char *pevent_get_input_buf(void);
+unsigned long long pevent_get_input_buf_ptr(void);
+
+/* for debugging */
+void pevent_print_funcs(struct pevent *pevent);
+void pevent_print_printk(struct pevent *pevent);
+
+/* ----------------------- filtering ----------------------- */
+
+enum filter_boolean_type {
+	FILTER_FALSE,
+	FILTER_TRUE,
+};
+
+enum filter_op_type {
+	FILTER_OP_AND = 1,
+	FILTER_OP_OR,
+	FILTER_OP_NOT,
+};
+
+enum filter_cmp_type {
+	FILTER_CMP_NONE,
+	FILTER_CMP_EQ,
+	FILTER_CMP_NE,
+	FILTER_CMP_GT,
+	FILTER_CMP_LT,
+	FILTER_CMP_GE,
+	FILTER_CMP_LE,
+	FILTER_CMP_MATCH,
+	FILTER_CMP_NOT_MATCH,
+	FILTER_CMP_REGEX,
+	FILTER_CMP_NOT_REGEX,
+};
+
+enum filter_exp_type {
+	FILTER_EXP_NONE,
+	FILTER_EXP_ADD,
+	FILTER_EXP_SUB,
+	FILTER_EXP_MUL,
+	FILTER_EXP_DIV,
+	FILTER_EXP_MOD,
+	FILTER_EXP_RSHIFT,
+	FILTER_EXP_LSHIFT,
+	FILTER_EXP_AND,
+	FILTER_EXP_OR,
+	FILTER_EXP_XOR,
+	FILTER_EXP_NOT,
+};
+
+enum filter_arg_type {
+	FILTER_ARG_NONE,
+	FILTER_ARG_BOOLEAN,
+	FILTER_ARG_VALUE,
+	FILTER_ARG_FIELD,
+	FILTER_ARG_EXP,
+	FILTER_ARG_OP,
+	FILTER_ARG_NUM,
+	FILTER_ARG_STR,
+};
+
+enum filter_value_type {
+	FILTER_NUMBER,
+	FILTER_STRING,
+	FILTER_CHAR
+};
+
+struct fliter_arg;
+
+struct filter_arg_boolean {
+	enum filter_boolean_type	value;
+};
+
+struct filter_arg_field {
+	struct format_field	*field;
+};
+
+struct filter_arg_value {
+	enum filter_value_type	type;
+	union {
+		char			*str;
+		unsigned long long	val;
+	};
+};
+
+struct filter_arg_op {
+	enum filter_op_type	type;
+	struct filter_arg	*left;
+	struct filter_arg	*right;
+};
+
+struct filter_arg_exp {
+	enum filter_exp_type	type;
+	struct filter_arg	*left;
+	struct filter_arg	*right;
+};
+
+struct filter_arg_num {
+	enum filter_cmp_type	type;
+	struct filter_arg	*left;
+	struct filter_arg	*right;
+};
+
+struct filter_arg_str {
+	enum filter_cmp_type	type;
+	struct format_field	*field;
+	char			*val;
+	char			*buffer;
+	regex_t			reg;
+};
+
+struct filter_arg {
+	enum filter_arg_type	type;
+	union {
+		struct filter_arg_boolean	boolean;
+		struct filter_arg_field		field;
+		struct filter_arg_value		value;
+		struct filter_arg_op		op;
+		struct filter_arg_exp		exp;
+		struct filter_arg_num		num;
+		struct filter_arg_str		str;
+	};
+};
+
+struct filter_type {
+	int			event_id;
+	struct event_format	*event;
+	struct filter_arg	*filter;
+};
+
+struct event_filter {
+	struct pevent		*pevent;
+	int			filters;
+	struct filter_type	*event_filters;
+};
+
+struct event_filter *pevent_filter_alloc(struct pevent *pevent);
+
+#define FILTER_NONE		-2
+#define FILTER_NOEXIST		-1
+#define FILTER_MISS		0
+#define FILTER_MATCH		1
+
+enum filter_trivial_type {
+	FILTER_TRIVIAL_FALSE,
+	FILTER_TRIVIAL_TRUE,
+	FILTER_TRIVIAL_BOTH,
+};
+
+int pevent_filter_add_filter_str(struct event_filter *filter,
+				 const char *filter_str,
+				 char **error_str);
+
+
+int pevent_filter_match(struct event_filter *filter,
+			struct pevent_record *record);
+
+int pevent_event_filtered(struct event_filter *filter,
+			  int event_id);
+
+void pevent_filter_reset(struct event_filter *filter);
+
+void pevent_filter_clear_trivial(struct event_filter *filter,
+				 enum filter_trivial_type type);
+
+void pevent_filter_free(struct event_filter *filter);
+
+char *pevent_filter_make_string(struct event_filter *filter, int event_id);
+
+int pevent_filter_remove_event(struct event_filter *filter,
+			       int event_id);
+
+int pevent_filter_event_has_trivial(struct event_filter *filter,
+				    int event_id,
+				    enum filter_trivial_type type);
+
+int pevent_filter_copy(struct event_filter *dest, struct event_filter *source);
+
+int pevent_update_trivial(struct event_filter *dest, struct event_filter *source,
+			  enum filter_trivial_type type);
+
+int pevent_filter_compare(struct event_filter *filter1, struct event_filter *filter2);
+
+#endif /* _PARSE_EVENTS_H */

tools/lib/traceevent/event-utils.h

@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef __UTIL_H
+#define __UTIL_H
+
+#include <ctype.h>
+
+/* Can be overridden */
+void die(const char *fmt, ...);
+void *malloc_or_die(unsigned int size);
+void warning(const char *fmt, ...);
+void pr_stat(const char *fmt, ...);
+void vpr_stat(const char *fmt, va_list ap);
+
+/* Always available */
+void __die(const char *fmt, ...);
+void __warning(const char *fmt, ...);
+void __pr_stat(const char *fmt, ...);
+
+void __vdie(const char *fmt, ...);
+void __vwarning(const char *fmt, ...);
+void __vpr_stat(const char *fmt, ...);
+
+#define min(x, y) ({				\
+	typeof(x) _min1 = (x);			\
+	typeof(y) _min2 = (y);			\
+	(void) (&_min1 == &_min2);		\
+	_min1 < _min2 ? _min1 : _min2; })
+
+static inline char *strim(char *string)
+{
+	char *ret;
+
+	if (!string)
+		return NULL;
+	while (*string) {
+		if (!isspace(*string))
+			break;
+		string++;
+	}
+	ret = string;
+
+	string = ret + strlen(ret) - 1;
+	while (string > ret) {
+		if (!isspace(*string))
+			break;
+		string--;
+	}
+	string[1] = 0;
+
+	return ret;
+}
+
+static inline int has_text(const char *text)
+{
+	if (!text)
+		return 0;
+
+	while (*text) {
+		if (!isspace(*text))
+			return 1;
+		text++;
+	}
+
+	return 0;
+}
+
+#endif

tools/lib/traceevent/parse-utils.c

@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <errno.h>
+
+#define __weak __attribute__((weak))
+
+void __vdie(const char *fmt, va_list ap)
+{
+	int ret = errno;
+
+	if (errno)
+		perror("trace-cmd");
+	else
+		ret = -1;
+
+	fprintf(stderr, "  ");
+	vfprintf(stderr, fmt, ap);
+
+	fprintf(stderr, "\n");
+	exit(ret);
+}
+
+void __die(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vdie(fmt, ap);
+	va_end(ap);
+}
+
+void __weak die(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vdie(fmt, ap);
+	va_end(ap);
+}
+
+void __vwarning(const char *fmt, va_list ap)
+{
+	if (errno)
+		perror("trace-cmd");
+	errno = 0;
+
+	fprintf(stderr, "  ");
+	vfprintf(stderr, fmt, ap);
+
+	fprintf(stderr, "\n");
+}
+
+void __warning(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vwarning(fmt, ap);
+	va_end(ap);
+}
+
+void __weak warning(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vwarning(fmt, ap);
+	va_end(ap);
+}
+
+void __vpr_stat(const char *fmt, va_list ap)
+{
+	vprintf(fmt, ap);
+	printf("\n");
+}
+
+void __pr_stat(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vpr_stat(fmt, ap);
+	va_end(ap);
+}
+
+void __weak vpr_stat(const char *fmt, va_list ap)
+{
+	__vpr_stat(fmt, ap);
+}
+
+void __weak pr_stat(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	__vpr_stat(fmt, ap);
+	va_end(ap);
+}
+
+void __weak *malloc_or_die(unsigned int size)
+{
+	void *data;
+
+	data = malloc(size);
+	if (!data)
+		die("malloc");
+	return data;
+}

tools/lib/traceevent/trace-seq.c

@@ -0,0 +1,199 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+
+#include "event-parse.h"
+#include "event-utils.h"
+
+/*
+ * The TRACE_SEQ_POISON is to catch the use of using
+ * a trace_seq structure after it was destroyed.
+ */
+#define TRACE_SEQ_POISON	((void *)0xdeadbeef)
+#define TRACE_SEQ_CHECK(s)						\
+do {									\
+	if ((s)->buffer == TRACE_SEQ_POISON)			\
+		die("Usage of trace_seq after it was destroyed");	\
+} while (0)
+
+/**
+ * trace_seq_init - initialize the trace_seq structure
+ * @s: a pointer to the trace_seq structure to initialize
+ */
+void trace_seq_init(struct trace_seq *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+	s->buffer_size = TRACE_SEQ_BUF_SIZE;
+	s->buffer = malloc_or_die(s->buffer_size);
+}
+
+/**
+ * trace_seq_destroy - free up memory of a trace_seq
+ * @s: a pointer to the trace_seq to free the buffer
+ *
+ * Only frees the buffer, not the trace_seq struct itself.
+ */
+void trace_seq_destroy(struct trace_seq *s)
+{
+	if (!s)
+		return;
+	TRACE_SEQ_CHECK(s);
+	free(s->buffer);
+	s->buffer = TRACE_SEQ_POISON;
+}
+
+static void expand_buffer(struct trace_seq *s)
+{
+	s->buffer_size += TRACE_SEQ_BUF_SIZE;
+	s->buffer = realloc(s->buffer, s->buffer_size);
+	if (!s->buffer)
+		die("Can't allocate trace_seq buffer memory");
+}
+
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	va_list ap;
+	int len;
+	int ret;
+
+	TRACE_SEQ_CHECK(s);
+
+ try_again:
+	len = (s->buffer_size - 1) - s->len;
+
+	va_start(ap, fmt);
+	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
+	va_end(ap);
+
+	if (ret >= len) {
+		expand_buffer(s);
+		goto try_again;
+	}
+
+	s->len += ret;
+
+	return 1;
+}
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+	int len;
+	int ret;
+
+	TRACE_SEQ_CHECK(s);
+
+ try_again:
+	len = (s->buffer_size - 1) - s->len;
+
+	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+	if (ret >= len) {
+		expand_buffer(s);
+		goto try_again;
+	}
+
+	s->len += ret;
+
+	return len;
+}
+
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
+int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	int len;
+
+	TRACE_SEQ_CHECK(s);
+
+	len = strlen(str);
+
+	while (len > ((s->buffer_size - 1) - s->len))
+		expand_buffer(s);
+
+	memcpy(s->buffer + s->len, str, len);
+	s->len += len;
+
+	return len;
+}
+
+int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	TRACE_SEQ_CHECK(s);
+
+	while (s->len >= (s->buffer_size - 1))
+		expand_buffer(s);
+
+	s->buffer[s->len++] = c;
+
+	return 1;
+}
+
+void trace_seq_terminate(struct trace_seq *s)
+{
+	TRACE_SEQ_CHECK(s);
+
+	/* There's always one character left on the buffer */
+	s->buffer[s->len] = 0;
+}
+
+int trace_seq_do_printf(struct trace_seq *s)
+{
+	TRACE_SEQ_CHECK(s);
+	return printf("%.*s", s->len, s->buffer);
+}

tools/mm/low-mem-test.c

@@ -0,0 +1,178 @@
+/* Copyright (c) 2012 The Chromium OS Authors. All rights reserved.
+ * This program is free software, released under the GPL.
+ * Based on code by Minchan Kim
+ *
+ * User program that tests low-memory notifications.
+ *
+ * Compile with -lpthread
+ * for instance
+ * i686-pc-linux-gnu-gcc low-mem-test.c -o low-mem-test -lpthread
+ *
+ * Run as: low-mem-test <allocation size> <allocation interval (microseconds)>
+ *
+ * This program runs in two threads.  One thread continuously allocates memory
+ * in the given chunk size, waiting for the specified microsecond interval
+ * between allocations.  The other runs in a loop that waits for a low-memory
+ * notification, then frees some of the memory that the first thread has
+ * allocated.
+ */
+
+#include <poll.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+
+int memory_chunk_size = 10000000;
+int wait_time_us = 10000;
+int autotesting;
+
+pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
+
+struct node {
+	void *memory;
+	struct node *prev;
+	struct node *next;
+};
+
+struct node head, tail;
+
+void work(void)
+{
+	int i;
+
+	while (1) {
+		struct node *new = malloc(sizeof(struct node));
+		if (new == NULL) {
+			perror("allocating node");
+			exit(1);
+		}
+		new->memory = malloc(memory_chunk_size);
+		if (new->memory == NULL) {
+			perror("allocating chunk");
+			exit(1);
+		}
+
+		pthread_mutex_lock(&mutex);
+		new->next = &head;
+		new->prev = head.prev;
+		new->prev->next = new;
+		new->next->prev = new;
+		for (i = 0; i < memory_chunk_size / 4096; i++) {
+			/* touch page */
+			((unsigned char *) new->memory)[i * 4096] = 1;
+		}
+
+		pthread_mutex_unlock(&mutex);
+
+		if (!autotesting) {
+			printf("+");
+			fflush(stdout);
+		}
+
+		usleep(wait_time_us);
+	}
+}
+
+void free_memory(void)
+{
+	struct node *old;
+	pthread_mutex_lock(&mutex);
+	old = tail.next;
+	if (old == &head) {
+		fprintf(stderr, "no memory left to free\n");
+		exit(1);
+	}
+	old->prev->next = old->next;
+	old->next->prev = old->prev;
+	free(old->memory);
+	free(old);
+	pthread_mutex_unlock(&mutex);
+	if (!autotesting) {
+		printf("-");
+		fflush(stdout);
+	}
+}
+
+void *poll_thread(void *dummy)
+{
+	struct pollfd pfd;
+	int fd = open("/dev/chromeos-low-mem", O_RDONLY);
+	if (fd == -1) {
+		perror("/dev/chromeos-low-mem");
+		exit(1);
+	}
+
+	pfd.fd = fd;
+	pfd.events = POLLIN;
+
+	if (autotesting) {
+		/* Check that there is no memory shortage yet. */
+		poll(&pfd, 1, 0);
+		if (pfd.revents != 0) {
+			exit(0);
+		} else {
+			fprintf(stderr, "expected no events but "
+				"poll() returned 0x%x\n", pfd.revents);
+			exit(1);
+		}
+	}
+
+	while (1) {
+		poll(&pfd, 1, -1);
+		if (autotesting) {
+			/* Free several chunks and check that the notification
+			 * is gone. */
+			free_memory();
+			free_memory();
+			free_memory();
+			free_memory();
+			free_memory();
+			poll(&pfd, 1, 0);
+			if (pfd.revents == 0) {
+				exit(0);
+			} else {
+				fprintf(stderr, "expected no events but "
+					"poll() returned 0x%x\n", pfd.revents);
+				exit(1);
+			}
+		}
+		free_memory();
+	}
+}
+
+int main(int argc, char **argv)
+{
+	pthread_t threadid;
+
+	head.next = NULL;
+	head.prev = &tail;
+	tail.next = &head;
+	tail.prev = NULL;
+
+	if (argc != 3 && (argc != 2 || strcmp(argv[1], "autotesting"))) {
+		fprintf(stderr,
+			"usage: low-mem-test <alloc size in bytes> "
+			"<alloc interval in microseconds>\n"
+			"or:    low-mem-test autotesting\n");
+		exit(1);
+	}
+
+	if (argc == 2) {
+		autotesting = 1;
+	} else {
+		memory_chunk_size = atoi(argv[1]);
+		wait_time_us = atoi(argv[2]);
+	}
+
+	if (pthread_create(&threadid, NULL, poll_thread, NULL)) {
+		perror("pthread");
+		return 1;
+	}
+
+	work();
+	return 0;
+}

tools/net/Makefile

@@ -0,0 +1,15 @@
+prefix = /usr
+
+CC = gcc
+
+all : bpf_jit_disasm
+
+bpf_jit_disasm : CFLAGS = -Wall -O2
+bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
+bpf_jit_disasm : bpf_jit_disasm.o
+
+clean :
+	rm -rf *.o bpf_jit_disasm
+
+install :
+	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm

tools/net/bpf_jit_disasm.c

@@ -0,0 +1,199 @@
+/*
+ * Minimal BPF JIT image disassembler
+ *
+ * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
+ * debugging or verification purposes.
+ *
+ * To get the disassembly of the JIT code, do the following:
+ *
+ *  1) `echo 2 > /proc/sys/net/core/bpf_jit_enable`
+ *  2) Load a BPF filter (e.g. `tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24`)
+ *  3) Run e.g. `bpf_jit_disasm -o` to read out the last JIT code
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+#include <bfd.h>
+#include <dis-asm.h>
+#include <sys/klog.h>
+#include <sys/types.h>
+#include <regex.h>
+
+static void get_exec_path(char *tpath, size_t size)
+{
+	char *path;
+	ssize_t len;
+
+	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
+	tpath[size - 1] = 0;
+
+	path = strdup(tpath);
+	assert(path);
+
+	len = readlink(path, tpath, size);
+	tpath[len] = 0;
+
+	free(path);
+}
+
+static void get_asm_insns(uint8_t *image, size_t len, unsigned long base,
+			  int opcodes)
+{
+	int count, i, pc = 0;
+	char tpath[256];
+	struct disassemble_info info;
+	disassembler_ftype disassemble;
+	bfd *bfdf;
+
+	memset(tpath, 0, sizeof(tpath));
+	get_exec_path(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+	info.buffer = image;
+	info.buffer_length = len;
+
+	disassemble_init_for_target(&info);
+
+	disassemble = disassembler(bfdf);
+	assert(disassemble);
+
+	do {
+		printf("%4x:\t", pc);
+
+		count = disassemble(pc, &info);
+
+		if (opcodes) {
+			printf("\n\t");
+			for (i = 0; i < count; ++i)
+				printf("%02x ", (uint8_t) image[pc + i]);
+		}
+		printf("\n");
+
+		pc += count;
+	} while(count > 0 && pc < len);
+
+	bfd_close(bfdf);
+}
+
+static char *get_klog_buff(int *klen)
+{
+	int ret, len = klogctl(10, NULL, 0);
+	char *buff = malloc(len);
+
+	assert(buff && klen);
+	ret = klogctl(3, buff, len);
+	assert(ret >= 0);
+	*klen = ret;
+
+	return buff;
+}
+
+static void put_klog_buff(char *buff)
+{
+	free(buff);
+}
+
+static int get_last_jit_image(char *haystack, size_t hlen,
+			      uint8_t *image, size_t ilen,
+			      unsigned long *base)
+{
+	char *ptr, *pptr, *tmp;
+	off_t off = 0;
+	int ret, flen, proglen, pass, ulen = 0;
+	regmatch_t pmatch[1];
+	regex_t regex;
+
+	if (hlen == 0)
+		return 0;
+
+	ret = regcomp(&regex, "flen=[[:alnum:]]+ proglen=[[:digit:]]+ "
+		      "pass=[[:digit:]]+ image=[[:xdigit:]]+", REG_EXTENDED);
+	assert(ret == 0);
+
+	ptr = haystack;
+	while (1) {
+		ret = regexec(&regex, ptr, 1, pmatch, 0);
+		if (ret == 0) {
+			ptr += pmatch[0].rm_eo;
+			off += pmatch[0].rm_eo;
+			assert(off < hlen);
+		} else
+			break;
+	}
+
+	ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
+	ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
+		     &flen, &proglen, &pass, base);
+	if (ret != 4)
+		return 0;
+
+	tmp = ptr = haystack + off;
+	while ((ptr = strtok(tmp, "\n")) != NULL && ulen < ilen) {
+		tmp = NULL;
+		if (!strstr(ptr, "JIT code"))
+			continue;
+		pptr = ptr;
+		while ((ptr = strstr(pptr, ":")))
+			pptr = ptr + 1;
+		ptr = pptr;
+		do {
+			image[ulen++] = (uint8_t) strtoul(pptr, &pptr, 16);
+			if (ptr == pptr || ulen >= ilen) {
+				ulen--;
+				break;
+			}
+			ptr = pptr;
+		} while (1);
+	}
+
+	assert(ulen == proglen);
+	printf("%d bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
+	       proglen, pass, flen);
+	printf("%lx + <x>:\n", *base);
+
+	regfree(&regex);
+	return ulen;
+}
+
+int main(int argc, char **argv)
+{
+	int len, klen, opcodes = 0;
+	char *kbuff;
+	unsigned long base;
+	uint8_t image[4096];
+
+	if (argc > 1) {
+		if (!strncmp("-o", argv[argc - 1], 2)) {
+			opcodes = 1;
+		} else {
+			printf("usage: bpf_jit_disasm [-o: show opcodes]\n");
+			exit(0);
+		}
+	}
+
+	bfd_init();
+	memset(image, 0, sizeof(image));
+
+	kbuff = get_klog_buff(&klen);
+
+	len = get_last_jit_image(kbuff, klen, image, sizeof(image), &base);
+	if (len > 0 && base > 0)
+		get_asm_insns(image, len, base, opcodes);
+
+	put_klog_buff(kbuff);
+
+	return 0;
+}

tools/nfsd/inject_fault.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+#
+# Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
+#
+# Script for easier NFSD fault injection
+
+# Check that debugfs has been mounted
+DEBUGFS=`cat /proc/mounts | grep debugfs`
+if [ "$DEBUGFS" == "" ]; then
+	echo "debugfs does not appear to be mounted!"
+	echo "Please mount debugfs and try again"
+	exit 1
+fi
+
+# Check that the fault injection directory exists
+DEBUGDIR=`echo $DEBUGFS | awk '{print $2}'`/nfsd
+if [ ! -d "$DEBUGDIR" ]; then
+	echo "$DEBUGDIR does not exist"
+	echo "Check that your .config selects CONFIG_NFSD_FAULT_INJECTION"
+	exit 1
+fi
+
+function help()
+{
+	echo "Usage $0 injection_type [count]"
+	echo ""
+	echo "Injection types are:"
+	ls $DEBUGDIR
+	exit 1
+}
+
+if [ $# == 0 ]; then
+	help
+elif [ ! -f $DEBUGDIR/$1 ]; then
+	help
+elif [ $# != 2 ]; then
+	COUNT=0
+else
+	COUNT=$2
+fi
+
+BEFORE=`mktemp`
+AFTER=`mktemp`
+dmesg > $BEFORE
+echo $COUNT > $DEBUGDIR/$1
+dmesg > $AFTER
+# Capture lines that only exist in the $AFTER file
+diff $BEFORE $AFTER | grep ">"
+rm -f $BEFORE $AFTER

tools/perf/.gitignore

@@ -0,0 +1,25 @@
+PERF-CFLAGS
+PERF-GUI-VARS
+PERF-VERSION-FILE
+perf
+perf-help
+perf-record
+perf-report
+perf-stat
+perf-top
+perf*.1
+perf*.xml
+perf*.html
+common-cmds.h
+perf.data
+perf.data.old
+perf-archive
+tags
+TAGS
+cscope*
+config.mak
+config.mak.autogen
+*-bison.*
+*-flex.*
+*.pyc
+*.pyo

tools/perf/CREDITS

@@ -0,0 +1,30 @@
+Most of the infrastructure that 'perf' uses here has been reused
+from the Git project, as of version:
+
+    66996ec: Sync with 1.6.2.4
+
+Here is an (incomplete!) list of main contributors to those files
+in util/* and elsewhere:
+
+ Alex Riesen
+ Christian Couder
+ Dmitry Potapov
+ Jeff King
+ Johannes Schindelin
+ Johannes Sixt
+ Junio C Hamano
+ Linus Torvalds
+ Matthias Kestenholz
+ Michal Ostrowski
+ Miklos Vajna
+ Petr Baudis
+ Pierre Habouzit
+ René Scharfe
+ Samuel Tardieu
+ Shawn O. Pearce
+ Steffen Prohaska
+ Steve Haslam
+
+Thanks guys!
+
+The full history of the files can be found in the upstream Git commits.

tools/perf/Documentation/Makefile

@@ -0,0 +1,352 @@
+include ../config/utilities.mak
+
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+  ifneq ($(O),)
+	OUTPUT := $(O)/
+  endif
+endif
+
+MAN1_TXT= \
+	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
+		$(wildcard perf-*.txt)) \
+	perf.txt
+MAN5_TXT=
+MAN7_TXT=
+
+MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)
+_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
+_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
+
+MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML))
+MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML))
+
+ARTICLES =
+# with their own formatting rules.
+SP_ARTICLES =
+API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technical/api-index.txt, $(wildcard technical/api-*.txt)))
+SP_ARTICLES += $(API_DOCS)
+SP_ARTICLES += technical/api-index
+
+_DOC_HTML = $(_MAN_HTML)
+_DOC_HTML+=$(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+DOC_HTML=$(addprefix $(OUTPUT),$(_DOC_HTML))
+
+_DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
+_DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
+_DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
+
+DOC_MAN1=$(addprefix $(OUTPUT),$(_DOC_MAN1))
+DOC_MAN5=$(addprefix $(OUTPUT),$(_DOC_MAN5))
+DOC_MAN7=$(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
+prefix?=$(HOME)
+endif
+bindir?=$(prefix)/bin
+htmldir?=$(prefix)/share/doc/perf-doc
+pdfdir?=$(prefix)/share/doc/perf-doc
+mandir?=$(prefix)/share/man
+man1dir=$(mandir)/man1
+man5dir=$(mandir)/man5
+man7dir=$(mandir)/man7
+
+ASCIIDOC=asciidoc
+ASCIIDOC_EXTRA = --unsafe
+MANPAGE_XSL = manpage-normal.xsl
+XMLTO_EXTRA =
+INSTALL?=install
+RM ?= rm -f
+DOC_REF = origin/man
+HTML_REF = origin/html
+
+infodir?=$(prefix)/share/info
+MAKEINFO=makeinfo
+INSTALL_INFO=install-info
+DOCBOOK2X_TEXI=docbook2x-texi
+DBLATEX=dblatex
+XMLTO=xmlto
+ifndef PERL_PATH
+	PERL_PATH = /usr/bin/perl
+endif
+
+-include ../config.mak.autogen
+-include ../config.mak
+
+_tmp_tool_path := $(call get-executable,$(ASCIIDOC))
+ifeq ($(_tmp_tool_path),)
+	missing_tools = $(ASCIIDOC)
+endif
+
+_tmp_tool_path := $(call get-executable,$(XMLTO))
+ifeq ($(_tmp_tool_path),)
+	missing_tools += $(XMLTO)
+endif
+
+#
+# For asciidoc ...
+#	-7.1.2,	no extra settings are needed.
+#	8.0-,	set ASCIIDOC8.
+#
+
+#
+# For docbook-xsl ...
+#	-1.68.1,	set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0)
+#	1.69.0,		no extra settings are needed?
+#	1.69.1-1.71.0,	set DOCBOOK_SUPPRESS_SP?
+#	1.71.1,		no extra settings are needed?
+#	1.72.0,		set DOCBOOK_XSL_172.
+#	1.73.0-,	set ASCIIDOC_NO_ROFF
+#
+
+#
+# If you had been using DOCBOOK_XSL_172 in an attempt to get rid
+# of 'the ".ft C" problem' in your generated manpages, and you
+# instead ended up with weird characters around callouts, try
+# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8).
+#
+
+ifdef ASCIIDOC8
+ASCIIDOC_EXTRA += -a asciidoc7compatible
+endif
+ifdef DOCBOOK_XSL_172
+ASCIIDOC_EXTRA += -a perf-asciidoc-no-roff
+MANPAGE_XSL = manpage-1.72.xsl
+else
+	ifdef ASCIIDOC_NO_ROFF
+	# docbook-xsl after 1.72 needs the regular XSL, but will not
+	# pass-thru raw roff codes from asciidoc.conf, so turn them off.
+	ASCIIDOC_EXTRA += -a perf-asciidoc-no-roff
+	endif
+endif
+ifdef MAN_BOLD_LITERAL
+XMLTO_EXTRA += -m manpage-bold-literal.xsl
+endif
+ifdef DOCBOOK_SUPPRESS_SP
+XMLTO_EXTRA += -m manpage-suppress-sp.xsl
+endif
+
+SHELL_PATH ?= $(SHELL)
+# Shell quote;
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
+
+#
+# Please note that there is a minor bug in asciidoc.
+# The version after 6.0.3 _will_ include the patch found here:
+#   http://marc.theaimsgroup.com/?l=perf&m=111558757202243&w=2
+#
+# Until that version is released you may have to apply the patch
+# yourself - yes, all 6 characters of it!
+#
+
+QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+QUIET_SUBDIR1  =
+
+ifneq ($(findstring $(MAKEFLAGS),w),w)
+PRINT_DIR = --no-print-directory
+else # "make -w"
+NO_SUBDIR = :
+endif
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifndef V
+	QUIET_ASCIIDOC	= @echo '   ' ASCIIDOC $@;
+	QUIET_XMLTO	= @echo '   ' XMLTO $@;
+	QUIET_DB2TEXI	= @echo '   ' DB2TEXI $@;
+	QUIET_MAKEINFO	= @echo '   ' MAKEINFO $@;
+	QUIET_DBLATEX	= @echo '   ' DBLATEX $@;
+	QUIET_XSLTPROC	= @echo '   ' XSLTPROC $@;
+	QUIET_GEN	= @echo '   ' GEN $@;
+	QUIET_STDERR	= 2> /dev/null
+	QUIET_SUBDIR0	= +@subdir=
+	QUIET_SUBDIR1	= ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
+			  $(MAKE) $(PRINT_DIR) -C $$subdir
+	export V
+endif
+endif
+
+all: html man
+
+html: $(DOC_HTML)
+
+$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7): asciidoc.conf
+
+man: man1 man5 man7
+man1: $(DOC_MAN1)
+man5: $(DOC_MAN5)
+man7: $(DOC_MAN7)
+
+info: $(OUTPUT)perf.info $(OUTPUT)perfman.info
+
+pdf: $(OUTPUT)user-manual.pdf
+
+install: install-man
+
+check-man-tools:
+ifdef missing_tools
+	$(error "You need to install $(missing_tools) for man pages")
+endif
+
+do-install-man: man
+	$(INSTALL) -d -m 755 $(DESTDIR)$(man1dir)
+#	$(INSTALL) -d -m 755 $(DESTDIR)$(man5dir)
+#	$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+	$(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir)
+#	$(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir)
+#	$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+install-man: check-man-tools man
+
+try-install-man:
+ifdef missing_tools
+	$(warning Please install $(missing_tools) to have the man pages installed)
+else
+	$(MAKE) do-install-man
+endif
+
+install-info: info
+	$(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
+	$(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir)
+	if test -r $(DESTDIR)$(infodir)/dir; then \
+	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
+	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
+	else \
+	  echo "No directory found in $(DESTDIR)$(infodir)" >&2 ; \
+	fi
+
+install-pdf: pdf
+	$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
+	$(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
+
+#install-html: html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE
+
+-include $(OUTPUT)PERF-VERSION-FILE
+endif
+endif
+
+#
+# Determine "include::" file references in asciidoc files.
+#
+$(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
+	$(QUIET_GEN)$(RM) $@+ $@ && \
+	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
+	mv $@+ $@
+
+-include $(OUPTUT)doc.dep
+
+_cmds_txt = cmds-ancillaryinterrogators.txt \
+	cmds-ancillarymanipulators.txt \
+	cmds-mainporcelain.txt \
+	cmds-plumbinginterrogators.txt \
+	cmds-plumbingmanipulators.txt \
+	cmds-synchingrepositories.txt \
+	cmds-synchelpers.txt \
+	cmds-purehelpers.txt \
+	cmds-foreignscminterface.txt
+cmds_txt=$(addprefix $(OUTPUT),$(_cmds_txt))
+
+$(cmds_txt): $(OUTPUT)cmd-list.made
+
+$(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
+	$(QUIET_GEN)$(RM) $@ && \
+	$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
+	date >$@
+
+clean:
+	$(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML))
+	$(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML))
+	$(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)
+	$(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++
+	$(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info
+	$(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep
+	$(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt
+	$(RM) $(cmds_txt) $(OUTPUT)*.made
+
+$(MAN_HTML): $(OUTPUT)%.html : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
+	$(QUIET_XMLTO)$(RM) $@ && \
+	$(XMLTO) -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+
+$(OUTPUT)%.xml : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+
+XSLT = docbook.xsl
+XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css
+
+$(OUTPUT)user-manual.html: $(OUTPUT)user-manual.xml
+	$(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $<
+
+$(OUTPUT)perf.info: $(OUTPUT)user-manual.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ $(OUTPUT)user-manual.texi
+
+$(OUTPUT)user-manual.texi: $(OUTPUT)user-manual.xml
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	$(DOCBOOK2X_TEXI) $(OUTPUT)user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
+	$(PERL_PATH) fix-texi.perl <$@++ >$@+ && \
+	rm $@++ && \
+	mv $@+ $@
+
+$(OUTPUT)user-manual.pdf: $(OUTPUT)user-manual.xml
+	$(QUIET_DBLATEX)$(RM) $@+ $@ && \
+	$(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \
+	mv $@+ $@
+
+$(OUTPUT)perfman.texi: $(MAN_XML) cat-texi.perl
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \
+		--to-stdout $(xml) &&) true) > $@++ && \
+	$(PERL_PATH) cat-texi.perl $@ <$@++ >$@+ && \
+	rm $@++ && \
+	mv $@+ $@
+
+$(OUTPUT)perfman.info: $(OUTPUT)perfman.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi
+
+$(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	$(DOCBOOK2X_TEXI) --to-stdout $*.xml >$@+ && \
+	mv $@+ $@
+
+howto-index.txt: howto-index.sh $(wildcard howto/*.txt)
+	$(QUIET_GEN)$(RM) $@+ $@ && \
+	'$(SHELL_PATH_SQ)' ./howto-index.sh $(wildcard howto/*.txt) >$@+ && \
+	mv $@+ $@
+
+$(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt
+	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt
+
+WEBDOC_DEST = /pub/software/tools/perf/docs
+
+$(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
+	mv $@+ $@
+
+# UNIMPLEMENTED
+#install-webdoc : html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
+
+# quick-install: quick-install-man
+
+# quick-install-man:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+
+#quick-install-html:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+
+.PHONY: .FORCE-PERF-VERSION-FILE

tools/perf/Documentation/android.txt

@@ -0,0 +1,78 @@
+How to compile perf for Android
+=========================================
+
+I. Set the Android NDK environment
+------------------------------------------------
+
+(a). Use the Android NDK
+------------------------------------------------
+1. You need to download and install the Android Native Development Kit (NDK).
+Set the NDK variable to point to the path where you installed the NDK:
+  export NDK=/path/to/android-ndk
+
+2. Set cross-compiling environment variables for NDK toolchain and sysroot.
+For arm:
+  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi-
+  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm
+For x86:
+  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android-
+  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86
+
+This method is not working for Android NDK versions up to Revision 8b.
+perf uses some bionic enhancements that are not included in these NDK versions.
+You can use method (b) described below instead.
+
+(b). Use the Android source tree
+-----------------------------------------------
+1. Download the master branch of the Android source tree.
+Set the environment for the target you want using:
+  source build/envsetup.sh
+  lunch
+
+2. Build your own NDK sysroot to contain latest bionic changes and set the
+NDK sysroot environment variable.
+  cd ${ANDROID_BUILD_TOP}/ndk
+For arm:
+  ./build/tools/build-ndk-sysroot.sh --abi=arm
+  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm
+For x86:
+  ./build/tools/build-ndk-sysroot.sh --abi=x86
+  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86
+
+3. Set the NDK toolchain environment variable.
+For arm:
+  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi-
+For x86:
+  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android-
+
+II. Compile perf for Android
+------------------------------------------------
+You need to run make with the NDK toolchain and sysroot defined above:
+For arm:
+  make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+For x86:
+  make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+
+III. Install perf
+-----------------------------------------------
+You need to connect to your Android device/emulator using adb.
+Install perf using:
+  adb push perf /data/perf
+
+If you also want to use perf-archive you need busybox tools for Android.
+For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh:
+  sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive
+  chmod +x /tmp/perf-archive
+  adb push /tmp/perf-archive /data/perf-archive
+
+IV. Environment settings for running perf
+------------------------------------------------
+Some perf features need environment variables to run properly.
+You need to set these before running perf on the target:
+  adb shell
+  # PERF_PAGER=cat
+
+IV. Run perf
+------------------------------------------------
+Run perf on your device/emulator to which you previously connected using adb:
+  # ./data/perf

tools/perf/Documentation/asciidoc.conf

@@ -0,0 +1,91 @@
+## linkperf: macro
+#
+# Usage: linkperf:command[manpage-section]
+#
+# Note, {0} is the manpage section, while {target} is the command.
+#
+# Show PERF link as: <command>(<section>); if section is defined, else just show
+# the command.
+
+[macros]
+(?su)[\\]?(?P<name>linkperf):(?P<target>\S*?)\[(?P<attrlist>.*?)\]=
+
+[attributes]
+asterisk=&#42;
+plus=&#43;
+caret=&#94;
+startsb=&#91;
+endsb=&#93;
+tilde=&#126;
+
+ifdef::backend-docbook[]
+[linkperf-inlinemacro]
+{0%{target}}
+{0#<citerefentry>}
+{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>}
+{0#</citerefentry>}
+endif::backend-docbook[]
+
+ifdef::backend-docbook[]
+ifndef::perf-asciidoc-no-roff[]
+# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this.
+# v1.72 breaks with this because it replaces dots not in roff requests.
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+ifdef::doctype-manpage[]
+&#10;.ft C&#10;
+endif::doctype-manpage[]
+|
+ifdef::doctype-manpage[]
+&#10;.ft&#10;
+endif::doctype-manpage[]
+</literallayout>
+{title#}</example>
+endif::perf-asciidoc-no-roff[]
+
+ifdef::perf-asciidoc-no-roff[]
+ifdef::doctype-manpage[]
+# The following two small workarounds insert a simple paragraph after screen
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+|
+</literallayout><simpara></simpara>
+{title#}</example>
+
+[verseblock]
+<formalpara{id? id="{id}"}><title>{title}</title><para>
+{title%}<literallayout{id? id="{id}"}>
+{title#}<literallayout>
+|
+</literallayout>
+{title#}</para></formalpara>
+{title%}<simpara></simpara>
+endif::doctype-manpage[]
+endif::perf-asciidoc-no-roff[]
+endif::backend-docbook[]
+
+ifdef::doctype-manpage[]
+ifdef::backend-docbook[]
+[header]
+template::[header-declarations]
+<refentry>
+<refmeta>
+<refentrytitle>{mantitle}</refentrytitle>
+<manvolnum>{manvolnum}</manvolnum>
+<refmiscinfo class="source">perf</refmiscinfo>
+<refmiscinfo class="version">{perf_version}</refmiscinfo>
+<refmiscinfo class="manual">perf Manual</refmiscinfo>
+</refmeta>
+<refnamediv>
+  <refname>{manname}</refname>
+  <refpurpose>{manpurpose}</refpurpose>
+</refnamediv>
+endif::backend-docbook[]
+endif::doctype-manpage[]
+
+ifdef::backend-xhtml11[]
+[linkperf-inlinemacro]
+<a href="{target}.html">{target}{0?({0})}</a>
+endif::backend-xhtml11[]

tools/perf/Documentation/examples.txt

@@ -0,0 +1,225 @@
+
+		------------------------------
+		****** 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                        [Tracepoint event]
+  kmem:mm_page_free_batched                [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_page_free_batched -e kmem:mm_page_free ./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_page_free_batched
+          20934  kmem:mm_page_free
+
+    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_page_free_batched -e
+   kmem:mm_page_free ./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_page_free_batched  ( +-   0.934% )
+          18376  kmem:mm_page_free	    ( +-   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_page_free_batched -e
+kmem:mm_page_free sleep 10
+
+ Performance counter stats for 'sleep 10':
+
+         171585  kmem:mm_page_pcpu_drain
+         322114  kmem:mm_page_alloc
+          73623  kmem:mm_page_free_batched
+         254115  kmem:mm_page_free
+
+   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_page_free_batched -e
+   kmem:mm_page_free 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_page_free_batched  ( +-   4.820% )
+          25653  kmem:mm_page_free	    ( +-   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/jit-interface.txt

@@ -0,0 +1,15 @@
+perf supports a simple JIT interface to resolve symbols for dynamic code generated
+by a JIT.
+
+The JIT has to write a /tmp/perf-%d.map  (%d = pid of process) file
+
+This is a text file.
+
+Each line has the following format, fields separated with spaces:
+
+START SIZE symbolname
+
+START and SIZE are hex numbers without 0x.
+symbolname is the rest of the line, so it could contain special characters.
+
+The ownership of the file has to match the process.

tools/perf/Documentation/manpage-1.72.xsl

@@ -0,0 +1,14 @@
+<!-- manpage-1.72.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles peculiarities in docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the special values for the roff control characters
+     needed for docbook-xsl 1.72.0 -->
+<xsl:param name="git.docbook.backslash">&#x2593;</xsl:param>
+<xsl:param name="git.docbook.dot"      >&#x2302;</xsl:param>
+
+</xsl:stylesheet>

tools/perf/Documentation/manpage-base.xsl

@@ -0,0 +1,35 @@
+<!-- manpage-base.xsl:
+     special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- these params silence some output from xmlto -->
+<xsl:param name="man.output.quietly" select="1"/>
+<xsl:param name="refentry.meta.get.quietly" select="1"/>
+
+<!-- convert asciidoc callouts to man page format;
+     git.docbook.backslash and git.docbook.dot params
+     must be supplied by another XSL file or other means -->
+<xsl:template match="co">
+	<xsl:value-of select="concat(
+			      $git.docbook.backslash,'fB(',
+			      substring-after(@id,'-'),')',
+			      $git.docbook.backslash,'fR')"/>
+</xsl:template>
+<xsl:template match="calloutlist">
+	<xsl:value-of select="$git.docbook.dot"/>
+	<xsl:text>sp&#10;</xsl:text>
+	<xsl:apply-templates/>
+	<xsl:text>&#10;</xsl:text>
+</xsl:template>
+<xsl:template match="callout">
+	<xsl:value-of select="concat(
+			      $git.docbook.backslash,'fB',
+			      substring-after(@arearefs,'-'),
+			      '. ',$git.docbook.backslash,'fR')"/>
+	<xsl:apply-templates/>
+	<xsl:value-of select="$git.docbook.dot"/>
+	<xsl:text>br&#10;</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>

tools/perf/Documentation/manpage-bold-literal.xsl

@@ -0,0 +1,17 @@
+<!-- manpage-bold-literal.xsl:
+     special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- render literal text as bold (instead of plain or monospace);
+     this makes literal text easier to distinguish in manpages
+     viewed on a tty -->
+<xsl:template match="literal">
+	<xsl:value-of select="$git.docbook.backslash"/>
+	<xsl:text>fB</xsl:text>
+	<xsl:apply-templates/>
+	<xsl:value-of select="$git.docbook.backslash"/>
+	<xsl:text>fR</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>

tools/perf/Documentation/manpage-normal.xsl

@@ -0,0 +1,13 @@
+<!-- manpage-normal.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles anything we want to keep away from docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the normal values for the roff control characters -->
+<xsl:param name="git.docbook.backslash">\</xsl:param>
+<xsl:param name="git.docbook.dot"	>.</xsl:param>
+
+</xsl:stylesheet>

tools/perf/Documentation/manpage-suppress-sp.xsl

@@ -0,0 +1,21 @@
+<!-- manpage-suppress-sp.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles erroneous, inline .sp in manpage output of some
+     versions of docbook-xsl -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- attempt to work around spurious .sp at the tail of the line
+     that some versions of docbook stylesheets seem to add -->
+<xsl:template match="simpara">
+  <xsl:variable name="content">
+    <xsl:apply-templates/>
+  </xsl:variable>
+  <xsl:value-of select="normalize-space($content)"/>
+  <xsl:if test="not(ancestor::authorblurb) and
+                not(ancestor::personblurb)">
+    <xsl:text>&#10;&#10;</xsl:text>
+  </xsl:if>
+</xsl:template>
+
+</xsl:stylesheet>

tools/perf/Documentation/perf-annotate.txt

@@ -0,0 +1,101 @@
+perf-annotate(1)
+================
+
+NAME
+----
+perf-annotate - Read perf.data (created by perf record) and display annotated code
+
+SYNOPSIS
+--------
+[verse]
+'perf annotate' [-i <file> | --input=file] [symbol_name]
+
+DESCRIPTION
+-----------
+This command reads the input file and displays an annotated version of the
+code. If the object file has debug symbols then the source code will be
+displayed alongside assembly code.
+
+If there is no debug info in the object, then annotated assembly is displayed.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-d::
+--dsos=<dso[,dso...]>::
+        Only consider symbols in these dsos.
+-s::
+--symbol=<symbol>::
+        Symbol to annotate.
+
+-f::
+--force::
+        Don't complain, do it.
+
+-v::
+--verbose::
+        Be more verbose. (Show symbol address, etc)
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel.
+
+-l::
+--print-line::
+        Print matching source lines (may be slow).
+
+-P::
+--full-paths::
+        Don't shorten the displayed pathnames.
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
+	present, as when piping to other commands, the stdio interface is
+	used. This interfaces starts by centering on the line with more
+	samples, TAB/UNTAB cycles through the lines with more samples.
+
+--gtk:: Use the GTK interface.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	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.
+
+--objdump=<path>::
+        Path to objdump binary.
+
+--skip-missing::
+	Skip symbols that cannot be annotated.
+
+--group::
+	Show event group information together
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-archive.txt

@@ -0,0 +1,22 @@
+perf-archive(1)
+===============
+
+NAME
+----
+perf-archive - Create archive with object files with build-ids found in perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf archive' [file]
+
+DESCRIPTION
+-----------
+This command runs runs perf-buildid-list --with-hits, and collects the files
+with the buildids found so that analisys of perf.data contents can be possible
+on another machine.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-buildid-list[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-bench.txt

@@ -0,0 +1,192 @@
+perf-bench(1)
+=============
+
+NAME
+----
+perf-bench - General framework for benchmark suites
+
+SYNOPSIS
+--------
+[verse]
+'perf bench' [<common options>] <subsystem> <suite> [<options>]
+
+DESCRIPTION
+-----------
+This 'perf bench' command is a general framework for benchmark suites.
+
+COMMON OPTIONS
+--------------
+-f::
+--format=::
+Specify format style.
+Current available format styles are:
+
+'default'::
+Default style. This is mainly for human reading.
+---------------------
+% perf bench sched pipe                      # with no style specified
+(executing 1000000 pipe operations between two tasks)
+        Total time:5.855 sec
+                5.855061 usecs/op
+		170792 ops/sec
+---------------------
+
+'simple'::
+This simple style is friendly for automated
+processing by scripts.
+---------------------
+% perf bench --format=simple sched pipe      # specified simple
+5.988
+---------------------
+
+SUBSYSTEM
+---------
+
+'sched'::
+	Scheduler and IPC mechanisms.
+
+'mem'::
+	Memory access performance.
+
+'all'::
+	All benchmark subsystems.
+
+SUITES FOR 'sched'
+~~~~~~~~~~~~~~~~~~
+*messaging*::
+Suite for evaluating performance of scheduler and IPC mechanisms.
+Based on hackbench by Rusty Russell.
+
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
+-p::
+--pipe::
+Use pipe() instead of socketpair()
+
+-t::
+--thread::
+Be multi thread instead of multi process
+
+-g::
+--group=::
+Specify number of groups
+
+-l::
+--loop=::
+Specify number of loops
+
+Example of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched messaging                 # run with default
+options (20 sender and receiver processes per group)
+(10 groups == 400 processes run)
+
+      Total time:0.308 sec
+
+% perf bench sched messaging -t -g 20        # be multi-thread, with 20 groups
+(20 sender and receiver threads per group)
+(20 groups == 800 threads run)
+
+      Total time:0.582 sec
+---------------------
+
+*pipe*::
+Suite for pipe() system call.
+Based on pipe-test-1m.c by Ingo Molnar.
+
+Options of *pipe*
+^^^^^^^^^^^^^^^^^
+-l::
+--loop=::
+Specify number of loops.
+
+Example of *pipe*
+^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched pipe
+(executing 1000000 pipe operations between two tasks)
+
+        Total time:8.091 sec
+                8.091833 usecs/op
+                123581 ops/sec
+
+% perf bench sched pipe -l 1000              # loop 1000
+(executing 1000 pipe operations between two tasks)
+
+        Total time:0.016 sec
+                16.948000 usecs/op
+                59004 ops/sec
+---------------------
+
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
+SEE ALSO
+--------
+linkperf:perf[1]

tools/perf/Documentation/perf-buildid-cache.txt

@@ -0,0 +1,40 @@
+perf-buildid-cache(1)
+=====================
+
+NAME
+----
+perf-buildid-cache - Manage build-id cache.
+
+SYNOPSIS
+--------
+[verse]
+'perf buildid-cache <options>'
+
+DESCRIPTION
+-----------
+This command manages the build-id cache. It can add and remove files to/from
+the cache. In the future it should as well purge older entries, set upper
+limits for the space used by the cache, etc.
+
+OPTIONS
+-------
+-a::
+--add=::
+        Add specified file to the cache.
+-r::
+--remove=::
+        Remove specified file from the cache.
+-M::
+--missing=:: 
+	List missing build ids in the cache for the specified file.
+-u::
+--update::
+	Update specified file of the cache. It can be used to update kallsyms
+	kernel dso to vmlinux in order to support annotation.
+-v::
+--verbose::
+	Be more verbose.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]

tools/perf/Documentation/perf-buildid-list.txt

@@ -0,0 +1,43 @@
+perf-buildid-list(1)
+====================
+
+NAME
+----
+perf-buildid-list - List the buildids in a perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf buildid-list <options>'
+
+DESCRIPTION
+-----------
+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::
+--with-hits::
+        Show only DSOs with hits.
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+-f::
+--force::
+	Don't do ownership validation.
+-k::
+--kernel::
+	Show running kernel build id.
+-v::
+--verbose::
+	Be more verbose.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-top[1],
+linkperf:perf-report[1]

tools/perf/Documentation/perf-diff.txt

@@ -0,0 +1,133 @@
+perf-diff(1)
+============
+
+NAME
+----
+perf-diff - Read two perf.data files and display the differential profile
+
+SYNOPSIS
+--------
+[verse]
+'perf diff' [oldfile] [newfile]
+
+DESCRIPTION
+-----------
+This command displays the performance difference amongst two perf.data files
+captured via perf record.
+
+If no parameters are passed it will assume perf.data.old and perf.data.
+
+The differential profile is displayed only for events matching both
+specified perf.data files.
+
+OPTIONS
+-------
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel
+
+-d::
+--dsos=::
+	Only consider symbols in these dsos. CSV that understands
+	file://filename entries.
+
+-C::
+--comms=::
+	Only consider symbols in these comms. CSV that understands
+	file://filename entries.
+
+-S::
+--symbols=::
+	Only consider these symbols. CSV that understands
+	file://filename entries.
+
+-s::
+--sort=::
+	Sort by key(s): pid, comm, dso, symbol.
+
+-t::
+--field-separator=::
+
+	Use a special separator character and don't pad with spaces, replacing
+	all occurrences of this separator in symbol names (and other output)
+	with a '.' character, that thus it's the only non valid separator.
+
+-v::
+--verbose::
+	Be verbose, for instance, show the raw counts in addition to the
+	diff.
+
+-f::
+--force::
+       Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-b::
+--baseline-only::
+        Show only items with match in baseline.
+
+-c::
+--compute::
+        Differential computation selection - delta,ratio,wdiff (default is delta).
+        If '+' is specified as a first character, the output is sorted based
+        on the computation results.
+        See COMPARISON METHODS section for more info.
+
+-p::
+--period::
+        Show period values for both compared hist entries.
+
+-F::
+--formula::
+        Show formula for given computation.
+
+COMPARISON METHODS
+------------------
+delta
+~~~~~
+If specified the 'Delta' column is displayed with value 'd' computed as:
+
+  d = A->period_percent - B->period_percent
+
+with:
+  - A/B being matching hist entry from first/second file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period_percent being the % of the hist entry period value within
+    single data file
+
+ratio
+~~~~~
+If specified the 'Ratio' column is displayed with value 'r' computed as:
+
+  r = A->period / B->period
+
+with:
+  - A/B being matching hist entry from first/second file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period being the hist entry period value
+
+wdiff
+~~~~~
+If specified the 'Weighted diff' column is displayed with value 'd' computed as:
+
+   d = B->period * WEIGHT-A - A->period * WEIGHT-B
+
+  - A/B being matching hist entry from first/second file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period being the hist entry period value
+
+  - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+    behind ':' separator like '-c wdiff:1,2'.
+
+SEE ALSO
+--------
+linkperf:perf-record[1]

tools/perf/Documentation/perf-evlist.txt

@@ -0,0 +1,38 @@
+perf-evlist(1)
+==============
+
+NAME
+----
+perf-evlist - List the event names in a perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf evlist <options>'
+
+DESCRIPTION
+-----------
+This command displays the names of events sampled in a perf.data file.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-F::
+--freq=::
+	Show just the sample frequency used for each event.
+
+-v::
+--verbose=::
+	Show all fields.
+
+-g::
+--group::
+	Show event group information.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-list[1],
+linkperf:perf-report[1]

tools/perf/Documentation/perf-help.txt

@@ -0,0 +1,38 @@
+perf-help(1)
+============
+
+NAME
+----
+perf-help - display help information about perf
+
+SYNOPSIS
+--------
+'perf help' [-a|--all] [COMMAND]
+
+DESCRIPTION
+-----------
+
+With no options and no COMMAND given, the synopsis of the 'perf'
+command and a list of the most commonly used perf commands are printed
+on the standard output.
+
+If the option '--all' or '-a' is given, then all available commands are
+printed on the standard output.
+
+If a perf command is named, a manual page for that command is brought
+up. The 'man' program is used by default for this purpose, but this
+can be overridden by other options or configuration variables.
+
+Note that `perf --help ...` is identical to `perf help ...` because the
+former is internally converted into the latter.
+
+OPTIONS
+-------
+-a::
+--all::
+	Prints all the available commands on the standard output. This
+	option supersedes any other option.
+
+PERF
+----
+Part of the linkperf:perf[1] suite

tools/perf/Documentation/perf-inject.txt

@@ -0,0 +1,46 @@
+perf-inject(1)
+==============
+
+NAME
+----
+perf-inject - Filter to augment the events stream with additional information
+
+SYNOPSIS
+--------
+[verse]
+'perf inject <options>'
+
+DESCRIPTION
+-----------
+perf-inject reads a perf-record event stream and repipes it to stdout.  At any
+point the processing code can inject other events into the event stream - in
+this case build-ids (-b option) are read and injected as needed into the event
+stream.
+
+Build-ids are just the first user of perf-inject - potentially anything that
+needs userspace processing to augment the events stream with additional
+information could make use of this facility.
+
+OPTIONS
+-------
+-b::
+--build-ids=::
+        Inject build-ids into the output stream
+-v::
+--verbose::
+	Be more verbose.
+-i::
+--input=::
+	Input file name. (default: stdin)
+-o::
+--output=::
+	Output file name. (default: stdout)
+-s::
+--sched-stat::
+	Merge sched_stat and sched_switch for getting events where and how long
+	tasks slept. sched_switch contains a callchain where a task slept and
+	sched_stat contains a timeslice how long a task slept.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]

tools/perf/Documentation/perf-kmem.txt

@@ -0,0 +1,47 @@
+perf-kmem(1)
+============
+
+NAME
+----
+perf-kmem - Tool to trace/measure kernel memory(slab) properties
+
+SYNOPSIS
+--------
+[verse]
+'perf kmem' {record|stat} [<options>]
+
+DESCRIPTION
+-----------
+There are two variants of perf kmem:
+
+  'perf kmem record <command>' to record the kmem events
+  of an arbitrary workload.
+
+  'perf kmem stat' to report kernel memory statistics.
+
+OPTIONS
+-------
+-i <file>::
+--input=<file>::
+	Select the input file (default: perf.data unless stdin is a fifo)
+
+--caller::
+	Show per-callsite statistics
+
+--alloc::
+	Show per-allocation statistics
+
+-s <key[,key2...]>::
+--sort=<key[,key2...]>::
+	Sort the output (default: frag,hit,bytes)
+
+-l <num>::
+--line=<num>::
+	Print n lines only
+
+--raw-ip::
+	Print raw ip instead of symbol
+
+SEE ALSO
+--------
+linkperf:perf-record[1]

tools/perf/Documentation/perf-kvm.txt

@@ -0,0 +1,100 @@
+perf-kvm(1)
+===========
+
+NAME
+----
+perf-kvm - Tool to trace/measure kvm guest os
+
+SYNOPSIS
+--------
+[verse]
+'perf kvm' [--host] [--guest] [--guestmount=<path>
+	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
+	{top|record|report|diff|buildid-list}
+'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
+
+DESCRIPTION
+-----------
+There are a couple of variants of perf kvm:
+
+  'perf kvm [options] top <command>' to generates and displays
+  a performance counter profile of guest os in realtime
+  of an arbitrary workload.
+
+  'perf kvm record <command>' to record the performance counter profile
+  of an arbitrary workload and save it into a perf data file. If both
+  --host and --guest are input, the perf data file name is perf.data.kvm.
+  If there is  no --host but --guest, the file name is perf.data.guest.
+  If there is no --guest but --host, the file name is perf.data.host.
+
+  'perf kvm report' to display the performance counter profile information
+  recorded via perf kvm record.
+
+  'perf kvm diff' to displays the performance difference amongst two perf.data
+  files captured via perf record.
+
+  'perf kvm buildid-list' to  display 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.
+
+  'perf kvm stat <command>' to run a command and gather performance counter
+  statistics.
+  Especially, perf 'kvm stat record/report' generates a statistical analysis
+  of KVM events. Currently, vmexit, mmio and ioport events are supported.
+  'perf kvm stat record <command>' records kvm events and the events between
+  start and end <command>.
+  And this command produces a file which contains tracing results of kvm
+  events.
+
+  'perf kvm stat report' reports statistical data which includes events
+  handled time, samples, and so on.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name.
+-o::
+--output::
+        Output file name.
+--host=::
+        Collect host side performance profile.
+--guest=::
+        Collect guest side performance profile.
+--guestmount=<path>::
+	Guest os root file system mount directory. Users mounts guest os
+        root directories under <path> by a specific filesystem access method,
+	typically, sshfs. For example, start 2 guest os. The one's pid is 8888
+	and the other's is 9999.
+        #mkdir ~/guestmount; cd ~/guestmount
+        #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/
+        #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/
+        #perf kvm --host --guest --guestmount=~/guestmount top
+--guestkallsyms=<path>::
+        Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest
+	kernel symbols. Users copy it out from guest os.
+--guestmodules=<path>::
+	Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest
+	kernel module information. Users copy it out from guest os.
+--guestvmlinux=<path>::
+	Guest os kernel vmlinux.
+
+STAT REPORT OPTIONS
+-------------------
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+--events=<value>::
+       events to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+
+SEE ALSO
+--------
+linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
+linkperf:perf-diff[1], linkperf:perf-buildid-list[1],
+linkperf:perf-stat[1]

tools/perf/Documentation/perf-list.txt

@@ -0,0 +1,118 @@
+perf-list(1)
+============
+
+NAME
+----
+perf-list - List all symbolic event types
+
+SYNOPSIS
+--------
+[verse]
+'perf list' [hw|sw|cache|tracepoint|event_glob]
+
+DESCRIPTION
+-----------
+This command displays the symbolic event types which can be selected in the
+various perf commands with the -e option.
+
+[[EVENT_MODIFIERS]]
+EVENT MODIFIERS
+---------------
+
+Events can optionally have a modifer by appending a colon and one or
+more modifiers. Modifiers allow the user to restrict the events to be
+counted. The following modifiers exist:
+
+ u - user-space counting
+ k - kernel counting
+ h - hypervisor counting
+ G - guest counting (in KVM guests)
+ H - host counting (not in KVM guests)
+ p - precise level
+
+The 'p' modifier can be used for specifying how precise the instruction
+address should be. The 'p' modifier can be specified multiple times:
+
+ 0 - SAMPLE_IP can have arbitrary skid
+ 1 - SAMPLE_IP must have constant skid
+ 2 - SAMPLE_IP requested to have 0 skid
+ 3 - SAMPLE_IP must have 0 skid
+
+For Intel systems precise event sampling is implemented with PEBS
+which supports up to precise-level 2.
+
+On AMD systems it is implemented using IBS (up to precise-level 2).
+The precise modifier works with event types 0x76 (cpu-cycles, CPU
+clocks not halted) and 0xC1 (micro-ops retired). Both events map to
+IBS execution sampling (IBS op) with the IBS Op Counter Control bit
+(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+Manual Volume 2: System Programming, 13.3 Instruction-Based
+Sampling). Examples to use IBS:
+
+ perf record -a -e cpu-cycles:p ...    # use ibs op counting cycles
+ perf record -a -e r076:p ...          # same as -e cpu-cycles:p
+ perf record -a -e r0C1:p ...          # use ibs op counting micro-ops
+
+RAW HARDWARE EVENT DESCRIPTOR
+-----------------------------
+Even when an event is not available in a symbolic form within perf right now,
+it can be encoded in a per processor specific way.
+
+For instance For x86 CPUs NNN represents the raw register encoding with the
+layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
+of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
+Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+
+Note: Only the following bit fields can be set in x86 counter
+registers: event, umask, edge, inv, cmask. Esp. guest/host only and
+OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
+MODIFIERS>>.
+
+Example:
+
+If the Intel docs for a QM720 Core i7 describe an event as:
+
+  Event  Umask  Event Mask
+  Num.   Value  Mnemonic    Description                        Comment
+
+  A8H      01H  LSD.UOPS    Counts the number of micro-ops     Use cmask=1 and
+                            delivered by loop stream detector  invert to count
+                                                               cycles
+
+raw encoding of 0x1A8 can be used:
+
+ perf stat -e r1a8 -a sleep 1
+ perf record -e r1a8 ...
+
+You should refer to the processor specific documentation for getting these
+details. Some of them are referenced in the SEE ALSO section below.
+
+OPTIONS
+-------
+
+Without options all known events will be listed.
+
+To limit the list use:
+
+. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
+
+. 'sw' or 'software' to list software events such as context switches, etc.
+
+. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
+
+. 'tracepoint' to list all tracepoint events, alternatively use
+  'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
+  block, etc.
+
+. If none of the above is matched, it will apply the supplied glob to all
+  events, printing the ones that match.
+
+One or more types can be used at the same time, listing the events for the
+types specified.
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-top[1],
+linkperf:perf-record[1],
+http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
+http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]

tools/perf/Documentation/perf-lock.txt

@@ -0,0 +1,66 @@
+perf-lock(1)
+============
+
+NAME
+----
+perf-lock - Analyze lock events
+
+SYNOPSIS
+--------
+[verse]
+'perf lock' {record|report|script|info}
+
+DESCRIPTION
+-----------
+You can analyze various lock behaviours
+and statistics with this 'perf lock' command.
+
+  'perf lock record <command>' records lock events
+  between start and end <command>. And this command
+  produces the file "perf.data" which contains tracing
+  results of lock events.
+
+  'perf lock report' reports statistical data.
+
+  'perf lock script' shows raw lock events.
+
+  'perf lock info' shows metadata like threads or addresses
+  of lock instances.
+
+COMMON OPTIONS
+--------------
+
+-i::
+--input=<file>::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose (show symbol address, etc).
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+REPORT OPTIONS
+--------------
+
+-k::
+--key=<value>::
+        Sorting key. Possible values: acquired (default), contended,
+        wait_total, wait_max, wait_min.
+
+INFO OPTIONS
+------------
+
+-t::
+--threads::
+	dump thread list in perf.data
+
+-m::
+--map::
+	dump map of lock instances (address:name table)
+
+SEE ALSO
+--------
+linkperf:perf[1]

tools/perf/Documentation/perf-mem.txt

@@ -0,0 +1,48 @@
+perf-mem(1)
+===========
+
+NAME
+----
+perf-mem - Profile memory accesses
+
+SYNOPSIS
+--------
+[verse]
+'perf mem' [<options>] (record [<command>] | report)
+
+DESCRIPTION
+-----------
+"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+from it, into perf.data. Perf record options are accepted and are passed through.
+
+"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile.
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-t::
+--type=::
+	Select the memory operation type: load or store (default: load)
+
+-D::
+--dump-raw-samples=::
+	Dump the raw decoded samples on the screen in a format that is easy to parse with
+	one sample per line.
+
+-x::
+--field-separator::
+	Specify the field separator used when dump raw samples (-D option). By default,
+	The separator is the space character.
+
+-C::
+--cpu-list::
+	Restrict dump of raw samples to those provided via this option. Note that the same
+	option can be passed in record mode. It will be interpreted the same way as perf
+	record.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-probe.txt

@@ -0,0 +1,205 @@
+perf-probe(1)
+=============
+
+NAME
+----
+perf-probe - Define new dynamic tracepoints
+
+SYNOPSIS
+--------
+[verse]
+'perf probe' [options] --add='PROBE' [...]
+or
+'perf probe' [options] PROBE
+or
+'perf probe' [options] --del='[GROUP:]EVENT' [...]
+or
+'perf probe' --list
+or
+'perf probe' [options] --line='LINE'
+or
+'perf probe' [options] --vars='PROBEPOINT'
+
+DESCRIPTION
+-----------
+This command defines dynamic tracepoint events, by symbol and registers
+without debuginfo, or by C expressions (C line numbers, C function names,
+and C local variables) with debuginfo.
+
+
+OPTIONS
+-------
+-k::
+--vmlinux=PATH::
+	Specify vmlinux path which has debuginfo (Dwarf binary).
+
+-m::
+--module=MODNAME|PATH::
+	Specify module name in which perf-probe searches probe points
+	or lines. If a path of module file is passed, perf-probe
+	treat it as an offline module (this means you can add a probe on
+        a module which has not been loaded yet).
+
+-s::
+--source=PATH::
+	Specify path to kernel source.
+
+-v::
+--verbose::
+        Be more verbose (show parsed arguments, etc).
+
+-a::
+--add=::
+	Define a probe event (see PROBE SYNTAX for detail).
+
+-d::
+--del=::
+	Delete probe events. This accepts glob wildcards('*', '?') and character
+	classes(e.g. [a-z], [!A-Z]).
+
+-l::
+--list::
+	List up current probe events.
+
+-L::
+--line=::
+	Show source code lines which can be probed. This needs an argument
+	which specifies a range of the source code. (see LINE SYNTAX for detail)
+
+-V::
+--vars=::
+	Show available local variables at given probe point. The argument
+	syntax is same as PROBE SYNTAX, but NO ARGs.
+
+--externs::
+	(Only for --vars) Show external defined variables in addition to local
+	variables.
+
+-F::
+--funcs::
+	Show available functions in given module or kernel. With -x/--exec,
+	can also list functions in a user space executable / shared library.
+
+--filter=FILTER::
+	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
+	pattern, see FILTER PATTERN for detail.
+	Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
+	for --funcs.
+	If several filters are specified, only the last filter is used.
+
+-f::
+--force::
+	Forcibly add events with existing name.
+
+-n::
+--dry-run::
+	Dry run. With this option, --add and --del doesn't execute actual
+	adding and removal operations.
+
+--max-probes::
+	Set the maximum number of probe points for an event. Default is 128.
+
+-x::
+--exec=PATH::
+	Specify path to the executable or shared library file for user
+	space tracing. Can also be used with --funcs option.
+
+In absence of -m/-x options, perf probe checks if the first argument after
+the options is an absolute path name. If its an absolute path, perf probe
+uses it as a target module/target user space binary to probe.
+
+PROBE SYNTAX
+------------
+Probe points are defined by following syntax.
+
+    1) Define event based on function name
+     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+
+    2) Define event based on source file with line number
+     [EVENT=]SRC:ALN [ARG ...]
+
+    3) Define event based on source file with lazy pattern
+     [EVENT=]SRC;PTN [ARG ...]
+
+
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
+'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
+It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
+'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
+
+PROBE ARGUMENT
+--------------
+Each probe argument follows below syntax.
+
+ [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
+
+'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+
+LINE SYNTAX
+-----------
+Line range is described by following syntax.
+
+ "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
+
+FUNC specifies the function name of showing lines. 'RLN' is the start line
+number from function entry line, and 'RLN2' is the end line number. As same as
+probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
+and 'ALN2' is end line number in the file. It is also possible to specify how
+many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
+for searching a specific function when several functions share same name.
+So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
+
+LAZY MATCHING
+-------------
+ The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
+
+e.g.
+ 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.
+
+This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
+
+FILTER PATTERN
+--------------
+ The filter pattern is a glob matching pattern(s) to filter variables.
+ In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+
+e.g.
+ With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
+ With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
+
+EXAMPLES
+--------
+Display which lines in schedule() can be probed:
+
+ ./perf probe --line schedule
+
+Add a probe on schedule() function 12th line with recording cpu local variable:
+
+ ./perf probe schedule:12 cpu
+ or
+ ./perf probe --add='schedule:12 cpu'
+
+ this will add one or more probes which has the name start with "schedule".
+
+ Add probes on lines in schedule() function which calls update_rq_clock().
+
+ ./perf probe 'schedule;update_rq_clock*'
+ or
+ ./perf probe --add='schedule;update_rq_clock*'
+
+Delete all probes on schedule().
+
+ ./perf probe --del='schedule*'
+
+Add probes at zfree() function on /bin/zsh
+
+ ./perf probe -x /bin/zsh zfree or ./perf probe /bin/zsh zfree
+
+Add probes at malloc() function on libc
+
+ ./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc
+
+SEE ALSO
+--------
+linkperf:perf-trace[1], linkperf:perf-record[1]

tools/perf/Documentation/perf-record.txt

@@ -0,0 +1,193 @@
+perf-record(1)
+==============
+
+NAME
+----
+perf-record - Run a command and record its profile into perf.data
+
+SYNOPSIS
+--------
+[verse]
+'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+
+DESCRIPTION
+-----------
+This command runs a command and gathers a performance counter profile
+from it, into perf.data - without displaying anything.
+
+This file can then be inspected later on, using 'perf report'.
+
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-e::
+--event=::
+	Select the PMU event. Selection can be:
+
+        - a symbolic event name	(use 'perf list' to list all events)
+
+        - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
+	  hexadecimal event descriptor.
+
+        - a hardware breakpoint event in the form of '\mem:addr[:access]'
+          where addr is the address in memory you want to break in.
+          Access is the memory access type (read, write, execute) it can
+          be passed as follows: '\mem:addr[:[r][w][x]]'.
+          If you want to profile read-write accesses in 0x1000, just set
+          'mem:0x1000:rw'.
+
+--filter=<filter>::
+        Event filter.
+
+-a::
+--all-cpus::
+        System-wide collection from all CPUs.
+
+-l::
+        Scale counter values.
+
+-p::
+--pid=::
+	Record events on existing process ID (comma separated list).
+
+-t::
+--tid=::
+        Record events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
+-r::
+--realtime=::
+	Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+	Collect data without buffering.
+-A::
+--append::
+	Append to the output file to do incremental profiling.
+
+-f::
+--force::
+	Overwrite existing data file. (deprecated)
+
+-c::
+--count=::
+	Event period to sample.
+
+-o::
+--output=::
+	Output file name.
+
+-i::
+--no-inherit::
+	Child tasks do not inherit counters.
+-F::
+--freq=::
+	Profile at this frequency.
+
+-m::
+--mmap-pages=::
+	Number of mmap data pages. Must be a power of two.
+
+-g::
+--call-graph::
+	Do call-graph (stack chain/backtrace) recording.
+
+-q::
+--quiet::
+	Don't print any message, useful for scripting.
+
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
+
+-s::
+--stat::
+	Per thread counts.
+
+-d::
+--data::
+	Sample addresses.
+
+-T::
+--timestamp::
+	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
+	for instance.
+
+-n::
+--no-samples::
+	Don't sample.
+
+-R::
+--raw-samples::
+Collect raw sample records from all opened counters (default for tracepoint counters).
+
+-C::
+--cpu::
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), samples are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+-N::
+--no-buildid-cache::
+Do not update the builid cache. This saves some overhead in situations
+where the information in the perf.data file (which includes buildids)
+is sufficient.
+
+-G name,...::
+--cgroup name,...::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
+-b::
+--branch-any::
+Enable taken branch stack sampling. Any type of taken branch may be sampled.
+This is a shortcut for --branch-filter any. See --branch-filter for more infos.
+
+-j::
+--branch-filter::
+Enable taken branch stack sampling. Each sample captures a series of consecutive
+taken branches. The number of branches captured with each sample depends on the
+underlying hardware, the type of branches of interest, and the executed code.
+It is possible to select the types of branches captured by enabling filters. The
+following filters are defined:
+
+        - any:  any type of branches
+        - any_call: any function call or system call
+        - any_ret: any function return or system call return
+        - ind_call: any indirect branch
+        - u:  only when the branch target is at the user level
+        - k: only when the branch target is in the kernel
+        - hv: only when the target is at the hypervisor level
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The privilege levels may be omitted, in which case, the privilege levels of the associated
+event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
+levels are subject to permissions.  When sampling on multiple events, branch stack sampling
+is enabled for all the sampling events. The sampled branch type is the same for all events.
+The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
+Note that this feature may not be available on all processors.
+
+-W::
+--weight::
+Enable weightened sampling. An additional weight is recorded per sample and can be
+displayed with the weight and local_weight sort keys.  This currently works for TSX
+abort events and some memory events in precise mode on modern Intel CPUs.
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-report.txt

@@ -0,0 +1,215 @@
+perf-report(1)
+==============
+
+NAME
+----
+perf-report - Read perf.data (created by perf record) and display the profile
+
+SYNOPSIS
+--------
+[verse]
+'perf report' [-i <file> | --input=file]
+
+DESCRIPTION
+-----------
+This command displays the performance counter profile information recorded
+via perf record.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
+-d::
+--dsos=::
+	Only consider symbols in these dsos. CSV that understands
+	file://filename entries.
+-n::
+--show-nr-samples::
+	Show the number of samples for each symbol
+
+--showcpuutilization::
+        Show sample percentage for different cpu modes.
+
+-T::
+--threads::
+	Show per-thread event counters
+-c::
+--comms=::
+	Only consider symbols in these comms. CSV that understands
+	file://filename entries.
+-S::
+--symbols=::
+	Only consider these symbols. CSV that understands
+	file://filename entries.
+
+--symbol-filter=::
+	Only show symbols that match (partially) with this filter.
+
+-U::
+--hide-unresolved::
+        Only display entries resolved to a symbol.
+
+-s::
+--sort=::
+	Sort histogram entries by given key(s) - multiple keys can be specified
+	in CSV format.  Following sort keys are available:
+	pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight.
+
+	Each key has following meaning:
+
+	- comm: command (name) of the task which can be read via /proc/<pid>/comm
+	- pid: command and tid of the task
+	- dso: name of library or module executed at the time of sample
+	- symbol: name of function executed at the time of sample
+	- parent: name of function matched to the parent regex filter. Unmatched
+	entries are displayed as "[other]".
+	- cpu: cpu number the task ran at the time of sample
+	- srcline: filename and line number executed at the time of sample.  The
+	DWARF debuggin info must be provided.
+
+	By default, comm, dso and symbol keys are used.
+	(i.e. --sort comm,dso,symbol)
+
+	If --branch-stack option is used, following sort keys are also
+	available:
+	dso_from, dso_to, symbol_from, symbol_to, mispredict.
+
+	- dso_from: name of library or module branched from
+	- dso_to: name of library or module branched to
+	- symbol_from: name of function branched from
+	- symbol_to: name of function branched to
+	- mispredict: "N" for predicted branch, "Y" for mispredicted branch
+
+	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
+	and symbol_to, see '--branch-stack'.
+
+-p::
+--parent=<regex>::
+        A regex filter to identify parent. The parent is a caller of this
+	function and searched through the callchain, thus it requires callchain
+	information recorded. The pattern is in the exteneded regex format and
+	defaults to "\^sys_|^do_page_fault", see '--sort parent'.
+
+-x::
+--exclude-other::
+        Only display entries with parent-match.
+
+-w::
+--column-widths=<width[,width...]>::
+	Force each column width to the provided list, for large terminal
+	readability.
+
+-t::
+--field-separator=::
+	Use a special separator character and don't pad with spaces, replacing
+	all occurrences of this separator in symbol names (and other output)
+	with a '.' character, that thus it's the only non valid separator.
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-g [type,min[,limit],order]::
+--call-graph::
+        Display call chains using type, min percent threshold, optional print
+	limit 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.
+
+-G::
+--inverted::
+        alias for inverted caller based call graph.
+
+--pretty=<key>::
+        Pretty printing style.  key: normal, raw
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface, that is integrated with annotate and allows
+        zooming into DSOs or threads, among other features. Use of --tui
+	requires a tty, if one is not present, as when piping to other
+	commands, the stdio interface is used.
+
+--gtk:: Use the GTK2 interface.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+-m::
+--modules::
+        Load module symbols. WARNING: This should only be used with -k and
+        a LIVE kernel.
+
+-f::
+--force::
+        Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	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.
+
+-b::
+--branch-stack::
+	Use the addresses of sampled taken branches instead of the instruction
+	address to build the histograms. To generate meaningful output, the
+	perf.data file must have been obtained using perf record -b or
+	perf record --branch-filter xxx where xxx is a branch filter option.
+	perf report is able to auto-detect whether a perf.data file contains
+	branch stacks and it will automatically switch to the branch view mode,
+	unless --no-branch-stack is used.
+
+--objdump=<path>::
+        Path to objdump binary.
+
+--group::
+	Show event group information together.
+
+--demangle::
+	Demangle symbol names to human readable form. It's enabled by default,
+	disable with --no-demangle.
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-annotate[1]

tools/perf/Documentation/perf-sched.txt

@@ -0,0 +1,55 @@
+perf-sched(1)
+==============
+
+NAME
+----
+perf-sched - Tool to trace/measure scheduler properties (latencies)
+
+SYNOPSIS
+--------
+[verse]
+'perf sched' {record|latency|map|replay|script}
+
+DESCRIPTION
+-----------
+There are five variants of perf sched:
+
+  'perf sched record <command>' to record the scheduling events
+  of an arbitrary workload.
+
+  'perf sched latency' to report the per task scheduling latencies
+  and other scheduling properties of the workload.
+
+  '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
+  that mimic the workload based on the events in the trace. These
+  threads can then replay the timings (CPU runtime and sleep patterns)
+  of the workload as it occurred when it was recorded - and can repeat
+  it a number of times, measuring its performance.)
+
+  'perf sched map' to print a textual context-switching outline of
+  workload captured via perf sched record.  Columns stand for
+  individual CPUs, and the two-letter shortcuts stand for tasks that
+  are running on a CPU. A '*' denotes the CPU that had the event, and
+  a dot signals an idle CPU.
+
+OPTIONS
+-------
+-i::
+--input=<file>::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
+-D::
+--dump-raw-trace=::
+        Display verbose dump of the sched data.
+
+SEE ALSO
+--------
+linkperf:perf-record[1]

tools/perf/Documentation/perf-script-perl.txt

@@ -0,0 +1,216 @@
+perf-script-perl(1)
+==================
+
+NAME
+----
+perf-script-perl - Process trace data with a Perl script
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [-s [Perl]:script[.pl] ]
+
+DESCRIPTION
+-----------
+
+This perf script option is used to process perf script data using perf's
+built-in Perl interpreter.  It reads and processes the input file and
+displays the results of the trace analysis implemented in the given
+Perl script, if any.
+
+STARTER SCRIPTS
+---------------
+
+You can avoid reading the rest of this document by running 'perf script
+-g perl' in the same directory as an existing perf.data trace file.
+That will generate a starter script containing a handler for each of
+the event types in the trace file; it simply prints every available
+field for each event in the trace file.
+
+You can also look at the existing scripts in
+~/libexec/perf-core/scripts/perl for typical examples showing how to
+do basic things like aggregate event data, print results, etc.  Also,
+the check-perf-script.pl script, while not interesting for its results,
+attempts to exercise all of the main scripting features.
+
+EVENT HANDLERS
+--------------
+
+When perf script is invoked using a trace script, a user-defined
+'handler function' is called for each event in the trace.  If there's
+no handler function defined for a given event type, the event is
+ignored (or passed to a 'trace_handled' function, see below) and the
+next event is processed.
+
+Most of the event's field values are passed as arguments to the
+handler function; some of the less common ones aren't - those are
+available as calls back into the perf executable (see below).
+
+As an example, the following perf record command can be used to record
+all sched_wakeup events in the system:
+
+ # perf record -a -e sched:sched_wakeup
+
+Traces meant to be processed using a script should be recorded with
+the above option: -a to enable system-wide collection.
+
+The format file for the sched_wakep event defines the following fields
+(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
+
+----
+ format:
+        field:unsigned short common_type;
+        field:unsigned char common_flags;
+        field:unsigned char common_preempt_count;
+        field:int common_pid;
+
+        field:char comm[TASK_COMM_LEN];
+        field:pid_t pid;
+        field:int prio;
+        field:int success;
+        field:int target_cpu;
+----
+
+The handler function for this event would be defined as:
+
+----
+sub sched::sched_wakeup
+{
+   my ($event_name, $context, $common_cpu, $common_secs,
+       $common_nsecs, $common_pid, $common_comm,
+       $comm, $pid, $prio, $success, $target_cpu) = @_;
+}
+----
+
+The handler function takes the form subsystem::event_name.
+
+The $common_* arguments in the handler's argument list are the set of
+arguments passed to all event handlers; some of the fields correspond
+to the common_* fields in the format file, but some are synthesized,
+and some of the common_* fields aren't common enough to to be passed
+to every event as arguments but are available as library functions.
+
+Here's a brief description of each of the invariant event args:
+
+ $event_name 	  	    the name of the event as text
+ $context		    an opaque 'cookie' used in calls back into perf
+ $common_cpu		    the cpu the event occurred on
+ $common_secs		    the secs portion of the event timestamp
+ $common_nsecs		    the nsecs portion of the event timestamp
+ $common_pid		    the pid of the current task
+ $common_comm		    the name of the current process
+
+All of the remaining fields in the event's format file have
+counterparts as handler function arguments of the same name, as can be
+seen in the example above.
+
+The above provides the basics needed to directly access every field of
+every event in a trace, which covers 90% of what you need to know to
+write a useful trace script.  The sections below cover the rest.
+
+SCRIPT LAYOUT
+-------------
+
+Every perf script Perl script should start by setting up a Perl module
+search path and 'use'ing a few support modules (see module
+descriptions below):
+
+----
+ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+ use lib "./Perf-Trace-Util/lib";
+ use Perf::Trace::Core;
+ use Perf::Trace::Context;
+ use Perf::Trace::Util;
+----
+
+The rest of the script can contain handler functions and support
+functions in any order.
+
+Aside from the event handler functions discussed above, every script
+can implement a set of optional functions:
+
+*trace_begin*, if defined, is called before any event is processed and
+gives scripts a chance to do setup tasks:
+
+----
+ sub trace_begin
+ {
+ }
+----
+
+*trace_end*, if defined, is called after all events have been
+ processed and gives scripts a chance to do end-of-script tasks, such
+ as display results:
+
+----
+sub trace_end
+{
+}
+----
+
+*trace_unhandled*, if defined, is called after for any event that
+ doesn't have a handler explicitly defined for it.  The standard set
+ of common arguments are passed into it:
+
+----
+sub trace_unhandled
+{
+    my ($event_name, $context, $common_cpu, $common_secs,
+        $common_nsecs, $common_pid, $common_comm) = @_;
+}
+----
+
+The remaining sections provide descriptions of each of the available
+built-in perf script Perl modules and their associated functions.
+
+AVAILABLE MODULES AND FUNCTIONS
+-------------------------------
+
+The following sections describe the functions and variables available
+via the various Perf::Trace::* Perl modules.  To use the functions and
+variables from the given module, add the corresponding 'use
+Perf::Trace::XXX' line to your perf script script.
+
+Perf::Trace::Core Module
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+These functions provide some essential functions to user scripts.
+
+The *flag_str* and *symbol_str* functions provide human-readable
+strings for flag and symbolic fields.  These correspond to the strings
+and values parsed from the 'print fmt' fields of the event format
+files:
+
+  flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name
+  symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name
+
+Perf::Trace::Context Module
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some of the 'common' fields in the event format file aren't all that
+common, but need to be made accessible to user scripts nonetheless.
+
+Perf::Trace::Context defines a set of functions that can be used to
+access this data in the context of the current event.  Each of these
+functions expects a $context variable, which is the same as the
+$context variable passed into every event handler as the second
+argument.
+
+ common_pc($context) - returns common_preempt count for the current event
+ common_flags($context) - returns common_flags for the current event
+ common_lock_depth($context) - returns common_lock_depth for the current event
+
+Perf::Trace::Util Module
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Various utility functions for use with perf script:
+
+  nsecs($secs, $nsecs) - returns total nsecs given secs/nsecs pair
+  nsecs_secs($nsecs) - returns whole secs portion given nsecs
+  nsecs_nsecs($nsecs) - returns nsecs remainder given nsecs
+  nsecs_str($nsecs) - returns printable string in the form secs.nsecs
+  avg($total, $n) - returns average given a sum and a total number of values
+
+SEE ALSO
+--------
+linkperf:perf-script[1]

tools/perf/Documentation/perf-script-python.txt

@@ -0,0 +1,620 @@
+perf-script-python(1)
+====================
+
+NAME
+----
+perf-script-python - Process trace data with a Python script
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [-s [Python]:script[.py] ]
+
+DESCRIPTION
+-----------
+
+This perf script option is used to process perf script data using perf's
+built-in Python interpreter.  It reads and processes the input file and
+displays the results of the trace analysis implemented in the given
+Python script, if any.
+
+A QUICK EXAMPLE
+---------------
+
+This section shows the process, start to finish, of creating a working
+Python script that aggregates and extracts useful information from a
+raw perf script stream.  You can avoid reading the rest of this
+document if an example is enough for you; the rest of the document
+provides more details on each step and lists the library functions
+available to script writers.
+
+This example actually details the steps that were used to create the
+'syscall-counts' script you see when you list the available perf script
+scripts via 'perf script -l'.  As such, this script also shows how to
+integrate your script into the list of general-purpose 'perf script'
+scripts listed by that command.
+
+The syscall-counts script is a simple script, but demonstrates all the
+basic ideas necessary to create a useful script.  Here's an example
+of its output (syscall names are not yet supported, they will appear
+as numbers):
+
+----
+syscall events:
+
+event                                          count
+----------------------------------------  -----------
+sys_write                                     455067
+sys_getdents                                    4072
+sys_close                                       3037
+sys_swapoff                                     1769
+sys_read                                         923
+sys_sched_setparam                               826
+sys_open                                         331
+sys_newfstat                                     326
+sys_mmap                                         217
+sys_munmap                                       216
+sys_futex                                        141
+sys_select                                       102
+sys_poll                                          84
+sys_setitimer                                     12
+sys_writev                                         8
+15                                                 8
+sys_lseek                                          7
+sys_rt_sigprocmask                                 6
+sys_wait4                                          3
+sys_ioctl                                          3
+sys_set_robust_list                                1
+sys_exit                                           1
+56                                                 1
+sys_access                                         1
+----
+
+Basically our task is to keep a per-syscall tally that gets updated
+every time a system call occurs in the system.  Our script will do
+that, but first we need to record the data that will be processed by
+that script.  Theoretically, there are a couple of ways we could do
+that:
+
+- we could enable every event under the tracing/events/syscalls
+  directory, but this is over 600 syscalls, well beyond the number
+  allowable by perf.  These individual syscall events will however be
+  useful if we want to later use the guidance we get from the
+  general-purpose scripts to drill down and get more detail about
+  individual syscalls of interest.
+
+- we can enable the sys_enter and/or sys_exit syscalls found under
+  tracing/events/raw_syscalls.  These are called for all syscalls; the
+  'id' field can be used to distinguish between individual syscall
+  numbers.
+
+For this script, we only need to know that a syscall was entered; we
+don't care how it exited, so we'll use 'perf record' to record only
+the sys_enter events:
+
+----
+# perf record -a -e raw_syscalls:sys_enter
+
+^C[ perf record: Woken up 1 times to write data ]
+[ perf record: Captured and wrote 56.545 MB perf.data (~2470503 samples) ]
+----
+
+The options basically say to collect data for every syscall event
+system-wide and multiplex the per-cpu output into a single stream.
+That single stream will be recorded in a file in the current directory
+called perf.data.
+
+Once we have a perf.data file containing our data, we can use the -g
+'perf script' option to generate a Python script that will contain a
+callback handler for each event type found in the perf.data trace
+stream (for more details, see the STARTER SCRIPTS section).
+
+----
+# perf script -g python
+generated Python script: perf-script.py
+
+The output file created also in the current directory is named
+perf-script.py.  Here's the file in its entirety:
+
+# perf script event handlers, generated by perf script -g python
+# Licensed under the terms of the GNU GPL License version 2
+
+# The common_* event handler fields are the most useful fields common to
+# all events.  They don't necessarily correspond to the 'common_*' fields
+# in the format files.  Those fields not available as handler params can
+# be retrieved using Python functions of the form common_*(context).
+# See the perf-script-python Documentation for the list of available functions.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+def trace_begin():
+	print "in trace_begin"
+
+def trace_end():
+	print "in trace_end"
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+		print_header(event_name, common_cpu, common_secs, common_nsecs,
+			common_pid, common_comm)
+
+		print "id=%d, args=%s\n" % \
+		(id, args),
+
+def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
+		common_pid, common_comm):
+		print_header(event_name, common_cpu, common_secs, common_nsecs,
+		common_pid, common_comm)
+
+def print_header(event_name, cpu, secs, nsecs, pid, comm):
+	print "%-20s %5u %05u.%09u %8u %-20s " % \
+	(event_name, cpu, secs, nsecs, pid, comm),
+----
+
+At the top is a comment block followed by some import statements and a
+path append which every perf script script should include.
+
+Following that are a couple generated functions, trace_begin() and
+trace_end(), which are called at the beginning and the end of the
+script respectively (for more details, see the SCRIPT_LAYOUT section
+below).
+
+Following those are the 'event handler' functions generated one for
+every event in the 'perf record' output.  The handler functions take
+the form subsystem__event_name, and contain named parameters, one for
+each field in the event; in this case, there's only one event,
+raw_syscalls__sys_enter().  (see the EVENT HANDLERS section below for
+more info on event handlers).
+
+The final couple of functions are, like the begin and end functions,
+generated for every script.  The first, trace_unhandled(), is called
+every time the script finds an event in the perf.data file that
+doesn't correspond to any event handler in the script.  This could
+mean either that the record step recorded event types that it wasn't
+really interested in, or the script was run against a trace file that
+doesn't correspond to the script.
+
+The script generated by -g option simply prints a line for each
+event found in the trace stream i.e. it basically just dumps the event
+and its parameter values to stdout.  The print_header() function is
+simply a utility function used for that purpose.  Let's rename the
+script and run it to see the default output:
+
+----
+# mv perf-script.py syscall-counts.py
+# perf script -s syscall-counts.py
+
+raw_syscalls__sys_enter     1 00840.847582083     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847595764     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847620860     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847710478     6533 npviewer.bin          id=78, args=
+raw_syscalls__sys_enter     1 00840.847719204     6533 npviewer.bin          id=142, args=
+raw_syscalls__sys_enter     1 00840.847755445     6533 npviewer.bin          id=3, args=
+raw_syscalls__sys_enter     1 00840.847775601     6533 npviewer.bin          id=3, args=
+raw_syscalls__sys_enter     1 00840.847781820     6533 npviewer.bin          id=3, args=
+.
+.
+.
+----
+
+Of course, for this script, we're not interested in printing every
+trace event, but rather aggregating it in a useful way.  So we'll get
+rid of everything to do with printing as well as the trace_begin() and
+trace_unhandled() functions, which we won't be using.  That leaves us
+with this minimalistic skeleton:
+
+----
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+def trace_end():
+	print "in trace_end"
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+----
+
+In trace_end(), we'll simply print the results, but first we need to
+generate some results to print.  To do that we need to have our
+sys_enter() handler do the necessary tallying until all events have
+been counted.  A hash table indexed by syscall id is a good way to
+store that information; every time the sys_enter() handler is called,
+we simply increment a count associated with that hash entry indexed by
+that syscall id:
+
+----
+  syscalls = autodict()
+
+  try:
+    syscalls[id] += 1
+  except TypeError:
+    syscalls[id] = 1
+----
+
+The syscalls 'autodict' object is a special kind of Python dictionary
+(implemented in Core.py) that implements Perl's 'autovivifying' hashes
+in Python i.e. with autovivifying hashes, you can assign nested hash
+values without having to go to the trouble of creating intermediate
+levels if they don't exist e.g syscalls[comm][pid][id] = 1 will create
+the intermediate hash levels and finally assign the value 1 to the
+hash entry for 'id' (because the value being assigned isn't a hash
+object itself, the initial value is assigned in the TypeError
+exception.  Well, there may be a better way to do this in Python but
+that's what works for now).
+
+Putting that code into the raw_syscalls__sys_enter() handler, we
+effectively end up with a single-level dictionary keyed on syscall id
+and having the counts we've tallied as values.
+
+The print_syscall_totals() function iterates over the entries in the
+dictionary and displays a line for each entry containing the syscall
+name (the dictonary keys contain the syscall ids, which are passed to
+the Util function syscall_name(), which translates the raw syscall
+numbers to the corresponding syscall name strings).  The output is
+displayed after all the events in the trace have been processed, by
+calling the print_syscall_totals() function from the trace_end()
+handler called at the end of script processing.
+
+The final script producing the output shown above is shown in its
+entirety below (syscall_name() helper is not yet available, you can
+only deal with id's for now):
+
+----
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+syscalls = autodict()
+
+def trace_end():
+	print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	try:
+		syscalls[id] += 1
+	except TypeError:
+		syscalls[id] = 1
+
+def print_syscall_totals():
+    if for_comm is not None:
+	    print "\nsyscall events for %s:\n\n" % (for_comm),
+    else:
+	    print "\nsyscall events:\n\n",
+
+    print "%-40s  %10s\n" % ("event", "count"),
+    print "%-40s  %10s\n" % ("----------------------------------------", \
+                                 "-----------"),
+
+    for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+				  reverse = True):
+	    print "%-40s  %10d\n" % (syscall_name(id), val),
+----
+
+The script can be run just as before:
+
+  # perf script -s syscall-counts.py
+
+So those are the essential steps in writing and running a script.  The
+process can be generalized to any tracepoint or set of tracepoints
+you're interested in - basically find the tracepoint(s) you're
+interested in by looking at the list of available events shown by
+'perf list' and/or look in /sys/kernel/debug/tracing events for
+detailed event and field info, record the corresponding trace data
+using 'perf record', passing it the list of interesting events,
+generate a skeleton script using 'perf script -g python' and modify the
+code to aggregate and display it for your particular needs.
+
+After you've done that you may end up with a general-purpose script
+that you want to keep around and have available for future use.  By
+writing a couple of very simple shell scripts and putting them in the
+right place, you can have your script listed alongside the other
+scripts listed by the 'perf script -l' command e.g.:
+
+----
+root@tropicana:~# perf script -l
+List of available trace scripts:
+  wakeup-latency                       system-wide min/max/avg wakeup latency
+  rw-by-file <comm>                    r/w activity for a program, by file
+  rw-by-pid                            system-wide r/w activity
+----
+
+A nice side effect of doing this is that you also then capture the
+probably lengthy 'perf record' command needed to record the events for
+the script.
+
+To have the script appear as a 'built-in' script, you write two simple
+scripts, one for recording and one for 'reporting'.
+
+The 'record' script is a shell script with the same base name as your
+script, but with -record appended.  The shell script should be put
+into the perf/scripts/python/bin directory in the kernel source tree.
+In that script, you write the 'perf record' command-line needed for
+your script:
+
+----
+# cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-record
+
+#!/bin/bash
+perf record -a -e raw_syscalls:sys_enter
+----
+
+The 'report' script is also a shell script with the same base name as
+your script, but with -report appended.  It should also be located in
+the perf/scripts/python/bin directory.  In that script, you write the
+'perf script -s' command-line needed for running your script:
+
+----
+# cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-report
+
+#!/bin/bash
+# description: system-wide syscall counts
+perf script -s ~/libexec/perf-core/scripts/python/syscall-counts.py
+----
+
+Note that the location of the Python script given in the shell script
+is in the libexec/perf-core/scripts/python directory - this is where
+the script will be copied by 'make install' when you install perf.
+For the installation to install your script there, your script needs
+to be located in the perf/scripts/python directory in the kernel
+source tree:
+
+----
+# ls -al kernel-source/tools/perf/scripts/python
+
+root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
+total 32
+drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
+drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
+drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin
+-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py
+drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util
+-rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py
+----
+
+Once you've done that (don't forget to do a new 'make install',
+otherwise your script won't show up at run-time), 'perf script -l'
+should show a new entry for your script:
+
+----
+root@tropicana:~# perf script -l
+List of available trace scripts:
+  wakeup-latency                       system-wide min/max/avg wakeup latency
+  rw-by-file <comm>                    r/w activity for a program, by file
+  rw-by-pid                            system-wide r/w activity
+  syscall-counts                       system-wide syscall counts
+----
+
+You can now perform the record step via 'perf script record':
+
+  # perf script record syscall-counts
+
+and display the output using 'perf script report':
+
+  # perf script report syscall-counts
+
+STARTER SCRIPTS
+---------------
+
+You can quickly get started writing a script for a particular set of
+trace data by generating a skeleton script using 'perf script -g
+python' in the same directory as an existing perf.data trace file.
+That will generate a starter script containing a handler for each of
+the event types in the trace file; it simply prints every available
+field for each event in the trace file.
+
+You can also look at the existing scripts in
+~/libexec/perf-core/scripts/python for typical examples showing how to
+do basic things like aggregate event data, print results, etc.  Also,
+the check-perf-script.py script, while not interesting for its results,
+attempts to exercise all of the main scripting features.
+
+EVENT HANDLERS
+--------------
+
+When perf script is invoked using a trace script, a user-defined
+'handler function' is called for each event in the trace.  If there's
+no handler function defined for a given event type, the event is
+ignored (or passed to a 'trace_handled' function, see below) and the
+next event is processed.
+
+Most of the event's field values are passed as arguments to the
+handler function; some of the less common ones aren't - those are
+available as calls back into the perf executable (see below).
+
+As an example, the following perf record command can be used to record
+all sched_wakeup events in the system:
+
+ # perf record -a -e sched:sched_wakeup
+
+Traces meant to be processed using a script should be recorded with
+the above option: -a to enable system-wide collection.
+
+The format file for the sched_wakep event defines the following fields
+(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
+
+----
+ format:
+        field:unsigned short common_type;
+        field:unsigned char common_flags;
+        field:unsigned char common_preempt_count;
+        field:int common_pid;
+
+        field:char comm[TASK_COMM_LEN];
+        field:pid_t pid;
+        field:int prio;
+        field:int success;
+        field:int target_cpu;
+----
+
+The handler function for this event would be defined as:
+
+----
+def sched__sched_wakeup(event_name, context, common_cpu, common_secs,
+       common_nsecs, common_pid, common_comm,
+       comm, pid, prio, success, target_cpu):
+       pass
+----
+
+The handler function takes the form subsystem__event_name.
+
+The common_* arguments in the handler's argument list are the set of
+arguments passed to all event handlers; some of the fields correspond
+to the common_* fields in the format file, but some are synthesized,
+and some of the common_* fields aren't common enough to to be passed
+to every event as arguments but are available as library functions.
+
+Here's a brief description of each of the invariant event args:
+
+ event_name 	  	    the name of the event as text
+ context		    an opaque 'cookie' used in calls back into perf
+ common_cpu		    the cpu the event occurred on
+ common_secs		    the secs portion of the event timestamp
+ common_nsecs		    the nsecs portion of the event timestamp
+ common_pid		    the pid of the current task
+ common_comm		    the name of the current process
+
+All of the remaining fields in the event's format file have
+counterparts as handler function arguments of the same name, as can be
+seen in the example above.
+
+The above provides the basics needed to directly access every field of
+every event in a trace, which covers 90% of what you need to know to
+write a useful trace script.  The sections below cover the rest.
+
+SCRIPT LAYOUT
+-------------
+
+Every perf script Python script should start by setting up a Python
+module search path and 'import'ing a few support modules (see module
+descriptions below):
+
+----
+ import os
+ import sys
+
+ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	      '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+ from perf_trace_context import *
+ from Core import *
+----
+
+The rest of the script can contain handler functions and support
+functions in any order.
+
+Aside from the event handler functions discussed above, every script
+can implement a set of optional functions:
+
+*trace_begin*, if defined, is called before any event is processed and
+gives scripts a chance to do setup tasks:
+
+----
+def trace_begin:
+    pass
+----
+
+*trace_end*, if defined, is called after all events have been
+ processed and gives scripts a chance to do end-of-script tasks, such
+ as display results:
+
+----
+def trace_end:
+    pass
+----
+
+*trace_unhandled*, if defined, is called after for any event that
+ doesn't have a handler explicitly defined for it.  The standard set
+ of common arguments are passed into it:
+
+----
+def trace_unhandled(event_name, context, common_cpu, common_secs,
+        common_nsecs, common_pid, common_comm):
+    pass
+----
+
+The remaining sections provide descriptions of each of the available
+built-in perf script Python modules and their associated functions.
+
+AVAILABLE MODULES AND FUNCTIONS
+-------------------------------
+
+The following sections describe the functions and variables available
+via the various perf script Python modules.  To use the functions and
+variables from the given module, add the corresponding 'from XXXX
+import' line to your perf script script.
+
+Core.py Module
+~~~~~~~~~~~~~~
+
+These functions provide some essential functions to user scripts.
+
+The *flag_str* and *symbol_str* functions provide human-readable
+strings for flag and symbolic fields.  These correspond to the strings
+and values parsed from the 'print fmt' fields of the event format
+files:
+
+  flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
+  symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
+
+The *autodict* function returns a special kind of Python
+dictionary that implements Perl's 'autovivifying' hashes in Python
+i.e. with autovivifying hashes, you can assign nested hash values
+without having to go to the trouble of creating intermediate levels if
+they don't exist.
+
+  autodict() - returns an autovivifying dictionary instance
+
+
+perf_trace_context Module
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some of the 'common' fields in the event format file aren't all that
+common, but need to be made accessible to user scripts nonetheless.
+
+perf_trace_context defines a set of functions that can be used to
+access this data in the context of the current event.  Each of these
+functions expects a context variable, which is the same as the
+context variable passed into every event handler as the second
+argument.
+
+ common_pc(context) - returns common_preempt count for the current event
+ common_flags(context) - returns common_flags for the current event
+ common_lock_depth(context) - returns common_lock_depth for the current event
+
+Util.py Module
+~~~~~~~~~~~~~~
+
+Various utility functions for use with perf script:
+
+  nsecs(secs, nsecs) - returns total nsecs given secs/nsecs pair
+  nsecs_secs(nsecs) - returns whole secs portion given nsecs
+  nsecs_nsecs(nsecs) - returns nsecs remainder given nsecs
+  nsecs_str(nsecs) - returns printable string in the form secs.nsecs
+  avg(total, n) - returns average given a sum and a total number of values
+
+SEE ALSO
+--------
+linkperf:perf-script[1]

tools/perf/Documentation/perf-script.txt

@@ -0,0 +1,209 @@
+perf-script(1)
+=============
+
+NAME
+----
+perf-script - Read perf.data (created by perf record) and display trace output
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [<options>]
+'perf script' [<options>] record <script> [<record-options>] <command>
+'perf script' [<options>] report <script> [script-args]
+'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf script' [<options>] <top-script> [script-args]
+
+DESCRIPTION
+-----------
+This command reads the input file and displays the trace recorded.
+
+There are several variants of perf script:
+
+  'perf script' to see a detailed trace of the workload that was
+  recorded.
+
+  You can also run a set of pre-canned scripts that aggregate and
+  summarize the raw trace data in various ways (the list of scripts is
+  available via 'perf script -l').  The following variants allow you to
+  record and run those scripts:
+
+  'perf script record <script> <command>' to record the events required
+  for 'perf script report'.  <script> is the name displayed in the
+  output of 'perf script --list' i.e. the actual script name minus any
+  language extension.  If <command> is not specified, the events are
+  recorded using the -a (system-wide) 'perf record' option.
+
+  'perf script report <script> [args]' to run and display the results
+  of <script>.  <script> is the name displayed in the output of 'perf
+  trace --list' i.e. the actual script name minus any language
+  extension.  The perf.data output from a previous run of 'perf script
+  record <script>' is used and should be present for this command to
+  succeed.  [args] refers to the (mainly optional) args expected by
+  the script.
+
+  'perf script <script> <required-script-args> <command>' to both
+  record the events required for <script> and to run the <script>
+  using 'live-mode' i.e. without writing anything to disk.  <script>
+  is the name displayed in the output of 'perf script --list' i.e. the
+  actual script name minus any language extension.  If <command> is
+  not specified, the events are recorded using the -a (system-wide)
+  'perf record' option.  If <script> has any required args, they
+  should be specified before <command>.  This mode doesn't allow for
+  optional script args to be specified; if optional script args are
+  desired, they can be specified using separate 'perf script record'
+  and 'perf script report' commands, with the stdout of the record step
+  piped to the stdin of the report script, using the '-o -' and '-i -'
+  options of the corresponding commands.
+
+  'perf script <top-script>' to both record the events required for
+  <top-script> and to run the <top-script> using 'live-mode'
+  i.e. without writing anything to disk.  <top-script> is the name
+  displayed in the output of 'perf script --list' i.e. the actual
+  script name minus any language extension; a <top-script> is defined
+  as any script name ending with the string 'top'.
+
+  [<record-options>] can be passed to the record steps of 'perf script
+  record' and 'live-mode' variants; this isn't possible however for
+  <top-script> 'live-mode' or 'perf script report' variants.
+
+  See the 'SEE ALSO' section for links to language-specific
+  information on how to write and run your own trace scripts.
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-D::
+--dump-raw-script=::
+        Display verbose dump of the trace data.
+
+-L::
+--Latency=::
+        Show latency attributes (irqs/preemption disabled, etc).
+
+-l::
+--list=::
+        Display a list of available trace scripts.
+
+-s ['lang']::
+--script=::
+        Process trace data with the given script ([lang]:script[.ext]).
+	If the string 'lang' is specified in place of a script name, a
+        list of supported languages will be displayed instead.
+
+-g::
+--gen-script=::
+        Generate perf-script.[ext] starter script for given language,
+        using current perf.data.
+
+-a::
+        Force system-wide collection.  Scripts run without a <command>
+        normally use -a by default, while scripts run with a <command>
+        normally don't - this option allows the latter to be run in
+        system-wide mode.
+
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-d::
+--debug-mode::
+        Do various checks like samples ordering and lost events.
+
+-f::
+--fields::
+        Comma separated list of fields to print. Options are:
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
+        Field list can be prepended with the type, trace, sw or hw,
+        to indicate to which event type the field list applies.
+        e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
+
+		perf script -f <fields>
+
+	is equivalent to:
+
+		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+    
+	i.e., the specified fields apply to all event types if the type string
+	is not given.
+    
+	The arguments are processed in the order received. A later usage can
+	reset a prior request. e.g.:
+    
+		-f trace: -f comm,tid,time,ip,sym
+    
+	The first -f suppresses trace events (field list is ""), but then the
+	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
+	warning is given to the user:
+    
+		"Overriding previous field request for all events."
+    
+	Alternativey, consider the order:
+    
+		-f comm,tid,time,ip,sym -f trace:
+    
+	The first -f sets the fields for all events and the second -f
+	suppresses trace events. The user is given a warning message about
+	the override, and the result of the above is that only S/W and H/W
+	events are displayed with the given fields.
+    
+	For the 'wildcard' option if a user selected field is invalid for an
+	event type, a message is displayed to the user that the option is
+	ignored for that type. For example:
+    
+		$ perf script -f comm,tid,trace
+		'trace' not valid for hardware events. Ignoring.
+		'trace' not valid for software events. Ignoring.
+    
+	Alternatively, if the type is given an invalid field is specified it
+	is an error. For example:
+    
+        perf script -v -f sw:comm,tid,trace
+        'trace' not valid for software events.
+    
+	At this point usage is displayed, and perf-script exits.
+    
+	Finally, a user may not set fields to none for all event types.
+	i.e., -f "" is not allowed.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-G::
+--hide-call-graph::
+        When printing symbols do not display call chain.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
+-c::
+--comms=::
+	Only display events for these comms. CSV that understands
+	file://filename entries.
+
+-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.
+
+--show-kernel-path::
+	Try to resolve the path of [kernel.kallsyms]
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-script-perl[1],
+linkperf:perf-script-python[1]

tools/perf/Documentation/perf-stat.txt

@@ -0,0 +1,155 @@
+perf-stat(1)
+============
+
+NAME
+----
+perf-stat - Run a command and gather performance counter statistics
+
+SYNOPSIS
+--------
+[verse]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
+
+DESCRIPTION
+-----------
+This command runs a command and gathers performance counter statistics
+from it.
+
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+
+-e::
+--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.
+
+-i::
+--no-inherit::
+        child tasks do not inherit counters
+-p::
+--pid=<pid>::
+        stat events on existing process id (comma separated list)
+
+-t::
+--tid=<tid>::
+        stat events on existing thread id (comma separated list)
+
+
+-a::
+--all-cpus::
+        system-wide collection from all CPUs
+
+-c::
+--scale::
+	scale/normalize counter values
+
+-r::
+--repeat=<n>::
+	repeat command and print average + stddev (max: 100). 0 means forever.
+
+-B::
+--big-num::
+        print large numbers with thousands' separators according to locale
+
+-C::
+--cpu=::
+Count only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode, this option is ignored. The -a option is still necessary
+to activate system-wide monitoring. Default is to count on all CPUs.
+
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
+This option is only valid in system-wide mode.
+
+-n::
+--null::
+        null run - don't start any counters
+
+-v::
+--verbose::
+        be more verbose (show counter open errors, etc)
+
+-x SEP::
+--field-separator SEP::
+print counts using a CSV-style output to make it easy to import directly into
+spreadsheets. Columns are separated by the string specified in SEP.
+
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+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 -- $cmd
+
+--pre::
+--post::
+	Pre and post measurement hooks, e.g.:
+
+perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
+
+-I msecs::
+--interval-print msecs::
+	Print count deltas every N milliseconds (minimum: 100ms)
+	example: perf stat -I 1000 -e cycles -a sleep 5
+
+--per-socket::
+Aggregate counts per processor socket for system-wide mode measurements.  This
+is a useful mode to detect imbalance between sockets.  To enable this mode,
+use --per-socket in addition to -a. (system-wide).  The output includes the
+socket number and the number of online processors on that socket. This is
+useful to gauge the amount of aggregation.
+
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.  This
+is a useful mode to detect imbalance between physical cores.  To enable this mode,
+use --per-core in addition to -a. (system-wide).  The output includes the
+core number and the number of online logical processors on that physical processor.
+
+EXAMPLES
+--------
+
+$ perf stat -- make -j
+
+ Performance counter stats for 'make -j':
+
+    8117.370256  task clock ticks     #      11.281 CPU utilization factor
+            678  context switches     #       0.000 M/sec
+            133  CPU migrations       #       0.000 M/sec
+         235724  pagefaults           #       0.029 M/sec
+    24821162526  CPU cycles           #    3057.784 M/sec
+    18687303457  instructions         #    2302.138 M/sec
+      172158895  cache references     #      21.209 M/sec
+       27075259  cache misses         #       3.335 M/sec
+
+ Wall-clock time elapsed:   719.554352 msecs
+
+SEE ALSO
+--------
+linkperf:perf-top[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-test.txt

@@ -0,0 +1,32 @@
+perf-test(1)
+============
+
+NAME
+----
+perf-test - Runs sanity tests.
+
+SYNOPSIS
+--------
+[verse]
+'perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]'
+
+DESCRIPTION
+-----------
+This command does assorted sanity tests, initially through linked routines but
+also will look for a directory with more tests in the form of scripts.
+
+To get a list of available tests use 'perf test list', specifying a test name
+fragment will show all tests that have it.
+
+To run just specific tests, inform test name fragments or the numbers obtained
+from 'perf test list'.
+
+OPTIONS
+-------
+-s::
+--skip::
+	Tests to skip (comma separater numeric list).
+
+-v::
+--verbose::
+	Be more verbose.

tools/perf/Documentation/perf-timechart.txt

@@ -0,0 +1,46 @@
+perf-timechart(1)
+=================
+
+NAME
+----
+perf-timechart - Tool to visualize total system behavior during a workload
+
+SYNOPSIS
+--------
+[verse]
+'perf timechart' {record}
+
+DESCRIPTION
+-----------
+There are two variants of perf timechart:
+
+  'perf timechart record <command>' to record the system level events
+  of an arbitrary workload.
+
+  'perf timechart' to turn a trace into a Scalable Vector Graphics file,
+  that can be viewed with popular SVG viewers such as 'Inkscape'.
+
+OPTIONS
+-------
+-o::
+--output=::
+        Select the output file (default: output.svg)
+-i::
+--input=::
+        Select the input file (default: perf.data unless stdin is a fifo)
+-w::
+--width=::
+        Select the width of the SVG file (default: 1000)
+-P::
+--power-only::
+        Only output the CPU power section of the diagram
+-p::
+--process::
+        Select the processes to display, by name or PID
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+SEE ALSO
+--------
+linkperf:perf-record[1]

tools/perf/Documentation/perf-top.txt

@@ -0,0 +1,193 @@
+perf-top(1)
+===========
+
+NAME
+----
+perf-top - System profiling tool.
+
+SYNOPSIS
+--------
+[verse]
+'perf top' [-e <EVENT> | --event=EVENT] [<options>]
+
+DESCRIPTION
+-----------
+This command generates and displays a performance counter profile in real time.
+
+
+OPTIONS
+-------
+-a::
+--all-cpus::
+        System-wide collection.  (default)
+
+-c <count>::
+--count=<count>::
+	Event period to sample.
+
+-C <cpu-list>::
+--cpu=<cpu>::
+Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Default is to monitor all CPUS.
+
+-d <seconds>::
+--delay=<seconds>::
+	Number of seconds to delay between refreshes.
+
+-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.
+
+-E <entries>::
+--entries=<entries>::
+	Display this many functions.
+
+-f <count>::
+--count-filter=<count>::
+	Only display functions with more events than this.
+
+-g::
+--group::
+        Put the counters into a counter group.
+
+-F <freq>::
+--freq=<freq>::
+	Profile at this frequency.
+
+-i::
+--inherit::
+	Child tasks do not inherit counters.
+
+-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 Process ID (comma separated list).
+
+-t <tid>::
+--tid=<tid>::
+        Profile events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
+-r <priority>::
+--realtime=<priority>::
+	Collect data with this RT SCHED_FIFO priority.
+
+-s <symbol>::
+--sym-annotate=<symbol>::
+        Annotate this symbol.
+
+-K::
+--hide_kernel_symbols::
+        Hide kernel symbols.
+
+-U::
+--hide_user_symbols::
+        Hide user symbols.
+
+-D::
+--dump-symtab::
+        Dump the symbol table used for profiling.
+
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
+
+-z::
+--zero::
+	Zero history across display updates.
+
+-s::
+--sort::
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight.
+
+-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
+--------------------------
+
+[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.
+
+[z]::
+	Toggle event count zeroing across display updates.
+
+[qQ]::
+	Quit.
+
+Pressing any unmapped key displays a menu, and prompts for input.
+
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-trace.txt

@@ -0,0 +1,59 @@
+perf-trace(1)
+=============
+
+NAME
+----
+perf-trace - strace inspired tool
+
+SYNOPSIS
+--------
+[verse]
+'perf trace'
+
+DESCRIPTION
+-----------
+This command will show the events associated with the target, initially
+syscalls, but other system events like pagefaults, task lifetime events,
+scheduling events, etc.
+
+Initially this is a live mode only tool, but eventually will work with
+perf.data files like the other tools, allowing a detached 'record' from
+analysis phases.
+
+OPTIONS
+-------
+
+--all-cpus::
+        System-wide collection from all CPUs.
+
+-p::
+--pid=::
+	Record events on existing process ID (comma separated list).
+
+--tid=::
+        Record events on existing thread ID (comma separated list).
+
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
+--no-inherit::
+	Child tasks do not inherit counters.
+
+--mmap-pages=::
+	Number of mmap data pages. Must be a power of two.
+
+--cpu::
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), Events are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+--duration:
+	Show only events that had a duration greater than N.M ms.
+
+--sched:
+	Accrue thread runtime and provide a summary at the end of the session.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-script[1]

tools/perf/Documentation/perf.txt

@@ -0,0 +1,24 @@
+perf(1)
+=======
+
+NAME
+----
+perf - Performance analysis tools for Linux
+
+SYNOPSIS
+--------
+[verse]
+'perf' [--version] [--help] COMMAND [ARGS]
+
+DESCRIPTION
+-----------
+Performance counters for Linux are a new kernel-based subsystem
+that provide a framework for all things performance analysis. It
+covers hardware level (CPU/PMU, Performance Monitoring Unit) features
+and software features (software counters, tracepoints) as well.
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-top[1],
+linkperf:perf-record[1], linkperf:perf-report[1],
+linkperf:perf-list[1]

tools/perf/Documentation/perfconfig.example

@@ -0,0 +1,29 @@
+[colors]
+
+	# These were the old defaults
+	top = red, lightgray
+	medium = green, lightgray
+	normal = black, lightgray
+	selected = lightgray, magenta
+	code = blue, lightgray
+	addr = magenta, lightgray
+
+[tui]
+
+	# Defaults if linked with libslang
+	report = on
+	annotate = on
+	top = on
+
+[buildid]
+
+	# Default, disable using /dev/null
+	dir = /root/.debug
+
+[annotate]
+
+	# Defaults
+	hide_src_code = false
+	use_offset = true
+	jump_arrows = true
+	show_nr_jumps = false

tools/perf/MANIFEST

@@ -0,0 +1,32 @@
+tools/perf
+tools/scripts
+tools/lib/traceevent
+tools/lib/lk
+include/linux/const.h
+include/linux/perf_event.h
+include/linux/rbtree.h
+include/linux/list.h
+include/linux/hash.h
+include/linux/stringify.h
+lib/rbtree.c
+include/linux/swab.h
+arch/*/include/asm/unistd*.h
+arch/*/include/asm/perf_regs.h
+arch/*/include/uapi/asm/unistd*.h
+arch/*/include/uapi/asm/perf_regs.h
+arch/*/lib/memcpy*.S
+arch/*/lib/memset*.S
+include/linux/poison.h
+include/linux/magic.h
+include/linux/hw_breakpoint.h
+include/linux/rbtree_augmented.h
+include/uapi/linux/perf_event.h
+include/uapi/linux/const.h
+include/uapi/linux/swab.h
+include/uapi/linux/hw_breakpoint.h
+arch/x86/include/asm/svm.h
+arch/x86/include/asm/vmx.h
+arch/x86/include/asm/kvm_host.h
+arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/vmx.h
+arch/x86/include/uapi/asm/kvm.h

tools/perf/arch/arm/Makefile

@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/arm/util/dwarf-regs.c

@@ -0,0 +1,64 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+	{.name = STR(%r##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	REG_DWARFNUM_NAME("%fp", 11),
+	REG_DWARFNUM_NAME("%ip", 12),
+	REG_DWARFNUM_NAME("%sp", 13),
+	REG_DWARFNUM_NAME("%lr", 14),
+	REG_DWARFNUM_NAME("%pc", 15),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}

tools/perf/arch/common.c

@@ -0,0 +1,212 @@
+#include <stdio.h>
+#include <sys/utsname.h>
+#include "common.h"
+#include "../util/debug.h"
+
+const char *const arm_triplets[] = {
+	"arm-eabi-",
+	"arm-linux-androideabi-",
+	"arm-unknown-linux-",
+	"arm-unknown-linux-gnu-",
+	"arm-unknown-linux-gnueabi-",
+	NULL
+};
+
+const char *const powerpc_triplets[] = {
+	"powerpc-unknown-linux-gnu-",
+	"powerpc64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const s390_triplets[] = {
+	"s390-ibm-linux-",
+	NULL
+};
+
+const char *const sh_triplets[] = {
+	"sh-unknown-linux-gnu-",
+	"sh64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const sparc_triplets[] = {
+	"sparc-unknown-linux-gnu-",
+	"sparc64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const x86_triplets[] = {
+	"x86_64-pc-linux-gnu-",
+	"x86_64-unknown-linux-gnu-",
+	"i686-pc-linux-gnu-",
+	"i586-pc-linux-gnu-",
+	"i486-pc-linux-gnu-",
+	"i386-pc-linux-gnu-",
+	"i686-linux-android-",
+	"i686-android-linux-",
+	NULL
+};
+
+const char *const mips_triplets[] = {
+	"mips-unknown-linux-gnu-",
+	"mipsel-linux-android-",
+	NULL
+};
+
+static bool lookup_path(char *name)
+{
+	bool found = false;
+	char *path, *tmp;
+	char buf[PATH_MAX];
+	char *env = getenv("PATH");
+
+	if (!env)
+		return false;
+
+	env = strdup(env);
+	if (!env)
+		return false;
+
+	path = strtok_r(env, ":", &tmp);
+	while (path) {
+		scnprintf(buf, sizeof(buf), "%s/%s", path, name);
+		if (access(buf, F_OK) == 0) {
+			found = true;
+			break;
+		}
+		path = strtok_r(NULL, ":", &tmp);
+	}
+	free(env);
+	return found;
+}
+
+static int lookup_triplets(const char *const *triplets, const char *name)
+{
+	int i;
+	char buf[PATH_MAX];
+
+	for (i = 0; triplets[i] != NULL; i++) {
+		scnprintf(buf, sizeof(buf), "%s%s", triplets[i], name);
+		if (lookup_path(buf))
+			return i;
+	}
+	return -1;
+}
+
+/*
+ * Return architecture name in a normalized form.
+ * The conversion logic comes from the Makefile.
+ */
+static const char *normalize_arch(char *arch)
+{
+	if (!strcmp(arch, "x86_64"))
+		return "x86";
+	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
+		return "x86";
+	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
+		return "sparc";
+	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
+		return "arm";
+	if (!strncmp(arch, "s390", 4))
+		return "s390";
+	if (!strncmp(arch, "parisc", 6))
+		return "parisc";
+	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
+		return "powerpc";
+	if (!strncmp(arch, "mips", 4))
+		return "mips";
+	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
+		return "sh";
+
+	return arch;
+}
+
+static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
+						  const char *name,
+						  const char **path)
+{
+	int idx;
+	const char *arch, *cross_env;
+	struct utsname uts;
+	const char *const *path_list;
+	char *buf = NULL;
+
+	arch = normalize_arch(env->arch);
+
+	if (uname(&uts) < 0)
+		goto out;
+
+	/*
+	 * We don't need to try to find objdump path for native system.
+	 * Just use default binutils path (e.g.: "objdump").
+	 */
+	if (!strcmp(normalize_arch(uts.machine), arch))
+		goto out;
+
+	cross_env = getenv("CROSS_COMPILE");
+	if (cross_env) {
+		if (asprintf(&buf, "%s%s", cross_env, name) < 0)
+			goto out_error;
+		if (buf[0] == '/') {
+			if (access(buf, F_OK) == 0)
+				goto out;
+			goto out_error;
+		}
+		if (lookup_path(buf))
+			goto out;
+		free(buf);
+		buf = NULL;
+	}
+
+	if (!strcmp(arch, "arm"))
+		path_list = arm_triplets;
+	else if (!strcmp(arch, "powerpc"))
+		path_list = powerpc_triplets;
+	else if (!strcmp(arch, "sh"))
+		path_list = sh_triplets;
+	else if (!strcmp(arch, "s390"))
+		path_list = s390_triplets;
+	else if (!strcmp(arch, "sparc"))
+		path_list = sparc_triplets;
+	else if (!strcmp(arch, "x86"))
+		path_list = x86_triplets;
+	else if (!strcmp(arch, "mips"))
+		path_list = mips_triplets;
+	else {
+		ui__error("binutils for %s not supported.\n", arch);
+		goto out_error;
+	}
+
+	idx = lookup_triplets(path_list, name);
+	if (idx < 0) {
+		ui__error("Please install %s for %s.\n"
+			  "You can add it to PATH, set CROSS_COMPILE or "
+			  "override the default using --%s.\n",
+			  name, arch, name);
+		goto out_error;
+	}
+
+	if (asprintf(&buf, "%s%s", path_list[idx], name) < 0)
+		goto out_error;
+
+out:
+	*path = buf;
+	return 0;
+out_error:
+	free(buf);
+	*path = NULL;
+	return -1;
+}
+
+int perf_session_env__lookup_objdump(struct perf_session_env *env)
+{
+	/*
+	 * For live mode, env->arch will be NULL and we can use
+	 * the native objdump tool.
+	 */
+	if (env->arch == NULL)
+		return 0;
+
+	return perf_session_env__lookup_binutils_path(env, "objdump",
+						      &objdump_path);
+}

tools/perf/arch/common.h

@@ -0,0 +1,10 @@
+#ifndef ARCH_PERF_COMMON_H
+#define ARCH_PERF_COMMON_H
+
+#include "../util/session.h"
+
+extern const char *objdump_path;
+
+int perf_session_env__lookup_objdump(struct perf_session_env *env);
+
+#endif /* ARCH_PERF_COMMON_H */

tools/perf/arch/powerpc/Makefile

@@ -0,0 +1,5 @@
+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

tools/perf/arch/powerpc/util/dwarf-regs.c

@@ -0,0 +1,88 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Ian Munsie, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num)	\
+	{.name = STR(%gpr##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	GPR_DWARFNUM_NAME(11),
+	GPR_DWARFNUM_NAME(12),
+	GPR_DWARFNUM_NAME(13),
+	GPR_DWARFNUM_NAME(14),
+	GPR_DWARFNUM_NAME(15),
+	GPR_DWARFNUM_NAME(16),
+	GPR_DWARFNUM_NAME(17),
+	GPR_DWARFNUM_NAME(18),
+	GPR_DWARFNUM_NAME(19),
+	GPR_DWARFNUM_NAME(20),
+	GPR_DWARFNUM_NAME(21),
+	GPR_DWARFNUM_NAME(22),
+	GPR_DWARFNUM_NAME(23),
+	GPR_DWARFNUM_NAME(24),
+	GPR_DWARFNUM_NAME(25),
+	GPR_DWARFNUM_NAME(26),
+	GPR_DWARFNUM_NAME(27),
+	GPR_DWARFNUM_NAME(28),
+	GPR_DWARFNUM_NAME(29),
+	GPR_DWARFNUM_NAME(30),
+	GPR_DWARFNUM_NAME(31),
+	REG_DWARFNUM_NAME("%msr",   66),
+	REG_DWARFNUM_NAME("%ctr",   109),
+	REG_DWARFNUM_NAME("%link",  108),
+	REG_DWARFNUM_NAME("%xer",   101),
+	REG_DWARFNUM_NAME("%dar",   119),
+	REG_DWARFNUM_NAME("%dsisr", 118),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}

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 = scnprintf(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;
+}

tools/perf/arch/s390/Makefile

@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/s390/util/dwarf-regs.c

@@ -0,0 +1,22 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+#define NUM_GPRS 16
+
+static const char *gpr_names[NUM_GPRS] = {
+	"%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
+	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+};
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+}

tools/perf/arch/sh/Makefile

@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/sh/util/dwarf-regs.c

@@ -0,0 +1,55 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Matt Fleming <matt@console-pimps.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+/*
+ * Generic dwarf analysis helpers
+ */
+
+#define SH_MAX_REGS 18
+const char *sh_regs_table[SH_MAX_REGS] = {
+	"r0",
+	"r1",
+	"r2",
+	"r3",
+	"r4",
+	"r5",
+	"r6",
+	"r7",
+	"r8",
+	"r9",
+	"r10",
+	"r11",
+	"r12",
+	"r13",
+	"r14",
+	"r15",
+	"pc",
+	"pr",
+};
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= SH_MAX_REGS) ? sh_regs_table[n] : NULL;
+}

tools/perf/arch/sparc/Makefile

@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif

tools/perf/arch/sparc/util/dwarf-regs.c

@@ -0,0 +1,43 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 David S. Miller <davem@davemloft.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+#define SPARC_MAX_REGS	96
+
+const char *sparc_regs_table[SPARC_MAX_REGS] = {
+	"%g0", "%g1", "%g2", "%g3", "%g4", "%g5", "%g6", "%g7",
+	"%o0", "%o1", "%o2", "%o3", "%o4", "%o5", "%sp", "%o7",
+	"%l0", "%l1", "%l2", "%l3", "%l4", "%l5", "%l6", "%l7",
+	"%i0", "%i1", "%i2", "%i3", "%i4", "%i5", "%fp", "%i7",
+	"%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
+	"%f8", "%f9", "%f10", "%f11", "%f12", "%f13", "%f14", "%f15",
+	"%f16", "%f17", "%f18", "%f19", "%f20", "%f21", "%f22", "%f23",
+	"%f24", "%f25", "%f26", "%f27", "%f28", "%f29", "%f30", "%f31",
+	"%f32", "%f33", "%f34", "%f35", "%f36", "%f37", "%f38", "%f39",
+	"%f40", "%f41", "%f42", "%f43", "%f44", "%f45", "%f46", "%f47",
+	"%f48", "%f49", "%f50", "%f51", "%f52", "%f53", "%f54", "%f55",
+	"%f56", "%f57", "%f58", "%f59", "%f60", "%f61", "%f62", "%f63",
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
+}

tools/perf/arch/x86/Makefile

@@ -0,0 +1,8 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o

tools/perf/arch/x86/include/perf_regs.h

@@ -0,0 +1,80 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include "../../util/types.h"
+#include <asm/perf_regs.h>
+
+#ifndef ARCH_X86_64
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+		       (1ULL << PERF_REG_X86_ES) | \
+		       (1ULL << PERF_REG_X86_FS) | \
+		       (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#endif
+#define PERF_REG_IP PERF_REG_X86_IP
+#define PERF_REG_SP PERF_REG_X86_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_X86_AX:
+		return "AX";
+	case PERF_REG_X86_BX:
+		return "BX";
+	case PERF_REG_X86_CX:
+		return "CX";
+	case PERF_REG_X86_DX:
+		return "DX";
+	case PERF_REG_X86_SI:
+		return "SI";
+	case PERF_REG_X86_DI:
+		return "DI";
+	case PERF_REG_X86_BP:
+		return "BP";
+	case PERF_REG_X86_SP:
+		return "SP";
+	case PERF_REG_X86_IP:
+		return "IP";
+	case PERF_REG_X86_FLAGS:
+		return "FLAGS";
+	case PERF_REG_X86_CS:
+		return "CS";
+	case PERF_REG_X86_SS:
+		return "SS";
+	case PERF_REG_X86_DS:
+		return "DS";
+	case PERF_REG_X86_ES:
+		return "ES";
+	case PERF_REG_X86_FS:
+		return "FS";
+	case PERF_REG_X86_GS:
+		return "GS";
+#ifdef ARCH_X86_64
+	case PERF_REG_X86_R8:
+		return "R8";
+	case PERF_REG_X86_R9:
+		return "R9";
+	case PERF_REG_X86_R10:
+		return "R10";
+	case PERF_REG_X86_R11:
+		return "R11";
+	case PERF_REG_X86_R12:
+		return "R12";
+	case PERF_REG_X86_R13:
+		return "R13";
+	case PERF_REG_X86_R14:
+		return "R14";
+	case PERF_REG_X86_R15:
+		return "R15";
+#endif /* ARCH_X86_64 */
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */

tools/perf/arch/x86/util/dwarf-regs.c

@@ -0,0 +1,75 @@
+/*
+ * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
+ * Extracted from probe-finder.c
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+/*
+ * Generic dwarf analysis helpers
+ */
+
+#define X86_32_MAX_REGS 8
+const char *x86_32_regs_table[X86_32_MAX_REGS] = {
+	"%ax",
+	"%cx",
+	"%dx",
+	"%bx",
+	"$stack",	/* Stack address instead of %sp */
+	"%bp",
+	"%si",
+	"%di",
+};
+
+#define X86_64_MAX_REGS 16
+const char *x86_64_regs_table[X86_64_MAX_REGS] = {
+	"%ax",
+	"%dx",
+	"%cx",
+	"%bx",
+	"%si",
+	"%di",
+	"%bp",
+	"%sp",
+	"%r8",
+	"%r9",
+	"%r10",
+	"%r11",
+	"%r12",
+	"%r13",
+	"%r14",
+	"%r15",
+};
+
+/* TODO: switching by dwarf address size */
+#ifdef __x86_64__
+#define ARCH_MAX_REGS X86_64_MAX_REGS
+#define arch_regs_table x86_64_regs_table
+#else
+#define ARCH_MAX_REGS X86_32_MAX_REGS
+#define arch_regs_table x86_32_regs_table
+#endif
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
+}

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 = scnprintf(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;
+}

tools/perf/arch/x86/util/unwind.c

@@ -0,0 +1,111 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef ARCH_X86_64
+int unwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_64_RAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_64_RDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_64_RCX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_64_RBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_64_RSI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_64_RDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_64_RBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_64_RSP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_64_R8:
+		id = PERF_REG_X86_R8;
+		break;
+	case UNW_X86_64_R9:
+		id = PERF_REG_X86_R9;
+		break;
+	case UNW_X86_64_R10:
+		id = PERF_REG_X86_R10;
+		break;
+	case UNW_X86_64_R11:
+		id = PERF_REG_X86_R11;
+		break;
+	case UNW_X86_64_R12:
+		id = PERF_REG_X86_R12;
+		break;
+	case UNW_X86_64_R13:
+		id = PERF_REG_X86_R13;
+		break;
+	case UNW_X86_64_R14:
+		id = PERF_REG_X86_R14;
+		break;
+	case UNW_X86_64_R15:
+		id = PERF_REG_X86_R15;
+		break;
+	case UNW_X86_64_RIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#else
+int unwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_EAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_EDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_ECX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_EBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_ESI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_EDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_EBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_ESP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_EIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#endif /* ARCH_X86_64 */

tools/perf/bash_completion

@@ -0,0 +1,62 @@
+# perf completion
+
+function_exists()
+{
+	declare -F $1 > /dev/null
+	return $?
+}
+
+function_exists __ltrim_colon_completions ||
+__ltrim_colon_completions()
+{
+	if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then
+		# Remove colon-word prefix from COMPREPLY items
+		local colon_word=${1%${1##*:}}
+		local i=${#COMPREPLY[*]}
+		while [[ $((--i)) -ge 0 ]]; do
+			COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"}
+		done
+	fi
+}
+
+have perf &&
+_perf()
+{
+	local cur prev cmd
+
+	COMPREPLY=()
+	if function_exists _get_comp_words_by_ref; then
+		_get_comp_words_by_ref -n : cur prev
+	else
+		cur=$(_get_cword :)
+		prev=${COMP_WORDS[COMP_CWORD-1]}
+	fi
+
+	cmd=${COMP_WORDS[0]}
+
+	# List perf subcommands or long options
+	if [ $COMP_CWORD -eq 1 ]; then
+		if [[ $cur == --* ]]; then
+			COMPREPLY=( $( compgen -W '--help --version \
+			--exec-path --html-path --paginate --no-pager \
+			--perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
+		else
+			cmds=$($cmd --list-cmds)
+			COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+		fi
+	# List possible events for -e option
+	elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then
+		evts=$($cmd list --raw-dump)
+		COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
+		__ltrim_colon_completions $cur
+	# List long option names
+	elif [[ $cur == --* ]];  then
+		subcmd=${COMP_WORDS[1]}
+		opts=$($cmd $subcmd --list-opts)
+		COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
+	# Fall down to list regular files
+	else
+		_filedir
+	fi
+} &&
+complete -F _perf perf

tools/perf/bench/bench.h

@@ -0,0 +1,44 @@
+#ifndef BENCH_H
+#define BENCH_H
+
+/*
+ * The madvise transparent hugepage constants were added in glibc
+ * 2.13. For compatibility with older versions of glibc, define these
+ * tokens if they are not already defined.
+ *
+ * PA-RISC uses different madvise values from other architectures and
+ * needs to be special-cased.
+ */
+#ifdef __hppa__
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		67
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	68
+# endif
+#else
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		14
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	15
+# endif
+#endif
+
+extern int bench_numa(int argc, const char **argv, const char *prefix);
+extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
+extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+extern int bench_mem_memcpy(int argc, const char **argv,
+			    const char *prefix __maybe_unused);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
+
+#define BENCH_FORMAT_DEFAULT_STR	"default"
+#define BENCH_FORMAT_DEFAULT		0
+#define BENCH_FORMAT_SIMPLE_STR		"simple"
+#define BENCH_FORMAT_SIMPLE		1
+
+#define BENCH_FORMAT_UNKNOWN		-1
+
+extern int bench_format;
+
+#endif

tools/perf/bench/mem-memcpy-arch.h

@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMCPY_FN(fn, name, desc)		\
+	extern void *fn(void *, const void *, size_t);
+
+#include "mem-memcpy-x86-64-asm-def.h"
+
+#undef MEMCPY_FN
+
+#endif
+

tools/perf/bench/mem-memcpy-x86-64-asm-def.h

@@ -0,0 +1,12 @@
+
+MEMCPY_FN(__memcpy,
+	"x86-64-unrolled",
+	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c,
+	"x86-64-movsq",
+	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c_e,
+	"x86-64-movsb",
+	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")