Commit 88a57667 authored by Linus Torvalds's avatar Linus Torvalds

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

Pull perf fixes and cleanups from Ingo Molnar:
 "A kernel fix plus mostly tooling fixes, but also some tooling
  restructuring and cleanups"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  perf: Fix building warning on ARM 32
  perf symbols: Fix use after free in filename__read_build_id
  perf evlist: Use roundup_pow_of_two
  tools: Adopt roundup_pow_of_two
  perf tools: Make the mmap length autotuning more robust
  tools: Adopt rounddown_pow_of_two and deps
  tools: Adopt fls_long and deps
  tools: Move bitops.h from tools/perf/util to tools/
  tools: Introduce asm-generic/bitops.h
  tools lib: Move asm-generic/bitops/find.h code to tools/include and tools/lib
  tools: Whitespace prep patches for moving bitops.h
  tools: Move code originally from asm-generic/atomic.h into tools/include/asm-generic/
  tools: Move code originally from linux/log2.h to tools/include/linux/
  tools: Move __ffs implementation to tools/include/asm-generic/bitops/__ffs.h
  perf evlist: Do not use hard coded value for a mmap_pages default
  perf trace: Let the perf_evlist__mmap autosize the number of pages to use
  perf evlist: Improve the strerror_mmap method
  perf evlist: Clarify sterror_mmap variable names
  perf evlist: Fixup brown paper bag on "hint" for --mmap-pages cmdline arg
  perf trace: Provide a better explanation when mmap fails
  ...
parents 34b85e35 ac931f87
...@@ -276,6 +276,17 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, ...@@ -276,6 +276,17 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
return box; return box;
} }
/*
* Using uncore_pmu_event_init pmu event_init callback
* as a detection point for uncore events.
*/
static int uncore_pmu_event_init(struct perf_event *event);
static bool is_uncore_event(struct perf_event *event)
{
return event->pmu->event_init == uncore_pmu_event_init;
}
static int static int
uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
{ {
...@@ -290,13 +301,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b ...@@ -290,13 +301,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
return -EINVAL; return -EINVAL;
n = box->n_events; n = box->n_events;
if (is_uncore_event(leader)) {
box->event_list[n] = leader; box->event_list[n] = leader;
n++; n++;
}
if (!dogrp) if (!dogrp)
return n; return n;
list_for_each_entry(event, &leader->sibling_list, group_entry) { list_for_each_entry(event, &leader->sibling_list, group_entry) {
if (event->state <= PERF_EVENT_STATE_OFF) if (!is_uncore_event(event) ||
event->state <= PERF_EVENT_STATE_OFF)
continue; continue;
if (n >= max_count) if (n >= max_count)
......
...@@ -7477,11 +7477,11 @@ SYSCALL_DEFINE5(perf_event_open, ...@@ -7477,11 +7477,11 @@ SYSCALL_DEFINE5(perf_event_open,
if (move_group) { if (move_group) {
synchronize_rcu(); synchronize_rcu();
perf_install_in_context(ctx, group_leader, event->cpu); perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx); get_ctx(ctx);
list_for_each_entry(sibling, &group_leader->sibling_list, list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) { group_entry) {
perf_install_in_context(ctx, sibling, event->cpu); perf_install_in_context(ctx, sibling, sibling->cpu);
get_ctx(ctx); get_ctx(ctx);
} }
} }
......
...@@ -330,10 +330,10 @@ static void set_subtitle(void) ...@@ -330,10 +330,10 @@ static void set_subtitle(void)
list_for_each_entry(sp, &trail, entries) { list_for_each_entry(sp, &trail, entries) {
if (sp->text) { if (sp->text) {
if (pos) { if (pos) {
pos->next = xcalloc(sizeof(*pos), 1); pos->next = xcalloc(1, sizeof(*pos));
pos = pos->next; pos = pos->next;
} else { } else {
subtitles = pos = xcalloc(sizeof(*pos), 1); subtitles = pos = xcalloc(1, sizeof(*pos));
} }
pos->text = sp->text; pos->text = sp->text;
} }
......
#ifndef __TOOLS_ASM_GENERIC_BITOPS_H
#define __TOOLS_ASM_GENERIC_BITOPS_H
/*
* tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed
* some functions.
*
* For the benefit of those who are trying to port Linux to another
* architecture, here are some C-language equivalents. You should
* recode these in the native assembly language, if at all possible.
*
* C language equivalents written by Theodore Ts'o, 9/26/92
*/
#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/find.h>
#ifndef _TOOLS_LINUX_BITOPS_H_
#error only <linux/bitops.h> can be included directly
#endif
#include <asm-generic/bitops/atomic.h>
#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
#include <asm/types.h>
/**
* __ffs - find first bit in word.
* @word: The word to search
*
* Undefined if no bit exists, so code should check against 0 first.
*/
static __always_inline unsigned long __ffs(unsigned long word)
{
int num = 0;
#if __BITS_PER_LONG == 64
if ((word & 0xffffffff) == 0) {
num += 32;
word >>= 32;
}
#endif
if ((word & 0xffff) == 0) {
num += 16;
word >>= 16;
}
if ((word & 0xff) == 0) {
num += 8;
word >>= 8;
}
if ((word & 0xf) == 0) {
num += 4;
word >>= 4;
}
if ((word & 0x3) == 0) {
num += 2;
word >>= 2;
}
if ((word & 0x1) == 0)
num += 1;
return num;
}
#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */
#include <../../../../include/asm-generic/bitops/__fls.h>
#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
#include <asm/types.h>
static inline void set_bit(int nr, unsigned long *addr)
{
addr[nr / __BITS_PER_LONG] |= 1UL << (nr % __BITS_PER_LONG);
}
static inline void clear_bit(int nr, unsigned long *addr)
{
addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
}
static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
{
return ((1UL << (nr % __BITS_PER_LONG)) &
(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
}
#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
#ifndef find_next_bit
/**
* find_next_bit - find the next set bit in a memory region
* @addr: The address to base the search on
* @offset: The bitnumber to start searching at
* @size: The bitmap size in bits
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
size, unsigned long offset);
#endif
#ifndef find_first_bit
/**
* find_first_bit - find the first set bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
*
* Returns the bit number of the first set bit.
* If no bits are set, returns @size.
*/
extern unsigned long find_first_bit(const unsigned long *addr,
unsigned long size);
#endif /* find_first_bit */
#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
#include <../../../../include/asm-generic/bitops/fls.h>
#include <../../../../include/asm-generic/bitops/fls64.h>
#ifndef _TOOLS_LINUX_BITOPS_H_
#define _TOOLS_LINUX_BITOPS_H_
#include <linux/kernel.h>
#include <linux/compiler.h>
#include <asm/hweight.h>
#ifndef __WORDSIZE
#define __WORDSIZE (__SIZEOF_LONG__ * 8)
#endif
#define BITS_PER_LONG __WORDSIZE
#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE)
/*
* Include this here because some architectures need generic_ffs/fls in
* scope
*
* XXX: this needs to be asm/bitops.h, when we get to per arch optimizations
*/
#include <asm-generic/bitops.h>
#define for_each_set_bit(bit, addr, size) \
for ((bit) = find_first_bit((addr), (size)); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
for ((bit) = find_next_bit((addr), (size), (bit)); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
static inline unsigned long hweight_long(unsigned long w)
{
return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
}
static inline unsigned fls_long(unsigned long l)
{
if (sizeof(l) == 4)
return fls(l);
return fls64(l);
}
#endif
/* Integer base 2 logarithm calculation
*
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@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.
*/
#ifndef _TOOLS_LINUX_LOG2_H
#define _TOOLS_LINUX_LOG2_H
/*
* deal with unrepresentable constant logarithms
*/
extern __attribute__((const, noreturn))
int ____ilog2_NaN(void);
/*
* non-constant log of base 2 calculators
* - the arch may override these in asm/bitops.h if they can be implemented
* more efficiently than using fls() and fls64()
* - the arch is not required to handle n==0 if implementing the fallback
*/
static inline __attribute__((const))
int __ilog2_u32(u32 n)
{
return fls(n) - 1;
}
static inline __attribute__((const))
int __ilog2_u64(u64 n)
{
return fls64(n) - 1;
}
/*
* Determine whether some value is a power of two, where zero is
* *not* considered a power of two.
*/
static inline __attribute__((const))
bool is_power_of_2(unsigned long n)
{
return (n != 0 && ((n & (n - 1)) == 0));
}
/*
* round up to nearest power of two
*/
static inline __attribute__((const))
unsigned long __roundup_pow_of_two(unsigned long n)
{
return 1UL << fls_long(n - 1);
}
/*
* round down to nearest power of two
*/
static inline __attribute__((const))
unsigned long __rounddown_pow_of_two(unsigned long n)
{
return 1UL << (fls_long(n) - 1);
}
/**
* ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value
* @n - parameter
*
* constant-capable log of base 2 calculation
* - this can be used to initialise global variables from constant data, hence
* the massive ternary operator construction
*
* selects the appropriately-sized optimised version depending on sizeof(n)
*/
#define ilog2(n) \
( \
__builtin_constant_p(n) ? ( \
(n) < 1 ? ____ilog2_NaN() : \
(n) & (1ULL << 63) ? 63 : \
(n) & (1ULL << 62) ? 62 : \
(n) & (1ULL << 61) ? 61 : \
(n) & (1ULL << 60) ? 60 : \
(n) & (1ULL << 59) ? 59 : \
(n) & (1ULL << 58) ? 58 : \
(n) & (1ULL << 57) ? 57 : \
(n) & (1ULL << 56) ? 56 : \
(n) & (1ULL << 55) ? 55 : \
(n) & (1ULL << 54) ? 54 : \
(n) & (1ULL << 53) ? 53 : \
(n) & (1ULL << 52) ? 52 : \
(n) & (1ULL << 51) ? 51 : \
(n) & (1ULL << 50) ? 50 : \
(n) & (1ULL << 49) ? 49 : \
(n) & (1ULL << 48) ? 48 : \
(n) & (1ULL << 47) ? 47 : \
(n) & (1ULL << 46) ? 46 : \
(n) & (1ULL << 45) ? 45 : \
(n) & (1ULL << 44) ? 44 : \
(n) & (1ULL << 43) ? 43 : \
(n) & (1ULL << 42) ? 42 : \
(n) & (1ULL << 41) ? 41 : \
(n) & (1ULL << 40) ? 40 : \
(n) & (1ULL << 39) ? 39 : \
(n) & (1ULL << 38) ? 38 : \
(n) & (1ULL << 37) ? 37 : \
(n) & (1ULL << 36) ? 36 : \
(n) & (1ULL << 35) ? 35 : \
(n) & (1ULL << 34) ? 34 : \
(n) & (1ULL << 33) ? 33 : \
(n) & (1ULL << 32) ? 32 : \
(n) & (1ULL << 31) ? 31 : \
(n) & (1ULL << 30) ? 30 : \
(n) & (1ULL << 29) ? 29 : \
(n) & (1ULL << 28) ? 28 : \
(n) & (1ULL << 27) ? 27 : \
(n) & (1ULL << 26) ? 26 : \
(n) & (1ULL << 25) ? 25 : \
(n) & (1ULL << 24) ? 24 : \
(n) & (1ULL << 23) ? 23 : \
(n) & (1ULL << 22) ? 22 : \
(n) & (1ULL << 21) ? 21 : \
(n) & (1ULL << 20) ? 20 : \
(n) & (1ULL << 19) ? 19 : \
(n) & (1ULL << 18) ? 18 : \
(n) & (1ULL << 17) ? 17 : \
(n) & (1ULL << 16) ? 16 : \
(n) & (1ULL << 15) ? 15 : \
(n) & (1ULL << 14) ? 14 : \
(n) & (1ULL << 13) ? 13 : \
(n) & (1ULL << 12) ? 12 : \
(n) & (1ULL << 11) ? 11 : \
(n) & (1ULL << 10) ? 10 : \
(n) & (1ULL << 9) ? 9 : \
(n) & (1ULL << 8) ? 8 : \
(n) & (1ULL << 7) ? 7 : \
(n) & (1ULL << 6) ? 6 : \
(n) & (1ULL << 5) ? 5 : \
(n) & (1ULL << 4) ? 4 : \
(n) & (1ULL << 3) ? 3 : \
(n) & (1ULL << 2) ? 2 : \
(n) & (1ULL << 1) ? 1 : \
(n) & (1ULL << 0) ? 0 : \
____ilog2_NaN() \
) : \
(sizeof(n) <= 4) ? \
__ilog2_u32(n) : \
__ilog2_u64(n) \
)
/**
* roundup_pow_of_two - round the given value up to nearest power of two
* @n - parameter
*
* round the given value up to the nearest power of two
* - the result is undefined when n == 0
* - this can be used to initialise global variables from constant data
*/
#define roundup_pow_of_two(n) \
( \
__builtin_constant_p(n) ? ( \
(n == 1) ? 1 : \
(1UL << (ilog2((n) - 1) + 1)) \
) : \
__roundup_pow_of_two(n) \
)
/**
* rounddown_pow_of_two - round the given value down to nearest power of two
* @n - parameter
*
* round the given value down to the nearest power of two
* - the result is undefined when n == 0
* - this can be used to initialise global variables from constant data
*/
#define rounddown_pow_of_two(n) \
( \
__builtin_constant_p(n) ? ( \
(1UL << ilog2(n))) : \
__rounddown_pow_of_two(n) \
)
#endif /* _TOOLS_LINUX_LOG2_H */
...@@ -7,6 +7,10 @@ ...@@ -7,6 +7,10 @@
#include <stdlib.h> #include <stdlib.h>
#include <string.h> #include <string.h>
#include <sys/vfs.h> #include <sys/vfs.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include "debugfs.h" #include "debugfs.h"
#include "fs.h" #include "fs.h"
...@@ -163,3 +167,33 @@ const char *name##__mountpoint(void) \ ...@@ -163,3 +167,33 @@ const char *name##__mountpoint(void) \
FS__MOUNTPOINT(sysfs, FS__SYSFS); FS__MOUNTPOINT(sysfs, FS__SYSFS);
FS__MOUNTPOINT(procfs, FS__PROCFS); FS__MOUNTPOINT(procfs, FS__PROCFS);
int filename__read_int(const char *filename, int *value)
{
char line[64];
int fd = open(filename, O_RDONLY), err = -1;
if (fd < 0)
return -1;
if (read(fd, line, sizeof(line)) > 0) {
*value = atoi(line);
err = 0;
}
close(fd);
return err;
}
int sysctl__read_int(const char *sysctl, int *value)
{
char path[PATH_MAX];
const char *procfs = procfs__mountpoint();
if (!procfs)
return -1;
snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl);
return filename__read_int(path, value);
}
...@@ -11,4 +11,7 @@ ...@@ -11,4 +11,7 @@
const char *sysfs__mountpoint(void); const char *sysfs__mountpoint(void);
const char *procfs__mountpoint(void); const char *procfs__mountpoint(void);
int filename__read_int(const char *filename, int *value);
int sysctl__read_int(const char *sysctl, int *value);
#endif /* __API_FS__ */ #endif /* __API_FS__ */
#ifndef _PERF_LINUX_BITOPS_H_ /* find_next_bit.c: fallback find next bit implementation
#define _PERF_LINUX_BITOPS_H_
#include <linux/kernel.h>
#include <linux/compiler.h>
#include <asm/hweight.h>
#ifndef __WORDSIZE
#define __WORDSIZE (__SIZEOF_LONG__ * 8)
#endif
#define BITS_PER_LONG __WORDSIZE
#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE)
#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
#define for_each_set_bit(bit, addr, size) \
for ((bit) = find_first_bit((addr), (size)); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
for ((bit) = find_next_bit((addr), (size), (bit)); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
static inline void set_bit(int nr, unsigned long *addr)
{
addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
}
static inline void clear_bit(int nr, unsigned long *addr)
{
addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
}
static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
{
return ((1UL << (nr % BITS_PER_LONG)) &
(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
}
static inline unsigned long hweight_long(unsigned long w)
{
return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
}
#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
/**
* __ffs - find first bit in word.
* @word: The word to search
* *
* Undefined if no bit exists, so code should check against 0 first. * Copied from lib/find_next_bit.c to tools/lib/next_bit.c
*/ *
static __always_inline unsigned long __ffs(unsigned long word) * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
{ * Written by David Howells (dhowells@redhat.com)
int num = 0; *
* This program is free software; you can redistribute it and/or
#if BITS_PER_LONG == 64 * modify it under the terms of the GNU General Public License
if ((word & 0xffffffff) == 0) { * as published by the Free Software Foundation; either version
num += 32; * 2 of the License, or (at your option) any later version.
word >>= 32;
}
#endif
if ((word & 0xffff) == 0) {
num += 16;
word >>= 16;
}
if ((word & 0xff) == 0) {
num += 8;
word >>= 8;
}
if ((word & 0xf) == 0) {
num += 4;
word >>= 4;
}
if ((word & 0x3) == 0) {
num += 2;
word >>= 2;
}
if ((word & 0x1) == 0)
num += 1;
return num;
}
typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
/*
* Find the first set bit in a memory region.
*/ */
static inline unsigned long
find_first_bit(const unsigned long *addr, unsigned long size)
{
long_alias_t *p = (long_alias_t *) addr;
unsigned long result = 0;
unsigned long tmp;
while (size & ~(BITS_PER_LONG-1)) { #include <linux/bitops.h>
if ((tmp = *(p++))) #include <asm/types.h>
goto found; #include <asm/byteorder.h>
result += BITS_PER_LONG;
size -= BITS_PER_LONG;
}
if (!size)
return result;
tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); #define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
if (tmp == 0UL) /* Are any bits set? */
return result + size; /* Nope. */
found:
return result + __ffs(tmp);
}
#ifndef find_next_bit
/* /*
* Find the next set bit in a memory region. * Find the next set bit in a memory region.
*/ */
static inline unsigned long unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) unsigned long offset)
{ {
const unsigned long *p = addr + BITOP_WORD(offset); const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG-1); unsigned long result = offset & ~(BITS_PER_LONG-1);
...@@ -158,5 +59,31 @@ find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offse ...@@ -158,5 +59,31 @@ find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offse
found_middle: found_middle:
return result + __ffs(tmp); return result + __ffs(tmp);
} }
#endif
#ifndef find_first_bit
/*
* Find the first set bit in a memory region.
*/
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
const unsigned long *p = addr;
unsigned long result = 0;
unsigned long tmp;
while (size & ~(BITS_PER_LONG-1)) {
if ((tmp = *(p++)))
goto found;
result += BITS_PER_LONG;
size -= BITS_PER_LONG;
}
if (!size)
return result;
tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
if (tmp == 0UL) /* Are any bits set? */
return result + size; /* Nope. */
found:
return result + __ffs(tmp);
}
#endif #endif
...@@ -18,6 +18,10 @@ OPTIONS ...@@ -18,6 +18,10 @@ OPTIONS
--debug verbose # sets verbose = 1 --debug verbose # sets verbose = 1
--debug verbose=2 # sets verbose = 2 --debug verbose=2 # sets verbose = 2
--buildid-dir::
Setup buildid cache directory. It has higher priority than
buildid.dir config file option.
DESCRIPTION DESCRIPTION
----------- -----------
Performance counters for Linux are a new kernel-based subsystem Performance counters for Linux are a new kernel-based subsystem
......
...@@ -4,17 +4,31 @@ tools/lib/traceevent ...@@ -4,17 +4,31 @@ tools/lib/traceevent
tools/lib/api tools/lib/api
tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
tools/include/asm/bug.h tools/include/asm/bug.h
tools/include/asm-generic/bitops/atomic.h
tools/include/asm-generic/bitops/__ffs.h
tools/include/asm-generic/bitops/__fls.h
tools/include/asm-generic/bitops/find.h
tools/include/asm-generic/bitops/fls64.h
tools/include/asm-generic/bitops/fls.h
tools/include/asm-generic/bitops.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h tools/include/linux/compiler.h
tools/include/linux/hash.h
tools/include/linux/export.h tools/include/linux/export.h
tools/include/linux/hash.h
tools/include/linux/log2.h
tools/include/linux/types.h tools/include/linux/types.h
include/asm-generic/bitops/fls64.h
include/asm-generic/bitops/__fls.h
include/asm-generic/bitops/fls.h
include/linux/const.h include/linux/const.h
include/linux/perf_event.h include/linux/perf_event.h
include/linux/rbtree.h include/linux/rbtree.h
include/linux/list.h include/linux/list.h
include/linux/hash.h include/linux/hash.h
include/linux/stringify.h include/linux/stringify.h
lib/find_next_bit.c
lib/rbtree.c lib/rbtree.c
include/linux/swab.h include/linux/swab.h
arch/*/include/asm/unistd*.h arch/*/include/asm/unistd*.h
......
...@@ -231,8 +231,16 @@ LIB_H += ../../include/uapi/linux/const.h ...@@ -231,8 +231,16 @@ LIB_H += ../../include/uapi/linux/const.h
LIB_H += ../include/linux/hash.h LIB_H += ../include/linux/hash.h
LIB_H += ../../include/linux/stringify.h LIB_H += ../../include/linux/stringify.h
LIB_H += util/include/linux/bitmap.h LIB_H += util/include/linux/bitmap.h
LIB_H += util/include/linux/bitops.h LIB_H += ../include/linux/bitops.h
LIB_H += ../include/asm-generic/bitops/atomic.h
LIB_H += ../include/asm-generic/bitops/find.h
LIB_H += ../include/asm-generic/bitops/fls64.h
LIB_H += ../include/asm-generic/bitops/fls.h
LIB_H += ../include/asm-generic/bitops/__ffs.h
LIB_H += ../include/asm-generic/bitops/__fls.h
LIB_H += ../include/asm-generic/bitops.h
LIB_H += ../include/linux/compiler.h LIB_H += ../include/linux/compiler.h
LIB_H += ../include/linux/log2.h
LIB_H += util/include/linux/const.h LIB_H += util/include/linux/const.h
LIB_H += util/include/linux/ctype.h LIB_H += util/include/linux/ctype.h
LIB_H += util/include/linux/kernel.h LIB_H += util/include/linux/kernel.h
...@@ -335,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/event.o ...@@ -335,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/event.o
LIB_OBJS += $(OUTPUT)util/evlist.o LIB_OBJS += $(OUTPUT)util/evlist.o
LIB_OBJS += $(OUTPUT)util/evsel.o LIB_OBJS += $(OUTPUT)util/evsel.o
LIB_OBJS += $(OUTPUT)util/exec_cmd.o LIB_OBJS += $(OUTPUT)util/exec_cmd.o
LIB_OBJS += $(OUTPUT)util/find_next_bit.o
LIB_OBJS += $(OUTPUT)util/help.o LIB_OBJS += $(OUTPUT)util/help.o
LIB_OBJS += $(OUTPUT)util/kallsyms.o LIB_OBJS += $(OUTPUT)util/kallsyms.o
LIB_OBJS += $(OUTPUT)util/levenshtein.o LIB_OBJS += $(OUTPUT)util/levenshtein.o
...@@ -458,7 +467,6 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o ...@@ -458,7 +467,6 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
endif endif
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
...@@ -735,6 +743,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS ...@@ -735,6 +743,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
......
...@@ -13,6 +13,7 @@ ...@@ -13,6 +13,7 @@
#include "../util/cloexec.h" #include "../util/cloexec.h"
#include "bench.h" #include "bench.h"
#include "mem-memcpy-arch.h" #include "mem-memcpy-arch.h"
#include "mem-memset-arch.h"
#include <stdio.h> #include <stdio.h>
#include <stdlib.h> #include <stdlib.h>
...@@ -48,20 +49,24 @@ static const struct option options[] = { ...@@ -48,20 +49,24 @@ static const struct option options[] = {
}; };
typedef void *(*memcpy_t)(void *, const void *, size_t); typedef void *(*memcpy_t)(void *, const void *, size_t);
typedef void *(*memset_t)(void *, int, size_t);
struct routine { struct routine {
const char *name; const char *name;
const char *desc; const char *desc;
memcpy_t fn; union {
memcpy_t memcpy;
memset_t memset;
} fn;
}; };
struct routine routines[] = { struct routine memcpy_routines[] = {
{ "default", { .name = "default",
"Default memcpy() provided by glibc", .desc = "Default memcpy() provided by glibc",
memcpy }, .fn.memcpy = memcpy },
#ifdef HAVE_ARCH_X86_64_SUPPORT #ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMCPY_FN(fn, name, desc) { name, desc, fn }, #define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
#include "mem-memcpy-x86-64-asm-def.h" #include "mem-memcpy-x86-64-asm-def.h"
#undef MEMCPY_FN #undef MEMCPY_FN
...@@ -69,7 +74,7 @@ struct routine routines[] = { ...@@ -69,7 +74,7 @@ struct routine routines[] = {
{ NULL, { NULL,
NULL, NULL,
NULL } {NULL} }
}; };
static const char * const bench_mem_memcpy_usage[] = { static const char * const bench_mem_memcpy_usage[] = {
...@@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts) ...@@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts)
(double)ts->tv_usec / (double)1000000; (double)ts->tv_usec / (double)1000000;
} }
static void alloc_mem(void **dst, void **src, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
*src = zalloc(length);
if (!*src)
die("memory allocation failed - maybe length is too large?\n");
/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
memset(*src, 0, length);
}
static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *src = NULL, *dst = NULL;
int i;
alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
cycle_end = get_cycle();
free(src);
free(dst);
return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
void *src = NULL, *dst = NULL;
int i;
alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(src);
free(dst);
return (double)((double)len / timeval2double(&tv_diff));
}
#define pf (no_prefault ? 0 : 1) #define pf (no_prefault ? 0 : 1)
#define print_bps(x) do { \ #define print_bps(x) do { \
...@@ -180,16 +128,25 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) ...@@ -180,16 +128,25 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
printf(" %14lf GB/Sec", x / K / K / K); \ printf(" %14lf GB/Sec", x / K / K / K); \
} while (0) } while (0)
int bench_mem_memcpy(int argc, const char **argv, struct bench_mem_info {
const char *prefix __maybe_unused) const struct routine *routines;
u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault);
double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault);
const char *const *usage;
};
static int bench_mem_common(int argc, const char **argv,
const char *prefix __maybe_unused,
struct bench_mem_info *info)
{ {
int i; int i;
size_t len; size_t len;
double totallen;
double result_bps[2]; double result_bps[2];
u64 result_cycle[2]; u64 result_cycle[2];
argc = parse_options(argc, argv, options, argc = parse_options(argc, argv, options,
bench_mem_memcpy_usage, 0); info->usage, 0);
if (no_prefault && only_prefault) { if (no_prefault && only_prefault) {
fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
...@@ -200,6 +157,7 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -200,6 +157,7 @@ int bench_mem_memcpy(int argc, const char **argv,
init_cycle(); init_cycle();
len = (size_t)perf_atoll((char *)length_str); len = (size_t)perf_atoll((char *)length_str);
totallen = (double)len * iterations;
result_cycle[0] = result_cycle[1] = 0ULL; result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0; result_bps[0] = result_bps[1] = 0.0;
...@@ -213,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -213,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv,
if (only_prefault && no_prefault) if (only_prefault && no_prefault)
only_prefault = no_prefault = false; only_prefault = no_prefault = false;
for (i = 0; routines[i].name; i++) { for (i = 0; info->routines[i].name; i++) {
if (!strcmp(routines[i].name, routine)) if (!strcmp(info->routines[i].name, routine))
break; break;
} }
if (!routines[i].name) { if (!info->routines[i].name) {
printf("Unknown routine:%s\n", routine); printf("Unknown routine:%s\n", routine);
printf("Available routines...\n"); printf("Available routines...\n");
for (i = 0; routines[i].name; i++) { for (i = 0; info->routines[i].name; i++) {
printf("\t%s ... %s\n", printf("\t%s ... %s\n",
routines[i].name, routines[i].desc); info->routines[i].name, info->routines[i].desc);
} }
return 1; return 1;
} }
...@@ -234,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -234,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv,
/* show both of results */ /* show both of results */
if (use_cycle) { if (use_cycle) {
result_cycle[0] = result_cycle[0] =
do_memcpy_cycle(routines[i].fn, len, false); info->do_cycle(&info->routines[i], len, false);
result_cycle[1] = result_cycle[1] =
do_memcpy_cycle(routines[i].fn, len, true); info->do_cycle(&info->routines[i], len, true);
} else { } else {
result_bps[0] = result_bps[0] =
do_memcpy_gettimeofday(routines[i].fn, info->do_gettimeofday(&info->routines[i],
len, false); len, false);
result_bps[1] = result_bps[1] =
do_memcpy_gettimeofday(routines[i].fn, info->do_gettimeofday(&info->routines[i],
len, true); len, true);
} }
} else { } else {
if (use_cycle) { if (use_cycle) {
result_cycle[pf] = result_cycle[pf] =
do_memcpy_cycle(routines[i].fn, info->do_cycle(&info->routines[i],
len, only_prefault); len, only_prefault);
} else { } else {
result_bps[pf] = result_bps[pf] =
do_memcpy_gettimeofday(routines[i].fn, info->do_gettimeofday(&info->routines[i],
len, only_prefault); len, only_prefault);
} }
} }
...@@ -263,10 +221,10 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -263,10 +221,10 @@ int bench_mem_memcpy(int argc, const char **argv,
if (use_cycle) { if (use_cycle) {
printf(" %14lf Cycle/Byte\n", printf(" %14lf Cycle/Byte\n",
(double)result_cycle[0] (double)result_cycle[0]
/ (double)len); / totallen);
printf(" %14lf Cycle/Byte (with prefault)\n", printf(" %14lf Cycle/Byte (with prefault)\n",
(double)result_cycle[1] (double)result_cycle[1]
/ (double)len); / totallen);
} else { } else {
print_bps(result_bps[0]); print_bps(result_bps[0]);
printf("\n"); printf("\n");
...@@ -277,7 +235,7 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -277,7 +235,7 @@ int bench_mem_memcpy(int argc, const char **argv,
if (use_cycle) { if (use_cycle) {
printf(" %14lf Cycle/Byte", printf(" %14lf Cycle/Byte",
(double)result_cycle[pf] (double)result_cycle[pf]
/ (double)len); / totallen);
} else } else
print_bps(result_bps[pf]); print_bps(result_bps[pf]);
...@@ -288,8 +246,8 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -288,8 +246,8 @@ int bench_mem_memcpy(int argc, const char **argv,
if (!only_prefault && !no_prefault) { if (!only_prefault && !no_prefault) {
if (use_cycle) { if (use_cycle) {
printf("%lf %lf\n", printf("%lf %lf\n",
(double)result_cycle[0] / (double)len, (double)result_cycle[0] / totallen,
(double)result_cycle[1] / (double)len); (double)result_cycle[1] / totallen);
} else { } else {
printf("%lf %lf\n", printf("%lf %lf\n",
result_bps[0], result_bps[1]); result_bps[0], result_bps[1]);
...@@ -297,7 +255,7 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -297,7 +255,7 @@ int bench_mem_memcpy(int argc, const char **argv,
} else { } else {
if (use_cycle) { if (use_cycle) {
printf("%lf\n", (double)result_cycle[pf] printf("%lf\n", (double)result_cycle[pf]
/ (double)len); / totallen);
} else } else
printf("%lf\n", result_bps[pf]); printf("%lf\n", result_bps[pf]);
} }
...@@ -310,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv, ...@@ -310,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv,
return 0; return 0;
} }
static void memcpy_alloc_mem(void **dst, void **src, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
*src = zalloc(length);
if (!*src)
die("memory allocation failed - maybe length is too large?\n");
/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
memset(*src, 0, length);
}
static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *src = NULL, *dst = NULL;
memcpy_t fn = r->fn.memcpy;
int i;
memcpy_alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
cycle_end = get_cycle();
free(src);
free(dst);
return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
memcpy_t fn = r->fn.memcpy;
void *src = NULL, *dst = NULL;
int i;
memcpy_alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(src);
free(dst);
return (double)(((double)len * iterations) / timeval2double(&tv_diff));
}
int bench_mem_memcpy(int argc, const char **argv,
const char *prefix __maybe_unused)
{
struct bench_mem_info info = {
.routines = memcpy_routines,
.do_cycle = do_memcpy_cycle,
.do_gettimeofday = do_memcpy_gettimeofday,
.usage = bench_mem_memcpy_usage,
};
return bench_mem_common(argc, argv, prefix, &info);
}
static void memset_alloc_mem(void **dst, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
}
static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
memset_t fn = r->fn.memset;
void *dst = NULL;
int i;
memset_alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
cycle_end = get_cycle();
free(dst);
return cycle_end - cycle_start;
}
static double do_memset_gettimeofday(const struct routine *r, size_t len,
bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
memset_t fn = r->fn.memset;
void *dst = NULL;
int i;
memset_alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(dst);
return (double)(((double)len * iterations) / timeval2double(&tv_diff));
}
static const char * const bench_mem_memset_usage[] = {
"perf bench mem memset <options>",
NULL
};
static const struct routine memset_routines[] = {
{ .name ="default",
.desc = "Default memset() provided by glibc",
.fn.memset = memset },
#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn },
#include "mem-memset-x86-64-asm-def.h"
#undef MEMSET_FN
#endif
{ .name = NULL,
.desc = NULL,
.fn.memset = NULL }
};
int bench_mem_memset(int argc, const char **argv,
const char *prefix __maybe_unused)
{
struct bench_mem_info info = {
.routines = memset_routines,
.do_cycle = do_memset_cycle,
.do_gettimeofday = do_memset_gettimeofday,
.usage = bench_mem_memset_usage,
};
return bench_mem_common(argc, argv, prefix, &info);
}
/*
* mem-memset.c
*
* memset: Simple memory set in various ways
*
* Trivial clone of mem-memcpy.c.
*/
#include "../perf.h"
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../util/header.h"
#include "../util/cloexec.h"
#include "bench.h"
#include "mem-memset-arch.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#include <errno.h>
#define K 1024
static const char *length_str = "1MB";
static const char *routine = "default";
static int iterations = 1;
static bool use_cycle;
static int cycle_fd;
static bool only_prefault;
static bool no_prefault;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
"Specify length of memory to set. "
"Available units: B, KB, MB, GB and TB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
"Specify routine to set"),
OPT_INTEGER('i', "iterations", &iterations,
"repeat memset() invocation this number of times"),
OPT_BOOLEAN('c', "cycle", &use_cycle,
"Use cycles event instead of gettimeofday() for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
"Show only the result with page faults before memset()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
"Show only the result without page faults before memset()"),
OPT_END()
};
typedef void *(*memset_t)(void *, int, size_t);
struct routine {
const char *name;
const char *desc;
memset_t fn;
};
static const struct routine routines[] = {
{ "default",
"Default memset() provided by glibc",
memset },
#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMSET_FN(fn, name, desc) { name, desc, fn },
#include "mem-memset-x86-64-asm-def.h"
#undef MEMSET_FN
#endif
{ NULL,
NULL,
NULL }
};
static const char * const bench_mem_memset_usage[] = {
"perf bench mem memset <options>",
NULL
};
static struct perf_event_attr cycle_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
static void init_cycle(void)
{
cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
perf_event_open_cloexec_flag());
if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
BUG_ON(cycle_fd < 0);
}
static u64 get_cycle(void)
{
int ret;
u64 clk;
ret = read(cycle_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
}
static double timeval2double(struct timeval *ts)
{
return (double)ts->tv_sec +
(double)ts->tv_usec / (double)1000000;
}
static void alloc_mem(void **dst, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
}
static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *dst = NULL;
int i;
alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
cycle_end = get_cycle();
free(dst);
return cycle_end - cycle_start;
}
static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
void *dst = NULL;
int i;
alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(dst);
return (double)((double)len / timeval2double(&tv_diff));
}
#define pf (no_prefault ? 0 : 1)
#define print_bps(x) do { \
if (x < K) \
printf(" %14lf B/Sec", x); \
else if (x < K * K) \
printf(" %14lfd KB/Sec", x / K); \
else if (x < K * K * K) \
printf(" %14lf MB/Sec", x / K / K); \
else \
printf(" %14lf GB/Sec", x / K / K / K); \
} while (0)
int bench_mem_memset(int argc, const char **argv,
const char *prefix __maybe_unused)
{
int i;
size_t len;
double result_bps[2];
u64 result_cycle[2];
argc = parse_options(argc, argv, options,
bench_mem_memset_usage, 0);
if (no_prefault && only_prefault) {
fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
return 1;
}
if (use_cycle)
init_cycle();
len = (size_t)perf_atoll((char *)length_str);
result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0;
if ((s64)len <= 0) {
fprintf(stderr, "Invalid length:%s\n", length_str);
return 1;
}
/* same to without specifying either of prefault and no-prefault */
if (only_prefault && no_prefault)
only_prefault = no_prefault = false;
for (i = 0; routines[i].name; i++) {
if (!strcmp(routines[i].name, routine))
break;
}
if (!routines[i].name) {
printf("Unknown routine:%s\n", routine);
printf("Available routines...\n");
for (i = 0; routines[i].name; i++) {
printf("\t%s ... %s\n",
routines[i].name, routines[i].desc);
}
return 1;
}
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Copying %s Bytes ...\n\n", length_str);
if (!only_prefault && !no_prefault) {
/* show both of results */
if (use_cycle) {
result_cycle[0] =
do_memset_cycle(routines[i].fn, len, false);
result_cycle[1] =
do_memset_cycle(routines[i].fn, len, true);
} else {
result_bps[0] =
do_memset_gettimeofday(routines[i].fn,
len, false);
result_bps[1] =
do_memset_gettimeofday(routines[i].fn,
len, true);
}
} else {
if (use_cycle) {
result_cycle[pf] =
do_memset_cycle(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
do_memset_gettimeofday(routines[i].fn,
len, only_prefault);
}
}
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (!only_prefault && !no_prefault) {
if (use_cycle) {
printf(" %14lf Cycle/Byte\n",
(double)result_cycle[0]
/ (double)len);
printf(" %14lf Cycle/Byte (with prefault)\n ",
(double)result_cycle[1]
/ (double)len);
} else {
print_bps(result_bps[0]);
printf("\n");
print_bps(result_bps[1]);
printf(" (with prefault)\n");
}
} else {
if (use_cycle) {
printf(" %14lf Cycle/Byte",
(double)result_cycle[pf]
/ (double)len);
} else
print_bps(result_bps[pf]);
printf("%s\n", only_prefault ? " (with prefault)" : "");
}
break;
case BENCH_FORMAT_SIMPLE:
if (!only_prefault && !no_prefault) {
if (use_cycle) {
printf("%lf %lf\n",
(double)result_cycle[0] / (double)len,
(double)result_cycle[1] / (double)len);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
if (use_cycle) {
printf("%lf\n", (double)result_cycle[pf]
/ (double)len);
} else
printf("%lf\n", result_bps[pf]);
}
break;
default:
/* reaching this means there's some disaster: */
die("unknown format: %d\n", bench_format);
break;
}
return 0;
}
...@@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv, ...@@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv,
struct str_node *pos; struct str_node *pos;
int ret = 0; int ret = 0;
bool force = false; bool force = false;
char debugdir[PATH_MAX];
char const *add_name_list_str = NULL, char const *add_name_list_str = NULL,
*remove_name_list_str = NULL, *remove_name_list_str = NULL,
*missing_filename = NULL, *missing_filename = NULL,
*update_name_list_str = NULL, *update_name_list_str = NULL,
*kcore_filename; *kcore_filename = NULL;
char sbuf[STRERR_BUFSIZE]; char sbuf[STRERR_BUFSIZE];
struct perf_data_file file = { struct perf_data_file file = {
...@@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv, ...@@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv,
setup_pager(); setup_pager();
snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
if (add_name_list_str) { if (add_name_list_str) {
list = strlist__new(true, add_name_list_str); list = strlist__new(true, add_name_list_str);
if (list) { if (list) {
strlist__for_each(pos, list) strlist__for_each(pos, list)
if (build_id_cache__add_file(pos->s, debugdir)) { if (build_id_cache__add_file(pos->s, buildid_dir)) {
if (errno == EEXIST) { if (errno == EEXIST) {
pr_debug("%s already in the cache\n", pr_debug("%s already in the cache\n",
pos->s); pos->s);
...@@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv, ...@@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv,
list = strlist__new(true, remove_name_list_str); list = strlist__new(true, remove_name_list_str);
if (list) { if (list) {
strlist__for_each(pos, list) strlist__for_each(pos, list)
if (build_id_cache__remove_file(pos->s, debugdir)) { if (build_id_cache__remove_file(pos->s, buildid_dir)) {
if (errno == ENOENT) { if (errno == ENOENT) {
pr_debug("%s wasn't in the cache\n", pr_debug("%s wasn't in the cache\n",
pos->s); pos->s);
...@@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv, ...@@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv,
list = strlist__new(true, update_name_list_str); list = strlist__new(true, update_name_list_str);
if (list) { if (list) {
strlist__for_each(pos, list) strlist__for_each(pos, list)
if (build_id_cache__update_file(pos->s, debugdir)) { if (build_id_cache__update_file(pos->s, buildid_dir)) {
if (errno == ENOENT) { if (errno == ENOENT) {
pr_debug("%s wasn't in the cache\n", pr_debug("%s wasn't in the cache\n",
pos->s); pos->s);
...@@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv, ...@@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv,
} }
if (kcore_filename && if (kcore_filename &&
build_id_cache__add_kcore(kcore_filename, debugdir, force)) build_id_cache__add_kcore(kcore_filename, buildid_dir, force))
pr_warning("Couldn't add %s\n", kcore_filename); pr_warning("Couldn't add %s\n", kcore_filename);
out: out:
......
...@@ -1293,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, ...@@ -1293,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
OPT_UINTEGER('d', "display", &kvm->display_time, OPT_UINTEGER('d', "display", &kvm->display_time,
"time in seconds between display updates"), "time in seconds between display updates"),
OPT_STRING(0, "event", &kvm->report_event, "report event", OPT_STRING(0, "event", &kvm->report_event, "report event",
"event for reporting: vmexit, mmio, ioport"), "event for reporting: "
"vmexit, mmio (x86 only), ioport (x86 only)"),
OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
"vcpu id to report"), "vcpu id to report"),
OPT_STRING('k', "key", &kvm->sort_key, "sort-key", OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
......
...@@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) ...@@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
unsigned long before; unsigned long before;
const bool forks = argc > 0; const bool forks = argc > 0;
bool draining = false; bool draining = false;
char sbuf[STRERR_BUFSIZE];
trace->live = true; trace->live = true;
...@@ -2106,11 +2105,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv) ...@@ -2106,11 +2105,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
goto out_error_open; goto out_error_open;
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false); err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
if (err < 0) { if (err < 0)
fprintf(trace->output, "Couldn't mmap the events: %s\n", goto out_error_mmap;
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
perf_evlist__enable(evlist); perf_evlist__enable(evlist);
...@@ -2210,6 +2206,10 @@ static int trace__run(struct trace *trace, int argc, const char **argv) ...@@ -2210,6 +2206,10 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
goto out_error; goto out_error;
out_error_mmap:
perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf));
goto out_error;
out_error_open: out_error_open:
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
...@@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) ...@@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
.user_freq = UINT_MAX, .user_freq = UINT_MAX,
.user_interval = ULLONG_MAX, .user_interval = ULLONG_MAX,
.no_buffering = true, .no_buffering = true,
.mmap_pages = 1024, .mmap_pages = UINT_MAX,
}, },
.output = stdout, .output = stdout,
.show_comm = true, .show_comm = true,
......
...@@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) ...@@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
*envchanged = 1; *envchanged = 1;
(*argv)++; (*argv)++;
(*argc)--; (*argc)--;
} else if (!strcmp(cmd, "--buildid-dir")) {
if (*argc < 2) {
fprintf(stderr, "No directory given for --buildid-dir.\n");
usage(perf_usage_string);
}
set_buildid_dir((*argv)[1]);
if (envchanged)
*envchanged = 1;
(*argv)++;
(*argc)--;
} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR)); perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
fprintf(stderr, "dir: %s\n", debugfs_mountpoint); fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
...@@ -499,7 +509,7 @@ int main(int argc, const char **argv) ...@@ -499,7 +509,7 @@ int main(int argc, const char **argv)
} }
if (!prefixcmp(cmd, "trace")) { if (!prefixcmp(cmd, "trace")) {
#ifdef HAVE_LIBAUDIT_SUPPORT #ifdef HAVE_LIBAUDIT_SUPPORT
set_buildid_dir(); set_buildid_dir(NULL);
setup_path(); setup_path();
argv[0] = "trace"; argv[0] = "trace";
return cmd_trace(argc, argv, NULL); return cmd_trace(argc, argv, NULL);
...@@ -514,7 +524,7 @@ int main(int argc, const char **argv) ...@@ -514,7 +524,7 @@ int main(int argc, const char **argv)
argc--; argc--;
handle_options(&argv, &argc, NULL); handle_options(&argv, &argc, NULL);
commit_pager_choice(); commit_pager_choice();
set_buildid_dir(); set_buildid_dir(NULL);
if (argc > 0) { if (argc > 0) {
if (!prefixcmp(argv[0], "--")) if (!prefixcmp(argv[0], "--"))
......
...@@ -5,7 +5,7 @@ group_fd=-1 ...@@ -5,7 +5,7 @@ group_fd=-1
flags=0|8 flags=0|8
cpu=* cpu=*
type=0|1 type=0|1
size=96 size=104
config=0 config=0
sample_period=4000 sample_period=4000
sample_type=263 sample_type=263
......
...@@ -5,7 +5,7 @@ group_fd=-1 ...@@ -5,7 +5,7 @@ group_fd=-1
flags=0|8 flags=0|8
cpu=* cpu=*
type=0 type=0
size=96 size=104
config=0 config=0
sample_period=0 sample_period=0
sample_type=0 sample_type=0
......
...@@ -1252,7 +1252,7 @@ static int hists__browser_title(struct hists *hists, ...@@ -1252,7 +1252,7 @@ static int hists__browser_title(struct hists *hists,
nr_samples = convert_unit(nr_samples, &unit); nr_samples = convert_unit(nr_samples, &unit);
printed = scnprintf(bf, size, printed = scnprintf(bf, size,
"Samples: %lu%c of event '%s', Event count (approx.): %lu", "Samples: %lu%c of event '%s', Event count (approx.): %" PRIu64,
nr_samples, unit, ev_name, nr_events); nr_samples, unit, ev_name, nr_events);
......
...@@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, ...@@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
return ret; return ret;
nr_members = evsel->nr_members; nr_members = evsel->nr_members;
fields_a = calloc(sizeof(*fields_a), nr_members); fields_a = calloc(nr_members, sizeof(*fields_a));
fields_b = calloc(sizeof(*fields_b), nr_members); fields_b = calloc(nr_members, sizeof(*fields_b));
if (!fields_a || !fields_b) if (!fields_a || !fields_b)
goto out; goto out;
......
...@@ -410,21 +410,18 @@ int perf_session__cache_build_ids(struct perf_session *session) ...@@ -410,21 +410,18 @@ int perf_session__cache_build_ids(struct perf_session *session)
{ {
struct rb_node *nd; struct rb_node *nd;
int ret; int ret;
char debugdir[PATH_MAX];
if (no_buildid_cache) if (no_buildid_cache)
return 0; return 0;
snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
return -1; return -1;
ret = machine__cache_build_ids(&session->machines.host, debugdir); ret = machine__cache_build_ids(&session->machines.host, buildid_dir);
for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node); struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__cache_build_ids(pos, debugdir); ret |= machine__cache_build_ids(pos, buildid_dir);
} }
return ret ? -1 : 0; return ret ? -1 : 0;
} }
......
...@@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg) ...@@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg)
ret = 0; ret = 0;
} else } else
pr_err("callchain: No more arguments " pr_err("callchain: No more arguments "
"needed for -g fp\n"); "needed for --call-graph fp\n");
break; break;
#ifdef HAVE_DWARF_UNWIND_SUPPORT #ifdef HAVE_DWARF_UNWIND_SUPPORT
......
...@@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value, ...@@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value,
const char *v; const char *v;
/* same dir for all commands */ /* same dir for all commands */
if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) { if (!strcmp(var, "buildid.dir")) {
v = perf_config_dirname(var, value); v = perf_config_dirname(var, value);
if (!v) if (!v)
return -1; return -1;
...@@ -539,11 +539,13 @@ static void check_buildid_dir_config(void) ...@@ -539,11 +539,13 @@ static void check_buildid_dir_config(void)
perf_config(buildid_dir_command_config, &c); perf_config(buildid_dir_command_config, &c);
} }
void set_buildid_dir(void) void set_buildid_dir(const char *dir)
{ {
buildid_dir[0] = '\0'; if (dir)
scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
/* try config file */ /* try config file */
if (buildid_dir[0] == '\0')
check_buildid_dir_config(); check_buildid_dir_config();
/* default to $HOME/.debug */ /* default to $HOME/.debug */
......
...@@ -8,6 +8,7 @@ ...@@ -8,6 +8,7 @@
*/ */
#include "util.h" #include "util.h"
#include <api/fs/debugfs.h> #include <api/fs/debugfs.h>
#include <api/fs/fs.h>
#include <poll.h> #include <poll.h>
#include "cpumap.h" #include "cpumap.h"
#include "thread_map.h" #include "thread_map.h"
...@@ -24,6 +25,7 @@ ...@@ -24,6 +25,7 @@
#include <linux/bitops.h> #include <linux/bitops.h>
#include <linux/hash.h> #include <linux/hash.h>
#include <linux/log2.h>
static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx); static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx); static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
...@@ -892,10 +894,24 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, ...@@ -892,10 +894,24 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
static size_t perf_evlist__mmap_size(unsigned long pages) static size_t perf_evlist__mmap_size(unsigned long pages)
{ {
/* 512 kiB: default amount of unprivileged mlocked memory */ if (pages == UINT_MAX) {
if (pages == UINT_MAX) int max;
pages = (512 * 1024) / page_size;
else if (!is_power_of_2(pages)) if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
/*
* Pick a once upon a time good value, i.e. things look
* strange since we can't read a sysctl value, but lets not
* die yet...
*/
max = 512;
} else {
max -= (page_size / 1024);
}
pages = (max * 1024) / page_size;
if (!is_power_of_2(pages))
pages = rounddown_pow_of_two(pages);
} else if (!is_power_of_2(pages))
return 0; return 0;
return (pages + 1) * page_size; return (pages + 1) * page_size;
...@@ -932,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min, ...@@ -932,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
/* leave number of pages at 0 */ /* leave number of pages at 0 */
} else if (!is_power_of_2(pages)) { } else if (!is_power_of_2(pages)) {
/* round pages up to next power of 2 */ /* round pages up to next power of 2 */
pages = next_pow2_l(pages); pages = roundup_pow_of_two(pages);
if (!pages) if (!pages)
return -EINVAL; return -EINVAL;
pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
...@@ -1483,6 +1499,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, ...@@ -1483,6 +1499,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
return 0; return 0;
} }
int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
{
char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
switch (err) {
case EPERM:
sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
printed += scnprintf(buf + printed, size - printed,
"Error:\t%s.\n"
"Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
"Hint:\tTried using %zd kB.\n",
emsg, pages_max_per_user, pages_attempted);
if (pages_attempted >= pages_max_per_user) {
printed += scnprintf(buf + printed, size - printed,
"Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n",
pages_max_per_user + pages_attempted);
}
printed += scnprintf(buf + printed, size - printed,
"Hint:\tTry using a smaller -m/--mmap-pages value.");
break;
default:
scnprintf(buf, size, "%s", emsg);
break;
}
return 0;
}
void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__to_front(struct perf_evlist *evlist,
struct perf_evsel *move_evsel) struct perf_evsel *move_evsel)
{ {
......
...@@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); ...@@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{ {
......
...@@ -1385,19 +1385,46 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, ...@@ -1385,19 +1385,46 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
static int add_callchain_ip(struct thread *thread, static int add_callchain_ip(struct thread *thread,
struct symbol **parent, struct symbol **parent,
struct addr_location *root_al, struct addr_location *root_al,
int cpumode, bool branch_history,
u64 ip) u64 ip)
{ {
struct addr_location al; struct addr_location al;
al.filtered = 0; al.filtered = 0;
al.sym = NULL; al.sym = NULL;
if (cpumode == -1) if (branch_history)
thread__find_cpumode_addr_location(thread, MAP__FUNCTION, thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
ip, &al); ip, &al);
else else {
u8 cpumode = PERF_RECORD_MISC_USER;
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
cpumode = PERF_RECORD_MISC_HYPERVISOR;
break;
case PERF_CONTEXT_KERNEL:
cpumode = PERF_RECORD_MISC_KERNEL;
break;
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER;
break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
/*
* It seems the callchain is corrupted.
* Discard all.
*/
callchain_cursor_reset(&callchain_cursor);
return 1;
}
return 0;
}
thread__find_addr_location(thread, cpumode, MAP__FUNCTION, thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
ip, &al); ip, &al);
}
if (al.sym != NULL) { if (al.sym != NULL) {
if (sort__has_parent && !*parent && if (sort__has_parent && !*parent &&
symbol__match_regex(al.sym, &parent_regex)) symbol__match_regex(al.sym, &parent_regex))
...@@ -1480,11 +1507,8 @@ static int thread__resolve_callchain_sample(struct thread *thread, ...@@ -1480,11 +1507,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
struct addr_location *root_al, struct addr_location *root_al,
int max_stack) int max_stack)
{ {
u8 cpumode = PERF_RECORD_MISC_USER;
int chain_nr = min(max_stack, (int)chain->nr); int chain_nr = min(max_stack, (int)chain->nr);
int i; int i, j, err;
int j;
int err;
int skip_idx = -1; int skip_idx = -1;
int first_call = 0; int first_call = 0;
...@@ -1542,10 +1566,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, ...@@ -1542,10 +1566,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
for (i = 0; i < nr; i++) { for (i = 0; i < nr; i++) {
err = add_callchain_ip(thread, parent, root_al, err = add_callchain_ip(thread, parent, root_al,
-1, be[i].to); true, be[i].to);
if (!err) if (!err)
err = add_callchain_ip(thread, parent, root_al, err = add_callchain_ip(thread, parent, root_al,
-1, be[i].from); true, be[i].from);
if (err == -EINVAL) if (err == -EINVAL)
break; break;
if (err) if (err)
...@@ -1574,36 +1598,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, ...@@ -1574,36 +1598,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
#endif #endif
ip = chain->ips[j]; ip = chain->ips[j];
if (ip >= PERF_CONTEXT_MAX) { err = add_callchain_ip(thread, parent, root_al, false, ip);
switch (ip) {
case PERF_CONTEXT_HV:
cpumode = PERF_RECORD_MISC_HYPERVISOR;
break;
case PERF_CONTEXT_KERNEL:
cpumode = PERF_RECORD_MISC_KERNEL;
break;
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER;
break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
/*
* It seems the callchain is corrupted.
* Discard all.
*/
callchain_cursor_reset(&callchain_cursor);
return 0;
}
continue;
}
err = add_callchain_ip(thread, parent, root_al,
cpumode, ip);
if (err == -EINVAL)
break;
if (err) if (err)
return err; return (err < 0) ? err : 0;
} }
return 0; return 0;
......
...@@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) ...@@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
static int get_max_rate(unsigned int *rate) static int get_max_rate(unsigned int *rate)
{ {
char path[PATH_MAX]; return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate);
const char *procfs = procfs__mountpoint();
if (!procfs)
return -1;
snprintf(path, PATH_MAX,
"%s/sys/kernel/perf_event_max_sample_rate", procfs);
return filename__read_int(path, (int *) rate);
} }
static int record_opts__config_freq(struct record_opts *opts) static int record_opts__config_freq(struct record_opts *opts)
......
...@@ -20,7 +20,7 @@ ...@@ -20,7 +20,7 @@
struct a2l_data { struct a2l_data {
const char *input; const char *input;
unsigned long addr; u64 addr;
bool found; bool found;
const char *filename; const char *filename;
...@@ -147,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l) ...@@ -147,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l)
free(a2l); free(a2l);
} }
static int addr2line(const char *dso_name, unsigned long addr, static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line, struct dso *dso) char **file, unsigned int *line, struct dso *dso)
{ {
int ret = 0; int ret = 0;
...@@ -193,7 +193,7 @@ void dso__free_a2l(struct dso *dso) ...@@ -193,7 +193,7 @@ void dso__free_a2l(struct dso *dso)
#else /* HAVE_LIBBFD_SUPPORT */ #else /* HAVE_LIBBFD_SUPPORT */
static int addr2line(const char *dso_name, unsigned long addr, static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line_nr, char **file, unsigned int *line_nr,
struct dso *dso __maybe_unused) struct dso *dso __maybe_unused)
{ {
...@@ -252,7 +252,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused) ...@@ -252,7 +252,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
*/ */
#define A2L_FAIL_LIMIT 123 #define A2L_FAIL_LIMIT 123
char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym, char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
bool show_sym) bool show_sym)
{ {
char *file = NULL; char *file = NULL;
...@@ -293,10 +293,10 @@ char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym, ...@@ -293,10 +293,10 @@ char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
dso__free_a2l(dso); dso__free_a2l(dso);
} }
if (sym) { if (sym) {
if (asprintf(&srcline, "%s+%ld", show_sym ? sym->name : "", if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
addr - sym->start) < 0) addr - sym->start) < 0)
return SRCLINE_UNKNOWN; return SRCLINE_UNKNOWN;
} else if (asprintf(&srcline, "%s[%lx]", dso->short_name, addr) < 0) } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
return SRCLINE_UNKNOWN; return SRCLINE_UNKNOWN;
return srcline; return srcline;
} }
......
...@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) ...@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
void *tmp; void *tmp;
long offset;
if (need_swap) { if (need_swap) {
phdr->p_type = bswap_32(phdr->p_type); phdr->p_type = bswap_32(phdr->p_type);
...@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) ...@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
continue; continue;
buf_size = phdr->p_filesz; buf_size = phdr->p_filesz;
offset = phdr->p_offset;
tmp = realloc(buf, buf_size); tmp = realloc(buf, buf_size);
if (tmp == NULL) if (tmp == NULL)
goto out_free; goto out_free;
buf = tmp; buf = tmp;
fseek(fp, phdr->p_offset, SEEK_SET); fseek(fp, offset, SEEK_SET);
if (fread(buf, buf_size, 1, fp) != 1) if (fread(buf, buf_size, 1, fp) != 1)
goto out_free; goto out_free;
...@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) ...@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
void *tmp; void *tmp;
long offset;
if (need_swap) { if (need_swap) {
phdr->p_type = bswap_32(phdr->p_type); phdr->p_type = bswap_32(phdr->p_type);
...@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) ...@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
continue; continue;
buf_size = phdr->p_filesz; buf_size = phdr->p_filesz;
offset = phdr->p_offset;
tmp = realloc(buf, buf_size); tmp = realloc(buf, buf_size);
if (tmp == NULL) if (tmp == NULL)
goto out_free; goto out_free;
buf = tmp; buf = tmp;
fseek(fp, phdr->p_offset, SEEK_SET); fseek(fp, offset, SEEK_SET);
if (fread(buf, buf_size, 1, fp) != 1) if (fread(buf, buf_size, 1, fp) != 1)
goto out_free; goto out_free;
......
...@@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) ...@@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
return (unsigned long) -1; return (unsigned long) -1;
} }
int filename__read_int(const char *filename, int *value)
{
char line[64];
int fd = open(filename, O_RDONLY), err = -1;
if (fd < 0)
return -1;
if (read(fd, line, sizeof(line)) > 0) {
*value = atoi(line);
err = 0;
}
close(fd);
return err;
}
int filename__read_str(const char *filename, char **buf, size_t *sizep) int filename__read_str(const char *filename, char **buf, size_t *sizep)
{ {
size_t size = 0, alloc_size = 0; size_t size = 0, alloc_size = 0;
...@@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void) ...@@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void)
int perf_event_paranoid(void) int perf_event_paranoid(void)
{ {
char path[PATH_MAX];
const char *procfs = procfs__mountpoint();
int value; int value;
if (!procfs) if (sysctl__read_int("kernel/perf_event_paranoid", &value))
return INT_MAX;
scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
if (filename__read_int(path, &value))
return INT_MAX; return INT_MAX;
return value; return value;
......
...@@ -153,7 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))) ...@@ -153,7 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
extern int prefixcmp(const char *str, const char *prefix); extern int prefixcmp(const char *str, const char *prefix);
extern void set_buildid_dir(void); extern void set_buildid_dir(const char *dir);
static inline const char *skip_prefix(const char *str, const char *prefix) static inline const char *skip_prefix(const char *str, const char *prefix)
{ {
...@@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr); ...@@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr);
#define _STR(x) #x #define _STR(x) #x
#define STR(x) _STR(x) #define STR(x) _STR(x)
/*
* Determine whether some value is a power of two, where zero is
* *not* considered a power of two.
*/
static inline __attribute__((const))
bool is_power_of_2(unsigned long n)
{
return (n != 0 && ((n & (n - 1)) == 0));
}
static inline unsigned next_pow2(unsigned x)
{
if (!x)
return 1;
return 1ULL << (32 - __builtin_clz(x - 1));
}
static inline unsigned long next_pow2_l(unsigned long x)
{
#if BITS_PER_LONG == 64
if (x <= (1UL << 31))
return next_pow2(x);
return (unsigned long)next_pow2(x >> 32) << 32;
#else
return next_pow2(x);
#endif
}
size_t hex_width(u64 v); size_t hex_width(u64 v);
int hex2u64(const char *ptr, u64 *val); int hex2u64(const char *ptr, u64 *val);
...@@ -339,11 +310,10 @@ static inline int path__join3(char *bf, size_t size, ...@@ -339,11 +310,10 @@ static inline int path__join3(char *bf, size_t size,
struct dso; struct dso;
struct symbol; struct symbol;
char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym, char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
bool show_sym); bool show_sym);
void free_srcline(char *srcline); void free_srcline(char *srcline);
int filename__read_int(const char *filename, int *value);
int filename__read_str(const char *filename, char **buf, size_t *sizep); int filename__read_str(const char *filename, char **buf, size_t *sizep);
int perf_event_paranoid(void); int perf_event_paranoid(void);
......
...@@ -446,7 +446,7 @@ int probe_thermal_sysfs(void) ...@@ -446,7 +446,7 @@ int probe_thermal_sysfs(void)
return -1; return -1;
} }
ptdata.tzi = calloc(sizeof(struct tz_info), ptdata.max_tz_instance+1); ptdata.tzi = calloc(ptdata.max_tz_instance+1, sizeof(struct tz_info));
if (!ptdata.tzi) { if (!ptdata.tzi) {
fprintf(stderr, "Err: allocate tz_info\n"); fprintf(stderr, "Err: allocate tz_info\n");
return -1; return -1;
...@@ -454,8 +454,8 @@ int probe_thermal_sysfs(void) ...@@ -454,8 +454,8 @@ int probe_thermal_sysfs(void)
/* we still show thermal zone information if there is no cdev */ /* we still show thermal zone information if there is no cdev */
if (ptdata.nr_cooling_dev) { if (ptdata.nr_cooling_dev) {
ptdata.cdi = calloc(sizeof(struct cdev_info), ptdata.cdi = calloc(ptdata.max_cdev_instance + 1,
ptdata.max_cdev_instance + 1); sizeof(struct cdev_info));
if (!ptdata.cdi) { if (!ptdata.cdi) {
free(ptdata.tzi); free(ptdata.tzi);
fprintf(stderr, "Err: allocate cdev_info\n"); fprintf(stderr, "Err: allocate cdev_info\n");
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment