mirror of
https://github.com/torvalds/linux.git
synced 2025-11-01 09:09:47 +02:00
Pull perf updates from Ingo Molnar:
"Kernel side changes:
- Intel Knights Landing support. (Harish Chegondi)
- Intel Broadwell-EP uncore PMU support. (Kan Liang)
- Core code improvements. (Peter Zijlstra.)
- Event filter, LBR and PEBS fixes. (Stephane Eranian)
- Enable cycles:pp on Intel Atom. (Stephane Eranian)
- Add cycles:ppp support for Skylake. (Andi Kleen)
- Various x86 NMI overhead optimizations. (Andi Kleen)
- Intel PT enhancements. (Takao Indoh)
- AMD cache events fix. (Vince Weaver)
Tons of tooling changes:
- Show random perf tool tips in the 'perf report' bottom line
(Namhyung Kim)
- perf report now defaults to --group if the perf.data file has
grouped events, try it with:
# perf record -e '{cycles,instructions}' -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
# perf report
# Samples: 1K of event 'anon group { cycles, instructions }'
# Event count (approx.): 1955219195
#
# Overhead Command Shared Object Symbol
2.86% 0.22% swapper [kernel.kallsyms] [k] intel_idle
1.05% 0.33% firefox libxul.so [.] js::SetObjectElement
1.05% 0.00% kworker/0:3 [kernel.kallsyms] [k] gen6_ring_get_seqno
0.88% 0.17% chrome chrome [.] 0x0000000000ee27ab
0.65% 0.86% firefox libxul.so [.] js::ValueToId<(js::AllowGC)1>
0.64% 0.23% JS Helper libxul.so [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
0.62% 1.27% firefox libxul.so [.] js::GetIterator
0.61% 1.74% firefox libxul.so [.] js::NativeSetProperty
0.61% 0.31% firefox libxul.so [.] js::SetPropertyByDefining
- Introduce the 'perf stat record/report' workflow:
Generate perf.data files from 'perf stat', to tap into the
scripting capabilities perf has instead of defining a 'perf stat'
specific scripting support to calculate event ratios, etc.
Simple example:
$ perf stat record -e cycles usleep 1
Performance counter stats for 'usleep 1':
1,134,996 cycles
0.000670644 seconds time elapsed
$ perf stat report
Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':
1,134,996 cycles
0.000670644 seconds time elapsed
$
It generates PERF_RECORD_ userspace records to store the details:
$ perf report -D | grep PERF_RECORD
0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
0x12a [0x40]: PERF_RECORD_STAT_CONFIG
0x16a [0x30]: PERF_RECORD_STAT
-1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
0x1da [0x18]: PERF_RECORD_STAT_ROUND
[acme@ssdandy linux]$
An effort was made to make perf.data files generated like this to
not generate cryptic messages when processed by older tools.
The 'perf script' bits need rebasing, will go up later.
- Make command line options always available, even when they depend
on some feature being enabled, warning the user about use of such
options (Wang Nan)
- Support hw breakpoint events (mem:0xAddress) in the default output
mode in 'perf script' (Wang Nan)
- Fixes and improvements for supporting annotating ARM binaries,
support ARM call and jump instructions, more work needed to have
arch specific stuff separated into tools/perf/arch/*/annotate/
(Russell King)
- Add initial 'perf config' command, for now just with a --list
command to the contents of the configuration file in use and a
basic man page describing its format, commands for doing edits and
detailed documentation are being reviewed and proof-read. (Taeung
Song)
- Allows BPF scriptlets specify arguments to be fetched using DWARF
info, using a prologue generated at compile/build time (He Kuang,
Wang Nan)
- Allow attaching BPF scriptlets to module symbols (Wang Nan)
- Allow attaching BPF scriptlets to userspace code using uprobe (Wang
Nan)
- BPF programs now can specify 'perf probe' tunables via its section
name, separating key=val values using semicolons (Wang Nan)
Testing some of these new BPF features:
Use case: get callchains when receiving SSL packets, filter then in the
kernel, at arbitrary place.
# cat ssl.bpf.c
#define SEC(NAME) __attribute__((section(NAME), used))
struct pt_regs;
SEC("func=__inet_lookup_established hnum")
int func(struct pt_regs *ctx, int err, unsigned short port)
{
return err == 0 && port == 443;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
#
# perf record -a -g -e ssl.bpf.c
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
# perf script | head -30
swapper 0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
1163ffa start_kernel ([kernel.vmlinux].init.text)
11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)
qemu-system-x86 9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
430a br_handle_frame_finish ([bridge])
48bc br_handle_frame ([bridge])
855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
#
- Use 'perf probe' various options to list functions, see what
variables can be collected at any given point, experiment first
collecting without a filter, then filter, use it together with
'perf trace', 'perf top', with or without callchains, if it
explodes, please tell us!
- Introduce a new callchain mode: "folded", that will list per line
representations of all callchains for a give histogram entry,
facilitating 'perf report' output processing by other tools, such
as Brendan Gregg's flamegraph tools (Namhyung Kim)
E.g:
# perf report | grep -v ^# | head
18.37% 0.00% swapper [kernel.kallsyms] [k] cpu_startup_entry
|
---cpu_startup_entry
|
|--12.07%--start_secondary
|
--6.30%--rest_init
start_kernel
x86_64_start_reservations
x86_64_start_kernel
#
Becomes, in "folded" mode:
# perf report -g folded | grep -v ^# | head -5
18.37% 0.00% swapper [kernel.kallsyms] [k] cpu_startup_entry
12.07% cpu_startup_entry;start_secondary
6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
16.90% 0.00% swapper [kernel.kallsyms] [k] call_cpuidle
11.23% call_cpuidle;cpu_startup_entry;start_secondary
5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
16.90% 0.00% swapper [kernel.kallsyms] [k] cpuidle_enter
11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
15.12% 0.00% swapper [kernel.kallsyms] [k] cpuidle_enter_state
#
The user can also select one of "count", "period" or "percent" as
the first column.
... and lots of infrastructure enhancements, plus fixes and other
changes, features I failed to list - see the shortlog and the git log
for details"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
perf evlist: Add --trace-fields option to show trace fields
perf record: Store data mmaps for dwarf unwind
perf libdw: Check for mmaps also in MAP__VARIABLE tree
perf unwind: Check for mmaps also in MAP__VARIABLE tree
perf unwind: Use find_map function in access_dso_mem
perf evlist: Remove perf_evlist__(enable|disable)_event functions
perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
perf report: Show random usage tip on the help line
perf hists: Export a couple of hist functions
perf diff: Use perf_hpp__register_sort_field interface
perf tools: Add overhead/overhead_children keys defaults via string
perf tools: Remove list entry from struct sort_entry
perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
perf script: Align event name properly
perf tools: Add missing headers in perf's MANIFEST
perf tools: Do not show trace command if it's not compiled in
perf report: Change default to use event group view
perf top: Decay periods in callchains
tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
tools lib: Sync tools/lib/find_bit.c with the kernel
...
237 lines
5.4 KiB
C
237 lines
5.4 KiB
C
/*
|
|
* Testsuite for atomic64_t functions
|
|
*
|
|
* Copyright © 2010 Luca Barbieri
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/atomic.h>
|
|
|
|
#ifdef CONFIG_X86
|
|
#include <asm/processor.h> /* for boot_cpu_has below */
|
|
#endif
|
|
|
|
#define TEST(bit, op, c_op, val) \
|
|
do { \
|
|
atomic##bit##_set(&v, v0); \
|
|
r = v0; \
|
|
atomic##bit##_##op(val, &v); \
|
|
r c_op val; \
|
|
WARN(atomic##bit##_read(&v) != r, "%Lx != %Lx\n", \
|
|
(unsigned long long)atomic##bit##_read(&v), \
|
|
(unsigned long long)r); \
|
|
} while (0)
|
|
|
|
/*
|
|
* Test for a atomic operation family,
|
|
* @test should be a macro accepting parameters (bit, op, ...)
|
|
*/
|
|
|
|
#define FAMILY_TEST(test, bit, op, args...) \
|
|
do { \
|
|
test(bit, op, ##args); \
|
|
test(bit, op##_acquire, ##args); \
|
|
test(bit, op##_release, ##args); \
|
|
test(bit, op##_relaxed, ##args); \
|
|
} while (0)
|
|
|
|
#define TEST_RETURN(bit, op, c_op, val) \
|
|
do { \
|
|
atomic##bit##_set(&v, v0); \
|
|
r = v0; \
|
|
r c_op val; \
|
|
BUG_ON(atomic##bit##_##op(val, &v) != r); \
|
|
BUG_ON(atomic##bit##_read(&v) != r); \
|
|
} while (0)
|
|
|
|
#define RETURN_FAMILY_TEST(bit, op, c_op, val) \
|
|
do { \
|
|
FAMILY_TEST(TEST_RETURN, bit, op, c_op, val); \
|
|
} while (0)
|
|
|
|
#define TEST_ARGS(bit, op, init, ret, expect, args...) \
|
|
do { \
|
|
atomic##bit##_set(&v, init); \
|
|
BUG_ON(atomic##bit##_##op(&v, ##args) != ret); \
|
|
BUG_ON(atomic##bit##_read(&v) != expect); \
|
|
} while (0)
|
|
|
|
#define XCHG_FAMILY_TEST(bit, init, new) \
|
|
do { \
|
|
FAMILY_TEST(TEST_ARGS, bit, xchg, init, init, new, new); \
|
|
} while (0)
|
|
|
|
#define CMPXCHG_FAMILY_TEST(bit, init, new, wrong) \
|
|
do { \
|
|
FAMILY_TEST(TEST_ARGS, bit, cmpxchg, \
|
|
init, init, new, init, new); \
|
|
FAMILY_TEST(TEST_ARGS, bit, cmpxchg, \
|
|
init, init, init, wrong, new); \
|
|
} while (0)
|
|
|
|
#define INC_RETURN_FAMILY_TEST(bit, i) \
|
|
do { \
|
|
FAMILY_TEST(TEST_ARGS, bit, inc_return, \
|
|
i, (i) + one, (i) + one); \
|
|
} while (0)
|
|
|
|
#define DEC_RETURN_FAMILY_TEST(bit, i) \
|
|
do { \
|
|
FAMILY_TEST(TEST_ARGS, bit, dec_return, \
|
|
i, (i) - one, (i) - one); \
|
|
} while (0)
|
|
|
|
static __init void test_atomic(void)
|
|
{
|
|
int v0 = 0xaaa31337;
|
|
int v1 = 0xdeadbeef;
|
|
int onestwos = 0x11112222;
|
|
int one = 1;
|
|
|
|
atomic_t v;
|
|
int r;
|
|
|
|
TEST(, add, +=, onestwos);
|
|
TEST(, add, +=, -one);
|
|
TEST(, sub, -=, onestwos);
|
|
TEST(, sub, -=, -one);
|
|
TEST(, or, |=, v1);
|
|
TEST(, and, &=, v1);
|
|
TEST(, xor, ^=, v1);
|
|
TEST(, andnot, &= ~, v1);
|
|
|
|
RETURN_FAMILY_TEST(, add_return, +=, onestwos);
|
|
RETURN_FAMILY_TEST(, add_return, +=, -one);
|
|
RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
|
|
RETURN_FAMILY_TEST(, sub_return, -=, -one);
|
|
|
|
INC_RETURN_FAMILY_TEST(, v0);
|
|
DEC_RETURN_FAMILY_TEST(, v0);
|
|
|
|
XCHG_FAMILY_TEST(, v0, v1);
|
|
CMPXCHG_FAMILY_TEST(, v0, v1, onestwos);
|
|
|
|
}
|
|
|
|
#define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
|
|
static __init void test_atomic64(void)
|
|
{
|
|
long long v0 = 0xaaa31337c001d00dLL;
|
|
long long v1 = 0xdeadbeefdeafcafeLL;
|
|
long long v2 = 0xfaceabadf00df001LL;
|
|
long long onestwos = 0x1111111122222222LL;
|
|
long long one = 1LL;
|
|
|
|
atomic64_t v = ATOMIC64_INIT(v0);
|
|
long long r = v0;
|
|
BUG_ON(v.counter != r);
|
|
|
|
atomic64_set(&v, v1);
|
|
r = v1;
|
|
BUG_ON(v.counter != r);
|
|
BUG_ON(atomic64_read(&v) != r);
|
|
|
|
TEST(64, add, +=, onestwos);
|
|
TEST(64, add, +=, -one);
|
|
TEST(64, sub, -=, onestwos);
|
|
TEST(64, sub, -=, -one);
|
|
TEST(64, or, |=, v1);
|
|
TEST(64, and, &=, v1);
|
|
TEST(64, xor, ^=, v1);
|
|
TEST(64, andnot, &= ~, v1);
|
|
|
|
RETURN_FAMILY_TEST(64, add_return, +=, onestwos);
|
|
RETURN_FAMILY_TEST(64, add_return, +=, -one);
|
|
RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
|
|
RETURN_FAMILY_TEST(64, sub_return, -=, -one);
|
|
|
|
INIT(v0);
|
|
atomic64_inc(&v);
|
|
r += one;
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(v0);
|
|
atomic64_dec(&v);
|
|
r -= one;
|
|
BUG_ON(v.counter != r);
|
|
|
|
INC_RETURN_FAMILY_TEST(64, v0);
|
|
DEC_RETURN_FAMILY_TEST(64, v0);
|
|
|
|
XCHG_FAMILY_TEST(64, v0, v1);
|
|
CMPXCHG_FAMILY_TEST(64, v0, v1, v2);
|
|
|
|
INIT(v0);
|
|
BUG_ON(atomic64_add_unless(&v, one, v0));
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(v0);
|
|
BUG_ON(!atomic64_add_unless(&v, one, v1));
|
|
r += one;
|
|
BUG_ON(v.counter != r);
|
|
|
|
#ifdef CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
|
|
INIT(onestwos);
|
|
BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1));
|
|
r -= one;
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(0);
|
|
BUG_ON(atomic64_dec_if_positive(&v) != -one);
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(-one);
|
|
BUG_ON(atomic64_dec_if_positive(&v) != (-one - one));
|
|
BUG_ON(v.counter != r);
|
|
#else
|
|
#warning Please implement atomic64_dec_if_positive for your architecture and select the above Kconfig symbol
|
|
#endif
|
|
|
|
INIT(onestwos);
|
|
BUG_ON(!atomic64_inc_not_zero(&v));
|
|
r += one;
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(0);
|
|
BUG_ON(atomic64_inc_not_zero(&v));
|
|
BUG_ON(v.counter != r);
|
|
|
|
INIT(-one);
|
|
BUG_ON(!atomic64_inc_not_zero(&v));
|
|
r += one;
|
|
BUG_ON(v.counter != r);
|
|
}
|
|
|
|
static __init int test_atomics(void)
|
|
{
|
|
test_atomic();
|
|
test_atomic64();
|
|
|
|
#ifdef CONFIG_X86
|
|
pr_info("passed for %s platform %s CX8 and %s SSE\n",
|
|
#ifdef CONFIG_X86_64
|
|
"x86-64",
|
|
#elif defined(CONFIG_X86_CMPXCHG64)
|
|
"i586+",
|
|
#else
|
|
"i386+",
|
|
#endif
|
|
boot_cpu_has(X86_FEATURE_CX8) ? "with" : "without",
|
|
boot_cpu_has(X86_FEATURE_XMM) ? "with" : "without");
|
|
#else
|
|
pr_info("passed\n");
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
|
|
core_initcall(test_atomics);
|