Merge tag 'perf-core-for-mingo-5.5-20191011' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf trace:

  Arnaldo Carvalho de Melo:

  - Reuse the strace-like syscall_arg_fmt->scnprintf() beautification routines
    (convert integer arguments into strings, like open flags, etc) in tracepoint
    arguments.

    For now the type based scnprintf routines (pid_t, umode_t, etc) and the
    ones based in well known arg name based ("fd", etc) gets associated with
    tracepoint args of that type.

    A tracepoint only arg, "msr", for the msr:{write,read}_msr gets added as
    an initial step.

  - Introduce syscall_arg_fmt->strtoul() methods to be the reverse operation
    of ->scnprintf(), i.e. to go from a string to an integer.

  - Implement --filter, just like in 'perf record', that affects the tracepoint
    events specied thus far in the command line, use the ->strtoul() methods
    to allow strings in tables associated with beautifiers to the integers
    the in-kernel tracepoint (eBPF later) filters expect, e.g.:

     # perf trace --max-events 1 -e sched:*ipi --filter="cpu==1 || cpu==2"
      0.000 as/24630 sched:sched_wake_idle_without_ipi(cpu: 1)
     #

     # perf trace --max-events 1 --max-stack=32 -e msr:* --filter="msr==IA32_TSC_DEADLINE"
      207.000 cc1/19963 msr:write_msr(msr: IA32_TSC_DEADLINE, val: 5442316760822)
                                        do_trace_write_msr ([kernel.kallsyms])
                                        do_trace_write_msr ([kernel.kallsyms])
                                        lapic_next_deadline ([kernel.kallsyms])
                                        clockevents_program_event ([kernel.kallsyms])
                                        hrtimer_interrupt ([kernel.kallsyms])
                                        smp_apic_timer_interrupt ([kernel.kallsyms])
                                        apic_timer_interrupt ([kernel.kallsyms])
                                        [0x6ff66c] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x7047c3] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x707708] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_one_pass (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d37] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d49] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_pass_list (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        cgraph_node::expand (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x2625b4] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        symbol_table::finalize_compilation_unit (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x5ae8b9] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        toplev::main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x26b6a] (/usr/lib/x86_64-linux-gnu/libc-2.29.so)
     #
     # perf trace --max-events 8 -e msr:* --filter="msr==IA32_SPEC_CTRL"
         0.000 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.063 migration/3/25 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.217 kworker/u16:1-/4826 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.687 rcu_sched/11 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.696 :13280/13280 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.305 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.355 :13274/13274 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         2.743 kworker/u16:0-/6711 msr:write_msr(msr: IA32_SPEC_CTRL)
     #
     # perf trace --max-events 8 --cpu 1 -e msr:* --filter="msr!=IA32_SPEC_CTRL && msr!=IA32_TSC_DEADLINE && msr != FS_BASE"
           0.000 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 68719479037)
           0.096 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
         238.925 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 8589936893)
         511.010 :0/0 msr:write_msr(msr: 0x830, val: 68719479037)
        1005.052 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
        1235.131 CPU 0/KVM/3750 msr:write_msr(msr: 0x830, val: 4294969595)
        1235.195 CPU 0/KVM/3750 msr:read_msr(msr: IA32_SYSENTER_ESP, val: -2199023037952)
        1235.201 CPU 0/KVM/3750 msr:read_msr(msr: IA32_APICBASE, val: 4276096000)
     #

  - Default to not using libtraceevent and its plugins for beautifying
    tracepoint arguments, since now we're reusing the strace-like beatufiers.
    Use --libtraceevent_print (using just --libtrace is unambiguous and can
    be used as a short hand) to go back to those beautifiers.

    This will help in the transition, as can be seen in some of the sched tracepoints
    that still need some work in the libbeauty based mode:

    # trace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.006 (         ): sched:sched_wakeup(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.348 (         ): sched:sched_process_exec(filename: 140212596720100, pid: 3319 (sleep), old_pid: 3319 (sleep))
         0.490 (         ): msr:write_msr(msr: FS_BASE, val: 139631189321088)
         0.670 (         ): nanosleep(rqtp: 0x7ffc52c23bc0)                                    ...
         0.674 (         ): sched:sched_stat_runtime(comm: "sleep", pid: 3319 (sleep), runtime: 659259, vruntime: 78942418342)
         0.675 (         ): sched:sched_switch(prev_comm: "sleep", prev_pid: 3319 (sleep), prev_prio: 120, prev_state: 1, next_comm: "swapper/0", next_prio: 120)
      1001.059 (         ): sched:sched_waking(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
      1001.098 (         ): sched:sched_wakeup(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
         0.670 (1000.504 ms):  ... [continued]: nanosleep())                                        = 0
      1001.456 (         ): sched:sched_process_exit(comm: "sleep", pid: 3319 (sleep), prio: 120)
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm=trace pid=3323 prio=120 target_cpu=000)
         0.007 (         ): sched:sched_wakeup(comm=trace pid=3323 prio=120 target_cpu=000)
         0.382 (         ): sched:sched_process_exec(filename=/usr/bin/sleep pid=3323 old_pid=3323)
         0.525 (         ): msr:write_msr(c0000100, value 7f5d508a0580)
         0.713 (         ): nanosleep(rqtp: 0x7fff487fb4a0)                                    ...
         0.717 (         ): sched:sched_stat_runtime(comm=sleep pid=3323 runtime=617722 [ns] vruntime=78957731636 [ns])
         0.719 (         ): sched:sched_switch(prev_comm=sleep prev_pid=3323 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120)
      1001.117 (         ): sched:sched_waking(comm=sleep pid=3323 prio=120 target_cpu=000)
      1001.157 (         ): sched:sched_wakeup(comm=sleep pid=3323 prio=120 target_cpu=000)
         0.713 (1000.522 ms):  ... [continued]: nanosleep())                                        = 0
      1001.538 (         ): sched:sched_process_exit(comm=sleep pid=3323 prio=120)
    #

  - Make -v (verbose) mode be honoured for .perfconfig based trace.add_events,
    to help in diagnosing problems with building eBPF events (-e source.c).

  - When using eBPF syscall payload augmentation do not show strace-like
    syscalls when all the user specified was some tracepoint event, bringing
    the behaviour in line with that of when not using eBPF augmentation.

Intel PT:

  exported-sql-viewer GUI:

  Adrian Hunter:

  - Add LookupModel, HBoxLayout, VBoxLayout, global time range calculations
    so as to add a time chart by CPU.

perf script:

  Andi Kleen:

  - Allow --time (to specify a time span of interest) with --reltime

perf diff:

  Jin Yao:

  - Report noise for cycles diff, i.e. a histogram + stddev.
    (timestamps relative to start).

perf annotate:

  Arnaldo Carvalho de Melo:

  - Initialize env->cpuid when running in live mode (perf top), as it
    is used in some of the per arch annotation init routines.

samples bpf:

  Björn Töpel:

  - Fixup fallout of using tools/perf/perf-sys. from outside tools/perf.

Core:

  Ian Rogers:

  - Avoid 'sample_reg_masks' being const + weak, as this breaks with some
    compilers that constant-propagate from the weak symbol.

libperf:

  - First part of moving the perf_mmap class from tools/perf to libperf.

  - Propagate CFLAGS to libperf from the tools/perf Makefile.

Vendor events:

  John Garry:

  - Add entry in MAINTAINERS with reviewers for the for perf tool arm64
    pmu-events files.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
2019-10-15 07:19:55 +02:00
74 changed files with 4272 additions and 711 deletions
+7
View File
@@ -12769,6 +12769,13 @@ F: arch/*/events/*
F: arch/*/events/*/*
F: tools/perf/
PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS
R: John Garry <john.garry@huawei.com>
R: Will Deacon <will@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: tools/perf/pmu-events/arch/arm64/
PERSONALITY HANDLING
M: Christoph Hellwig <hch@infradead.org>
L: linux-abi-devel@lists.sourceforge.net
+1
View File
@@ -176,6 +176,7 @@ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0
HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
File diff suppressed because it is too large Load Diff
+5
View File
@@ -561,6 +561,11 @@ trace.*::
trace.show_zeros::
Do not suppress syscall arguments that are equal to zero.
trace.tracepoint_beautifiers::
Use "libtraceevent" to use that library to augment the tracepoint arguments,
"libbeauty", the default, to use the same argument beautifiers used in the
strace-like sys_enter+sys_exit lines.
llvm.*::
llvm.clang-path::
Path to clang. If omit, search it from $PATH.
+5
View File
@@ -95,6 +95,11 @@ OPTIONS
diff.compute config option. See COMPARISON METHODS section for
more info.
--cycles-hist::
Report a histogram and the standard deviation for cycles data.
It can help us to judge if the reported cycles data is noisy or
not. This option should be used with '-c cycles'.
-p::
--period::
Show period values for both compared hist entries.
+10
View File
@@ -42,6 +42,11 @@ OPTIONS
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
--filter=<filter>::
Event filter. This option should follow an event selector (-e) which
selects tracepoint event(s).
-D msecs::
--delay msecs::
After starting the program, wait msecs before measuring. This is useful to
@@ -219,6 +224,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
may happen, for instance, when a thread gets migrated to a different CPU
while processing a syscall.
--libtraceevent_print::
Use libtraceevent to print tracepoint arguments. By default 'perf trace' uses
the same beautifiers used in the strace-like enter+exit lines to augment the
tracepoint arguments.
--map-dump::
Dump BPF maps setup by events passed via -e, for instance the augmented_raw_syscalls
living in tools/perf/examples/bpf/augmented_raw_syscalls.c. For now this
+15 -13
View File
@@ -188,7 +188,7 @@ endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
CFLAGS += -Werror
CORE_CFLAGS += -Werror
CXXFLAGS += -Werror
endif
@@ -198,9 +198,9 @@ endif
ifeq ($(DEBUG),0)
ifeq ($(CC_NO_CLANG), 0)
CFLAGS += -O3
CORE_CFLAGS += -O3
else
CFLAGS += -O6
CORE_CFLAGS += -O6
endif
endif
@@ -245,12 +245,12 @@ FEATURE_CHECK_LDFLAGS-libaio = -lrt
FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
CFLAGS += -fno-omit-frame-pointer
CFLAGS += -ggdb3
CFLAGS += -funwind-tables
CFLAGS += -Wall
CFLAGS += -Wextra
CFLAGS += -std=gnu99
CORE_CFLAGS += -fno-omit-frame-pointer
CORE_CFLAGS += -ggdb3
CORE_CFLAGS += -funwind-tables
CORE_CFLAGS += -Wall
CORE_CFLAGS += -Wextra
CORE_CFLAGS += -std=gnu99
CXXFLAGS += -std=gnu++11 -fno-exceptions -fno-rtti
CXXFLAGS += -Wall
@@ -272,12 +272,12 @@ include $(FEATURES_DUMP)
endif
ifeq ($(feature-stackprotector-all), 1)
CFLAGS += -fstack-protector-all
CORE_CFLAGS += -fstack-protector-all
endif
ifeq ($(DEBUG),0)
ifeq ($(feature-fortify-source), 1)
CFLAGS += -D_FORTIFY_SOURCE=2
CORE_CFLAGS += -D_FORTIFY_SOURCE=2
endif
endif
@@ -301,10 +301,12 @@ INC_FLAGS += -I$(src-perf)/util
INC_FLAGS += -I$(src-perf)
INC_FLAGS += -I$(srctree)/tools/lib/
CFLAGS += $(INC_FLAGS)
CORE_CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
CFLAGS += $(CORE_CFLAGS) $(INC_FLAGS)
CXXFLAGS += $(INC_FLAGS)
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
LIBPERF_CFLAGS := $(CORE_CFLAGS) $(EXTRA_CFLAGS)
ifeq ($(feature-sync-compare-and-swap), 1)
CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
+10 -1
View File
@@ -407,6 +407,7 @@ linux_uapi_dir := $(srctree)/tools/include/uapi/linux
asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
x86_arch_asm_uapi_dir := $(srctree)/tools/arch/x86/include/uapi/asm/
x86_arch_asm_dir := $(srctree)/tools/arch/x86/include/asm/
beauty_outdir := $(OUTPUT)trace/beauty/generated
beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -543,6 +544,12 @@ x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
$(x86_arch_prctl_code_array): $(x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(x86_arch_asm_uapi_dir) > $@
x86_arch_MSRs_array := $(beauty_outdir)/x86_arch_MSRs_array.c
x86_arch_MSRs_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_msr.sh
$(x86_arch_MSRs_array): $(x86_arch_asm_dir)/msr-index.h $(x86_arch_MSRs_tbl)
$(Q)$(SHELL) '$(x86_arch_MSRs_tbl)' $(x86_arch_asm_dir) > $@
rename_flags_array := $(beauty_outdir)/rename_flags_array.c
rename_flags_tbl := $(srctree)/tools/perf/trace/beauty/rename_flags.sh
@@ -677,6 +684,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
$(perf_ioctl_array) \
$(prctl_option_array) \
$(usbdevfs_ioctl_array) \
$(x86_arch_MSRs_array) \
$(x86_arch_prctl_code_array) \
$(rename_flags_array) \
$(arch_errno_name_array) \
@@ -761,7 +769,7 @@ $(LIBBPF)-clean:
$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
$(LIBPERF): FORCE
$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(OUTPUT) $(OUTPUT)libperf.a
$(Q)$(MAKE) -C $(LIBPERF_DIR) EXTRA_CFLAGS="$(LIBPERF_CFLAGS)" O=$(OUTPUT) $(OUTPUT)libperf.a
$(LIBPERF)-clean:
$(call QUIET_CLEAN, libperf)
@@ -981,6 +989,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
$(OUTPUT)$(perf_ioctl_array) \
$(OUTPUT)$(prctl_option_array) \
$(OUTPUT)$(usbdevfs_ioctl_array) \
$(OUTPUT)$(x86_arch_MSRs_array) \
$(OUTPUT)$(x86_arch_prctl_code_array) \
$(OUTPUT)$(rename_flags_array) \
$(OUTPUT)$(arch_errno_name_array) \
+2
View File
@@ -1,3 +1,5 @@
perf-y += perf_regs.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
};
+1
View File
@@ -1,4 +1,5 @@
perf-y += header.o
perf-y += perf_regs.o
perf-y += sym-handling.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
};
+2
View File
@@ -1,2 +1,4 @@
perf-y += perf_regs.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
};
+2
View File
@@ -1,2 +1,4 @@
perf-y += perf_regs.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
};
+1
View File
@@ -1,5 +1,6 @@
perf-y += header.o
perf-y += kvm-stat.o
perf-y += perf_regs.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../util/perf_regs.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG_END
};
+5 -4
View File
@@ -9,6 +9,7 @@
#include <sys/prctl.h>
#include <perf/cpumap.h>
#include <perf/evlist.h>
#include <perf/mmap.h>
#include "debug.h"
#include "parse-events.h"
@@ -117,10 +118,10 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
for (i = 0; i < evlist->core.nr_mmaps; i++) {
md = &evlist->mmap[i];
if (perf_mmap__read_init(md) < 0)
if (perf_mmap__read_init(&md->core) < 0)
continue;
while ((event = perf_mmap__read_event(md)) != NULL) {
while ((event = perf_mmap__read_event(&md->core)) != NULL) {
struct perf_sample sample;
if (event->header.type != PERF_RECORD_COMM ||
@@ -139,9 +140,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
comm2_time = sample.time;
}
next_event:
perf_mmap__consume(md);
perf_mmap__consume(&md->core);
}
perf_mmap__read_done(md);
perf_mmap__read_done(&md->core);
}
if (!comm1_time || !comm2_time)
+143
View File
@@ -23,6 +23,7 @@
#include "util/time-utils.h"
#include "util/annotate.h"
#include "util/map.h"
#include "util/spark.h"
#include <linux/err.h>
#include <linux/zalloc.h>
#include <subcmd/pager.h>
@@ -53,6 +54,7 @@ enum {
PERF_HPP_DIFF__FORMULA,
PERF_HPP_DIFF__DELTA_ABS,
PERF_HPP_DIFF__CYCLES,
PERF_HPP_DIFF__CYCLES_HIST,
PERF_HPP_DIFF__MAX_INDEX
};
@@ -87,6 +89,7 @@ static bool force;
static bool show_period;
static bool show_formula;
static bool show_baseline_only;
static bool cycles_hist;
static unsigned int sort_compute = 1;
static s64 compute_wdiff_w1;
@@ -164,6 +167,10 @@ static struct header_column {
[PERF_HPP_DIFF__CYCLES] = {
.name = "[Program Block Range] Cycles Diff",
.width = 70,
},
[PERF_HPP_DIFF__CYCLES_HIST] = {
.name = "stddev/Hist",
.width = NUM_SPARKS + 9,
}
};
@@ -610,6 +617,9 @@ static void init_block_info(struct block_info *bi, struct symbol *sym,
bi->cycles_aggr = ch->cycles_aggr;
bi->num = ch->num;
bi->num_aggr = ch->num_aggr;
memcpy(bi->cycles_spark, ch->cycles_spark,
NUM_SPARKS * sizeof(u64));
}
static int process_block_per_sym(struct hist_entry *he)
@@ -689,6 +699,21 @@ static struct hist_entry *get_block_pair(struct hist_entry *he,
return NULL;
}
static void init_spark_values(unsigned long *svals, int num)
{
for (int i = 0; i < num; i++)
svals[i] = 0;
}
static void update_spark_value(unsigned long *svals, int num,
struct stats *stats, u64 val)
{
int n = stats->n;
if (n < num)
svals[n] = val;
}
static void compute_cycles_diff(struct hist_entry *he,
struct hist_entry *pair)
{
@@ -697,6 +722,26 @@ static void compute_cycles_diff(struct hist_entry *he,
pair->diff.cycles =
pair->block_info->cycles_aggr / pair->block_info->num_aggr -
he->block_info->cycles_aggr / he->block_info->num_aggr;
if (!cycles_hist)
return;
init_stats(&pair->diff.stats);
init_spark_values(pair->diff.svals, NUM_SPARKS);
for (int i = 0; i < pair->block_info->num; i++) {
u64 val;
if (i >= he->block_info->num || i >= NUM_SPARKS)
break;
val = labs(pair->block_info->cycles_spark[i] -
he->block_info->cycles_spark[i]);
update_spark_value(pair->diff.svals, NUM_SPARKS,
&pair->diff.stats, val);
update_stats(&pair->diff.stats, val);
}
}
}
@@ -1255,6 +1300,9 @@ static const struct option options[] = {
"Show period values."),
OPT_BOOLEAN('F', "formula", &show_formula,
"Show formula."),
OPT_BOOLEAN(0, "cycles-hist", &cycles_hist,
"Show cycles histogram and standard deviation "
"- WARNING: use only with -c cycles."),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -1462,6 +1510,90 @@ static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
}
static int all_zero(unsigned long *vals, int len)
{
int i;
for (i = 0; i < len; i++)
if (vals[i] != 0)
return 0;
return 1;
}
static int print_cycles_spark(char *bf, int size, unsigned long *svals, u64 n)
{
int printed;
if (n <= 1)
return 0;
if (n > NUM_SPARKS)
n = NUM_SPARKS;
if (all_zero(svals, n))
return 0;
printed = print_spark(bf, size, svals, n);
printed += scnprintf(bf + printed, size - printed, " ");
return printed;
}
static int hpp__color_cycles_hist(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
struct hist_entry *pair = get_pair_fmt(he, dfmt);
struct block_hist *bh = container_of(he, struct block_hist, he);
struct block_hist *bh_pair;
struct hist_entry *block_he;
char spark[32], buf[128];
double r;
int ret, pad;
if (!pair) {
if (bh->block_idx)
hpp->skip = true;
goto no_print;
}
bh_pair = container_of(pair, struct block_hist, he);
block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
if (!block_he) {
hpp->skip = true;
goto no_print;
}
ret = print_cycles_spark(spark, sizeof(spark), block_he->diff.svals,
block_he->diff.stats.n);
r = rel_stddev_stats(stddev_stats(&block_he->diff.stats),
avg_stats(&block_he->diff.stats));
if (ret) {
/*
* Padding spaces if number of sparks less than NUM_SPARKS
* otherwise the output is not aligned.
*/
pad = NUM_SPARKS - ((ret - 1) / 3);
scnprintf(buf, sizeof(buf), "%s%5.1f%% %s", "\u00B1", r, spark);
ret = scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, buf);
if (pad) {
ret += scnprintf(hpp->buf + ret, hpp->size - ret,
"%-*s", pad, " ");
}
return ret;
}
no_print:
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, " ");
}
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
@@ -1667,6 +1799,10 @@ static void data__hpp_register(struct data__file *d, int idx)
fmt->color = hpp__color_cycles;
fmt->sort = hist_entry__cmp_nop;
break;
case PERF_HPP_DIFF__CYCLES_HIST:
fmt->color = hpp__color_cycles_hist;
fmt->sort = hist_entry__cmp_nop;
break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
@@ -1692,10 +1828,14 @@ static int ui_init(void)
* PERF_HPP_DIFF__DELTA
* PERF_HPP_DIFF__RATIO
* PERF_HPP_DIFF__WEIGHTED_DIFF
* PERF_HPP_DIFF__CYCLES
*/
data__hpp_register(d, i ? compute_2_hpp[compute] :
PERF_HPP_DIFF__BASELINE);
if (cycles_hist && i)
data__hpp_register(d, PERF_HPP_DIFF__CYCLES_HIST);
/*
* And the rest:
*
@@ -1850,6 +1990,9 @@ int cmd_diff(int argc, const char **argv)
if (quiet)
perf_quiet_option();
if (cycles_hist && (compute != COMPUTE_CYCLES))
usage_with_options(diff_usage, options);
symbol__annotation_init();
if (symbol__init(NULL) < 0)

Some files were not shown because too many files have changed in this diff Show More