summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/uapi/linux/perf_event.h10
-rw-r--r--kernel/events/callchain.c15
-rw-r--r--kernel/events/core.c54
-rw-r--r--kernel/events/internal.h4
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h4
-rw-r--r--tools/arch/x86/include/asm/disabled-features.h8
-rw-r--r--tools/include/uapi/linux/perf_event.h10
-rw-r--r--tools/perf/Documentation/perf-record.txt3
-rw-r--r--tools/perf/Documentation/perf-report.txt37
-rw-r--r--tools/perf/Documentation/perf-script.txt39
-rw-r--r--tools/perf/Documentation/perf.data-file-format.txt4
-rw-r--r--tools/perf/Makefile.config2
-rw-r--r--tools/perf/Makefile.perf2
-rw-r--r--tools/perf/arch/x86/util/unwind-libunwind.c2
-rw-r--r--tools/perf/builtin-record.c18
-rw-r--r--tools/perf/builtin-report.c249
-rw-r--r--tools/perf/builtin-script.c136
-rw-r--r--tools/perf/builtin-trace.c1
-rw-r--r--tools/perf/tests/bpf-script-example.c4
-rw-r--r--tools/perf/tests/bpf.c65
-rw-r--r--tools/perf/util/annotate.c3
-rw-r--r--tools/perf/util/event.c8
-rw-r--r--tools/perf/util/event.h1
-rw-r--r--tools/perf/util/evlist.h2
-rw-r--r--tools/perf/util/evsel.c2
-rw-r--r--tools/perf/util/header.c60
-rw-r--r--tools/perf/util/header.h1
-rw-r--r--tools/perf/util/machine.c2
-rw-r--r--tools/perf/util/map.c2
-rw-r--r--tools/perf/util/session.c6
-rw-r--r--tools/perf/util/sort.c16
-rw-r--r--tools/perf/util/srcline.c9
-rw-r--r--tools/perf/util/srcline.h5
-rw-r--r--tools/perf/util/time-utils.c233
-rw-r--r--tools/perf/util/time-utils.h6
-rw-r--r--tools/perf/util/tool.h1
36 files changed, 884 insertions, 140 deletions
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b9a4953018ed..c77c9a2ebbbb 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -612,9 +612,12 @@ struct perf_event_mmap_page {
*/
#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
/*
- * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
- * different events so can reuse the same bit position.
- * Ditto PERF_RECORD_MISC_SWITCH_OUT.
+ * Following PERF_RECORD_MISC_* are used on different
+ * events, so can reuse the same bit position:
+ *
+ * PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events
+ * PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event
+ * PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
*/
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
@@ -864,6 +867,7 @@ enum perf_event_type {
* struct perf_event_header header;
* u32 pid;
* u32 tid;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_ITRACE_START = 12,
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 1b2be63c8528..772a43fea825 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -179,21 +179,6 @@ put_callchain_entry(int rctx)
}
struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs)
-{
- bool kernel = !event->attr.exclude_callchain_kernel;
- bool user = !event->attr.exclude_callchain_user;
- /* Disallow cross-task user callchains. */
- bool crosstask = event->ctx->task && event->ctx->task != current;
- const u32 max_stack = event->attr.sample_max_stack;
-
- if (!kernel && !user)
- return NULL;
-
- return get_perf_callchain(regs, 0, kernel, user, max_stack, crosstask, true);
-}
-
-struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
u32 max_stack, bool crosstask, bool add_mark)
{
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4df5b695bf0d..4e1a1bf8d867 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5815,19 +5815,11 @@ void perf_output_sample(struct perf_output_handle *handle,
perf_output_read(handle, event);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
- if (data->callchain) {
- int size = 1;
-
- if (data->callchain)
- size += data->callchain->nr;
-
- size *= sizeof(u64);
+ int size = 1;
- __output_copy(handle, data->callchain, size);
- } else {
- u64 nr = 0;
- perf_output_put(handle, nr);
- }
+ size += data->callchain->nr;
+ size *= sizeof(u64);
+ __output_copy(handle, data->callchain, size);
}
if (sample_type & PERF_SAMPLE_RAW) {
@@ -5980,6 +5972,26 @@ static u64 perf_virt_to_phys(u64 virt)
return phys_addr;
}
+static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
+
+static struct perf_callchain_entry *
+perf_callchain(struct perf_event *event, struct pt_regs *regs)
+{
+ bool kernel = !event->attr.exclude_callchain_kernel;
+ bool user = !event->attr.exclude_callchain_user;
+ /* Disallow cross-task user callchains. */
+ bool crosstask = event->ctx->task && event->ctx->task != current;
+ const u32 max_stack = event->attr.sample_max_stack;
+ struct perf_callchain_entry *callchain;
+
+ if (!kernel && !user)
+ return &__empty_callchain;
+
+ callchain = get_perf_callchain(regs, 0, kernel, user,
+ max_stack, crosstask, true);
+ return callchain ?: &__empty_callchain;
+}
+
void perf_prepare_sample(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
@@ -6002,9 +6014,7 @@ void perf_prepare_sample(struct perf_event_header *header,
int size = 1;
data->callchain = perf_callchain(event, regs);
-
- if (data->callchain)
- size += data->callchain->nr;
+ size += data->callchain->nr;
header->size += size * sizeof(u64);
}
@@ -10703,6 +10713,19 @@ inherit_event(struct perf_event *parent_event,
if (IS_ERR(child_event))
return child_event;
+
+ if ((child_event->attach_state & PERF_ATTACH_TASK_DATA) &&
+ !child_ctx->task_ctx_data) {
+ struct pmu *pmu = child_event->pmu;
+
+ child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
+ GFP_KERNEL);
+ if (!child_ctx->task_ctx_data) {
+ free_event(child_event);
+ return NULL;
+ }
+ }
+
/*
* is_orphaned_event() and list_add_tail(&parent_event->child_list)
* must be under the same lock in order to serialize against
@@ -10713,6 +10736,7 @@ inherit_event(struct perf_event *parent_event,
if (is_orphaned_event(parent_event) ||
!atomic_long_inc_not_zero(&parent_event->refcount)) {
mutex_unlock(&parent_event->child_mutex);
+ /* task_ctx_data is freed with child_ctx */
free_event(child_event);
return NULL;
}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 09b1537ae06c..6dc725a7e7bc 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -201,10 +201,6 @@ arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
-/* Callchain handling */
-extern struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs);
-
static inline int get_recursion_context(int *recursion)
{
int rctx;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 800104c8a3ed..21ac898df2d8 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -197,11 +197,12 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -340,5 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 14d6d5007314..b027633e7300 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -50,6 +50,12 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI 0
+#else
+# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -60,7 +66,7 @@
#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
-#define DISABLED_MASK7 0
+#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b9a4953018ed..c77c9a2ebbbb 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -612,9 +612,12 @@ struct perf_event_mmap_page {
*/
#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
/*
- * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
- * different events so can reuse the same bit position.
- * Ditto PERF_RECORD_MISC_SWITCH_OUT.
+ * Following PERF_RECORD_MISC_* are used on different
+ * events, so can reuse the same bit position:
+ *
+ * PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events
+ * PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event
+ * PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
*/
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
@@ -864,6 +867,7 @@ enum perf_event_type {
* struct perf_event_header header;
* u32 pid;
* u32 tid;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_ITRACE_START = 12,
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5a626ef666c2..3eea6de35a38 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -430,6 +430,9 @@ Configure all used events to run in user space.
--timestamp-filename
Append timestamp to output file name.
+--timestamp-boundary::
+Record timestamp boundary (time of first/last samples).
+
--switch-output[=mode]::
Generate multiple perf.data files, timestamp prefixed, switching to a new one
based on 'mode' value:
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index ddde2b54af57..63d0db3184c9 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -402,6 +402,26 @@ OPTIONS
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
+ Also support time percent with multiple time range. Time string is
+ 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10.
+
+ For example:
+ Select the second 10% time slice:
+
+ perf report --time 10%/2
+
+ Select from 0% to 10% time slice:
+
+ perf report --time 0%-10%
+
+ Select the first and second 10% time slices:
+
+ perf report --time 10%/1,10%/2
+
+ Select from 0% to 10% and 30% to 40% slices:
+
+ perf report --time 0%-10%,30%-40%
+
--itrace::
Options for decoding instruction tracing data. The options are:
@@ -437,8 +457,23 @@ include::itrace.txt[]
will be printed. Each entry is function name or file/line. Enabled by
default, disable with --no-inline.
+--mmaps::
+ Show --tasks output plus mmap information in a format similar to
+ /proc/<PID>/maps.
+
+ Please note that not all mmaps are stored, options affecting which ones
+ are include 'perf record --data', for instance.
+
+--stats::
+ Display overall events statistics without any further processing.
+ (like the one at the end of the perf report -D command)
+
+--tasks::
+ Display monitored tasks stored in perf data. Displaying pid/tid/ppid
+ plus the command string aligned to distinguish parent and child tasks.
+
include::callchain-overhead-calculation.txt[]
SEE ALSO
--------
-linkperf:perf-stat[1], linkperf:perf-annotate[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 974ceb12c7f3..806ec6391fd6 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
- brstackoff, callindent, insn, insnlen, synth, phys_addr, metric.
+ brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
@@ -225,6 +225,24 @@ OPTIONS
that the metric computed is averaged over the whole sampling
period, not just for the sample point.
+ For sample events it's possible to display misc field with -F +misc option,
+ following letters are displayed for each bit:
+
+ PERF_RECORD_MISC_KERNEL K
+ PERF_RECORD_MISC_USER U
+ PERF_RECORD_MISC_HYPERVISOR H
+ PERF_RECORD_MISC_GUEST_KERNEL G
+ PERF_RECORD_MISC_GUEST_USER g
+ PERF_RECORD_MISC_MMAP_DATA* M
+ PERF_RECORD_MISC_COMM_EXEC E
+ PERF_RECORD_MISC_SWITCH_OUT S
+
+ $ perf script -F +misc ...
+ sched-messaging 1414 K 28690.636582: 4590 cycles ...
+ sched-messaging 1407 U 28690.636600: 325620 cycles ...
+ sched-messaging 1414 K 28690.636608: 19473 cycles ...
+ misc field ___________/
+
-k::
--vmlinux=<file>::
vmlinux pathname
@@ -282,6 +300,9 @@ OPTIONS
Display context switch events i.e. events of type PERF_RECORD_SWITCH or
PERF_RECORD_SWITCH_CPU_WIDE.
+--show-lost-events
+ Display lost events i.e. events of type PERF_RECORD_LOST.
+
--demangle::
Demangle symbol names to human readable form. It's enabled by default,
disable with --no-demangle.
@@ -329,6 +350,22 @@ include::itrace.txt[]
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
+ Also support time percent with multipe time range. Time string is
+ 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10.
+
+ For example:
+ Select the second 10% time slice
+ perf script --time 10%/2
+
+ Select from 0% to 10% time slice
+ perf script --time 0%-10%
+
+ Select the first and second 10% time slices
+ perf script --time 10%/1,10%/2
+
+ Select from 0% to 10% and 30% to 40% slices
+ perf script --time 0%-10%,30%-40%
+
--max-blocks::
Set the maximum number of program blocks to print with brstackasm for
each sample.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 15e8b48077ba..f7d85e89a98a 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -261,6 +261,10 @@ struct {
struct perf_header_string map;
}[number_of_cache_levels];
+ HEADER_SAMPLE_TIME = 21,
+
+Two uint64_t for the time of first sample and the time of last sample.
+
other bits are reserved and should ignored for now
HEADER_FEAT_BITS = 256,
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f050f38d8fa3..12dec6ea5ed2 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -780,7 +780,7 @@ else
NO_PERF_READ_VDSOX32 := 1
endif
-ifdef LIBBABELTRACE
+ifndef NO_LIBBABELTRACE
$(call feature_check,libbabeltrace)
ifeq ($(feature-libbabeltrace), 1)
CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 68cf1360a3f3..9fdefd748e2e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -77,7 +77,7 @@ include ../scripts/utilities.mak
#
# Define NO_ZLIB if you do not want to support compressed kernel modules
#
-# Define LIBBABELTRACE if you DO want libbabeltrace support
+# Define NO_LIBBABELTRACE if you do not want libbabeltrace support
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f80c906..05920e3edf7a 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
-#ifndef REMOTE_UNWIND_LIBUNWIND
#include <errno.h>
+#ifndef REMOTE_UNWIND_LIBUNWIND
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 50385d89c497..65681a1a292a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -78,6 +78,7 @@ struct record {
bool no_buildid_cache_set;
bool buildid_all;
bool timestamp_filename;
+ bool timestamp_boundary;
struct switch_output switch_output;
unsigned long long samples;
};
@@ -409,8 +410,15 @@ static int process_sample_event(struct perf_tool *tool,
{
struct record *rec = container_of(tool, struct record, tool);
- rec->samples++;
+ if (rec->evlist->first_sample_time == 0)
+ rec->evlist->first_sample_time = sample->time;
+
+ rec->evlist->last_sample_time = sample->time;
+ if (rec->buildid_all)
+ return 0;
+
+ rec->samples++;
return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
}
@@ -435,9 +443,11 @@ static int process_buildids(struct record *rec)
/*
* If --buildid-all is given, it marks all DSO regardless of hits,
- * so no need to process samples.
+ * so no need to process samples. But if timestamp_boundary is enabled,
+ * it still needs to walk on all samples to get the timestamps of
+ * first/last samples.
*/
- if (rec->buildid_all)
+ if (rec->buildid_all && !rec->timestamp_boundary)
rec->tool.sample = NULL;
return perf_session__process_events(session);
@@ -1621,6 +1631,8 @@ static struct option __record_options[] = {
"Record build-id of all DSOs regardless of hits"),
OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
"append timestamp to output filename"),
+ OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
+ "Record timestamp boundary (time of first/last samples)"),
OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
&record.switch_output.set, "signal,size,time",
"Switch output when receive SIGUSR2 or cross size,time threshold",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index eb9ce6327e71..dd4df9a5cd06 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -15,6 +15,7 @@
#include "util/color.h"
#include <linux/list.h>
#include <linux/rbtree.h>
+#include <linux/err.h>
#include "util/symbol.h"
#include "util/callchain.h"
#include "util/values.h"
@@ -51,6 +52,9 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
+#include <linux/mman.h>
+
+#define PTIME_RANGE_MAX 10
struct report {
struct perf_tool tool;
@@ -60,6 +64,9 @@ struct report {
bool show_threads;
bool inverted_callchain;
bool mem_mode;
+ bool stats_mode;
+ bool tasks_mode;
+ bool mmaps_mode;
bool header;
bool header_only;
bool nonany_branch_mode;
@@ -69,7 +76,8 @@ struct report {
const char *cpu_list;
const char *symbol_filter_str;
const char *time_str;
- struct perf_time_interval ptime;
+ struct perf_time_interval ptime_range[PTIME_RANGE_MAX];
+ int range_num;
float min_percent;
u64 nr_entries;
u64 queue_size;
@@ -162,12 +170,28 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
struct hist_entry *he = iter->he;
struct report *rep = arg;
struct branch_info *bi;
+ struct perf_sample *sample = iter->sample;
+ struct perf_evsel *evsel = iter->evsel;
+ int err;
+
+ if (!ui__has_annotation())
+ return 0;
+
+ hist__account_cycles(sample->branch_stack, al, sample,
+ rep->nonany_branch_mode);
bi = he->branch_info;
+ err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
+ if (err)
+ goto out;
+
+ err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
+
branch_type_count(&rep->brtype_stat, &bi->flags,
bi->from.addr, bi->to.addr);
- return 0;
+out:
+ return err;
}
static int process_sample_event(struct perf_tool *tool,
@@ -186,8 +210,10 @@ static int process_sample_event(struct perf_tool *tool,
};
int ret = 0;
- if (perf_time__skip_sample(&rep->ptime, sample->time))
+ if (perf_time__ranges_skip_sample(rep->ptime_range, rep->range_num,
+ sample->time)) {
return 0;
+ }
if (machine__resolve(machine, &al, sample) < 0) {
pr_debug("problem processing %d event, skipping it.\n",
@@ -567,6 +593,174 @@ static void report__output_resort(struct report *rep)
ui_progress__finish();
}
+static void stats_setup(struct report *rep)
+{
+ memset(&rep->tool, 0, sizeof(rep->tool));
+ rep->tool.no_warn = true;
+}
+
+static int stats_print(struct report *rep)
+{
+ struct perf_session *session = rep->session;
+
+ perf_session__fprintf_nr_events(session, stdout);
+ return 0;
+}
+
+static void tasks_setup(struct report *rep)
+{
+ memset(&rep->tool, 0, sizeof(rep->tool));
+ if (rep->mmaps_mode) {
+ rep->tool.mmap = perf_event__process_mmap;
+ rep->tool.mmap2 = perf_event__process_mmap2;
+ }
+ rep->tool.comm = perf_event__process_comm;
+ rep->tool.exit = perf_event__process_exit;
+ rep->tool.fork = perf_event__process_fork;
+ rep->tool.no_warn = true;
+}
+
+struct task {
+ struct thread *thread;
+ struct list_head list;
+ struct list_head children;
+};
+
+static struct task *tasks_list(struct task *task, struct machine *machine)
+{
+ struct thread *parent_thread, *thread = task->thread;
+ struct task *parent_task;
+
+ /* Already listed. */
+ if (!list_empty(&task->list))
+ return NULL;
+
+ /* Last one in the chain. */
+ if (thread->ppid == -1)
+ return task;
+
+ parent_thread = machine__find_thread(machine, -1, thread->ppid);
+ if (!parent_thread)
+ return ERR_PTR(-ENOENT);
+
+ parent_task = thread__priv(parent_thread);
+ list_add_tail(&task->list, &parent_task->children);
+ return tasks_list(parent_task, machine);
+}
+
+static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+{
+ size_t printed = 0;
+ struct rb_node *nd;
+
+ for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
+ struct map *map = rb_entry(nd, struct map, rb_node);
+
+ printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
+ indent, "", map->start, map->end,
+ map->prot & PROT_READ ? 'r' : '-',
+ map->prot & PROT_WRITE ? 'w' : '-',
+ map->prot & PROT_EXEC ? 'x' : '-',
+ map->flags & MAP_SHARED ? 's' : 'p',
+ map->pgoff,
+ map->ino, map->dso->name);
+ }
+
+ return printed;
+}
+
+static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp)
+{
+ int printed = 0, i;
+ for (i = 0; i < MAP__NR_TYPES; ++i)
+ printed += maps__fprintf_task(&mg->maps[i], indent, fp);
+ return printed;
+}
+
+static void task__print_level(struct task *task, FILE *fp, int level)
+{
+ struct thread *thread = task->thread;
+ struct task *child;
+ int comm_indent = fprintf(fp, " %8d %8d %8d |%*s",
+ thread->pid_, thread->tid, thread->ppid,
+ level, "");
+
+ fprintf(fp, "%s\n", thread__comm_str(thread));
+
+ map_groups__fprintf_task(thread->mg, comm_indent, fp);
+