summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/Documentation/perf-buildid-cache.txt2
-rw-r--r--tools/perf/Documentation/perf-list.txt13
-rw-r--r--tools/perf/Documentation/perf-mem.txt9
-rw-r--r--tools/perf/Documentation/perf-record.txt19
-rw-r--r--tools/perf/Documentation/perf-script.txt28
-rw-r--r--tools/perf/Documentation/perf-stat.txt20
-rw-r--r--tools/perf/MANIFEST6
-rw-r--r--tools/perf/Makefile.perf11
-rw-r--r--tools/perf/arch/powerpc/util/skip-callchain-idx.c19
-rw-r--r--tools/perf/bench/futex.h13
-rw-r--r--tools/perf/bench/sched-pipe.c2
-rw-r--r--tools/perf/builtin-annotate.c2
-rw-r--r--tools/perf/builtin-buildid-cache.c4
-rw-r--r--tools/perf/builtin-diff.c254
-rw-r--r--tools/perf/builtin-inject.c5
-rw-r--r--tools/perf/builtin-list.c13
-rw-r--r--tools/perf/builtin-mem.c131
-rw-r--r--tools/perf/builtin-record.c70
-rw-r--r--tools/perf/builtin-report.c40
-rw-r--r--tools/perf/builtin-stat.c2
-rw-r--r--tools/perf/builtin-top.c7
-rw-r--r--tools/perf/builtin-trace.c106
-rw-r--r--tools/perf/config/Makefile8
-rw-r--r--tools/perf/config/Makefile.arch26
-rw-r--r--tools/perf/config/feature-checks/Makefile4
-rw-r--r--tools/perf/config/feature-checks/test-all.c5
-rw-r--r--tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c14
-rw-r--r--tools/perf/perf-sys.h1
-rw-r--r--tools/perf/scripts/perl/Perf-Trace-Util/Context.c5
-rw-r--r--tools/perf/tests/attr.py1
-rw-r--r--tools/perf/tests/dwarf-unwind.c36
-rw-r--r--tools/perf/tests/hists_cumulate.c68
-rw-r--r--tools/perf/tests/hists_filter.c2
-rw-r--r--tools/perf/tests/hists_output.c12
-rw-r--r--tools/perf/tests/make1
-rw-r--r--tools/perf/tests/parse-events.c60
-rw-r--r--tools/perf/tests/sample-parsing.c2
-rw-r--r--tools/perf/ui/browsers/annotate.c3
-rw-r--r--tools/perf/ui/browsers/hists.c2
-rw-r--r--tools/perf/ui/hist.c15
-rw-r--r--tools/perf/ui/progress.h4
-rw-r--r--tools/perf/ui/tui/helpline.c3
-rw-r--r--tools/perf/ui/tui/setup.c29
-rw-r--r--tools/perf/util/annotate.c20
-rw-r--r--tools/perf/util/annotate.h8
-rw-r--r--tools/perf/util/cache.h2
-rw-r--r--tools/perf/util/callchain.c30
-rw-r--r--tools/perf/util/callchain.h2
-rw-r--r--tools/perf/util/color.c126
-rw-r--r--tools/perf/util/color.h2
-rw-r--r--tools/perf/util/dso.c6
-rw-r--r--tools/perf/util/dso.h1
-rw-r--r--tools/perf/util/evlist.c27
-rw-r--r--tools/perf/util/evlist.h1
-rw-r--r--tools/perf/util/evsel.c4
-rw-r--r--tools/perf/util/header.c2
-rw-r--r--tools/perf/util/hist.c66
-rw-r--r--tools/perf/util/hist.h13
-rw-r--r--tools/perf/util/hweight.c31
-rw-r--r--tools/perf/util/include/asm/hweight.h8
-rw-r--r--tools/perf/util/machine.c4
-rw-r--r--tools/perf/util/map.h16
-rw-r--r--tools/perf/util/parse-events.c27
-rw-r--r--tools/perf/util/parse-events.h3
-rw-r--r--tools/perf/util/parse-events.l1
-rw-r--r--tools/perf/util/parse-events.y26
-rw-r--r--tools/perf/util/parse-options.c2
-rw-r--r--tools/perf/util/pmu.c102
-rw-r--r--tools/perf/util/probe-event.c44
-rw-r--r--tools/perf/util/probe-finder.c18
-rw-r--r--tools/perf/util/python-ext-sources2
-rw-r--r--tools/perf/util/python.c2
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c2
-rw-r--r--tools/perf/util/session.c8
-rw-r--r--tools/perf/util/session.h3
-rw-r--r--tools/perf/util/sort.c37
-rw-r--r--tools/perf/util/symbol-elf.c13
-rw-r--r--tools/perf/util/symbol.c33
-rw-r--r--tools/perf/util/symbol.h1
-rw-r--r--tools/perf/util/unwind-libunwind.c59
80 files changed, 1187 insertions, 642 deletions
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index fd77d81ea748..0294c57b1f5e 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -38,7 +38,7 @@ OPTIONS
--remove=::
Remove specified file from the cache.
-M::
---missing=::
+--missing=::
List missing build ids in the cache for the specified file.
-u::
--update::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index cbb4f743d921..3e2aec94f806 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -89,6 +89,19 @@ raw encoding of 0x1A8 can be used:
You should refer to the processor specific documentation for getting these
details. Some of them are referenced in the SEE ALSO section below.
+PARAMETERIZED EVENTS
+--------------------
+
+Some pmu events listed by 'perf-list' will be displayed with '?' in them. For
+example:
+
+ hv_gpci/dtbp_ptitc,phys_processor_idx=?/
+
+This means that when provided as an event, a value for '?' must
+also be supplied. For example:
+
+ perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
+
OPTIONS
-------
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 1d78a4064da4..43310d8661fe 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -12,11 +12,12 @@ SYNOPSIS
DESCRIPTION
-----------
-"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+"perf mem record" runs a command and gathers memory operation data
from it, into perf.data. Perf record options are accepted and are passed through.
-"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
-right set of options to display a memory access profile.
+"perf mem report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile. By default, loads
+and stores are sampled. Use the -t option to limit to loads or stores.
Note that on Intel systems the memory latency reported is the use-latency,
not the pure load (or store latency). Use latency includes any pipeline
@@ -29,7 +30,7 @@ OPTIONS
-t::
--type=::
- Select the memory operation type: load or store (default: load)
+ Select the memory operation type: load or store (default: load,store)
-D::
--dump-raw-samples=::
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index af9a54ece024..31e977459c51 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,12 +33,27 @@ OPTIONS
- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
hexadecimal event descriptor.
- - a hardware breakpoint event in the form of '\mem:addr[:access]'
+ - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
+ 'param1', 'param2', etc are defined as formats for the PMU in
+ /sys/bus/event_sources/devices/<pmu>/format/*.
+
+ - a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
+
+ where M, N, K are numbers (in decimal, hex, octal format). Acceptable
+ values for each of 'config', 'config1' and 'config2' are defined by
+ corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/*
+ param1 and param2 are defined as formats for the PMU in:
+ /sys/bus/event_sources/devices/<pmu>/format/*
+
+ - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
where addr is the address in memory you want to break in.
Access is the memory access type (read, write, execute) it can
- be passed as follows: '\mem:addr[:[r][w][x]]'.
+ be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
+ number of bytes from specified addr, which the breakpoint will cover.
If you want to profile read-write accesses in 0x1000, just set
'mem:0x1000:rw'.
+ If you want to profile write accesses in [0x1000~1008), just set
+ 'mem:0x1000/8:w'.
--filter=<filter>::
Event filter.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 21494806c0ab..a21eec05bc42 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -125,46 +125,46 @@ OPTIONS
is equivalent to:
perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
-
+
i.e., the specified fields apply to all event types if the type string
is not given.
-
+
The arguments are processed in the order received. A later usage can
reset a prior request. e.g.:
-
+
-f trace: -f comm,tid,time,ip,sym
-
+
The first -f suppresses trace events (field list is ""), but then the
second invocation sets the fields to comm,tid,time,ip,sym. In this case a
warning is given to the user:
-
+
"Overriding previous field request for all events."
-
+
Alternatively, consider the order:
-
+
-f comm,tid,time,ip,sym -f trace:
-
+
The first -f sets the fields for all events and the second -f
suppresses trace events. The user is given a warning message about
the override, and the result of the above is that only S/W and H/W
events are displayed with the given fields.
-
+
For the 'wildcard' option if a user selected field is invalid for an
event type, a message is displayed to the user that the option is
ignored for that type. For example:
-
+
$ perf script -f comm,tid,trace
'trace' not valid for hardware events. Ignoring.
'trace' not valid for software events. Ignoring.
-
+
Alternatively, if the type is given an invalid field is specified it
is an error. For example:
-
+
perf script -v -f sw:comm,tid,trace
'trace' not valid for software events.
-
+
At this point usage is displayed, and perf-script exits.
-
+
Finally, a user may not set fields to none for all event types.
i.e., -f "" is not allowed.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 29ee857c09c6..04e150d83e7d 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -25,10 +25,22 @@ OPTIONS
-e::
--event=::
- Select the PMU event. Selection can be a symbolic event name
- (use 'perf list' to list all events) or a raw PMU
- event (eventsel+umask) in the form of rNNN where NNN is a
- hexadecimal event descriptor.
+ Select the PMU event. Selection can be:
+
+ - a symbolic event name (use 'perf list' to list all events)
+
+ - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
+ hexadecimal event descriptor.
+
+ - a symbolically formed event like 'pmu/param1=0x3,param2/' where
+ param1 and param2 are defined as formats for the PMU in
+ /sys/bus/event_sources/devices/<pmu>/format/*
+
+ - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
+ where M, N, K are numbers (in decimal, hex, octal format).
+ Acceptable values for each of 'config', 'config1' and 'config2'
+ parameters are defined by corresponding entries in
+ /sys/bus/event_sources/devices/<pmu>/format/*
-i::
--no-inherit::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 83e2887f91a3..fbbfdc39271d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -6,12 +6,15 @@ tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
tools/include/asm/bug.h
+tools/include/asm-generic/bitops/arch_hweight.h
tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/const_hweight.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/hweight.h
tools/include/asm-generic/bitops.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
@@ -19,6 +22,8 @@ tools/include/linux/export.h
tools/include/linux/hash.h
tools/include/linux/log2.h
tools/include/linux/types.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
include/asm-generic/bitops/fls64.h
include/asm-generic/bitops/__fls.h
include/asm-generic/bitops/fls.h
@@ -29,6 +34,7 @@ include/linux/list.h
include/linux/hash.h
include/linux/stringify.h
lib/find_next_bit.c
+lib/hweight.c
lib/rbtree.c
include/linux/swab.h
arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 67a03a825b3c..aa6a50447c32 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -232,12 +232,15 @@ LIB_H += ../include/linux/hash.h
LIB_H += ../../include/linux/stringify.h
LIB_H += util/include/linux/bitmap.h
LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/arch_hweight.h
LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/const_hweight.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/hweight.h
LIB_H += ../include/asm-generic/bitops.h
LIB_H += ../include/linux/compiler.h
LIB_H += ../include/linux/log2.h
@@ -255,7 +258,6 @@ LIB_H += util/include/linux/linkage.h
LIB_H += util/include/asm/asm-offsets.h
LIB_H += ../include/asm/bug.h
LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
LIB_H += util/include/asm/swab.h
LIB_H += util/include/asm/system.h
LIB_H += util/include/asm/uaccess.h
@@ -462,10 +464,12 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
# Benchmark modules
BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-ifeq ($(RAW_ARCH),x86_64)
+ifeq ($(ARCH), x86)
+ifeq ($(IS_64_BIT), 1)
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-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/futex-hash.o
BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
@@ -743,6 +747,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.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)"' $<
+$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(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)"' $<
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3bb50eac5542..0c370f81e002 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
return NULL;
}
- result = dwarf_cfi_addrframe(cfi, pc, &frame);
+ result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
if (result) {
pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
return NULL;
@@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
return NULL;
}
- result = dwarf_cfi_addrframe(cfi, pc, &frame);
+ result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
if (result) {
pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
return NULL;
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
* yet used)
* -1 in case of errors
*/
-static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
{
int rc = -1;
Dwfl *dwfl;
@@ -155,6 +155,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
Dwarf_Addr start = pc;
Dwarf_Addr end = pc;
bool signalp;
+ const char *exec_file = dso->long_name;
dwfl = dso->dwfl;
@@ -165,8 +166,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
return -1;
}
- if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
- pr_debug("dwfl_report_offline() failed %s\n",
+ mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1,
+ map_start, false);
+ if (!mod) {
+ pr_debug("dwfl_report_elf() failed %s\n",
dwarf_errmsg(-1));
/*
* We normally cache the DWARF debug info and never
@@ -256,10 +259,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
return skip_slot;
}
- rc = check_return_addr(dso, ip);
+ rc = check_return_addr(dso, al.map->start, ip);
- pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
- dso->long_name, chain->nr, ip, rc);
+ pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+ dso->long_name, al.sym->name, ip, rc);
if (rc == 0) {
/*
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 71f2844cf97f..7ed22ff1e1ac 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -68,4 +68,17 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
val, opflags);
}
+#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
+#include <pthread.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
+ size_t cpusetsize,
+ cpu_set_t *cpuset)
+{
+ attr = attr;
+ cpusetsize = cpusetsize;
+ cpuset = cpuset;
+ return 0;
+}
+#endif
+
#endif /* _FUTEX_H */
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 07a8d7646a15..005cc283790c 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -19,12 +19,12 @@
#include <stdlib.h>
#include <signal.h>
#include <sys/wait.h>
-#include <linux/unistd.h>
#include <string.h>
#include <errno.h>
#include <assert.h>
#include <sys/time.h>
#include <sys/types.h>
+#include <sys/syscall.h>
#include <pthread.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e7417fe97a97..747f86103599 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
if (nr_samples > 0) {
total_nr_samples += nr_samples;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (symbol_conf.event_group &&
!perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 77d5cae54c6a..50e6b66aea1f 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -236,10 +236,10 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
if (errno == ENOENT)
return false;
- pr_warning("Problems with %s file, consider removing it from the cache\n",
+ pr_warning("Problems with %s file, consider removing it from the cache\n",
filename);
} else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) {
- pr_warning("Problems with %s file, consider removing it from the cache\n",
+ pr_warning("Problems with %s file, consider removing it from the cache\n",
filename);
}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1ce425d101a9..74aada554b12 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -390,6 +390,15 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
}
}
+static struct data__file *fmt_to_data_file(struct perf_hpp_fmt *fmt)
+{
+ struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt);
+ void *ptr = dfmt - dfmt->idx;
+ struct data__file *d = container_of(ptr, struct data__file, fmt);
+
+ return d;
+}
+
static struct hist_entry*
get_pair_data(struct hist_entry *he, struct data__file *d)
{
@@ -407,8 +416,7 @@ get_pair_data(struct hist_entry *he, struct data__file *d)
static struct hist_entry*
get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt)
{
- void *ptr = dfmt - dfmt->idx;
- struct data__file *d = container_of(ptr, struct data__file, fmt);
+ struct data__file *d = fmt_to_data_file(&dfmt->fmt);
return get_pair_data(he, d);
}
@@ -430,7 +438,7 @@ static void hists__baseline_only(struct hists *hists)
next = rb_next(&he->rb_node_in);
if (!hist_entry__next_pair(he)) {
rb_erase(&he->rb_node_in, root);
- hist_entry__free(he);
+ hist_entry__delete(he);
}
}
}
@@ -448,26 +456,30 @@ static void hists__precompute(struct hists *hists)
next = rb_first(root);
while (next != NULL) {
struct hist_entry *he, *pair;
+ struct data__file *d;
+ int i;
he = rb_entry(next, struct hist_entry, rb_node_in);
next = rb_next(&he->rb_node_in);
- pair = get_pair_data(he, &data__files[sort_compute]);
- if (!pair)
- continue;
+ data__for_each_file_new(i, d) {
+ pair = get_pair_data(he, d);
+ if (!pair)
+ continue;
- switch (compute) {
- case COMPUTE_DELTA:
- compute_delta(he, pair);
- break;
- case COMPUTE_RATIO:
- compute_ratio(he, pair);
- break;
- case COMPUTE_WEIGHTED_DIFF:
- compute_wdiff(he, pair);
- break;
- default:
- BUG_ON(1);
+ switch (compute) {
+ case COMPUTE_DELTA:
+ compute_delta(he, pair);
+ break;
+ case COMPUTE_RATIO:
+ compute_ratio(he, pair);
+ break;
+ case COMPUTE_WEIGHTED_DIFF:
+ compute_wdiff(he, pair);
+ break;
+ default:
+ BUG_ON(1);
+ }
}
}
}
@@ -517,7 +529,7 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
static int64_t
hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
- int c)
+ int c, int sort_idx)
{
bool pairs_left = hist_entry__has_pairs(left);
bool pairs_right = hist_entry__has_pairs(right);
@@ -529,8 +541,8 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
if (!pairs_left || !pairs_right)
return pairs_left ? -1 : 1;
- p_left = get_pair_data(left, &data__files[sort_compute]);
- p_right = get_pair_data(right, &data__files[sort_compute]);
+ p_left = get_pair_data(left, &data__files[sort_idx]);
+ p_right = get_pair_data(right, &data__files[sort_idx]);
if (!p_left && !p_right)
return 0;
@@ -545,55 +557,103 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
return __hist_entry__cmp_compute(p_left, p_right, c);
}
-static void insert_hist_entry_by_compute(struct rb_root *root,
- struct hist_entry *he,
- int c)
+static int64_t
+hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
+ int c, int sort_idx)
{
- struct rb_node **p = &root->rb_node;
- struct rb_node *parent = NULL;
- struct hist_entry *iter;
-
- while (*p != NULL) {
- parent = *p;
- iter = rb_entry(parent, struct hist_entry, rb_node);
- if (hist_entry__cmp_compute(he, iter, c) < 0)
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
+ struct hist_entry *p_right, *p_left;
+
+ p_left = get_pair_data(left, &data__files[sort_idx]);
+ p_right = get_pair_data(right, &data__files[sort_idx]);
+
+ if (!p_left && !p_right)
+ return 0;
+
+ if (!p_left || !p_right)
+ return p_left ? -1 : 1;
+
+ if (c != COMPUTE_DELTA) {
+ /*
+ * The delta can be computed without the baseline, but
+ * others are not. Put those entries which have no
+ * values below.
+ */
+ if (left->dummy && right->dummy)
+ return 0;
+
+ if (left->dummy || right->dummy)
+ return left->dummy ? 1 : -1;
}
- rb_link_node(&he->rb_node, parent, p);
- rb_insert_color(&he->rb_node, root);
+ return __hist_entry__cmp_compute(p_left, p_right, c);
}
-static void hists__compute_resort(struct hists *hists)
+static int64_t
+hist_entry__cmp_nop(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left __maybe_unused,
+ struct hist_entry *right __maybe_unused)
{
- struct rb_root *root;
- struct rb_node *next;
+ return 0;
+}
- if (sort__need_collapse)
- root = &hists->entries_collapsed;
- else
- root = hists->entries_in;
+static int64_t
+hist_entry__cmp_baseline(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ if (left->stat.period == right->stat.period)
+ return 0;
+ return left->stat.period > right->stat.period ? 1 : -1;
+}
- hists->entries = RB_ROOT;
- next = rb_first(root);
+static int64_t
+hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct data__file *d = fmt_to_data_file(fmt);
- hists__reset_stats(hists);
- hists__reset_col_len(hists);
+ return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx);
+}
- while (next != NULL) {
- struct hist_entry *he;
+static int64_t
+hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct data__file *d = fmt_to_data_file(fmt);
- he = rb_entry(next, struct hist_entry, rb_node_in);
- next = rb_next(&he->rb_node_in);
+ return hist_entry__cmp_compute(right, left, COMPUTE_RATIO, d->idx);
+}
+
+static int64_t
+hist_entry__cmp_wdiff(struct perf_hpp_fmt *fmt,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct data__file *d = fmt_to_data_file(fmt);
- insert_hist_entry_by_compute(&hists->entries, he, compute);
- hists__inc_stats(hists, he);
+ return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF, d->idx);
+}
- if (!he->filtered)
- hists__calc_col_len(hists, he);
- }
+static int64_t
+hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA,
+ sort_compute);
+}
+
+static int64_t
+hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return hist_entry__cmp_compute_idx(right, left, COMPUTE_RATIO,
+ sort_compute);
+}
+
+static int64_t
+hist_entry__cmp_wdiff_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return hist_entry__cmp_compute_idx(right, left, COMPUTE_WEIGHTED_DIFF,
+ sort_compute);
}
static void hists__process(struct hists *hists)
@@ -601,12 +661,8 @@ static void hists__process(struct hists *hists)
if (show_baseline_only)
hists__baseline_only(hists);
- if (sort_compute) {
- hists__precompute(hists);
- hists__compute_resort(hists);
- } else {
- hists__output_resort(hists);
- }
+ hists__precompute(hists);
+ hists__output_resort(hists, NULL);
hists__fprintf(hists, true, 0, 0, 0, stdout);
}
@@ -805,7 +861,7 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
char pfmt[20] = " ";
if (!pair)
- goto dummy_print;
+ goto no_print;
switch (comparison_method) {
case COMPUTE_DELTA:
@@ -814,8 +870,6 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
else
diff = compute_delta(he, pair);
- if (fabs(diff) < 0.01)
- goto dummy_print;
scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
return percent_color_snprintf(hpp->buf, hpp->size,
pfmt, diff);
@@ -847,6 +901,9 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
}
dummy_print:
return scnprintf(hpp->buf, hpp->size, "%*s",
+ dfmt->header_width, "N/A");
+no_print:
+ return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, pfmt);
}
@@ -896,14 +953,15 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
else
diff = compute_delta(he, pair);
- if (fabs(diff) >= 0.01)
- scnprintf(buf, size, "%+4.2F%%", diff);
+ scnprintf(buf, size, "%+4.2F%%", diff);
break;
case PERF_HPP_DIFF__RATIO:
/* No point for ratio number if we are dummy.. */
- if (he->dummy)
+ if (he->dummy) {
+ scnprintf(buf, size, "N/A");
break;
+ }
if (pair->diff.computed)
ratio = pair->diff.period_ratio;
@@ -916,8 +974,10 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
case PERF_HPP_DIFF__WEIGHTED_DIFF:
/* No point for wdiff number if we are dummy.. */
- if (he->dummy)
+ if (he->dummy) {
+ scnprintf(buf, size, "N/A");
break;
+ }
if (pair->diff.computed)
wdiff = pair->diff.wdiff;
@@ -1038,32 +1098,41 @@ static void data__hpp_register(struct data__file *d, int idx)
fmt->header = hpp__header;
fmt->width = hpp__width;
fmt->entry = hpp__entry_global;
+ fmt->cmp = hist_entry__cmp_nop;
+ fmt->collapse = hist_entry__cmp_nop;
/* TODO more colors */
switch (idx) {
case PERF_HPP_DIFF__BASELINE:
fmt->color = hpp__color_baseline;
+ fmt->sort = hist_entry__cmp_baseline;
break;
case PERF_HPP_DIFF__DELTA:
fmt->color = hpp__color_delta;
+ fmt->sort = hist_entry__cmp_delta;
break;
case PERF_HPP_DIFF__RATIO:
fmt->color = hpp__color_ratio;
+ fmt->sort = hist_entry__cmp_ratio;
break;
case PERF_HPP_DIFF__WEIGHTED_DIFF:
fmt->color = hpp__color_wdiff;
+ fmt->sort = hist_entry__cmp_wdiff;
break;
default:
+ fmt->sort = hist_entry__cmp_nop;
break;
}
init_header(d, dfmt);
perf_hpp__column_register(fmt);
+ perf_hpp__register_sort_field(fmt);
}
-static void ui_init(void)
+static int ui_init(void)
{
struct data__file *d;
+ struct perf_hpp_fmt *fmt;
int i;
data__for_each_file(i, d) {
@@ -1093,6 +1162,46 @@ static void ui_init(void)
data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD :
PERF_HPP_DIFF__PERIOD_BASELINE);
}
+
+ if (!sort_compute)
+ return 0;
+
+ /*
+ * Prepend an fmt to sort on columns at 'sort_compute' first.
+ * This fmt is added only to the sort list but not to the
+ * output fields list.
+ *
+ * Note that this column (data) can be compared twice - one
+ * for this 'sort_compute' fmt and another for the normal
+ * diff_hpp_fmt. But it shouldn't a problem as most entries
+ * will be sorted out by first try or baseline and comparing
+ * is not a costly operation.
+ */
+ fmt = zalloc(sizeof(*fmt));
+ if (fmt == NULL) {
+ pr_err("Memory allocation failed\n");
+ return -1;
+ }
+
+ fmt->cmp = hist_entry__cmp_nop;
+ fmt->collapse = hist_entry__cmp_nop;
+
+ switch (compute) {
+ case COMPUTE_DELTA:
+ fmt->sort = hist_entry__cmp_delta_idx;
+ break;
+ case COMPUTE_RATIO:
+ fmt->sort = hist_entry__cmp_ratio_idx;
+ break;
+ case COMPUTE_WEIGHTED_DIFF:
+ fmt->sort = hist_entry__cmp_wdiff_idx;
+ break;
+ default:
+ BUG_ON(1);
+ }
+
+ list_add(&fmt->sort_list, &perf_hpp__sort_list);
+ return 0;
}
static int data_init(int argc, const char **argv)
@@ -1158,7 +1267,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
if (data_init(argc, argv) < 0)
return -1;
- ui_init();
+ if (ui_init() < 0)
+ return -1;
sort__mode = SORT_MODE__DIFF;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 84df2deed988..a13641e066f5 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -343,6 +343,7 @@ static int __cmd_inject(struct perf_inject *inject)
int ret = -EINVAL;
struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
+ int fd = perf_data_file__fd(file_out);
signal(SIGINT, sig_handler);
@@ -376,7 +377,7 @@ static int __cmd_inject(struct perf_inject *inject)
}
if (!file_out->is_pipe)
- lseek(file_out->fd, session->header.data_offset, SEEK_SET);
+ lseek(fd, session->header.data_offset, SEEK_SET);
ret = perf_session__process_events(session, &inject->tool);
@@ -385,7 +386,7 @@ static int __cmd_inject(struct perf_inject *inject)
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
session->header.data_size = inject->bytes_written;
- perf_session__write_header(session, session->evlist, file_out->fd, true);
+ perf_session__write_header(session, session->evlist, fd, true);
}
return ret;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 011195e38f21..198f3c3aff95 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,7 +19,9 @@
int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
{
int i;
- const struct option list_options[] = {
+ bool raw_dump = false;
+ struct option list_options[] = {
+ OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
OPT_END()
};
const char * const list_usage[] = {
@@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
+ set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN);
+
argc = parse_options(argc, argv, list_options, list_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
setup_pager();
+ if (raw_dump) {
+ print_events(NULL, true);
+ return 0;
+ }
+
if (argc == 0) {
print_events(NULL, false);
return 0;
@@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
print_hwcache_events(NULL, false);
else if (strcmp(argv[i], "pmu") == 0)
print_pmu_events(NULL, false);
- else if (strcmp(argv[i], "--raw-dump") == 0)
- print_events(NULL, true);
else {
char *sep = strchr(argv[i], ':'), *s;
int sep_idx;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 24db6ffe2957..9b5663950a4d 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,44 +7,47 @@
#include "util/session.h"
#include "util/data.h"
-#define MEM_OPERATION_LOAD "load"
-#define MEM_OPERATION_STORE "store"
-
-static const char *mem_operation = MEM_OPERATION_LOAD;
+#define MEM_OPERATION_LOAD 0x1
+#define MEM_OPERATION_STORE 0x2
struct perf_mem {
struct perf_tool tool;
char const *input_name;
bool hide_unresolved;
bool dump_raw;
+ int operation;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
-static int __cmd_record(int argc, const char **argv)
+static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
{
int rec_argc, i = 0, j;
const char **rec_argv;
- char event[64];
int ret;
- rec_argc = argc + 4;
+ rec_argc = argc + 7; /* max number of arguments */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (!rec_argv)
return -1;
- rec_argv[i++] = strdup("record");
- if (!strcmp(mem_operation, MEM_OPERATION_LOAD))
- rec_argv[i++] = strdup("-W");
- rec_argv[i++] = strdup("-d");
- rec_argv[i++] = strdup("-e");
+ rec_argv[i++] = "record";
- if (strcmp(mem_operation, MEM_OPERATION_LOAD))
- sprintf(event, "cpu/mem-stores/pp");
- else
- sprintf(event, "cpu/mem-loads/pp");
+ if (mem->operation & MEM_OPERATION_LOAD)
+ rec_argv[i++] = "-W";
+
+ rec_argv[i++] = "-d";
+
+ if (mem->operation & MEM_OPERATION_LOAD) {
+ rec_argv[i++] = "-e";
+ rec_argv[i++] = "cpu/mem-loads/pp";
+ }
+
+ if (mem->operation & MEM_OPERATION_STORE) {
+ rec_argv[i++] = "-e";
+ rec_argv[i++] = "cpu/mem-stores/pp";
+ }
- rec_argv[i++] = strdup(event);
for (j = 1; j < argc; j++, i++)
rec_argv[i] = argv[j];
@@ -162,17 +165,17 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
if (!rep_argv)
return -1;
- rep_argv[i++] = strdup("report");
- rep_argv[i++] = strdup("--mem-mode");
- rep_argv[i++] = strdup("-n"); /* display number of samples */
+ rep_argv[i++] = "report";
+ rep_argv[i++] = "--mem-mode";
+ rep_argv[i++] = "-n"; /* display number of samples */
/*
* there is no weight (cost) associated with stores, so don't print
* the column
*/
- if (strcmp(mem_operation, MEM_OPERATION_LOAD))
- rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr,"
- "dso_daddr,tlb,locked");
+ if (!(mem->operation & MEM_OPERATION_LOAD))
+ rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+ "dso_daddr,tlb,locked";
for (j = 1; j < argc; j++, i++)
rep_argv[i] = argv[j];
@@ -182,6 +185,75 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
return ret;
}
+struct mem_mode {
+ const char *name;
+ int mode;
+};
+
+#define MEM_OPT(n, m) \
+ { .name = n, .mode = (m) }
+
+#define MEM_END { .name = NULL }
+
+static const struct mem_mode mem_modes[]={
+ MEM_OPT("load", MEM_OPERATION_LOAD),
+ MEM_OPT("store", MEM_OPERATION_STORE),
+ MEM_END
+};
+
+static int
+parse_mem_ops(const struct option *opt, const char *str, int unset)
+{
+ int *mode = (int *)opt->value;
+ const struct mem_mode *m;
+ char *s, *os = NULL, *p;
+ int ret = -1;
+
+ if (unset)
+ return 0;
+
+ /* str may be NULL in case no arg is passed to -t */
+ if (str) {
+ /* because str is read-only */
+ s = os = strdup(str);
+ if (!s)
+ return -1;
+
+ /* reset mode */
+ *mode = 0;
+
+ for (;;) {
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ for (m = mem_modes; m->name; m++) {
+ if (!strcasecmp(s, m->name))
+ break;
+ }
+ if (!m->name) {
+ fprintf(stderr, "unknown sampling op %s,"
+ " check man page\n", s);
+ goto error;
+ }
+
+ *mode |= m->mode;
+
+ if (!p)
+ break;
+
+ s = p + 1;
+ }
+ }
+ ret = 0;
+
+ if (*mode == 0)
+ *mode = MEM_OPERATION_LOAD;
+error:
+ free(os);
+ return ret;
+}
+
int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct stat st;
@@ -197,10 +269,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
.ordered_events = true,
},
.input_name = "perf.data",
+ /*
+ * default to both load an store sampling
+ */
+ .operation = MEM_OPERATION_LOAD | MEM_OPERATION_STORE,
};
const struct option mem_options[] = {
- OPT_STRING('t', "type", &mem_operation,
- "type", "memory operations(load/store)"),
+ OPT_CALLBACK('t', "type", &mem.operation,
+ "type", "memory operations(load,store) Default load,store",
+ parse_mem_ops),
OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
"dump raw samples in ASCII"),
OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
@@ -225,7 +302,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
+ if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
usage_with_options(mem_usage, mem_options);
if (!mem.input_name || !strlen(mem.input_name)) {
@@ -236,7 +313,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
}
if (!strncmp(argv[0], "rec", 3))
- return __cmd_record(argc, argv);
+ return __cmd_record(argc, argv, &mem);
else if (!strncmp(argv[0], "rep", 3))
return report_events(argc, argv, &mem);
else
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8648c6d3003d..404ab3434052 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -190,16 +190,30 @@ out:
return rc;
}
+static int process_sample_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine)
+{
+ struct record *rec = container_of(tool, struct record, tool);
+
+ rec->samples++;
+
+ return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
+}
+
static int process_buildids(struct record *rec)
{
struct perf_data_file *file = &rec->file;
struct perf_session *session = rec->session;
- u64 start = session->header.data_offset;
- u64 size = lseek(file->fd, 0, SEEK_CUR);
+ u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
if (size == 0)
return 0;
+ file->size = size;
+
/*
* During this process, it'll load kernel map and replace the
* dso->long_name to a real pathname it found. In this case
@@ -211,9 +225,7 @@ static int process_buildids(struct record *rec)
*/
symbol_conf.ignore_vmlinux_buildid = true;
- return __perf_session__process_events(session, start,
- size - start,
- size, &build_id__mark_dso_hit_ops);
+ return perf_session__process_events(session, &rec->tool);
}
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
@@ -322,6 +334,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
struct perf_data_file *file = &rec->file;
struct perf_session *session;
bool disabled = false, draining = false;
+ int fd;
rec->progname = argv[0];
@@ -336,6 +349,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
return -1;
}
+ fd = perf_data_file__fd(file);
rec->session = session;
record__init_features(rec);
@@ -360,12 +374,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
if (file->is_pipe) {
- err = perf_header__write_pipe(file->fd);
+ err = perf_header__write_pipe(fd);
if (err < 0)
goto out_child;
} else {
- err = perf_session__write_header(session, rec->evlist,
- file->fd, false);
+ err = perf_session__write_header(session, rec->evlist, fd, false);
if (err < 0)
goto out_child;
}
@@ -397,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
* return this more properly and also
* propagate errors that now are calling die()
*/
- err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
+ err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
@@ -504,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
goto out_child;
}
- if (!quiet) {
+ if (!quiet)
fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
- /*
- * Approximate RIP event size: 24 bytes.
- */
- fprintf(stderr,
- "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
- (double)rec->bytes_written / 1024.0 / 1024.0,
- file->path,
- rec->bytes_written / 24);
- }
-
out_child:
if (forks) {
int exit_status;
@@ -535,13 +538,29 @@ out_child:
} else
status = err;
+ /* this will be recalculated during process_buildids() */
+ rec->samples = 0;
+
if (!err && !file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
if (!rec->no_buildid)
process_buildids(rec);
- perf_session__write_header(rec->session, rec->evlist,
- file->fd, true);
+ perf_session__write_header(rec->session, rec->evlist, fd, true);
+ }
+
+ if (!err && !quiet) {
+ char samples[128];
+
+ if (rec->samples)
+ scnprintf(samples, sizeof(samples),
+ " (%" PRIu64 " samples)", rec->samples);
+ else
+ samples[0] = '\0';
+
+ fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n",
+ perf_data_file__size(file) / 1024.0 / 1024.0,
+ file->path, samples);
}
out_delete_session:
@@ -720,6 +739,13 @@ static struct record record = {
.default_per_cpu = true,
},
},
+ .tool = {
+ .sample = process_sample_event,
+ .fork = perf_event__process_fork,
+ .comm = perf_event__process_comm,
+ .mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
+ },
};
#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 39367609c707..2f91094e228b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -86,17 +86,6 @@ static int report__config(const char *var, const char *value, void *cb)
return perf_default_config(var, value, cb);
}
-static void report__inc_stats(struct report *rep, struct hist_entry *he)
-{
- /*
- * The @he is either of a newly created one or an existing one
- * merging current sample. We only want to count a new one so
- * checking ->nr_events being 1.
- */
- if (he->stat.nr_events == 1)
- rep->nr_entries++;
-}
-
static int hist_iter__report_callback(struct hist_entry_iter *iter,
struct addr_location *al, bool single,
void *arg)
@@ -108,8 +97,6 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
struct mem_info *mi;
struct branch_info *bi;
- report__inc_stats(rep, he);
-
if (!ui__has_annotation())
return 0;
@@ -457,6 +444,19 @@ static void report__collapse_hists(struct report *rep)
ui_progress__finish();
}
+static void report__output_resort(struct report *rep)
+{
+ struct ui_progress prog;
+ struct perf_evsel *pos;
+
+ ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
+
+ evlist__for_each(rep->session->evlist, pos)
+ hists__output_resort(evsel__hists(pos), &prog);
+
+ ui_progress__finish();
+}
+
static int __cmd_report(struct report *rep)
{
int ret;
@@ -486,6 +486,9 @@ static int __cmd_report(struct report *rep)
report__warn_kptr_restrict(rep);
+ evlist__for_each(session->evlist, pos)
+ rep->nr_entries += evsel__hists(pos)->nr_entries;
+
if (use_browser == 0) {
if (verbose > 3)
perf_session__fprintf(session, stdout);
@@ -505,13 +508,20 @@ static int __cmd_report(struct report *rep)
if (session_done())
return 0;
+ /*
+ * recalculate number of entries after collapsing since it
+ * might be changed during the collapse phase.
+ */
+ rep->nr_entries = 0;
+ evlist__for_each(session->evlist, pos)
+ rep->nr_entries += evsel__hists(pos)->nr_entries;
+
if (rep->nr_entries == 0) {
ui__error("The %s file has no samples!\n", file->path);
return 0;
}
- evlist__for_each(session->evlist, pos)
- hists__output_resort(evsel__hists(pos));
+ report__output_resort(rep);
return report__browse_hists(rep);
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 891086376381..e598e4e98170 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1730,7 +1730,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
"detailed run - start a lot of events"),
OPT_BOOLEAN('S', "sync", &sync_run,
"call sync() before starting a run"),
- OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
+ OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
"print large numbers with thousands\' separators",
stat__set_big_num),
OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0aa7747ff139..c4c7eac69de4 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -66,7 +66,6 @@
#include <sys/utsname.h>
#include <sys/mman.h>
-#include <linux/unistd.h>
#include <linux/types.h>
static volatile int done;
@@ -166,7 +165,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
err ? "[unknown]" : uts.release, perf_version_string);
if (use_browser <= 0)
sleep(5);
-
+
map->erange_warned = true;
}
@@ -285,7 +284,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
}
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
hists__output_recalc_col_len(hists, top->print_entries - printed);
putchar('\n');
@@ -554,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg)
}
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
}
static void *display_thread_tui(void *arg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index badfabc6a01f..7e935f1083ec 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -929,66 +929,66 @@ static struct syscall_fmt {
.arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
{ .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), },
{ .name = "close", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
{ .name = "connect", .errmsg = true, },
{ .name = "dup", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "dup2", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "dup3", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
{ .name = "eventfd2", .errmsg = true,
.arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
{ .name = "faccessat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "fadvise64", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fallocate", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchdir", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchmod", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchmodat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "fchown", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchownat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "fcntl", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[1] = SCA_STRARRAY, /* cmd */ },
.arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
{ .name = "fdatasync", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "flock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[1] = SCA_FLOCK, /* cmd */ }, },
{ .name = "fsetxattr", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fstat", .errmsg = true, .alias = "newfstat",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fstatat", .errmsg = true, .alias = "newfstatat",
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "fstatfs", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fsync", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "ftruncate", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "futex", .errmsg = true,
.arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
{ .name = "futimesat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "getdents", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "getdents64", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "ioctl", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
@@ -1002,7 +1002,7 @@ static struct syscall_fmt {
{ .name = "kill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "linkat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "lseek", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[2] = SCA_STRARRAY, /* whence */ },
@@ -1012,9 +1012,9 @@ static struct syscall_fmt {
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MADV_BHV, /* behavior */ }, },
{ .name = "mkdirat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "mknodat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "mlock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mlockall", .errmsg = true,
@@ -1036,9 +1036,9 @@ static struct syscall_fmt {
{ .name = "munmap", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "name_to_handle_at", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "newfstatat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "open", .errmsg = true,
.arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "open_by_handle_at", .errmsg = true,
@@ -1052,20 +1052,20 @@ static struct syscall_fmt {
{ .name = "poll", .errmsg = true, .timeout = true, },
{ .name = "ppoll", .errmsg = true, .timeout = true, },
{ .name = "pread", .errmsg = true, .alias = "pread64",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "preadv", .errmsg = true, .alias = "pread",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
{ .name = "pwrite", .errmsg = true, .alias = "pwrite64",
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "pwritev", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "read", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "readlinkat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "readv", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "recvfrom", .errmsg = true,
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "recvmmsg", .errmsg = true,
@@ -1073,7 +1073,7 @@ static struct syscall_fmt {
{ .name = "recvmsg", .errmsg = true,
.arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "renameat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "rt_sigaction", .errmsg = true,
.arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
{ .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), },
@@ -1091,7 +1091,7 @@ static struct syscall_fmt {
{ .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "shutdown", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "socket", .errmsg = true,
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
[1] = SCA_SK_TYPE, /* type */ },
@@ -1102,7 +1102,7 @@ static struct syscall_fmt {
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
{ .name = "stat", .errmsg = true, .alias = "newstat", },
{ .name = "symlinkat", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+ .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "tgkill", .errmsg = true,
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
{ .name = "tkill", .errmsg = true,
@@ -1113,9 +1113,9 @@ static struct syscall_fmt {
{ .name = "utimensat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
{ .name = "write", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "writev", .errmsg = true,
- .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+ .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
};
static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1191,7 +1191,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
if (thread__priv(thread) == NULL)
thread__set_priv(thread, thread_trace__new());
-
+
if (thread__priv(thread) == NULL)
goto fail;
@@ -2056,23 +2056,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
if (trace->trace_syscalls &&
perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
trace__sys_exit))
- goto out_error_tp;
+ goto out_error_raw_syscalls;
if (trace->trace_syscalls)
perf_evlist__add_vfs_getname(evlist);
if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
- perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ))
- goto out_error_tp;
+ perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) {
+ goto out_error_mem;
+ }
if ((trace->trace_pgfaults & TRACE_PFMIN) &&
perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
- goto out_error_tp;
+ goto out_error_mem;
if (trace->sched &&
- perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
- trace__sched_stat_runtime))
- goto out_error_tp;
+ perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
+ trace__sched_stat_runtime))
+ goto out_error_sched_stat_runtime;
err = perf_evlist__create_maps(evlist, &trace->opts.target);
if (err < 0) {
@@ -2202,8 +2203,12 @@ out:
{
char errbuf[BUFSIZ];
-out_error_tp:
- perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
+out_error_sched_stat_runtime:
+ debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
+ goto out_error;
+
+out_error_raw_syscalls:
+ debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)");
goto out_error;
out_error_mmap:
@@ -2217,6 +2222,9 @@ out_error:
fprintf(trace->output, "%s\n", errbuf);
goto out_delete_evlist;
}
+out_error_mem:
+ fprintf(trace->output, "Not enough memory to run!\n");
+ goto out_delete_evlist;
}
static int trace__replay(struct trace *trace)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5d4b039fe1ed..cc224080b525 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -20,7 +20,7 @@ NO_PERF_REGS := 1
# Additional ARCH settings for x86
ifeq ($(ARCH),x86)
- ifeq (${IS_X86_64}, 1)
+ ifeq (${IS_64_BIT}, 1)
CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
@@ -198,6 +198,7 @@ CORE_FEATURE_TESTS = \
libpython-version \
libslang \
libunwind \
+ pthread-attr-setaffinity-np \
stackprotector-all \
timerfd \
libdw-dwarf-unwind \
@@ -226,6 +227,7 @@ VF_FEATURE_TESTS = \
libelf-getphdrnum \
libelf-mmap \
libpython-version \
+ pthread-attr-setaffinity-np \
stackprotector-all \
timerfd \
libunwind-debug-frame \
@@ -301,6 +303,10 @@ ifeq ($(feature-sync-compare-and-swap), 1)
CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
endif
+ifeq ($(feature-pthread-attr-setaffinity-np), 1)
+ CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP
+endif
+
ifndef NO_BIONIC
$(call feature_check,bionic)
ifeq ($(feature-bionic), 1)
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 851cd0172a76..ff95a68741d1 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -1,7 +1,7 @@
uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/arm.*/arm/ -e s/sa110/arm/ \
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
@@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/tile.*/tile/ )
# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
- override ARCH := x86
+ifeq ($(RAW_ARCH),i386)
+ ARCH ?= x86
endif
-ifeq ($(ARCH),x86_64)
- override ARCH := x86
- IS_X86_64 := 0
- ifeq (, $(findstring m32,$(CFLAGS)))
- IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
- RAW_ARCH := x86_64
+ifeq ($(RAW_ARCH),x86_64)
+ ARCH ?= x86
+
+ ifneq (, $(findstring m32,$(CFLAGS)))
+ RAW_ARCH := x86_32
endif
endif
-ifeq (${IS_X86_64}, 1)
+ARCH ?= $(RAW_ARCH)
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
IS_64_BIT := 1
-else ifeq ($(ARCH),x86)
- IS_64_BIT := 0
else
- IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ IS_64_BIT := 0
endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 53f19b5dbc37..42ac05aaf8ac 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -25,6 +25,7 @@ FILES= \
test-libslang.bin \
test-libunwind.bin \
test-libunwind-debug-frame.bin \
+ test-pthread-attr-setaffinity-np.bin \
test-stackprotector-all.bin \
test-timerfd.bin \
test-libdw-dwarf-unwind.bin \
@@ -47,6 +48,9 @@ test-all.bin:
test-hello.bin:
$(BUILD)
+test-pthread-attr-setaffinity-np.bin:
+ $(BUILD) -Werror -lpthread
+
test-stackprotector-all.bin:
$(BUILD) -Werror -fstack-protector-all
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 652e0098eba6..6d4d09323922 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -97,6 +97,10 @@
# include "test-zlib.c"
#undef main
+#define main main_test_pthread_attr_setaffinity_np
+# include "test-pthread_attr_setaffinity_np.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
@@ -121,6 +125,7 @@ int main(int argc, char *argv[])
main_test_libdw_dwarf_unwind();
main_test_sync_compare_and_swap(argc, argv);
main_test_zlib();
+ main_test_pthread_attr_setaffinity_np();
return 0;
}
diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
new file mode 100644
index 000000000000..0a0d3ecb4e8a
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
@@ -0,0 +1,14 @@
+#include <stdint.h>
+#include <pthread.h>
+
+int main(void)
+{
+ int ret = 0;
+ pthread_attr_t thread_attr;
+
+ pthread_attr_init(&thread_attr);
+ /* don't care abt exact args, just the API itself in libpthread */
+ ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
+
+ return ret;
+}
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index a3b13d7dc1d4..6ef68165c9db 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,7 +6,6 @@
#include <sys/syscall.h>
#include <linux/types.h>
#include <linux/perf_event.h>
-#include <asm/unistd.h>
#if defined(__i386__)
#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 790ceba6ad3f..28431d1bbcf5 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -5,7 +5,10 @@
* ANY CHANGES MADE HERE WILL BE LOST!
*
*/
-
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
#line 1 "Context.xs"
/*
* Context.xs. XS interfaces for perf script.
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index c9b4b6269b51..1091bd47adfd 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -104,7 +104,6 @@ class Event(dict):
continue
if not self.compare_data(self[t], other[t]):
log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
-
# Test file description needs to have following sections:
# [config]
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index ab28cca2cb97..0bf06bec68c7 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,6 +11,9 @@
#include "thread.h"
#include "callchain.h"
+/* For bsearch. We try to unwind functions in shared object. */
+#include <stdlib.h>
+
static int mmap_handler(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine)
mmap_handler, machine, true);
}
-#define MAX_STACK 6
+#define MAX_STACK 8
static int unwind_entry(struct unwind_entry *entry, void *arg)
{
@@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
static const char *funcs[MAX_STACK] = {
"test__arch_unwind_sample",
"unwind_thread",
+ "compare",
+ "bsearch",
"krava_3",
"krava_2",
"krava_1",
@@ -88,10 +93,37 @@ static int unwind_thread(struct thread *thread)
return err;
}
+static int global_unwind_retval = -INT_MAX;
+
+__attribute__ ((noinline))
+static int compare(void *p1, void *p2)
+{
+ /* Any possible value should be 'thread' */
+ struct thread *thread = *(struct thread **)p1;
+
+ if (global_unwind_retval == -INT_MAX)
+ global_unwind_retval = unwind_thread(thread);
+
+ return p1 - p2;
+}
+
__attribute__ ((noinline))
static int krava_3(struct thread *thread)
{
- return unwind_thread(thread);
+ struct thread *array[2] = {thread, thread};
+ void *fp = &bsearch;
+ /*
+ * make _bsearch a volatile function pointer to
+ * prevent potential optimization, which may expand
+ * bsearch and call compare directly from this function,
+ * instead of libc shared object.
+ */
+ void *(*volatile _bsearch)(void *, void *, size_t,
+ size_t, int (*)(void *, void *));
+
+ _bsearch = fp;
+ _bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+ return global_unwind_retval;
}
__attribute__ ((noinline))
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 614d5c4978ab..18619966454c 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -140,7 +140,7 @@ static void del_hist_entries(struct hists *hists)
he = rb_entry(node, struct hist_entry, rb_node);
rb_erase(node, root_out);
rb_erase(&he->rb_node_in, root_in);
- hist_entry__free(he);
+ hist_entry__delete(he);
}
}
@@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
* function since TEST_ASSERT_VAL() returns in case of failure.
*/
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("use callchain: %d, cumulate callchain: %d\n",
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
* 30.00% 10.00% perf perf [.] cmd_record
* 20.00% 0.00% bash libc [.] malloc
* 10.00% 10.00% bash [kernel] [k] page_fault
- * 10.00% 10.00% perf [kernel] [k] schedule
- * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open
+ * 10.00% 10.00% bash bash [.] xmalloc
* 10.00% 10.00% perf [kernel] [k] page_fault
- * 10.00% 10.00% perf libc [.] free
* 10.00% 10.00% perf libc [.] malloc
- * 10.00% 10.00% bash bash [.] xmalloc
+ * 10.00% 10.00% perf [kernel] [k] schedule
+ * 10.00% 10.00% perf libc [.] free
+ * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open
*/
struct result expected[] = {
{ 7000, 2000, "perf", "perf", "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
{ 3000, 1000, "perf", "perf", "cmd_record" },
{ 2000, 0, "bash", "libc", "malloc" },
{ 1000, 1000, "bash", "[kernel]", "page_fault" },
- { 1000, 1000, "perf", "[kernel]", "schedule" },
- { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" },
+ { 1000, 1000, "bash", "bash", "xmalloc" },
{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+ { 1000, 1000, "perf", "[kernel]", "schedule" },
{ 1000, 1000, "perf", "libc", "free" },
{ 1000, 1000, "perf", "libc", "malloc" },
- { 1000, 1000, "bash", "bash", "xmalloc" },
+ { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" },
};
symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
* malloc
* main
*
- * 10.00% 10.00% perf [kernel] [k] schedule
+ * 10.00% 10.00% bash bash [.] xmalloc
* |
- * --- schedule
- * run_command
+ * --- xmalloc
+ * malloc
+ * xmalloc <--- NOTE: there's a cycle
+ * malloc
+ * xmalloc
* main
*
* 10.00% 0.00% perf [kernel] [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
* run_command
* main
*
+ * 10.00% 10.00% perf [kernel] [k] schedule
+ * |
+ * --- schedule
+ * run_command
+ * main
+ *
* 10.00% 10.00% perf libc [.] free
* |
* --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
* run_command
* main
*
- * 10.00% 10.00% bash bash [.] xmalloc
- * |
- * --- xmalloc
- * malloc
- * xmalloc <--- NOTE: there's a cycle
- * malloc
- * xmalloc
- * main
- *
*/
struct result expected[] = {
{ 7000, 2000, "perf", "perf", "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
{ 3000, 1000, "perf", "perf", "cmd_record" },
{ 2000, 0, "bash", "libc", "malloc" },
{ 1000, 1000, "bash", "[kernel]", "page_fault" },
- { 1000, 1000, "perf", "[kernel]", "schedule" },
+ { 1000, 1000, "bash", "bash", "xmalloc" },
{ 1000, 0, "perf", "[kernel]", "sys_perf_event_open" },
{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+ { 1000, 1000, "perf", "[kernel]", "schedule" },
{ 1000, 1000, "perf", "libc", "free" },
{ 1000, 1000, "perf", "libc", "malloc" },
- { 1000, 1000, "bash", "bash", "xmalloc" },
};
struct callchain_result expected_callchain[] = {
{
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
{ "bash", "main" }, },
},
{
- 3, { { "[kernel]", "schedule" },
- { "perf", "run_command" },
- { "perf", "main" }, },
+ 6, { { "bash", "xmalloc" },
+ { "libc", "malloc" },
+ { "bash", "xmalloc" },
+ { "libc", "malloc" },
+ { "bash", "xmalloc" },
+ { "bash", "main" }, },
},
{
3, { { "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
{ "perf", "main" }, },
},
{
+ 3, { { "[kernel]", "schedule" },
+ { "perf", "run_command" },
+ { "perf", "main" }, },
+ },
+ {
4, { { "libc", "free" },
{ "perf", "cmd_record" },
{ "perf", "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
{ "perf", "run_command" },
{ "perf", "main" }, },
},
- {
- 6, { { "bash", "xmalloc" },
- { "libc", "malloc" },
- { "bash", "xmalloc" },
- { "libc", "malloc" },
- { "bash", "xmalloc" },
- { "bash", "main" }, },
- },
};
symbol_conf.use_callchain = true;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 74f257a81265..59e53db7914c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -138,7 +138,7 @@ int test__hists_filter(void)
struct hists *hists = evsel__hists(evsel);
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a748f2be1222..b52c9faea224 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -106,7 +106,7 @@ static void del_hist_entries(struct hists *hists)
he = rb_entry(node, struct hist_entry, rb_node);
rb_erase(node, root_out);
rb_erase(&he->rb_node_in, root_in);
- hist_entry__free(he);
+ hist_entry__delete(he);
}
}
@@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
goto out;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
goto out;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
goto out;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
goto out;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
goto out;
hists__collapse_resort(hists, NULL);
- hists__output_resort(hists);
+ hists__output_resort(hists, NULL);
if (verbose > 2) {
pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 69a71ff84e01..75709d2b17b4 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -222,7 +222,6 @@ tarpkg:
@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
echo "- $@: $$cmd" && echo $$cmd > $@ && \
( eval $$cmd ) >> $@ 2>&1
-
all: $(run) $(run_O) tarpkg
@echo OK
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7f2f51f93619..1cdab0ce00e2 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1145,6 +1145,49 @@ static int test__pinned_group(struct perf_evlist *evlist)
return 0;
}
+static int test__checkevent_breakpoint_len(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+ TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+ evsel->attr.bp_type);
+ TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 ==
+ evsel->attr.bp_len);
+
+ return 0;
+}
+
+static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+ TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W ==
+ evsel->attr.bp_type);
+ TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 ==
+ evsel->attr.bp_len);
+
+ return 0;
+}
+
+static int
+test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+ return test__checkevent_breakpoint_rw(evlist);
+}
+
static int count_tracepoints(void)
{
char events_path[PATH_MAX];
@@ -1420,6 +1463,21 @@ static struct evlist_test test__events[] = {
.check = test__pinned_group,
.id = 41,
},
+ {
+ .name = "mem:0/1",
+ .check = test__checkevent_breakpoint_len,
+ .id = 42,
+ },
+ {
+ .name = "mem:0/2:w",
+ .check = test__checkevent_breakpoint_len_w,
+ .id = 43,
+ },
+ {
+ .name = "mem:0/4:rw:u",
+ .check = test__checkevent_breakpoint_len_rw_modifier,
+ .id = 44
+ },
#if defined(__s390x__)
{
.name = "kvm-s390:kvm_s390_create_vm",
@@ -1471,7 +1529,7 @@ static int test_event(struct evlist_test *e)
} else {
ret = e->check(evlist);
}
-
+
perf_evlist__delete(evlist);
return ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 4908c648a597..30c02181e78b 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -110,7 +110,7 @@ static bool samples_same(const struct perf_sample *s1,
if (type & PERF_SAMPLE_STACK_USER) {
COMP(user_stack.size);
- if (memcmp(s1->user_stack.data, s1->user_stack.data,
+ if (memcmp(s1->user_stack.data, s2->user_stack.data,
s1->user_stack.size)) {
pr_debug("Samples differ at 'user_stack'\n");
return false;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1e0a2fd80115..9d32e3c0cfee 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -517,7 +517,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
}
annotate_browser__set_top(browser, dl, idx);
-
+
return true;
}
@@ -867,7 +867,6 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser
++browser->nr_jumps;
}
-
}
static inline int width_jumps(int n)
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e6bb04b5b09b..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
bool need_percent;
node = rb_first(root);
- need_percent = !!rb_next(node);
+ need_percent = node && rb_next(node);
while (node) {
struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index dc0d095f318c..25d608394d74 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
if (ret)
return ret;
+ if (a->thread != b->thread || !symbol_conf.use_callchain)
+ return 0;
+
ret = b->callchain->max_depth - a->callchain->max_depth;
}
return ret;
@@ -282,7 +285,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
}
#define __HPP_SORT_FN(_type, _field) \
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+ struct hist_entry *a, struct hist_entry *b) \
{ \
return __hpp__sort(a, b, he_get_##_field); \
}
@@ -309,7 +313,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
}
#define __HPP_SORT_ACC_FN(_type, _field) \
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+ struct hist_entry *a, struct hist_entry *b) \
{ \
return __hpp__sort_acc(a, b, he_get_acc_##_field); \
}
@@ -328,7 +333,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
}
#define __HPP_SORT_RAW_FN(_type, _field) \
-static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+ struct hist_entry *a, struct hist_entry *b) \
{ \
return __hpp__sort(a, b, he_get_raw_##_field); \
}
@@ -358,7 +364,8 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
HPP_RAW_FNS(samples, nr_events)
HPP_RAW_FNS(period, period)
-static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
+static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *a __maybe_unused,
struct hist_entry *b __maybe_unused)
{
return 0;
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index f34f89eb607c..717d39d3052b 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -4,12 +4,12 @@
#include <linux/types.h>
void ui_progress__finish(void);
-
+
struct ui_progress {
const char *title;
u64 curr, next, step, total;
};
-
+
void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
void ui_progress__update(struct ui_progress *p, u64 adv);
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 1c8b9afd5d6e..88f5143a5981 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -9,6 +9,7 @@
#include "../libslang.h"
char ui_helpline__last_msg[1024];
+bool tui_helpline__set;
static void tui_helpline__pop(void)
{
@@ -35,6 +36,8 @@ static int tui_helpline__show(const char *format, va_list ap)
sizeof(ui_helpline__last_msg) - backlog, format, ap);
backlog += ret;
+ tui_helpline__set = true;
+
if (ui_helpline__last_msg[backlog - 1] == '\n') {
ui_helpline__puts(ui_helpline__last_msg);
SLsmg_refresh();
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 2f612562978c..b77e1d771363 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,5 +1,8 @@
#include <signal.h>
#include <stdbool.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
#include "../../util/cache.h"
#include "../../util/debug.h"
@@ -14,6 +17,7 @@
static volatile int ui__need_resize;
extern struct perf_error_ops perf_tui_eops;
+extern bool tui_helpline__set;
extern void hist_browser__init_hpp(void);
@@ -88,6 +92,25 @@ int ui__getch(int delay_secs)
return SLkp_getkey();
}
+#ifdef HAVE_BACKTRACE_SUPPORT
+static void ui__signal_backtrace(int sig)
+{
+ void *stackdump[32];
+ size_t size;
+
+ ui__exit(false);
+ psignal(sig, "perf");
+
+ printf("-------- backtrace --------\n");
+ size = backtrace(stackdump, ARRAY_SIZE(stackdump));
+ backtrace_symbols_fd(stackdump, size, STDOUT_FILENO);
+
+ exit(0);
+}
+#else
+# define ui__signal_backtrace ui__signal
+#endif
+
static void ui__signal(int sig)
{
ui__exit(false);
@@ -122,8 +145,8 @@ int ui__init(void)
ui_browser__init();
tui_progress__init();
- signal(SIGSEGV, ui__signal);
- signal(SIGFPE, ui__signal);
+ signal(SIGSEGV, ui__signal_backtrace);
+ signal(SIGFPE, ui__signal_backtrace);
signal(SIGINT, ui__signal);
signal(SIGQUIT, ui__signal);
signal(SIGTERM, ui__signal);
@@ -137,7 +160,7 @@ out:
void ui__exit(bool wait_for_ok)
{
- if (wait_for_ok)
+ if (wait_for_ok && tui_helpline__set)
ui__question_window("Fatal Error",
ui_helpline__last_msg,
"Press any key...", 0);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79999ceaf2be..61bf9128e1f2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -177,14 +177,17 @@ static int lock__parse(struct ins_operands *ops)
goto out_free_ops;
ops->locked.ins = ins__find(name);
+ free(name);
+
if (ops->locked.ins == NULL)
goto out_free_ops;
if (!ops->locked.ins->ops)
return 0;
- if (ops->locked.ins->ops->parse)
- ops->locked.ins->ops->parse(ops->locked.ops);
+ if (ops->locked.ins->ops->parse &&
+ ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+ goto out_free_ops;
return 0;
@@ -208,6 +211,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
static void lock__delete(struct ins_operands *ops)
{
+ struct ins *ins = ops->locked.ins;
+
+ if (ins && ins->ops->free)
+ ins->ops->free(ops->locked.ops);
+ else
+ ins__delete(ops->locked.ops);
+
zfree(&ops->locked.ops);
zfree(&ops->target.raw);
zfree(&ops->target.name);
@@ -229,7 +239,7 @@ static int mov__parse(struct ins_operands *ops)
*s = '\0';
ops->source.raw = strdup(ops->raw);
*s = ',';
-
+
if (ops->source.raw == NULL)
return -1;
@@ -531,8 +541,8 @@ static void disasm_line__init_ins(struct disasm_line *dl)
if (!dl->ins->ops)
return;
- if (dl->ins->ops->parse)
- dl->ins->ops->parse(&dl->ops);
+ if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+ dl->ins = NULL;
}
static int disasm_line__parse(char *line, char **namep, char **rawp)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0784a9420528..cadbdc90a5cb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -116,11 +116,6 @@ struct annotation {
struct annotated_source *src;
};
-struct sannotation {
- struct annotation annotation;
- struct symbol symbol;
-};
-
static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
{
return (((void *)&notes->src->histograms) +
@@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
static inline struct annotation *symbol__annotation(struct symbol *sym)
{
- struct sannotation *a = container_of(sym, struct sannotation, symbol);
- return &a->annotation;
+ return (void *)sym - symbol_conf.priv_size;
}
int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 5cf9e1b5989d..d04d770d90f6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
extern char *perf_pathdup(const char *fmt, ...)
__attribute__((format (printf, 1, 2)));
+#ifndef __UCLIBC__
/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
#endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 64b377e591e4..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
return bf;
}
+
+static void free_callchain_node(struct callchain_node *node)
+{
+ struct callchain_list *list, *tmp;
+ struct callchain_node *child;
+ struct rb_node *n;
+
+ list_for_each_entry_safe(list, tmp, &node->val, list) {
+ list_del(&list->list);
+ free(list);
+ }
+
+ n = rb_first(&node->rb_root_in);
+ while (n) {
+ child = container_of(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+ rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+ free_callchain_node(child);
+ free(child);
+ }
+}
+
+void free_callchain(struct callchain_root *root)
+{
+ if (!symbol_conf.use_callchain)
+ return;
+
+ free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso);
+void free_callchain(struct callchain_root *root);
+
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index f4654183d391..55355b3d4f85 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -5,132 +5,6 @@
int perf_use_color_default = -1;
-static int parse_color(const char *name, int len)
-{
- static const char * const color_names[] = {
- "normal", "black", "red", "green", "yellow",
- "blue", "magenta", "cyan", "white"
- };
- char *end;
- int i;
-
- for (i = 0; i < (int)ARRAY_SIZE(color_names); i++) {
- const char *str = color_names[i];
- if (!strncasecmp(name, str, len) && !str[len])
- return i - 1;
- }
- i = strtol(name, &end, 10);
- if (end - name == len && i >= -1 && i <= 255)
- return i;
- return -2;
-}
-
-static int parse_attr(const char *name, int len)
-{
- static const int attr_values[] = { 1, 2, 4, 5, 7 };
- static const char * const attr_names[] = {
- "bold", "dim", "ul", "blink", "reverse"
- };
- unsigned int i;
-
- for (i = 0; i < ARRAY_SIZE(attr_names); i++) {
- const char *str = attr_names[i];
- if (!strncasecmp(name, str, len) && !str[len])
- return attr_values[i];
- }
- return -1;
-}
-
-void color_parse(const char *value, const char *var, char *dst)
-{
- color_parse_mem(value, strlen(value), var, dst);
-}
-
-void color_parse_mem(const char *value, int value_len, const char *var,
- char *dst)
-{
- const char *ptr = value;
- int len = value_len;
- int attr = -1;
- int fg = -2;
- int bg = -2;
-
- if (!strncasecmp(value, "reset", len)) {
- strcpy(dst, PERF_COLOR_RESET);
- return;
- }
-
- /* [fg [bg]] [attr] */
- while (len > 0) {
- const char *word = ptr;
- int val, wordlen = 0;
-
- while (len > 0 && !isspace(word[wordlen])) {
- wordlen++;
- len--;
- }
-
- ptr = word + wordlen;
- while (len > 0 && isspace(*ptr)) {
- ptr++;
- len--;
- }
-
- val = parse_color(word, wordlen);
- if (val >= -1) {
- if (fg == -2) {
- fg = val;
- continue;
- }
- if (bg == -2) {
- bg = val;
- continue;
- }
- goto bad;
- }
- val = parse_attr(word, wordlen);
- if (val < 0 || attr != -1)
- goto bad;
- attr = val;
- }
-
- if (attr >= 0 || fg >= 0 || bg >= 0) {
- int sep = 0;
-
- *dst++ = '\033';
- *dst++ = '[';
- if (attr >= 0) {
- *dst++ = '0' + attr;
- sep++;
- }
- if (fg >= 0) {
- if (sep++)
- *dst++ = ';';
- if (fg < 8) {
- *dst++ = '3';
- *dst++ = '0' + fg;
- } else {
- dst += sprintf(dst, "38;5;%d", fg);
- }
- }
- if (bg >= 0) {
- if (sep++)
- *dst++ = ';';
- if (bg < 8) {
- *dst++ = '4';
- *dst++ = '0' + bg;
- } else {
- dst += sprintf(dst, "48;5;%d", bg);
- }
- }
- *dst++ = 'm';
- }
- *dst = 0;
- return;
-bad:
- die("bad color value '%.*s' for variable '%s'", value_len, value, var);
-}
-
int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
{
if (value) {
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 0a594b8a0c26..38146f922c54 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -30,8 +30,6 @@ extern int perf_use_color_default;
int perf_color_default_config(const char *var, const char *value, void *cb);
int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
-void color_parse(const char *value, const char *var, char *dst);
-void color_parse_mem(const char *value, int len, const char *var, char *dst);
int color_vsnprintf(char *bf, size_t size, const char *color,
const char *fmt, va_list args);
int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 45be944d450a..c2f7d3b90966 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -532,12 +532,8 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
break;
cache_offset = offset & DSO__DATA_CACHE_MASK;
- ret = -EINVAL;
- if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
- break;
-
- ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
+ ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
if (ret <= 0)
break;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3782c82c6e44..ced92841ff97 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -139,6 +139,7 @@ struct dso {
u32 status_seen;
size_t file_size;
struct list_head open_entry;
+ u64 frame_offset;
} data;
union { /* Tool specific area */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cbab1fb77b1d..28b8ce86bf12 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1436,33 +1436,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
return printed + fprintf(fp, "\n");
}
-int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
- int err, char *buf, size_t size)
-{
- char sbuf[128];
-
- switch (err) {
- case ENOENT:
- scnprintf(buf, size, "%s",
- "Error:\tUnable to find debugfs\n"
- "Hint:\tWas your kernel was compiled with debugfs support?\n"
- "Hint:\tIs the debugfs filesystem mounted?\n"
- "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
- break;
- case EACCES:
- scnprintf(buf, size,
- "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
- "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
- debugfs_mountpoint, debugfs_mountpoint);
- break;
- default:
- scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
- break;
- }
-
- return 0;
-}
-
int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
int err, char *buf, size_t size)
{
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0ba93f67ab94..c94a9e03ecf1 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -183,7 +183,6 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
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_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);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1e90c8557ede..ea51a90e20a0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -709,6 +709,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
if (opts->sample_weight)
perf_evsel__set_sample_bit(evsel, WEIGHT);
+ attr->task = track;
attr->mmap = track;
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
@@ -797,6 +798,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
+ if (ncpus == 0 || nthreads == 0)
+ return 0;
+
if (evsel->system_wide)
nthreads = 1;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b20e40c74468..1f407f7352a7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2237,6 +2237,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
* - unique number to identify actual perf.data files
* - encode endianness of file
*/
+ ph->version = PERF_HEADER_VERSION_2;
/* check magic number with one endianness */
if (magic == __perf_magic2)
@@ -2247,7 +2248,6 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
return -1;
ph->needs_swap = true;
- ph->version = PERF_HEADER_VERSION_2;
return 0;
}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..70b48a65064c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
#include "evlist.h"
#include "evsel.h"
#include "annotate.h"
+#include "ui/progress.h"
#include <math.h>
static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -240,6 +241,20 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
return he->stat.period == 0;
}
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
+{
+ rb_erase(&he->rb_node, &hists->entries);
+
+ if (sort__need_collapse)
+ rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+
+ --hists->nr_entries;
+ if (!he->filtered)
+ --hists->nr_non_filtered_entries;
+
+ hist_entry__delete(he);
+}
+
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
{
struct rb_node *next = rb_first(&hists->entries);
@@ -257,16 +272,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
(zap_kernel && n->level != '.') ||
hists__decay_entry(hists, n)) &&
!n->used) {
- rb_erase(&n->rb_node, &hists->entries);
-
- if (sort__need_collapse)
- rb_erase(&n->rb_node_in, &hists->entries_collapsed);
-
- --hists->nr_entries;
- if (!n->filtered)
- --hists->nr_non_filtered_entries;
-
- hist_entry__free(n);
+ hists__delete_entry(hists, n);
}
}
}
@@ -280,16 +286,7 @@ void hists__delete_entries(struct hists *hists)
n = rb_entry(next, struct hist_entry, rb_node);
next = rb_next(&n->rb_node);
- rb_erase(&n->rb_node, &hists->entries);
-
- if (sort__need_collapse)
- rb_erase(&n->rb_node_in, &hists->entries_collapsed);
-
- --hists->nr_entries;
- if (!n->filtered)
- --hists->nr_non_filtered_entries;
-
- hist_entry__free(n);
+ hists__delete_entry(hists, n);
}
}
@@ -303,7 +300,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
size_t callchain_size = 0;
struct hist_entry *he;
- if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+ if (symbol_conf.use_callchain)
callchain_size = sizeof(struct callchain_root);
he = zalloc(sizeof(*he) + callchain_size);
@@ -432,6 +429,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
if (!he)
return NULL;
+ hists->nr_entries++;
+
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, hists->entries_in);
out:
@@ -736,7 +735,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
iter->he = he;
he_cache[iter->curr++] = he;
- callchain_append(he->callchain, &callchain_cursor, sample->period);
+ hist_entry__append_callchain(he, sample);
/*
* We need to re-initialize the cursor since callchain_append()
@@ -809,7 +808,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
iter->he = he;
he_cache[iter->curr++] = he;
- callchain_append(he->callchain, &cursor, sample->period);
+ if (symbol_conf.use_callchain)
+ callchain_append(he->callchain, &cursor, sample->period);
return 0;
}
@@ -913,7 +913,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
if (perf_hpp__should_skip(fmt))
continue;
- cmp = fmt->cmp(left, right);
+ cmp = fmt->cmp(fmt, left, right);
if (cmp)
break;
}
@@ -931,7 +931,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
if (perf_hpp__should_skip(fmt))
continue;
- cmp = fmt->collapse(left, right);
+ cmp = fmt->collapse(fmt, left, right);
if (cmp)
break;
}
@@ -939,12 +939,13 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
return cmp;
}
-void hist_entry__free(struct hist_entry *he)
+void hist_entry__delete(struct hist_entry *he)
{
zfree(&he->branch_info);
zfree(&he->mem_info);
zfree(&he->stat_acc);
free_srcline(he->srcline);
+ free_callchain(he->callchain);
free(he);
}
@@ -978,7 +979,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
iter->callchain,
he->callchain);
}
- hist_entry__free(he);
+ hist_entry__delete(he);
return false;
}
@@ -987,6 +988,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
else
p = &(*p)->rb_right;
}
+ hists->nr_entries++;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1026,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
if (!sort__need_collapse)
return;
+ hists->nr_entries = 0;
+
root = hists__get_rotate_entries_in(hists);
+
next = rb_first(root);
while (next) {
@@ -1056,7 +1061,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
if (perf_hpp__should_skip(fmt))
continue;
- cmp = fmt->sort(a, b);
+ cmp = fmt->sort(fmt, a, b);
if (cmp)
break;
}
@@ -1119,7 +1124,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
rb_insert_color(&he->rb_node, entries);
}
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
{
struct rb_root *root;
struct rb_node *next;
@@ -1148,6 +1153,9 @@ void hists__output_resort(struct hists *hists)
if (!n->filtered)
hists__calc_col_len(hists, n);
+
+ if (prog)
+ ui_progress__update(prog, 1);
}
}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..2b690d028907 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -119,9 +119,9 @@ int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
int hist_entry__transaction_len(void);
int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
struct hists *hists);
-void hist_entry__free(struct hist_entry *);
+void hist_entry__delete(struct hist_entry *he);
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
@@ -195,9 +195,12 @@ struct perf_hpp_fmt {
struct hist_entry *he);
int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he);
- int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b);
- int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
- int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
+ int64_t (*cmp)(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b);
+ int64_t (*collapse)(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b);
+ int64_t (*sort)(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b);
struct list_head list;
struct list_head sort_list;
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
deleted file mode 100644
index 5c1d0d099f0d..000000000000
--- a/tools/perf/util/hweight.c
+++ /dev/null
@@ -1,31 +0,0 @@
-#include <linux/bitops.h>
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-unsigned int hweight32(unsigned int w)
-{
- unsigned int res = w - ((w >> 1) & 0x55555555);
- res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
- res = (res + (res >> 4)) & 0x0F0F0F0F;
- res = res + (res >> 8);
- return (res + (res >> 16)) & 0x000000FF;
-}
-
-unsigned long hweight64(__u64 w)
-{
-#if BITS_PER_LONG == 32
- return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
-#elif BITS_PER_LONG == 64
- __u64 res = w - ((w >> 1) & 0x5555555555555555ul);
- res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
- res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
- res = res + (res >> 8);
- res = res + (res >> 16);
- return (res + (res >> 32)) & 0x00000000000000FFul;
-#endif
-}
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
deleted file mode 100644
index 36cf26d434a5..000000000000
--- a/tools/perf/util/include/asm/hweight.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PERF_HWEIGHT_H
-#define PERF_HWEIGHT_H
-
-#include <linux/types.h>
-unsigned int hweight32(unsigned int w);
-unsigned long hweight64(__u64 w);
-
-#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 94de3e48b490..1bca3a9f2b16 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
if (th != NULL) {
rb_link_node(&th->rb_node, parent, p);
rb_insert_color(&th->rb_node, &machine->threads);
- machine->last_match = th;
/*
* We have to initialize map_groups separately
@@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
* leader and that would screwed the rb tree.
*/
if (thread__init_map_groups(th, machine)) {
+ rb_erase(&th->rb_node, &machine->threads);
thread__delete(th);
return NULL;
}
+
+ machine->last_match = th;
}
return th;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 6951a9d42339..0e42438b1e59 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -116,6 +116,22 @@ struct thread;
#define map__for_each_symbol(map, pos, n) \
dso__for_each_symbol(map->dso, pos, n, map->type)
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ * that have the given name
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @filter: to use when loading the DSO
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \
+ for (pos = map__find_symbol_by_name(map, sym_name, filter); \
+ pos && strcmp(pos->name, sym_name) == 0; \
+ pos = symbol__next_by_name(pos))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos) \
+ __map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
+
typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 77b43fe43d55..7f8ec6ce2823 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -526,7 +526,7 @@ do { \
}
int parse_events_add_breakpoint(struct list_head *list, int *idx,
- void *ptr, char *type)
+ void *ptr, char *type, u64 len)
{
struct perf_event_attr attr;
@@ -536,14 +536,15 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
if (parse_breakpoint_type(type, &attr))
return -EINVAL;
- /*
- * We should find a nice way to override the access length
- * Provide some defaults for now
- */
- if (attr.bp_type == HW_BREAKPOINT_X)
- attr.bp_len = sizeof(long);
- else
- attr.bp_len = HW_BREAKPOINT_LEN_4;
+ /* Provide some defaults if len is not specified */
+ if (!len) {
+ if (attr.bp_type == HW_BREAKPOINT_X)
+ len = sizeof(long);
+ else
+ len = HW_BREAKPOINT_LEN_4;
+ }
+
+ attr.bp_len = len;
attr.type = PERF_TYPE_BREAKPOINT;
attr.sample_period = 1;
@@ -1121,7 +1122,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
return;
for_each_subsystem(sys_dir, sys_dirent, sys_next) {
- if (subsys_glob != NULL &&
+ if (subsys_glob != NULL &&
!strglobmatch(sys_dirent.d_name, subsys_glob))
continue;
@@ -1132,7 +1133,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
continue;
for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
- if (event_glob != NULL &&
+ if (event_glob != NULL &&
!strglobmatch(evt_dirent.d_name, event_glob))
continue;
@@ -1305,7 +1306,7 @@ static void print_symbol_events(const char *event_glob, unsigned type,
for (i = 0; i < max; i++, syms++) {
- if (event_glob != NULL &&
+ if (event_glob != NULL &&
!(strglobmatch(syms->symbol, event_glob) ||
(syms->alias && strglobmatch(syms->alias, event_glob))))
continue;
@@ -1366,7 +1367,7 @@ void print_events(const char *event_glob, bool name_only)
printf("\n");
printf(" %-50s [%s]\n",
- "mem:<addr>[:access]",
+ "mem:<addr>[/len][:access]",
event_type_descriptors[PERF_TYPE_BREAKPOINT]);
printf("\n");
}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index db2cf78ff0f3..ff6e1fa4111e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ struct parse_events_term {
int type_val;
int type_term;
struct list_head list;
+ bool used;
};
struct parse_events_evlist {
@@ -104,7 +105,7 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
int parse_events_add_cache(struct list_head *list, int *idx,
char *type, char *op_result1, char *op_result2);
int parse_events_add_breakpoint(struct list_head *list, int *idx,
- void *ptr, char *type);
+ void *ptr, char *type, u64 len);
int parse_events_add_pmu(struct list_head *list, int *idx,
char *pmu , struct list_head *head_config);
enum perf_pmu_event_symbol_type
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 906630bbf8eb..94eacb6c1ef7 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -159,6 +159,7 @@ branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
<mem>{
{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
: { return ':'; }
+"/" { return '/'; }
{num_dec} { return value(yyscanner, 10); }
{num_hex} { return value(yyscanner, 16); }
/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 93c4c9fbc922..72def077dbbf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -326,6 +326,28 @@ PE_NAME_CACHE_TYPE
}
event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+ struct parse_events_evlist *data = _data;
+ struct list_head *list;
+
+ ALLOC_LIST(list);
+ ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+ (void *) $2, $6, $4));
+ $$ = list;
+}
+|
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
+{
+ struct parse_events_evlist *data = _data;
+ struct list_head *list;
+
+ ALLOC_LIST(list);
+ ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+ (void *) $2, NULL, $4));
+ $$ = list;
+}
+|
PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
{
struct parse_events_evlist *data = _data;
@@ -333,7 +355,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
ALLOC_LIST(list);
ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
- (void *) $2, $4));
+ (void *) $2, $4, 0));
$$ = list;
}
|
@@ -344,7 +366,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
ALLOC_LIST(list);
ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
- (void *) $2, NULL));
+ (void *) $2, NULL, 0));
$$ = list;
}
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index f62dee7bd924..4a015f77e2b5 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -46,7 +46,7 @@ static int get_value(struct parse_opt_ctx_t *p,
return opterror(opt, "is not usable", flags);
if (opt->flags & PARSE_OPT_EXCLUSIVE) {
- if (p->excl_opt) {
+ if (p->excl_opt && p->excl_opt != opt) {
char msg[128];
if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 5c9c4947cfb4..48411674da0f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -551,31 +551,68 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
}
/*
+ * Term is a string term, and might be a param-term. Try to look up it's value
+ * in the remaining terms.
+ * - We have a term like "base-or-format-term=param-term",
+ * - We need to find the value supplied for "param-term" (with param-term named
+ * in a config string) later on in the term list.
+ */
+static int pmu_resolve_param_term(struct parse_events_term *term,
+ struct list_head *head_terms,
+ __u64 *value)
+{
+ struct parse_events_term *t;
+
+ list_for_each_entry(t, head_terms, list) {
+ if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+ if (!strcmp(t->config, term->config)) {
+ t->used = true;
+ *value = t->val.num;
+ return 0;
+ }
+ }
+ }
+
+ if (verbose)
+ printf("Required parameter '%s' not specified\n", term->config);
+
+ return -1;
+}
+
+/*
* Setup one of config[12] attr members based on the
* user input data - term parameter.
*/
static int pmu_config_term(struct list_head *formats,
struct perf_event_attr *attr,
struct parse_events_term *term,
+ struct list_head *head_terms,
bool zero)
{
struct perf_pmu_format *format;
__u64 *vp;
+ __u64 val;
+
+ /*
+ * If this is a parameter we've already used for parameterized-eval,
+ * skip it in normal eval.
+ */
+ if (term->used)
+ return 0;
/*
- * Support only for hardcoded and numnerial terms.
* Hardcoded terms should be already in, so nothing
* to be done for them.
*/
if (parse_events__is_hardcoded_term(term))
return 0;
- if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
- return -EINVAL;
-
format = pmu_find_format(formats, term->config);
- if (!format)
+ if (!format) {
+ if (verbose)
+ printf("Invalid event/parameter '%s'\n", term->config);
return -EINVAL;
+ }
switch (format->value) {
case PERF_PMU_FORMAT_VALUE_CONFIG:
@@ -592,11 +629,25 @@ static int pmu_config_term(struct list_head *formats,
}
/*
- * XXX If we ever decide to go with string values for
- * non-hardcoded terms, here's the place to translate
- * them into value.
+ * Either directly use a numeric term, or try to translate string terms
+ * using event parameters.
*/
- pmu_format_value(format->bits, term->val.num, vp, zero);
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+ val = term->val.num;
+ else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+ if (strcmp(term->val.str, "?")) {
+ if (verbose)
+ pr_info("Invalid sysfs entry %s=%s\n",
+ term->config, term->val.str);
+ return -EINVAL;
+ }
+
+ if (pmu_resolve_param_term(term, head_terms, &val))
+ return -EINVAL;
+ } else
+ return -EINVAL;
+
+ pmu_format_value(format->bits, val, vp, zero);
return 0;
}
@@ -607,9 +658,10 @@ int perf_pmu__config_terms(struct list_head *formats,
{
struct parse_events_term *term;
- list_for_each_entry(term, head_terms, list)
- if (pmu_config_term(formats, attr, term, zero))
+ list_for_each_entry(term, head_terms, list) {
+ if (pmu_config_term(formats, attr, term, head_terms, zero))
return -EINVAL;
+ }
return 0;
}
@@ -767,10 +819,36 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
set_bit(b, bits);
}
+static int sub_non_neg(int a, int b)
+{
+ if (b > a)
+ return 0;
+ return a - b;
+}
+
static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
struct perf_pmu_alias *alias)
{
- snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+ struct parse_events_term *term;
+ int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
+
+ list_for_each_entry(term, &alias->terms, list) {
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+ used += snprintf(buf + used, sub_non_neg(len, used),
+ ",%s=%s", term->config,
+ term->val.str);
+ }
+
+ if (sub_non_neg(len, used) > 0) {
+ buf[used] = '/';
+ used++;
+ }
+ if (sub_non_neg(len, used) > 0) {
+ buf[used] = '\0';
+ used++;
+ } else
+ buf[len - 1] = '\0';
+
return buf;
}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..919937eb0be2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
}
for (i = 0; i < ntevs; i++) {
- if (tevs[i].point.address) {
+ if (tevs[i].point.address && !tevs[i].point.retprobe) {
tmp = strdup(reloc_sym->name);
if (!tmp)
return -ENOMEM;
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
}
if (ntevs == 0) { /* No error but failed to find probe point. */
- pr_warning("Probe point '%s' not found.\n",
+ pr_warning("Probe point '%s' not found in debuginfo.\n",
synthesize_perf_probe_point(&pev->point));
- return -ENOENT;
+ if (need_dwarf)
+ return -ENOENT;
+ return 0;
}
/* Error path : ntevs < 0 */
pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
@@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
pr_debug("Writing event: %s\n", buf);
if (!probe_event_dry_run) {
ret = write(fd, buf, strlen(buf));
- if (ret <= 0)
+ if (ret <= 0) {
+ ret = -errno;
pr_warning("Failed to write event: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
+ }
}
free(buf);
return ret;
@@ -2189,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
return ret;
}
-static char *looking_function_name;
-static int num_matched_functions;
-
-static int probe_function_filter(struct map *map __maybe_unused,
- struct symbol *sym)
+static int find_probe_functions(struct map *map, char *name)
{
- if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
- strcmp(looking_function_name, sym->name) == 0) {
- num_matched_functions++;
- return 0;
+ int found = 0;
+ struct symbol *sym;
+
+ map__for_each_symbol_by_name(map, name, sym) {
+ if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
+ found++;
}
- return 1;
+
+ return found;
}
#define strdup_or_goto(str, label) \
@@ -2218,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
struct kmap *kmap = NULL;
struct ref_reloc_sym *reloc_sym = NULL;
struct symbol *sym;
- struct rb_node *nd;
struct probe_trace_event *tev;
struct perf_probe_point *pp = &pev->point;
struct probe_trace_point *tp;
+ int num_matched_functions;
int ret, i;
/* Init maps of given executable or kernel */
@@ -2238,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
* Load matched symbols: Since the different local symbols may have
* same name but different addresses, this lists all the symbols.
*/
- num_matched_functions = 0;
- looking_function_name = pp->function;
- ret = map__load(map, probe_function_filter);
- if (ret || num_matched_functions == 0) {
+ num_matched_functions = find_probe_functions(map, pp->function);
+ if (num_matched_functions == 0) {
pr_err("Failed to find symbol %s in %s\n", pp->function,
target ? : "kernel");
ret = -ENOENT;
@@ -2253,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
goto out;
}
- if (!pev->uprobes) {
+ if (!pev->uprobes && !pp->retprobe) {
kmap = map__kmap(map);
reloc_sym = kmap->ref_reloc_sym;
if (!reloc_sym) {
@@ -2271,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
}
ret = 0;
- map__for_each_symbol(map, sym, nd) {
+
+ map__for_each_symbol_by_name(map, pp->function, sym) {
tev = (*tevs) + ret;
tp = &tev->point;
if (ret == num_matched_functions) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
int ret = 0;
#if _ELFUTILS_PREREQ(0, 142)
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+
/* Get the call frame information from this dwarf */
- pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+ elf = dwarf_getelf(dbg->dbg);
+ if (elf == NULL)
+ return -EINVAL;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ return -EINVAL;
+
+ if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+ shdr.sh_type == SHT_PROGBITS) {
+ pf->cfi = dwarf_getcfi_elf(elf);
+ } else {
+ pf->cfi = dwarf_getcfi(dbg->dbg);
+ }
#endif
off = 0;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 16a475a7d492..6c6a6953fa93 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
util/evlist.c
util/evsel.c
util/cpumap.c
-util/hweight.c
+../../lib/hweight.c
util/thread_map.c
util/util.c
util/xyarray.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 3dda85ca50c1..d906d0ad5d40 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -768,7 +768,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
Py_DECREF(file);
goto free_list;
}
-
+
Py_DECREF(file);
}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d808a328f4dc..0c815a40a6e8 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -89,7 +89,7 @@ static void handler_call_die(const char *handler_name)
/*
* Insert val into into the dictionary and decrement the reference counter.
- * This is necessary for dictionaries since PyDict_SetItemString() does not
+ * This is necessary for dictionaries since PyDict_SetItemString() does not
* steal a reference, as opposed to PyTuple_SetItem().
*/
static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5f0e05a76c05..0baf75f12b7c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -274,7 +274,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
if (tool->id_index == NULL)
tool->id_index = process_id_index_stub;
}
-
+
static void swap_sample_id_all(union perf_event *event, void *data)
{
void *end = (void *) event + event->header.size;
@@ -1251,9 +1251,9 @@ fetch_mmaped_event(struct perf_session *session,
#define NUM_MMAPS 128
#endif
-int __perf_session__process_events(struct perf_session *session,
- u64 data_offset, u64 data_size,
- u64 file_size, struct perf_tool *tool)
+static int __perf_session__process_events(struct perf_session *session,
+ u64 data_offset, u64 data_size,
+ u64 file_size, struct perf_tool *tool)
{
int fd = perf_data_file__fd(session->file);
u64 head, page_offset, file_offset, file_pos, size;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dc26ebf60fe4..6d663dc76404 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -49,9 +49,6 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
union perf_event **event_ptr,
struct perf_sample *sample);
-int __perf_session__process_events(struct perf_session *session,
- u64 data_offset, u64 data_size, u64 size,
- struct perf_tool *tool);
int perf_session__process_events(struct perf_session *session,
struct perf_tool *tool);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 9139dda9f9a3..7a39c1ed8d37 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1304,6 +1304,37 @@ static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
}
+static int64_t __sort__hpp_cmp(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b)
+{
+ struct hpp_sort_entry *hse;
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ return hse->se->se_cmp(a, b);
+}
+
+static int64_t __sort__hpp_collapse(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b)
+{
+ struct hpp_sort_entry *hse;
+ int64_t (*collapse_fn)(struct hist_entry *, struct hist_entry *);
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ collapse_fn = hse->se->se_collapse ?: hse->se->se_cmp;
+ return collapse_fn(a, b);
+}
+
+static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
+ struct hist_entry *a, struct hist_entry *b)
+{
+ struct hpp_sort_entry *hse;
+ int64_t (*sort_fn)(struct hist_entry *, struct hist_entry *);
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ sort_fn = hse->se->se_sort ?: hse->se->se_cmp;
+ return sort_fn(a, b);
+}
+
static struct hpp_sort_entry *
__sort_dimension__alloc_hpp(struct sort_dimension *sd)
{
@@ -1322,9 +1353,9 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
hse->hpp.entry = __sort__hpp_entry;
hse->hpp.color = NULL;
- hse->hpp.cmp = sd->entry->se_cmp;
- hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
- hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse;
+ hse->hpp.cmp = __sort__hpp_cmp;
+ hse->hpp.collapse = __sort__hpp_collapse;
+ hse->hpp.sort = __sort__hpp_sort;
INIT_LIST_HEAD(&hse->hpp.list);
INIT_LIST_HEAD(&hse->hpp.sort_list);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 06fcd1bf98b6..b24f9d8727a8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -574,13 +574,16 @@ static int decompress_kmodule(struct dso *dso, const char *name,
const char *ext = strrchr(name, '.');
char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
- if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
- type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
- type != dso->symtab_type)
+ if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+ type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
+ type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
return -1;
- if (!ext || !is_supported_compression(ext + 1))
- return -1;
+ if (!ext || !is_supported_compression(ext + 1)) {
+ ext = strrchr(dso->name, '.');
+ if (!ext || !is_supported_compression(ext + 1))
+ return -1;
+ }
fd = mkstemp(tmpbuf);
if (fd < 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c24c5b83156c..a69066865a55 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -396,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
const char *name)
{
struct rb_node *n;
+ struct symbol_name_rb_node *s;
if (symbols == NULL)
return NULL;
@@ -403,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
n = symbols->rb_node;
while (n) {
- struct symbol_name_rb_node *s;
int cmp;
s = rb_entry(n, struct symbol_name_rb_node, rb_node);
@@ -414,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
else if (cmp > 0)
n = n->rb_right;
else
- return &s->sym;
+ break;
}
- return NULL;
+ if (n == NULL)
+ return NULL;
+
+ /* return first symbol that has same name (if any) */
+ for (n = rb_prev(n); n; n = rb_prev(n)) {
+ struct symbol_name_rb_node *tmp;
+
+ tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
+ if (strcmp(tmp->sym.name, s->sym.name))
+ break;
+
+ s = tmp;
+ }
+
+ return &s->sym;
}
struct symbol *dso__find_symbol(struct dso *dso,
@@ -436,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym)
return symbols__next(sym);
}
+struct symbol *symbol__next_by_name(struct symbol *sym)
+{
+ struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
+ struct rb_node *n = rb_next(&s->rb_node);
+
+ return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+}
+
+ /*
+ * Teturns first symbol that matched with @name.
+ */
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name)
{
@@ -660,7 +685,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
struct machine *machine = kmaps->machine;
struct map *curr_map = map;
struct symbol *pos;
- int count = 0, moved = 0;
+ int count = 0, moved = 0;
struct rb_root *root = &dso->symbols[map->type];
struct rb_node *next = rb_first(root);
int kernel_range = 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9d602e9c6f59..1650dcb3a67b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -231,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name);
+struct symbol *symbol__next_by_name(struct symbol *sym);
struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
struct symbol *dso__next_symbol(struct symbol *sym);
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 371219a6daf1..e3c40a520a25 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name)
return offset;
}
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ int retval = 0;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ return 0;
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ goto out;
+
+ retval = (ehdr.e_type == ET_EXEC);
+
+out:
+ elf_end(elf);
+ pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+ return retval;
+}
+#endif
+
struct table_entry {
u32 start_ip_offset;
u32 fde_offset;
@@ -244,14 +266,17 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
u64 *fde_count)
{
int ret = -EINVAL, fd;
- u64 offset;
+ u64 offset = dso->data.frame_offset;
- fd = dso__data_fd(dso, machine);
- if (fd < 0)
- return -EINVAL;
+ if (offset == 0) {
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return -EINVAL;
- /* Check the .eh_frame section for unwinding info */
- offset = elf_section_offset(fd, ".eh_frame_hdr");
+ /* Check the .eh_frame section for unwinding info */
+ offset = elf_section_offset(fd, ".eh_frame_hdr");
+ dso->data.frame_offset = offset;
+ }
if (offset)
ret = unwind_spec_ehframe(dso, machine, offset,
@@ -265,14 +290,20 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
static int read_unwind_spec_debug_frame(struct dso *dso,
struct machine *machine, u64 *offset)
{
- int fd = dso__data_fd(dso, machine);
+ int fd;
+ u64 ofs = dso->data.frame_offset;
- if (fd < 0)
- return -EINVAL;
+ if (ofs == 0) {
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return -EINVAL;
- /* Check the .debug_frame section for unwinding info */
- *offset = elf_section_offset(fd, ".debug_frame");
+ /* Check the .debug_frame section for unwinding info */
+ ofs = elf_section_offset(fd, ".debug_frame");
+ dso->data.frame_offset = ofs;
+ }
+ *offset = ofs;
if (*offset)
return 0;
@@ -322,8 +353,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
#ifndef NO_LIBUNWIND_DEBUG_FRAME
/* Check the .debug_frame section for unwinding info */
if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+ int fd = dso__data_fd(map->dso, ui->machine);
+ int is_exec = elf_is_exec(fd, map->dso->name);
+ unw_word_t base = is_exec ? 0 : map->start;
+
memset(&di, 0, sizeof(di));
- if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+ if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
map->start, map->end))
return dwarf_search_unwind_table(as, ip, &di, pi,
need_unwind_info, arg);