summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/thread.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-07-25 13:20:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-25 13:20:41 -0700
commit7e4dc77b2869a683fc43c0394fca5441816390ba (patch)
tree62e734c599bc1da2712fdb63be996622c415a83a /tools/perf/util/thread.c
parent89e7eb098adfe342bc036f00201eb579d448f033 (diff)
parent5048c2af078d5976895d521262a8802ea791f3b0 (diff)
downloadlinux-7e4dc77b2869a683fc43c0394fca5441816390ba.tar.bz2
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "With over 300 commits it's been a busy cycle - with most of the work concentrated on the tooling side (as it should). The main kernel side enhancements were: - Add per event callchain limit: Recently we introduced a sysctl to tune the max-stack for all events for which callchains were requested: $ sysctl kernel.perf_event_max_stack kernel.perf_event_max_stack = 127 Now this patch introduces a way to configure this per event, i.e. this becomes possible: $ perf record -e sched:*/max-stack=2/ -e block:*/max-stack=10/ -a allowing finer tuning of how much buffer space callchains use. This uses an u16 from the reserved space at the end, leaving another u16 for future use. There has been interest in even finer tuning, namely to control the max stack for kernel and userspace callchains separately. Further discussion is needed, we may for instance use the remaining u16 for that and when it is present, assume that the sample_max_stack introduced in this patch applies for the kernel, and the u16 left is used for limiting the userspace callchain (Arnaldo Carvalho de Melo) - Optimize AUX event (hardware assisted side-band event) delivery (Kan Liang) - Rework Intel family name macro usage (this is partially x86 arch work) (Dave Hansen) - Refine and fix Intel LBR support (David Carrillo-Cisneros) - Add support for Intel 'TopDown' events (Andi Kleen) - Intel uncore PMU driver fixes and enhancements (Kan Liang) - ... other misc changes. Here's an incomplete list of the tooling enhancements (but there's much more, see the shortlog and the git log for details): - Support cross unwinding, i.e. collecting '--call-graph dwarf' perf.data files in one machine and then doing analysis in another machine of a different hardware architecture. This enables, for instance, to do: $ perf record -a --call-graph dwarf on a x86-32 or aarch64 system and then do 'perf report' on it on a x86_64 workstation (He Kuang) - Allow reading from a backward ring buffer (one setup via sys_perf_event_open() with perf_event_attr.write_backward = 1) (Wang Nan) - Finish merging initial SDT (Statically Defined Traces) support, see cset comments for details about how it all works (Masami Hiramatsu) - Support attaching eBPF programs to tracepoints (Wang Nan) - Add demangling of symbols in programs written in the Rust language (David Tolnay) - Add support for tracepoints in the python binding, including an example, that sets up and parses sched:sched_switch events, tools/perf/python/tracepoint.py (Jiri Olsa) - Introduce --stdio-color to set up the color output mode selection in 'annotate' and 'report', allowing emit color escape sequences when redirecting the output of these tools (Arnaldo Carvalho de Melo) - Add 'callindent' option to 'perf script -F', to indent the Intel PT call stack, making this output more ftrace-like (Adrian Hunter, Andi Kleen) - Allow dumping the object files generated by llvm when processing eBPF scriptlet events (Wang Nan) - Add stackcollapse.py script to help generating flame graphs (Paolo Bonzini) - Add --ldlat option to 'perf mem' to specify load latency for loads event (e.g. cpu/mem-loads/ ) (Jiri Olsa) - Tooling support for Intel TopDown counters, recently added to the kernel (Andi Kleen)" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (303 commits) perf tests: Add is_printable_array test perf tools: Make is_printable_array global perf script python: Fix string vs byte array resolving perf probe: Warn unmatched function filter correctly perf cpu_map: Add more helpers perf stat: Balance opening and reading events tools: Copy linux/{hash,poison}.h and check for drift perf tools: Remove include/linux/list.h from perf's MANIFEST tools: Copy the bitops files accessed from the kernel and check for drift Remove: kernel unistd*h files from perf's MANIFEST, not used perf tools: Remove tools/perf/util/include/linux/const.h perf tools: Remove tools/perf/util/include/asm/byteorder.h perf tools: Add missing linux/compiler.h include to perf-sys.h perf jit: Remove some no-op error handling perf jit: Add missing curly braces objtool: Initialize variable to silence old compiler objtool: Add -I$(srctree)/tools/arch/$(ARCH)/include/uapi perf record: Add --tail-synthesize option perf session: Don't warn about out of order event if write_backward is used perf tools: Enable overwrite settings ...
Diffstat (limited to 'tools/perf/util/thread.c')
-rw-r--r--tools/perf/util/thread.c61
1 files changed, 55 insertions, 6 deletions
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 45fcb715a36b..8b10a55410a2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -43,9 +43,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
thread->cpu = -1;
INIT_LIST_HEAD(&thread->comm_list);
- if (unwind__prepare_access(thread) < 0)
- goto err_thread;
-
comm_str = malloc(32);
if (!comm_str)
goto err_thread;
@@ -201,10 +198,51 @@ size_t thread__fprintf(struct thread *thread, FILE *fp)
map_groups__fprintf(thread->mg, fp);
}
-void thread__insert_map(struct thread *thread, struct map *map)
+int thread__insert_map(struct thread *thread, struct map *map)
{
+ int ret;
+
+ ret = unwind__prepare_access(thread, map, NULL);
+ if (ret)
+ return ret;
+
map_groups__fixup_overlappings(thread->mg, map, stderr);
map_groups__insert(thread->mg, map);
+
+ return 0;
+}
+
+static int __thread__prepare_access(struct thread *thread)
+{
+ bool initialized = false;
+ int i, err = 0;
+
+ for (i = 0; i < MAP__NR_TYPES; ++i) {
+ struct maps *maps = &thread->mg->maps[i];
+ struct map *map;
+
+ pthread_rwlock_rdlock(&maps->lock);
+
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ err = unwind__prepare_access(thread, map, &initialized);
+ if (err || initialized)
+ break;
+ }
+
+ pthread_rwlock_unlock(&maps->lock);
+ }
+
+ return err;
+}
+
+static int thread__prepare_access(struct thread *thread)
+{
+ int err = 0;
+
+ if (symbol_conf.use_callchain)
+ err = __thread__prepare_access(thread);
+
+ return err;
}
static int thread__clone_map_groups(struct thread *thread,
@@ -214,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread,
/* This is new thread, we share map groups for process. */
if (thread->pid_ == parent->pid_)
- return 0;
+ return thread__prepare_access(thread);
if (thread->mg == parent->mg) {
pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
@@ -224,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread,
/* But this one is new process, copy maps. */
for (i = 0; i < MAP__NR_TYPES; ++i)
- if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+ if (map_groups__clone(thread, parent->mg, i) < 0)
return -ENOMEM;
return 0;
@@ -265,3 +303,14 @@ void thread__find_cpumode_addr_location(struct thread *thread,
break;
}
}
+
+struct thread *thread__main_thread(struct machine *machine, struct thread *thread)
+{
+ if (thread->pid_ == thread->tid)
+ return thread__get(thread);
+
+ if (thread->pid_ == -1)
+ return NULL;
+
+ return machine__find_thread(machine, thread->pid_, thread->pid_);
+}