Merge tag 'perf-core-for-mingo-20160415' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements from Arnaldo Carvalho de Melo:

User visible changes:

- Wire the callchain unwinding "max-stack" now to 'perf script --max-stack',
  allowing to limit the depth of callchains, possibly reducing processing
  time (Arnaldo Carvalho de Melo)

- Ditto for 'perf trace --max-stack' (Arnaldo Carvalho de Melo)

- Introduce a --min-stack filter for 'perf trace', to show syscalls that
  had a userspace callchain leading to it at least min-stack deep (Arnaldo Carvalho de Melo)

- Make 'perf trace' work with multiple threads and the --duration filter,
  i.e. do not print the start of an interrupted syscall followed by ...
  to print interrupts from other threads, as we need to wait the sys_exit
  syscall tracepoint to calculate the duration, duh. (Arnaldo Carvalho de Melo)

  System wide --duration now works as expected:

   [root@jouet ~]# trace --duration 100
     152.393 (145.147 ms): Timer/24358 futex(uaddr: 0x7f5ed98e56cc, op: WAIT_BITSET|PRIV|CLKRT, val: 7055125, utime: 0x7f5ecdbfec30, val3: 4294967295) = -1 ETIMEDOUT Connection timed out
     152.438 (145.040 ms): firefox/24321 poll(ufds: 0x7f5ec388b460, nfds: 6, timeout_msecs: 4294967295) = 1
     358.580 (158.279 ms): Xorg/2025 select(n: 512, inp: 0x83a8e0, tvp: 0x7ffdcbb63610) = 0 Timeout
     358.687 (148.285 ms): gnome-terminal/2711 poll(ufds: 0x55b7e6811ad0, nfds: 15, timeout_msecs: 249) = 1
     370.150 (169.569 ms): gnome-shell/2287 poll(ufds: 0x55e623d65490, nfds: 86, timeout_msecs: 4294967295) = 1

- Now 'perf trace's --max-stack and --min-stack will automatically set
  "--call-graph dwarf", if --call-graph is not present on the command line:

   [root@jouet ~]# perf trace -e nanosleep --max-stack 3 usleep 1
     0.299 ( 0.057 ms): usleep/29658 nanosleep(rqtp: 0x7fff80f3b230) = 0
                                       __nanosleep+0x10 (/usr/lib64/libc-2.22.so)
                                       usleep+0x34 (/usr/lib64/libc-2.22.so)
                                       main+0x1eb (/usr/bin/usleep)
   [root@jouet ~]#

- Bump 'perf trace --mmap-pages' for root when using callchains and not
  specifying --mmap-pages explicitely (Arnaldo Carvalho de Melo)

Build fixes:

- The python binding object had missing symbols, to some refactoring
  to fix that (Arnaldo Carvalho de Melo)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 15 insertions, 11 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 80b9b6a87990..0c4dabc69932 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1599,6 +1599,7 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 }
 
 static int add_callchain_ip(struct thread *thread,
+			    struct callchain_cursor *cursor,
 			    struct symbol **parent,
 			    struct addr_location *root_al,
 			    u8 *cpumode,
@@ -1630,7 +1631,7 @@ static int add_callchain_ip(struct thread *thread,
 				 * It seems the callchain is corrupted.
 				 * Discard all.
 				 */
-				callchain_cursor_reset(&callchain_cursor);
+				callchain_cursor_reset(cursor);
 				return 1;
 			}
 			return 0;
@@ -1648,13 +1649,13 @@ static int add_callchain_ip(struct thread *thread,
 			/* Treat this symbol as the root,
 			   forgetting its callees. */
 			*root_al = al;
-			callchain_cursor_reset(&callchain_cursor);
+			callchain_cursor_reset(cursor);
 		}
 	}
 
 	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		return 0;
-	return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
+	return callchain_cursor_append(cursor, al.addr, al.map, al.sym);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1724,6 +1725,7 @@ static int remove_loops(struct branch_entry *l, int nr)
  * negative error code on other errors.
  */
 static int resolve_lbr_callchain_sample(struct thread *thread,
+					struct callchain_cursor *cursor,
 					struct perf_sample *sample,
 					struct symbol **parent,
 					struct addr_location *root_al,
@@ -1778,7 +1780,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = lbr_stack->entries[0].to;
 			}
 
-			err = add_callchain_ip(thread, parent, root_al, &cpumode, ip);
+			err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 			if (err)
 				return (err < 0) ? err : 0;
 		}
@@ -1789,6 +1791,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 }
 
 static int thread__resolve_callchain_sample(struct thread *thread,
+					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
 					    struct perf_sample *sample,
 					    struct symbol **parent,
@@ -1803,10 +1806,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	int skip_idx = -1;
 	int first_call = 0;
 
-	callchain_cursor_reset(&callchain_cursor);
+	callchain_cursor_reset(cursor);
 
 	if (has_branch_callstack(evsel)) {
-		err = resolve_lbr_callchain_sample(thread, sample, parent,
+		err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
 						   root_al, max_stack);
 		if (err)
 			return (err < 0) ? err : 0;
@@ -1863,10 +1866,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 		nr = remove_loops(be, nr);
 
 		for (i = 0; i < nr; i++) {
-			err = add_callchain_ip(thread, parent, root_al,
+			err = add_callchain_ip(thread, cursor, parent, root_al,
 					       NULL, be[i].to);
 			if (!err)
-				err = add_callchain_ip(thread, parent, root_al,
+				err = add_callchain_ip(thread, cursor, parent, root_al,
 						       NULL, be[i].from);
 			if (err == -EINVAL)
 				break;
@@ -1896,7 +1899,7 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
-		err = add_callchain_ip(thread, parent, root_al, &cpumode, ip);
+		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
 			return (err < 0) ? err : 0;
@@ -1916,13 +1919,14 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 }
 
 int thread__resolve_callchain(struct thread *thread,
+			      struct callchain_cursor *cursor,
 			      struct perf_evsel *evsel,
 			      struct perf_sample *sample,
 			      struct symbol **parent,
 			      struct addr_location *root_al,
 			      int max_stack)
 {
-	int ret = thread__resolve_callchain_sample(thread, evsel,
+	int ret = thread__resolve_callchain_sample(thread, cursor, evsel,
 						   sample, parent,
 						   root_al, max_stack);
 	if (ret)
@@ -1938,7 +1942,7 @@ int thread__resolve_callchain(struct thread *thread,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor,
+	return unwind__get_entries(unwind_entry, cursor,
 				   thread, sample, max_stack);
 
 }