From 1d90f2e707e75afdb6b644f774cf5e54dc9c33fc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 9 Jun 2010 07:13:16 -0300 Subject: perf record: Don't call newt functions when not initialized MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When processing events we want to give visual feedback to the user when using the newt browser, so there are ui_progress calls in __perf_session__process_events, but those should check if newt is being used. Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Frédéric Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu , Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: <20100609123530.GB9471@ghostprotocols.net> Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/newt.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c index cf182ca132fe..7537ca15900b 100644 --- a/tools/perf/util/newt.c +++ b/tools/perf/util/newt.c @@ -43,6 +43,9 @@ struct ui_progress *ui_progress__new(const char *title, u64 total) if (self != NULL) { int cols; + + if (use_browser <= 0) + return self; newtGetScreenSize(&cols, NULL); cols -= 4; newtCenteredWindow(cols, 1, title); @@ -67,14 +70,22 @@ out_free_self: void ui_progress__update(struct ui_progress *self, u64 curr) { + /* + * FIXME: We should have a per UI backend way of showing progress, + * stdio will just show a percentage as NN%, etc. + */ + if (use_browser <= 0) + return; newtScaleSet(self->scale, curr); newtRefresh(); } void ui_progress__delete(struct ui_progress *self) { - newtFormDestroy(self->form); - newtPopWindow(); + if (use_browser > 0) { + newtFormDestroy(self->form); + newtPopWindow(); + } free(self); } -- cgit v1.2.3 From d11007703c31db534674ebeeb9eb047bbbe758bd Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 10 Jun 2010 13:25:01 +0200 Subject: perf_events: Fix Intel Westmere event constraints Based on Intel Vol3b (March 2010), the event SNOOPQ_REQUEST_OUTSTANDING is restricted to counters 0,1 so update the event table for Intel Westmere accordingly. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: paulus@samba.org Cc: davem@davemloft.net Cc: fweisbec@gmail.com Cc: perfmon2-devel@lists.sf.net Cc: eranian@gmail.com Cc: # .34.x LKML-Reference: <4c10cb56.5120e30a.2eb4.ffffc3de@mx.google.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index fdbc652d3feb..214ac860ebe0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -72,6 +72,7 @@ static struct event_constraint intel_westmere_event_constraints[] = INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ + INTEL_EVENT_CONSTRAINT(0xb3, 0x1), /* SNOOPQ_REQUEST_OUTSTANDING */ EVENT_CONSTRAINT_END }; -- cgit v1.2.3 From a8fb2608053547bc3152ea61a5ec7cdfce5d942c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 10 Jun 2010 14:53:16 -0400 Subject: perf/tracing: Fix regression of perf losing kprobe events With the addition of the code to shrink the kernel tracepoint infrastructure, we lost kprobes being traced by perf. The reason is that I tested if the "tp_event->class->perf_probe" existed before enabling it. This prevents "ftrace only" events (like the function trace events) from being enabled by perf. Unfortunately, kprobe events do not use perf_probe. This causes kprobes to be missed by perf. To fix this, we add the test to see if "tp_event->class->reg" exists as well as perf_probe. Normal trace events have only "perf_probe" but no "reg" function, and kprobes and syscalls have the "reg" but no "perf_probe". The ftrace unique events do not have either, so this is a valid test. If a kprobe or syscall is not to be probed by perf, the "reg" function is called anyway, and will return a failure and prevent perf from probing it. Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Acked-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index e6f65887842c..8a2b73f7c068 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -96,7 +96,9 @@ int perf_trace_init(struct perf_event *p_event) mutex_lock(&event_mutex); list_for_each_entry(tp_event, &ftrace_events, list) { if (tp_event->event.type == event_id && - tp_event->class && tp_event->class->perf_probe && + tp_event->class && + (tp_event->class->perf_probe || + tp_event->class->reg) && try_module_get(tp_event->mod)) { ret = perf_trace_event_init(tp_event, p_event); break; -- cgit v1.2.3 From 720a3aeb7373cb49cf222d5f12e121f78d3d4410 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 17 Jun 2010 08:37:44 -0300 Subject: perf session: Remove threads from tree on PERF_RECORD_EXIT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move them to a session->dead_threads list just like we do with maps that are replaced, because we may have hist_entries pointing to them. This fixes a bug when inserting maps for a new thread that reused the TID, mixing maps for two different threads, causing an endless loop. The code for insering maps should be made more robust but for .35 this is the minimalistic patch. Reported-by: Ingo Molnar Cc: David S. Miller Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 4 +++- tools/perf/util/session.c | 11 +++++++++++ tools/perf/util/session.h | 2 ++ tools/perf/util/thread.h | 5 ++++- 4 files changed, 20 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1f08f008d289..2fbf6a463c81 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -538,8 +538,10 @@ int event__process_task(event_t *self, struct perf_session *session) dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, self->fork.ppid, self->fork.ptid); - if (self->header.type == PERF_RECORD_EXIT) + if (self->header.type == PERF_RECORD_EXIT) { + perf_session__remove_thread(session, thread); return 0; + } if (thread == NULL || parent == NULL || thread__fork(thread, parent) < 0) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8f83a1835766..c422cd676313 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -90,6 +90,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc memcpy(self->filename, filename, len); self->threads = RB_ROOT; + INIT_LIST_HEAD(&self->dead_threads); self->hists_tree = RB_ROOT; self->last_match = NULL; self->mmap_window = 32; @@ -131,6 +132,16 @@ void perf_session__delete(struct perf_session *self) free(self); } +void perf_session__remove_thread(struct perf_session *self, struct thread *th) +{ + rb_erase(&th->rb_node, &self->threads); + /* + * We may have references to this thread, for instance in some hist_entry + * instances, so just move them to a separate list. + */ + list_add_tail(&th->node, &self->dead_threads); +} + static bool symbol__match_parent_regex(struct symbol *sym) { if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 55c6881b218d..9fa0fc2a863f 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -26,6 +26,7 @@ struct perf_session { unsigned long size; unsigned long mmap_window; struct rb_root threads; + struct list_head dead_threads; struct thread *last_match; struct machine host_machine; struct rb_root machines; @@ -99,6 +100,7 @@ int perf_session__create_kernel_maps(struct perf_session *self); int do_read(int fd, void *buf, size_t size); void perf_session__update_sample_type(struct perf_session *self); +void perf_session__remove_thread(struct perf_session *self, struct thread *th); static inline struct machine *perf_session__find_host_machine(struct perf_session *self) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 1dfd9ff8bdcd..ee6bbcf277ca 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -6,7 +6,10 @@ #include "symbol.h" struct thread { - struct rb_node rb_node; + union { + struct rb_node rb_node; + struct list_head node; + }; struct map_groups mg; pid_t pid; char shortname[3]; -- cgit v1.2.3 From 5ffc88819c84098e3f39185a38f8f7f7f8b210df Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Wed, 9 Jun 2010 18:38:00 +1000 Subject: perf record: prevent kill(0, SIGTERM); MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At exit, perf record will kill the process it was profiling by sending a SIGTERM to child_pid (if it had been initialised), but in certain situations child_pid may be 0 and perf would mistakenly kill more processes than intended. child_pid is set to the return of fork() to either 0 or the pid of the child. Ordinarily this would not present an issue as the child calls execvp to spawn the process to be profiled and would therefore never run it's sig_atexit and never attempt to kill pid 0. However, if a nonexistant binary had been passed in to perf record the call to execvp would fail and child_pid would be left set to 0. The child would then exit and it's atexit handler, finding that child_pid was initialised to 0, would call kill(0, SIGTERM), resulting in every process within it's process group being killed. In the case that perf was being run directly from the shell this typically would not be an issue as the shell isolates the process. However, if perf was being called from another program it could kill unexpected processes, which may even include X. This patch changes the logic of the test for whether child_pid was initialised to only consider positive pids as valid, thereby never attempting to kill pid 0. Cc: David S. Miller Cc: Frédéric Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: <1276072680-17378-1-git-send-email-imunsie@au1.ibm.com> Signed-off-by: Ian Munsie Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index dc3435e18bde..711745f56bba 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -193,7 +193,7 @@ static void sig_handler(int sig) static void sig_atexit(void) { - if (child_pid != -1) + if (child_pid > 0) kill(child_pid, SIGTERM); if (signr == -1) -- cgit v1.2.3 From b70e4f0529c089b00d0a6da13106db4de1ada4c7 Mon Sep 17 00:00:00 2001 From: Wu Zhangjin Date: Mon, 21 Jun 2010 19:09:09 +0800 Subject: tracing: Fix undeclared ENOSYS in include/linux/tracepoint.h The header file include/linux/tracepoint.h may be included without include/linux/errno.h and then the compiler will fail on building for undelcared ENOSYS. This patch fixes this problem via including to include/linux/tracepoint.h. Signed-off-by: Wu Zhangjin LKML-Reference: <1277118549-622-1-git-send-email-wuzhangjin@gmail.com> Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 9a59d1f98cd4..103d1b61aacb 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,6 +14,7 @@ * See the file COPYING for more details. */ +#include #include #include -- cgit v1.2.3