From bb7ab785ad05a97a2c9ffb3a06547ed39f3133e8 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 21 Sep 2010 03:26:35 -0400 Subject: oprofile: Add Support for Intel CPU Family 6 / Model 29 This patch adds CPU type detection for dunnington processor (Family 6 / Model 29) to be identified as core 2 family cpu type (wikipedia source). I tested oprofile on Intel(R) Xeon(R) CPU E7440 reporting itself as model 29, and it runs without an issue. Spec: http://www.intel.com/Assets/en_US/PDF/specupdate/320336.pdf Signed-off-by: Jiri Olsa Acked-by: Andi Kleen Cc: stable@kernel.org Signed-off-by: Robert Richter --- arch/x86/oprofile/nmi_int.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 009b819f48d0..f1575c9a2572 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -674,6 +674,7 @@ static int __init ppro_init(char **cpu_type) case 0x0f: case 0x16: case 0x17: + case 0x1d: *cpu_type = "i386/core_2"; break; case 0x1a: -- cgit v1.2.3 From 9ecd4e1689208afe9b059a5ce1333acb2f42c4d2 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 22 Sep 2010 17:07:27 -0700 Subject: tracing/x86: Don't use mcount in pvclock.c When using a paravirt clock, pvclock.c can be used by sched_clock(), which in turn is used by the tracing mechanism for timestamps, which leads to infinite recursion. Disable mcount/tracing for pvclock.o. Cc: stable@kernel.org Signed-off-by: Jeremy Fitzhardinge LKML-Reference: <4C9A9A3F.4040201@goop.org> Signed-off-by: Steven Rostedt --- arch/x86/kernel/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0925676266bd..882bbff9d50b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -11,6 +11,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -- cgit v1.2.3 From 258af47479980d8238a04568b94a4e55aa1cb537 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 22 Sep 2010 22:22:25 -0400 Subject: tracing/x86: Don't use mcount in kvmclock.c The guest can use the paravirt clock in kvmclock.c which is used by sched_clock(), which in turn is used by the tracing mechanism for timestamps, which leads to infinite recursion. Disable mcount/tracing for kvmclock.o. Cc: stable@kernel.org Cc: Jeremy Fitzhardinge Cc: Avi Kivity Signed-off-by: Steven Rostedt --- arch/x86/kernel/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 882bbff9d50b..fedf32a8c3ec 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -12,6 +12,7 @@ CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg +CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -- cgit v1.2.3 From 63e6be6d98e1a2bcdca86872b67052e51ab6afa1 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 15 Sep 2010 18:20:34 +0200 Subject: perf, x86: Catch spurious interrupts after disabling counters Some cpus still deliver spurious interrupts after disabling a counter. This caused 'undelivered NMI' messages. This patch fixes this. Introduced by: 4177c42: perf, x86: Try to handle unknown nmis with an enabled PMU Reported-by: Ingo Molnar Signed-off-by: Robert Richter Cc: Don Zickus Cc: gorcunov@gmail.com Cc: fweisbec@gmail.com Cc: ying.huang@intel.com Cc: ming.m.lin@intel.com Cc: yinghai@kernel.org Cc: andi@firstfloor.org Cc: eranian@google.com Cc: Peter Zijlstra LKML-Reference: <20100915162034.GO13563@erda.amd.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3efdf2870a35..03a5b0385ad6 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -102,6 +102,7 @@ struct cpu_hw_events { */ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; int enabled; int n_events; @@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event) x86_perf_event_set_period(event); cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); + __set_bit(idx, cpuc->running); x86_pmu.enable(event); perf_event_update_userpage(event); @@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) + if (!test_bit(idx, cpuc->active_mask)) { + /* + * Though we deactivated the counter some cpus + * might still deliver spurious interrupts still + * in flight. Catch them: + */ + if (__test_and_clear_bit(idx, cpuc->running)) + handled++; continue; + } event = cpuc->events[idx]; hwc = &event->hw; -- cgit v1.2.3 From 98d943b02f6f1b57787ff1aa6f34d019a407e3ee Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 29 Sep 2010 16:52:25 +0200 Subject: oprofile, ARM: Release resources on failure This patch fixes a resource leak on failure, where the oprofilefs and some counters may not released properly. Signed-off-by: Robert Richter Acked-by: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: # .35.x LKML-Reference: <20100929145225.GJ13563@erda.amd.com> Signed-off-by: Ingo Molnar --- arch/arm/oprofile/common.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 0691176899ff..72e09eb642dd 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -102,6 +102,7 @@ static int op_create_counter(int cpu, int event) if (IS_ERR(pevent)) { ret = PTR_ERR(pevent); } else if (pevent->state != PERF_EVENT_STATE_ACTIVE) { + perf_event_release_kernel(pevent); pr_warning("oprofile: failed to enable event %d " "on CPU %d\n", event, cpu); ret = -EBUSY; @@ -365,6 +366,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) ret = init_driverfs(); if (ret) { kfree(counter_config); + counter_config = NULL; return ret; } @@ -402,7 +404,6 @@ void oprofile_arch_exit(void) struct perf_event *event; if (*perf_events) { - exit_driverfs(); for_each_possible_cpu(cpu) { for (id = 0; id < perf_num_counters; ++id) { event = perf_events[cpu][id]; @@ -413,8 +414,10 @@ void oprofile_arch_exit(void) } } - if (counter_config) + if (counter_config) { kfree(counter_config); + exit_driverfs(); + } } #else int __init oprofile_arch_init(struct oprofile_operations *ops) -- cgit v1.2.3 From 03e22198d2379ffa746c9ea332fbb1f094f9423b Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 29 Sep 2010 23:01:38 -0400 Subject: perf, x86: Handle in flight NMIs on P4 platform Stephane reported we've forgot to guard the P4 platform against spurious in-flight performance IRQs. Fix it. This fixes potential spurious 'dazed and confused' NMI messages. Reported-by: Stephane Eranian Signed-off-by: Cyrill Gorcunov Signed-off-by: Don Zickus Cc: fweisbec@gmail.com Cc: peterz@infradead.org Cc: Robert Richter Cc: Lin Ming LKML-Reference: <1285815698-4298-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_p4.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index b560db3305be..249015173992 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -660,8 +660,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) for (idx = 0; idx < x86_pmu.num_counters; idx++) { int overflow; - if (!test_bit(idx, cpuc->active_mask)) + if (!test_bit(idx, cpuc->active_mask)) { + /* catch in-flight IRQs */ + if (__test_and_clear_bit(idx, cpuc->running)) + handled++; continue; + } event = cpuc->events[idx]; hwc = &event->hw; -- cgit v1.2.3 From 39cfae64dfd243fa7a7ca73643591bdebc1cf1e9 Mon Sep 17 00:00:00 2001 From: Kusanagi Kouichi Date: Sun, 26 Sep 2010 14:17:42 -0300 Subject: perf tools: Fix build breakage The patch ecafda6 introduced a problem where all object files would be always rebuilt, fix it by using: http://www.gnu.org/software/make/manual/html_node/Prerequisite-Types.html Reported-by: Arnaldo Carvalho de Melo Cc: Bernd Petrovitsch Signed-off-by: Kusanagi Kouichi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 4f1fa77c1feb..1950e19af1cf 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -1017,7 +1017,7 @@ builtin-revert.o wt-status.o: wt-status.h # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So # we depend the various files onto their directories. DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -$(DIRECTORY_DEPS): $(sort $(dir $(DIRECTORY_DEPS))) +$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS))) # In the second step, we make a rule to actually create these directories $(sort $(dir $(DIRECTORY_DEPS))): $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null -- cgit v1.2.3 From c569d3326bca6774f6c23f1dc91acad5400b6409 Mon Sep 17 00:00:00 2001 From: Frederik Deweerdt Date: Thu, 23 Sep 2010 22:19:01 +0200 Subject: perf ui hist browser: Fix segfault on 'a' for annotate There a typo in util/ui/browsers/hists.c that leads to a segfault when you press the 'a' key on a non-resolved symbol (plain hex address). LKML-Reference: <20100923201901.GE31726@gambetta> Signed-off-by: Frederik Deweerdt Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ui/browsers/hists.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index dafdf6775d77..6866aa4c41e0 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -773,7 +773,7 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) switch (key) { case 'a': - if (browser->selection->map == NULL && + if (browser->selection->map == NULL || browser->selection->map->dso->annotate_warned) continue; goto do_annotate; -- cgit v1.2.3 From 0f940cb7d970f4fd569bb5f9f49774422f2ccbee Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 21 Sep 2010 00:45:01 +0200 Subject: perf trace scripting: Fix extern struct definitions Both python_scripting_ops and perl_scripting_ops have two global definitions. One in trace-event-scripting.c and one in their respective scripting-engine modules. The issue is that depending on the linker order one definition or the other is chosen. One is uninitialized (bss), while the other is initialized. If the uninitialized version is chosen, then perf does not function properly. This patch fixes this by adding the extern prefix to the definitions in trace-event-scripting.c. Cc: David S. Miller Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter LKML-Reference: <4c97e41a.078fd80a.7a8b.3cc9@mx.google.com> Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/trace-event-scripting.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 7ea983acfaea..f7af2fca965d 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -97,7 +97,7 @@ void setup_python_scripting(void) register_python_scripting(&python_scripting_unsupported_ops); } #else -struct scripting_ops python_scripting_ops; +extern struct scripting_ops python_scripting_ops; void setup_python_scripting(void) { @@ -158,7 +158,7 @@ void setup_perl_scripting(void) register_perl_scripting(&perl_scripting_unsupported_ops); } #else -struct scripting_ops perl_scripting_ops; +extern struct scripting_ops perl_scripting_ops; void setup_perl_scripting(void) { -- cgit v1.2.3