From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751890Ab3EEKK7 (ORCPT ); Sun, 5 May 2013 06:10:59 -0400 Received: from mail-ea0-f177.google.com ([209.85.215.177]:47394 "EHLO mail-ea0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751818Ab3EEKK5 (ORCPT ); Sun, 5 May 2013 06:10:57 -0400 Date: Sun, 5 May 2013 12:10:51 +0200 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Peter Zijlstra , Arnaldo Carvalho de Melo , Thomas Gleixner , Andrew Morton Subject: [GIT PULL] perf fixes Message-ID: <20130505101051.GA4371@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest perf-urgent-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus HEAD: 7cc23cd6c0c7d7f4bee057607e7ce01568925717 perf/x86/intel/lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL Misc fixes plus a small hw-enablement patch for Intel IB model 58 uncore events. Thanks, Ingo ------------------> Jan-Simon Möller (1): perf/x86/intel: Fix unintended variable name reuse Jiri Olsa (1): perf: Fix vmalloc ring buffer pages handling Li Fei (1): x86: Eliminate irq_mis_count counted in arch_irq_stat Peter Zijlstra (3): perf/x86: Blacklist all MEM_*_RETIRED events for Ivy Bridge perf/x86/intel/lbr: Fix LBR filter perf/x86/intel/lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL Vince Weaver (2): perf/x86/intel: Fix typo in perf_event_intel_uncore.c perf/x86/intel: Add support for IvyBridge model 58 Uncore arch/x86/kernel/cpu/perf_event_intel.c | 13 +++++++++---- arch/x86/kernel/cpu/perf_event_intel_lbr.c | 27 ++++++++++++++++++++++----- arch/x86/kernel/cpu/perf_event_intel_uncore.c | 19 ++++++++++--------- arch/x86/kernel/irq.c | 4 ---- kernel/events/ring_buffer.c | 14 ++++++++++---- 5 files changed, 51 insertions(+), 26 deletions(-) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cc45deb..4a0a462 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -125,10 +125,15 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* + * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT + * siblings; disable these events because they can corrupt unrelated + * counters. + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index da02e9c..d978353 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -310,7 +310,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,8 +318,11 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { + if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; mask |= X86_BR_KERNEL; + } /* we ignore BRANCH_HV here */ @@ -339,6 +342,8 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; + + return 0; } /* @@ -386,7 +391,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - intel_pmu_setup_sw_lbr_filter(event); + ret = intel_pmu_setup_sw_lbr_filter(event); + if (ret) + return ret; /* * setup HW LBR filter, if any @@ -442,8 +449,18 @@ static int branch_type(unsigned long from, unsigned long to) return X86_BR_NONE; addr = buf; - } else - addr = (void *)from; + } else { + /* + * The LBR logs any address in the IP, even if the IP just + * faulted. This means userspace can control the from address. + * Ensure we don't blindy read any address by validating it is + * a known text address. + */ + if (kernel_text_address(from)) + addr = (void *)from; + else + return X86_BR_NONE; + } /* * decoder needs to know the ABI especially diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index b43200d..45f6d13 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2428,7 +2428,7 @@ static void __init uncore_types_exit(struct intel_uncore_type **types) static int __init uncore_type_init(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmus; - struct attribute_group *events_group; + struct attribute_group *attr_group; struct attribute **attrs; int i, j; @@ -2455,19 +2455,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type) while (type->event_descs[i].attr.attr.name) i++; - events_group = kzalloc(sizeof(struct attribute *) * (i + 1) + - sizeof(*events_group), GFP_KERNEL); - if (!events_group) + attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + + sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) goto fail; - attrs = (struct attribute **)(events_group + 1); - events_group->name = "events"; - events_group->attrs = attrs; + attrs = (struct attribute **)(attr_group + 1); + attr_group->name = "events"; + attr_group->attrs = attrs; for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->events_group = events_group; + type->events_group = attr_group; } type->pmu_group = &uncore_pmu_attr_group; @@ -2853,11 +2853,12 @@ static int __init uncore_cpu_init(void) msr_uncores = nhm_msr_uncores; break; case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ if (snb_uncore_cbox.num_boxes > max_cores) snb_uncore_cbox.num_boxes = max_cores; msr_uncores = snb_msr_uncores; break; - case 45: /* Sandy Birdge-EP */ + case 45: /* Sandy Bridge-EP */ if (snbep_uncore_cbox.num_boxes > max_cores) snbep_uncore_cbox.num_boxes = max_cores; msr_uncores = snbep_msr_uncores; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e4595f1..84b7789 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -165,10 +165,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) u64 arch_irq_stat(void) { u64 sum = atomic_read(&irq_err_count); - -#ifdef CONFIG_X86_IO_APIC - sum += atomic_read(&irq_mis_count); -#endif return sum; } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 97fddb0..cd55144 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -326,11 +326,16 @@ void rb_free(struct ring_buffer *rb) } #else +static int data_page_nr(struct ring_buffer *rb) +{ + return rb->nr_pages << page_order(rb); +} struct page * perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { - if (pgoff > (1UL << page_order(rb))) + /* The '>' counts in the user page. */ + if (pgoff > data_page_nr(rb)) return NULL; return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE); @@ -350,10 +355,11 @@ static void rb_free_work(struct work_struct *work) int i, nr; rb = container_of(work, struct ring_buffer, work); - nr = 1 << page_order(rb); + nr = data_page_nr(rb); base = rb->user_page; - for (i = 0; i < nr + 1; i++) + /* The '<=' counts in the user page. */ + for (i = 0; i <= nr; i++) perf_mmap_unmark_page(base + (i * PAGE_SIZE)); vfree(base); @@ -387,7 +393,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) rb->user_page = all_buf; rb->data_pages[0] = all_buf + PAGE_SIZE; rb->page_order = ilog2(nr_pages); - rb->nr_pages = 1; + rb->nr_pages = !!nr_pages; ring_buffer_init(rb, watermark, flags);