From e5ea9b54a055619160bbfe527ebb7d7191823d66 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 17 Mar 2018 14:52:16 +0300 Subject: [PATCH 1/5] perf/x86/intel: Don't accidentally clear high bits in bdw_limit_period() We intended to clear the lowest 6 bits but because of a type bug we clear the high 32 bits as well. Andi says that periods are rarely more than U32_MAX so this bug probably doesn't have a huge runtime impact. Signed-off-by: Dan Carpenter Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 294fe0f52a44 ("perf/x86/intel: Add INST_RETIRED.ALL workarounds") Link: http://lkml.kernel.org/r/20180317115216.GB4035@mwanda Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 56457cb73448..9b18a227fff7 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left) X86_CONFIG(.event=0xc0, .umask=0x01)) { if (left < 128) left = 128; - left &= ~0x3fu; + left &= ~0x3fULL; } return left; } From e340895c9ed0b44548f08bbaaee4afc7bfacd354 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 12 Mar 2018 08:41:34 -0700 Subject: [PATCH 2/5] perf/x86/intel/uncore: Add missing filter constraint for SKX CHA event Adding a filter constraint for Intel Skylake CHA event UNC_CHA_UPI_CREDITS_ACQUIRED (0x38). The event supports core-id/thread-id and link filtering. Signed-off-by: Stephane Eranian Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1520869294-14176-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore_snbep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 22ec65bc033a..0876798f2ac9 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3), EVENT_EXTRA_END }; From 174afc3e7dd7823df8218e16e7768b834097184e Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 12 Mar 2018 10:45:37 -0400 Subject: [PATCH 3/5] perf/x86/intel: Rename confusing 'freerunning PEBS' API and implementation to 'large PEBS' The 'freerunning PEBS' and 'large PEBS' are the same thing. Both of these names appear in the code and in the API, which causes confusion. Rename 'freerunning PEBS' to 'large PEBS' to unify the code, which eliminates the confusion. No functional change. Reported-by: Vince Weaver Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1520865937-22910-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 2 +- arch/x86/events/intel/core.c | 12 ++++++------ arch/x86/events/intel/ds.c | 6 +++--- arch/x86/events/perf_event.h | 6 +++--- 4 files changed, 13 insertions(+), 13 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 3d24edfef3e4..88797c80b3e0 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2119,7 +2119,7 @@ static int x86_pmu_event_init(struct perf_event *event) } if (READ_ONCE(x86_pmu.attr_rdpmc) && - !(event->hw.flags & PERF_X86_EVENT_FREERUNNING)) + !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9b18a227fff7..1e41d7508d99 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event) return intel_pebs_aliases_precdist(event); } -static unsigned long intel_pmu_free_running_flags(struct perf_event *event) +static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) { - unsigned long flags = x86_pmu.free_running_flags; + unsigned long flags = x86_pmu.large_pebs_flags; if (event->attr.use_clockid) flags &= ~PERF_SAMPLE_TIME; @@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event) if (!event->attr.freq) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & - ~intel_pmu_free_running_flags(event))) - event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + ~intel_pmu_large_pebs_flags(event))) + event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); @@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32-bit width, @@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 18c25ab28557..d8015235ba76 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs++; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs--; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -1530,7 +1530,7 @@ void __init intel_ds_init(void) x86_pmu.pebs_record_size = sizeof(struct pebs_record_skl); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; - x86_pmu.free_running_flags |= PERF_SAMPLE_TIME; + x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; default: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 78f91ec1056e..39cd0615f04f 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -69,7 +69,7 @@ struct event_constraint { #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ struct amd_nb { @@ -88,7 +88,7 @@ struct amd_nb { * REGS_USER can be handled for events limited to ring 3. * */ -#define PEBS_FREERUNNING_FLAGS \ +#define LARGE_PEBS_FLAGS \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ @@ -608,7 +608,7 @@ struct x86_pmu { struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); int max_pebs_events; - unsigned long free_running_flags; + unsigned long large_pebs_flags; /* * Intel LBR From 320b0651f32b830add6497fcdcfdcb6ae8c7b8a0 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 13 Mar 2018 11:51:34 -0700 Subject: [PATCH 4/5] perf/x86/intel/uncore: Fix multi-domain PCI CHA enumeration bug on Skylake servers The number of CHAs is miscalculated on multi-domain PCI Skylake server systems, resulting in an uncore driver initialization error. Gary Kroening explains: "For systems with a single PCI segment, it is sufficient to look for the bus number to change in order to determine that all of the CHa's have been counted for a single socket. However, for multi PCI segment systems, each socket is given a new segment and the bus number does NOT change. So looking only for the bus number to change ends up counting all of the CHa's on all sockets in the system. This leads to writing CPU MSRs beyond a valid range and causes an error in ivbep_uncore_msr_init_box()." To fix this bug, query the number of CHAs from the CAPID6 register: it should read bits 27:0 in the CAPID6 register located at Device 30, Function 3, Offset 0x9C. These 28 bits form a bit vector of available LLC slices and the CHAs that manage those slices. Reported-by: Kroening, Gary Tested-by: Kroening, Gary Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andy Shevchenko Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: abanman@hpe.com Cc: dimitri.sivanich@hpe.com Cc: hpa@zytor.com Cc: mike.travis@hpe.com Cc: russ.anderson@hpe.com Fixes: cd34cd97b7b4 ("perf/x86/intel/uncore: Add Skylake server uncore support") Link: http://lkml.kernel.org/r/1520967094-13219-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore_snbep.c | 31 +++++++++++++++------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 0876798f2ac9..c98b943e58b4 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3563,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = { NULL, }; +/* + * To determine the number of CHAs, it should read bits 27:0 in the CAPID6 + * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083. + */ +#define SKX_CAPID6 0x9c +#define SKX_CHA_BIT_MASK GENMASK(27, 0) + static int skx_count_chabox(void) { - struct pci_dev *chabox_dev = NULL; - int bus, count = 0; + struct pci_dev *dev = NULL; + u32 val = 0; - while (1) { - chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev); - if (!chabox_dev) - break; - if (count == 0) - bus = chabox_dev->bus->number; - if (bus != chabox_dev->bus->number) - break; - count++; - } + dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev); + if (!dev) + goto out; - pci_dev_put(chabox_dev); - return count; + pci_read_config_dword(dev, SKX_CAPID6, &val); + val &= SKX_CHA_BIT_MASK; +out: + pci_dev_put(dev); + return hweight32(val); } void skx_uncore_cpu_init(void) From c917e0f259908e75bd2a65877e25f9d90c22c848 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 12 Mar 2018 09:59:43 -0700 Subject: [PATCH 5/5] perf/cgroup: Fix child event counting bug When a perf_event is attached to parent cgroup, it should count events for all children cgroups: parent_group <---- perf_event \ - child_group <---- process(es) However, in our tests, we found this perf_event cannot report reliable results. Here is an example case: # create cgroups mkdir -p /sys/fs/cgroup/p/c # start perf for parent group perf stat -e instructions -G "p" # on another console, run test process in child cgroup: stressapptest -s 2 -M 1000 & echo $! > /sys/fs/cgroup/p/c/cgroup.procs # after the test process is done, stop perf in the first console shows instructions p The instruction should not be "not counted" as the process runs in the child cgroup. We found this is because perf_event->cgrp and cpuctx->cgrp are not identical, thus perf_event->cgrp are not updated properly. This patch fixes this by updating perf_cgroup properly for ancestor cgroup(s). Reported-by: Ephraim Park Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/20180312165943.1057894-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 4b838470fac4..709a55b9ad97 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp) static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp_out = cpuctx->cgrp; - if (cgrp_out) - __update_cgrp_time(cgrp_out); + struct perf_cgroup *cgrp = cpuctx->cgrp; + struct cgroup_subsys_state *css; + + if (cgrp) { + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + __update_cgrp_time(cgrp); + } + } } static inline void update_cgrp_time_from_event(struct perf_event *event) @@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, { struct perf_cgroup *cgrp; struct perf_cgroup_info *info; + struct cgroup_subsys_state *css; /* * ctx->lock held by caller @@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, return; cgrp = perf_cgroup_from_task(task, ctx); - info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + info = this_cpu_ptr(cgrp->info); + info->timestamp = ctx->timestamp; + } } static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);