From 13301c6b16a6d809b331bb88e40ab9ce38238b8b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 20 Oct 2019 00:07:26 +0200 Subject: perf/x86/intel/pt: Fix base for single entry topa Jan reported failing ltp test for PT: https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/tracing/pt_test/pt_test.c It looks like the reason is this new commit added in this v5.4 merge window: 38bb8d77d0b9 ("perf/x86/intel/pt: Split ToPA metadata and page layout") which did not keep the TOPA_SHIFT for entry base. Add it back. Reported-by: Jan Stancek Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 38bb8d77d0b9 ("perf/x86/intel/pt: Split ToPA metadata and page layout") Link: https://lkml.kernel.org/r/20191019220726.12213-1-jolsa@kernel.org [ Minor changelog edits. ] Signed-off-by: Ingo Molnar --- arch/x86/events/intel/pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 74e80ed9c6c4..05e43d0f430b 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -627,7 +627,7 @@ static struct topa *topa_alloc(int cpu, gfp_t gfp) * link as the 2nd entry in the table */ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) { - TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p); + TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT; TOPA_ENTRY(&tp->topa, 1)->end = 1; } -- cgit v1.2.3 From 317b96bb14303c7998dbcd5bc606bd8038fdd4b4 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 23 Oct 2019 10:09:54 -0500 Subject: perf/x86/amd/ibs: Fix reading of the IBS OpData register and thus precise RIP validity The loop that reads all the IBS MSRs into *buf stopped one MSR short of reading the IbsOpData register, which contains the RipInvalid status bit. Fix the offset_max assignment so the MSR gets read, so the RIP invalid evaluation is based on what the IBS h/w output, instead of what was left in memory. Signed-off-by: Kim Phillips Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: d47e8238cd76 ("perf/x86-ibs: Take instruction pointer from ibs sample") Link: https://lkml.kernel.org/r/20191023150955.30292-1-kim.phillips@amd.com Signed-off-by: Ingo Molnar --- arch/x86/events/amd/ibs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 5b35b7ea5d72..98ba21a588a1 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -614,7 +614,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { -- cgit v1.2.3 From e431e79b60603079d269e0c2a5177943b95fa4b6 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 23 Oct 2019 10:09:55 -0500 Subject: perf/x86/amd/ibs: Handle erratum #420 only on the affected CPU family (10h) This saves us writing the IBS control MSR twice when disabling the event. I searched revision guides for all families since 10h, and did not find occurrence of erratum #420, nor anything remotely similar: so we isolate the secondary MSR write to family 10h only. Also unconditionally update the count mask for IBS Op implementations that have read & writeable current count (CurCnt) fields in addition to the MaxCnt field. These bits were reserved on prior implementations, and therefore shouldn't have negative impact. Signed-off-by: Kim Phillips Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: c9574fe0bdb9 ("perf/x86-ibs: Implement workaround for IBS erratum #420") Link: https://lkml.kernel.org/r/20191023150955.30292-2-kim.phillips@amd.com Signed-off-by: Ingo Molnar --- arch/x86/events/amd/ibs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 98ba21a588a1..26c36357c4c9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, -- cgit v1.2.3 From 75be6f703a141b048590d659a3954c4fedd30bba Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 25 Oct 2019 07:43:13 -0700 Subject: perf/x86/uncore: Fix event group support The events in the same group don't start or stop simultaneously. Here is the ftrace when enabling event group for uncore_iio_0: # perf stat -e "{uncore_iio_0/event=0x1/,uncore_iio_0/event=0xe/}" -0 [000] d.h. 8959.064832: read_msr: a41, value b2b0b030 //Read counter reg of IIO unit0 counter0 -0 [000] d.h. 8959.064835: write_msr: a48, value 400001 //Write Ctrl reg of IIO unit0 counter0 to enable counter0. <------ Although counter0 is enabled, Unit Ctrl is still freezed. Nothing will count. We are still good here. -0 [000] d.h. 8959.064836: read_msr: a40, value 30100 //Read Unit Ctrl reg of IIO unit0 -0 [000] d.h. 8959.064838: write_msr: a40, value 30000 //Write Unit Ctrl reg of IIO unit0 to enable all counters in the unit by clear Freeze bit <------Unit0 is un-freezed. Counter0 has been enabled. Now it starts counting. But counter1 has not been enabled yet. The issue starts here. -0 [000] d.h. 8959.064846: read_msr: a42, value 0 //Read counter reg of IIO unit0 counter1 -0 [000] d.h. 8959.064847: write_msr: a49, value 40000e //Write Ctrl reg of IIO unit0 counter1 to enable counter1. <------ Now, counter1 just starts to count. Counter0 has been running for a while. Current code un-freezes the Unit Ctrl right after the first counter is enabled. The subsequent group events always loses some counter values. Implement pmu_enable and pmu_disable support for uncore, which can help to batch hardware accesses. No one uses uncore_enable_box and uncore_disable_box. Remove them. 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: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: linux-drivers-review@eclists.intel.com Cc: linux-perf@eclists.intel.com Fixes: 087bfbb03269 ("perf/x86: Add generic Intel uncore PMU support") Link: https://lkml.kernel.org/r/1572014593-31591-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore.c | 44 ++++++++++++++++++++++++++++++++++++------ arch/x86/events/intel/uncore.h | 12 ------------ 2 files changed, 38 insertions(+), 18 deletions(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6fc2e06ab4c6..86467f85c383 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags) local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); uncore_enable_event(box, event); - if (box->n_active == 1) { - uncore_enable_box(box); + if (box->n_active == 1) uncore_pmu_start_hrtimer(box); - } } void uncore_pmu_event_stop(struct perf_event *event, int flags) @@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags) WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; - if (box->n_active == 0) { - uncore_disable_box(box); + if (box->n_active == 0) uncore_pmu_cancel_hrtimer(box); - } } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { @@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event) return ret; } +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { @@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) pmu->pmu = (struct pmu) { .attr_groups = pmu->type->attr_groups, .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, .event_init = uncore_pmu_event_init, .add = uncore_pmu_event_add, .del = uncore_pmu_event_del, diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index f36f7bebbc1b..bbfdaa720b45 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box, return -EINVAL; } -static inline void uncore_disable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->disable_box) - box->pmu->type->ops->disable_box(box); -} - -static inline void uncore_enable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->enable_box) - box->pmu->type->ops->enable_box(box); -} - static inline void uncore_disable_event(struct intel_uncore_box *box, struct perf_event *event) { -- cgit v1.2.3