From e97df76377b8b3b1f7dfd5d6f8a1d5a31438b140 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Feb 2014 20:48:51 +0100 Subject: perf/x86/intel/p6: Add userspace RDPMC quirk for PPro PPro machines can die hard when PCE gets enabled due to a CPU erratum. The safe way it so disable it by default and keep it disabled. See erratum 26 in: http://download.intel.com/design/archives/processors/pro/docs/24268935.pdf Reported-and-Tested-by: Mark Davies Cc: Alan Cox Cc: Stephane Eranian Cc: Vince Weaver Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140206170815.GW2936@laptop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 6 ++++- arch/x86/kernel/cpu/perf_event.h | 1 + arch/x86/kernel/cpu/perf_event_p6.c | 48 +++++++++++++++++++++++++------------ 3 files changed, 39 insertions(+), 16 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b88645191fe5..1246b853c4e0 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1521,6 +1521,8 @@ static int __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); @@ -1534,7 +1536,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0, 0); - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (x86_pmu.event_attrs) @@ -1820,6 +1821,9 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (ret) return ret; + if (x86_pmu.attr_rdpmc_broken) + return -ENOTSUPP; + if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; smp_call_function(change_rdpmc, (void *)val, 1); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index c1a861829d81..4972c244d0bc 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -409,6 +409,7 @@ struct x86_pmu { /* * sysfs attrs */ + int attr_rdpmc_broken; int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index b1e2fe115323..7c1a0c07b607 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = { }; +static __init void p6_pmu_rdpmc_quirk(void) +{ + if (boot_cpu_data.x86_mask < 9) { + /* + * PPro erratum 26; fixed in stepping 9 and above. + */ + pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n"); + x86_pmu.attr_rdpmc_broken = 1; + x86_pmu.attr_rdpmc = 0; + } +} + __init int p6_pmu_init(void) { + x86_pmu = p6_pmu; + switch (boot_cpu_data.x86_model) { - case 1: - case 3: /* Pentium Pro */ - case 5: - case 6: /* Pentium II */ - case 7: - case 8: - case 11: /* Pentium III */ - case 9: - case 13: - /* Pentium M */ + case 1: /* Pentium Pro */ + x86_add_quirk(p6_pmu_rdpmc_quirk); + break; + + case 3: /* Pentium II - Klamath */ + case 5: /* Pentium II - Deschutes */ + case 6: /* Pentium II - Mendocino */ break; + + case 7: /* Pentium III - Katmai */ + case 8: /* Pentium III - Coppermine */ + case 10: /* Pentium III Xeon */ + case 11: /* Pentium III - Tualatin */ + break; + + case 9: /* Pentium M - Banias */ + case 13: /* Pentium M - Dothan */ + break; + default: - pr_cont("unsupported p6 CPU model %d ", - boot_cpu_data.x86_model); + pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model); return -ENODEV; } - x86_pmu = p6_pmu; - memcpy(hw_cache_event_ids, p6_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - return 0; } -- cgit v1.2.3-70-g09d2 From 0e9f2204cfa6d79abe3e525ddf7c4ab5792cc751 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Feb 2014 11:19:56 +0100 Subject: perf/x86: Fix Userspace RDPMC switch The current code forgets to change the CR4 state on the current CPU. Use on_each_cpu() instead of smp_call_function(). Reported-by: Mark Davies Suggested-by: Mark Davies Signed-off-by: Peter Zijlstra Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/n/tip-69efsat90ibhnd577zy3z9gh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1246b853c4e0..895604f2e916 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1826,7 +1826,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; - smp_call_function(change_rdpmc, (void *)val, 1); + on_each_cpu(change_rdpmc, (void *)val, 1); } return count; -- cgit v1.2.3-70-g09d2 From a3ef2229c94ff70998724cb64b9cb4c77db9e950 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Fri, 14 Feb 2014 16:44:08 -0800 Subject: perf, nmi: Fix unknown NMI warning When using BTS on Core i7-4*, I get the below kernel warning. $ perf record -c 1 -e branches:u ls Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317893] Uhhuh. NMI received for unknown reason 31 on CPU 2. Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317920] Do you have a strange power saving mode enabled? Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317945] Dazed and confused, but trying to continue Make intel_pmu_handle_irq() take the full exit path when returning early. Cc: eranian@google.com Cc: peterz@infradead.org Cc: mingo@kernel.org Signed-off-by: Markus Metzger Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1392425048-5309-1-git-send-email-andi@firstfloor.org Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0fa4f242f050..698ae77d6f18 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); - if (!status) { - intel_pmu_enable_all(0); - return handled; - } + if (!status) + goto done; loops = 0; again: -- cgit v1.2.3-70-g09d2 From c9b08884c9c98929ec2d8abafd78e89062d01ee7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 3 Feb 2014 14:29:03 +0100 Subject: perf/x86: Correctly use FEATURE_PDCM The current code simply assumes Intel Arch PerfMon v2+ to have the IA32_PERF_CAPABILITIES MSR; the SDM specifies that we should check CPUID[1].ECX[15] (aka, FEATURE_PDCM) instead. This was found by KVM which implements v2+ but didn't provide the capabilities MSR. Change the code to DTRT; KVM will also implement the MSR and return 0. Cc: pbonzini@redhat.com Reported-by: "Michael S. Tsirkin" Suggested-by: Eduardo Habkost Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140203132903.GI8874@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 698ae77d6f18..aa333d966886 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2308,10 +2308,7 @@ __init int intel_pmu_init(void) if (version > 1) x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - /* - * v2 and above have a perf capabilities MSR - */ - if (version > 1) { + if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); -- cgit v1.2.3-70-g09d2 From 337397f3afc911d94d1d71371a36a53ce218b41f Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 19 Feb 2014 14:10:18 +0100 Subject: perf/x86/uncore: Fix IVT/SNB-EP uncore CBOX NID filter table This patch updates the CBOX PMU filters mapping tables for SNB-EP and IVT (model 45 and 62 respectively). The NID umask always comes in addition to another umask. When set, the NID filter is applied. The current mapping tables were missing some code/umask combinations to account for the NID umask. This patch fixes that. Cc: mingo@elte.hu Cc: ak@linux.intel.com Reviewed-by: Yan, Zheng Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140219131018.GA24475@quad Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel_uncore.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 29c248799ced..c88f7f4b03ee 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), @@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), -- cgit v1.2.3-70-g09d2 From 26e61e8939b1fe8729572dabe9a9e97d930dd4f6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 21 Feb 2014 16:03:12 +0100 Subject: perf/x86: Fix event scheduling Vince "Super Tester" Weaver reported a new round of syscall fuzzing (Trinity) failures, with perf WARN_ON()s triggering. He also provided traces of the failures. This is I think the relevant bit: > pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_disable: x86_pmu_disable > pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_state: Events: { > pec_1076_warn-2804 [000] d... 147.926156: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null)) > pec_1076_warn-2804 [000] d... 147.926158: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926159: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926160: x86_pmu_state: n_events: 1, n_added: 0, n_txn: 1 > pec_1076_warn-2804 [000] d... 147.926161: x86_pmu_state: Assignment: { > pec_1076_warn-2804 [000] d... 147.926162: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926163: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926166: collect_events: Adding event: 1 (ffff880119ec8800) So we add the insn:p event (fd[23]). At this point we should have: n_events = 2, n_added = 1, n_txn = 1 > pec_1076_warn-2804 [000] d... 147.926170: collect_events: Adding event: 0 (ffff8800c9e01800) > pec_1076_warn-2804 [000] d... 147.926172: collect_events: Adding event: 4 (ffff8800cbab2c00) We try and add the {BP,cycles,br_insn} group (fd[3], fd[4], fd[15]). These events are 0:cycles and 4:br_insn, the BP event isn't x86_pmu so that's not visible. group_sched_in() pmu->start_txn() /* nop - BP pmu */ event_sched_in() event->pmu->add() So here we should end up with: 0: n_events = 3, n_added = 2, n_txn = 2 4: n_events = 4, n_added = 3, n_txn = 3 But seeing the below state on x86_pmu_enable(), the must have failed, because the 0 and 4 events aren't there anymore. Looking at group_sched_in(), since the BP is the leader, its event_sched_in() must have succeeded, for otherwise we would not have seen the sibling adds. But since neither 0 or 4 are in the below state; their event_sched_in() must have failed; but I don't see why, the complete state: 0,0,1:p,4 fits perfectly fine on a core2. However, since we try and schedule 4 it means the 0 event must have succeeded! Therefore the 4 event must have failed, its failure will have put group_sched_in() into the fail path, which will call: event_sched_out() event->pmu->del() on 0 and the BP event. Now x86_pmu_del() will reduce n_events; but it will not reduce n_added; giving what we see below: n_event = 2, n_added = 2, n_txn = 2 > pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_enable: x86_pmu_enable > pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_state: Events: { > pec_1076_warn-2804 [000] d... 147.926179: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null)) > pec_1076_warn-2804 [000] d... 147.926181: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926182: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: n_events: 2, n_added: 2, n_txn: 2 > pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: Assignment: { > pec_1076_warn-2804 [000] d... 147.926186: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: 1->0 tag: 1 config: 1 (ffff880119ec8800) > pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926190: x86_pmu_enable: S0: hwc->idx: 33, hwc->last_cpu: 0, hwc->last_tag: 1 hwc->state: 0 So the problem is that x86_pmu_del(), when called from a group_sched_in() that fails (for whatever reason), and without x86_pmu TXN support (because the leader is !x86_pmu), will corrupt the n_added state. Reported-and-Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Stephane Eranian Cc: Dave Jones Cc: Link: http://lkml.kernel.org/r/20140221150312.GF3104@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 895604f2e916..79f9f848bee4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags) for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); -- cgit v1.2.3-70-g09d2