From afbef30149587ad46f4780b1e0cc5e219745ce90 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 30 Nov 2020 11:38:41 -0800 Subject: perf/x86/intel: Set PERF_ATTACH_SCHED_CB for large PEBS and LBR To supply a PID/TID for large PEBS, it requires flushing the PEBS buffer in a context switch. For normal LBRs, a context switch can flip the address space and LBR entries are not tagged with an identifier, we need to wipe the LBR, even for per-cpu events. For LBR callstack, save/restore the stack is required during a context switch. Set PERF_ATTACH_SCHED_CB for the event with large PEBS & LBR. Fixes: 9c964efa4330 ("perf/x86/intel: Drain the PEBS buffer during context switches") Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20201130193842.10569-2-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 5bac48d5c18e..7bbb5bb98d8c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3662,8 +3662,10 @@ static int intel_pmu_hw_config(struct perf_event *event) if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & - ~intel_pmu_large_pebs_flags(event))) + ~intel_pmu_large_pebs_flags(event))) { event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; + event->attach_state |= PERF_ATTACH_SCHED_CB; + } } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); @@ -3676,6 +3678,7 @@ static int intel_pmu_hw_config(struct perf_event *event) ret = intel_pmu_setup_lbr_filter(event); if (ret) return ret; + event->attach_state |= PERF_ATTACH_SCHED_CB; /* * BTS is set up earlier in this path, so don't account twice -- cgit v1.2.3 From c8e2fe13d1d1f3a02842b7b909d4e4846a4b6a2c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 9 Mar 2021 09:10:19 -0800 Subject: x86/perf: Use RET0 as default for guest_get_msrs to handle "no PMU" case Initialize x86_pmu.guest_get_msrs to return 0/NULL to handle the "nop" case. Patching in perf_guest_get_msrs_nop() during setup does not work if there is no PMU, as setup bails before updating the static calls, leaving x86_pmu.guest_get_msrs NULL and thus a complete nop. Ultimately, this causes VMX abort on VM-Exit due to KVM putting random garbage from the stack into the MSR load list. Add a comment in KVM to note that nr_msrs is valid if and only if the return value is non-NULL. Fixes: abd562df94d1 ("x86/perf: Use static_call for x86_pmu.guest_get_msrs") Reported-by: Dmitry Vyukov Reported-by: syzbot+cce9ef2dd25246f815ee@syzkaller.appspotmail.com Suggested-by: Peter Zijlstra Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210309171019.1125243-1-seanjc@google.com --- arch/x86/events/core.c | 15 ++++++--------- arch/x86/kvm/vmx/vmx.c | 2 +- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'arch/x86/events') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 6ddeed3cd2ac..18df17129695 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -81,7 +81,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx); DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); -DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs); +/* + * This one is magic, it will get called even when PMU init fails (because + * there is no PMU), in which case it should simply return NULL. + */ +DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs); u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -1944,13 +1948,6 @@ static void _x86_pmu_read(struct perf_event *event) x86_perf_event_update(event); } -static inline struct perf_guest_switch_msr * -perf_guest_get_msrs_nop(int *nr) -{ - *nr = 0; - return NULL; -} - static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -2025,7 +2022,7 @@ static int __init init_hw_perf_events(void) x86_pmu.read = _x86_pmu_read; if (!x86_pmu.guest_get_msrs) - x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop; + x86_pmu.guest_get_msrs = (void *)&__static_call_return0; x86_pmu_static_call_update(); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 50810d471462..32cf8287d4a7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) int i, nr_msrs; struct perf_guest_switch_msr *msrs; + /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ msrs = perf_guest_get_msrs(&nr_msrs); - if (!msrs) return; -- cgit v1.2.3