From 1279e41d535e28cc3b56fa4a09e71a709641cae6 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Wed, 3 Apr 2019 14:54:24 +0800 Subject: perf/headers: Fix stale comment for struct perf_addr_filter The @inode field has been removed after: 9511bce9fe8e ("perf/core: Fix bad use of igrab()") Update the description. Signed-off-by: Shaokun Zhang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: https://lkml.kernel.org/r/1554274464-5739-1-git-send-email-zhangshaokun@hisilicon.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..085a95e2582a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -464,7 +464,7 @@ enum perf_addr_filter_action_t { /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage - * @inode: object file's inode for file-based filters + * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop -- cgit v1.2.3 From c68d224e5ed15605e651e2482c6ffd95915ddf58 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 8 Apr 2019 10:32:51 -0700 Subject: perf/core: Add perf_pmu_resched() as global function This patch add perf_pmu_resched() a global function that can be called to force rescheduling of events for a given PMU. The function locks both cpuctx and task_ctx internally. This will be used by a subsequent patch. Signed-off-by: Stephane Eranian [ Simplified the calling convention. ] 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 Cc: kan.liang@intel.com Cc: nelson.dsouza@intel.com Cc: tonyj@suse.com Link: https://lkml.kernel.org/r/20190408173252.37932-2-eranian@google.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 +++ kernel/events/core.c | 10 ++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 085a95e2582a..f3864e1c5569 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -888,6 +888,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); + +extern void perf_pmu_resched(struct pmu *pmu); + extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); diff --git a/kernel/events/core.c b/kernel/events/core.c index 30a572e4c6f1..abbd4b3b96c2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2478,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, perf_pmu_enable(cpuctx->ctx.pmu); } +void perf_pmu_resched(struct pmu *pmu) +{ + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); + perf_ctx_unlock(cpuctx, task_ctx); +} + /* * Cross CPU call to install and enable a performance event * -- cgit v1.2.3 From d15d356887e770c5f2dcf963b52c7cb510c9e42d Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 23 Apr 2019 00:26:52 +0800 Subject: perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER Currently perf callchain doesn't work well with ORC unwinder when sampling from trace point. We'll get useless in kernel callchain like this: perf 6429 [000] 22.498450: kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) 7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 5651468729c1 [unknown] (/usr/bin/perf) 5651467ee82a main+0x69a (/usr/bin/perf) 7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) The root cause is that, for trace point events, it doesn't provide a real snapshot of the hardware registers. Instead perf tries to get required caller's registers and compose a fake register snapshot which suppose to contain enough information for start a unwinding. However without CONFIG_FRAME_POINTER, if failed to get caller's BP as the frame pointer, so current frame pointer is returned instead. We get a invalid register combination which confuse the unwinder, and end the stacktrace early. So in such case just don't try dump BP, and let the unwinder start directly when the register is not a real snapshot. Use SP as the skip mark, unwinder will skip all the frames until it meet the frame of the trace point caller. Tested with frame pointer unwinder and ORC unwinder, this makes perf callchain get the full kernel space stacktrace again like this: perf 6503 [000] 1567.570191: kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux) 7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 55a22960d9c1 [unknown] (/usr/bin/perf) 55a22958982a main+0x69a (/usr/bin/perf) 7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) Co-developed-by: Josh Poimboeuf Signed-off-by: Kairui Song Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Dave Young Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190422162652.15483-1-kasong@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 21 +++++++++++++++++---- arch/x86/include/asm/perf_event.h | 7 +------ arch/x86/include/asm/stacktrace.h | 13 ------------- include/linux/perf_event.h | 14 ++++++++++---- 4 files changed, 28 insertions(+), 27 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index de1a924a4914..f315425d8468 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2382,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2393,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 04768a3a5454..1392d5e6e8d6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -308,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f3864e1c5569..cf023db0e8a2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1058,12 +1058,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { -- cgit v1.2.3 From 8479e04e7d6b1974629a0f657afa8ec5f17d2e90 Mon Sep 17 00:00:00 2001 From: Luwei Kang Date: Mon, 18 Feb 2019 19:26:07 -0500 Subject: KVM: x86: Inject PMI for KVM guest Inject a PMI for KVM guest when Intel PT working in Host-Guest mode and Guest ToPA entry memory buffer was completely filled. Signed-off-by: Luwei Kang Signed-off-by: Paolo Bonzini --- arch/x86/events/intel/core.c | 6 +++++- arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kvm/x86.c | 10 ++++++++++ include/linux/perf_event.h | 1 + 4 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux/perf_event.h') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 8baa441d8000..386151b2c62f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2307,7 +2307,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (__test_and_clear_bit(55, (unsigned long *)&status)) { handled++; - intel_pt_interrupt(); + if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() && + perf_guest_cbs->handle_intel_pt_intr)) + perf_guest_cbs->handle_intel_pt_intr(); + else + intel_pt_interrupt(); } /* diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..be40c094bc49 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -781,6 +781,10 @@ #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +/* PERF_GLOBAL_OVF_CTL bits */ +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55 +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT) + /* Geode defined MSRs */ #define MSR_GEODE_BUSCONT_CONF0 0x00001900 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c27d224f744..cedd396e3003 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6839,10 +6839,20 @@ static unsigned long kvm_get_guest_ip(void) return ip; } +static void kvm_handle_intel_pt_intr(void) +{ + struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); + + kvm_make_request(KVM_REQ_PMI, vcpu); + __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, + (unsigned long *)&vcpu->arch.pmu.global_status); +} + static struct perf_guest_info_callbacks kvm_guest_cbs = { .is_in_guest = kvm_is_in_guest, .is_user_mode = kvm_is_user_mode, .get_guest_ip = kvm_get_guest_ip, + .handle_intel_pt_intr = kvm_handle_intel_pt_intr, }; static void kvm_set_mmio_spte_mask(void) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..820c4ff31bc5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -30,6 +30,7 @@ struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); + void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT -- cgit v1.2.3