From patchwork Mon Apr 19 05:32:41 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yanmin Zhang X-Patchwork-Id: 93420 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o3J5Y8ER003338 for ; Mon, 19 Apr 2010 05:34:09 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752067Ab0DSFdY (ORCPT ); Mon, 19 Apr 2010 01:33:24 -0400 Received: from mga12.intel.com ([143.182.124.36]:39678 "EHLO azsmga102.ch.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751744Ab0DSFdF (ORCPT ); Mon, 19 Apr 2010 01:33:05 -0400 Received: from azsmga001.ch.intel.com ([10.2.17.19]) by azsmga102.ch.intel.com with ESMTP; 18 Apr 2010 22:33:03 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.52,234,1270450800"; d="scan'208";a="267235202" Received: from ymzhang.sh.intel.com (HELO [10.239.13.36]) ([10.239.13.36]) by azsmga001.ch.intel.com with ESMTP; 18 Apr 2010 22:33:00 -0700 Subject: [PATCH V5 1/3] perf & kvm: Enhance perf to collect KVM guest os statistics from host side From: "Zhang, Yanmin" To: Avi Kivity Cc: Ingo Molnar , Peter Zijlstra , Avi Kivity , Sheng Yang , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, Marcelo Tosatti , oerg Roedel , Jes Sorensen , Gleb Natapov , Zachary Amsden , zhiteng.huang@intel.com, tim.c.chen@intel.com, Arnaldo Carvalho de Melo Date: Mon, 19 Apr 2010 13:32:41 +0800 Message-Id: <1271655161.2078.603.camel@ymzhang.sh.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.28.0 (2.28.0-2.fc12) Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Mon, 19 Apr 2010 05:34:09 +0000 (UTC) diff -Nraup --exclude-from=exclude.diff linux-2.6_tip0417/arch/x86/include/asm/perf_event.h linux-2.6_tip0417_perfkvm/arch/x86/include/asm/perf_event.h --- linux-2.6_tip0417/arch/x86/include/asm/perf_event.h 2010-04-19 09:51:47.557797121 +0800 +++ linux-2.6_tip0417_perfkvm/arch/x86/include/asm/perf_event.h 2010-04-19 09:53:59.689452915 +0800 @@ -135,17 +135,10 @@ extern void perf_events_lapic_init(void) */ #define PERF_EFLAGS_EXACT (1UL << 3) -#define perf_misc_flags(regs) \ -({ int misc = 0; \ - if (user_mode(regs)) \ - misc |= PERF_RECORD_MISC_USER; \ - else \ - misc |= PERF_RECORD_MISC_KERNEL; \ - if (regs->flags & PERF_EFLAGS_EXACT) \ - misc |= PERF_RECORD_MISC_EXACT; \ - misc; }) - -#define perf_instruction_pointer(regs) ((regs)->ip) +struct pt_regs; +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) #else static inline void init_hw_perf_events(void) { } diff -Nraup --exclude-from=exclude.diff linux-2.6_tip0417/arch/x86/kernel/cpu/perf_event.c linux-2.6_tip0417_perfkvm/arch/x86/kernel/cpu/perf_event.c --- linux-2.6_tip0417/arch/x86/kernel/cpu/perf_event.c 2010-04-19 09:51:48.347655964 +0800 +++ linux-2.6_tip0417_perfkvm/arch/x86/kernel/cpu/perf_event.c 2010-04-19 09:53:59.689452915 +0800 @@ -1720,6 +1720,11 @@ struct perf_callchain_entry *perf_callch { struct perf_callchain_entry *entry; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* TODO: We don't support guest os callchain now */ + return NULL; + } + if (in_nmi()) entry = &__get_cpu_var(pmc_nmi_entry); else @@ -1743,3 +1748,30 @@ void perf_arch_fetch_caller_regs(struct regs->cs = __KERNEL_CS; local_save_flags(regs->flags); } + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + unsigned long ip; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + ip = perf_guest_cbs->get_guest_ip(); + else + ip = instruction_pointer(regs); + return ip; +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + int misc = 0; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + misc |= perf_guest_cbs->is_user_mode() ? + PERF_RECORD_MISC_GUEST_USER : + PERF_RECORD_MISC_GUEST_KERNEL; + } else + misc |= user_mode(regs) ? PERF_RECORD_MISC_USER : + PERF_RECORD_MISC_KERNEL; + if (regs->flags & PERF_EFLAGS_EXACT) + misc |= PERF_RECORD_MISC_EXACT; + + return misc; +} + diff -Nraup --exclude-from=exclude.diff linux-2.6_tip0417/include/linux/perf_event.h linux-2.6_tip0417_perfkvm/include/linux/perf_event.h --- linux-2.6_tip0417/include/linux/perf_event.h 2010-04-19 09:51:59.544791000 +0800 +++ linux-2.6_tip0417_perfkvm/include/linux/perf_event.h 2010-04-19 09:53:59.691378953 +0800 @@ -288,11 +288,13 @@ struct perf_event_mmap_page { __u64 data_tail; /* user-space written tail */ }; -#define PERF_RECORD_MISC_CPUMODE_MASK (3 << 0) +#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) #define PERF_RECORD_MISC_USER (2 << 0) #define PERF_RECORD_MISC_HYPERVISOR (3 << 0) +#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) +#define PERF_RECORD_MISC_GUEST_USER (5 << 0) #define PERF_RECORD_MISC_EXACT (1 << 14) /* @@ -446,6 +448,12 @@ enum perf_callchain_context { # include #endif +struct perf_guest_info_callbacks { + int (*is_in_guest) (void); + int (*is_user_mode) (void); + unsigned long (*get_guest_ip) (void); +}; + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include #endif @@ -932,6 +940,12 @@ static inline void perf_event_mmap(struc __perf_event_mmap(vma); } +extern struct perf_guest_info_callbacks *perf_guest_cbs; +extern int perf_register_guest_info_callbacks( + struct perf_guest_info_callbacks *); +extern int perf_unregister_guest_info_callbacks( + struct perf_guest_info_callbacks *); + extern void perf_event_comm(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); @@ -1001,6 +1015,11 @@ perf_sw_event(u32 event_id, u64 nr, int static inline void perf_bp_event(struct perf_event *event, void *data) { } +static inline int perf_register_guest_info_callbacks +(struct perf_guest_info_callbacks *) {return 0; } +static inline int perf_unregister_guest_info_callbacks +(struct perf_guest_info_callbacks *) {return 0; } + static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } diff -Nraup --exclude-from=exclude.diff linux-2.6_tip0417/kernel/perf_event.c linux-2.6_tip0417_perfkvm/kernel/perf_event.c --- linux-2.6_tip0417/kernel/perf_event.c 2010-04-19 09:52:40.907135718 +0800 +++ linux-2.6_tip0417_perfkvm/kernel/perf_event.c 2010-04-19 09:53:59.693377237 +0800 @@ -2798,6 +2798,27 @@ void perf_arch_fetch_caller_regs(struct /* + * We assume there is only KVM supporting the callbacks. + * Later on, we might change it to a list if there is + * another virtualization implementation supporting the callbacks. + */ +struct perf_guest_info_callbacks *perf_guest_cbs; + +int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = cbs; + return 0; +} +EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); + +int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = NULL; + return 0; +} +EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); + +/* * Output */ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail, @@ -3749,7 +3770,7 @@ void __perf_event_mmap(struct vm_area_st .event_id = { .header = { .type = PERF_RECORD_MMAP, - .misc = 0, + .misc = PERF_RECORD_MISC_USER, /* .size */ }, /* .pid */