From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Received: from mail-pb0-f49.google.com ([209.85.160.49]) by merlin.infradead.org with esmtps (Exim 4.76 #1 (Red Hat Linux)) id 1TbCD5-0003jl-66 for kexec@lists.infradead.org; Wed, 21 Nov 2012 15:27:31 +0000 Received: by mail-pb0-f49.google.com with SMTP id un15so4768182pbc.36 for ; Wed, 21 Nov 2012 07:27:30 -0800 (PST) Message-ID: <50ACF2D7.7060607@gmail.com> Date: Wed, 21 Nov 2012 23:27:19 +0800 From: Zhang Yanfei MIME-Version: 1.0 Subject: [PATCH v6 2/2] KVM-INTEL: add a notifier and a bitmap to support VMCLEAR in kdump References: <50ACF210.5020802@gmail.com> In-Reply-To: <50ACF210.5020802@gmail.com> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: kexec-bounces@lists.infradead.org Errors-To: kexec-bounces+dwmw2=infradead.org@lists.infradead.org To: x86@kernel.org, kexec@lists.infradead.org, mtosatti@redhat.com, Gleb Natapov Cc: zhangyanfei@cn.fujitsu.com, linux-kernel@vger.kernel.org, "kvm@vger.kernel.org" The notifier will be registered in vmclear_notifier_list when loading kvm-intel module. And the bitmap indicates whether we should do VMCLEAR operation in kdump. The bits in the bitmap are set/unset according to different conditions. Signed-off-by: Zhang Yanfei --- arch/x86/kvm/vmx.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++- 1 files changed, 76 insertions(+), 1 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4ff0ab9..eea55b3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -41,6 +41,7 @@ #include #include #include +#include #include "trace.h" @@ -963,6 +964,49 @@ static void vmcs_load(struct vmcs *vmcs) vmcs, phys_addr); } +#ifdef CONFIG_KEXEC +/* + * This bitmap is used to indicate whether the vmclear + * operation is enabled on all cpus. All disabled by + * default. + */ +static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; + +static inline void crash_enable_local_vmclear(int cpu) +{ + cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static inline void crash_disable_local_vmclear(int cpu) +{ + cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static inline int crash_local_vmclear_enabled(int cpu) +{ + return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); +} + +static void vmclear_local_loaded_vmcss(void); +static int crash_vmclear_local_loaded_vmcss(struct notifier_block *this, + unsigned long val, void *ptr) +{ + int cpu = raw_smp_processor_id(); + + if (crash_local_vmclear_enabled(cpu)) + vmclear_local_loaded_vmcss(); + + return NOTIFY_DONE; +} + +static struct notifier_block crash_vmclear_notifier = { + .notifier_call = crash_vmclear_local_loaded_vmcss, +}; +#else +static inline void crash_enable_local_vmclear(int cpu) { } +static inline void crash_disable_local_vmclear(int cpu) { } +#endif /* CONFIG_KEXEC */ + static void __loaded_vmcs_clear(void *arg) { struct loaded_vmcs *loaded_vmcs = arg; @@ -972,8 +1016,10 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; + crash_disable_local_vmclear(cpu); list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); loaded_vmcs_init(loaded_vmcs); + crash_enable_local_vmclear(cpu); } static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -1491,8 +1537,10 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); local_irq_disable(); + crash_disable_local_vmclear(cpu); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); + crash_enable_local_vmclear(cpu); local_irq_enable(); /* @@ -2302,6 +2350,18 @@ static int hardware_enable(void *garbage) return -EBUSY; INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + + /* + * Now we can enable the vmclear operation in kdump + * since the loaded_vmcss_on_cpu list on this cpu + * has been initialized. + * + * Though the cpu is not in VMX operation now, there + * is no problem to enable the vmclear operation + * for the loaded_vmcss_on_cpu list is empty! + */ + crash_enable_local_vmclear(cpu); + rdmsrl(MSR_IA32_FEATURE_CONTROL, old); test_bits = FEATURE_CONTROL_LOCKED; @@ -2335,7 +2395,6 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } - /* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot() * tricks. */ @@ -2348,6 +2407,12 @@ static void hardware_disable(void *garbage) { if (vmm_exclusive) { vmclear_local_loaded_vmcss(); + /* + * vmclear operation in kdump should be disabled here + * because the cpu is going to exit VMX operation + * and the loaded_vmcss_on_cpu list may not be empty! + */ + crash_disable_local_vmclear(raw_smp_processor_id()); kvm_cpu_vmxoff(); } write_cr4(read_cr4() & ~X86_CR4_VMXE); @@ -7230,6 +7295,11 @@ static int __init vmx_init(void) if (r) goto out3; +#ifdef CONFIG_KEXEC + atomic_notifier_chain_register(&vmclear_notifier_list, + &crash_vmclear_notifier); +#endif + vmx_disable_intercept_for_msr(MSR_FS_BASE, false); vmx_disable_intercept_for_msr(MSR_GS_BASE, false); vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); @@ -7265,6 +7335,11 @@ static void __exit vmx_exit(void) free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); +#ifdef CONFIG_KEXEC + atomic_notifier_chain_unregister(&vmclear_notifier_list, + &crash_vmclear_notifier); +#endif + kvm_exit(); } -- 1.7.1 _______________________________________________ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec