From: Lan Tianyu Date: Sun, 13 Mar 2016 03:10:24 +0000 (+0800) Subject: KVM: Remove redundant smp_mb() in the kvm_mmu_commit_zap_page() X-Git-Tag: v4.14-rc1~3564^2~9 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=9753f529156d03112d1ff6f3758ccd6fa6faf189;p=platform%2Fkernel%2Flinux-rpi.git KVM: Remove redundant smp_mb() in the kvm_mmu_commit_zap_page() There is already a barrier inside of kvm_flush_remote_tlbs() which can help to make sure everyone sees our modifications to the page tables and see changes to vcpu->mode here. So remove the smp_mb in the kvm_mmu_commit_zap_page() and update the comment. Signed-off-by: Lan Tianyu Signed-off-by: Paolo Bonzini --- diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e46a81f..fc8ab1f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2390,14 +2390,13 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, return; /* - * wmb: make sure everyone sees our modifications to the page tables - * rmb: make sure we see changes to vcpu->mode - */ - smp_mb(); - - /* - * Wait for all vcpus to exit guest mode and/or lockless shadow - * page table walks. + * We need to make sure everyone sees our modifications to + * the page tables and see changes to vcpu->mode here. The barrier + * in the kvm_flush_remote_tlbs() achieves this. This pairs + * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end. + * + * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit + * guest mode and/or lockless shadow page table walks. */ kvm_flush_remote_tlbs(kvm);