[2/2] kvm: change the dirty page tracking to work with dirty bit instead of page fault

Message ID	1244634691-9765-3-git-send-email-ieidus@redhat.com (mailing list archive)
State	New, archived
Headers	show Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id n5ABqvxk024191 for <patchwork-kvm@patchwork.kernel.org>; Wed, 10 Jun 2009 11:52:58 GMT From: Izik Eidus <ieidus@redhat.com> To: kvm@vger.kernel.org Cc: avi@redhat.com, Izik Eidus <ieidus@redhat.com> Subject: [PATCH 2/2] kvm: change the dirty page tracking to work with dirty bit instead of page fault Date: Wed, 10 Jun 2009 14:51:31 +0300 Message-Id: <1244634691-9765-3-git-send-email-ieidus@redhat.com> In-Reply-To: <1244634691-9765-2-git-send-email-ieidus@redhat.com> References: <1244634691-9765-1-git-send-email-ieidus@redhat.com> <1244634691-9765-2-git-send-email-ieidus@redhat.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 3199221..5914128 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1809,6 +1809,10 @@ void kvm_arch_exit(void) kvm_vmm_info = NULL; } +void kvm_arch_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ +} + static int kvm_ia64_sync_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 2cf915e..6beb368 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -418,6 +418,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return -ENOTSUPP; } +void kvm_arch_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 981ab04..ab6f115 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -130,6 +130,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, return 0; } +void kvm_arch_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c7b0cc2..8a24149 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -527,6 +527,7 @@ struct kvm_x86_ops { int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + int (*dirty_bit_support)(void); }; extern struct kvm_x86_ops *kvm_x86_ops; @@ -796,4 +797,6 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_age_hva(struct kvm *kvm, unsigned long hva); int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); +int is_dirty_and_clean_rmapp(struct kvm *kvm, unsigned long *rmapp); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 809cce0..3ec6a7d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -140,6 +140,8 @@ module_param(oos_shadow, bool, 0644); #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +#define SPTE_DONT_DIRTY (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) + #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) struct kvm_rmap_desc { @@ -629,6 +631,25 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) return NULL; } +int is_dirty_and_clean_rmapp(struct kvm *kvm, unsigned long *rmapp) +{ + u64 *spte; + int dirty = 0; + + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + if (*spte & PT_DIRTY_MASK) { + set_shadow_pte(spte, (*spte &= ~PT_DIRTY_MASK) | + SPTE_DONT_DIRTY); + dirty = 1; + } + spte = rmap_next(kvm, rmapp, spte); + } + + return dirty; +} + + static int rmap_write_protect(struct kvm *kvm, u64 gfn) { unsigned long *rmapp; @@ -1676,7 +1697,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, * whether the guest actually used the pte (in order to detect * demand paging). */ - spte = shadow_base_present_pte | shadow_dirty_mask; + spte = shadow_base_present_pte; + if (!(spte & SPTE_DONT_DIRTY)) + spte |= shadow_dirty_mask; + if (!speculative) spte |= shadow_accessed_mask; if (!dirty) @@ -1725,8 +1749,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, } } - if (pte_access & ACC_WRITE_MASK) - mark_page_dirty(vcpu->kvm, gfn); + if (!shadow_dirty_mask) { + if (pte_access & ACC_WRITE_MASK) + mark_page_dirty(vcpu->kvm, gfn); + } set_pte: set_shadow_pte(shadow_pte, spte); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 37397f6..5b6351e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2724,6 +2724,11 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return 0; } +static int svm_dirty_bit_support(void) +{ + return 1; +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -2785,6 +2790,8 @@ static struct kvm_x86_ops svm_x86_ops = { .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, .get_mt_mask = svm_get_mt_mask, + + .dirty_bit_support = svm_dirty_bit_support, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 673bcb3..8903314 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3774,6 +3774,11 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return ret; } +static int vmx_dirty_bit_support(void) +{ + return false; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -3833,6 +3838,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, .get_mt_mask = vmx_get_mt_mask, + + .dirty_bit_support = vmx_dirty_bit_support, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 272e2e8..d28fbcb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1963,6 +1963,19 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, return 0; } +void kvm_arch_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ + int i; + gfn_t gfn; + + for (i = 0; i < memslot->npages; ++i) { + if (!test_bit(i, memslot->dirty_bitmap)) { + if (is_dirty_and_clean_rmapp(kvm, &memslot->rmap[i])) + set_bit(i, memslot->dirty_bitmap); + } + } +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -1982,9 +1995,11 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - spin_lock(&kvm->mmu_lock); - kvm_mmu_slot_remove_write_access(kvm, log->slot); - spin_unlock(&kvm->mmu_lock); + if (kvm_x86_ops->dirty_bit_support()) { + spin_lock(&kvm->mmu_lock); + kvm_mmu_slot_remove_write_access(kvm, log->slot); + spin_unlock(&kvm->mmu_lock); + } kvm_flush_remote_tlbs(kvm); memslot = &kvm->memslots[log->slot]; n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cdf1279..d1657a3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -250,6 +250,7 @@ int kvm_dev_ioctl_check_extension(long ext); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty); +void kvm_arch_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4a60c72..bddc561 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -998,14 +998,18 @@ out: /* * Free any memory in @free but not in @dont. */ -static void kvm_free_physmem_slot(struct kvm_memory_slot *free, +static void kvm_free_physmem_slot(struct kvm *kvm, + struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { if (!dont || free->rmap != dont->rmap) vfree(free->rmap); - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) + if (!dont || free->dirty_bitmap != dont->dirty_bitmap) { + if (dont && free->rmap == dont->rmap) + kvm_arch_flush_shadow(kvm); vfree(free->dirty_bitmap); + } if (!dont || free->lpage_info != dont->lpage_info) vfree(free->lpage_info); @@ -1021,7 +1025,7 @@ void kvm_free_physmem(struct kvm *kvm) int i; for (i = 0; i < kvm->nmemslots; ++i) - kvm_free_physmem_slot(&kvm->memslots[i], NULL); + kvm_free_physmem_slot(kvm, &kvm->memslots[i], NULL); } static void kvm_destroy_vm(struct kvm *kvm) @@ -1217,7 +1221,7 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out_free; } - kvm_free_physmem_slot(&old, npages ? &new : NULL); + kvm_free_physmem_slot(kvm, &old, npages ? &new : NULL); /* Slot deletion case: we have to update the current slot */ spin_lock(&kvm->mmu_lock); if (!npages) @@ -1232,7 +1236,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return 0; out_free: - kvm_free_physmem_slot(&new, &old); + kvm_free_physmem_slot(kvm, &new, &old); out: return r; @@ -1279,6 +1283,7 @@ int kvm_get_dirty_log(struct kvm *kvm, if (!memslot->dirty_bitmap) goto out; + kvm_arch_get_dirty_log(kvm, memslot); n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; for (i = 0; !any && i < n/sizeof(long); ++i)

[2/2] kvm: change the dirty page tracking to work with dirty bit instead of page fault

Commit Message

Comments

Patch