[20/27] KVM: x86/mmu: Drop infrastructure for multiple page-track modes

Message ID	20221223005739.1295925-21-seanjc@google.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <kvm-owner@vger.kernel.org> Reply-To: Sean Christopherson <seanjc@google.com> Date: Fri, 23 Dec 2022 00:57:32 +0000 In-Reply-To: <20221223005739.1295925-1-seanjc@google.com> Mime-Version: 1.0 References: <20221223005739.1295925-1-seanjc@google.com> Message-ID: <20221223005739.1295925-21-seanjc@google.com> Subject: [PATCH 20/27] KVM: x86/mmu: Drop infrastructure for multiple page-track modes From: Sean Christopherson <seanjc@google.com> To: Sean Christopherson <seanjc@google.com>, Paolo Bonzini <pbonzini@redhat.com>, Zhenyu Wang <zhenyuw@linux.intel.com>, Zhi Wang <zhi.a.wang@intel.com> Cc: kvm@vger.kernel.org, intel-gvt-dev@lists.freedesktop.org, intel-gfx@lists.freedesktop.org, linux-kernel@vger.kernel.org, Yan Zhao <yan.y.zhao@intel.com>, Ben Gardon <bgardon@google.com> Content-Type: text/plain; charset="UTF-8" Precedence: bulk
Series	drm/i915/gvt: KVM: KVMGT fixes and page-track cleanups \| expand [00/27] drm/i915/gvt: KVM: KVMGT fixes and page-track cleanups [01/27] drm/i915/gvt: Verify pfn is "valid" before dereferencing "struct page" [02/27] KVM: x86/mmu: Factor out helper to get max mapping size of a memslot [03/27] drm/i915/gvt: Incorporate KVM memslot info into check for 2MiB GTT entry [04/27] drm/i915/gvt: Verify VFIO-pinned page is THP when shadowing 2M gtt entry [05/27] drm/i915/gvt: Put the page reference obtained by KVM's gfn_to_pfn() [06/27] drm/i915/gvt: Don't rely on KVM's gfn_to_pfn() to query possible 2M GTT [07/27] drm/i915/gvt: Use an "unsigned long" to iterate over memslot gfns [08/27] drm/i915/gvt: Hoist acquisition of vgpu_lock out to kvmgt_page_track_write() [09/27] drm/i915/gvt: Protect gfn hash table with dedicated mutex [10/27] KVM: x86/mmu: Don't rely on page-track mechanism to flush on memslot change [11/27] KVM: x86/mmu: Don't bounce through page-track mechanism for guest PTEs [12/27] KVM: drm/i915/gvt: Drop @vcpu from KVM's ->track_write() hook [13/27] KVM: x86: Reject memslot MOVE operations if KVMGT is attached [14/27] drm/i915/gvt: Don't bother removing write-protection on to-be-deleted slot [15/27] KVM: x86: Add a new page-track hook to handle memslot deletion [16/27] drm/i915/gvt: switch from ->track_flush_slot() to ->track_remove_region() [17/27] KVM: x86: Remove the unused page-track hook track_flush_slot() [18/27] KVM: x86/mmu: Move KVM-only page-track declarations to internal header [19/27] KVM: x86/mmu: Use page-track notifiers iff there are external users [20/27] KVM: x86/mmu: Drop infrastructure for multiple page-track modes [21/27] KVM: x86/mmu: Rename page-track APIs to reflect the new reality [22/27] KVM: x86/mmu: Assert that correct locks are held for page write-tracking [23/27] KVM: x86/mmu: Bug the VM if write-tracking is used but not enabled [24/27] KVM: x86/mmu: Drop @slot param from exported/external page-track APIs [25/27] KVM: x86/mmu: Handle KVM bookkeeping in page-track APIs, not callers [26/27] KVM: x86/mmu: Add page-track API to query if a gfn is valid [27/27] drm/i915/gvt: Drop final dependencies on KVM internal details

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e8f8e1bd96c7..f110e1bd1282 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -290,13 +290,13 @@ struct kvm_kernel_irq_routing_entry; * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page * also includes TDP pages) to determine whether or not a page can be used in * the given MMU context. This is a subset of the overall kvm_cpu_role to - * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating - * 2 bytes per gfn instead of 4 bytes per gfn. + * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows + * allocating 2 bytes per gfn instead of 4 bytes per gfn. * * Upper-level shadow pages having gptes are tracked for write-protection via - * gfn_track. As above, gfn_track is a 16 bit counter, so KVM must not create - * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise - * gfn_track will overflow and explosions will ensure. + * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must + * not create more than 2^16-1 upper-level shadow pages at a single gfn, + * otherwise gfn_write_track will overflow and explosions will ensue. * * A unique shadow page (SP) for a gfn is created if and only if an existing SP * cannot be reused. The ability to reuse a SP is tracked by its role, which @@ -1018,7 +1018,7 @@ struct kvm_lpage_info { struct kvm_arch_memory_slot { struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; - unsigned short *gfn_track[KVM_PAGE_TRACK_MAX]; + unsigned short *gfn_write_track; }; /* diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 53c2adb25a07..42a4ae451d36 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -4,11 +4,6 @@ #include <linux/kvm_types.h> -enum kvm_page_track_mode { - KVM_PAGE_TRACK_WRITE, - KVM_PAGE_TRACK_MAX, -}; - /* * The notifier represented by @kvm_page_track_notifier_node is linked into * the head which will be notified when guest is triggering the track event. @@ -49,11 +44,9 @@ struct kvm_page_track_notifier_node { }; void kvm_slot_page_track_add_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); + struct kvm_memory_slot *slot, gfn_t gfn); void kvm_slot_page_track_remove_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); + struct kvm_memory_slot *slot, gfn_t gfn); #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING enum pg_level kvm_page_track_max_mapping_level(struct kvm *kvm, gfn_t gfn, diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6477ef435575..ffcfc75cd4c1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -807,8 +807,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) /* the non-leaf shadow pages are keeping readonly. */ if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_add_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return kvm_slot_page_track_add_page(kvm, slot, gfn); kvm_mmu_gfn_disallow_lpage(slot, gfn); @@ -854,8 +853,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_remove_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return kvm_slot_page_track_remove_page(kvm, slot, gfn); kvm_mmu_gfn_allow_lpage(slot, gfn); } @@ -2727,7 +2725,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(kvm, slot, gfn)) return -EPERM; /* @@ -4137,7 +4135,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn)) return true; return false; @@ -5366,8 +5364,8 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * physical address properties) in a single VM would require tracking * all relevant CPUID information in kvm_mmu_page_role. That is very * undesirable as it would increase the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments). For now that - * problem is swept under the rug; KVM's CPUID API is horrific and + * gfn_write_track (see struct kvm_mmu_page_role comments). For now + * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.root_role.word = 0; diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index f932909aa9b5..4077aa6d6ff4 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -26,76 +26,50 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { - int i; + kvfree(slot->arch.gfn_write_track); + slot->arch.gfn_write_track = NULL; +} - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - kvfree(slot->arch.gfn_track[i]); - slot->arch.gfn_track[i] = NULL; - } +static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot, + unsigned long npages) +{ + const size_t size = sizeof(*slot->arch.gfn_write_track); + + if (!slot->arch.gfn_write_track) + slot->arch.gfn_write_track = __vcalloc(npages, size, + GFP_KERNEL_ACCOUNT); + + return slot->arch.gfn_write_track ? 0 : -ENOMEM; } int kvm_page_track_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { - int i; - - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - if (i == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) - continue; - - slot->arch.gfn_track[i] = - __vcalloc(npages, sizeof(*slot->arch.gfn_track[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.gfn_track[i]) - goto track_free; - } - - return 0; - -track_free: - kvm_page_track_free_memslot(slot); - return -ENOMEM; -} - -static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode) -{ - if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX) - return false; - - return true; -} - -int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot) -{ - unsigned short *gfn_track; - - if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE]) + if (!kvm_page_track_write_tracking_enabled(kvm)) return 0; - gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track), - GFP_KERNEL_ACCOUNT); - if (gfn_track == NULL) - return -ENOMEM; + return __kvm_page_track_write_tracking_alloc(slot, npages); +} - slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track; - return 0; +int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot) +{ + return __kvm_page_track_write_tracking_alloc(slot, slot->npages); } -static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode, short count) +static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn, + short count) { int index, val; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - val = slot->arch.gfn_track[mode][index]; + val = slot->arch.gfn_write_track[index]; if (WARN_ON(val + count < 0 || val + count > USHRT_MAX)) return; - slot->arch.gfn_track[mode][index] += count; + slot->arch.gfn_write_track[index] += count; } /* @@ -108,21 +82,15 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, * @kvm: the guest instance we are interested in. * @slot: the @gfn belongs to. * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. */ void kvm_slot_page_track_add_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) + struct kvm_memory_slot *slot, gfn_t gfn) { - if (WARN_ON(!page_track_mode_is_valid(mode))) + if (WARN_ON(!kvm_page_track_write_tracking_enabled(kvm))) return; - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) - return; - - update_gfn_track(slot, gfn, mode, 1); + update_gfn_write_track(slot, gfn, 1); /* * new track stops large page mapping for the @@ -130,9 +98,8 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, */ kvm_mmu_gfn_disallow_lpage(slot, gfn); - if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs(kvm); + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) + kvm_flush_remote_tlbs(kvm); } EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); @@ -147,20 +114,14 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); * @kvm: the guest instance we are interested in. * @slot: the @gfn belongs to. * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. */ void kvm_slot_page_track_remove_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) + struct kvm_memory_slot *slot, gfn_t gfn) { - if (WARN_ON(!page_track_mode_is_valid(mode))) + if (WARN_ON(!kvm_page_track_write_tracking_enabled(kvm))) return; - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) - return; - - update_gfn_track(slot, gfn, mode, -1); + update_gfn_write_track(slot, gfn, -1); /* * allow large page mapping for the tracked page @@ -175,22 +136,18 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); */ bool kvm_slot_page_track_is_active(struct kvm *kvm, const struct kvm_memory_slot *slot, - gfn_t gfn, enum kvm_page_track_mode mode) + gfn_t gfn) { int index; - if (WARN_ON(!page_track_mode_is_valid(mode))) - return false; - if (!slot) return false; - if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) + if (!kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - return !!READ_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_write_track[index]); } #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h index 1b363784aa4a..ae2860bdf560 100644 --- a/arch/x86/kvm/mmu/page_track.h +++ b/arch/x86/kvm/mmu/page_track.h @@ -16,8 +16,7 @@ int kvm_page_track_create_memslot(struct kvm *kvm, unsigned long npages); bool kvm_slot_page_track_is_active(struct kvm *kvm, - const struct kvm_memory_slot *slot, - gfn_t gfn, enum kvm_page_track_mode mode); + const struct kvm_memory_slot *slot, gfn_t gfn); #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING int kvm_page_track_init(struct kvm *kvm); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 9f251bc00a7e..cabad0ff722c 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1584,7 +1584,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn) } write_lock(&kvm->mmu_lock); - kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); + kvm_slot_page_track_add_page(kvm, slot, gfn); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); @@ -1618,7 +1618,7 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn) } write_lock(&kvm->mmu_lock); - kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); + kvm_slot_page_track_remove_page(kvm, slot, gfn); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx);

[20/27] KVM: x86/mmu: Drop infrastructure for multiple page-track modes

Commit Message

Patch