Re: [PATCH v8 5/8] KVM: x86/mmu: Don't pass FOLL_GET to __kvm_follow_pfn
On 8/24/23 11:04, David Stevens wrote: From: David Stevens Stop passing FOLL_GET to __kvm_follow_pfn. This allows the host to map memory into the guest that is backed by un-refcounted struct pages - for example, the tail pages of higher order non-compound pages allocated by the amdgpu driver via ttm_pool_alloc_page. The bulk of this change is tracking the is_refcounted_page flag so that non-refcounted pages don't trigger page_count() == 0 warnings. This is done by storing the flag in an unused bit in the sptes. This only bit is not available in PAE SPTEs, so FOLL_GET is only omitted for TDP on x86-64. Signed-off-by: David Stevens --- arch/x86/kvm/mmu/mmu.c | 55 +++-- arch/x86/kvm/mmu/mmu_internal.h | 1 + arch/x86/kvm/mmu/paging_tmpl.h | 8 +++-- arch/x86/kvm/mmu/spte.c | 4 ++- arch/x86/kvm/mmu/spte.h | 12 ++- arch/x86/kvm/mmu/tdp_mmu.c | 22 +++-- include/linux/kvm_host.h| 3 ++ virt/kvm/kvm_main.c | 6 ++-- 8 files changed, 79 insertions(+), 32 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index dabae67f198b..4f5d33e95c6e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -553,12 +553,14 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) { flush = true; - kvm_set_pfn_accessed(spte_to_pfn(old_spte)); + if (is_refcounted_page_pte(old_spte)) + kvm_set_page_accessed(pfn_to_page(spte_to_pfn(old_spte))); } if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) { flush = true; - kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + if (is_refcounted_page_pte(old_spte)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(old_spte))); } return flush; @@ -596,14 +598,18 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) * before they are reclaimed. Sanity check that, if the pfn is backed * by a refcounted page, the refcount is elevated. */ - page = kvm_pfn_to_refcounted_page(pfn); - WARN_ON(page && !page_count(page)); + if (is_refcounted_page_pte(old_spte)) { + page = kvm_pfn_to_refcounted_page(pfn); + WARN_ON(!page || !page_count(page)); + } - if (is_accessed_spte(old_spte)) - kvm_set_pfn_accessed(pfn); + if (is_refcounted_page_pte(old_spte)) { + if (is_accessed_spte(old_spte)) + kvm_set_page_accessed(pfn_to_page(pfn)); - if (is_dirty_spte(old_spte)) - kvm_set_pfn_dirty(pfn); + if (is_dirty_spte(old_spte)) + kvm_set_page_dirty(pfn_to_page(pfn)); + } return old_spte; } @@ -639,8 +645,8 @@ static bool mmu_spte_age(u64 *sptep) * Capture the dirty status of the page, so that it doesn't get * lost when the SPTE is marked for access tracking. */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); + if (is_writable_pte(spte) && is_refcounted_page_pte(spte)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(spte))); spte = mark_spte_for_access_track(spte); mmu_spte_update_no_track(sptep, spte); @@ -1278,8 +1284,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable && !spte_ad_enabled(*sptep)) - kvm_set_pfn_dirty(spte_to_pfn(*sptep)); + if (was_writable && !spte_ad_enabled(*sptep) && is_refcounted_page_pte(*sptep)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(*sptep))); return was_writable; } @@ -2937,6 +2943,11 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, bool host_writable = !fault || fault->map_writable; bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; + /* +* Prefetching uses gfn_to_page_many_atomic, which never gets +* non-refcounted pages. +*/ + bool is_refcounted = !fault || fault->is_refcounted_page; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2969,7 +2980,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, - true, host_writable, ); + true, host_writable, is_refcounted, ); if (*sptep == spte) { ret = RET_PF_SPURIOUS; @@ -4296,11 +4307,19 @@ void
[PATCH v8 5/8] KVM: x86/mmu: Don't pass FOLL_GET to __kvm_follow_pfn
From: David Stevens Stop passing FOLL_GET to __kvm_follow_pfn. This allows the host to map memory into the guest that is backed by un-refcounted struct pages - for example, the tail pages of higher order non-compound pages allocated by the amdgpu driver via ttm_pool_alloc_page. The bulk of this change is tracking the is_refcounted_page flag so that non-refcounted pages don't trigger page_count() == 0 warnings. This is done by storing the flag in an unused bit in the sptes. This only bit is not available in PAE SPTEs, so FOLL_GET is only omitted for TDP on x86-64. Signed-off-by: David Stevens --- arch/x86/kvm/mmu/mmu.c | 55 +++-- arch/x86/kvm/mmu/mmu_internal.h | 1 + arch/x86/kvm/mmu/paging_tmpl.h | 8 +++-- arch/x86/kvm/mmu/spte.c | 4 ++- arch/x86/kvm/mmu/spte.h | 12 ++- arch/x86/kvm/mmu/tdp_mmu.c | 22 +++-- include/linux/kvm_host.h| 3 ++ virt/kvm/kvm_main.c | 6 ++-- 8 files changed, 79 insertions(+), 32 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index dabae67f198b..4f5d33e95c6e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -553,12 +553,14 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) { flush = true; - kvm_set_pfn_accessed(spte_to_pfn(old_spte)); + if (is_refcounted_page_pte(old_spte)) + kvm_set_page_accessed(pfn_to_page(spte_to_pfn(old_spte))); } if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) { flush = true; - kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + if (is_refcounted_page_pte(old_spte)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(old_spte))); } return flush; @@ -596,14 +598,18 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) * before they are reclaimed. Sanity check that, if the pfn is backed * by a refcounted page, the refcount is elevated. */ - page = kvm_pfn_to_refcounted_page(pfn); - WARN_ON(page && !page_count(page)); + if (is_refcounted_page_pte(old_spte)) { + page = kvm_pfn_to_refcounted_page(pfn); + WARN_ON(!page || !page_count(page)); + } - if (is_accessed_spte(old_spte)) - kvm_set_pfn_accessed(pfn); + if (is_refcounted_page_pte(old_spte)) { + if (is_accessed_spte(old_spte)) + kvm_set_page_accessed(pfn_to_page(pfn)); - if (is_dirty_spte(old_spte)) - kvm_set_pfn_dirty(pfn); + if (is_dirty_spte(old_spte)) + kvm_set_page_dirty(pfn_to_page(pfn)); + } return old_spte; } @@ -639,8 +645,8 @@ static bool mmu_spte_age(u64 *sptep) * Capture the dirty status of the page, so that it doesn't get * lost when the SPTE is marked for access tracking. */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); + if (is_writable_pte(spte) && is_refcounted_page_pte(spte)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(spte))); spte = mark_spte_for_access_track(spte); mmu_spte_update_no_track(sptep, spte); @@ -1278,8 +1284,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable && !spte_ad_enabled(*sptep)) - kvm_set_pfn_dirty(spte_to_pfn(*sptep)); + if (was_writable && !spte_ad_enabled(*sptep) && is_refcounted_page_pte(*sptep)) + kvm_set_page_dirty(pfn_to_page(spte_to_pfn(*sptep))); return was_writable; } @@ -2937,6 +2943,11 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, bool host_writable = !fault || fault->map_writable; bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; + /* +* Prefetching uses gfn_to_page_many_atomic, which never gets +* non-refcounted pages. +*/ + bool is_refcounted = !fault || fault->is_refcounted_page; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2969,7 +2980,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, - true, host_writable, ); + true, host_writable, is_refcounted, ); if (*sptep == spte) { ret = RET_PF_SPURIOUS; @@ -4296,11 +4307,19 @@ void