From 1d58a17ef54599506d44c45ac95be27273a4d2b1 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Tue, 5 Oct 2021 10:01:41 +0100 Subject: [PATCH 1/5] KVM: arm64: Fix host stage-2 PGD refcount The KVM page-table library refcounts the pages of concatenated stage-2 PGDs individually. However, when running KVM in protected mode, the host's stage-2 PGD is currently managed by EL2 as a single high-order compound page, which can cause the refcount of the tail pages to reach 0 when they shouldn't, hence corrupting the page-table. Fix this by introducing a new hyp_split_page() helper in the EL2 page allocator (matching the kernel's split_page() function), and make use of it from host_s2_zalloc_pages_exact(). Fixes: 1025c8c0c6ac ("KVM: arm64: Wrap the host with a stage 2") Acked-by: Will Deacon Suggested-by: Will Deacon Signed-off-by: Quentin Perret Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211005090155.734578-5-qperret@google.com --- arch/arm64/kvm/hyp/include/nvhe/gfp.h | 1 + arch/arm64/kvm/hyp/nvhe/mem_protect.c | 13 ++++++++++++- arch/arm64/kvm/hyp/nvhe/page_alloc.c | 14 ++++++++++++++ 3 files changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h index fb0f523d1492..0a048dc06a7d 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h @@ -24,6 +24,7 @@ struct hyp_pool { /* Allocation */ void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order); +void hyp_split_page(struct hyp_page *page); void hyp_get_page(struct hyp_pool *pool, void *addr); void hyp_put_page(struct hyp_pool *pool, void *addr); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index bacd493a4eac..34eeb524b686 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1; static void *host_s2_zalloc_pages_exact(size_t size) { - return hyp_alloc_pages(&host_s2_pool, get_order(size)); + void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size)); + + hyp_split_page(hyp_virt_to_page(addr)); + + /* + * The size of concatenated PGDs is always a power of two of PAGE_SIZE, + * so there should be no need to free any of the tail pages to make the + * allocation exact. + */ + WARN_ON(size != (PAGE_SIZE << get_order(size))); + + return addr; } static void *host_s2_zalloc_page(void *pool) diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index 41fc25bdfb34..a6e874e61a40 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -193,6 +193,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr) hyp_spin_unlock(&pool->lock); } +void hyp_split_page(struct hyp_page *p) +{ + unsigned short order = p->order; + unsigned int i; + + p->order = 0; + for (i = 1; i < (1 << order); i++) { + struct hyp_page *tail = p + i; + + tail->order = 0; + hyp_set_page_refcounted(tail); + } +} + void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order) { unsigned short i = order; From 7615c2a514788559c6684234b8fc27f3a843c2c6 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Tue, 5 Oct 2021 10:01:42 +0100 Subject: [PATCH 2/5] KVM: arm64: Report corrupted refcount at EL2 Some of the refcount manipulation helpers used at EL2 are instrumented to catch a corrupted state, but not all of them are treated equally. Let's make things more consistent by instrumenting hyp_page_ref_dec_and_test() as well. Acked-by: Will Deacon Suggested-by: Will Deacon Signed-off-by: Quentin Perret Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211005090155.734578-6-qperret@google.com --- arch/arm64/kvm/hyp/nvhe/page_alloc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index a6e874e61a40..0bd7701ad1df 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p) static inline int hyp_page_ref_dec_and_test(struct hyp_page *p) { + BUG_ON(!p->refcount); p->refcount--; return (p->refcount == 0); } From 6e6a8ef088e1222cb1250942f51ad9c1ab219ab2 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Tue, 5 Oct 2021 13:20:31 +0100 Subject: [PATCH 3/5] KVM: arm64: Release mmap_lock when using VM_SHARED with MTE VM_SHARED mappings are currently forbidden in a memslot with MTE to prevent two VMs racing to sanitise the same page. However, this check is performed while holding current->mm's mmap_lock, but fails to release it. Fix this by releasing the lock when needed. Fixes: ea7fc1bb1cd1 ("KVM: arm64: Introduce MTE VM feature") Signed-off-by: Quentin Perret Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211005122031.809857-1-qperret@google.com --- arch/arm64/kvm/mmu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 1a94a7ca48f2..69bd1732a299 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * when updating the PG_mte_tagged page flag, see * sanitise_mte_tags for more details. */ - if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) - return -EINVAL; + if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) { + ret = -EINVAL; + break; + } if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ From 019057bd73d1751fdfec41e43148baf3303d98f9 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 12 Oct 2021 11:07:59 -0400 Subject: [PATCH 4/5] KVM: SEV-ES: fix length of string I/O The size of the data in the scratch buffer is not divided by the size of each port I/O operation, so vcpu->arch.pio.count ends up being larger than it should be by a factor of size. Cc: stable@vger.kernel.org Fixes: 7ed9abfe8e9f ("KVM: SVM: Support string IO operations for an SEV-ES guest") Acked-by: Tom Lendacky Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c36b5fe4c27c..e672493b5d8d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2583,7 +2583,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len, in); + svm->ghcb_sa, svm->ghcb_sa_len / size, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) From fa13843d1565d4c5b3aeb9be3343b313416bef46 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 15 Oct 2021 13:05:00 -0400 Subject: [PATCH 5/5] KVM: X86: fix lazy allocation of rmaps If allocation of rmaps fails, but some of the pointers have already been written, those pointers can be cleaned up when the memslot is freed, or even reused later for another attempt at allocating the rmaps. Therefore there is no need to WARN, as done for example in memslot_rmap_alloc, but the allocation *must* be skipped lest KVM will overwrite the previous pointer and will indeed leak memory. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index aabd3a2ec1bc..0c8b5129effd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11392,7 +11392,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot, int level = i + 1; int lpages = __kvm_mmu_slot_lpages(slot, npages, level); - WARN_ON(slot->arch.rmap[i]); + if (slot->arch.rmap[i]) + continue; slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) {