From 47ab8751695f71d85562ff497e21b521c789247c Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 5 Aug 2015 12:04:26 +0800 Subject: [PATCH] KVM: MMU: fully check zero bits for sptes The #PF with PFEC.RSV = 1 is designed to speed MMIO emulation, however, it is possible that the RSV #PF is caused by real BUG by mis-configure shadow page table entries This patch enables full check for the zero bits on shadow page table entries (which includes not only bits reserved by the hardware, but also bits that will never be set in the SPTE), then dump the shadow page table hierarchy. Signed-off-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 43 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 823e3bbbbfdd..dfa3cee2aa10 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3295,31 +3295,62 @@ static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) return vcpu_match_mmio_gva(vcpu, addr); } -static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) +/* return true if reserved bit is detected on spte. */ +static bool +walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; - u64 spte = 0ull; + u64 sptes[PT64_ROOT_LEVEL], spte = 0ull; + int root, leaf; + bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return spte; + goto exit; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) + + for (shadow_walk_init(&iterator, vcpu, addr), root = iterator.level; + shadow_walk_okay(&iterator); + __shadow_walk_next(&iterator, spte)) { + leaf = iterator.level; + spte = mmu_spte_get_lockless(iterator.sptep); + + sptes[leaf - 1] = spte; + if (!is_shadow_present_pte(spte)) break; + + reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte, + leaf); + } + walk_shadow_page_lockless_end(vcpu); - return spte; + if (reserved) { + pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", + __func__, addr); + while (root >= leaf) { + pr_err("------ spte 0x%llx level %d.\n", + sptes[root - 1], root); + root--; + } + } +exit: + *sptep = spte; + return reserved; } int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; + bool reserved; if (quickly_check_mmio_pf(vcpu, addr, direct)) return RET_MMIO_PF_EMULATE; - spte = walk_shadow_page_get_mmio_spte(vcpu, addr); + reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); + if (unlikely(reserved)) + return RET_MMIO_PF_BUG; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); -- 2.20.1