From 6c0d706b563af732adb094c5bf807437e8963e84 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 3 May 2017 15:17:51 +0100 Subject: [PATCH] kvm: arm/arm64: Fix race in resetting stage2 PGD MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit In kvm_free_stage2_pgd() we check the stage2 PGD before holding the lock and proceed to take the lock if it is valid. And we unmap the page tables, followed by releasing the lock. We reset the PGD only after dropping this lock, which could cause a race condition where another thread waiting on or even holding the lock, could potentially see that the PGD is still valid and proceed to perform a stage2 operation and later encounter a NULL PGD. [223090.242280] Unable to handle kernel NULL pointer dereference at virtual address 00000040 [223090.262330] PC is at unmap_stage2_range+0x8c/0x428 [223090.262332] LR is at kvm_unmap_hva_handler+0x2c/0x3c [223090.262531] Call trace: [223090.262533] [] unmap_stage2_range+0x8c/0x428 [223090.262535] [] kvm_unmap_hva_handler+0x2c/0x3c [223090.262537] [] handle_hva_to_gpa+0xb0/0x104 [223090.262539] [] kvm_unmap_hva+0x5c/0xbc [223090.262543] [] kvm_mmu_notifier_invalidate_page+0x50/0x8c [223090.262547] [] __mmu_notifier_invalidate_page+0x5c/0x84 [223090.262551] [] try_to_unmap_one+0x1d0/0x4a0 [223090.262553] [] rmap_walk+0x1cc/0x2e0 [223090.262555] [] try_to_unmap+0x74/0xa4 [223090.262557] [] migrate_pages+0x31c/0x5ac [223090.262561] [] compact_zone+0x3fc/0x7ac [223090.262563] [] compact_zone_order+0x94/0xb0 [223090.262564] [] try_to_compact_pages+0x108/0x290 [223090.262569] [] __alloc_pages_direct_compact+0x70/0x1ac [223090.262571] [] __alloc_pages_nodemask+0x434/0x9f4 [223090.262572] [] alloc_pages_vma+0x230/0x254 [223090.262574] [] do_huge_pmd_anonymous_page+0x114/0x538 [223090.262576] [] handle_mm_fault+0xd40/0x17a4 [223090.262577] [] __get_user_pages+0x12c/0x36c [223090.262578] [] get_user_pages_unlocked+0xa4/0x1b8 [223090.262579] [] __gfn_to_pfn_memslot+0x280/0x31c [223090.262580] [] gfn_to_pfn_prot+0x4c/0x5c [223090.262582] [] kvm_handle_guest_abort+0x240/0x774 [223090.262584] [] handle_exit+0x11c/0x1ac [223090.262586] [] kvm_arch_vcpu_ioctl_run+0x31c/0x648 [223090.262587] [] kvm_vcpu_ioctl+0x378/0x768 [223090.262590] [] do_vfs_ioctl+0x324/0x5a4 [223090.262591] [] SyS_ioctl+0x90/0xa4 [223090.262595] [] el0_svc_naked+0x38/0x3c This patch moves the stage2 PGD manipulation under the lock. Reported-by: Alexander Graf Cc: Mark Rutland Cc: Marc Zyngier Cc: Paolo Bonzini Cc: Radim Krčmář Reviewed-by: Christoffer Dall Reviewed-by: Marc Zyngier Signed-off-by: Suzuki K Poulose Signed-off-by: Christoffer Dall --- virt/kvm/arm/mmu.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 313ee64..909a1a7 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -829,22 +829,22 @@ void stage2_unmap_vm(struct kvm *kvm) * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all * underlying level-2 and level-3 tables before freeing the actual level-1 table * and setting the struct pointer to NULL. - * - * Note we don't need locking here as this is only called when the VM is - * destroyed, which can only be done once. */ void kvm_free_stage2_pgd(struct kvm *kvm) { - if (kvm->arch.pgd == NULL) - return; + void *pgd = NULL; spin_lock(&kvm->mmu_lock); - unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + if (kvm->arch.pgd) { + unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + pgd = kvm->arch.pgd; + kvm->arch.pgd = NULL; + } spin_unlock(&kvm->mmu_lock); /* Free the HW pgd, one page at a time */ - free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE); - kvm->arch.pgd = NULL; + if (pgd) + free_pages_exact(pgd, S2_PGD_SIZE); } static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, -- 2.7.4