From 8e88806117e4868bc459a3042e55f8bf06c0b9e0 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 16 Mar 2017 18:20:49 +0000 Subject: arm/arm64: KVM: Take mmap_sem in stage2_unmap_vm commit 90f6e150e44a0dc3883110eeb3ab35d1be42b6bb upstream. We don't hold the mmap_sem while searching for the VMAs when we try to unmap each memslot for a VM. Fix this properly to avoid unexpected results. Fixes: commit 957db105c997 ("arm/arm64: KVM: Introduce stage2_unmap_vm") Reviewed-by: Christoffer Dall Signed-off-by: Suzuki K Poulose Signed-off-by: Marc Zyngier Signed-off-by: Greg Kroah-Hartman --- arch/arm/kvm/mmu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 11b6595c2672..5366a736151e 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -796,6 +796,7 @@ void stage2_unmap_vm(struct kvm *kvm) int idx; idx = srcu_read_lock(&kvm->srcu); + down_read(¤t->mm->mmap_sem); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); @@ -803,6 +804,7 @@ void stage2_unmap_vm(struct kvm *kvm) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); srcu_read_unlock(&kvm->srcu, idx); } -- cgit v1.2.3 From d4ad442b9982fba9eab0f9003c8cd185a1afeff6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 16 Mar 2017 18:20:50 +0000 Subject: arm/arm64: KVM: Take mmap_sem in kvm_arch_prepare_memory_region commit 72f310481a08db821b614e7b5d00febcc9064b36 upstream. We don't hold the mmap_sem while searching for VMAs (via find_vma), in kvm_arch_prepare_memory_region, which can end up in expected failures. Fixes: commit 8eef91239e57 ("arm/arm64: KVM: map MMIO regions at creation time") Cc: Ard Biesheuvel Cc: Eric Auger Reviewed-by: Christoffer Dall [ Handle dirty page logging failure case ] Signed-off-by: Suzuki K Poulose Signed-off-by: Marc Zyngier Signed-off-by: Greg Kroah-Hartman --- arch/arm/kvm/mmu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 5366a736151e..f91ee2f27b41 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1761,6 +1761,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, (KVM_PHYS_SIZE >> PAGE_SHIFT)) return -EFAULT; + down_read(¤t->mm->mmap_sem); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we can map @@ -1804,8 +1805,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) - return -EINVAL; + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + ret = -EINVAL; + goto out; + } ret = kvm_phys_addr_ioremap(kvm, gpa, pa, vm_end - vm_start, @@ -1817,7 +1820,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } while (hva < reg_end); if (change == KVM_MR_FLAGS_ONLY) - return ret; + goto out; spin_lock(&kvm->mmu_lock); if (ret) @@ -1825,6 +1828,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, else stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); +out: + up_read(¤t->mm->mmap_sem); return ret; } -- cgit v1.2.3 From 2a60bb635236ead6437b37a5b4085da1e33962b1 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 3 Apr 2017 15:12:43 +0100 Subject: kvm: arm/arm64: Fix locking for kvm_free_stage2_pgd commit 8b3405e345b5a098101b0c31b264c812bba045d9 upstream. In kvm_free_stage2_pgd() we don't hold the kvm->mmu_lock while calling unmap_stage2_range() on the entire memory range for the guest. This could cause problems with other callers (e.g, munmap on a memslot) trying to unmap a range. And since we have to unmap the entire Guest memory range holding a spinlock, make sure we yield the lock if necessary, after we unmap each PUD range. Fixes: commit d5d8184d35c9 ("KVM: ARM: Memory virtualization setup") Cc: Paolo Bonzini Cc: Marc Zyngier Cc: Christoffer Dall Cc: Mark Rutland Signed-off-by: Suzuki K Poulose [ Avoid vCPU starvation and lockup detector warnings ] Signed-off-by: Marc Zyngier Signed-off-by: Suzuki K Poulose Signed-off-by: Christoffer Dall Signed-off-by: Greg Kroah-Hartman --- arch/arm/kvm/mmu.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index f91ee2f27b41..01cf10556081 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -300,6 +300,14 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) unmap_puds(kvm, pgd, addr, next); + /* + * If we are dealing with a large range in + * stage2 table, release the kvm->mmu_lock + * to prevent starvation and lockup detector + * warnings. + */ + if (kvm && (next != end)) + cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } @@ -738,6 +746,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) { + assert_spin_locked(&kvm->mmu_lock); unmap_range(kvm, kvm->arch.pgd, start, size); } @@ -824,7 +833,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) if (kvm->arch.pgd == NULL) return; + spin_lock(&kvm->mmu_lock); unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + spin_unlock(&kvm->mmu_lock); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); -- cgit v1.2.3 From f267b064a6e92610061dc5a51c1c8b72443a7066 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 5 Jun 2017 19:17:18 +0100 Subject: KVM: arm/arm64: Handle possible NULL stage2 pud when ageing pages commit d6dbdd3c8558cad3b6d74cc357b408622d122331 upstream. Under memory pressure, we start ageing pages, which amounts to parsing the page tables. Since we don't want to allocate any extra level, we pass NULL for our private allocation cache. Which means that stage2_get_pud() is allowed to fail. This results in the following splat: [ 1520.409577] Unable to handle kernel NULL pointer dereference at virtual address 00000008 [ 1520.417741] pgd = ffff810f52fef000 [ 1520.421201] [00000008] *pgd=0000010f636c5003, *pud=0000010f56f48003, *pmd=0000000000000000 [ 1520.429546] Internal error: Oops: 96000006 [#1] PREEMPT SMP [ 1520.435156] Modules linked in: [ 1520.438246] CPU: 15 PID: 53550 Comm: qemu-system-aar Tainted: G W 4.12.0-rc4-00027-g1885c397eaec #7205 [ 1520.448705] Hardware name: FOXCONN R2-1221R-A4/C2U4N_MB, BIOS G31FB12A 10/26/2016 [ 1520.463726] task: ffff800ac5fb4e00 task.stack: ffff800ce04e0000 [ 1520.469666] PC is at stage2_get_pmd+0x34/0x110 [ 1520.474119] LR is at kvm_age_hva_handler+0x44/0xf0 [ 1520.478917] pc : [] lr : [] pstate: 40000145 [ 1520.486325] sp : ffff800ce04e33d0 [ 1520.489644] x29: ffff800ce04e33d0 x28: 0000000ffff40064 [ 1520.494967] x27: 0000ffff27e00000 x26: 0000000000000000 [ 1520.500289] x25: ffff81051ba65008 x24: 0000ffff40065000 [ 1520.505618] x23: 0000ffff40064000 x22: 0000000000000000 [ 1520.510947] x21: ffff810f52b20000 x20: 0000000000000000 [ 1520.516274] x19: 0000000058264000 x18: 0000000000000000 [ 1520.521603] x17: 0000ffffa6fe7438 x16: ffff000008278b70 [ 1520.526940] x15: 000028ccd8000000 x14: 0000000000000008 [ 1520.532264] x13: ffff7e0018298000 x12: 0000000000000002 [ 1520.537582] x11: ffff000009241b93 x10: 0000000000000940 [ 1520.542908] x9 : ffff0000092ef800 x8 : 0000000000000200 [ 1520.548229] x7 : ffff800ce04e36a8 x6 : 0000000000000000 [ 1520.553552] x5 : 0000000000000001 x4 : 0000000000000000 [ 1520.558873] x3 : 0000000000000000 x2 : 0000000000000008 [ 1520.571696] x1 : ffff000008fd5000 x0 : ffff0000080b149c [ 1520.577039] Process qemu-system-aar (pid: 53550, stack limit = 0xffff800ce04e0000) [...] [ 1521.510735] [] stage2_get_pmd+0x34/0x110 [ 1521.516221] [] kvm_age_hva_handler+0x44/0xf0 [ 1521.522054] [] handle_hva_to_gpa+0xb8/0xe8 [ 1521.527716] [] kvm_age_hva+0x44/0xf0 [ 1521.532854] [] kvm_mmu_notifier_clear_flush_young+0x70/0xc0 [ 1521.539992] [] __mmu_notifier_clear_flush_young+0x88/0xd0 [ 1521.546958] [] page_referenced_one+0xf0/0x188 [ 1521.552881] [] rmap_walk_anon+0xec/0x250 [ 1521.558370] [] rmap_walk+0x78/0xa0 [ 1521.563337] [] page_referenced+0x164/0x180 [ 1521.569002] [] shrink_active_list+0x178/0x3b8 [ 1521.574922] [] shrink_node_memcg+0x328/0x600 [ 1521.580758] [] shrink_node+0xc4/0x328 [ 1521.585986] [] do_try_to_free_pages+0xc0/0x340 [ 1521.592000] [] try_to_free_pages+0xcc/0x240 [...] The trivial fix is to handle this NULL pud value early, rather than dereferencing it blindly. Signed-off-by: Marc Zyngier Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall Signed-off-by: Greg Kroah-Hartman --- arch/arm/kvm/mmu.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 01cf10556081..1f1ff7e7b9cf 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -869,6 +869,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pmd_t *pmd; pud = stage2_get_pud(kvm, cache, addr); + if (!pud) + return NULL; + if (pud_none(*pud)) { if (!cache) return NULL; -- cgit v1.2.3