diff options
Diffstat (limited to 'arch/arm/kvm/mmu.c')
| -rw-r--r-- | arch/arm/kvm/mmu.c | 95 |
1 files changed, 71 insertions, 24 deletions
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 11b6595c2672..e0267532bd4e 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); } @@ -796,6 +805,7 @@ 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 +813,7 @@ 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); } @@ -813,21 +824,25 @@ 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; + void *hwpgd = NULL; - unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - kvm_free_hwpgd(kvm_get_hwpgd(kvm)); - if (KVM_PREALLOC_LEVEL > 0) - kfree(kvm->arch.pgd); + spin_lock(&kvm->mmu_lock); + if (kvm->arch.pgd) { + unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + pgd = READ_ONCE(kvm->arch.pgd); + hwpgd = kvm_get_hwpgd(kvm); + kvm->arch.pgd = NULL; + } + spin_unlock(&kvm->mmu_lock); - kvm->arch.pgd = NULL; + if (hwpgd) + kvm_free_hwpgd(hwpgd); + if (KVM_PREALLOC_LEVEL > 0 && pgd) + kfree(pgd); } static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, @@ -855,6 +870,9 @@ 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; @@ -874,19 +892,35 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache pmd = stage2_get_pmd(kvm, cache, addr); VM_BUG_ON(!pmd); - /* - * Mapping in huge pages should only happen through a fault. If a - * page is merged into a transparent huge page, the individual - * subpages of that huge page should be unmapped through MMU - * notifiers before we get here. - * - * Merging of CompoundPages is not supported; they should become - * splitting first, unmapped, merged, and mapped back in on-demand. - */ - VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); - old_pmd = *pmd; if (pmd_present(old_pmd)) { + /* + * Multiple vcpus faulting on the same PMD entry, can + * lead to them sequentially updating the PMD with the + * same value. Following the break-before-make + * (pmd_clear() followed by tlb_flush()) process can + * hinder forward progress due to refaults generated + * on missing translations. + * + * Skip updating the page table if the entry is + * unchanged. + */ + if (pmd_val(old_pmd) == pmd_val(*new_pmd)) + return 0; + + /* + * Mapping in huge pages should only happen through a + * fault. If a page is merged into a transparent huge + * page, the individual subpages of that huge page + * should be unmapped through MMU notifiers before we + * get here. + * + * Merging of CompoundPages is not supported; they + * should become splitting first, unmapped, merged, + * and mapped back in on-demand. + */ + VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); } else { @@ -943,6 +977,10 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, /* Create 2nd stage page table mapping - Level 3 */ old_pte = *pte; if (pte_present(old_pte)) { + /* Skip page table update if there is no change */ + if (pte_val(old_pte) == pte_val(*new_pte)) + return 0; + kvm_set_pte(pte, __pte(0)); kvm_tlb_flush_vmid_ipa(kvm, addr); } else { @@ -1612,12 +1650,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) { + if (!kvm->arch.pgd) + return 0; trace_kvm_age_hva(start, end); return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); } int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) { + if (!kvm->arch.pgd) + return 0; trace_kvm_test_age_hva(hva); return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); } @@ -1759,6 +1801,7 @@ 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 @@ -1802,8 +1845,10 @@ 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, @@ -1815,7 +1860,7 @@ 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) @@ -1823,6 +1868,8 @@ 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; } |