diff options
Diffstat (limited to 'virt/kvm/kvm_main.c')
| -rw-r--r-- | virt/kvm/kvm_main.c | 61 |
1 files changed, 44 insertions, 17 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 71f77ae6c2a6..36b9f2b29071 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -165,6 +165,7 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) */ if (pfn_valid(pfn)) return PageReserved(pfn_to_page(pfn)) && + !is_zero_pfn(pfn) && !kvm_is_zone_device_pfn(pfn); return true; @@ -381,9 +382,8 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, */ kvm->mmu_notifier_count++; need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); - need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ - if (need_tlb_flush) + if (need_tlb_flush || kvm->tlbs_dirty) kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); @@ -1485,15 +1485,24 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) return true; } +static int kvm_try_get_pfn(kvm_pfn_t pfn) +{ + if (kvm_is_reserved_pfn(pfn)) + return 1; + return get_page_unless_zero(pfn_to_page(pfn)); +} + static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool *async, bool write_fault, bool *writable, kvm_pfn_t *p_pfn) { - unsigned long pfn; + kvm_pfn_t pfn; + pte_t *ptep; + spinlock_t *ptl; int r; - r = follow_pfn(vma, addr, &pfn); + r = follow_pte_pmd(vma->vm_mm, addr, NULL, NULL, &ptep, NULL, &ptl); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does @@ -1508,14 +1517,19 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, if (r) return r; - r = follow_pfn(vma, addr, &pfn); + r = follow_pte_pmd(vma->vm_mm, addr, NULL, NULL, &ptep, NULL, &ptl); if (r) return r; + } + if (write_fault && !pte_write(*ptep)) { + pfn = KVM_PFN_ERR_RO_FAULT; + goto out; } if (writable) - *writable = true; + *writable = pte_write(*ptep); + pfn = pte_pfn(*ptep); /* * Get a reference here because callers of *hva_to_pfn* and @@ -1527,11 +1541,21 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. + * + * Certain IO or PFNMAP mappings can be backed with valid + * struct pages, but be allocated without refcounting e.g., + * tail pages of non-compound higher order allocations, which + * would then underflow the refcount when the caller does the + * required put_page. Don't allow those pages here. */ - kvm_get_pfn(pfn); + if (!kvm_try_get_pfn(pfn)) + r = -EFAULT; +out: + pte_unmap_unlock(ptep, ptl); *p_pfn = pfn; - return 0; + + return r; } /* @@ -3688,7 +3712,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { - int i; + int i, j; struct kvm_io_bus *new_bus, *bus; bus = kvm_get_bus(kvm, bus_idx); @@ -3705,17 +3729,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) * sizeof(struct kvm_io_range)), GFP_KERNEL); - if (!new_bus) { + if (new_bus) { + memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); + new_bus->dev_count--; + memcpy(new_bus->range + i, bus->range + i + 1, + (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); + } else { pr_err("kvm: failed to shrink bus, removing it completely\n"); - goto broken; + for (j = 0; j < bus->dev_count; j++) { + if (j == i) + continue; + kvm_iodevice_destructor(bus->range[j].dev); + } } - memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); - new_bus->dev_count--; - memcpy(new_bus->range + i, bus->range + i + 1, - (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); - -broken: rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); |