#include <linux/srcu.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/bsearch.h>
#include <asm/processor.h>
#include <asm/io.h>
*/
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
+
kvm->mmu_notifier_seq++;
need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
- spin_unlock(&kvm->mmu_lock);
- srcu_read_unlock(&kvm->srcu, idx);
-
/* we've to flush the tlb before the pages can be freed */
if (need_tlb_flush)
kvm_flush_remote_tlbs(kvm);
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
for (; start < end; start += PAGE_SIZE)
need_tlb_flush |= kvm_unmap_hva(kvm, start);
need_tlb_flush |= kvm->tlbs_dirty;
- spin_unlock(&kvm->mmu_lock);
- srcu_read_unlock(&kvm->srcu, idx);
-
/* we've to flush the tlb before the pages can be freed */
if (need_tlb_flush)
kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
- young = kvm_age_hva(kvm, address);
- spin_unlock(&kvm->mmu_lock);
- srcu_read_unlock(&kvm->srcu, idx);
+ young = kvm_age_hva(kvm, address);
if (young)
kvm_flush_remote_tlbs(kvm);
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
return young;
}
new.userspace_addr = mem->userspace_addr;
#endif /* not defined CONFIG_S390 */
- if (!npages) {
+ if (!npages || base_gfn != old.base_gfn) {
r = -ENOMEM;
slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!slots)
old_memslots = kvm->memslots;
rcu_assign_pointer(kvm->memslots, slots);
synchronize_srcu_expedited(&kvm->srcu);
- /* From this point no new shadow pages pointing to a deleted
- * memslot will be created.
+ /* slot was deleted or moved, clear iommu mapping */
+ kvm_iommu_unmap_pages(kvm, &old);
+ /* From this point no new shadow pages pointing to a deleted,
+ * or moved, memslot will be created.
*
* validation of sp->gfn happens in:
* - gfn_to_hva (kvm_read_guest, gfn_to_pfn)
if (r)
goto out_free;
- /* map the pages in iommu page table */
- if (npages) {
- r = kvm_iommu_map_pages(kvm, &new);
- if (r)
- goto out_free;
- }
-
r = -ENOMEM;
slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!slots)
slots->nmemslots = mem->slot + 1;
slots->generation++;
+ /* map new memory slot into the iommu */
+ if (npages) {
+ r = kvm_iommu_map_pages(kvm, &new);
+ if (r)
+ goto out_slots;
+ }
+
/* actual memory is freed via old in kvm_free_physmem_slot below */
if (!npages) {
new.rmap = NULL;
return 0;
+out_slots:
+ kfree(slots);
out_free:
kvm_free_physmem_slot(&new, &old);
out:
}
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
- gpa_t gpa)
+ gpa_t gpa, unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
int offset = offset_in_page(gpa);
- gfn_t gfn = gpa >> PAGE_SHIFT;
+ gfn_t start_gfn = gpa >> PAGE_SHIFT;
+ gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
+ gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
+ gfn_t nr_pages_avail;
ghc->gpa = gpa;
ghc->generation = slots->generation;
- ghc->memslot = __gfn_to_memslot(slots, gfn);
- ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
- if (!kvm_is_error_hva(ghc->hva))
+ ghc->len = len;
+ ghc->memslot = __gfn_to_memslot(slots, start_gfn);
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
+ if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
ghc->hva += offset;
- else
- return -EFAULT;
-
+ } else {
+ /*
+ * If the requested region crosses two memslots, we still
+ * verify that the entire region is valid here.
+ */
+ while (start_gfn <= end_gfn) {
+ ghc->memslot = __gfn_to_memslot(slots, start_gfn);
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
+ &nr_pages_avail);
+ if (kvm_is_error_hva(ghc->hva))
+ return -EFAULT;
+ start_gfn += nr_pages_avail;
+ }
+ /* Use the slow path for cross page reads and writes. */
+ ghc->memslot = NULL;
+ }
return 0;
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;
+ BUG_ON(len > ghc->len);
+
if (slots->generation != ghc->generation)
- kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+ kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+ if (unlikely(!ghc->memslot))
+ return kvm_write_guest(kvm, ghc->gpa, data, len);
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;
+ BUG_ON(len > ghc->len);
+
if (slots->generation != ghc->generation)
- kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+ kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+ if (unlikely(!ghc->memslot))
+ return kvm_read_guest(kvm, ghc->gpa, data, len);
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
int r;
struct kvm_vcpu *vcpu, *v;
+ if (id >= KVM_MAX_VCPUS)
+ return -EINVAL;
+
vcpu = kvm_arch_vcpu_create(kvm, id);
if (IS_ERR(vcpu))
return PTR_ERR(vcpu);
goto vcpu_destroy;
mutex_lock(&kvm->lock);
+ if (!kvm_vcpu_compatible(vcpu)) {
+ r = -EINVAL;
+ goto unlock_vcpu_destroy;
+ }
if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) {
r = -EINVAL;
goto unlock_vcpu_destroy;
int i;
for (i = 0; i < bus->dev_count; i++) {
- struct kvm_io_device *pos = bus->devs[i];
+ struct kvm_io_device *pos = bus->range[i].dev;
kvm_iodevice_destructor(pos);
}
kfree(bus);
}
+int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+{
+ const struct kvm_io_range *r1 = p1;
+ const struct kvm_io_range *r2 = p2;
+
+ if (r1->addr < r2->addr)
+ return -1;
+ if (r1->addr + r1->len > r2->addr + r2->len)
+ return 1;
+ return 0;
+}
+
+int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
+ gpa_t addr, int len)
+{
+ if (bus->dev_count == NR_IOBUS_DEVS)
+ return -ENOSPC;
+
+ bus->range[bus->dev_count++] = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ .dev = dev,
+ };
+
+ sort(bus->range, bus->dev_count, sizeof(struct kvm_io_range),
+ kvm_io_bus_sort_cmp, NULL);
+
+ return 0;
+}
+
+int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
+ gpa_t addr, int len)
+{
+ struct kvm_io_range *range, key;
+ int off;
+
+ key = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
+
+ range = bsearch(&key, bus->range, bus->dev_count,
+ sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp);
+ if (range == NULL)
+ return -ENOENT;
+
+ off = range - bus->range;
+
+ while (off > 0 && kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0)
+ off--;
+
+ return off;
+}
+
/* kvm_io_bus_write - called under kvm->slots_lock */
int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, const void *val)
{
- int i;
+ int idx;
struct kvm_io_bus *bus;
+ struct kvm_io_range range;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
- for (i = 0; i < bus->dev_count; i++)
- if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
+ idx = kvm_io_bus_get_first_dev(bus, addr, len);
+ if (idx < 0)
+ return -EOPNOTSUPP;
+
+ while (idx < bus->dev_count &&
+ kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
+ if (!kvm_iodevice_write(bus->range[idx].dev, addr, len, val))
return 0;
+ idx++;
+ }
+
return -EOPNOTSUPP;
}
int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val)
{
- int i;
+ int idx;
struct kvm_io_bus *bus;
+ struct kvm_io_range range;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
- for (i = 0; i < bus->dev_count; i++)
- if (!kvm_iodevice_read(bus->devs[i], addr, len, val))
+ idx = kvm_io_bus_get_first_dev(bus, addr, len);
+ if (idx < 0)
+ return -EOPNOTSUPP;
+
+ while (idx < bus->dev_count &&
+ kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
+ if (!kvm_iodevice_read(bus->range[idx].dev, addr, len, val))
return 0;
+ idx++;
+ }
+
return -EOPNOTSUPP;
}
/* Caller must hold slots_lock. */
-int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
- struct kvm_io_device *dev)
+int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+ int len, struct kvm_io_device *dev)
{
struct kvm_io_bus *new_bus, *bus;
if (!new_bus)
return -ENOMEM;
memcpy(new_bus, bus, sizeof(struct kvm_io_bus));
- new_bus->devs[new_bus->dev_count++] = dev;
+ kvm_io_bus_insert_dev(new_bus, dev, addr, len);
rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
synchronize_srcu_expedited(&kvm->srcu);
kfree(bus);
r = -ENOENT;
for (i = 0; i < new_bus->dev_count; i++)
- if (new_bus->devs[i] == dev) {
+ if (new_bus->range[i].dev == dev) {
r = 0;
- new_bus->devs[i] = new_bus->devs[--new_bus->dev_count];
+ new_bus->dev_count--;
+ new_bus->range[i] = new_bus->range[new_bus->dev_count];
+ sort(new_bus->range, new_bus->dev_count,
+ sizeof(struct kvm_io_range),
+ kvm_io_bus_sort_cmp, NULL);
break;
}