@@ -2354,6 +2354,41 @@ struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
}
EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
+int vfio_iommu_dev_fault_handler(struct iommu_fault *fault, void *data)
+{
+ struct device *dev = (struct device *)data;
+ struct vfio_container *container;
+ struct vfio_group *group;
+ struct vfio_iommu_driver *driver;
+ int ret;
+
+ if (!dev)
+ return -EINVAL;
+
+ group = vfio_group_get_from_dev(dev);
+ if (!group)
+ return -ENODEV;
+
+ ret = vfio_group_add_container_user(group);
+ if (ret)
+ goto out;
+
+ container = group->container;
+ driver = container->iommu_driver;
+ if (likely(driver && driver->ops->dma_map_iopf))
+ ret = driver->ops->dma_map_iopf(container->iommu_data,
+ fault, dev);
+ else
+ ret = -ENOTTY;
+
+ vfio_group_try_dissolve_container(group);
+
+out:
+ vfio_group_put(group);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_iommu_dev_fault_handler);
+
/**
* Module/class support
*/
@@ -3330,6 +3330,172 @@ static void vfio_iommu_type1_notify(void *iommu_data,
wake_up_all(&iommu->vaddr_wait);
}
+/*
+ * To optimize for fewer page fault handlings, try to
+ * pre-map more pages than requested.
+ */
+#define IOPF_PREMAP_LEN 512
+
+static void unpin_pages_iopf(struct vfio_dma *dma,
+ unsigned long pfn, unsigned long npages)
+{
+ while (npages--)
+ put_pfn(pfn++, dma->prot);
+}
+
+/*
+ * Return 0 on success or a negative error code, the
+ * number of pages contiguously pinned is in @*pinned.
+ */
+static int pin_pages_iopf(struct vfio_dma *dma, unsigned long vaddr,
+ unsigned long npages, unsigned long *pfn_base,
+ unsigned long *pinned, struct vfio_batch *batch)
+{
+ struct mm_struct *mm;
+ unsigned long pfn;
+ int ret = 0;
+ *pinned = 0;
+
+ mm = get_task_mm(dma->task);
+ if (!mm)
+ return -ENODEV;
+
+ if (batch->size) {
+ *pfn_base = page_to_pfn(batch->pages[batch->offset]);
+ pfn = *pfn_base;
+ } else
+ *pfn_base = 0;
+
+ while (npages) {
+ if (!batch->size) {
+ unsigned long req_pages = min_t(unsigned long, npages,
+ batch->capacity);
+
+ ret = vaddr_get_pfns(mm, vaddr, req_pages, dma->prot,
+ &pfn, batch->pages);
+ if (ret < 0)
+ goto out;
+
+ batch->size = ret;
+ batch->offset = 0;
+ ret = 0;
+
+ if (!*pfn_base)
+ *pfn_base = pfn;
+ }
+
+ while (true) {
+ if (pfn != *pfn_base + *pinned)
+ goto out;
+
+ (*pinned)++;
+ npages--;
+ vaddr += PAGE_SIZE;
+ batch->offset++;
+ batch->size--;
+
+ if (!batch->size)
+ break;
+
+ pfn = page_to_pfn(batch->pages[batch->offset]);
+ }
+
+ if (unlikely(disable_hugepages))
+ break;
+ }
+
+out:
+ mmput(mm);
+ return ret;
+}
+
+static int vfio_iommu_type1_dma_map_iopf(void *iommu_data,
+ struct iommu_fault *fault,
+ struct device *dev)
+{
+ struct vfio_iommu *iommu = iommu_data;
+ dma_addr_t iova = ALIGN_DOWN(fault->prm.addr, PAGE_SIZE);
+ struct vfio_dma *dma;
+ int access_flags = 0;
+ size_t premap_len, map_len, mapped_len = 0;
+ unsigned long bit_offset, npages, i, vaddr, pfn;
+ struct vfio_batch batch;
+ enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
+ struct iommu_page_response resp = {0};
+
+ mutex_lock(&iommu->lock);
+
+ dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
+ if (!dma)
+ goto out_invalid;
+
+ if (fault->prm.perm & IOMMU_FAULT_PERM_READ)
+ access_flags |= IOMMU_READ;
+ if (fault->prm.perm & IOMMU_FAULT_PERM_WRITE)
+ access_flags |= IOMMU_WRITE;
+ if ((dma->prot & access_flags) != access_flags)
+ goto out_invalid;
+
+ bit_offset = (iova - dma->iova) >> PAGE_SHIFT;
+ if (IOPF_MAPPED_BITMAP_GET(dma, bit_offset))
+ goto out_success;
+
+ premap_len = IOPF_PREMAP_LEN << PAGE_SHIFT;
+ npages = dma->size >> PAGE_SHIFT;
+ map_len = PAGE_SIZE;
+ for (i = bit_offset + 1; i < npages; i++) {
+ if (map_len >= premap_len || IOPF_MAPPED_BITMAP_GET(dma, i))
+ break;
+ map_len += PAGE_SIZE;
+ }
+ vaddr = iova - dma->iova + dma->vaddr;
+ vfio_batch_init(&batch);
+
+ while (map_len) {
+ int ret;
+
+ ret = pin_pages_iopf(dma, vaddr + mapped_len,
+ map_len >> PAGE_SHIFT, &pfn,
+ &npages, &batch);
+ if (!npages)
+ break;
+
+ if (vfio_iommu_map(iommu, iova + mapped_len, pfn,
+ npages, dma->prot)) {
+ unpin_pages_iopf(dma, pfn, npages);
+ vfio_batch_unpin(&batch, dma);
+ break;
+ }
+
+ bitmap_set(dma->iopf_mapped_bitmap,
+ bit_offset + (mapped_len >> PAGE_SHIFT), npages);
+
+ unpin_pages_iopf(dma, pfn, npages);
+
+ map_len -= npages << PAGE_SHIFT;
+ mapped_len += npages << PAGE_SHIFT;
+
+ if (ret)
+ break;
+ }
+
+ vfio_batch_fini(&batch);
+
+ if (!mapped_len)
+ goto out_invalid;
+
+out_success:
+ status = IOMMU_PAGE_RESP_SUCCESS;
+
+out_invalid:
+ mutex_unlock(&iommu->lock);
+ resp.version = IOMMU_PAGE_RESP_VERSION_1;
+ resp.grpid = fault->prm.grpid;
+ resp.code = status;
+ iommu_page_response(dev, &resp);
+ return 0;
+}
+
static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.name = "vfio-iommu-type1",
.owner = THIS_MODULE,
@@ -3345,6 +3511,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.dma_rw = vfio_iommu_type1_dma_rw,
.group_iommu_domain = vfio_iommu_type1_group_iommu_domain,
.notify = vfio_iommu_type1_notify,
+ .dma_map_iopf = vfio_iommu_type1_dma_map_iopf,
};
static int __init vfio_iommu_type1_init(void)
@@ -99,6 +99,9 @@ struct vfio_iommu_driver_ops {
struct iommu_group *group);
void (*notify)(void *iommu_data,
enum vfio_iommu_notify_type event);
+ int (*dma_map_iopf)(void *iommu_data,
+ struct iommu_fault *fault,
+ struct device *dev);
};
extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -160,6 +163,8 @@ extern int vfio_unregister_notifier(struct device *dev,
struct kvm;
extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
+extern int vfio_iommu_dev_fault_handler(struct iommu_fault *fault, void *data);
+
/*
* Sub-module helpers
*/
VFIO manages the DMA mapping itself. To support IOPF for VFIO devices, we add a VFIO page fault handler to serve the reported page faults from the IOMMU driver. Besides, we can pre-map more pages than requested at once to optimize for fewer page fault handlings. Signed-off-by: Shenming Lu <lushenming@huawei.com> --- drivers/vfio/vfio.c | 35 +++++++ drivers/vfio/vfio_iommu_type1.c | 167 ++++++++++++++++++++++++++++++++ include/linux/vfio.h | 5 + 3 files changed, 207 insertions(+)