To optimize for fewer page fault handlings, we can pre-map more pages
than requested at once.
Note that IOPF_PREMAP_LEN is just an arbitrary value for now, which we
could try further tuning.
Signed-off-by: Shenming Lu
---
drivers/vfio/vfio_iommu_type1.c | 131 ++--
1 file changed, 123 insertions(+), 8 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 1cb9d1f2717b..01e296c6dc9e 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -3217,6 +3217,91 @@ static int vfio_iommu_type1_dirty_pages(struct
vfio_iommu *iommu,
return -EINVAL;
}
+/*
+ * To optimize for fewer page fault handlings, try to
+ * pre-map more pages than requested.
+ */
+#define IOPF_PREMAP_LEN512
+
+/*
+ * 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,
+, 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:
+ if (batch->size == 1 && !batch->offset) {
+ put_pfn(pfn, dma->prot);
+ batch->size = 0;
+ }
+
+ mmput(mm);
+ return ret;
+}
+
+static void unpin_pages_iopf(struct vfio_dma *dma,
+unsigned long pfn, unsigned long npages)
+{
+ while (npages--)
+ put_pfn(pfn++, dma->prot);
+}
+
/* VFIO I/O Page Fault handler */
static int vfio_iommu_type1_dma_map_iopf(struct iommu_fault *fault, void *data)
{
@@ -3225,9 +3310,11 @@ static int vfio_iommu_type1_dma_map_iopf(struct
iommu_fault *fault, void *data)
struct vfio_iopf_group *iopf_group;
struct vfio_iommu *iommu;
struct vfio_dma *dma;
+ struct vfio_batch batch;
dma_addr_t iova = ALIGN_DOWN(fault->prm.addr, PAGE_SIZE);
int access_flags = 0;
- unsigned long bit_offset, vaddr, pfn;
+ size_t premap_len, map_len, mapped_len = 0;
+ unsigned long bit_offset, vaddr, pfn, i, npages;
int ret;
enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
struct iommu_page_response resp = {0};
@@ -3263,19 +3350,47 @@ static int vfio_iommu_type1_dma_map_iopf(struct
iommu_fault *fault, void *data)
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();
- if (vfio_pin_page_external(dma, vaddr, , false))
- goto out_invalid;
+ while (map_len) {
+ ret = pin_pages_iopf(dma, vaddr + mapped_len,
+map_len >> PAGE_SHIFT, ,
+, );
+ if (!npages)
+ break;
- if (vfio_iommu_map(iommu, iova, pfn, 1, dma->prot)) {
- put_pfn(pfn, dma->prot);
- goto
