[PATCH v4 2/5] vfio/type1: optimize vfio_pin_pages_remote()

[lizhe.67@bytedance.com]

From: Li Zhe <lizhe.67@bytedance.com>

When vfio_pin_pages_remote() is called with a range of addresses that
includes large folios, the function currently performs individual
statistics counting operations for each page. This can lead to significant
performance overheads, especially when dealing with large ranges of pages.
Batch processing of statistical counting operations can effectively enhance
performance.

In addition, the pages obtained through longterm GUP are neither invalid
nor reserved. Therefore, we can reduce the overhead associated with some
calls to function is_invalid_reserved_pfn().

The performance test results for completing the 16G VFIO IOMMU DMA mapping
are as follows.

Base(v6.16-rc4):
------- AVERAGE (MADV_HUGEPAGE) --------
VFIO MAP DMA in 0.047 s (340.2 GB/s)
------- AVERAGE (MAP_POPULATE) --------
VFIO MAP DMA in 0.280 s (57.2 GB/s)
------- AVERAGE (HUGETLBFS) --------
VFIO MAP DMA in 0.052 s (310.5 GB/s)

With this patch:
------- AVERAGE (MADV_HUGEPAGE) --------
VFIO MAP DMA in 0.027 s (602.1 GB/s)
------- AVERAGE (MAP_POPULATE) --------
VFIO MAP DMA in 0.257 s (62.4 GB/s)
------- AVERAGE (HUGETLBFS) --------
VFIO MAP DMA in 0.031 s (517.4 GB/s)

For large folio, we achieve an over 40% performance improvement.
For small folios, the performance test results indicate a
slight improvement.

Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
Co-developed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 83 ++++++++++++++++++++++++++++-----
 1 file changed, 71 insertions(+), 12 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 1136d7ac6b59..6909275e46c2 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -318,7 +318,13 @@ static void vfio_dma_bitmap_free_all(struct vfio_iommu *iommu)
 /*
  * Helper Functions for host iova-pfn list
  */
-static struct vfio_pfn *vfio_find_vpfn(struct vfio_dma *dma, dma_addr_t iova)
+
+/*
+ * Find the highest vfio_pfn that overlapping the range
+ * [iova_start, iova_end) in rb tree.
+ */
+static struct vfio_pfn *vfio_find_vpfn_range(struct vfio_dma *dma,
+		dma_addr_t iova_start, dma_addr_t iova_end)
 {
 	struct vfio_pfn *vpfn;
 	struct rb_node *node = dma->pfn_list.rb_node;
@@ -326,9 +332,9 @@ static struct vfio_pfn *vfio_find_vpfn(struct vfio_dma *dma, dma_addr_t iova)
 	while (node) {
 		vpfn = rb_entry(node, struct vfio_pfn, node);
 
-		if (iova < vpfn->iova)
+		if (iova_end <= vpfn->iova)
 			node = node->rb_left;
-		else if (iova > vpfn->iova)
+		else if (iova_start > vpfn->iova)
 			node = node->rb_right;
 		else
 			return vpfn;
@@ -336,6 +342,11 @@ static struct vfio_pfn *vfio_find_vpfn(struct vfio_dma *dma, dma_addr_t iova)
 	return NULL;
 }
 
+static inline struct vfio_pfn *vfio_find_vpfn(struct vfio_dma *dma, dma_addr_t iova)
+{
+	return vfio_find_vpfn_range(dma, iova, iova + PAGE_SIZE);
+}
+
 static void vfio_link_pfn(struct vfio_dma *dma,
 			  struct vfio_pfn *new)
 {
@@ -614,6 +625,39 @@ static long vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr,
 	return ret;
 }
 
+
+static long vpfn_pages(struct vfio_dma *dma,
+		dma_addr_t iova_start, long nr_pages)
+{
+	dma_addr_t iova_end = iova_start + (nr_pages << PAGE_SHIFT);
+	struct vfio_pfn *top = vfio_find_vpfn_range(dma, iova_start, iova_end);
+	long ret = 1;
+	struct vfio_pfn *vpfn;
+	struct rb_node *prev;
+	struct rb_node *next;
+
+	if (likely(!top))
+		return 0;
+
+	prev = next = &top->node;
+
+	while ((prev = rb_prev(prev))) {
+		vpfn = rb_entry(prev, struct vfio_pfn, node);
+		if (vpfn->iova < iova_start)
+			break;
+		ret++;
+	}
+
+	while ((next = rb_next(next))) {
+		vpfn = rb_entry(next, struct vfio_pfn, node);
+		if (vpfn->iova >= iova_end)
+			break;
+		ret++;
+	}
+
+	return ret;
+}
+
 /*
  * Attempt to pin pages.  We really don't want to track all the pfns and
  * the iommu can only map chunks of consecutive pfns anyway, so get the
@@ -680,32 +724,47 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 		 * and rsvd here, and therefore continues to use the batch.
 		 */
 		while (true) {
+			long nr_pages, acct_pages = 0;
+
 			if (pfn != *pfn_base + pinned ||
 			    rsvd != is_invalid_reserved_pfn(pfn))
 				goto out;
 
+			/*
+			 * Using GUP with the FOLL_LONGTERM in
+			 * vaddr_get_pfns() will not return invalid
+			 * or reserved pages.
+			 */
+			nr_pages = num_pages_contiguous(
+					&batch->pages[batch->offset],
+					batch->size);
+			if (!rsvd) {
+				acct_pages = nr_pages;
+				acct_pages -= vpfn_pages(dma, iova, nr_pages);
+			}
+
 			/*
 			 * Reserved pages aren't counted against the user,
 			 * externally pinned pages are already counted against
 			 * the user.
 			 */
-			if (!rsvd && !vfio_find_vpfn(dma, iova)) {
+			if (acct_pages) {
 				if (!dma->lock_cap &&
-				    mm->locked_vm + lock_acct + 1 > limit) {
+				     mm->locked_vm + lock_acct + acct_pages > limit) {
 					pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
 						__func__, limit << PAGE_SHIFT);
 					ret = -ENOMEM;
 					goto unpin_out;
 				}
-				lock_acct++;
+				lock_acct += acct_pages;
 			}
 
-			pinned++;
-			npage--;
-			vaddr += PAGE_SIZE;
-			iova += PAGE_SIZE;
-			batch->offset++;
-			batch->size--;
+			pinned += nr_pages;
+			npage -= nr_pages;
+			vaddr += PAGE_SIZE * nr_pages;
+			iova += PAGE_SIZE * nr_pages;
+			batch->offset += nr_pages;
+			batch->size -= nr_pages;
 
 			if (!batch->size)
 				break;
-- 
2.20.1