[PATCH v6 4/5] udmabuf: Pin the pages using memfd_pin_user_pages() API (v4)

[Vivek Kasireddy <vivek.kasireddy@intel.com>]

Using memfd_pin_user_pages() will ensure that the pages are pinned
correctly using FOLL_PIN. And, this also ensures that we don't
accidentally break features such as memory hotunplug as it would
not allow pinning pages in the movable zone.

Using this new API also simplifies the code as we no longer have
to deal with extracting individual pages from their mappings. As
a result, we can drop some of the local variables such as page,
hpage, mapping, etc.

v2:
- Adjust to the change in signature of pin_user_pages_fd() by
  passing in file * instead of fd.

v3:
- Limit the changes in this patch only to those that are required
  for using pin_user_pages_fd()
- Slightly improve the commit message

v4:
- Adjust to the change in name of the API (memfd_pin_user_pages)

Cc: David Hildenbrand <david@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
 drivers/dma-buf/udmabuf.c | 62 +++++++++++++++------------------------
 1 file changed, 23 insertions(+), 39 deletions(-)

diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 1d1cc5e7e613..887dc287a23c 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -156,7 +156,8 @@ static void release_udmabuf(struct dma_buf *buf)
 		put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
 
 	for (pg = 0; pg < ubuf->pagecount; pg++)
-		put_page(ubuf->pages[pg]);
+		unpin_user_page(ubuf->pages[pg]);
+
 	kfree(ubuf->subpgoff);
 	kfree(ubuf->pages);
 	kfree(ubuf);
@@ -217,15 +218,13 @@ static long udmabuf_create(struct miscdevice *device,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
-	struct address_space *mapping = NULL;
 	struct udmabuf *ubuf;
 	struct dma_buf *buf;
-	pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
-	struct page *page, *hpage = NULL;
-	struct folio *folio;
+	pgoff_t pgcnt, pgbuf = 0, pglimit, nr_pages;
 	pgoff_t mapidx, chunkoff, maxchunks;
 	struct hstate *hpstate;
-	int seals, ret = -EINVAL;
+	long ret = -EINVAL;
+	int seals;
 	u32 i, flags;
 
 	ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
@@ -259,8 +258,7 @@ static long udmabuf_create(struct miscdevice *device,
 		memfd = fget(list[i].memfd);
 		if (!memfd)
 			goto err;
-		mapping = memfd->f_mapping;
-		if (!shmem_mapping(mapping) && !is_file_hugepages(memfd))
+		if (!shmem_file(memfd) && !is_file_hugepages(memfd))
 			goto err;
 		seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
 		if (seals == -EINVAL)
@@ -269,7 +267,7 @@ static long udmabuf_create(struct miscdevice *device,
 		if ((seals & SEALS_WANTED) != SEALS_WANTED ||
 		    (seals & SEALS_DENIED) != 0)
 			goto err;
-		pgoff = list[i].offset >> PAGE_SHIFT;
+		mapidx = list[i].offset >> PAGE_SHIFT;
 		pgcnt = list[i].size   >> PAGE_SHIFT;
 		if (is_file_hugepages(memfd)) {
 			if (!ubuf->subpgoff) {
@@ -288,42 +286,27 @@ static long udmabuf_create(struct miscdevice *device,
 				    ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
 			maxchunks = huge_page_size(hpstate) >> PAGE_SHIFT;
 		}
-		for (pgidx = 0; pgidx < pgcnt; pgidx++) {
+
+		do {
+			nr_pages = shmem_file(memfd) ? pgcnt : 1;
+			ret = memfd_pin_user_pages(memfd, mapidx, nr_pages,
+						   ubuf->pages + pgbuf);
+			if (ret < 0)
+				goto err;
+
 			if (is_file_hugepages(memfd)) {
-				if (!hpage) {
-					folio = __filemap_get_folio(mapping, mapidx,
-								    FGP_ACCESSED, 0);
-					hpage = IS_ERR(folio) ? NULL: &folio->page;
-					if (!hpage) {
-						ret = -EINVAL;
-						goto err;
-					}
-				}
-				get_page(hpage);
-				ubuf->pages[pgbuf] = hpage;
-				ubuf->subpgoff[pgbuf++] = chunkoff << PAGE_SHIFT;
+				ubuf->subpgoff[pgbuf] = chunkoff << PAGE_SHIFT;
 				if (++chunkoff == maxchunks) {
-					put_page(hpage);
-					hpage = NULL;
 					chunkoff = 0;
 					mapidx += pages_per_huge_page(hpstate);
 				}
-			} else {
-				mapidx = pgoff + pgidx;
-				page = shmem_read_mapping_page(mapping, mapidx);
-				if (IS_ERR(page)) {
-					ret = PTR_ERR(page);
-					goto err;
-				}
-				ubuf->pages[pgbuf++] = page;
 			}
-		}
+			pgbuf += nr_pages;
+			pgcnt -= nr_pages;
+		} while (pgcnt > 0);
+
 		fput(memfd);
 		memfd = NULL;
-		if (hpage) {
-			put_page(hpage);
-			hpage = NULL;
-		}
 	}
 
 	exp_info.ops  = &udmabuf_ops;
@@ -344,8 +327,9 @@ static long udmabuf_create(struct miscdevice *device,
 	return dma_buf_fd(buf, flags);
 
 err:
-	while (pgbuf > 0)
-		put_page(ubuf->pages[--pgbuf]);
+	while (pgbuf-- > 0)
+		if (ubuf->pages[pgbuf])
+			unpin_user_page(ubuf->pages[pgbuf]);
 	if (memfd)
 		fput(memfd);
 	kfree(ubuf->subpgoff);
-- 
2.39.2