[PATCH v6 4/6] io_uring: rsrc: delegate VMA file-backed check to GUP

[PATCH v6 4/6] io_uring: rsrc: delegate VMA file-backed check to GUP

[Lorenzo Stoakes]

Now that the GUP explicitly checks FOLL_LONGTERM pin_user_pages() for
broken file-backed mappings in "mm/gup: disallow FOLL_LONGTERM GUP-nonfast
writing to file-backed mappings", there is no need to explicitly check VMAs
for this condition, so simply remove this logic from io_uring altogether.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
---
 io_uring/rsrc.c | 34 ++++++----------------------------
 1 file changed, 6 insertions(+), 28 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index d46f72a5ef73..b6451f8bc5d5 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1030,9 +1030,8 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
 struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
 {
 	unsigned long start, end, nr_pages;
-	struct vm_area_struct **vmas = NULL;
 	struct page **pages = NULL;
-	int i, pret, ret = -ENOMEM;
+	int pret, ret = -ENOMEM;
 
 	end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	start = ubuf >> PAGE_SHIFT;
@@ -1042,45 +1041,24 @@ struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
 	if (!pages)
 		goto done;
 
-	vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *),
-			      GFP_KERNEL);
-	if (!vmas)
-		goto done;
-
 	ret = 0;
 	mmap_read_lock(current->mm);
 	pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
-			      pages, vmas);
-	if (pret == nr_pages) {
-		/* don't support file backed memory */
-		for (i = 0; i < nr_pages; i++) {
-			struct vm_area_struct *vma = vmas[i];
-
-			if (vma_is_shmem(vma))
-				continue;
-			if (vma->vm_file &&
-			    !is_file_hugepages(vma->vm_file)) {
-				ret = -EOPNOTSUPP;
-				break;
-			}
-		}
+			      pages, NULL);
+	if (pret == nr_pages)
 		*npages = nr_pages;
-	} else {
+	else
 		ret = pret < 0 ? pret : -EFAULT;
-	}
+
 	mmap_read_unlock(current->mm);
 	if (ret) {
-		/*
-		 * if we did partial map, or found file backed vmas,
-		 * release any pages we did get
-		 */
+		/* if we did partial map, release any pages we did get */
 		if (pret > 0)
 			unpin_user_pages(pages, pret);
 		goto done;
 	}
 	ret = 0;
 done:
-	kvfree(vmas);
 	if (ret < 0) {
 		kvfree(pages);
 		pages = ERR_PTR(ret);
-- 
2.40.1

[PATCH v6 5/6] mm/gup: remove vmas parameter from pin_user_pages()

[Lorenzo Stoakes]

We are now in a position where no caller of pin_user_pages() requires the
vmas parameter at all, so eliminate this parameter from the function and
all callers.

This clears the way to removing the vmas parameter from GUP altogether.

Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> (for qib)
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com> (for drivers/media)
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
---
 arch/powerpc/mm/book3s64/iommu_api.c       | 2 +-
 drivers/infiniband/hw/qib/qib_user_pages.c | 2 +-
 drivers/infiniband/hw/usnic/usnic_uiom.c   | 2 +-
 drivers/infiniband/sw/siw/siw_mem.c        | 2 +-
 drivers/media/v4l2-core/videobuf-dma-sg.c  | 2 +-
 drivers/vdpa/vdpa_user/vduse_dev.c         | 2 +-
 drivers/vhost/vdpa.c                       | 2 +-
 include/linux/mm.h                         | 3 +--
 io_uring/rsrc.c                            | 2 +-
 mm/gup.c                                   | 9 +++------
 mm/gup_test.c                              | 9 ++++-----
 net/xdp/xdp_umem.c                         | 2 +-
 12 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 81d7185e2ae8..d19fb1f3007d 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -105,7 +105,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 
 		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
-				mem->hpages + entry, NULL);
+				mem->hpages + entry);
 		if (ret == n) {
 			pinned += n;
 			continue;
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index f693bc753b6b..1bb7507325bc 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -111,7 +111,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 		ret = pin_user_pages(start_page + got * PAGE_SIZE,
 				     num_pages - got,
 				     FOLL_LONGTERM | FOLL_WRITE,
-				     p + got, NULL);
+				     p + got);
 		if (ret < 0) {
 			mmap_read_unlock(current->mm);
 			goto bail_release;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 2a5cac2658ec..84e0f41e7dfa 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -140,7 +140,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 		ret = pin_user_pages(cur_base,
 				     min_t(unsigned long, npages,
 				     PAGE_SIZE / sizeof(struct page *)),
-				     gup_flags, page_list, NULL);
+				     gup_flags, page_list);
 
 		if (ret < 0)
 			goto out;
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index f51ab2ccf151..e6e25f15567d 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -422,7 +422,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
 		umem->page_chunk[i].plist = plist;
 		while (nents) {
 			rv = pin_user_pages(first_page_va, nents, foll_flags,
-					    plist, NULL);
+					    plist);
 			if (rv < 0)
 				goto out_sem_up;
 
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 53001532e8e3..405b89ea1054 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -180,7 +180,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 		data, size, dma->nr_pages);
 
 	err = pin_user_pages(data & PAGE_MASK, dma->nr_pages, gup_flags,
-			     dma->pages, NULL);
+			     dma->pages);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index de97e38c3b82..4d4405f058e8 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1052,7 +1052,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev,
 		goto out;
 
 	pinned = pin_user_pages(uaddr, npages, FOLL_LONGTERM | FOLL_WRITE,
-				page_list, NULL);
+				page_list);
 	if (pinned != npages) {
 		ret = pinned < 0 ? pinned : -ENOMEM;
 		goto out;
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 8c1aefc865f0..61223fcbe82b 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -983,7 +983,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 	while (npages) {
 		sz2pin = min_t(unsigned long, npages, list_size);
 		pinned = pin_user_pages(cur_base, sz2pin,
-					gup_flags, page_list, NULL);
+					gup_flags, page_list);
 		if (sz2pin != pinned) {
 			if (pinned < 0) {
 				ret = pinned;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 679b41ef7a6d..db09c7062965 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2412,8 +2412,7 @@ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm,
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages);
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
-		    unsigned int gup_flags, struct page **pages,
-		    struct vm_area_struct **vmas);
+		    unsigned int gup_flags, struct page **pages);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index b6451f8bc5d5..b56bda46a9eb 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1044,7 +1044,7 @@ struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
 	ret = 0;
 	mmap_read_lock(current->mm);
 	pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
-			      pages, NULL);
+			      pages);
 	if (pret == nr_pages)
 		*npages = nr_pages;
 	else
diff --git a/mm/gup.c b/mm/gup.c
index 1493cc8dd526..36701b5f0123 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3274,8 +3274,6 @@ EXPORT_SYMBOL(pin_user_pages_remote);
  * @gup_flags:	flags modifying lookup behaviour
  * @pages:	array that receives pointers to the pages pinned.
  *		Should be at least nr_pages long.
- * @vmas:	array of pointers to vmas corresponding to each page.
- *		Or NULL if the caller does not require them.
  *
  * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
  * FOLL_PIN is set.
@@ -3284,15 +3282,14 @@ EXPORT_SYMBOL(pin_user_pages_remote);
  * see Documentation/core-api/pin_user_pages.rst for details.
  */
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
-		    unsigned int gup_flags, struct page **pages,
-		    struct vm_area_struct **vmas)
+		    unsigned int gup_flags, struct page **pages)
 {
 	int locked = 1;
 
-	if (!is_valid_gup_args(pages, vmas, NULL, &gup_flags, FOLL_PIN))
+	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_PIN))
 		return 0;
 	return __gup_longterm_locked(current->mm, start, nr_pages,
-				     pages, vmas, &locked, gup_flags);
+				     pages, NULL, &locked, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages);
 
diff --git a/mm/gup_test.c b/mm/gup_test.c
index 9ba8ea23f84e..1668ce0e0783 100644
--- a/mm/gup_test.c
+++ b/mm/gup_test.c
@@ -146,18 +146,17 @@ static int __gup_test_ioctl(unsigned int cmd,
 						 pages + i);
 			break;
 		case PIN_BASIC_TEST:
-			nr = pin_user_pages(addr, nr, gup->gup_flags, pages + i,
-					    NULL);
+			nr = pin_user_pages(addr, nr, gup->gup_flags, pages + i);
 			break;
 		case PIN_LONGTERM_BENCHMARK:
 			nr = pin_user_pages(addr, nr,
 					    gup->gup_flags | FOLL_LONGTERM,
-					    pages + i, NULL);
+					    pages + i);
 			break;
 		case DUMP_USER_PAGES_TEST:
 			if (gup->test_flags & GUP_TEST_FLAG_DUMP_PAGES_USE_PIN)
 				nr = pin_user_pages(addr, nr, gup->gup_flags,
-						    pages + i, NULL);
+						    pages + i);
 			else
 				nr = get_user_pages(addr, nr, gup->gup_flags,
 						    pages + i);
@@ -270,7 +269,7 @@ static inline int pin_longterm_test_start(unsigned long arg)
 							gup_flags, pages);
 		else
 			cur_pages = pin_user_pages(addr, remaining_pages,
-						   gup_flags, pages, NULL);
+						   gup_flags, pages);
 		if (cur_pages < 0) {
 			pin_longterm_test_stop();
 			ret = cur_pages;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 02207e852d79..06cead2b8e34 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -103,7 +103,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 
 	mmap_read_lock(current->mm);
 	npgs = pin_user_pages(address, umem->npgs,
-			      gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
+			      gup_flags | FOLL_LONGTERM, &umem->pgs[0]);
 	mmap_read_unlock(current->mm);
 
 	if (npgs != umem->npgs) {
-- 
2.40.1