[PATCH 04/17] iov_iter: Define flags to qualify page extraction.

From: David Howells
Date: Thu Feb 16 2023 - 16:49:30 EST


Define flags to qualify page extraction to pass into iov_iter_*_pages*()
rather than passing in FOLL_* flags.

For now only a flag to allow peer-to-peer DMA is supported.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
Reviewed-by: Jens Axboe <axboe@xxxxxxxxx>
cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
cc: linux-fsdevel@xxxxxxxxxxxxxxx
cc: linux-block@xxxxxxxxxxxxxxx
---
block/bio.c | 6 +++---
block/blk-map.c | 8 ++++----
include/linux/uio.h | 10 ++++++++--
lib/iov_iter.c | 14 ++++++++------
4 files changed, 23 insertions(+), 15 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index ab59a491a883..b97f3991c904 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1245,11 +1245,11 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
*/
static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
+ iov_iter_extraction_t extraction_flags = 0;
unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
- unsigned int gup_flags = 0;
ssize_t size, left;
unsigned len, i = 0;
size_t offset, trim;
@@ -1264,7 +1264,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);

if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
- gup_flags |= FOLL_PCI_P2PDMA;
+ extraction_flags |= ITER_ALLOW_P2PDMA;

/*
* Each segment in the iov is required to be a block size multiple.
@@ -1275,7 +1275,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
*/
size = iov_iter_get_pages(iter, pages,
UINT_MAX - bio->bi_iter.bi_size,
- nr_pages, &offset, gup_flags);
+ nr_pages, &offset, extraction_flags);
if (unlikely(size <= 0))
return size ? size : -EFAULT;

diff --git a/block/blk-map.c b/block/blk-map.c
index 19940c978c73..080dd60485be 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -265,9 +265,9 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq,
static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
gfp_t gfp_mask)
{
+ iov_iter_extraction_t extraction_flags = 0;
unsigned int max_sectors = queue_max_hw_sectors(rq->q);
unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
- unsigned int gup_flags = 0;
struct bio *bio;
int ret;
int j;
@@ -280,7 +280,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
return -ENOMEM;

if (blk_queue_pci_p2pdma(rq->q))
- gup_flags |= FOLL_PCI_P2PDMA;
+ extraction_flags |= ITER_ALLOW_P2PDMA;

while (iov_iter_count(iter)) {
struct page **pages, *stack_pages[UIO_FASTIOV];
@@ -291,10 +291,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
if (nr_vecs <= ARRAY_SIZE(stack_pages)) {
pages = stack_pages;
bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
- nr_vecs, &offs, gup_flags);
+ nr_vecs, &offs, extraction_flags);
} else {
bytes = iov_iter_get_pages_alloc(iter, &pages,
- LONG_MAX, &offs, gup_flags);
+ LONG_MAX, &offs, extraction_flags);
}
if (unlikely(bytes <= 0)) {
ret = bytes ? bytes : -EFAULT;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 9f158238edba..eec6ed8a627a 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -13,6 +13,8 @@
struct page;
struct pipe_inode_info;

+typedef unsigned int __bitwise iov_iter_extraction_t;
+
struct kvec {
void *iov_base; /* and that should *never* hold a userland pointer */
size_t iov_len;
@@ -252,12 +254,12 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *
loff_t start, size_t count);
ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start,
- unsigned gup_flags);
+ iov_iter_extraction_t extraction_flags);
ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start);
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize, size_t *start,
- unsigned gup_flags);
+ iov_iter_extraction_t extraction_flags);
ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
size_t maxsize, size_t *start);
int iov_iter_npages(const struct iov_iter *i, int maxpages);
@@ -360,4 +362,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
};
}

+/* Flags for iov_iter_get/extract_pages*() */
+/* Allow P2PDMA on the extracted pages */
+#define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01)
+
#endif
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 47c484551c59..9d4949ea9b27 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1426,9 +1426,9 @@ static struct page *first_bvec_segment(const struct iov_iter *i,
static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages, size_t *start,
- unsigned int gup_flags)
+ iov_iter_extraction_t extraction_flags)
{
- unsigned int n;
+ unsigned int n, gup_flags = 0;

if (maxsize > i->count)
maxsize = i->count;
@@ -1436,6 +1436,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
return 0;
if (maxsize > MAX_RW_COUNT)
maxsize = MAX_RW_COUNT;
+ if (extraction_flags & ITER_ALLOW_P2PDMA)
+ gup_flags |= FOLL_PCI_P2PDMA;

if (likely(user_backed_iter(i))) {
unsigned long addr;
@@ -1489,14 +1491,14 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,

ssize_t iov_iter_get_pages(struct iov_iter *i,
struct page **pages, size_t maxsize, unsigned maxpages,
- size_t *start, unsigned gup_flags)
+ size_t *start, iov_iter_extraction_t extraction_flags)
{
if (!maxpages)
return 0;
BUG_ON(!pages);

return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages,
- start, gup_flags);
+ start, extraction_flags);
}
EXPORT_SYMBOL_GPL(iov_iter_get_pages);

@@ -1509,14 +1511,14 @@ EXPORT_SYMBOL(iov_iter_get_pages2);

ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize,
- size_t *start, unsigned gup_flags)
+ size_t *start, iov_iter_extraction_t extraction_flags)
{
ssize_t len;

*pages = NULL;

len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start,
- gup_flags);
+ extraction_flags);
if (len <= 0) {
kvfree(*pages);
*pages = NULL;