block: ensure iov_iter advances for added pages
Subsystems (2)
PATCH v2 1/3 block: ensure iov_iter advances for added pages
From: Keith Busch <[email protected]>
There are cases where a bio may not accept additional pages, and the iov needs to advance to the last data length that was accepted. The zone append used to handle this correctly, but was inadvertently broken when the setup was made common with the normal r/w case.
--- block/bio.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
block/bio.c +4 -4
@@ -1211,6 +1211,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)ssize_t size, left;unsigned len, i;size_t offset; +int ret =0 ;/* * Move page array up in the allocated memory for the bio vecs as far as
@@ -1235,7 +1236,6 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)for (left = size, i =0 ; left >0 ; left -= len, i++) {struct page *page = pages[i]; -int ret; len =min_t (size_t,PAGE_SIZE - offset, left);if (bio_op (bio) ==REQ_OP_ZONE_APPEND )
@@ -1246,13 +1246,13 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)if (ret) {bio_put_pages (pages + i, left, offset); -return ret; +break ; } offset =0 ; } -iov_iter_advance (iter, size); -return 0 ; +iov_iter_advance (iter, size - left); +return ret; }/**
Signature · 1 line
2.30.2
PATCH v2 2/3 block: ensure bio_iov_add_page can't fail
From: Keith Busch <[email protected]>
Adding the page could fail on the bio_full() condition, which checks for either exceeding the bio's max segments or total size exceeding UINT_MAX. We already ensure the max segments can't be exceeded, so just ensure the total size won't reach the limit. This simplifies error handling and removes unnecessary repeated bio_full() checks.
--- block/bio.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)
block/bio.c +9 -10
@@ -1165,8 +1165,6 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,bool same_page = false;if (!__bio_try_merge_page (bio, page, len, offset, &same_page)) { -if (WARN_ON_ONCE (bio_full (bio, len))) -return -EINVAL ;__bio_add_page (bio, page, len, offset);return 0 ; }
@@ -1228,7 +1226,8 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)* result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ - size =iov_iter_get_pages (iter, pages,LONG_MAX , nr_pages, &offset); + size =iov_iter_get_pages (iter, pages,UINT_MAX - bio->bi_iter.bi_size, + nr_pages, &offset);if (size >0 ) size =ALIGN_DOWN (size,bdev_logical_block_size (bio->bi_bdev));if (unlikely (size <=0 ))
@@ -1238,16 +1237,16 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)struct page *page = pages[i]; len =min_t (size_t,PAGE_SIZE - offset, left); -if (bio_op (bio) ==REQ_OP_ZONE_APPEND ) +if (bio_op (bio) ==REQ_OP_ZONE_APPEND ) { ret =bio_iov_add_zone_append_page (bio, page, len, offset); -else - ret =bio_iov_add_page (bio, page, len, offset); +if (ret) { +bio_put_pages (pages + i, left, offset); +break ; + } + }else +bio_iov_add_page (bio, page, len, offset); -if (ret) { -bio_put_pages (pages + i, left, offset); -break ; - } offset =0 ; }
Signature · 1 line
2.30.2
PATCH v2 3/3 block: fix leaking page ref on truncated direct io
In reply to Keith BuschFrom: Keith Busch <[email protected]>
The size being added to a bio from an iov is aligned to a block size after the pages were gotten. If the new aligned size truncates the last page, its reference was being leaked. Ensure all pages that were not added to the bio have their reference released.
Since this essentially requires doing the same that bio_put_pages(), and there was only one caller for that function, this patch makes the put_page() loop common for everyone.
---v1->v2: fixed possible uninitialized variable
This update is also pushed to my repo,
https://git.kernel.org/pub/scm/linux/kernel/git/kbusch/linux.git/log/?h=alignment-fixes-rebased
block/bio.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-)
block/bio.c +15 -15
@@ -1151,14 +1151,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)bio_set_flag (bio,BIO_CLONED ); } -static void bio_put_pages (struct page **pages,size_t size,size_t off) -{ -size_t i, nr =DIV_ROUND_UP (size + (off & ~PAGE_MASK ),PAGE_SIZE ); - -for (i =0 ; i < nr; i++) -put_page (pages[i]); -} -static int bio_iov_add_page (struct bio *bio,struct page *page,unsigned int len,unsigned int offset) {
@@ -1207,7 +1199,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;struct page **pages = (struct page **)bv;ssize_t size, left; -unsigned len, i; +unsigned len, i =0 ;size_t offset;int ret =0 ;
@@ -1228,10 +1220,16 @@ 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); -if (size >0 ) +if (size >0 ) { + nr_pages =DIV_ROUND_UP (offset + size,PAGE_SIZE ); size =ALIGN_DOWN (size,bdev_logical_block_size (bio->bi_bdev)); -if (unlikely (size <=0 )) -return size ? size : -EFAULT ; + }else + nr_pages =0 ; + +if (unlikely (size <=0 )) { + ret = size ? size : -EFAULT ; + goto out; + }for (left = size, i =0 ; left >0 ; left -= len, i++) {struct page *page = pages[i];
@@ -1240,10 +1238,8 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)if (bio_op (bio) ==REQ_OP_ZONE_APPEND ) { ret =bio_iov_add_zone_append_page (bio, page, len, offset); -if (ret) { -bio_put_pages (pages + i, left, offset); +if (ret)break ; - } }else bio_iov_add_page (bio, page, len, offset);
@@ -1251,6 +1247,10 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) }iov_iter_advance (iter, size - left); +out: +while (i < nr_pages) +put_page (pages[i++]); +return ret; }
Signature · 1 line
2.30.2
Jens Axboe
maintainerQuoted 6 lines · Keith Busch
From: Keith Busch <[email protected]>
There are cases where a bio may not accept additional pages, and the iov needs to advance to the last data length that was accepted. The zone append used to handle this correctly, but was inadvertently broken when the setup was made common with the normal r/w case.
Al, how do you want to handle this? I currently see you have that block-fixes branch, but I don't see anything depending on it. I can do one of the following with these three fixes:
1) Apply them on top of for-5.20/block
2) Apply them to a new branch off the tag I made for you
And that still leaves the question of what will happen with your block-fixes branch. Did you want me to pull that in? Or?
Signature · 1 line
Jens Axboe
Quoted 8 lines · Keith Busch
From: Keith Busch <[email protected]>
There are cases where a bio may not accept additional pages, and the iov needs to advance to the last data length that was accepted. The zone append used to handle this correctly, but was inadvertently broken when the setup was made common with the normal r/w case.
[...]
Applied, thanks!
[1/3] block: ensure iov_iter advances for added pages
commit: 5a044eef1265581683530e75351c19e29ee33a11
[2/3] block: ensure bio_iov_add_page can't fail
commit: ac3c48e32c047a3781d6bc28bb5013e4431350fd
[3/3] block: fix leaking page ref on truncated direct io
commit: 44b6b0b0e980d99d24de7e5d57baae48a78db3b6Best regards,
Signature · 1 line
Jens Axboe