From: Pavel Begunkov <asml.silence@gmail.com>
To: Ming Lei <ming.lei@redhat.com>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Matthew Wilcox <willy@infradead.org>,
Christoph Hellwig <hch@infradead.org>,
linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH] block: add bio_iov_iter_nvecs for figuring out nr_vecs
Date: Mon, 7 Dec 2020 18:07:39 +0000 [thread overview]
Message-ID: <3eb1020d-c336-dbe6-d75e-70c388464e6e@gmail.com> (raw)
In-Reply-To: <20201201120652.487077-1-ming.lei@redhat.com>
On 01/12/2020 12:06, Ming Lei wrote:
> Pavel reported that iov_iter_npages is a bit heavy in case of bvec
> iter.
>
> Turns out it isn't necessary to iterate every page in the bvec iter,
> and we call iov_iter_npages() just for figuring out how many bio
> vecs need to be allocated. And we can simply map each vector in bvec iter
> to bio's vec, so just return iter->nr_segs from bio_iov_iter_nvecs() for
> bvec iter.
>
> Also rename local variable 'nr_pages' as 'nr_vecs' which exactly matches its
> real usage.
>
> This patch is based on Mathew's post:
Tried this, the system didn't boot + discovered a filesystem blowned after
booting with a stable kernel. That's on top of 4498a8536c816 ("block: use
an xarray for disk->part_tbl"), which works fine. Ideas?
> https://lore.kernel.org/linux-block/20201120123931.GN29991@casper.infradead.org/
>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Pavel Begunkov <asml.silence@gmail.com>
> Cc: Christoph Hellwig <hch@infradead.org>
> Cc: linux-fsdevel@vger.kernel.org
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
> fs/block_dev.c | 30 +++++++++++++++---------------
> fs/iomap/direct-io.c | 14 +++++++-------
> include/linux/bio.h | 10 ++++++++++
> 3 files changed, 32 insertions(+), 22 deletions(-)
>
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index d8664f5c1ff6..4fd9bb4306db 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -218,7 +218,7 @@ static void blkdev_bio_end_io_simple(struct bio *bio)
>
> static ssize_t
> __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
> - int nr_pages)
> + int nr_vecs)
> {
> struct file *file = iocb->ki_filp;
> struct block_device *bdev = I_BDEV(bdev_file_inode(file));
> @@ -233,16 +233,16 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
> (bdev_logical_block_size(bdev) - 1))
> return -EINVAL;
>
> - if (nr_pages <= DIO_INLINE_BIO_VECS)
> + if (nr_vecs <= DIO_INLINE_BIO_VECS)
> vecs = inline_vecs;
> else {
> - vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
> + vecs = kmalloc_array(nr_vecs, sizeof(struct bio_vec),
> GFP_KERNEL);
> if (!vecs)
> return -ENOMEM;
> }
>
> - bio_init(&bio, vecs, nr_pages);
> + bio_init(&bio, vecs, nr_vecs);
> bio_set_dev(&bio, bdev);
> bio.bi_iter.bi_sector = pos >> 9;
> bio.bi_write_hint = iocb->ki_hint;
> @@ -353,7 +353,7 @@ static void blkdev_bio_end_io(struct bio *bio)
> }
>
> static ssize_t
> -__blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
> +__blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_vecs)
> {
> struct file *file = iocb->ki_filp;
> struct inode *inode = bdev_file_inode(file);
> @@ -371,7 +371,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
> (bdev_logical_block_size(bdev) - 1))
> return -EINVAL;
>
> - bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
> + bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, &blkdev_dio_pool);
>
> dio = container_of(bio, struct blkdev_dio, bio);
> dio->is_sync = is_sync = is_sync_kiocb(iocb);
> @@ -420,8 +420,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
> dio->size += bio->bi_iter.bi_size;
> pos += bio->bi_iter.bi_size;
>
> - nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
> - if (!nr_pages) {
> + nr_vecs = bio_iov_iter_nvecs(iter, BIO_MAX_PAGES);
> + if (!nr_vecs) {
> bool polled = false;
>
> if (iocb->ki_flags & IOCB_HIPRI) {
> @@ -451,7 +451,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
> }
>
> submit_bio(bio);
> - bio = bio_alloc(GFP_KERNEL, nr_pages);
> + bio = bio_alloc(GFP_KERNEL, nr_vecs);
> }
>
> if (!is_poll)
> @@ -483,15 +483,15 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
> static ssize_t
> blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
> {
> - int nr_pages;
> + int nr_vecs;
>
> - nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1);
> - if (!nr_pages)
> + nr_vecs = bio_iov_iter_nvecs(iter, BIO_MAX_PAGES + 1);
> + if (!nr_vecs)
> return 0;
> - if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
> - return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
> + if (is_sync_kiocb(iocb) && nr_vecs <= BIO_MAX_PAGES)
> + return __blkdev_direct_IO_simple(iocb, iter, nr_vecs);
>
> - return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES));
> + return __blkdev_direct_IO(iocb, iter, min(nr_vecs, BIO_MAX_PAGES));
> }
>
> static __init int blkdev_init(void)
> diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
> index 933f234d5bec..cc779ecc8144 100644
> --- a/fs/iomap/direct-io.c
> +++ b/fs/iomap/direct-io.c
> @@ -211,7 +211,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
> struct bio *bio;
> bool need_zeroout = false;
> bool use_fua = false;
> - int nr_pages, ret = 0;
> + int nr_vecs, ret = 0;
> size_t copied = 0;
> size_t orig_count;
>
> @@ -250,9 +250,9 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
> orig_count = iov_iter_count(dio->submit.iter);
> iov_iter_truncate(dio->submit.iter, length);
>
> - nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
> - if (nr_pages <= 0) {
> - ret = nr_pages;
> + nr_vecs = bio_iov_iter_nvecs(dio->submit.iter, BIO_MAX_PAGES);
> + if (nr_vecs <= 0) {
> + ret = nr_vecs;
> goto out;
> }
>
> @@ -271,7 +271,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
> goto out;
> }
>
> - bio = bio_alloc(GFP_KERNEL, nr_pages);
> + bio = bio_alloc(GFP_KERNEL, nr_vecs);
> bio_set_dev(bio, iomap->bdev);
> bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
> bio->bi_write_hint = dio->iocb->ki_hint;
> @@ -308,10 +308,10 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
> dio->size += n;
> copied += n;
>
> - nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
> + nr_vecs = bio_iov_iter_nvecs(dio->submit.iter, BIO_MAX_PAGES);
> iomap_dio_submit_bio(dio, iomap, bio, pos);
> pos += n;
> - } while (nr_pages);
> + } while (nr_vecs);
>
> /*
> * We need to zeroout the tail of a sub-block write if the extent type
> diff --git a/include/linux/bio.h b/include/linux/bio.h
> index ecf67108f091..b985857ce9d1 100644
> --- a/include/linux/bio.h
> +++ b/include/linux/bio.h
> @@ -10,6 +10,7 @@
> #include <linux/ioprio.h>
> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
> #include <linux/blk_types.h>
> +#include <linux/uio.h>
>
> #define BIO_DEBUG
>
> @@ -807,4 +808,13 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
> bio->bi_opf |= REQ_NOWAIT;
> }
>
> +static inline int bio_iov_iter_nvecs(const struct iov_iter *i, int maxvecs)
> +{
> + if (!iov_iter_count(i))
> + return 0;
> + if (iov_iter_is_bvec(i))
> + return min_t(int, maxvecs, i->nr_segs);
> + return iov_iter_npages(i, maxvecs);
> +}
> +
> #endif /* __LINUX_BIO_H */
>
--
Pavel Begunkov
next prev parent reply other threads:[~2020-12-07 18:11 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-01 12:06 [PATCH] block: add bio_iov_iter_nvecs for figuring out nr_vecs Ming Lei
2020-12-01 12:52 ` Matthew Wilcox
2020-12-01 12:59 ` Christoph Hellwig
2020-12-01 13:17 ` Pavel Begunkov
2020-12-01 13:32 ` Christoph Hellwig
2020-12-01 13:36 ` Pavel Begunkov
2020-12-01 13:45 ` Christoph Hellwig
2020-12-01 13:48 ` Pavel Begunkov
2020-12-02 2:10 ` Ming Lei
2020-12-02 8:02 ` Christoph Hellwig
2020-12-03 22:36 ` Johannes Weiner
2020-12-03 23:43 ` Pavel Begunkov
2020-12-04 12:48 ` Christoph Hellwig
2020-12-10 13:18 ` Johannes Weiner
2020-12-11 13:22 ` Pavel Begunkov
2020-12-02 1:46 ` Ming Lei
2020-12-02 14:06 ` Pavel Begunkov
2020-12-02 15:02 ` Christoph Hellwig
2020-12-02 16:56 ` Jens Axboe
2020-12-07 18:07 ` Pavel Begunkov [this message]
2020-12-08 1:21 ` Ming Lei
2020-12-08 1:50 ` Ming Lei
2020-12-08 2:54 ` Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3eb1020d-c336-dbe6-d75e-70c388464e6e@gmail.com \
--to=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=hch@infradead.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).