diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-26 22:47:20 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-26 22:47:20 +0300 |
commit | a0433f8cae3ac51f59b4b1863032822aaa2d8164 (patch) | |
tree | 9eb7b096aa9f7fa53921e6ff247488f3a55471f5 /fs/direct-io.c | |
parent | 0aa69d53ac7c30f6184f88f2e310d808b32b35a5 (diff) | |
parent | fcaa174a9c995cf0af3967e55644a1543ea07e36 (diff) | |
download | linux-a0433f8cae3ac51f59b4b1863032822aaa2d8164.tar.xz |
Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe:
- NVMe pull request via Keith:
- Various cleanups all around (Irvin, Chaitanya, Christophe)
- Better struct packing (Christophe JAILLET)
- Reduce controller error logs for optional commands (Keith)
- Support for >=64KiB block sizes (Daniel Gomez)
- Fabrics fixes and code organization (Max, Chaitanya, Daniel
Wagner)
- bcache updates via Coly:
- Fix a race at init time (Mingzhe Zou)
- Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)
- use page pinning in the block layer for dio (David)
- convert old block dio code to page pinning (David, Christoph)
- cleanups for pktcdvd (Andy)
- cleanups for rnbd (Guoqing)
- use the unchecked __bio_add_page() for the initial single page
additions (Johannes)
- fix overflows in the Amiga partition handling code (Michael)
- improve mq-deadline zoned device support (Bart)
- keep passthrough requests out of the IO schedulers (Christoph, Ming)
- improve support for flush requests, making them less special to deal
with (Christoph)
- add bdev holder ops and shutdown methods (Christoph)
- fix the name_to_dev_t() situation and use cases (Christoph)
- decouple the block open flags from fmode_t (Christoph)
- ublk updates and cleanups, including adding user copy support (Ming)
- BFQ sanity checking (Bart)
- convert brd from radix to xarray (Pankaj)
- constify various structures (Thomas, Ivan)
- more fine grained persistent reservation ioctl capability checks
(Jingbo)
- misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
Jordy, Li, Min, Yu, Zhong, Waiman)
* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
scsi/sg: don't grab scsi host module reference
ext4: Fix warning in blkdev_put()
block: don't return -EINVAL for not found names in devt_from_devname
cdrom: Fix spectre-v1 gadget
block: Improve kernel-doc headers
blk-mq: don't insert passthrough request into sw queue
bsg: make bsg_class a static const structure
ublk: make ublk_chr_class a static const structure
aoe: make aoe_class a static const structure
block/rnbd: make all 'class' structures const
block: fix the exclusive open mask in disk_scan_partitions
block: add overflow checks for Amiga partition support
block: change all __u32 annotations to __be32 in affs_hardblocks.h
block: fix signed int overflow in Amiga partition support
block: add capacity validation in bdev_add_partition()
block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
block: disallow Persistent Reservation on partitions
reiserfs: fix blkdev_put() warning from release_journal_dev()
block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
block: document the holder argument to blkdev_get_by_path
...
Diffstat (limited to 'fs/direct-io.c')
-rw-r--r-- | fs/direct-io.c | 71 |
1 files changed, 44 insertions, 27 deletions
diff --git a/fs/direct-io.c b/fs/direct-io.c index 0b380bb8a81e..2ceb378b93c0 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -42,8 +42,8 @@ #include "internal.h" /* - * How many user pages to map in one call to get_user_pages(). This determines - * the size of a structure in the slab cache + * How many user pages to map in one call to iov_iter_extract_pages(). This + * determines the size of a structure in the slab cache */ #define DIO_PAGES 64 @@ -121,12 +121,13 @@ struct dio { struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ + bool is_pinned; /* T if we have pins on the pages */ void *private; /* copy from map_bh.b_private */ /* BIO completion state */ spinlock_t bio_lock; /* protects BIO fields below */ - int page_errors; /* errno from get_user_pages() */ + int page_errors; /* err from iov_iter_extract_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ bool should_dirty; /* if pages should be dirtied */ @@ -165,14 +166,14 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio) */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { + struct page **pages = dio->pages; const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; - ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, - &sdio->from); + ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX, + DIO_PAGES, 0, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { - struct page *page = ZERO_PAGE(0); /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid @@ -180,8 +181,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) */ if (dio->page_errors == 0) dio->page_errors = ret; - get_page(page); - dio->pages[0] = page; + dio->pages[0] = ZERO_PAGE(0); sdio->head = 0; sdio->tail = 1; sdio->from = 0; @@ -201,9 +201,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) /* * Get another userspace page. Returns an ERR_PTR on error. Pages are - * buffered inside the dio so that we can call get_user_pages() against a - * decent number of pages, less frequently. To provide nicer use of the - * L1 cache. + * buffered inside the dio so that we can call iov_iter_extract_pages() + * against a decent number of pages, less frequently. To provide nicer use of + * the L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, struct dio_submit *sdio) @@ -219,6 +219,18 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; } +static void dio_pin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + folio_add_pin(page_folio(page)); +} + +static void dio_unpin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + unpin_user_page(page); +} + /* * dio_complete() - called when all DIO BIO I/O has been completed * @@ -402,6 +414,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; + if (dio->is_pinned) + bio_set_flag(bio, BIO_PAGE_PINNED); sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } @@ -442,8 +456,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { - while (sdio->head < sdio->tail) - put_page(dio->pages[sdio->head++]); + if (dio->is_pinned) + unpin_user_pages(dio->pages + sdio->head, + sdio->tail - sdio->head); + sdio->head = sdio->tail; } /* @@ -674,7 +690,7 @@ out: * * Return zero on success. Non-zero means the caller needs to start a new BIO. */ -static inline int dio_bio_add_page(struct dio_submit *sdio) +static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio) { int ret; @@ -686,7 +702,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio) */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; - get_page(sdio->cur_page); + dio_pin_page(dio, sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; @@ -741,11 +757,11 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, goto out; } - if (dio_bio_add_page(sdio) != 0) { + if (dio_bio_add_page(dio, sdio) != 0) { dio_bio_submit(dio, sdio); ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret == 0) { - ret = dio_bio_add_page(sdio); + ret = dio_bio_add_page(dio, sdio); BUG_ON(ret != 0); } } @@ -802,13 +818,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } - get_page(page); /* It is in dio */ + dio_pin_page(dio, page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; @@ -823,7 +839,7 @@ out: ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; } return ret; @@ -924,7 +940,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, ret = get_more_blocks(dio, sdio, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } if (!buffer_mapped(map_bh)) @@ -969,7 +985,7 @@ do_holes: /* AKPM: eargh, -ENOTBLK is a hack */ if (dio_op == REQ_OP_WRITE) { - put_page(page); + dio_unpin_page(dio, page); return -ENOTBLK; } @@ -982,7 +998,7 @@ do_holes: if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ - put_page(page); + dio_unpin_page(dio, page); goto out; } zero_user(page, from, 1 << blkbits); @@ -1022,7 +1038,7 @@ do_holes: sdio->next_block_for_io, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } sdio->next_block_for_io += this_chunk_blocks; @@ -1037,8 +1053,8 @@ next_block: break; } - /* Drop the ref which was taken in get_user_pages() */ - put_page(page); + /* Drop the pin which was taken in get_user_pages() */ + dio_unpin_page(dio, page); } out: return ret; @@ -1133,6 +1149,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, /* will be released by direct_io_worker */ inode_lock(inode); } + dio->is_pinned = iov_iter_extract_will_pin(iter); /* Once we sampled i_size check for reads beyond EOF */ dio->i_size = i_size_read(inode); @@ -1257,7 +1274,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; - put_page(sdio.cur_page); + dio_unpin_page(dio, sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) |