summaryrefslogtreecommitdiffstats
path: root/block/fops.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-30 05:21:42 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-30 05:21:42 +0200
commit3d3dfeb3aec7b612d266d500c82054f1fded4980 (patch)
tree11649eab5c74deb74e6e0879613e8053ae3b9970 /block/fops.c
parentMerge tag 'for-6.6/io_uring-2023-08-28' of git://git.kernel.dk/linux (diff)
parentblock: use strscpy() to instead of strncpy() (diff)
downloadlinux-3d3dfeb3aec7b612d266d500c82054f1fded4980.tar.xz
linux-3d3dfeb3aec7b612d266d500c82054f1fded4980.zip
Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe: "Pretty quiet round for this release. This contains: - Add support for zoned storage to ublk (Andreas, Ming) - Series improving performance for drivers that mark themselves as needing a blocking context for issue (Bart) - Cleanup the flush logic (Chengming) - sed opal keyring support (Greg) - Fixes and improvements to the integrity support (Jinyoung) - Add some exports for bcachefs that we can hopefully delete again in the future (Kent) - deadline throttling fix (Zhiguo) - Series allowing building the kernel without buffer_head support (Christoph) - Sanitize the bio page adding flow (Christoph) - Write back cache fixes (Christoph) - MD updates via Song: - Fix perf regression for raid0 large sequential writes (Jan) - Fix split bio iostat for raid0 (David) - Various raid1 fixes (Heinz, Xueshi) - raid6test build fixes (WANG) - Deprecate bitmap file support (Christoph) - Fix deadlock with md sync thread (Yu) - Refactor md io accounting (Yu) - Various non-urgent fixes (Li, Yu, Jack) - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li, Ming, Nitesh, Ruan, Tejun, Thomas, Xu)" * tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits) block: use strscpy() to instead of strncpy() block: sed-opal: keyring support for SED keys block: sed-opal: Implement IOC_OPAL_REVERT_LSP block: sed-opal: Implement IOC_OPAL_DISCOVERY blk-mq: prealloc tags when increase tagset nr_hw_queues blk-mq: delete redundant tagset map update when fallback blk-mq: fix tags leak when shrink nr_hw_queues ublk: zoned: support REQ_OP_ZONE_RESET_ALL md: raid0: account for split bio in iostat accounting md/raid0: Fix performance regression for large sequential writes md/raid0: Factor out helper for mapping and submitting a bio md raid1: allow writebehind to work on any leg device set WriteMostly md/raid1: hold the barrier until handle_read_error() finishes md/raid1: free the r1bio before waiting for blocked rdev md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io() blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init drivers/rnbd: restore sysfs interface to rnbd-client md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid() raid6: test: only check for Altivec if building on powerpc hosts raid6: test: make sure all intermediate and artifact files are .gitignored ...
Diffstat (limited to 'block/fops.c')
-rw-r--r--block/fops.c143
1 files changed, 130 insertions, 13 deletions
diff --git a/block/fops.c b/block/fops.c
index 838ffada5341..a24a624d3bf7 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -15,6 +15,7 @@
#include <linux/falloc.h>
#include <linux/suspend.h>
#include <linux/fs.h>
+#include <linux/iomap.h>
#include <linux/module.h>
#include "blk.h"
@@ -23,15 +24,6 @@ static inline struct inode *bdev_file_inode(struct file *file)
return file->f_mapping->host;
}
-static int blkdev_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create)
-{
- bh->b_bdev = I_BDEV(inode);
- bh->b_blocknr = iblock;
- set_buffer_mapped(bh);
- return 0;
-}
-
static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
{
blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
@@ -387,6 +379,37 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}
+static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+ struct block_device *bdev = I_BDEV(inode);
+ loff_t isize = i_size_read(inode);
+
+ iomap->bdev = bdev;
+ iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
+ if (iomap->offset >= isize)
+ return -EIO;
+ iomap->type = IOMAP_MAPPED;
+ iomap->addr = iomap->offset;
+ iomap->length = isize - iomap->offset;
+ iomap->flags |= IOMAP_F_BUFFER_HEAD; /* noop for !CONFIG_BUFFER_HEAD */
+ return 0;
+}
+
+static const struct iomap_ops blkdev_iomap_ops = {
+ .iomap_begin = blkdev_iomap_begin,
+};
+
+#ifdef CONFIG_BUFFER_HEAD
+static int blkdev_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create)
+{
+ bh->b_bdev = I_BDEV(inode);
+ bh->b_blocknr = iblock;
+ set_buffer_mapped(bh);
+ return 0;
+}
+
static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, blkdev_get_block, wbc);
@@ -429,10 +452,58 @@ const struct address_space_operations def_blk_aops = {
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
- .direct_IO = blkdev_direct_IO,
.migrate_folio = buffer_migrate_folio_norefs,
.is_dirty_writeback = buffer_check_dirty_writeback,
};
+#else /* CONFIG_BUFFER_HEAD */
+static int blkdev_read_folio(struct file *file, struct folio *folio)
+{
+ return iomap_read_folio(folio, &blkdev_iomap_ops);
+}
+
+static void blkdev_readahead(struct readahead_control *rac)
+{
+ iomap_readahead(rac, &blkdev_iomap_ops);
+}
+
+static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
+ struct inode *inode, loff_t offset)
+{
+ loff_t isize = i_size_read(inode);
+
+ if (WARN_ON_ONCE(offset >= isize))
+ return -EIO;
+ if (offset >= wpc->iomap.offset &&
+ offset < wpc->iomap.offset + wpc->iomap.length)
+ return 0;
+ return blkdev_iomap_begin(inode, offset, isize - offset,
+ IOMAP_WRITE, &wpc->iomap, NULL);
+}
+
+static const struct iomap_writeback_ops blkdev_writeback_ops = {
+ .map_blocks = blkdev_map_blocks,
+};
+
+static int blkdev_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct iomap_writepage_ctx wpc = { };
+
+ return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
+}
+
+const struct address_space_operations def_blk_aops = {
+ .dirty_folio = filemap_dirty_folio,
+ .release_folio = iomap_release_folio,
+ .invalidate_folio = iomap_invalidate_folio,
+ .read_folio = blkdev_read_folio,
+ .readahead = blkdev_readahead,
+ .writepages = blkdev_writepages,
+ .is_partially_uptodate = iomap_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
+ .migrate_folio = filemap_migrate_folio,
+};
+#endif /* CONFIG_BUFFER_HEAD */
/*
* for a block special file file_inode(file)->i_size is zero
@@ -506,7 +577,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
* during an unstable branch.
*/
filp->f_flags |= O_LARGEFILE;
- filp->f_mode |= FMODE_BUF_RASYNC;
+ filp->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
/*
* Use the file private data to store the holder for exclusive openes.
@@ -534,6 +605,35 @@ static int blkdev_release(struct inode *inode, struct file *filp)
return 0;
}
+static ssize_t
+blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+ size_t count = iov_iter_count(from);
+ ssize_t written;
+
+ written = kiocb_invalidate_pages(iocb, count);
+ if (written) {
+ if (written == -EBUSY)
+ return 0;
+ return written;
+ }
+
+ written = blkdev_direct_IO(iocb, from);
+ if (written > 0) {
+ kiocb_invalidate_post_direct_write(iocb, count);
+ iocb->ki_pos += written;
+ count -= written;
+ }
+ if (written != -EIOCBQUEUED)
+ iov_iter_revert(from, count - iov_iter_count(from));
+ return written;
+}
+
+static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
+{
+ return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops);
+}
+
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
@@ -543,7 +643,8 @@ static int blkdev_release(struct inode *inode, struct file *filp)
*/
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+ struct file *file = iocb->ki_filp;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct inode *bd_inode = bdev->bd_inode;
loff_t size = bdev_nr_bytes(bdev);
size_t shorted = 0;
@@ -570,7 +671,23 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
iov_iter_truncate(from, size);
}
- ret = __generic_file_write_iter(iocb, from);
+ ret = file_remove_privs(file);
+ if (ret)
+ return ret;
+
+ ret = file_update_time(file);
+ if (ret)
+ return ret;
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ ret = blkdev_direct_write(iocb, from);
+ if (ret >= 0 && iov_iter_count(from))
+ ret = direct_write_fallback(iocb, from, ret,
+ blkdev_buffered_write(iocb, from));
+ } else {
+ ret = blkdev_buffered_write(iocb, from);
+ }
+
if (ret > 0)
ret = generic_write_sync(iocb, ret);
iov_iter_reexpand(from, iov_iter_count(from) + shorted);