f2fs: use iomap for direct I/O
Subsystems (2)
v2 cover f2fs: use iomap for direct I/O
This series makes f2fs use the iomap direct I/O implementation instead of the fs/direct-io.c one. In order to do this, it adds f2fs_iomap_ops, since this is the first use of iomap in f2fs.
The iomap direct I/O implementation is more efficient than fs/direct-io.c. Switching to iomap also avoids the need to add new features and optimizations to the old implementation; e.g., see
https://lore.kernel.org/r/[email protected] and
https://lore.kernel.org/r/[email protected].
Patch 1 adds f2fs_iomap_ops, and patch 2 switches direct I/O reads and writes to iomap.
Careful review is appreciated, as I'm not an expert in all areas here.
This series applies to commit 0de0db9b033a of f2fs.git#dev
(https://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git/log/?h=dev).
Changed since v1:
- Dropped the preparatory cleanups/fixes for f2fs_file_write_iter(), since they have been applied.
- Merged the last three patches into one.
- Implemented iomap_dio_ops::end_io() and switched to __iomap_dio_rw() to simplify updating of f2fs's in-flight DIO counters, as suggested by Christoph.
Eric Biggers (2):
f2fs: implement iomap operations
f2fs: use iomap for direct I/O
fs/f2fs/Kconfig | 1 + fs/f2fs/data.c | 260 +++++++++--------------------------- fs/f2fs/f2fs.h | 22 +-- fs/f2fs/file.c | 346 ++++++++++++++++++++++++++++++++++++++++++------ 4 files changed, 370 insertions(+), 259 deletions(-)
base-commit: 0de0db9b033af99f494c9ee4a2c9bac6456da1eb
Signature · 1 line
2.32.0
PATCH v2 1/2 f2fs: implement iomap operations
From: Eric Biggers <[email protected]>
Implement 'struct iomap_ops' for f2fs, in preparation for making f2fs use iomap for direct I/O.
Note that this may be used for other things besides direct I/O in the future; however, for now I've only tested it for direct I/O.
--- fs/f2fs/Kconfig | 1 + fs/f2fs/data.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++ fs/f2fs/f2fs.h | 1 + 3 files changed, 60 insertions(+)
fs/f2fs/Kconfig +1 -0
@@ -7,6 +7,7 @@ config F2FS_FS select CRYPTO_CRC32 select F2FS_FS_XATTR if FS_ENCRYPTION select FS_ENCRYPTION_ALGS if FS_ENCRYPTION + select FS_IOMAP select LZ4_COMPRESS if F2FS_FS_LZ4 select LZ4_DECOMPRESS if F2FS_FS_LZ4 select LZ4HC_COMPRESS if F2FS_FS_LZ4HC
fs/f2fs/data.c +58 -0
67 lines not on this page · raw message
fs/f2fs/f2fs.h +1 -0
@@ -3644,6 +3644,7 @@ int f2fs_init_post_read_processing(void);void f2fs_destroy_post_read_processing (void );int f2fs_init_post_read_wq (struct f2fs_sb_info *sbi);void f2fs_destroy_post_read_wq (struct f2fs_sb_info *sbi); +extern const struct iomap_ops f2fs_iomap_ops;/* * gc.c
Signature · 1 line
2.32.0
PATCH v2 2/2 f2fs: use iomap for direct I/O
In reply to Eric BiggersFrom: Eric Biggers <[email protected]>
Make f2fs_file_read_iter() and f2fs_file_write_iter() use the iomap direct I/O implementation instead of the fs/direct-io.c one.
The iomap implementation is more efficient, and it also avoids the need to add new features and optimizations to the old implementation.
This new implementation also eliminates the need for f2fs to hook bio submission and completion and to allocate memory per-bio. This is because it's possible to correctly update f2fs's in-flight DIO counters using __iomap_dio_rw() in combination with an implementation of iomap_dio_ops::end_io() (as suggested by Christoph Hellwig).
When possible, this new implementation preserves existing f2fs behavior such as the conditions for falling back to buffered I/O.
This patch has been tested with xfstests by running 'gce-xfstests -c f2fs -g auto -X generic/017' with and without this patch; no regressions were seen. (Some tests fail both before and after. generic/017 hangs both before and after, so it had to be excluded.)
--- fs/f2fs/data.c | 202 +---------------------------- fs/f2fs/f2fs.h | 21 +-- fs/f2fs/file.c | 346 ++++++++++++++++++++++++++++++++++++++++++------- 3 files changed, 310 insertions(+), 259 deletions(-)
fs/f2fs/data.c +2 -200
@@ -1363,11 +1363,6 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)f2fs_invalidate_compress_page (sbi, old_blkaddr); }f2fs_update_data_blkaddr (dn, dn->data_blkaddr); - -/* -* i_size will be updated by direct_IO. Otherwise, we'll get stale -* data from unwritten block via dio_read. -*/ return 0 ; }
@@ -1655,47 +1650,6 @@ static inline u64 blks_to_bytes(struct inode *inode, u64 blks)return (blks << inode->i_blkbits); } -static int __get_data_block (struct inode *inode,sector_t iblock, -struct buffer_head *bh,int create,int flag, -pgoff_t *next_pgofs,int seg_type,bool may_write) -{ -struct f2fs_map_blocks map; -int err; - - map.m_lblk = iblock; - map.m_len =bytes_to_blks (inode, bh->b_size); - map.m_next_pgofs = next_pgofs; - map.m_next_extent =NULL ; - map.m_seg_type = seg_type; - map.m_may_create = may_write; - - err =f2fs_map_blocks (inode, &map, create, flag); -if (!err) { -map_bh (bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS ) | map.m_flags; - bh->b_size =blks_to_bytes (inode, map.m_len); - } -return err; -} - -static int get_data_block_dio_write (struct inode *inode,sector_t iblock, -struct buffer_head *bh_result,int create) -{ -return __get_data_block (inode, iblock, bh_result, create, -F2FS_GET_BLOCK_DIO ,NULL , -f2fs_rw_hint_to_seg_type (inode->i_write_hint), - true); -} - -static int get_data_block_dio (struct inode *inode,sector_t iblock, -struct buffer_head *bh_result,int create) -{ -return __get_data_block (inode, iblock, bh_result, create, -F2FS_GET_BLOCK_DIO ,NULL , -f2fs_rw_hint_to_seg_type (inode->i_write_hint), - false); -} -static int f2fs_xattr_fiemap (struct inode *inode,struct fiemap_extent_info *fieinfo) {
@@ -3132,7 +3086,7 @@ static int f2fs_write_data_pages(struct address_space *mapping, FS_CP_DATA_IO : FS_DATA_IO); } -static void f2fs_write_failed (struct inode *inode,loff_t to) +void f2fs_write_failed (struct inode *inode,loff_t to) {loff_t i_size =i_size_read (inode);
@@ -3417,158 +3371,6 @@ static int f2fs_write_end(struct file *file,return copied; } -static int check_direct_IO (struct inode *inode,struct iov_iter *iter, -loff_t offset) -{ -unsigned i_blkbits =READ_ONCE (inode->i_blkbits); -unsigned blkbits = i_blkbits; -unsigned blocksize_mask = (1 << blkbits) -1 ; -unsigned long align = offset |iov_iter_alignment (iter); -struct block_device *bdev = inode->i_sb->s_bdev; - -if (iov_iter_rw (iter) ==READ && offset >=i_size_read (inode)) -return 1 ; - -if (align & blocksize_mask) { -if (bdev) - blkbits =blksize_bits (bdev_logical_block_size (bdev)); - blocksize_mask = (1 << blkbits) -1 ; -if (align & blocksize_mask) -return -EINVAL ; -return 1 ; - } -return 0 ; -} - -static void f2fs_dio_end_io (struct bio *bio) -{ -struct f2fs_private_dio *dio = bio->bi_private; - -dec_page_count (F2FS_I_SB (dio->inode), - dio->write ?F2FS_DIO_WRITE :F2FS_DIO_READ ); - - bio->bi_private = dio->orig_private; - bio->bi_end_io = dio->orig_end_io; - -kfree (dio); - -bio_endio (bio); -} - -static void f2fs_dio_submit_bio (struct bio *bio,struct inode *inode, -loff_t file_offset) -{ -struct f2fs_private_dio *dio; -bool write = (bio_op (bio) ==REQ_OP_WRITE ); - - dio =f2fs_kzalloc (F2FS_I_SB (inode), -sizeof (struct f2fs_private_dio ),GFP_NOFS ); -if (!dio) - goto out; - - dio->inode = inode; - dio->orig_end_io = bio->bi_end_io; - dio->orig_private = bio->bi_private; - dio->write = write; - - bio->bi_end_io = f2fs_dio_end_io; - bio->bi_private = dio; - -inc_page_count (F2FS_I_SB (inode), - write ?F2FS_DIO_WRITE :F2FS_DIO_READ ); - -submit_bio (bio); -return ; -out: - bio->bi_status =BLK_STS_IOERR ; -bio_endio (bio); -} - -static ssize_t f2fs_direct_IO (struct kiocb *iocb,struct iov_iter *iter) -{ -struct address_space *mapping = iocb->ki_filp->f_mapping; -struct inode *inode = mapping->host; -struct f2fs_sb_info *sbi =F2FS_I_SB (inode); -struct f2fs_inode_info *fi =F2FS_I (inode); -size_t count =iov_iter_count (iter); -loff_t offset = iocb->ki_pos; -int rw =iov_iter_rw (iter); -int err; -enum rw_hint hint = iocb->ki_hint; -int whint_mode =F2FS_OPTION (sbi).whint_mode; -bool do_opu; - - err =check_direct_IO (inode, iter, offset); -if (err) -return err <0 ? err :0 ; - -if (f2fs_force_buffered_io (inode, iocb, iter)) -return 0 ; - - do_opu = rw ==WRITE &&f2fs_lfs_mode (sbi); - -trace_f2fs_direct_IO_enter (inode, offset, count, rw); - -if (rw ==WRITE && whint_mode ==WHINT_MODE_OFF ) - iocb->ki_hint =WRITE_LIFE_NOT_SET ; - -if (iocb->ki_flags &IOCB_NOWAIT ) { -if (!down_read_trylock (&fi->i_gc_rwsem[rw])) { - iocb->ki_hint = hint; - err = -EAGAIN ; - goto out; - } -if (do_opu && !down_read_trylock (&fi->i_gc_rwsem[READ ])) { -up_read (&fi->i_gc_rwsem[rw]); - iocb->ki_hint = hint; - err = -EAGAIN ; - goto out; - } - }else { -down_read (&fi->i_gc_rwsem[rw]); -if (do_opu) -down_read (&fi->i_gc_rwsem[READ ]); - } - - err =__blockdev_direct_IO (iocb, inode, inode->i_sb->s_bdev, - iter, rw ==WRITE ? get_data_block_dio_write : - get_data_block_dio,NULL , f2fs_dio_submit_bio, - rw ==WRITE ?DIO_LOCKING |DIO_SKIP_HOLES : -DIO_SKIP_HOLES ); - -if (do_opu) -up_read (&fi->i_gc_rwsem[READ ]); - -up_read (&fi->i_gc_rwsem[rw]); - -if (rw ==WRITE ) { -if (whint_mode ==WHINT_MODE_OFF ) - iocb->ki_hint = hint; -if (err >0 ) { -f2fs_update_iostat (F2FS_I_SB (inode),APP_DIRECT_IO , - err); -if (!do_opu) -set_inode_flag (inode,FI_UPDATE_WRITE ); - }else if (err == -EIOCBQUEUED ) { -f2fs_update_iostat (F2FS_I_SB (inode),APP_DIRECT_IO , - count -iov_iter_count (iter)); - }else if (err <0 ) { -f2fs_write_failed (inode, offset + count); - } - }else { -if (err >0 ) -f2fs_update_iostat (sbi,APP_DIRECT_READ_IO , err); -else if (err == -EIOCBQUEUED ) -f2fs_update_iostat (F2FS_I_SB (inode),APP_DIRECT_READ_IO , - count -iov_iter_count (iter)); - } - -out: -trace_f2fs_direct_IO_exit (inode, offset, count, rw, err); - -return err; -} -void f2fs_invalidate_page (struct page *page,unsigned int offset,unsigned int length) {
@@ -4024,7 +3826,7 @@ const struct address_space_operations f2fs_dblock_aops = { .set_page_dirty = f2fs_set_data_page_dirty, .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, - .direct_IO = f2fs_direct_IO, + .direct_IO = noop_direct_IO, .bmap = f2fs_bmap, .swap_activate = f2fs_swap_activate, .swap_deactivate = f2fs_swap_deactivate,
fs/f2fs/f2fs.h +6 -15
@@ -1755,13 +1755,6 @@ struct f2fs_sb_info {#endif }; -struct f2fs_private_dio { -struct inode *inode; -void *orig_private; -bio_end_io_t *orig_end_io; -bool write; -}; -#ifdef CONFIG_F2FS_FAULT_INJECTION #define f2fs_show_injection_info (sbi, type) \ printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", \
@@ -3243,15 +3236,12 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,spin_lock (&sbi->iostat_lock); sbi->rw_iostat[type] += io_bytes; -if (type ==APP_WRITE_IO || type ==APP_DIRECT_IO ) - sbi->rw_iostat[APP_BUFFERED_IO ] = - sbi->rw_iostat[APP_WRITE_IO ] - - sbi->rw_iostat[APP_DIRECT_IO ]; +if (type ==APP_BUFFERED_IO || type ==APP_DIRECT_IO ) + sbi->rw_iostat[APP_WRITE_IO ] += io_bytes; + +if (type ==APP_BUFFERED_READ_IO || type ==APP_DIRECT_READ_IO ) + sbi->rw_iostat[APP_READ_IO ] += io_bytes; -if (type ==APP_READ_IO || type ==APP_DIRECT_READ_IO ) - sbi->rw_iostat[APP_BUFFERED_READ_IO ] = - sbi->rw_iostat[APP_READ_IO ] - - sbi->rw_iostat[APP_DIRECT_READ_IO ];spin_unlock (&sbi->iostat_lock);f2fs_record_iostat (sbi);
@@ -3631,6 +3621,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,struct writeback_control *wbc, enum iostat_type io_type, int compr_blocks, bool allow_balance); +void f2fs_write_failed (struct inode *inode,loff_t to);void f2fs_invalidate_page (struct page *page,unsigned int offset,unsigned int length);int f2fs_release_page (struct page *page,gfp_t wait);
fs/f2fs/file.c +302 -44
421 lines not on this page · raw message
Signature · 1 line
2.32.0