From a4c9ab1d4975746c14b34c7bb908869245a9dd4f Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Tue, 15 Jul 2025 13:21:18 -0700 Subject: [PATCH] fuse: use iomap for buffered writes Have buffered writes go through iomap. This has two advantages: * granular large folio synchronous reads * granular large folio dirty tracking If for example there is a 1 MB large folio and a write issued at pos 1 to pos 1 MB - 2, only the head and tail pages will need to be read in and marked uptodate instead of the entire folio needing to be read in. Non-relevant trailing pages are also skipped (eg if for a 1 MB large folio a write is issued at pos 1 to 4099, only the first two pages are read in and the ones after that are skipped). iomap also has granular dirty tracking. This is useful in that when it comes to writeback time, only the dirty portions of the large folio will be written instead of having to write out the entire folio. For example if there is a 1 MB large folio and only 2 bytes in it are dirty, only the page for those dirty bytes get written out. Please note that granular writeback is only done once fuse also uses iomap in writeback (separate commit). .release_folio needs to be set to iomap_release_folio so that any allocated iomap ifs structs get freed. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/20250715202122.2282532-2-joannelkoong@gmail.com Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/fuse/Kconfig | 1 + fs/fuse/file.c | 148 ++++++++++++++++++------------------------------ 2 files changed, 55 insertions(+), 94 deletions(-) diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index ca215a3cba3e3..a774166264de6 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -2,6 +2,7 @@ config FUSE_FS tristate "FUSE (Filesystem in Userspace) support" select FS_POSIX_ACL + select FS_IOMAP help With FUSE it is possible to implement a fully functional filesystem in a userspace program. diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f102afc03359b..ee6b7c7adba1b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -21,6 +21,7 @@ #include #include #include +#include static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, int opcode, @@ -788,12 +789,16 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read, } } -static int fuse_do_readfolio(struct file *file, struct folio *folio) +static int fuse_do_readfolio(struct file *file, struct folio *folio, + size_t off, size_t len) { struct inode *inode = folio->mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); - loff_t pos = folio_pos(folio); - struct fuse_folio_desc desc = { .length = folio_size(folio) }; + loff_t pos = folio_pos(folio) + off; + struct fuse_folio_desc desc = { + .offset = off, + .length = len, + }; struct fuse_io_args ia = { .ap.args.page_zeroing = true, .ap.args.out_pages = true, @@ -820,8 +825,6 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio) if (res < desc.length) fuse_short_read(inode, attr_ver, res, &ia.ap); - folio_mark_uptodate(folio); - return 0; } @@ -834,13 +837,26 @@ static int fuse_read_folio(struct file *file, struct folio *folio) if (fuse_is_bad(inode)) goto out; - err = fuse_do_readfolio(file, folio); + err = fuse_do_readfolio(file, folio, 0, folio_size(folio)); + if (!err) + folio_mark_uptodate(folio); + fuse_invalidate_atime(inode); out: folio_unlock(folio); return err; } +static int fuse_iomap_read_folio_range(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, + size_t len) +{ + struct file *file = iter->private; + size_t off = offset_in_folio(folio, pos); + + return fuse_do_readfolio(file, folio, off, len); +} + static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, int err) { @@ -1375,6 +1391,24 @@ static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive) } } +static const struct iomap_write_ops fuse_iomap_write_ops = { + .read_folio_range = fuse_iomap_read_folio_range, +}; + +static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned int flags, struct iomap *iomap, + struct iomap *srcmap) +{ + iomap->type = IOMAP_MAPPED; + iomap->length = length; + iomap->offset = offset; + return 0; +} + +static const struct iomap_ops fuse_iomap_ops = { + .iomap_begin = fuse_iomap_begin, +}; + static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; @@ -1384,6 +1418,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = mapping->host; ssize_t err, count; struct fuse_conn *fc = get_fuse_conn(inode); + bool writeback = false; if (fc->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ @@ -1392,16 +1427,11 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) return err; - if (fc->handle_killpriv_v2 && - setattr_should_drop_suidgid(idmap, - file_inode(file))) { - goto writethrough; - } - - return generic_file_write_iter(iocb, from); + if (!fc->handle_killpriv_v2 || + !setattr_should_drop_suidgid(idmap, file_inode(file))) + writeback = true; } -writethrough: inode_lock(inode); err = count = generic_write_checks(iocb, from); @@ -1420,6 +1450,15 @@ writethrough: goto out; written = direct_write_fallback(iocb, from, written, fuse_perform_write(iocb, from)); + } else if (writeback) { + /* + * Use iomap so that we can do granular uptodate reads + * and granular dirty tracking for large folios. + */ + written = iomap_file_buffered_write(iocb, from, + &fuse_iomap_ops, + &fuse_iomap_write_ops, + file); } else { written = fuse_perform_write(iocb, from); } @@ -2209,84 +2248,6 @@ out: return err; } -/* - * It's worthy to make sure that space is reserved on disk for the write, - * but how to implement it without killing performance need more thinking. - */ -static int fuse_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct folio **foliop, void **fsdata) -{ - pgoff_t index = pos >> PAGE_SHIFT; - struct fuse_conn *fc = get_fuse_conn(file_inode(file)); - struct folio *folio; - loff_t fsize; - int err = -ENOMEM; - - WARN_ON(!fc->writeback_cache); - - folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, - mapping_gfp_mask(mapping)); - if (IS_ERR(folio)) - goto error; - - if (folio_test_uptodate(folio) || len >= folio_size(folio)) - goto success; - /* - * Check if the start of this folio comes after the end of file, - * in which case the readpage can be optimized away. - */ - fsize = i_size_read(mapping->host); - if (fsize <= folio_pos(folio)) { - size_t off = offset_in_folio(folio, pos); - if (off) - folio_zero_segment(folio, 0, off); - goto success; - } - err = fuse_do_readfolio(file, folio); - if (err) - goto cleanup; -success: - *foliop = folio; - return 0; - -cleanup: - folio_unlock(folio); - folio_put(folio); -error: - return err; -} - -static int fuse_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct folio *folio, void *fsdata) -{ - struct inode *inode = folio->mapping->host; - - /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ - if (!copied) - goto unlock; - - pos += copied; - if (!folio_test_uptodate(folio)) { - /* Zero any unwritten bytes at the end of the page */ - size_t endoff = pos & ~PAGE_MASK; - if (endoff) - folio_zero_segment(folio, endoff, PAGE_SIZE); - folio_mark_uptodate(folio); - } - - if (pos > inode->i_size) - i_size_write(inode, pos); - - folio_mark_dirty(folio); - -unlock: - folio_unlock(folio); - folio_put(folio); - - return copied; -} - static int fuse_launder_folio(struct folio *folio) { int err = 0; @@ -3145,11 +3106,10 @@ static const struct address_space_operations fuse_file_aops = { .writepages = fuse_writepages, .launder_folio = fuse_launder_folio, .dirty_folio = filemap_dirty_folio, + .release_folio = iomap_release_folio, .migrate_folio = filemap_migrate_folio, .bmap = fuse_bmap, .direct_IO = fuse_direct_IO, - .write_begin = fuse_write_begin, - .write_end = fuse_write_end, }; void fuse_init_file_inode(struct inode *inode, unsigned int flags) -- 2.47.2