diff options
Diffstat (limited to 'fs/fuse/file.c')
| -rw-r--r-- | fs/fuse/file.c | 1860 |
1 files changed, 904 insertions, 956 deletions
diff --git a/fs/fuse/file.c b/fs/fuse/file.c index bc4115288eec..01bc894e9c2b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -19,7 +19,9 @@ #include <linux/uio.h> #include <linux/fs.h> #include <linux/filelock.h> -#include <linux/file.h> +#include <linux/splice.h> +#include <linux/task_io_accounting_ops.h> +#include <linux/iomap.h> static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, int opcode, @@ -50,13 +52,7 @@ static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, return fuse_simple_request(fm, &args); } -struct fuse_release_args { - struct fuse_args args; - struct fuse_release_in inarg; - struct inode *inode; -}; - -struct fuse_file *fuse_file_alloc(struct fuse_mount *fm) +struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release) { struct fuse_file *ff; @@ -65,15 +61,15 @@ struct fuse_file *fuse_file_alloc(struct fuse_mount *fm) return NULL; ff->fm = fm; - ff->release_args = kzalloc(sizeof(*ff->release_args), - GFP_KERNEL_ACCOUNT); - if (!ff->release_args) { - kfree(ff); - return NULL; + if (release) { + ff->args = kzalloc(sizeof(*ff->args), GFP_KERNEL_ACCOUNT); + if (!ff->args) { + kfree(ff); + return NULL; + } } INIT_LIST_HEAD(&ff->write_entry); - mutex_init(&ff->readdir.lock); refcount_set(&ff->count, 1); RB_CLEAR_NODE(&ff->polled_node); init_waitqueue_head(&ff->poll_wait); @@ -85,8 +81,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_mount *fm) void fuse_file_free(struct fuse_file *ff) { - kfree(ff->release_args); - mutex_destroy(&ff->readdir.lock); + kfree(ff->args); kfree(ff); } @@ -105,13 +100,18 @@ static void fuse_release_end(struct fuse_mount *fm, struct fuse_args *args, kfree(ra); } -static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir) +static void fuse_file_put(struct fuse_file *ff, bool sync) { if (refcount_dec_and_test(&ff->count)) { - struct fuse_args *args = &ff->release_args->args; + struct fuse_release_args *ra = &ff->args->release_args; + struct fuse_args *args = (ra ? &ra->args : NULL); + + if (ra && ra->inode) + fuse_file_io_release(ff, ra->inode); - if (isdir ? ff->fm->fc->no_opendir : ff->fm->fc->no_open) { - /* Do nothing when client does not implement 'open' */ + if (!args) { + /* Do nothing when server does not implement 'opendir' */ + } else if (args->opcode == FUSE_RELEASE && ff->fm->fc->no_open) { fuse_release_end(ff->fm, args, 0); } else if (sync) { fuse_simple_request(ff->fm, args); @@ -132,31 +132,45 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid, struct fuse_conn *fc = fm->fc; struct fuse_file *ff; int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN; + bool open = isdir ? !fc->no_opendir : !fc->no_open; + bool release = !isdir || open; - ff = fuse_file_alloc(fm); + /* + * ff->args->release_args still needs to be allocated (so we can hold an + * inode reference while there are pending inflight file operations when + * ->release() is called, see fuse_prepare_release()) even if + * fc->no_open is set else it becomes possible for reclaim to deadlock + * if while servicing the readahead request the server triggers reclaim + * and reclaim evicts the inode of the file being read ahead. + */ + ff = fuse_file_alloc(fm, release); if (!ff) return ERR_PTR(-ENOMEM); ff->fh = 0; /* Default for no-open */ ff->open_flags = FOPEN_KEEP_CACHE | (isdir ? FOPEN_CACHE_DIR : 0); - if (isdir ? !fc->no_opendir : !fc->no_open) { - struct fuse_open_out outarg; + if (open) { + /* Store outarg for fuse_finish_open() */ + struct fuse_open_out *outargp = &ff->args->open_outarg; int err; - err = fuse_send_open(fm, nodeid, open_flags, opcode, &outarg); + err = fuse_send_open(fm, nodeid, open_flags, opcode, outargp); if (!err) { - ff->fh = outarg.fh; - ff->open_flags = outarg.open_flags; - + ff->fh = outargp->fh; + ff->open_flags = outargp->open_flags; } else if (err != -ENOSYS) { fuse_file_free(ff); return ERR_PTR(err); } else { - if (isdir) + if (isdir) { + /* No release needed */ + kfree(ff->args); + ff->args = NULL; fc->no_opendir = 1; - else + } else { fc->no_open = 1; + } } } @@ -195,40 +209,50 @@ static void fuse_link_write_file(struct file *file) spin_unlock(&fi->lock); } -void fuse_finish_open(struct inode *inode, struct file *file) +int fuse_finish_open(struct inode *inode, struct file *file) { struct fuse_file *ff = file->private_data; struct fuse_conn *fc = get_fuse_conn(inode); + int err; + + err = fuse_file_io_open(file, inode); + if (err) + return err; if (ff->open_flags & FOPEN_STREAM) stream_open(inode, file); else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); - if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { - struct fuse_inode *fi = get_fuse_inode(inode); - - spin_lock(&fi->lock); - fi->attr_version = atomic64_inc_return(&fc->attr_version); - i_size_write(inode, 0); - spin_unlock(&fi->lock); - file_update_time(file); - fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); - } if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); + + return 0; } -int fuse_open_common(struct inode *inode, struct file *file, bool isdir) +static void fuse_truncate_update_attr(struct inode *inode, struct file *file) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + + spin_lock(&fi->lock); + fi->attr_version = atomic64_inc_return(&fc->attr_version); + i_size_write(inode, 0); + spin_unlock(&fi->lock); + file_update_time(file); + fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); +} + +static int fuse_open(struct inode *inode, struct file *file) { struct fuse_mount *fm = get_fuse_mount(inode); + struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = fm->fc; + struct fuse_file *ff; int err; - bool is_wb_truncate = (file->f_flags & O_TRUNC) && - fc->atomic_o_trunc && - fc->writeback_cache; - bool dax_truncate = (file->f_flags & O_TRUNC) && - fc->atomic_o_trunc && FUSE_IS_DAX(inode); + bool is_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc; + bool is_wb_truncate = is_truncate && fc->writeback_cache; + bool dax_truncate = is_truncate && FUSE_IS_DAX(inode); if (fuse_is_bad(inode)) return -EIO; @@ -242,7 +266,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (dax_truncate) { filemap_invalidate_lock(inode->i_mapping); - err = fuse_dax_break_layouts(inode, 0, 0); + err = fuse_dax_break_layouts(inode, 0, -1); if (err) goto out_inode_unlock; } @@ -250,16 +274,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (is_wb_truncate || dax_truncate) fuse_set_nowrite(inode); - err = fuse_do_open(fm, get_node_id(inode), file, isdir); - if (!err) - fuse_finish_open(inode, file); + err = fuse_do_open(fm, get_node_id(inode), file, false); + if (!err) { + ff = file->private_data; + err = fuse_finish_open(inode, file); + if (err) + fuse_sync_release(fi, ff, file->f_flags); + else if (is_truncate) + fuse_truncate_update_attr(inode, file); + } if (is_wb_truncate || dax_truncate) fuse_release_nowrite(inode); if (!err) { - struct fuse_file *ff = file->private_data; - - if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) + if (is_truncate) truncate_pagecache(inode, 0); else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); @@ -274,10 +302,13 @@ out_inode_unlock: } static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff, - unsigned int flags, int opcode) + unsigned int flags, int opcode, bool sync) { struct fuse_conn *fc = ff->fm->fc; - struct fuse_release_args *ra = ff->release_args; + struct fuse_release_args *ra = &ff->args->release_args; + + if (fuse_file_passthrough(ff)) + fuse_passthrough_release(ff, fuse_inode_backing(fi)); /* Inode is NULL on error path of fuse_create_open() */ if (likely(fi)) { @@ -292,6 +323,11 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff, wake_up_interruptible_all(&ff->poll_wait); + if (!ra) + return; + + /* ff->args was used for open outarg */ + memset(ff->args, 0, sizeof(*ff->args)); ra->inarg.fh = ff->fh; ra->inarg.flags = flags; ra->args.in_numargs = 1; @@ -301,23 +337,28 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff, ra->args.nodeid = ff->nodeid; ra->args.force = true; ra->args.nocreds = true; + + /* + * Hold inode until release is finished. + * From fuse_sync_release() the refcount is 1 and everything's + * synchronous, so we are fine with not doing igrab() here. + */ + ra->inode = sync ? NULL : igrab(&fi->inode); } void fuse_file_release(struct inode *inode, struct fuse_file *ff, unsigned int open_flags, fl_owner_t id, bool isdir) { struct fuse_inode *fi = get_fuse_inode(inode); - struct fuse_release_args *ra = ff->release_args; + struct fuse_release_args *ra = &ff->args->release_args; int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE; - fuse_prepare_release(fi, ff, open_flags, opcode); + fuse_prepare_release(fi, ff, open_flags, opcode, false); - if (ff->flock) { + if (ra && ff->flock) { ra->inarg.release_flags |= FUSE_RELEASE_FLOCK_UNLOCK; ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc, id); } - /* Hold inode until release is finished */ - ra->inode = igrab(inode); /* * Normally this will send the RELEASE request, however if @@ -327,8 +368,14 @@ void fuse_file_release(struct inode *inode, struct fuse_file *ff, * Make the release synchronous if this is a fuseblk mount, * synchronous RELEASE is allowed (and desirable) in this case * because the server can be trusted not to screw up. + * + * Always use the asynchronous file put because the current thread + * might be the fuse server. This can happen if a process starts some + * aio and closes the fd before the aio completes. Since aio takes its + * own ref to the file, the IO completion has to drop the ref, which is + * how the fuse server can end up closing its clients' files. */ - fuse_file_put(ff, ff->fm->fc->destroy, isdir); + fuse_file_put(ff, false); } void fuse_release_common(struct file *file, bool isdir) @@ -337,11 +384,6 @@ void fuse_release_common(struct file *file, bool isdir) (fl_owner_t) file, isdir); } -static int fuse_open(struct inode *inode, struct file *file) -{ - return fuse_open_common(inode, file, false); -} - static int fuse_release(struct inode *inode, struct file *file) { struct fuse_conn *fc = get_fuse_conn(inode); @@ -363,12 +405,8 @@ void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff, unsigned int flags) { WARN_ON(refcount_read(&ff->count) > 1); - fuse_prepare_release(fi, ff, flags, FUSE_RELEASE); - /* - * iput(NULL) is a no-op and since the refcount is 1 and everything's - * synchronous, we are fine with not doing igrab() here" - */ - fuse_file_put(ff, true, false); + fuse_prepare_release(fi, ff, flags, FUSE_RELEASE, true); + fuse_file_put(ff, true); } EXPORT_SYMBOL_GPL(fuse_sync_release); @@ -396,74 +434,11 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id) struct fuse_writepage_args { struct fuse_io_args ia; - struct rb_node writepages_entry; struct list_head queue_entry; - struct fuse_writepage_args *next; struct inode *inode; struct fuse_sync_bucket *bucket; }; -static struct fuse_writepage_args *fuse_find_writeback(struct fuse_inode *fi, - pgoff_t idx_from, pgoff_t idx_to) -{ - struct rb_node *n; - - n = fi->writepages.rb_node; - - while (n) { - struct fuse_writepage_args *wpa; - pgoff_t curr_index; - - wpa = rb_entry(n, struct fuse_writepage_args, writepages_entry); - WARN_ON(get_fuse_inode(wpa->inode) != fi); - curr_index = wpa->ia.write.in.offset >> PAGE_SHIFT; - if (idx_from >= curr_index + wpa->ia.ap.num_pages) - n = n->rb_right; - else if (idx_to < curr_index) - n = n->rb_left; - else - return wpa; - } - return NULL; -} - -/* - * Check if any page in a range is under writeback - * - * This is currently done by walking the list of writepage requests - * for the inode, which can be pretty inefficient. - */ -static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from, - pgoff_t idx_to) -{ - struct fuse_inode *fi = get_fuse_inode(inode); - bool found; - - spin_lock(&fi->lock); - found = fuse_find_writeback(fi, idx_from, idx_to); - spin_unlock(&fi->lock); - - return found; -} - -static inline bool fuse_page_is_writeback(struct inode *inode, pgoff_t index) -{ - return fuse_range_is_writeback(inode, index, index); -} - -/* - * Wait for page writeback to be completed. - * - * Since fuse doesn't rely on the VM writeback tracking, this has to - * use some other means. - */ -static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index) -{ - struct fuse_inode *fi = get_fuse_inode(inode); - - wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index)); -} - /* * Wait for all pending writepages on the inode to finish. * @@ -479,36 +454,44 @@ static void fuse_sync_writes(struct inode *inode) fuse_release_nowrite(inode); } -struct fuse_flush_args { - struct fuse_args args; - struct fuse_flush_in inarg; - struct work_struct work; - struct file *file; -}; - -static int fuse_do_flush(struct fuse_flush_args *fa) +static int fuse_flush(struct file *file, fl_owner_t id) { - int err; - struct inode *inode = file_inode(fa->file); + struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); + struct fuse_file *ff = file->private_data; + struct fuse_flush_in inarg; + FUSE_ARGS(args); + int err; + + if (fuse_is_bad(inode)) + return -EIO; + + if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache) + return 0; err = write_inode_now(inode, 1); if (err) - goto out; - - inode_lock(inode); - fuse_sync_writes(inode); - inode_unlock(inode); + return err; - err = filemap_check_errors(fa->file->f_mapping); + err = filemap_check_errors(file->f_mapping); if (err) - goto out; + return err; err = 0; if (fm->fc->no_flush) goto inval_attr_out; - err = fuse_simple_request(fm, &fa->args); + memset(&inarg, 0, sizeof(inarg)); + inarg.fh = ff->fh; + inarg.lock_owner = fuse_lock_owner_id(fm->fc, id); + args.opcode = FUSE_FLUSH; + args.nodeid = get_node_id(inode); + args.in_numargs = 1; + args.in_args[0].size = sizeof(inarg); + args.in_args[0].value = &inarg; + args.force = true; + + err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_flush = 1; err = 0; @@ -521,57 +504,9 @@ inval_attr_out: */ if (!err && fm->fc->writeback_cache) fuse_invalidate_attr_mask(inode, STATX_BLOCKS); - -out: - fput(fa->file); - kfree(fa); return err; } -static void fuse_flush_async(struct work_struct *work) -{ - struct fuse_flush_args *fa = container_of(work, typeof(*fa), work); - - fuse_do_flush(fa); -} - -static int fuse_flush(struct file *file, fl_owner_t id) -{ - struct fuse_flush_args *fa; - struct inode *inode = file_inode(file); - struct fuse_mount *fm = get_fuse_mount(inode); - struct fuse_file *ff = file->private_data; - - if (fuse_is_bad(inode)) - return -EIO; - - if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache) - return 0; - - fa = kzalloc(sizeof(*fa), GFP_KERNEL); - if (!fa) - return -ENOMEM; - - fa->inarg.fh = ff->fh; - fa->inarg.lock_owner = fuse_lock_owner_id(fm->fc, id); - fa->args.opcode = FUSE_FLUSH; - fa->args.nodeid = get_node_id(inode); - fa->args.in_numargs = 1; - fa->args.in_args[0].size = sizeof(fa->inarg); - fa->args.in_args[0].value = &fa->inarg; - fa->args.force = true; - fa->file = get_file(file); - - /* Don't wait if the task is exiting */ - if (current->flags & PF_EXITING) { - INIT_WORK(&fa->work, fuse_flush_async); - schedule_work(&fa->work); - return 0; - } - - return fuse_do_flush(fa); -} - int fuse_fsync_common(struct file *file, loff_t start, loff_t end, int datasync, int opcode) { @@ -662,16 +597,20 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos, args->out_args[0].size = count; } -static void fuse_release_user_pages(struct fuse_args_pages *ap, +static void fuse_release_user_pages(struct fuse_args_pages *ap, ssize_t nres, bool should_dirty) { unsigned int i; - for (i = 0; i < ap->num_pages; i++) { + for (i = 0; i < ap->num_folios; i++) { if (should_dirty) - set_page_dirty_lock(ap->pages[i]); - put_page(ap->pages[i]); + folio_mark_dirty_lock(ap->folios[i]); + if (ap->args.is_pinned) + unpin_folio(ap->folios[i]); } + + if (nres > 0 && ap->args.invalidate_vmap) + invalidate_kernel_vmap_range(ap->args.vmap_base, nres); } static void fuse_io_release(struct kref *kref) @@ -741,16 +680,16 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) } static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io, - unsigned int npages) + unsigned int nfolios) { struct fuse_io_args *ia; ia = kzalloc(sizeof(*ia), GFP_KERNEL); if (ia) { ia->io = io; - ia->ap.pages = fuse_pages_alloc(npages, GFP_KERNEL, - &ia->ap.descs); - if (!ia->ap.pages) { + ia->ap.folios = fuse_folios_alloc(nfolios, GFP_KERNEL, + &ia->ap.descs); + if (!ia->ap.folios) { kfree(ia); ia = NULL; } @@ -760,7 +699,7 @@ static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io, static void fuse_io_free(struct fuse_io_args *ia) { - kfree(ia->ap.pages); + kfree(ia->ap.folios); kfree(ia); } @@ -770,25 +709,29 @@ static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args, struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args); struct fuse_io_priv *io = ia->io; ssize_t pos = -1; - - fuse_release_user_pages(&ia->ap, io->should_dirty); + size_t nres; if (err) { /* Nothing */ } else if (io->write) { if (ia->write.out.size > ia->write.in.size) { err = -EIO; - } else if (ia->write.in.size != ia->write.out.size) { - pos = ia->write.in.offset - io->offset + - ia->write.out.size; + } else { + nres = ia->write.out.size; + if (ia->write.in.size != ia->write.out.size) + pos = ia->write.in.offset - io->offset + + ia->write.out.size; } } else { u32 outsize = args->out_args[0].size; + nres = outsize; if (ia->read.in.size != outsize) pos = ia->read.in.offset - io->offset + outsize; } + fuse_release_user_pages(&ia->ap, err ?: nres, io->should_dirty); + fuse_aio_complete(io, err, pos); fuse_io_free(ia); } @@ -859,34 +802,31 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read, * reached the client fs yet. So the hole is not present there. */ if (!fc->writeback_cache) { - loff_t pos = page_offset(ap->pages[0]) + num_read; + loff_t pos = folio_pos(ap->folios[0]) + num_read; fuse_read_update_size(inode, pos, attr_ver); } } -static int fuse_do_readpage(struct file *file, struct page *page) +static int fuse_do_readfolio(struct file *file, struct folio *folio, + size_t off, size_t len) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); - loff_t pos = page_offset(page); - struct fuse_page_desc desc = { .length = PAGE_SIZE }; + 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, - .ap.num_pages = 1, - .ap.pages = &page, + .ap.num_folios = 1, + .ap.folios = &folio, .ap.descs = &desc, }; ssize_t res; u64 attr_ver; - /* - * Page writeback can extend beyond the lifetime of the - * page-cache page, so make sure we read a properly synced - * page. - */ - fuse_wait_on_page_writeback(inode, page->index); - attr_ver = fuse_get_attr_version(fm->fc); /* Don't overflow end offset */ @@ -903,26 +843,155 @@ static int fuse_do_readpage(struct file *file, struct page *page) if (res < desc.length) fuse_short_read(inode, attr_ver, res, &ia.ap); - SetPageUptodate(page); + return 0; +} + +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, +}; + +struct fuse_fill_read_data { + struct file *file; + + /* Fields below are used if sending the read request asynchronously */ + struct fuse_conn *fc; + struct fuse_io_args *ia; + unsigned int nr_bytes; +}; + +/* forward declarations */ +static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos, + unsigned len, struct fuse_args_pages *ap, + unsigned cur_bytes, bool write); +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file, + unsigned int count, bool async); + +static int fuse_handle_readahead(struct folio *folio, + struct readahead_control *rac, + struct fuse_fill_read_data *data, loff_t pos, + size_t len) +{ + struct fuse_io_args *ia = data->ia; + size_t off = offset_in_folio(folio, pos); + struct fuse_conn *fc = data->fc; + struct fuse_args_pages *ap; + unsigned int nr_pages; + + if (ia && fuse_folios_need_send(fc, pos, len, &ia->ap, data->nr_bytes, + false)) { + fuse_send_readpages(ia, data->file, data->nr_bytes, + fc->async_read); + data->nr_bytes = 0; + data->ia = NULL; + ia = NULL; + } + if (!ia) { + if (fc->num_background >= fc->congestion_threshold && + rac->ra->async_size >= readahead_count(rac)) + /* + * Congested and only async pages left, so skip the + * rest. + */ + return -EAGAIN; + + nr_pages = min(fc->max_pages, readahead_count(rac)); + data->ia = fuse_io_alloc(NULL, nr_pages); + if (!data->ia) + return -ENOMEM; + ia = data->ia; + } + folio_get(folio); + ap = &ia->ap; + ap->folios[ap->num_folios] = folio; + ap->descs[ap->num_folios].offset = off; + ap->descs[ap->num_folios].length = len; + data->nr_bytes += len; + ap->num_folios++; return 0; } +static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, + size_t len) +{ + struct fuse_fill_read_data *data = ctx->read_ctx; + struct folio *folio = ctx->cur_folio; + loff_t pos = iter->pos; + size_t off = offset_in_folio(folio, pos); + struct file *file = data->file; + int ret; + + if (ctx->rac) { + ret = fuse_handle_readahead(folio, ctx->rac, data, pos, len); + } else { + /* + * for non-readahead read requests, do reads synchronously + * since it's not guaranteed that the server can handle + * out-of-order reads + */ + ret = fuse_do_readfolio(file, folio, off, len); + if (!ret) + iomap_finish_folio_read(folio, off, len, ret); + } + return ret; +} + +static void fuse_iomap_read_submit(struct iomap_read_folio_ctx *ctx) +{ + struct fuse_fill_read_data *data = ctx->read_ctx; + + if (data->ia) + fuse_send_readpages(data->ia, data->file, data->nr_bytes, + data->fc->async_read); +} + +static const struct iomap_read_ops fuse_iomap_read_ops = { + .read_folio_range = fuse_iomap_read_folio_range_async, + .submit_read = fuse_iomap_read_submit, +}; + static int fuse_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; - struct inode *inode = page->mapping->host; - int err; + struct inode *inode = folio->mapping->host; + struct fuse_fill_read_data data = { + .file = file, + }; + struct iomap_read_folio_ctx ctx = { + .cur_folio = folio, + .ops = &fuse_iomap_read_ops, + .read_ctx = &data, - err = -EIO; - if (fuse_is_bad(inode)) - goto out; + }; - err = fuse_do_readpage(file, page); + if (fuse_is_bad(inode)) { + folio_unlock(folio); + return -EIO; + } + + iomap_read_folio(&fuse_iomap_ops, &ctx); fuse_invalidate_atime(inode); - out: - unlock_page(page); - return err; + return 0; +} + +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, @@ -933,46 +1002,39 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, struct fuse_args_pages *ap = &ia->ap; size_t count = ia->read.in.size; size_t num_read = args->out_args[0].size; - struct address_space *mapping = NULL; - - for (i = 0; mapping == NULL && i < ap->num_pages; i++) - mapping = ap->pages[i]->mapping; - - if (mapping) { - struct inode *inode = mapping->host; + struct address_space *mapping; + struct inode *inode; - /* - * Short read means EOF. If file size is larger, truncate it - */ - if (!err && num_read < count) - fuse_short_read(inode, ia->read.attr_ver, num_read, ap); + WARN_ON_ONCE(!ap->num_folios); + mapping = ap->folios[0]->mapping; + inode = mapping->host; - fuse_invalidate_atime(inode); - } + /* + * Short read means EOF. If file size is larger, truncate it + */ + if (!err && num_read < count) + fuse_short_read(inode, ia->read.attr_ver, num_read, ap); - for (i = 0; i < ap->num_pages; i++) { - struct page *page = ap->pages[i]; + fuse_invalidate_atime(inode); - if (!err) - SetPageUptodate(page); - else - SetPageError(page); - unlock_page(page); - put_page(page); + for (i = 0; i < ap->num_folios; i++) { + iomap_finish_folio_read(ap->folios[i], ap->descs[i].offset, + ap->descs[i].length, err); + folio_put(ap->folios[i]); } if (ia->ff) - fuse_file_put(ia->ff, false, false); + fuse_file_put(ia->ff, false); fuse_io_free(ia); } -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file) +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file, + unsigned int count, bool async) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_args_pages *ap = &ia->ap; - loff_t pos = page_offset(ap->pages[0]); - size_t count = ap->num_pages << PAGE_SHIFT; + loff_t pos = folio_pos(ap->folios[0]); ssize_t res; int err; @@ -983,13 +1045,13 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file) /* Don't overflow end offset */ if (pos + (count - 1) == LLONG_MAX) { count--; - ap->descs[ap->num_pages - 1].length--; + ap->descs[ap->num_folios - 1].length--; } WARN_ON((loff_t) (pos + count) < 0); fuse_read_args_fill(ia, file, pos, count, FUSE_READ); ia->read.attr_ver = fuse_get_attr_version(fm->fc); - if (fm->fc->async_read) { + if (async) { ia->ff = fuse_file_get(ff); ap->args.end = fuse_readpages_end; err = fuse_simple_background(fm, &ap->args, GFP_KERNEL); @@ -1006,44 +1068,20 @@ static void fuse_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - unsigned int i, max_pages, nr_pages = 0; + struct fuse_fill_read_data data = { + .file = rac->file, + .fc = fc, + }; + struct iomap_read_folio_ctx ctx = { + .ops = &fuse_iomap_read_ops, + .rac = rac, + .read_ctx = &data + }; if (fuse_is_bad(inode)) return; - max_pages = min_t(unsigned int, fc->max_pages, - fc->max_read / PAGE_SIZE); - - for (;;) { - struct fuse_io_args *ia; - struct fuse_args_pages *ap; - - if (fc->num_background >= fc->congestion_threshold && - rac->ra->async_size >= readahead_count(rac)) - /* - * Congested and only async pages left, so skip the - * rest. - */ - break; - - nr_pages = readahead_count(rac) - nr_pages; - if (nr_pages > max_pages) - nr_pages = max_pages; - if (nr_pages == 0) - break; - ia = fuse_io_alloc(NULL, nr_pages); - if (!ia) - return; - ap = &ia->ap; - nr_pages = __readahead_batch(rac, ap->pages, nr_pages); - for (i = 0; i < nr_pages; i++) { - fuse_wait_on_page_writeback(inode, - readahead_index(rac) + i); - ap->descs[i].length = PAGE_SIZE; - } - ap->num_pages = nr_pages; - fuse_send_readpages(ia, rac->file); - } + iomap_readahead(&fuse_iomap_ops, &ctx); } static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -1159,8 +1197,8 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia, bool short_write; int err; - for (i = 0; i < ap->num_pages; i++) - fuse_wait_on_page_writeback(inode, ap->pages[i]->index); + for (i = 0; i < ap->num_folios; i++) + folio_wait_writeback(ap->folios[i]); fuse_write_args_fill(ia, ff, pos, count); ia->write.in.flags = fuse_write_flags(iocb); @@ -1174,24 +1212,24 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia, short_write = ia->write.out.size < count; offset = ap->descs[0].offset; count = ia->write.out.size; - for (i = 0; i < ap->num_pages; i++) { - struct page *page = ap->pages[i]; + for (i = 0; i < ap->num_folios; i++) { + struct folio *folio = ap->folios[i]; if (err) { - ClearPageUptodate(page); + folio_clear_uptodate(folio); } else { - if (count >= PAGE_SIZE - offset) - count -= PAGE_SIZE - offset; + if (count >= folio_size(folio) - offset) + count -= folio_size(folio) - offset; else { if (short_write) - ClearPageUptodate(page); + folio_clear_uptodate(folio); count = 0; } offset = 0; } - if (ia->write.page_locked && (i == ap->num_pages - 1)) - unlock_page(page); - put_page(page); + if (ia->write.folio_locked && (i == ap->num_folios - 1)) + folio_unlock(folio); + folio_put(folio); } return err; @@ -1200,73 +1238,84 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia, static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia, struct address_space *mapping, struct iov_iter *ii, loff_t pos, - unsigned int max_pages) + unsigned int max_folios) { struct fuse_args_pages *ap = &ia->ap; struct fuse_conn *fc = get_fuse_conn(mapping->host); unsigned offset = pos & (PAGE_SIZE - 1); size_t count = 0; - int err; + unsigned int num; + int err = 0; + + num = min(iov_iter_count(ii), fc->max_write); ap->args.in_pages = true; - ap->descs[0].offset = offset; - do { + while (num && ap->num_folios < max_folios) { size_t tmp; - struct page *page; + struct folio *folio; pgoff_t index = pos >> PAGE_SHIFT; - size_t bytes = min_t(size_t, PAGE_SIZE - offset, - iov_iter_count(ii)); - - bytes = min_t(size_t, bytes, fc->max_write - count); + unsigned int bytes; + unsigned int folio_offset; again: - err = -EFAULT; - if (fault_in_iov_iter_readable(ii, bytes)) - break; - - err = -ENOMEM; - page = grab_cache_page_write_begin(mapping, index); - if (!page) + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); break; + } if (mapping_writably_mapped(mapping)) - flush_dcache_page(page); + flush_dcache_folio(folio); - tmp = copy_page_from_iter_atomic(page, offset, bytes, ii); - flush_dcache_page(page); + folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset; + bytes = min(folio_size(folio) - folio_offset, num); + + tmp = copy_folio_from_iter_atomic(folio, folio_offset, bytes, ii); + flush_dcache_folio(folio); if (!tmp) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); + + /* + * Ensure forward progress by faulting in + * while not holding the folio lock: + */ + if (fault_in_iov_iter_readable(ii, bytes)) { + err = -EFAULT; + break; + } + goto again; } - err = 0; - ap->pages[ap->num_pages] = page; - ap->descs[ap->num_pages].length = tmp; - ap->num_pages++; + ap->folios[ap->num_folios] = folio; + ap->descs[ap->num_folios].offset = folio_offset; + ap->descs[ap->num_folios].length = tmp; + ap->num_folios++; count += tmp; pos += tmp; + num -= tmp; offset += tmp; - if (offset == PAGE_SIZE) + if (offset == folio_size(folio)) offset = 0; - /* If we copied full page, mark it uptodate */ - if (tmp == PAGE_SIZE) - SetPageUptodate(page); + /* If we copied full folio, mark it uptodate */ + if (tmp == folio_size(folio)) + folio_mark_uptodate(folio); - if (PageUptodate(page)) { - unlock_page(page); + if (folio_test_uptodate(folio)) { + folio_unlock(folio); } else { - ia->write.page_locked = true; + ia->write.folio_locked = true; break; } - if (!fc->big_writes) + if (!fc->big_writes || offset != 0) break; - } while (iov_iter_count(ii) && count < fc->max_write && - ap->num_pages < max_pages && offset == 0); + } return count > 0 ? count : err; } @@ -1300,8 +1349,8 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii) unsigned int nr_pages = fuse_wr_pages(pos, iov_iter_count(ii), fc->max_pages); - ap->pages = fuse_pages_alloc(nr_pages, GFP_KERNEL, &ap->descs); - if (!ap->pages) { + ap->folios = fuse_folios_alloc(nr_pages, GFP_KERNEL, &ap->descs); + if (!ap->folios) { err = -ENOMEM; break; } @@ -1323,7 +1372,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii) err = -EIO; } } - kfree(ap->pages); + kfree(ap->folios); } while (!err && iov_iter_count(ii)); fuse_write_update_attr(inode, pos, res); @@ -1335,14 +1384,100 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii) return res; } +static bool fuse_io_past_eof(struct kiocb *iocb, struct iov_iter *iter) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode); +} + +/* + * @return true if an exclusive lock for direct IO writes is needed + */ +static bool fuse_dio_wr_exclusive_lock(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct fuse_file *ff = file->private_data; + struct inode *inode = file_inode(iocb->ki_filp); + struct fuse_inode *fi = get_fuse_inode(inode); + + /* Server side has to advise that it supports parallel dio writes. */ + if (!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES)) + return true; + + /* + * Append will need to know the eventual EOF - always needs an + * exclusive lock. + */ + if (iocb->ki_flags & IOCB_APPEND) + return true; + + /* shared locks are not allowed with parallel page cache IO */ + if (test_bit(FUSE_I_CACHE_IO_MODE, &fi->state)) + return true; + + /* Parallel dio beyond EOF is not supported, at least for now. */ + if (fuse_io_past_eof(iocb, from)) + return true; + + return false; +} + +static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, + bool *exclusive) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct fuse_inode *fi = get_fuse_inode(inode); + + *exclusive = fuse_dio_wr_exclusive_lock(iocb, from); + if (*exclusive) { + inode_lock(inode); + } else { + inode_lock_shared(inode); + /* + * New parallal dio allowed only if inode is not in caching + * mode and denies new opens in caching mode. This check + * should be performed only after taking shared inode lock. + * Previous past eof check was without inode lock and might + * have raced, so check it again. + */ + if (fuse_io_past_eof(iocb, from) || + fuse_inode_uncached_io_start(fi, NULL) != 0) { + inode_unlock_shared(inode); + inode_lock(inode); + *exclusive = true; + } + } +} + +static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct fuse_inode *fi = get_fuse_inode(inode); + + if (exclusive) { + inode_unlock(inode); + } else { + /* Allow opens in caching mode after last parallel dio end */ + fuse_inode_uncached_io_end(fi); + inode_unlock_shared(inode); + } +} + +static const struct iomap_write_ops fuse_iomap_write_ops = { + .read_folio_range = fuse_iomap_read_folio_range, +}; + static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; + struct mnt_idmap *idmap = file_mnt_idmap(file); struct address_space *mapping = file->f_mapping; ssize_t written = 0; struct inode *inode = mapping->host; - ssize_t err; + 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) */ @@ -1351,27 +1486,20 @@ 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(&nop_mnt_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 = generic_write_checks(iocb, from); + err = count = generic_write_checks(iocb, from); if (err <= 0) goto out; - err = file_remove_privs(file); - if (err) - goto out; + task_io_account_write(count); - err = file_update_time(file); + err = kiocb_modified(iocb); if (err) goto out; @@ -1381,6 +1509,15 @@ 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); } @@ -1405,55 +1542,97 @@ static inline size_t fuse_get_frag_size(const struct iov_iter *ii, static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, size_t *nbytesp, int write, - unsigned int max_pages) + unsigned int max_pages, + bool use_pages_for_kvec_io) { + bool flush_or_invalidate = false; + unsigned int nr_pages = 0; size_t nbytes = 0; /* # bytes already packed in req */ ssize_t ret = 0; - /* Special case for kernel I/O: can copy directly into the buffer */ + /* Special case for kernel I/O: can copy directly into the buffer. + * However if the implementation of fuse_conn requires pages instead of + * pointer (e.g., virtio-fs), use iov_iter_extract_pages() instead. + */ if (iov_iter_is_kvec(ii)) { - unsigned long user_addr = fuse_get_user_addr(ii); - size_t frag_size = fuse_get_frag_size(ii, *nbytesp); + void *user_addr = (void *)fuse_get_user_addr(ii); - if (write) - ap->args.in_args[1].value = (void *) user_addr; - else - ap->args.out_args[0].value = (void *) user_addr; + if (!use_pages_for_kvec_io) { + size_t frag_size = fuse_get_frag_size(ii, *nbytesp); - iov_iter_advance(ii, frag_size); - *nbytesp = frag_size; - return 0; + if (write) + ap->args.in_args[1].value = user_addr; + else + ap->args.out_args[0].value = user_addr; + + iov_iter_advance(ii, frag_size); + *nbytesp = frag_size; + return 0; + } + + if (is_vmalloc_addr(user_addr)) { + ap->args.vmap_base = user_addr; + flush_or_invalidate = true; + } + } + + /* + * Until there is support for iov_iter_extract_folios(), we have to + * manually extract pages using iov_iter_extract_pages() and then + * copy that to a folios array. + */ + struct page **pages = kzalloc(max_pages * sizeof(struct page *), + GFP_KERNEL); + if (!pages) { + ret = -ENOMEM; + goto out; } - while (nbytes < *nbytesp && ap->num_pages < max_pages) { - unsigned npages; + while (nbytes < *nbytesp && nr_pages < max_pages) { + unsigned nfolios, i; size_t start; - ret = iov_iter_get_pages2(ii, &ap->pages[ap->num_pages], - *nbytesp - nbytes, - max_pages - ap->num_pages, - &start); + + ret = iov_iter_extract_pages(ii, &pages, + *nbytesp - nbytes, + max_pages - nr_pages, + 0, &start); if (ret < 0) break; nbytes += ret; - ret += start; - npages = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); + + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); - ap->descs[ap->num_pages].offset = start; - fuse_page_descs_length_init(ap->descs, ap->num_pages, npages); + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_pages += npages; - ap->descs[ap->num_pages - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); + nr_pages += nfolios; } + kfree(pages); + + if (write && flush_or_invalidate) + flush_kernel_vmap_range(ap->args.vmap_base, nbytes); + ap->args.invalidate_vmap = !write && flush_or_invalidate; + ap->args.is_pinned = iov_iter_extract_will_pin(ii); ap->args.user_pages = true; if (write) ap->args.in_pages = true; else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; @@ -1465,7 +1644,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, int write = flags & FUSE_DIO_WRITE; int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fm->fc; size_t nmax = write ? fc->max_write : fc->max_read; @@ -1477,13 +1657,21 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, int err = 0; struct fuse_io_args *ia; unsigned int max_pages; + bool fopen_direct_io = ff->open_flags & FOPEN_DIRECT_IO; max_pages = iov_iter_npages(iter, fc->max_pages); ia = fuse_io_alloc(io, max_pages); if (!ia) return -ENOMEM; - if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) { + if (fopen_direct_io) { + res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); + if (res) { + fuse_io_free(ia); + return res; + } + } + if (!cuse && filemap_range_has_writeback(mapping, pos, (pos + count - 1))) { if (!write) inode_lock(inode); fuse_sync_writes(inode); @@ -1491,6 +1679,14 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, inode_unlock(inode); } + if (fopen_direct_io && write) { + res = invalidate_inode_pages2_range(mapping, idx_from, idx_to); + if (res) { + fuse_io_free(ia); + return res; + } + } + io->should_dirty = !write && user_backed_iter(iter); while (count) { ssize_t nres; @@ -1498,7 +1694,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, size_t nbytes = min(count, nmax); err = fuse_get_user_pages(&ia->ap, iter, &nbytes, write, - max_pages); + max_pages, fc->use_pages_for_kvec_io); if (err && !nbytes) break; @@ -1512,7 +1708,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, } if (!io->async || nres < 0) { - fuse_release_user_pages(&ia->ap, io->should_dirty); + fuse_release_user_pages(&ia->ap, nres, io->should_dirty); fuse_io_free(ia); } ia = NULL; @@ -1542,6 +1738,15 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (res > 0) *ppos = pos; + if (res > 0 && write && fopen_direct_io) { + /* + * As in generic_file_direct_write(), invalidate after the + * write, to invalidate read-ahead cache that may have competed + * with the write. + */ + invalidate_inode_pages2_range(mapping, idx_from, idx_to); + } + return res > 0 ? res : err; } EXPORT_SYMBOL_GPL(fuse_direct_io); @@ -1566,7 +1771,7 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) { ssize_t res; - if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) { + if (!is_sync_kiocb(iocb)) { res = fuse_direct_IO(iocb, to); } else { struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); @@ -1577,61 +1782,27 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) return res; } -static bool fuse_direct_write_extending_i_size(struct kiocb *iocb, - struct iov_iter *iter) -{ - struct inode *inode = file_inode(iocb->ki_filp); - - return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode); -} - static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); - struct file *file = iocb->ki_filp; - struct fuse_file *ff = file->private_data; - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); ssize_t res; - bool exclusive_lock = - !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) || - iocb->ki_flags & IOCB_APPEND || - fuse_direct_write_extending_i_size(iocb, from); - - /* - * Take exclusive lock if - * - Parallel direct writes are disabled - a user space decision - * - Parallel direct writes are enabled and i_size is being extended. - * This might not be needed at all, but needs further investigation. - */ - if (exclusive_lock) - inode_lock(inode); - else { - inode_lock_shared(inode); - - /* A race with truncate might have come up as the decision for - * the lock type was done without holding the lock, check again. - */ - if (fuse_direct_write_extending_i_size(iocb, from)) { - inode_unlock_shared(inode); - inode_lock(inode); - exclusive_lock = true; - } - } + bool exclusive; + fuse_dio_lock(iocb, from, &exclusive); res = generic_write_checks(iocb, from); if (res > 0) { - if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) { + task_io_account_write(res); + if (!is_sync_kiocb(iocb)) { res = fuse_direct_IO(iocb, from); } else { + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); + res = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE); fuse_write_update_attr(inode, iocb->ki_pos, res); } } - if (exclusive_lock) - inode_unlock(inode); - else - inode_unlock_shared(inode); + fuse_dio_unlock(iocb, exclusive); return res; } @@ -1648,10 +1819,13 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (FUSE_IS_DAX(inode)) return fuse_dax_read_iter(iocb, to); - if (!(ff->open_flags & FOPEN_DIRECT_IO)) - return fuse_cache_read_iter(iocb, to); - else + /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ + if (ff->open_flags & FOPEN_DIRECT_IO) return fuse_direct_read_iter(iocb, to); + else if (fuse_file_passthrough(ff)) + return fuse_passthrough_read_iter(iocb, to); + else + return fuse_cache_read_iter(iocb, to); } static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) @@ -1666,44 +1840,69 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (FUSE_IS_DAX(inode)) return fuse_dax_write_iter(iocb, from); - if (!(ff->open_flags & FOPEN_DIRECT_IO)) + /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ + if (ff->open_flags & FOPEN_DIRECT_IO) + return fuse_direct_write_iter(iocb, from); + else if (fuse_file_passthrough(ff)) + return fuse_passthrough_write_iter(iocb, from); + else return fuse_cache_write_iter(iocb, from); +} + +static ssize_t fuse_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct fuse_file *ff = in->private_data; + + /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ + if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO)) + return fuse_passthrough_splice_read(in, ppos, pipe, len, flags); else - return fuse_direct_write_iter(iocb, from); + return filemap_splice_read(in, ppos, pipe, len, flags); +} + +static ssize_t fuse_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + struct fuse_file *ff = out->private_data; + + /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ + if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO)) + return fuse_passthrough_splice_write(pipe, out, ppos, len, flags); + else + return iter_file_splice_write(pipe, out, ppos, len, flags); } static void fuse_writepage_free(struct fuse_writepage_args *wpa) { struct fuse_args_pages *ap = &wpa->ia.ap; - int i; if (wpa->bucket) fuse_sync_bucket_dec(wpa->bucket); - for (i = 0; i < ap->num_pages; i++) - __free_page(ap->pages[i]); + fuse_file_put(wpa->ia.ff, false); - if (wpa->ia.ff) - fuse_file_put(wpa->ia.ff, false, false); - - kfree(ap->pages); + kfree(ap->folios); kfree(wpa); } -static void fuse_writepage_finish(struct fuse_mount *fm, - struct fuse_writepage_args *wpa) +static void fuse_writepage_finish(struct fuse_writepage_args *wpa) { struct fuse_args_pages *ap = &wpa->ia.ap; struct inode *inode = wpa->inode; struct fuse_inode *fi = get_fuse_inode(inode); - struct backing_dev_info *bdi = inode_to_bdi(inode); int i; - for (i = 0; i < ap->num_pages; i++) { - dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP); - wb_writeout_inc(&bdi->wb); - } + for (i = 0; i < ap->num_folios; i++) + /* + * Benchmarks showed that ending writeback within the + * scope of the fi->lock alleviates xarray lock + * contention and noticeably improves performance. + */ + iomap_finish_folio_write(inode, ap->folios[i], + ap->descs[i].length); + wake_up(&fi->page_waitq); } @@ -1713,12 +1912,15 @@ static void fuse_send_writepage(struct fuse_mount *fm, __releases(fi->lock) __acquires(fi->lock) { - struct fuse_writepage_args *aux, *next; struct fuse_inode *fi = get_fuse_inode(wpa->inode); + struct fuse_args_pages *ap = &wpa->ia.ap; struct fuse_write_in *inarg = &wpa->ia.write.in; - struct fuse_args *args = &wpa->ia.ap.args; - __u64 data_size = wpa->ia.ap.num_pages * PAGE_SIZE; - int err; + struct fuse_args *args = &ap->args; + __u64 data_size = 0; + int err, i; + + for (i = 0; i < ap->num_folios; i++) + data_size += ap->descs[i].length; fi->writectr++; if (inarg->offset + data_size <= size) { @@ -1749,17 +1951,8 @@ __acquires(fi->lock) out_free: fi->writectr--; - rb_erase(&wpa->writepages_entry, &fi->writepages); - fuse_writepage_finish(fm, wpa); + fuse_writepage_finish(wpa); spin_unlock(&fi->lock); - - /* After fuse_writepage_finish() aux request list is private */ - for (aux = wpa->next; aux; aux = next) { - next = aux->next; - aux->next = NULL; - fuse_writepage_free(aux); - } - fuse_writepage_free(wpa); spin_lock(&fi->lock); } @@ -1787,43 +1980,6 @@ __acquires(fi->lock) } } -static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root, - struct fuse_writepage_args *wpa) -{ - pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT; - pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1; - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - - WARN_ON(!wpa->ia.ap.num_pages); - while (*p) { - struct fuse_writepage_args *curr; - pgoff_t curr_index; - - parent = *p; - curr = rb_entry(parent, struct fuse_writepage_args, - writepages_entry); - WARN_ON(curr->inode != wpa->inode); - curr_index = curr->ia.write.in.offset >> PAGE_SHIFT; - - if (idx_from >= curr_index + curr->ia.ap.num_pages) - p = &(*p)->rb_right; - else if (idx_to < curr_index) - p = &(*p)->rb_left; - else - return curr; - } - - rb_link_node(&wpa->writepages_entry, parent, p); - rb_insert_color(&wpa->writepages_entry, root); - return NULL; -} - -static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa) -{ - WARN_ON(fuse_insert_writeback(root, wpa)); -} - static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args, int error) { @@ -1843,44 +1999,8 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args, if (!fc->writeback_cache) fuse_invalidate_attr_mask(inode, FUSE_STATX_MODIFY); spin_lock(&fi->lock); - rb_erase(&wpa->writepages_entry, &fi->writepages); - while (wpa->next) { - struct fuse_mount *fm = get_fuse_mount(inode); - struct fuse_write_in *inarg = &wpa->ia.write.in; - struct fuse_writepage_args *next = wpa->next; - - wpa->next = next->next; - next->next = NULL; - next->ia.ff = fuse_file_get(wpa->ia.ff); - tree_insert(&fi->writepages, next); - - /* - * Skip fuse_flush_writepages() to make it easy to crop requests - * based on primary request size. - * - * 1st case (trivial): there are no concurrent activities using - * fuse_set/release_nowrite. Then we're on safe side because - * fuse_flush_writepages() would call fuse_send_writepage() - * anyway. - * - * 2nd case: someone called fuse_set_nowrite and it is waiting - * now for completion of all in-flight requests. This happens - * rarely and no more than once per page, so this should be - * okay. - * - * 3rd case: someone (e.g. fuse_do_setattr()) is in the middle - * of fuse_set_nowrite..fuse_release_nowrite section. The fact - * that fuse_set_nowrite returned implies that all in-flight - * requests were completed along with all of their secondary - * requests. Further primary requests are blocked by negative - * writectr. Hence there cannot be any in-flight requests and - * no invocations of fuse_writepage_end() while we're in - * fuse_set_nowrite..fuse_release_nowrite section. - */ - fuse_send_writepage(fm, next, inarg->offset + inarg->size); - } fi->writectr--; - fuse_writepage_finish(fm, wpa); + fuse_writepage_finish(wpa); spin_unlock(&fi->lock); fuse_writepage_free(wpa); } @@ -1912,21 +2032,10 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc) struct fuse_file *ff; int err; - /* - * Inode is always written before the last reference is dropped and - * hence this should not be reached from reclaim. - * - * Writing back the inode from reclaim can deadlock if the request - * processing itself needs an allocation. Allocations triggering - * reclaim while serving a request can't be prevented, because it can - * involve any number of unrelated userspace processes. - */ - WARN_ON(wbc->for_reclaim); - ff = __fuse_write_file_get(fi); err = fuse_flush_times(inode, ff); if (ff) - fuse_file_put(ff, false, false); + fuse_file_put(ff, false); return err; } @@ -1939,9 +2048,9 @@ static struct fuse_writepage_args *fuse_writepage_args_alloc(void) wpa = kzalloc(sizeof(*wpa), GFP_NOFS); if (wpa) { ap = &wpa->ia.ap; - ap->num_pages = 0; - ap->pages = fuse_pages_alloc(1, GFP_NOFS, &ap->descs); - if (!ap->pages) { + ap->num_folios = 0; + ap->folios = fuse_folios_alloc(1, GFP_NOFS, &ap->descs); + if (!ap->folios) { kfree(wpa); wpa = NULL; } @@ -1964,463 +2073,244 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc, rcu_read_unlock(); } -static int fuse_writepage_locked(struct page *page) +static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio, + uint32_t folio_index, loff_t offset, unsigned len) { - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; + struct fuse_args_pages *ap = &wpa->ia.ap; + + ap->folios[folio_index] = folio; + ap->descs[folio_index].offset = offset; + ap->descs[folio_index].length = len; +} + +static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio, + size_t offset, + struct fuse_file *ff) +{ + struct inode *inode = folio->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_writepage_args *wpa; struct fuse_args_pages *ap; - struct page *tmp_page; - int error = -ENOMEM; - - set_page_writeback(page); wpa = fuse_writepage_args_alloc(); if (!wpa) - goto err; - ap = &wpa->ia.ap; - - tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); - if (!tmp_page) - goto err_free; - - error = -EIO; - wpa->ia.ff = fuse_write_file_get(fi); - if (!wpa->ia.ff) - goto err_nofile; + return NULL; fuse_writepage_add_to_bucket(fc, wpa); - fuse_write_args_fill(&wpa->ia, wpa->ia.ff, page_offset(page), 0); - - copy_highpage(tmp_page, page); + fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio) + offset, 0); wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE; - wpa->next = NULL; - ap->args.in_pages = true; - ap->num_pages = 1; - ap->pages[0] = tmp_page; - ap->descs[0].offset = 0; - ap->descs[0].length = PAGE_SIZE; - ap->args.end = fuse_writepage_end; wpa->inode = inode; + wpa->ia.ff = ff; - inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); - inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP); - - spin_lock(&fi->lock); - tree_insert(&fi->writepages, wpa); - list_add_tail(&wpa->queue_entry, &fi->queued_writes); - fuse_flush_writepages(inode); - spin_unlock(&fi->lock); - - end_page_writeback(page); - - return 0; - -err_nofile: - __free_page(tmp_page); -err_free: - kfree(wpa); -err: - mapping_set_error(page->mapping, error); - end_page_writeback(page); - return error; -} - -static int fuse_writepage(struct page *page, struct writeback_control *wbc) -{ - struct fuse_conn *fc = get_fuse_conn(page->mapping->host); - int err; - - if (fuse_page_is_writeback(page->mapping->host, page->index)) { - /* - * ->writepages() should be called for sync() and friends. We - * should only get here on direct reclaim and then we are - * allowed to skip a page which is already in flight - */ - WARN_ON(wbc->sync_mode == WB_SYNC_ALL); - - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; - } - - if (wbc->sync_mode == WB_SYNC_NONE && - fc->num_background >= fc->congestion_threshold) - return AOP_WRITEPAGE_ACTIVATE; - - err = fuse_writepage_locked(page); - unlock_page(page); + ap = &wpa->ia.ap; + ap->args.in_pages = true; + ap->args.end = fuse_writepage_end; - return err; + return wpa; } struct fuse_fill_wb_data { struct fuse_writepage_args *wpa; struct fuse_file *ff; - struct inode *inode; - struct page **orig_pages; - unsigned int max_pages; + unsigned int max_folios; + /* + * nr_bytes won't overflow since fuse_folios_need_send() caps + * wb requests to never exceed fc->max_pages (which has an upper bound + * of U16_MAX). + */ + unsigned int nr_bytes; }; -static bool fuse_pages_realloc(struct fuse_fill_wb_data *data) +static bool fuse_pages_realloc(struct fuse_fill_wb_data *data, + unsigned int max_pages) { struct fuse_args_pages *ap = &data->wpa->ia.ap; - struct fuse_conn *fc = get_fuse_conn(data->inode); - struct page **pages; - struct fuse_page_desc *descs; - unsigned int npages = min_t(unsigned int, - max_t(unsigned int, data->max_pages * 2, - FUSE_DEFAULT_MAX_PAGES_PER_REQ), - fc->max_pages); - WARN_ON(npages <= data->max_pages); - - pages = fuse_pages_alloc(npages, GFP_NOFS, &descs); - if (!pages) + struct folio **folios; + struct fuse_folio_desc *descs; + unsigned int nfolios = min_t(unsigned int, + max_t(unsigned int, data->max_folios * 2, + FUSE_DEFAULT_MAX_PAGES_PER_REQ), + max_pages); + WARN_ON(nfolios <= data->max_folios); + + folios = fuse_folios_alloc(nfolios, GFP_NOFS, &descs); + if (!folios) return false; - memcpy(pages, ap->pages, sizeof(struct page *) * ap->num_pages); - memcpy(descs, ap->descs, sizeof(struct fuse_page_desc) * ap->num_pages); - kfree(ap->pages); - ap->pages = pages; + memcpy(folios, ap->folios, sizeof(struct folio *) * ap->num_folios); + memcpy(descs, ap->descs, sizeof(struct fuse_folio_desc) * ap->num_folios); + kfree(ap->folios); + ap->folios = folios; ap->descs = descs; - data->max_pages = npages; + data->max_folios = nfolios; return true; } -static void fuse_writepages_send(struct fuse_fill_wb_data *data) +static void fuse_writepages_send(struct inode *inode, + struct fuse_fill_wb_data *data) { struct fuse_writepage_args *wpa = data->wpa; - struct inode *inode = data->inode; struct fuse_inode *fi = get_fuse_inode(inode); - int num_pages = wpa->ia.ap.num_pages; - int i; - wpa->ia.ff = fuse_file_get(data->ff); spin_lock(&fi->lock); list_add_tail(&wpa->queue_entry, &fi->queued_writes); fuse_flush_writepages(inode); spin_unlock(&fi->lock); - - for (i = 0; i < num_pages; i++) - end_page_writeback(data->orig_pages[i]); } -/* - * Check under fi->lock if the page is under writeback, and insert it onto the - * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's - * one already added for a page at this offset. If there's none, then insert - * this new request onto the auxiliary list, otherwise reuse the existing one by - * swapping the new temp page with the old one. - */ -static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa, - struct page *page) +static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos, + unsigned len, struct fuse_args_pages *ap, + unsigned cur_bytes, bool write) { - struct fuse_inode *fi = get_fuse_inode(new_wpa->inode); - struct fuse_writepage_args *tmp; - struct fuse_writepage_args *old_wpa; - struct fuse_args_pages *new_ap = &new_wpa->ia.ap; - - WARN_ON(new_ap->num_pages != 0); - new_ap->num_pages = 1; - - spin_lock(&fi->lock); - old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa); - if (!old_wpa) { - spin_unlock(&fi->lock); - return true; - } - - for (tmp = old_wpa->next; tmp; tmp = tmp->next) { - pgoff_t curr_index; - - WARN_ON(tmp->inode != new_wpa->inode); - curr_index = tmp->ia.write.in.offset >> PAGE_SHIFT; - if (curr_index == page->index) { - WARN_ON(tmp->ia.ap.num_pages != 1); - swap(tmp->ia.ap.pages[0], new_ap->pages[0]); - break; - } - } - - if (!tmp) { - new_wpa->next = old_wpa->next; - old_wpa->next = new_wpa; - } + struct folio *prev_folio; + struct fuse_folio_desc prev_desc; + unsigned bytes = cur_bytes + len; + loff_t prev_pos; + size_t max_bytes = write ? fc->max_write : fc->max_read; - spin_unlock(&fi->lock); - - if (tmp) { - struct backing_dev_info *bdi = inode_to_bdi(new_wpa->inode); - - dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(new_ap->pages[0], NR_WRITEBACK_TEMP); - wb_writeout_inc(&bdi->wb); - fuse_writepage_free(new_wpa); - } - - return false; -} - -static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page, - struct fuse_args_pages *ap, - struct fuse_fill_wb_data *data) -{ - WARN_ON(!ap->num_pages); - - /* - * Being under writeback is unlikely but possible. For example direct - * read to an mmaped fuse file will set the page dirty twice; once when - * the pages are faulted with get_user_pages(), and then after the read - * completed. - */ - if (fuse_page_is_writeback(data->inode, page->index)) - return true; + WARN_ON(!ap->num_folios); /* Reached max pages */ - if (ap->num_pages == fc->max_pages) + if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages) return true; - /* Reached max write bytes */ - if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write) + if (bytes > max_bytes) return true; /* Discontinuity */ - if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index) - return true; - - /* Need to grow the pages array? If so, did the expansion fail? */ - if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data)) + prev_folio = ap->folios[ap->num_folios - 1]; + prev_desc = ap->descs[ap->num_folios - 1]; + prev_pos = folio_pos(prev_folio) + prev_desc.offset + prev_desc.length; + if (prev_pos != pos) return true; return false; } -static int fuse_writepages_fill(struct folio *folio, - struct writeback_control *wbc, void *_data) +static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc, + struct folio *folio, u64 pos, + unsigned len, u64 end_pos) { - struct fuse_fill_wb_data *data = _data; + struct fuse_fill_wb_data *data = wpc->wb_ctx; struct fuse_writepage_args *wpa = data->wpa; struct fuse_args_pages *ap = &wpa->ia.ap; - struct inode *inode = data->inode; + struct inode *inode = wpc->inode; struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); - struct page *tmp_page; - int err; + loff_t offset = offset_in_folio(folio, pos); + + WARN_ON_ONCE(!data); if (!data->ff) { - err = -EIO; data->ff = fuse_write_file_get(fi); if (!data->ff) - goto out_unlock; - } - - if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) { - fuse_writepages_send(data); - data->wpa = NULL; + return -EIO; } - err = -ENOMEM; - tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); - if (!tmp_page) - goto out_unlock; + if (wpa) { + bool send = fuse_folios_need_send(fc, pos, len, ap, + data->nr_bytes, true); - /* - * The page must not be redirtied until the writeout is completed - * (i.e. userspace has sent a reply to the write request). Otherwise - * there could be more than one temporary page instance for each real - * page. - * - * This is ensured by holding the page lock in page_mkwrite() while - * checking fuse_page_is_writeback(). We already hold the page lock - * since clear_page_dirty_for_io() and keep it held until we add the - * request to the fi->writepages list and increment ap->num_pages. - * After this fuse_page_is_writeback() will indicate that the page is - * under writeback, so we can release the page lock. - */ - if (data->wpa == NULL) { - err = -ENOMEM; - wpa = fuse_writepage_args_alloc(); - if (!wpa) { - __free_page(tmp_page); - goto out_unlock; + if (!send) { + /* + * Need to grow the pages array? If so, did the + * expansion fail? + */ + send = (ap->num_folios == data->max_folios) && + !fuse_pages_realloc(data, fc->max_pages); } - fuse_writepage_add_to_bucket(fc, wpa); - data->max_pages = 1; + if (send) { + fuse_writepages_send(inode, data); + data->wpa = NULL; + data->nr_bytes = 0; + } + } + if (data->wpa == NULL) { + wpa = fuse_writepage_args_setup(folio, offset, data->ff); + if (!wpa) + return -ENOMEM; + fuse_file_get(wpa->ia.ff); + data->max_folios = 1; ap = &wpa->ia.ap; - fuse_write_args_fill(&wpa->ia, data->ff, folio_pos(folio), 0); - wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE; - wpa->next = NULL; - ap->args.in_pages = true; - ap->args.end = fuse_writepage_end; - ap->num_pages = 0; - wpa->inode = inode; } - folio_start_writeback(folio); - copy_highpage(tmp_page, &folio->page); - ap->pages[ap->num_pages] = tmp_page; - ap->descs[ap->num_pages].offset = 0; - ap->descs[ap->num_pages].length = PAGE_SIZE; - data->orig_pages[ap->num_pages] = &folio->page; + fuse_writepage_args_page_fill(wpa, folio, ap->num_folios, + offset, len); + data->nr_bytes += len; - inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); - inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP); + ap->num_folios++; + if (!data->wpa) + data->wpa = wpa; + + return len; +} + +static int fuse_iomap_writeback_submit(struct iomap_writepage_ctx *wpc, + int error) +{ + struct fuse_fill_wb_data *data = wpc->wb_ctx; + + WARN_ON_ONCE(!data); - err = 0; if (data->wpa) { - /* - * Protected by fi->lock against concurrent access by - * fuse_page_is_writeback(). - */ - spin_lock(&fi->lock); - ap->num_pages++; - spin_unlock(&fi->lock); - } else if (fuse_writepage_add(wpa, &folio->page)) { - data->wpa = wpa; - } else { - folio_end_writeback(folio); + WARN_ON(!data->wpa->ia.ap.num_folios); + fuse_writepages_send(wpc->inode, data); } -out_unlock: - folio_unlock(folio); - return err; + if (data->ff) + fuse_file_put(data->ff, false); + + return error; } +static const struct iomap_writeback_ops fuse_writeback_ops = { + .writeback_range = fuse_iomap_writeback_range, + .writeback_submit = fuse_iomap_writeback_submit, +}; + static int fuse_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_fill_wb_data data; - int err; + struct fuse_fill_wb_data data = {}; + struct iomap_writepage_ctx wpc = { + .inode = inode, + .iomap.type = IOMAP_MAPPED, + .wbc = wbc, + .ops = &fuse_writeback_ops, + .wb_ctx = &data, + }; - err = -EIO; if (fuse_is_bad(inode)) - goto out; + return -EIO; if (wbc->sync_mode == WB_SYNC_NONE && fc->num_background >= fc->congestion_threshold) return 0; - data.inode = inode; - data.wpa = NULL; - data.ff = NULL; - - err = -ENOMEM; - data.orig_pages = kcalloc(fc->max_pages, - sizeof(struct page *), - GFP_NOFS); - if (!data.orig_pages) - goto out; - - err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data); - if (data.wpa) { - WARN_ON(!data.wpa->ia.ap.num_pages); - fuse_writepages_send(&data); - } - if (data.ff) - fuse_file_put(data.ff, false, false); - - kfree(data.orig_pages); -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 page **pagep, void **fsdata) -{ - pgoff_t index = pos >> PAGE_SHIFT; - struct fuse_conn *fc = get_fuse_conn(file_inode(file)); - struct page *page; - loff_t fsize; - int err = -ENOMEM; - - WARN_ON(!fc->writeback_cache); - - page = grab_cache_page_write_begin(mapping, index); - if (!page) - goto error; - - fuse_wait_on_page_writeback(mapping->host, page->index); - - if (PageUptodate(page) || len == PAGE_SIZE) - goto success; - /* - * Check if the start this page comes after the end of file, in which - * case the readpage can be optimized away. - */ - fsize = i_size_read(mapping->host); - if (fsize <= (pos & PAGE_MASK)) { - size_t off = pos & ~PAGE_MASK; - if (off) - zero_user_segment(page, 0, off); - goto success; - } - err = fuse_do_readpage(file, page); - if (err) - goto cleanup; -success: - *pagep = page; - return 0; - -cleanup: - unlock_page(page); - put_page(page); -error: - return err; -} - -static int fuse_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - struct inode *inode = page->mapping->host; - - /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ - if (!copied) - goto unlock; - - pos += copied; - if (!PageUptodate(page)) { - /* Zero any unwritten bytes at the end of the page */ - size_t endoff = pos & ~PAGE_MASK; - if (endoff) - zero_user_segment(page, endoff, PAGE_SIZE); - SetPageUptodate(page); - } - - if (pos > inode->i_size) - i_size_write(inode, pos); - - set_page_dirty(page); - -unlock: - unlock_page(page); - put_page(page); - - return copied; + return iomap_writepages(&wpc); } static int fuse_launder_folio(struct folio *folio) { int err = 0; - if (folio_clear_dirty_for_io(folio)) { - struct inode *inode = folio->mapping->host; + struct fuse_fill_wb_data data = {}; + struct iomap_writepage_ctx wpc = { + .inode = folio->mapping->host, + .iomap.type = IOMAP_MAPPED, + .ops = &fuse_writeback_ops, + .wb_ctx = &data, + }; - /* Serialize with pending writeback for the same page */ - fuse_wait_on_page_writeback(inode, folio->index); - err = fuse_writepage_locked(&folio->page); + if (folio_clear_dirty_for_io(folio)) { + err = iomap_writeback_folio(&wpc, folio); + err = fuse_iomap_writeback_submit(&wpc, err); if (!err) - fuse_wait_on_page_writeback(inode, folio->index); + folio_wait_writeback(folio); } return err; } @@ -2454,17 +2344,17 @@ static void fuse_vma_close(struct vm_area_struct *vma) */ static vm_fault_t fuse_page_mkwrite(struct vm_fault *vmf) { - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vmf->vma->vm_file); file_update_time(vmf->vma->vm_file); - lock_page(page); - if (page->mapping != inode->i_mapping) { - unlock_page(page); + folio_lock(folio); + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); return VM_FAULT_NOPAGE; } - fuse_wait_on_page_writeback(inode, page->index); + folio_wait_writeback(folio); return VM_FAULT_LOCKED; } @@ -2478,19 +2368,53 @@ static const struct vm_operations_struct fuse_file_vm_ops = { static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) { struct fuse_file *ff = file->private_data; + struct fuse_conn *fc = ff->fm->fc; + struct inode *inode = file_inode(file); + int rc; /* DAX mmap is superior to direct_io mmap */ - if (FUSE_IS_DAX(file_inode(file))) + if (FUSE_IS_DAX(inode)) return fuse_dax_mmap(file, vma); + /* + * If inode is in passthrough io mode, because it has some file open + * in passthrough mode, either mmap to backing file or fail mmap, + * because mixing cached mmap and passthrough io mode is not allowed. + */ + if (fuse_file_passthrough(ff)) + return fuse_passthrough_mmap(file, vma); + else if (fuse_inode_backing(get_fuse_inode(inode))) + return -ENODEV; + + /* + * FOPEN_DIRECT_IO handling is special compared to O_DIRECT, + * as does not allow MAP_SHARED mmap without FUSE_DIRECT_IO_ALLOW_MMAP. + */ if (ff->open_flags & FOPEN_DIRECT_IO) { - /* Can't provide the coherency needed for MAP_SHARED */ - if (vma->vm_flags & VM_MAYSHARE) + /* + * Can't provide the coherency needed for MAP_SHARED + * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. + */ + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); - return generic_file_mmap(file, vma); + if (!(vma->vm_flags & VM_MAYSHARE)) { + /* MAP_PRIVATE */ + return generic_file_mmap(file, vma); + } + + /* + * First mmap of direct_io file enters caching inode io mode. + * Also waits for parallel dio writers to go into serial mode + * (exclusive instead of shared lock). + * After first mmap, the inode stays in caching io mode until + * the direct_io file release. + */ + rc = fuse_file_cached_io_open(inode, ff); + if (rc) + return rc; } if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) @@ -2523,14 +2447,14 @@ static int convert_fuse_file_lock(struct fuse_conn *fc, * translate it into the caller's pid namespace. */ rcu_read_lock(); - fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns); + fl->c.flc_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns); rcu_read_unlock(); break; default: return -EIO; } - fl->fl_type = ffl->type; + fl->c.flc_type = ffl->type; return 0; } @@ -2544,10 +2468,10 @@ static void fuse_lk_fill(struct fuse_args *args, struct file *file, memset(inarg, 0, sizeof(*inarg)); inarg->fh = ff->fh; - inarg->owner = fuse_lock_owner_id(fc, fl->fl_owner); + inarg->owner = fuse_lock_owner_id(fc, fl->c.flc_owner); inarg->lk.start = fl->fl_start; inarg->lk.end = fl->fl_end; - inarg->lk.type = fl->fl_type; + inarg->lk.type = fl->c.flc_type; inarg->lk.pid = pid; if (flock) inarg->lk_flags |= FUSE_LK_FLOCK; @@ -2584,8 +2508,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_lk_in inarg; - int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK; - struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL; + int opcode = (fl->c.flc_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK; + struct pid *pid = fl->c.flc_type != F_UNLCK ? task_tgid(current) : NULL; pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns); int err; @@ -2594,10 +2518,6 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) return -ENOLCK; } - /* Unlock on close is handled by the flush method */ - if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX) - return 0; - fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg); err = fuse_simple_request(fm, &args); @@ -2885,7 +2805,7 @@ static void fuse_do_truncate(struct file *file) attr.ia_file = file; attr.ia_valid |= ATTR_FILE; - fuse_do_setattr(file_dentry(file), &attr, file); + fuse_do_setattr(file_mnt_idmap(file), file_dentry(file), &attr, file); } static inline loff_t fuse_round_up(struct fuse_conn *fc, loff_t off) @@ -3028,7 +2948,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, inode_lock(inode); if (block_faults) { filemap_invalidate_lock(inode->i_mapping); - err = fuse_dax_break_layouts(inode, 0, 0); + err = fuse_dax_break_layouts(inode, 0, -1); if (err) goto out; } @@ -3115,6 +3035,8 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, .flags = flags }; struct fuse_write_out outarg; + struct fuse_copy_file_range_out outarg_64; + u64 bytes_copied; ssize_t err; /* mark unstable when write-back is not used, and file_out gets * extended */ @@ -3164,30 +3086,51 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, if (is_unstable) set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); - args.opcode = FUSE_COPY_FILE_RANGE; + args.opcode = FUSE_COPY_FILE_RANGE_64; args.nodeid = ff_in->nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; - args.out_args[0].size = sizeof(outarg); - args.out_args[0].value = &outarg; + args.out_args[0].size = sizeof(outarg_64); + args.out_args[0].value = &outarg_64; + if (fc->no_copy_file_range_64) { +fallback: + /* Fall back to old op that can't handle large copy length */ + args.opcode = FUSE_COPY_FILE_RANGE; + args.out_args[0].size = sizeof(outarg); + args.out_args[0].value = &outarg; + inarg.len = len = min_t(size_t, len, UINT_MAX & PAGE_MASK); + } err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { - fc->no_copy_file_range = 1; - err = -EOPNOTSUPP; + if (fc->no_copy_file_range_64) { + fc->no_copy_file_range = 1; + err = -EOPNOTSUPP; + } else { + fc->no_copy_file_range_64 = 1; + goto fallback; + } } if (err) goto out; + bytes_copied = fc->no_copy_file_range_64 ? + outarg.size : outarg_64.bytes_copied; + + if (bytes_copied > len) { + err = -EIO; + goto out; + } + truncate_inode_pages_range(inode_out->i_mapping, ALIGN_DOWN(pos_out, PAGE_SIZE), - ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1); + ALIGN(pos_out + bytes_copied, PAGE_SIZE) - 1); file_update_time(file_out); - fuse_write_update_attr(inode_out, pos_out + outarg.size, outarg.size); + fuse_write_update_attr(inode_out, pos_out + bytes_copied, bytes_copied); - err = outarg.size; + err = bytes_copied; out: if (is_unstable) clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); @@ -3210,8 +3153,8 @@ static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off, len, flags); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_file, src_off, dst_file, - dst_off, len, flags); + ret = splice_copy_file_range(src_file, src_off, dst_file, + dst_off, len); return ret; } @@ -3227,8 +3170,8 @@ static const struct file_operations fuse_file_operations = { .lock = fuse_file_lock, .get_unmapped_area = thp_get_unmapped_area, .flock = fuse_file_flock, - .splice_read = filemap_splice_read, - .splice_write = iter_file_splice_write, + .splice_read = fuse_splice_read, + .splice_write = fuse_splice_write, .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, @@ -3239,28 +3182,33 @@ static const struct file_operations fuse_file_operations = { static const struct address_space_operations fuse_file_aops = { .read_folio = fuse_read_folio, .readahead = fuse_readahead, - .writepage = fuse_writepage, .writepages = fuse_writepages, .launder_folio = fuse_launder_folio, - .dirty_folio = filemap_dirty_folio, + .dirty_folio = iomap_dirty_folio, + .release_folio = iomap_release_folio, + .invalidate_folio = iomap_invalidate_folio, + .is_partially_uptodate = iomap_is_partially_uptodate, + .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) { struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_conn *fc = get_fuse_conn(inode); inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; + if (fc->writeback_cache) + mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); fi->writectr = 0; + fi->iocachectr = 0; init_waitqueue_head(&fi->page_waitq); - fi->writepages = RB_ROOT; + init_waitqueue_head(&fi->direct_io_waitq); if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_inode_init(inode, flags); |