diff options
Diffstat (limited to 'fs/buffer.c')
| -rw-r--r-- | fs/buffer.c | 2832 |
1 files changed, 1283 insertions, 1549 deletions
diff --git a/fs/buffer.c b/fs/buffer.c index 4d7433534f5c..838c0c571022 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * @@ -19,8 +20,10 @@ */ #include <linux/kernel.h> +#include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> +#include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> @@ -30,79 +33,74 @@ #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> +#include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> -#include <linux/notifier.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> +#include <linux/pagevec.h> +#include <linux/sched/mm.h> #include <trace/events/block.h> +#include <linux/fscrypt.h> +#include <linux/fsverity.h> +#include <linux/sched/isolation.h> + +#include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); +static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, + enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) -void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) -{ - bh->b_end_io = handler; - bh->b_private = private; -} -EXPORT_SYMBOL(init_buffer); - inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); - mark_page_accessed(bh->b_page); + folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); -static int sleep_on_buffer(void *word) -{ - io_schedule(); - return 0; -} - void __lock_buffer(struct buffer_head *bh) { - wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer, - TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* - * Returns if the page has dirty or writeback buffers. If all the buffers - * are unlocked and clean then the PageDirty information is stale. If - * any of the pages are locked, it is assumed they are locked for IO. + * Returns if the folio has dirty or writeback buffers. If all the buffers + * are unlocked and clean then the folio_test_dirty information is stale. If + * any of the buffers are locked, it is assumed they are locked for IO. */ -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_has_buffers(page)) + head = folio_buffers(folio); + if (!head) return; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) *writeback = true; - head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) @@ -114,7 +112,6 @@ void buffer_check_dirty_writeback(struct page *page, bh = bh->b_this_page; } while (bh != head); } -EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it @@ -123,33 +120,16 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback); */ void __wait_on_buffer(struct buffer_head * bh) { - wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); -static void -__clear_page_buffers(struct page *page) +static void buffer_io_error(struct buffer_head *bh, char *msg) { - ClearPagePrivate(page); - set_page_private(page, 0); - page_cache_release(page); -} - - -static int quiet_error(struct buffer_head *bh) -{ - if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit()) - return 0; - return 1; -} - - -static void buffer_io_error(struct buffer_head *bh) -{ - char b[BDEVNAME_SIZE]; - printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n", - bdevname(bh->b_bdev, b), - (unsigned long long)bh->b_blocknr); + if (!test_bit(BH_Quiet, &bh->b_state)) + printk_ratelimited(KERN_ERR + "Buffer I/O error on dev %pg, logical block %llu%s\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* @@ -165,7 +145,7 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) if (uptodate) { set_buffer_uptodate(bh); } else { - /* This happens, due to failed READA attempts. */ + /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); @@ -173,29 +153,22 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and - * unlock the buffer. This is what ll_rw_block uses too. + * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { - __end_buffer_read_notouch(bh, uptodate); put_bh(bh); + __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { - char b[BDEVNAME_SIZE]; - if (uptodate) { set_buffer_uptodate(bh); } else { - if (!quiet_error(bh)) { - buffer_io_error(bh); - printk(KERN_WARNING "lost page write due to " - "I/O error on %s\n", - bdevname(bh->b_bdev, b)); - } - set_buffer_write_io_error(bh); + buffer_io_error(bh, ", lost sync page write"); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); @@ -203,38 +176,46 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) } EXPORT_SYMBOL(end_buffer_write_sync); -/* - * Various filesystems appear to want __find_get_block to be non-blocking. - * But it's the page lock which protects the buffers. To get around this, - * we get exclusion from try_to_free_buffers with the blockdev mapping's - * private_lock. - * - * Hack idea: for the blockdev mapping, i_bufferlist_lock contention - * may be quite high. This code could TryLock the page, and if that - * succeeds, there is no need to take private_lock. (But if - * private_lock is contended then so is mapping->tree_lock). - */ static struct buffer_head * -__find_get_block_slow(struct block_device *bdev, sector_t block) +__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic) { - struct inode *bd_inode = bdev->bd_inode; - struct address_space *bd_mapping = bd_inode->i_mapping; + struct address_space *bd_mapping = bdev->bd_mapping; + const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; - struct page *page; + struct folio *folio; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); - index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); - if (!page) + index = ((loff_t)block << blkbits) / PAGE_SIZE; + folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); + if (IS_ERR(folio)) goto out; - spin_lock(&bd_mapping->private_lock); - if (!page_has_buffers(page)) + /* + * Folio lock protects the buffers. Callers that cannot block + * will fallback to serializing vs try_to_free_buffers() via + * the i_private_lock. + */ + if (atomic) + spin_lock(&bd_mapping->i_private_lock); + else + folio_lock(folio); + + head = folio_buffers(folio); + if (!head) goto out_unlock; - head = page_buffers(page); + /* + * Upon a noref migration, the folio lock serializes here; + * otherwise bail. + */ + if (test_bit_acquire(BH_Migrate, &head->b_state)) { + WARN_ON(!atomic); + goto out_unlock; + } + bh = head; do { if (!buffer_mapped(bh)) @@ -252,68 +233,42 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - char b[BDEVNAME_SIZE]; - - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %s blocksize: %d\n", bdevname(bdev, b), - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << blkbits); } out_unlock: - spin_unlock(&bd_mapping->private_lock); - page_cache_release(page); + if (atomic) + spin_unlock(&bd_mapping->i_private_lock); + else + folio_unlock(folio); + folio_put(folio); out: return ret; } -/* - * Kick the writeback threads then try to free up some ZONE_NORMAL memory. - */ -static void free_more_memory(void) -{ - struct zone *zone; - int nid; - - wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM); - yield(); - - for_each_online_node(nid) { - (void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS), - gfp_zone(GFP_NOFS), NULL, - &zone); - if (zone) - try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0, - GFP_NOFS, NULL); - } -} - -/* - * I/O completion handler for block_read_full_page() - pages - * which come unlocked at the end of I/O. - */ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; - struct page *page; - int page_uptodate = 1; + struct folio *folio; + int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); - page = bh->b_page; + folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); - if (!quiet_error(bh)) - buffer_io_error(bh); - SetPageError(page); + buffer_io_error(bh, ", async page read"); } /* @@ -321,72 +276,134 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ - first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + first = folio_buffers(folio); + spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) - page_uptodate = 0; + folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + spin_unlock_irqrestore(&first->b_uptodate_lock, flags); - /* - * If none of the buffers had errors and they are all - * uptodate then we can set the page uptodate. - */ - if (page_uptodate && !PageError(page)) - SetPageUptodate(page); - unlock_page(page); + folio_end_read(folio, folio_uptodate); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + spin_unlock_irqrestore(&first->b_uptodate_lock, flags); +} + +struct postprocess_bh_ctx { + struct work_struct work; + struct buffer_head *bh; +}; + +static void verify_bh(struct work_struct *work) +{ + struct postprocess_bh_ctx *ctx = + container_of(work, struct postprocess_bh_ctx, work); + struct buffer_head *bh = ctx->bh; + bool valid; + + valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); + end_buffer_async_read(bh, valid); + kfree(ctx); +} + +static bool need_fsverity(struct buffer_head *bh) +{ + struct folio *folio = bh->b_folio; + struct inode *inode = folio->mapping->host; + + return fsverity_active(inode) && + /* needed by ext4 */ + folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); +} + +static void decrypt_bh(struct work_struct *work) +{ + struct postprocess_bh_ctx *ctx = + container_of(work, struct postprocess_bh_ctx, work); + struct buffer_head *bh = ctx->bh; + int err; + + err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size, + bh_offset(bh)); + if (err == 0 && need_fsverity(bh)) { + /* + * We use different work queues for decryption and for verity + * because verity may require reading metadata pages that need + * decryption, and we shouldn't recurse to the same workqueue. + */ + INIT_WORK(&ctx->work, verify_bh); + fsverity_enqueue_verify_work(&ctx->work); + return; + } + end_buffer_async_read(bh, err == 0); + kfree(ctx); +} + +/* + * I/O completion handler for block_read_full_folio() - pages + * which come unlocked at the end of I/O. + */ +static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) +{ + struct inode *inode = bh->b_folio->mapping->host; + bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); + bool verify = need_fsverity(bh); + + /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ + if (uptodate && (decrypt || verify)) { + struct postprocess_bh_ctx *ctx = + kmalloc(sizeof(*ctx), GFP_ATOMIC); + + if (ctx) { + ctx->bh = bh; + if (decrypt) { + INIT_WORK(&ctx->work, decrypt_bh); + fscrypt_enqueue_decrypt_work(&ctx->work); + } else { + INIT_WORK(&ctx->work, verify_bh); + fsverity_enqueue_verify_work(&ctx->work); + } + return; + } + uptodate = 0; + } + end_buffer_async_read(bh, uptodate); } /* - * Completion handler for block_write_full_page() - pages which are unlocked - * during I/O, and which have PageWriteback cleared upon I/O completion. + * Completion handler for block_write_full_folio() - folios which are unlocked + * during I/O, and which have the writeback flag cleared upon I/O completion. */ -void end_buffer_async_write(struct buffer_head *bh, int uptodate) +static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { - char b[BDEVNAME_SIZE]; unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; - struct page *page; + struct folio *folio; BUG_ON(!buffer_async_write(bh)); - page = bh->b_page; + folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { - if (!quiet_error(bh)) { - buffer_io_error(bh); - printk(KERN_WARNING "lost page write due to " - "I/O error on %s\n", - bdevname(bh->b_bdev, b)); - } - set_bit(AS_EIO, &page->mapping->flags); - set_buffer_write_io_error(bh); + buffer_io_error(bh, ", lost async page write"); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); - SetPageError(page); } - first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + first = folio_buffers(folio); + spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); @@ -398,17 +415,13 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - end_page_writeback(page); + spin_unlock_irqrestore(&first->b_uptodate_lock, flags); + folio_end_writeback(folio); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } -EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read @@ -433,7 +446,7 @@ EXPORT_SYMBOL(end_buffer_async_write); */ static void mark_buffer_async_read(struct buffer_head *bh) { - bh->b_end_io = end_buffer_async_read; + bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } @@ -458,27 +471,27 @@ EXPORT_SYMBOL(mark_buffer_async_write); * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * - * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), + * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the - * management of a list of dependent buffers at ->i_mapping->private_list. + * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. - * So the locking for private_list is via the private_lock in the address_space + * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, - * mapping->private_lock does *not* protect mapping->private_list! In fact, - * mapping->private_list will always be protected by the backing blockdev's - * ->private_lock. + * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, + * mapping->i_private_list will always be protected by the backing blockdev's + * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's - * ->private_list must be from the same address_space: the blockdev's. + * ->i_private_list must be from the same address_space: the blockdev's. * - * address_spaces which do not place buffers at ->private_list via these - * utility functions are free to use private_lock and private_list for - * whatever they want. The only requirement is that list_empty(private_list) + * address_spaces which do not place buffers at ->i_private_list via these + * utility functions are free to use i_private_lock and i_private_list for + * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The @@ -501,20 +514,18 @@ EXPORT_SYMBOL(mark_buffer_async_write); */ /* - * The buffer's backing address_space's private_lock must be held + * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); - if (buffer_write_io_error(bh)) - set_bit(AS_EIO, &bh->b_assoc_map->flags); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { - return !list_empty(&inode->i_data.private_list); + return !list_empty(&inode->i_data.i_private_list); } /* @@ -522,8 +533,8 @@ int inode_has_buffers(struct inode *inode) * all already-submitted IO to complete, but does not queue any new * writes to the disk. * - * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as - * you dirty the buffers, and then use osync_inode_buffers to wait for + * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer + * as you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ @@ -552,59 +563,98 @@ repeat: return err; } -static void do_thaw_one(struct super_block *sb, void *unused) +/** + * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers + * @mapping: the mapping which wants those buffers written + * + * Starts I/O against the buffers at mapping->i_private_list, and waits upon + * that I/O. + * + * Basically, this is a convenience function for fsync(). + * @mapping is a file or directory which needs those buffers to be written for + * a successful fsync(). + */ +int sync_mapping_buffers(struct address_space *mapping) { - char b[BDEVNAME_SIZE]; - while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) - printk(KERN_WARNING "Emergency Thaw on %s\n", - bdevname(sb->s_bdev, b)); -} + struct address_space *buffer_mapping = mapping->i_private_data; -static void do_thaw_all(struct work_struct *work) -{ - iterate_supers(do_thaw_one, NULL); - kfree(work); - printk(KERN_WARNING "Emergency Thaw complete\n"); + if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) + return 0; + + return fsync_buffers_list(&buffer_mapping->i_private_lock, + &mapping->i_private_list); } +EXPORT_SYMBOL(sync_mapping_buffers); /** - * emergency_thaw_all -- forcibly thaw every frozen filesystem + * generic_buffers_fsync_noflush - generic buffer fsync implementation + * for simple filesystems with no inode lock + * + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true * - * Used for emergency unfreeze of all filesystems via SysRq + * This is a generic implementation of the fsync method for simple + * filesystems which track all non-inode metadata in the buffers list + * hanging off the address_space structure. */ -void emergency_thaw_all(void) +int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, + bool datasync) { - struct work_struct *work; + struct inode *inode = file->f_mapping->host; + int err; + int ret; - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - INIT_WORK(work, do_thaw_all); - schedule_work(work); - } + err = file_write_and_wait_range(file, start, end); + if (err) + return err; + + ret = sync_mapping_buffers(inode->i_mapping); + if (!(inode_state_read_once(inode) & I_DIRTY_ALL)) + goto out; + if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) + goto out; + + err = sync_inode_metadata(inode, 1); + if (ret == 0) + ret = err; + +out: + /* check and advance again to catch errors after syncing out buffers */ + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; + return ret; } +EXPORT_SYMBOL(generic_buffers_fsync_noflush); /** - * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers - * @mapping: the mapping which wants those buffers written + * generic_buffers_fsync - generic buffer fsync implementation + * for simple filesystems with no inode lock * - * Starts I/O against the buffers at mapping->private_list, and waits upon - * that I/O. + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true * - * Basically, this is a convenience function for fsync(). - * @mapping is a file or directory which needs those buffers to be written for - * a successful fsync(). + * This is a generic implementation of the fsync method for simple + * filesystems which track all non-inode metadata in the buffers list + * hanging off the address_space structure. This also makes sure that + * a device cache flush operation is called at the end. */ -int sync_mapping_buffers(struct address_space *mapping) +int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, + bool datasync) { - struct address_space *buffer_mapping = mapping->private_data; - - if (buffer_mapping == NULL || list_empty(&mapping->private_list)) - return 0; + struct inode *inode = file->f_mapping->host; + int ret; - return fsync_buffers_list(&buffer_mapping->private_lock, - &mapping->private_list); + ret = generic_buffers_fsync_noflush(file, start, end, datasync); + if (!ret) + ret = blkdev_issue_flush(inode->i_sb->s_bdev); + return ret; } -EXPORT_SYMBOL(sync_mapping_buffers); +EXPORT_SYMBOL(generic_buffers_fsync); /* * Called when we've recently written block `bblock', and it is known that @@ -615,10 +665,12 @@ EXPORT_SYMBOL(sync_mapping_buffers); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { - struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); + struct buffer_head *bh; + + bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) - ll_rw_block(WRITE, 1, &bh); + write_dirty_buffer(bh, 0); put_bh(bh); } } @@ -626,81 +678,64 @@ void write_boundary_block(struct block_device *bdev, void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; - struct address_space *buffer_mapping = bh->b_page->mapping; + struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); - if (!mapping->private_data) { - mapping->private_data = buffer_mapping; + if (!mapping->i_private_data) { + mapping->i_private_data = buffer_mapping; } else { - BUG_ON(mapping->private_data != buffer_mapping); + BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); -/* - * Mark the page dirty, and set it dirty in the radix tree, and mark the inode - * dirty. +/** + * block_dirty_folio - Mark a folio as dirty. + * @mapping: The address space containing this folio. + * @folio: The folio to mark dirty. * - * If warn is true, then emit a warning if the page is not uptodate and has - * not been truncated. - */ -static void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) -{ - spin_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } - spin_unlock_irq(&mapping->tree_lock); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); -} - -/* - * Add a page to the dirty page list. + * Filesystems which use buffer_heads can use this function as their + * ->dirty_folio implementation. Some filesystems need to do a little + * work before calling this function. Filesystems which do not use + * buffer_heads should call filemap_dirty_folio() instead. * - * It is a sad fact of life that this function is called from several places - * deeply under spinlocking. It may not sleep. + * If the folio has buffers, the uptodate buffers are set dirty, to + * preserve dirty-state coherency between the folio and the buffers. + * Buffers added to a dirty folio are created dirty. * - * If the page has buffers, the uptodate buffers are set dirty, to preserve - * dirty-state coherency between the page and the buffers. It the page does - * not have buffers then when they are later attached they will all be set - * dirty. + * The buffers are dirtied before the folio is dirtied. There's a small + * race window in which writeback may see the folio cleanness but not the + * buffer dirtiness. That's fine. If this code were to set the folio + * dirty before the buffers, writeback could clear the folio dirty flag, + * see a bunch of clean buffers and we'd end up with dirty buffers/clean + * folio on the dirty folio list. * - * The buffers are dirtied before the page is dirtied. There's a small race - * window in which a writepage caller may see the page cleanness but not the - * buffer dirtiness. That's fine. If this code were to set the page dirty - * before the buffers, a concurrent writepage caller could clear the page dirty - * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean - * page on the dirty page list. + * We use i_private_lock to lock against try_to_free_buffers() while + * using the folio's buffer list. This also prevents clean buffers + * being added to the folio after it was set dirty. * - * We use private_lock to lock against try_to_free_buffers while using the - * page's buffer list. Also use this to protect against clean buffers being - * added to the page after it was set dirty. + * Context: May only be called from process context. Does not sleep. + * Caller must ensure that @folio cannot be truncated during this call, + * typically by holding the folio lock or having a page in the folio + * mapped and holding the page table lock. * - * FIXME: may need to call ->reservepage here as well. That's rather up to the - * address_space though. + * Return: True if the folio was dirtied; false if it was already dirtied. */ -int __set_page_dirty_buffers(struct page *page) +bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { - int newly_dirty; - struct address_space *mapping = page_mapping(page); - - if (unlikely(!mapping)) - return !TestSetPageDirty(page); + struct buffer_head *head; + bool newly_dirty; - spin_lock(&mapping->private_lock); - if (page_has_buffers(page)) { - struct buffer_head *head = page_buffers(page); + spin_lock(&mapping->i_private_lock); + head = folio_buffers(folio); + if (head) { struct buffer_head *bh = head; do { @@ -708,14 +743,22 @@ int __set_page_dirty_buffers(struct page *page) bh = bh->b_this_page; } while (bh != head); } - newly_dirty = !TestSetPageDirty(page); - spin_unlock(&mapping->private_lock); + /* + * Lock out page's memcg migration to keep PageDirty + * synchronized with per-memcg dirty page counters. + */ + newly_dirty = !folio_test_set_dirty(folio); + spin_unlock(&mapping->i_private_lock); if (newly_dirty) - __set_page_dirty(page, mapping, 1); + __folio_mark_dirty(folio, mapping, 1); + + if (newly_dirty) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return newly_dirty; } -EXPORT_SYMBOL(__set_page_dirty_buffers); +EXPORT_SYMBOL(block_dirty_folio); /* * Write out and wait upon a list of buffers. @@ -739,12 +782,11 @@ EXPORT_SYMBOL(__set_page_dirty_buffers); static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; - struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; + LIST_HEAD(tmp); - INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); @@ -768,7 +810,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * still in flight on potentially older * contents. */ - write_dirty_buffer(bh, WRITE_SYNC); + write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note @@ -796,7 +838,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); @@ -820,21 +862,20 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * - * NOTE: we take the inode's blockdev's mapping's private_lock. Which - * assumes that all the buffers are against the blockdev. Not true - * for reiserfs. + * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which + * assumes that all the buffers are against the blockdev. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); @@ -851,10 +892,10 @@ int remove_inode_buffers(struct inode *inode) if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { @@ -863,13 +904,13 @@ int remove_inode_buffers(struct inode *inode) } __remove_assoc_queue(bh); } - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } return ret; } /* - * Create the appropriate buffers when given a page for data area and + * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. @@ -877,17 +918,21 @@ int remove_inode_buffers(struct inode *inode) * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - int retry) +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + gfp_t gfp) { struct buffer_head *bh, *head; long offset; + struct mem_cgroup *memcg, *old_memcg; + + /* The folio lock pins the memcg */ + memcg = folio_memcg(folio); + old_memcg = set_active_memcg(memcg); -try_again: head = NULL; - offset = PAGE_SIZE; + offset = folio_size(folio); while ((offset -= size) >= 0) { - bh = alloc_buffer_head(GFP_NOFS); + bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; @@ -897,9 +942,11 @@ try_again: bh->b_size = size; - /* Link the buffer to its page */ - set_bh_page(bh, page, offset); + /* Link the buffer to its folio */ + folio_set_bh(bh, folio, offset); } +out: + set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. @@ -913,28 +960,20 @@ no_grow: } while (head); } - /* - * Return failure for non-async IO requests. Async IO requests - * are not allowed to fail, so we have to wait until buffer heads - * become available. But we don't want tasks sleeping with - * partially complete buffers, so all were released above. - */ - if (!retry) - return NULL; + goto out; +} +EXPORT_SYMBOL_GPL(folio_alloc_buffers); - /* We're _really_ low on memory. Now we just - * wait for old buffer heads to become free due to - * finishing IO. Since this is an async request and - * the reserve list is empty, we're sure there are - * async buffer heads in use. - */ - free_more_memory(); - goto try_again; +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) +{ + gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; + + return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); -static inline void -link_dev_buffers(struct page *page, struct buffer_head *head) +static inline void link_dev_buffers(struct folio *folio, + struct buffer_head *head) { struct buffer_head *bh, *tail; @@ -944,13 +983,13 @@ link_dev_buffers(struct page *page, struct buffer_head *head) bh = bh->b_this_page; } while (bh); tail->b_this_page = head; - attach_page_buffers(page, head); + folio_attach_private(folio, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); - loff_t sz = i_size_read(bdev->bd_inode); + loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); @@ -960,20 +999,21 @@ static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) } /* - * Initialise the state of a blockdev page's buffers. + * Initialise the state of a blockdev folio's buffers. */ -static sector_t -init_page_buffers(struct page *page, struct block_device *bdev, - sector_t block, int size) +static sector_t folio_init_buffers(struct folio *folio, + struct block_device *bdev, unsigned size) { - struct buffer_head *head = page_buffers(page); + struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh = head; - int uptodate = PageUptodate(page); - sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); + bool uptodate = folio_test_uptodate(folio); + sector_t block = div_u64(folio_pos(folio), size); + sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { - init_buffer(bh, NULL, NULL); + bh->b_end_io = NULL; + bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) @@ -992,125 +1032,114 @@ init_page_buffers(struct page *page, struct block_device *bdev, } /* - * Create the page-cache page that contains the requested block. + * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. + * + * Returns false if we have a failure which cannot be cured by retrying + * without sleeping. Returns true if we succeeded, or the caller should retry. */ -static int -grow_dev_page(struct block_device *bdev, sector_t block, - pgoff_t index, int size, int sizebits) +static bool grow_dev_folio(struct block_device *bdev, sector_t block, + pgoff_t index, unsigned size, gfp_t gfp) { - struct inode *inode = bdev->bd_inode; - struct page *page; + struct address_space *mapping = bdev->bd_mapping; + struct folio *folio; struct buffer_head *bh; - sector_t end_block; - int ret = 0; /* Will call free_more_memory() */ - - page = find_or_create_page(inode->i_mapping, index, - (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); - if (!page) - return ret; + sector_t end_block = 0; - BUG_ON(!PageLocked(page)); + folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); + if (IS_ERR(folio)) + return false; - if (page_has_buffers(page)) { - bh = page_buffers(page); + bh = folio_buffers(folio); + if (bh) { if (bh->b_size == size) { - end_block = init_page_buffers(page, bdev, - index << sizebits, size); - goto done; + end_block = folio_init_buffers(folio, bdev, size); + goto unlock; + } + + /* + * Retrying may succeed; for example the folio may finish + * writeback, or buffers may be cleaned. This should not + * happen very often; maybe we have old buffers attached to + * this blockdev's page cache and we're trying to change + * the block size? + */ + if (!try_to_free_buffers(folio)) { + end_block = ~0ULL; + goto unlock; } - if (!try_to_free_buffers(page)) - goto failed; } - /* - * Allocate some buffers for this page - */ - bh = alloc_page_buffers(page, size, 0); + bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); if (!bh) - goto failed; + goto unlock; /* - * Link the page to the buffers and initialise them. Take the + * Link the folio to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not - * run under the page lock. + * run under the folio lock. */ - spin_lock(&inode->i_mapping->private_lock); - link_dev_buffers(page, bh); - end_block = init_page_buffers(page, bdev, index << sizebits, size); - spin_unlock(&inode->i_mapping->private_lock); -done: - ret = (block < end_block) ? 1 : -ENXIO; -failed: - unlock_page(page); - page_cache_release(page); - return ret; + spin_lock(&mapping->i_private_lock); + link_dev_buffers(folio, bh); + end_block = folio_init_buffers(folio, bdev, size); + spin_unlock(&mapping->i_private_lock); +unlock: + folio_unlock(folio); + folio_put(folio); + return block < end_block; } /* - * Create buffers for the specified block device block's page. If - * that page was dirty, the buffers are set dirty also. + * Create buffers for the specified block device block's folio. If + * that folio was dirty, the buffers are set dirty also. Returns false + * if we've hit a permanent error. */ -static int -grow_buffers(struct block_device *bdev, sector_t block, int size) +static bool grow_buffers(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { - pgoff_t index; - int sizebits; - - sizebits = -1; - do { - sizebits++; - } while ((size << sizebits) < PAGE_SIZE); - - index = block >> sizebits; + loff_t pos; /* - * Check for a block which wants to lie outside our maximum possible - * pagecache index. (this comparison is done using sector_t types). + * Check for a block which lies outside our maximum possible + * pagecache index. */ - if (unlikely(index != block >> sizebits)) { - char b[BDEVNAME_SIZE]; - - printk(KERN_ERR "%s: requested out-of-range block %llu for " - "device %s\n", + if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) { + printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n", __func__, (unsigned long long)block, - bdevname(bdev, b)); - return -EIO; + bdev); + return false; } - /* Create a page with the proper size buffers.. */ - return grow_dev_page(bdev, block, index, size, sizebits); + /* Create a folio with the proper size buffers */ + return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp); } static struct buffer_head * -__getblk_slow(struct block_device *bdev, sector_t block, int size) +__getblk_slow(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { - /* Size must be multiple of hard sectorsize */ - if (unlikely(size & (bdev_logical_block_size(bdev)-1) || - (size < 512 || size > PAGE_SIZE))) { - printk(KERN_ERR "getblk(): invalid block size %d requested\n", - size); - printk(KERN_ERR "logical block size: %d\n", - bdev_logical_block_size(bdev)); + bool blocking = gfpflags_allow_blocking(gfp); - dump_stack(); + if (WARN_ON_ONCE(!IS_ALIGNED(size, bdev_logical_block_size(bdev)))) { + printk(KERN_ERR "getblk(): block size %d not aligned to logical block size %d\n", + size, bdev_logical_block_size(bdev)); return NULL; } for (;;) { struct buffer_head *bh; - int ret; - bh = __find_get_block(bdev, block, size); + if (!grow_buffers(bdev, block, size, gfp)) + return NULL; + + if (blocking) + bh = __find_get_block_nonatomic(bdev, block, size); + else + bh = __find_get_block(bdev, block, size); if (bh) return bh; - - ret = grow_buffers(bdev, block, size); - if (ret < 0) - return NULL; - if (ret == 0) - free_more_memory(); } } @@ -1118,7 +1147,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and - * the page is tagged dirty in its radix tree. + * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is @@ -1133,21 +1162,21 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent - * block_read_full_page() against that page will discover all the uptodate - * buffers, will set the page uptodate and will perform no I/O. + * block_read_full_folio() against that folio will discover all the uptodate + * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * - * mark_buffer_dirty() will set the dirty bit against the buffer, then set its - * backing page dirty, then tag the page as dirty in its address_space's radix - * tree and then attach the address_space's inode to its superblock's dirty + * mark_buffer_dirty() will set the dirty bit against the buffer, then set + * its backing page dirty, then tag the page as dirty in the page cache + * and then attach the address_space's inode to its superblock's dirty * inode list. * - * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, - * mapping->tree_lock and mapping->host->i_lock. + * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, + * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { @@ -1168,47 +1197,64 @@ void mark_buffer_dirty(struct buffer_head *bh) } if (!test_set_buffer_dirty(bh)) { - struct page *page = bh->b_page; - if (!TestSetPageDirty(page)) { - struct address_space *mapping = page_mapping(page); + struct folio *folio = bh->b_folio; + struct address_space *mapping = NULL; + + if (!folio_test_set_dirty(folio)) { + mapping = folio->mapping; if (mapping) - __set_page_dirty(page, mapping, 0); + __folio_mark_dirty(folio, mapping, 0); } + if (mapping) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); -/* - * Decrement a buffer_head's reference count. If all buffers against a page - * have zero reference count, are clean and unlocked, and if the page is clean - * and unlocked then try_to_free_buffers() may strip the buffers from the page - * in preparation for freeing it (sometimes, rarely, buffers are removed from - * a page but it ends up not being freed, and buffers may later be reattached). +void mark_buffer_write_io_error(struct buffer_head *bh) +{ + set_buffer_write_io_error(bh); + /* FIXME: do we need to set this in both places? */ + if (bh->b_folio && bh->b_folio->mapping) + mapping_set_error(bh->b_folio->mapping, -EIO); + if (bh->b_assoc_map) + mapping_set_error(bh->b_assoc_map, -EIO); +} +EXPORT_SYMBOL(mark_buffer_write_io_error); + +/** + * __brelse - Release a buffer. + * @bh: The buffer to release. + * + * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ -void __brelse(struct buffer_head * buf) +void __brelse(struct buffer_head *bh) { - if (atomic_read(&buf->b_count)) { - put_bh(buf); + if (atomic_read(&bh->b_count)) { + put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); -/* - * bforget() is like brelse(), except it discards any - * potentially dirty data. +/** + * __bforget - Discard any dirty data in a buffer. + * @bh: The buffer to forget. + * + * This variant of bforget() can be called if @bh is guaranteed to not + * be NULL. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { - struct address_space *buffer_mapping = bh->b_page->mapping; + struct address_space *buffer_mapping = bh->b_folio->mapping; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } @@ -1223,7 +1269,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh) } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ, bh); + submit_bh(REQ_OP_READ, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -1246,7 +1292,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh) * a local interrupt disable for that. */ -#define BH_LRU_SIZE 8 +#define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; @@ -1270,44 +1316,42 @@ static inline void check_irqs_on(void) } /* - * The LRU management algorithm is dopey-but-simple. Sorry. + * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is + * inserted at the front, and the buffer_head at the back if any is evicted. + * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { - struct buffer_head *evictee = NULL; + struct buffer_head *evictee = bh; + struct bh_lru *b; + int i; check_irqs_on(); bh_lru_lock(); - if (__this_cpu_read(bh_lrus.bhs[0]) != bh) { - struct buffer_head *bhs[BH_LRU_SIZE]; - int in; - int out = 0; - get_bh(bh); - bhs[out++] = bh; - for (in = 0; in < BH_LRU_SIZE; in++) { - struct buffer_head *bh2 = - __this_cpu_read(bh_lrus.bhs[in]); + /* + * the refcount of buffer_head in bh_lru prevents dropping the + * attached page(i.e., try_to_free_buffers) so it could cause + * failing page migration. + * Skip putting upcoming bh into bh_lru until migration is done. + */ + if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) { + bh_lru_unlock(); + return; + } - if (bh2 == bh) { - __brelse(bh2); - } else { - if (out >= BH_LRU_SIZE) { - BUG_ON(evictee != NULL); - evictee = bh2; - } else { - bhs[out++] = bh2; - } - } + b = this_cpu_ptr(&bh_lrus); + for (i = 0; i < BH_LRU_SIZE; i++) { + swap(evictee, b->bhs[i]); + if (evictee == bh) { + bh_lru_unlock(); + return; } - while (out < BH_LRU_SIZE) - bhs[out++] = NULL; - memcpy(__this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs)); } - bh_lru_unlock(); - if (evictee) - __brelse(evictee); + get_bh(bh); + bh_lru_unlock(); + brelse(evictee); } /* @@ -1321,11 +1365,15 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) check_irqs_on(); bh_lru_lock(); + if (cpu_is_isolated(smp_processor_id())) { + bh_lru_unlock(); + return NULL; + } for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); - if (bh && bh->b_bdev == bdev && - bh->b_blocknr == block && bh->b_size == size) { + if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && + bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], @@ -1346,77 +1394,141 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return - * NULL + * NULL. Atomic context callers may also return NULL if the buffer is being + * migrated; similarly the page is not marked accessed either. */ -struct buffer_head * -__find_get_block(struct block_device *bdev, sector_t block, unsigned size) +static struct buffer_head * +find_get_block_common(struct block_device *bdev, sector_t block, + unsigned size, bool atomic) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { - bh = __find_get_block_slow(bdev, block); + /* __find_get_block_slow will mark the page accessed */ + bh = __find_get_block_slow(bdev, block, atomic); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } + +struct buffer_head * +__find_get_block(struct block_device *bdev, sector_t block, unsigned size) +{ + return find_get_block_common(bdev, block, size, true); +} EXPORT_SYMBOL(__find_get_block); -/* - * __getblk will locate (and, if necessary, create) the buffer_head - * which corresponds to the passed block_device, block and size. The - * returned buffer has its reference count incremented. +/* same as __find_get_block() but allows sleeping contexts */ +struct buffer_head * +__find_get_block_nonatomic(struct block_device *bdev, sector_t block, + unsigned size) +{ + return find_get_block_common(bdev, block, size, false); +} +EXPORT_SYMBOL(__find_get_block_nonatomic); + +/** + * bdev_getblk - Get a buffer_head in a block device's buffer cache. + * @bdev: The block device. + * @block: The block number. + * @size: The size of buffer_heads for this @bdev. + * @gfp: The memory allocation flags to use. * - * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers() - * attempt is failing. FIXME, perhaps? + * The returned buffer head has its reference count incremented, but is + * not locked. The caller should call brelse() when it has finished + * with the buffer. The buffer may not be uptodate. If needed, the + * caller can bring it uptodate either by reading it or overwriting it. + * + * Return: The buffer head, or NULL if memory could not be allocated. */ -struct buffer_head * -__getblk(struct block_device *bdev, sector_t block, unsigned size) +struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { - struct buffer_head *bh = __find_get_block(bdev, block, size); + struct buffer_head *bh; - might_sleep(); - if (bh == NULL) - bh = __getblk_slow(bdev, block, size); - return bh; + if (gfpflags_allow_blocking(gfp)) + bh = __find_get_block_nonatomic(bdev, block, size); + else + bh = __find_get_block(bdev, block, size); + + might_alloc(gfp); + if (bh) + return bh; + + return __getblk_slow(bdev, block, size, gfp); } -EXPORT_SYMBOL(__getblk); +EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { - struct buffer_head *bh = __getblk(bdev, block, size); + struct buffer_head *bh = bdev_getblk(bdev, block, size, + GFP_NOWAIT | __GFP_MOVABLE); + if (likely(bh)) { - ll_rw_block(READA, 1, &bh); + bh_readahead(bh, REQ_RAHEAD); brelse(bh); } } EXPORT_SYMBOL(__breadahead); /** - * __bread() - reads a specified block and returns the bh - * @bdev: the block_device to read from - * @block: number of block - * @size: size (in bytes) to read - * - * Reads a specified block, and returns buffer head that contains it. - * It returns NULL if the block was unreadable. + * __bread_gfp() - Read a block. + * @bdev: The block device to read from. + * @block: Block number in units of block size. + * @size: The block size of this device in bytes. + * @gfp: Not page allocation flags; see below. + * + * You are not expected to call this function. You should use one of + * sb_bread(), sb_bread_unmovable() or __bread(). + * + * Read a specified block, and return the buffer head that refers to it. + * If @gfp is 0, the memory will be allocated using the block device's + * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be + * allocated from a movable area. Do not pass in a complete set of + * GFP flags. + * + * The returned buffer head has its refcount increased. The caller should + * call brelse() when it has finished with the buffer. + * + * Context: May sleep waiting for I/O. + * Return: NULL if the block was unreadable. */ -struct buffer_head * -__bread(struct block_device *bdev, sector_t block, unsigned size) +struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { - struct buffer_head *bh = __getblk(bdev, block, size); + struct buffer_head *bh; + + gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); + + /* + * Prefer looping in the allocator rather than here, at least that + * code knows what it's doing. + */ + gfp |= __GFP_NOFAIL; + + bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } -EXPORT_SYMBOL(__bread); +EXPORT_SYMBOL(__bread_gfp); + +static void __invalidate_bh_lrus(struct bh_lru *b) +{ + int i; + for (i = 0; i < BH_LRU_SIZE; i++) { + brelse(b->bhs[i]); + b->bhs[i] = NULL; + } +} /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq @@ -1425,101 +1537,117 @@ EXPORT_SYMBOL(__bread); static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); - int i; - for (i = 0; i < BH_LRU_SIZE; i++) { - brelse(b->bhs[i]); - b->bhs[i] = NULL; - } + __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } -static bool has_bh_in_lru(int cpu, void *dummy) +bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) - return 1; + return true; } - return 0; + return false; } void invalidate_bh_lrus(void) { - on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL); + on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); -void set_bh_page(struct buffer_head *bh, - struct page *page, unsigned long offset) +/* + * It's called from workqueue context so we need a bh_lru_lock to close + * the race with preemption/irq. + */ +void invalidate_bh_lrus_cpu(void) +{ + struct bh_lru *b; + + bh_lru_lock(); + b = this_cpu_ptr(&bh_lrus); + __invalidate_bh_lrus(b); + bh_lru_unlock(); +} + +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset) { - bh->b_page = page; - BUG_ON(offset >= PAGE_SIZE); - if (PageHighMem(page)) + bh->b_folio = folio; + BUG_ON(offset >= folio_size(folio)); + if (folio_test_highmem(folio)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else - bh->b_data = page_address(page) + offset; + bh->b_data = folio_address(folio) + offset; } -EXPORT_SYMBOL(set_bh_page); +EXPORT_SYMBOL(folio_set_bh); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = READ_ONCE(bh->b_state); + do { + } while (!try_cmpxchg_relaxed(&bh->b_state, &b_state, + b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } /** - * block_invalidatepage - invalidate part or all of a buffer-backed page - * - * @page: the page which is affected + * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. + * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * - * block_invalidatepage() is called when all or part of the page has become + * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * - * block_invalidatepage() does not have to release all buffers, but it must + * block_invalidate_folio() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ -void block_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; - unsigned int curr_off = 0; - unsigned int stop = length + offset; + size_t curr_off = 0; + size_t stop = length + offset; - BUG_ON(!PageLocked(page)); - if (!page_has_buffers(page)) - goto out; + BUG_ON(!folio_test_locked(folio)); /* * Check for overflow */ - BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + BUG_ON(stop > folio_size(folio) || stop < length); + + head = folio_buffers(folio); + if (!head) + return; - head = page_buffers(page); bh = head; do { - unsigned int next_off = curr_off + bh->b_size; + size_t next_off = curr_off + bh->b_size; next = bh->b_this_page; /* @@ -1538,29 +1666,29 @@ void block_invalidatepage(struct page *page, unsigned int offset, } while (bh != head); /* - * We release buffers only if the entire page is being invalidated. + * We release buffers only if the entire folio is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ - if (offset == 0) - try_to_release_page(page, 0); + if (length == folio_size(folio)) + filemap_release_folio(folio, 0); out: - return; + folio_clear_mappedtodisk(folio); } -EXPORT_SYMBOL(block_invalidatepage); - +EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt - * __set_page_dirty_buffers() via private_lock. try_to_free_buffers - * is already excluded via the page lock. + * block_dirty_folio() via i_private_lock. try_to_free_buffers + * is already excluded via the folio lock. */ -void create_empty_buffers(struct page *page, - unsigned long blocksize, unsigned long b_state) +struct buffer_head *create_empty_buffers(struct folio *folio, + unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; + gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; - head = alloc_page_buffers(page, blocksize, 1); + head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; @@ -1569,74 +1697,111 @@ void create_empty_buffers(struct page *page, } while (bh); tail->b_this_page = head; - spin_lock(&page->mapping->private_lock); - if (PageUptodate(page) || PageDirty(page)) { + spin_lock(&folio->mapping->i_private_lock); + if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { - if (PageDirty(page)) + if (folio_test_dirty(folio)) set_buffer_dirty(bh); - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } - attach_page_buffers(page, head); - spin_unlock(&page->mapping->private_lock); + folio_attach_private(folio, head); + spin_unlock(&folio->mapping->i_private_lock); + + return head; } EXPORT_SYMBOL(create_empty_buffers); -/* - * We are taking a block for data and we don't want any output from any - * buffer-cache aliases starting from return from that function and - * until the moment when something will explicitly mark the buffer - * dirty (hopefully that will not happen until we will free that block ;-) - * We don't even need to mark it not-uptodate - nobody can expect - * anything from a newly allocated buffer anyway. We used to used - * unmap_buffer() for such invalidation, but that was wrong. We definitely - * don't want to mark the alias unmapped, for example - it would confuse - * anyone who might pick it with bread() afterwards... - * - * Also.. Note that bforget() doesn't lock the buffer. So there can - * be writeout I/O going on against recently-freed buffers. We don't - * wait on that I/O in bforget() - it's more efficient to wait on the I/O - * only if we really need to. That happens here. - */ -void unmap_underlying_metadata(struct block_device *bdev, sector_t block) -{ - struct buffer_head *old_bh; +/** + * clean_bdev_aliases: clean a range of buffers in block device + * @bdev: Block device to clean buffers in + * @block: Start of a range of blocks to clean + * @len: Number of blocks to clean + * + * We are taking a range of blocks for data and we don't want writeback of any + * buffer-cache aliases starting from return from this function and until the + * moment when something will explicitly mark the buffer dirty (hopefully that + * will not happen until we will free that block ;-) We don't even need to mark + * it not-uptodate - nobody can expect anything from a newly allocated buffer + * anyway. We used to use unmap_buffer() for such invalidation, but that was + * wrong. We definitely don't want to mark the alias unmapped, for example - it + * would confuse anyone who might pick it with bread() afterwards... + * + * Also.. Note that bforget() doesn't lock the buffer. So there can be + * writeout I/O going on against recently-freed buffers. We don't wait on that + * I/O in bforget() - it's more efficient to wait on the I/O only if we really + * need to. That happens here. + */ +void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) +{ + struct address_space *bd_mapping = bdev->bd_mapping; + const int blkbits = bd_mapping->host->i_blkbits; + struct folio_batch fbatch; + pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; + pgoff_t end; + int i, count; + struct buffer_head *bh; + struct buffer_head *head; - might_sleep(); + end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; + folio_batch_init(&fbatch); + while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { + count = folio_batch_count(&fbatch); + for (i = 0; i < count; i++) { + struct folio *folio = fbatch.folios[i]; - old_bh = __find_get_block_slow(bdev, block); - if (old_bh) { - clear_buffer_dirty(old_bh); - wait_on_buffer(old_bh); - clear_buffer_req(old_bh); - __brelse(old_bh); + if (!folio_buffers(folio)) + continue; + /* + * We use folio lock instead of bd_mapping->i_private_lock + * to pin buffers here since we can afford to sleep and + * it scales better than a global spinlock lock. + */ + folio_lock(folio); + /* Recheck when the folio is locked which pins bhs */ + head = folio_buffers(folio); + if (!head) + goto unlock_page; + bh = head; + do { + if (!buffer_mapped(bh) || (bh->b_blocknr < block)) + goto next; + if (bh->b_blocknr >= block + len) + break; + clear_buffer_dirty(bh); + wait_on_buffer(bh); + clear_buffer_req(bh); +next: + bh = bh->b_this_page; + } while (bh != head); +unlock_page: + folio_unlock(folio); + } + folio_batch_release(&fbatch); + cond_resched(); + /* End of range already reached? */ + if (index > end || !index) + break; } } -EXPORT_SYMBOL(unmap_underlying_metadata); +EXPORT_SYMBOL(clean_bdev_aliases); -/* - * Size is a power-of-two in the range 512..PAGE_SIZE, - * and the case we care about most is PAGE_SIZE. - * - * So this *could* possibly be written with those - * constraints in mind (relevant mostly if some - * architecture has a slow bit-scan instruction) - */ -static inline int block_size_bits(unsigned int blocksize) +static struct buffer_head *folio_create_buffers(struct folio *folio, + struct inode *inode, + unsigned int b_state) { - return ilog2(blocksize); -} + struct buffer_head *bh; -static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) -{ - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state); - return page_buffers(page); + bh = folio_buffers(folio); + if (!bh) + bh = create_empty_buffers(folio, + 1 << READ_ONCE(inode->i_blkbits), b_state); + return bh; } /* @@ -1653,53 +1818,50 @@ static struct buffer_head *create_page_buffers(struct page *page, struct inode * */ /* - * While block_write_full_page is writing back the dirty buffers under + * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * - * If block_write_full_page() is called for regular writeback + * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * - * If block_write_full_page() is called with wbc->sync_mode == - * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this + * If block_write_full_folio() is called with wbc->sync_mode == + * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ -static int __block_write_full_page(struct inode *inode, struct page *page, - get_block_t *get_block, struct writeback_control *wbc, - bh_end_io_t *handler) +int __block_write_full_folio(struct inode *inode, struct folio *folio, + get_block_t *get_block, struct writeback_control *wbc) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; - unsigned int blocksize, bbits; + size_t blocksize; int nr_underway = 0; - int write_op = (wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC : WRITE); + blk_opf_t write_flags = wbc_to_write_flags(wbc); - head = create_page_buffers(page, inode, - (1 << BH_Dirty)|(1 << BH_Uptodate)); + head = folio_create_buffers(folio, inode, + (1 << BH_Dirty) | (1 << BH_Uptodate)); /* - * Be very careful. We have no exclusion from __set_page_dirty_buffers + * Be very careful. We have no exclusion from block_dirty_folio * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it - * then we just miss that fact, and the page stays dirty. + * then we just miss that fact, and the folio stays dirty. * - * Buffers outside i_size may be dirtied by __set_page_dirty_buffers; + * Buffers outside i_size may be dirtied by block_dirty_folio; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; - bbits = block_size_bits(blocksize); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); - last_block = (i_size_read(inode) - 1) >> bbits; + block = div_u64(folio_pos(folio), blocksize); + last_block = div_u64(i_size_read(inode) - 1, blocksize); /* * Get all the dirty buffers mapped to disk addresses and @@ -1709,11 +1871,11 @@ static int __block_write_full_page(struct inode *inode, struct page *page, if (block > last_block) { /* * mapped buffers outside i_size will occur, because - * this page can be outside i_size when there is a + * this folio can be outside i_size when there is a * truncate in progress. */ /* - * The buffer was zeroed by block_write_full_page() + * The buffer was zeroed by block_write_full_folio() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); @@ -1727,8 +1889,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); + clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; @@ -1740,7 +1901,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, continue; /* * If it's a fully non-blocking write attempt and we cannot - * lock the buffer then redirty the page. Note that this can + * lock the buffer then redirty the folio. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. @@ -1748,45 +1909,47 @@ static int __block_write_full_page(struct inode *inode, struct page *page, if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); continue; } if (test_clear_buffer_dirty(bh)) { - mark_buffer_async_write_endio(bh, handler); + mark_buffer_async_write_endio(bh, + end_buffer_async_write); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* - * The page and its buffers are protected by PageWriteback(), so we can - * drop the bh refcounts early. + * The folio and its buffers are protected by the writeback flag, + * so we can drop the bh refcounts early. */ - BUG_ON(PageWriteback(page)); - set_page_writeback(page); + BUG_ON(folio_test_writeback(folio)); + folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh(write_op, bh); + submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); - unlock_page(page); + folio_unlock(folio); err = 0; done: if (nr_underway == 0) { /* - * The page was marked dirty, but the buffers were + * The folio was marked dirty, but the buffers were * clean. Someone wrote them back by hand with - * ll_rw_block/submit_bh. A rare case. + * write_dirty_buffer/submit_bh. A rare case. */ - end_page_writeback(page); + folio_end_writeback(folio); /* - * The page and buffer_heads can be released at any time from + * The folio and buffer_heads can be released at any time from * here on. */ } @@ -1797,7 +1960,7 @@ recover: * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. - * The page is currently locked and not marked for writeback + * The folio is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ @@ -1805,60 +1968,63 @@ recover: if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); - mark_buffer_async_write_endio(bh, handler); + mark_buffer_async_write_endio(bh, + end_buffer_async_write); } else { /* * The buffer may have been set dirty during - * attachment to a dirty page. + * attachment to a dirty folio. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); - SetPageError(page); - BUG_ON(PageWriteback(page)); - mapping_set_error(page->mapping, err); - set_page_writeback(page); + BUG_ON(folio_test_writeback(folio)); + mapping_set_error(folio->mapping, err); + folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh(write_op, bh); + submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); - unlock_page(page); + folio_unlock(folio); goto done; } +EXPORT_SYMBOL(__block_write_full_folio); /* - * If a page has any new buffers, zero them out here, and mark them uptodate + * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ -void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) +void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { - unsigned int block_start, block_end; + size_t block_start, block_end; struct buffer_head *head, *bh; - BUG_ON(!PageLocked(page)); - if (!page_has_buffers(page)) + BUG_ON(!folio_test_locked(folio)); + head = folio_buffers(folio); + if (!head) return; - bh = head = page_buffers(page); + bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { - if (!PageUptodate(page)) { - unsigned start, size; + if (!folio_test_uptodate(folio)) { + size_t start, xend; start = max(from, block_start); - size = min(to, block_end) - start; + xend = min(to, block_end); - zero_user(page, start, size); + folio_zero_segment(folio, start, xend); set_buffer_uptodate(bh); } @@ -1871,36 +2037,101 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) bh = bh->b_this_page; } while (bh != head); } -EXPORT_SYMBOL(page_zero_new_buffers); +EXPORT_SYMBOL(folio_zero_new_buffers); -int __block_write_begin(struct page *page, loff_t pos, unsigned len, - get_block_t *get_block) +static int +iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, + const struct iomap *iomap) +{ + loff_t offset = (loff_t)block << inode->i_blkbits; + + bh->b_bdev = iomap->bdev; + + /* + * Block points to offset in file we need to map, iomap contains + * the offset at which the map starts. If the map ends before the + * current block, then do not map the buffer and let the caller + * handle it. + */ + if (offset >= iomap->offset + iomap->length) + return -EIO; + + switch (iomap->type) { + case IOMAP_HOLE: + /* + * If the buffer is not up to date or beyond the current EOF, + * we need to mark it as new to ensure sub-block zeroing is + * executed if necessary. + */ + if (!buffer_uptodate(bh) || + (offset >= i_size_read(inode))) + set_buffer_new(bh); + return 0; + case IOMAP_DELALLOC: + if (!buffer_uptodate(bh) || + (offset >= i_size_read(inode))) + set_buffer_new(bh); + set_buffer_uptodate(bh); + set_buffer_mapped(bh); + set_buffer_delay(bh); + return 0; + case IOMAP_UNWRITTEN: + /* + * For unwritten regions, we always need to ensure that regions + * in the block we are not writing to are zeroed. Mark the + * buffer as new to ensure this. + */ + set_buffer_new(bh); + set_buffer_unwritten(bh); + fallthrough; + case IOMAP_MAPPED: + if ((iomap->flags & IOMAP_F_NEW) || + offset >= i_size_read(inode)) { + /* + * This can happen if truncating the block device races + * with the check in the caller as i_size updates on + * block devices aren't synchronized by i_rwsem for + * block devices. + */ + if (S_ISBLK(inode->i_mode)) + return -EIO; + set_buffer_new(bh); + } + bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> + inode->i_blkbits; + set_buffer_mapped(bh); + return 0; + default: + WARN_ON_ONCE(1); + return -EIO; + } +} + +int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, + get_block_t *get_block, const struct iomap *iomap) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); - unsigned to = from + len; - struct inode *inode = page->mapping->host; - unsigned block_start, block_end; + size_t from = offset_in_folio(folio, pos); + size_t to = from + len; + struct inode *inode = folio->mapping->host; + size_t block_start, block_end; sector_t block; int err = 0; - unsigned blocksize, bbits; + size_t blocksize; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; - BUG_ON(!PageLocked(page)); - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(!folio_test_locked(folio)); + BUG_ON(to > folio_size(folio)); BUG_ON(from > to); - head = create_page_buffers(page, inode, 0); + head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; - bbits = block_size_bits(blocksize); + block = div_u64(folio_pos(folio), blocksize); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); - - for(bh = head, block_start = 0; bh != head || !block_start; + for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { - if (PageUptodate(page)) { + if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } @@ -1910,26 +2141,29 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); - err = get_block(inode, block, bh, 1); + if (get_block) + err = get_block(inode, block, bh, 1); + else + err = iomap_to_bh(inode, block, bh, iomap); if (err) break; + if (buffer_new(bh)) { - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); - if (PageUptodate(page)) { + clean_bdev_bh_alias(bh); + if (folio_test_uptodate(folio)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) - zero_user_segments(page, + folio_zero_segments(folio, to, block_end, block_start, from); continue; } } - if (PageUptodate(page)) { + if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; @@ -1937,7 +2171,7 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { - ll_rw_block(READ, 1, &bh); + bh_read_nowait(bh, 0); *wait_bh++=bh; } } @@ -1950,20 +2184,27 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, err = -EIO; } if (unlikely(err)) - page_zero_new_buffers(page, from, to); + folio_zero_new_buffers(folio, from, to); return err; } + +int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, + get_block_t *get_block) +{ + return __block_write_begin_int(folio, pos, len, get_block, NULL); +} EXPORT_SYMBOL(__block_write_begin); -static int __block_commit_write(struct inode *inode, struct page *page, - unsigned from, unsigned to) +void block_commit_write(struct folio *folio, size_t from, size_t to) { - unsigned block_start, block_end; - int partial = 0; + size_t block_start, block_end; + bool partial = false; unsigned blocksize; struct buffer_head *bh, *head; - bh = head = page_buffers(page); + bh = head = folio_buffers(folio); + if (!bh) + return; blocksize = bh->b_size; block_start = 0; @@ -1971,12 +2212,13 @@ static int __block_commit_write(struct inode *inode, struct page *page, block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) - partial = 1; + partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } - clear_buffer_new(bh); + if (buffer_new(bh)) + clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; @@ -1984,14 +2226,14 @@ static int __block_commit_write(struct inode *inode, struct page *page, /* * If this is a partial write which happened to make all buffers - * uptodate then we can optimize away a bogus readpage() for - * the next read(). Here we 'discover' whether the page went + * uptodate then we can optimize away a bogus read_folio() for + * the next read(). Here we 'discover' whether the folio went * uptodate as a result of this (potentially partial) write. */ if (!partial) - SetPageUptodate(page); - return 0; + folio_mark_uptodate(folio); } +EXPORT_SYMBOL(block_commit_write); /* * block_write_begin takes care of the basic task of block allocation and @@ -2000,88 +2242,88 @@ static int __block_commit_write(struct inode *inode, struct page *page, * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block) + struct folio **foliop, get_block_t *get_block) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - struct page *page; + pgoff_t index = pos >> PAGE_SHIFT; + struct folio *folio; int status; - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) - return -ENOMEM; + folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) + return PTR_ERR(folio); - status = __block_write_begin(page, pos, len, get_block); + status = __block_write_begin_int(folio, pos, len, get_block, NULL); if (unlikely(status)) { - unlock_page(page); - page_cache_release(page); - page = NULL; + folio_unlock(folio); + folio_put(folio); + folio = NULL; } - *pagep = page; + *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); -int block_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +int block_write_end(loff_t pos, unsigned len, unsigned copied, + struct folio *folio) { - struct inode *inode = mapping->host; - unsigned start; - - start = pos & (PAGE_CACHE_SIZE - 1); + size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { /* - * The buffers that were written will now be uptodate, so we - * don't have to worry about a readpage reading them and - * overwriting a partial write. However if we have encountered - * a short write and only partially written into a buffer, it - * will not be marked uptodate, so a readpage might come in and - * destroy our partial write. + * The buffers that were written will now be uptodate, so + * we don't have to worry about a read_folio reading them + * and overwriting a partial write. However if we have + * encountered a short write and only partially written + * into a buffer, it will not be marked uptodate, so a + * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a - * non uptodate page as a zero-length write, and force the + * non uptodate folio as a zero-length write, and force the * caller to redo the whole thing. */ - if (!PageUptodate(page)) + if (!folio_test_uptodate(folio)) copied = 0; - page_zero_new_buffers(page, start+copied, start+len); + folio_zero_new_buffers(folio, start+copied, start+len); } - flush_dcache_page(page); + flush_dcache_folio(folio); /* This could be a short (even 0-length) commit */ - __block_commit_write(inode, page, start, start+copied); + block_commit_write(folio, start, start + copied); return copied; } EXPORT_SYMBOL(block_write_end); -int generic_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +int generic_write_end(const struct kiocb *iocb, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; - int i_size_changed = 0; + loff_t old_size = inode->i_size; + bool i_size_changed = false; - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = block_write_end(pos, len, copied, folio); /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. + * No need to use i_size_read() here, the i_size cannot change under us + * because we hold i_rwsem. * - * But it's important to update i_size while still holding page lock: + * But it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { - i_size_write(inode, pos+copied); - i_size_changed = 1; + if (pos + copied > inode->i_size) { + i_size_write(inode, pos + copied); + i_size_changed = true; } - unlock_page(page); - page_cache_release(page); + folio_unlock(folio); + folio_put(folio); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -2090,35 +2332,32 @@ int generic_write_end(struct file *file, struct address_space *mapping, */ if (i_size_changed) mark_inode_dirty(inode); - return copied; } EXPORT_SYMBOL(generic_write_end); /* - * block_is_partially_uptodate checks whether buffers within a page are + * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * - * Returns true if all buffers which correspond to a file portion - * we want to read are uptodate. + * Returns true if all buffers which correspond to the specified part + * of the folio are uptodate. */ -int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, - unsigned long from) +bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; - int ret = 1; - - if (!page_has_buffers(page)) - return 0; + bool ret = true; - head = page_buffers(page); + head = folio_buffers(folio); + if (!head) + return false; blocksize = head->b_size; - to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count); + to = min_t(unsigned, folio_size(folio) - from, count); to = from + to; - if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) - return 0; + if (from < blocksize && to > folio_size(folio) - blocksize) + return false; bh = head; block_start = 0; @@ -2126,7 +2365,7 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { - ret = 0; + ret = false; break; } if (block_end >= to) @@ -2141,30 +2380,32 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, EXPORT_SYMBOL(block_is_partially_uptodate); /* - * Generic "read page" function for block devices that have the normal + * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. - * Reads the page asynchronously --- the unlock_buffer() and + * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the - * page struct once IO has completed. + * folio once IO has completed. */ -int block_read_full_page(struct page *page, get_block_t *get_block) +int block_read_full_folio(struct folio *folio, get_block_t *get_block) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; sector_t iblock, lblock; - struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; - unsigned int blocksize, bbits; - int nr, i; + struct buffer_head *bh, *head, *prev = NULL; + size_t blocksize; int fully_mapped = 1; + bool page_error = false; + loff_t limit = i_size_read(inode); + + /* This is needed for ext4. */ + if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) + limit = inode->i_sb->s_maxbytes; - head = create_page_buffers(page, inode, 0); + head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; - bbits = block_size_bits(blocksize); - iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); - lblock = (i_size_read(inode)+blocksize-1) >> bbits; + iblock = div_u64(folio_pos(folio), blocksize); + lblock = div_u64(limit + blocksize - 1, blocksize); bh = head; - nr = 0; - i = 0; do { if (buffer_uptodate(bh)) @@ -2178,10 +2419,11 @@ int block_read_full_page(struct page *page, get_block_t *get_block) WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) - SetPageError(page); + page_error = true; } if (!buffer_mapped(bh)) { - zero_user(page, i * blocksize, blocksize); + folio_zero_range(folio, bh_offset(bh), + blocksize); if (!err) set_buffer_uptodate(bh); continue; @@ -2193,45 +2435,36 @@ int block_read_full_page(struct page *page, get_block_t *get_block) if (buffer_uptodate(bh)) continue; } - arr[nr++] = bh; - } while (i++, iblock++, (bh = bh->b_this_page) != head); - if (fully_mapped) - SetPageMappedToDisk(page); - - if (!nr) { - /* - * All buffers are uptodate - we can set the page uptodate - * as well. But not if get_block() returned an error. - */ - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); - return 0; - } - - /* Stage two: lock the buffers */ - for (i = 0; i < nr; i++) { - bh = arr[i]; lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + continue; + } + mark_buffer_async_read(bh); - } + if (prev) + submit_bh(REQ_OP_READ, prev); + prev = bh; + } while (iblock++, (bh = bh->b_this_page) != head); + + if (fully_mapped) + folio_set_mappedtodisk(folio); /* - * Stage 3: start the IO. Check for uptodateness - * inside the buffer lock in case another process reading - * the underlying blockdev brought it uptodate (the sct fix). + * All buffers are uptodate or get_block() returned an error + * when trying to map them - we must finish the read because + * end_buffer_async_read() will never be called on any buffer + * in this folio. */ - for (i = 0; i < nr; i++) { - bh = arr[i]; - if (buffer_uptodate(bh)) - end_buffer_async_read(bh, 1); - else - submit_bh(READ, bh); - } + if (prev) + submit_bh(REQ_OP_READ, prev); + else + folio_end_read(folio, !page_error); + return 0; } -EXPORT_SYMBOL(block_read_full_page); +EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to @@ -2240,21 +2473,20 @@ EXPORT_SYMBOL(block_read_full_page); int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; - struct page *page; - void *fsdata; + const struct address_space_operations *aops = mapping->a_ops; + struct folio *folio; + void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; - err = pagecache_write_begin(NULL, mapping, size, 0, - AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND, - &page, &fsdata); + err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; - err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); + err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: @@ -2262,48 +2494,54 @@ out: } EXPORT_SYMBOL(generic_cont_expand_simple); -static int cont_expand_zero(struct file *file, struct address_space *mapping, +static int cont_expand_zero(const struct kiocb *iocb, + struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; - struct page *page; - void *fsdata; + const struct address_space_operations *aops = mapping->a_ops; + unsigned int blocksize = i_blocksize(inode); + struct folio *folio; + void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; - index = pos >> PAGE_CACHE_SHIFT; - offset = pos & ~PAGE_CACHE_MASK; + index = pos >> PAGE_SHIFT; + offset = pos & ~PAGE_MASK; - while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) { - zerofrom = curpos & ~PAGE_CACHE_MASK; + while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { + zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } - len = PAGE_CACHE_SIZE - zerofrom; + len = PAGE_SIZE - zerofrom; - err = pagecache_write_begin(file, mapping, curpos, len, - AOP_FLAG_UNINTERRUPTIBLE, - &page, &fsdata); + err = aops->write_begin(iocb, mapping, curpos, len, + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); - err = pagecache_write_end(file, mapping, curpos, len, len, - page, fsdata); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); + err = aops->write_end(iocb, mapping, curpos, len, len, + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); + + if (fatal_signal_pending(current)) { + err = -EINTR; + goto out; + } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { - zerofrom = curpos & ~PAGE_CACHE_MASK; + zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; @@ -2314,14 +2552,13 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, } len = offset - zerofrom; - err = pagecache_write_begin(file, mapping, curpos, len, - AOP_FLAG_UNINTERRUPTIBLE, - &page, &fsdata); + err = aops->write_begin(iocb, mapping, curpos, len, + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); - err = pagecache_write_end(file, mapping, curpos, len, len, - page, fsdata); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); + err = aops->write_end(iocb, mapping, curpos, len, len, + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2335,38 +2572,29 @@ out: * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ -int cont_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata, - get_block_t *get_block, loff_t *bytes) +int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping, + loff_t pos, unsigned len, struct folio **foliop, + void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; - unsigned zerofrom; + unsigned int blocksize = i_blocksize(inode); + unsigned int zerofrom; int err; - err = cont_expand_zero(file, mapping, pos, bytes); + err = cont_expand_zero(iocb, mapping, pos, bytes); if (err) return err; - zerofrom = *bytes & ~PAGE_CACHE_MASK; + zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } - return block_write_begin(mapping, pos, len, flags, pagep, get_block); + return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); -int block_commit_write(struct page *page, unsigned from, unsigned to) -{ - struct inode *inode = page->mapping->host; - __block_commit_write(inode,page,from,to); - return 0; -} -EXPORT_SYMBOL(block_commit_write); - /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must @@ -2375,7 +2603,7 @@ EXPORT_SYMBOL(block_commit_write); * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * - * We are not allowed to take the i_mutex here so we have to play games to + * We are not allowed to take the i_rwsem here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not @@ -2383,445 +2611,78 @@ EXPORT_SYMBOL(block_commit_write); * unlock the page. * * Direct callers of this function should protect against filesystem freezing - * using sb_start_write() - sb_end_write() functions. + * using sb_start_pagefault() - sb_end_pagefault() functions. */ -int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, +int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; - lock_page(page); + folio_lock(folio); size = i_size_read(inode); - if ((page->mapping != inode->i_mapping) || - (page_offset(page) > size)) { + if ((folio->mapping != inode->i_mapping) || + (folio_pos(folio) >= size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } - /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_CACHE_SHIFT) > size) - end = size & ~PAGE_CACHE_MASK; - else - end = PAGE_CACHE_SIZE; + end = folio_size(folio); + /* folio is wholly or partially inside EOF */ + if (folio_pos(folio) + end > size) + end = size - folio_pos(folio); - ret = __block_write_begin(page, 0, end, get_block); - if (!ret) - ret = block_commit_write(page, 0, end); - - if (unlikely(ret < 0)) + ret = __block_write_begin_int(folio, 0, end, get_block, NULL); + if (unlikely(ret)) goto out_unlock; - set_page_dirty(page); - wait_for_stable_page(page); - return 0; -out_unlock: - unlock_page(page); - return ret; -} -EXPORT_SYMBOL(__block_page_mkwrite); - -int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - get_block_t get_block) -{ - int ret; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; - - sb_start_pagefault(sb); - - /* - * Update file times before taking page lock. We may end up failing the - * fault so this update may be superfluous but who really cares... - */ - file_update_time(vma->vm_file); - - ret = __block_page_mkwrite(vma, vmf, get_block); - sb_end_pagefault(sb); - return block_page_mkwrite_return(ret); -} -EXPORT_SYMBOL(block_page_mkwrite); - -/* - * nobh_write_begin()'s prereads are special: the buffer_heads are freed - * immediately, while under the page lock. So it needs a special end_io - * handler which does not touch the bh after unlocking it. - */ -static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) -{ - __end_buffer_read_notouch(bh, uptodate); -} - -/* - * Attach the singly-linked list of buffers created by nobh_write_begin, to - * the page (converting it to circular linked list and taking care of page - * dirty races). - */ -static void attach_nobh_buffers(struct page *page, struct buffer_head *head) -{ - struct buffer_head *bh; - - BUG_ON(!PageLocked(page)); - - spin_lock(&page->mapping->private_lock); - bh = head; - do { - if (PageDirty(page)) - set_buffer_dirty(bh); - if (!bh->b_this_page) - bh->b_this_page = head; - bh = bh->b_this_page; - } while (bh != head); - attach_page_buffers(page, head); - spin_unlock(&page->mapping->private_lock); -} - -/* - * On entry, the page is fully not uptodate. - * On exit the page is fully uptodate in the areas outside (from,to) - * The filesystem needs to handle block truncation upon failure. - */ -int nobh_write_begin(struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata, - get_block_t *get_block) -{ - struct inode *inode = mapping->host; - const unsigned blkbits = inode->i_blkbits; - const unsigned blocksize = 1 << blkbits; - struct buffer_head *head, *bh; - struct page *page; - pgoff_t index; - unsigned from, to; - unsigned block_in_page; - unsigned block_start, block_end; - sector_t block_in_file; - int nr_reads = 0; - int ret = 0; - int is_mapped_to_disk = 1; - - index = pos >> PAGE_CACHE_SHIFT; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; - - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) - return -ENOMEM; - *pagep = page; - *fsdata = NULL; - - if (page_has_buffers(page)) { - ret = __block_write_begin(page, pos, len, get_block); - if (unlikely(ret)) - goto out_release; - return ret; - } - - if (PageMappedToDisk(page)) - return 0; - - /* - * Allocate buffers so that we can keep track of state, and potentially - * attach them to the page if an error occurs. In the common case of - * no error, they will just be freed again without ever being attached - * to the page (which is all OK, because we're under the page lock). - * - * Be careful: the buffer linked list is a NULL terminated one, rather - * than the circular one we're used to. - */ - head = alloc_page_buffers(page, blocksize, 0); - if (!head) { - ret = -ENOMEM; - goto out_release; - } - - block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); - - /* - * We loop across all blocks in the page, whether or not they are - * part of the affected region. This is so we can discover if the - * page is fully mapped-to-disk. - */ - for (block_start = 0, block_in_page = 0, bh = head; - block_start < PAGE_CACHE_SIZE; - block_in_page++, block_start += blocksize, bh = bh->b_this_page) { - int create; - - block_end = block_start + blocksize; - bh->b_state = 0; - create = 1; - if (block_start >= to) - create = 0; - ret = get_block(inode, block_in_file + block_in_page, - bh, create); - if (ret) - goto failed; - if (!buffer_mapped(bh)) - is_mapped_to_disk = 0; - if (buffer_new(bh)) - unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); - if (PageUptodate(page)) { - set_buffer_uptodate(bh); - continue; - } - if (buffer_new(bh) || !buffer_mapped(bh)) { - zero_user_segments(page, block_start, from, - to, block_end); - continue; - } - if (buffer_uptodate(bh)) - continue; /* reiserfs does this */ - if (block_start < from || block_end > to) { - lock_buffer(bh); - bh->b_end_io = end_buffer_read_nobh; - submit_bh(READ, bh); - nr_reads++; - } - } - if (nr_reads) { - /* - * The page is locked, so these buffers are protected from - * any VM or truncate activity. Hence we don't need to care - * for the buffer_head refcounts. - */ - for (bh = head; bh; bh = bh->b_this_page) { - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - ret = -EIO; - } - if (ret) - goto failed; - } - - if (is_mapped_to_disk) - SetPageMappedToDisk(page); - - *fsdata = head; /* to be released by nobh_write_end */ + block_commit_write(folio, 0, end); + folio_mark_dirty(folio); + folio_wait_stable(folio); return 0; - -failed: - BUG_ON(!ret); - /* - * Error recovery is a bit difficult. We need to zero out blocks that - * were newly allocated, and dirty them to ensure they get written out. - * Buffers need to be attached to the page at this point, otherwise - * the handling of potential IO errors during writeout would be hard - * (could try doing synchronous writeout, but what if that fails too?) - */ - attach_nobh_buffers(page, head); - page_zero_new_buffers(page, from, to); - -out_release: - unlock_page(page); - page_cache_release(page); - *pagep = NULL; - - return ret; -} -EXPORT_SYMBOL(nobh_write_begin); - -int nobh_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; - struct buffer_head *head = fsdata; - struct buffer_head *bh; - BUG_ON(fsdata != NULL && page_has_buffers(page)); - - if (unlikely(copied < len) && head) - attach_nobh_buffers(page, head); - if (page_has_buffers(page)) - return generic_write_end(file, mapping, pos, len, - copied, page, fsdata); - - SetPageUptodate(page); - set_page_dirty(page); - if (pos+copied > inode->i_size) { - i_size_write(inode, pos+copied); - mark_inode_dirty(inode); - } - - unlock_page(page); - page_cache_release(page); - - while (head) { - bh = head; - head = head->b_this_page; - free_buffer_head(bh); - } - - return copied; -} -EXPORT_SYMBOL(nobh_write_end); - -/* - * nobh_writepage() - based on block_full_write_page() except - * that it tries to operate without attaching bufferheads to - * the page. - */ -int nobh_writepage(struct page *page, get_block_t *get_block, - struct writeback_control *wbc) -{ - struct inode * const inode = page->mapping->host; - loff_t i_size = i_size_read(inode); - const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; - unsigned offset; - int ret; - - /* Is the page fully inside i_size? */ - if (page->index < end_index) - goto out; - - /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); - if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ -#if 0 - /* Not really sure about this - do we need this ? */ - if (page->mapping->a_ops->invalidatepage) - page->mapping->a_ops->invalidatepage(page, offset); -#endif - unlock_page(page); - return 0; /* don't care */ - } - - /* - * The page straddles i_size. It must be zeroed out on each and every - * writepage invocation because it may be mmapped. "A file is mapped - * in multiples of the page size. For a file that is not a multiple of - * the page size, the remaining memory is zeroed when mapped, and - * writes to that region are not written out to the file." - */ - zero_user_segment(page, offset, PAGE_CACHE_SIZE); -out: - ret = mpage_writepage(page, get_block, wbc); - if (ret == -EAGAIN) - ret = __block_write_full_page(inode, page, get_block, wbc, - end_buffer_async_write); +out_unlock: + folio_unlock(folio); return ret; } -EXPORT_SYMBOL(nobh_writepage); - -int nobh_truncate_page(struct address_space *mapping, - loff_t from, get_block_t *get_block) -{ - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned blocksize; - sector_t iblock; - unsigned length, pos; - struct inode *inode = mapping->host; - struct page *page; - struct buffer_head map_bh; - int err; - - blocksize = 1 << inode->i_blkbits; - length = offset & (blocksize - 1); - - /* Block boundary? Nothing to do */ - if (!length) - return 0; - - length = blocksize - length; - iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - - page = grab_cache_page(mapping, index); - err = -ENOMEM; - if (!page) - goto out; - - if (page_has_buffers(page)) { -has_buffers: - unlock_page(page); - page_cache_release(page); - return block_truncate_page(mapping, from, get_block); - } - - /* Find the buffer that contains "offset" */ - pos = blocksize; - while (offset >= pos) { - iblock++; - pos += blocksize; - } - - map_bh.b_size = blocksize; - map_bh.b_state = 0; - err = get_block(inode, iblock, &map_bh, 0); - if (err) - goto unlock; - /* unmapped? It's a hole - nothing to do */ - if (!buffer_mapped(&map_bh)) - goto unlock; - - /* Ok, it's mapped. Make sure it's up-to-date */ - if (!PageUptodate(page)) { - err = mapping->a_ops->readpage(NULL, page); - if (err) { - page_cache_release(page); - goto out; - } - lock_page(page); - if (!PageUptodate(page)) { - err = -EIO; - goto unlock; - } - if (page_has_buffers(page)) - goto has_buffers; - } - zero_user(page, offset, length); - set_page_dirty(page); - err = 0; - -unlock: - unlock_page(page); - page_cache_release(page); -out: - return err; -} -EXPORT_SYMBOL(nobh_truncate_page); +EXPORT_SYMBOL(block_page_mkwrite); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + pgoff_t index = from >> PAGE_SHIFT; unsigned blocksize; sector_t iblock; - unsigned length, pos; + size_t offset, length, pos; struct inode *inode = mapping->host; - struct page *page; + struct folio *folio; struct buffer_head *bh; - int err; + int err = 0; - blocksize = 1 << inode->i_blkbits; - length = offset & (blocksize - 1); + blocksize = i_blocksize(inode); + length = from & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; - iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - - page = grab_cache_page(mapping, index); - err = -ENOMEM; - if (!page) - goto out; + iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits; - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); + folio = filemap_grab_folio(mapping, index); + if (IS_ERR(folio)) + return PTR_ERR(folio); + + bh = folio_buffers(folio); + if (!bh) + bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ - bh = page_buffers(page); + offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; @@ -2829,7 +2690,6 @@ int block_truncate_page(struct address_space *mapping, pos += blocksize; } - err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); @@ -2841,165 +2701,88 @@ int block_truncate_page(struct address_space *mapping, } /* Ok, it's mapped. Make sure it's up-to-date */ - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { - err = -EIO; - ll_rw_block(READ, 1, &bh); - wait_on_buffer(bh); + err = bh_read(bh, 0); /* Uhhuh. Read error. Complain and punt. */ - if (!buffer_uptodate(bh)) + if (err < 0) goto unlock; } - zero_user(page, offset, length); + folio_zero_range(folio, offset, length); mark_buffer_dirty(bh); - err = 0; unlock: - unlock_page(page); - page_cache_release(page); -out: + folio_unlock(folio); + folio_put(folio); + return err; } EXPORT_SYMBOL(block_truncate_page); /* - * The generic ->writepage function for buffer-backed address_spaces - * this form passes in the end_io handler used to finish the IO. + * The generic write folio function for buffer-backed address_spaces */ -int block_write_full_page_endio(struct page *page, get_block_t *get_block, - struct writeback_control *wbc, bh_end_io_t *handler) +int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, + void *get_block) { - struct inode * const inode = page->mapping->host; + struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); - const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; - unsigned offset; - /* Is the page fully inside i_size? */ - if (page->index < end_index) - return __block_write_full_page(inode, page, get_block, wbc, - handler); + /* Is the folio fully inside i_size? */ + if (folio_next_pos(folio) <= i_size) + return __block_write_full_folio(inode, folio, get_block, wbc); - /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); - if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); - unlock_page(page); + /* Is the folio fully outside i_size? (truncate in progress) */ + if (folio_pos(folio) >= i_size) { + folio_unlock(folio); return 0; /* don't care */ } /* - * The page straddles i_size. It must be zeroed out on each and every - * writepage invocation because it may be mmapped. "A file is mapped + * The folio straddles i_size. It must be zeroed out on each and every + * writeback invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of - * the page size, the remaining memory is zeroed when mapped, and + * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_segment(page, offset, PAGE_CACHE_SIZE); - return __block_write_full_page(inode, page, get_block, wbc, handler); + folio_zero_segment(folio, offset_in_folio(folio, i_size), + folio_size(folio)); + return __block_write_full_folio(inode, folio, get_block, wbc); } -EXPORT_SYMBOL(block_write_full_page_endio); - -/* - * The generic ->writepage function for buffer-backed address_spaces - */ -int block_write_full_page(struct page *page, get_block_t *get_block, - struct writeback_control *wbc) -{ - return block_write_full_page_endio(page, get_block, wbc, - end_buffer_async_write); -} -EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { - struct buffer_head tmp; struct inode *inode = mapping->host; - tmp.b_state = 0; - tmp.b_blocknr = 0; - tmp.b_size = 1 << inode->i_blkbits; + struct buffer_head tmp = { + .b_size = i_blocksize(inode), + }; + get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); -static void end_bio_bh_io_sync(struct bio *bio, int err) +static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; - if (err == -EOPNOTSUPP) { - set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - } - - if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags))) + if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); - bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags)); + bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } -/* - * This allows us to do IO even on the odd last sectors - * of a device, even if the bh block size is some multiple - * of the physical sector size. - * - * We'll just truncate the bio to the size of the device, - * and clear the end of the buffer head manually. - * - * Truly out-of-range accesses will turn into actual IO - * errors, this only handles the "we need to be able to - * do IO at the final sector" case. - */ -static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh) -{ - sector_t maxsector; - unsigned bytes; - - maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; - if (!maxsector) - return; - - /* - * If the *whole* IO is past the end of the device, - * let it through, and the IO layer will turn it into - * an EIO. - */ - if (unlikely(bio->bi_sector >= maxsector)) - return; - - maxsector -= bio->bi_sector; - bytes = bio->bi_size; - if (likely((bytes >> 9) <= maxsector)) - return; - - /* Uhhuh. We've got a bh that straddles the device size! */ - bytes = maxsector << 9; - - /* Truncate the bio.. */ - bio->bi_size = bytes; - bio->bi_io_vec[0].bv_len = bytes; - - /* ..and clear the end of the buffer for reads */ - if ((rw & RW_MASK) == READ) { - void *kaddr = kmap_atomic(bh->b_page); - memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes); - kunmap_atomic(kaddr); - flush_dcache_page(bh->b_page); - } -} - -int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) +static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, + enum rw_hint write_hint, + struct writeback_control *wbc) { + const enum req_op op = opf & REQ_OP_MASK; struct bio *bio; - int ret = 0; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); @@ -3010,108 +2793,44 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) /* * Only clear out a write error when rewriting */ - if (test_set_buffer_req(bh) && (rw & WRITE)) + if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); - /* - * from here on down, it's all bio -- do the initial mapping, - * submit_bio -> generic_make_request may further map this bio around - */ - bio = bio_alloc(GFP_NOIO, 1); + if (buffer_meta(bh)) + opf |= REQ_META; + if (buffer_prio(bh)) + opf |= REQ_PRIO; + + bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO); + + fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); - bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; - bio->bi_io_vec[0].bv_page = bh->b_page; - bio->bi_io_vec[0].bv_len = bh->b_size; - bio->bi_io_vec[0].bv_offset = bh_offset(bh); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_write_hint = write_hint; - bio->bi_vcnt = 1; - bio->bi_size = bh->b_size; + bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; - bio->bi_flags |= bio_flags; /* Take care of bh's that straddle the end of the device */ - guard_bh_eod(rw, bio, bh); - - if (buffer_meta(bh)) - rw |= REQ_META; - if (buffer_prio(bh)) - rw |= REQ_PRIO; + guard_bio_eod(bio); - bio_get(bio); - submit_bio(rw, bio); - - if (bio_flagged(bio, BIO_EOPNOTSUPP)) - ret = -EOPNOTSUPP; + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size); + } - bio_put(bio); - return ret; + submit_bio(bio); } -EXPORT_SYMBOL_GPL(_submit_bh); -int submit_bh(int rw, struct buffer_head *bh) +void submit_bh(blk_opf_t opf, struct buffer_head *bh) { - return _submit_bh(rw, bh, 0); + submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL); } EXPORT_SYMBOL(submit_bh); -/** - * ll_rw_block: low-level access to block devices (DEPRECATED) - * @rw: whether to %READ or %WRITE or maybe %READA (readahead) - * @nr: number of &struct buffer_heads in the array - * @bhs: array of pointers to &struct buffer_head - * - * ll_rw_block() takes an array of pointers to &struct buffer_heads, and - * requests an I/O operation on them, either a %READ or a %WRITE. The third - * %READA option is described in the documentation for generic_make_request() - * which ll_rw_block() calls. - * - * This function drops any buffer that it cannot get a lock on (with the - * BH_Lock state bit), any buffer that appears to be clean when doing a write - * request, and any buffer that appears to be up-to-date when doing read - * request. Further it marks as clean buffers that are processed for - * writing (the buffer cache won't assume that they are actually clean - * until the buffer gets unlocked). - * - * ll_rw_block sets b_end_io to simple completion handler that marks - * the buffer up-to-date (if approriate), unlocks the buffer and wakes - * any waiters. - * - * All of the buffers must be for the same device, and must also be a - * multiple of the current approved size for the device. - */ -void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) -{ - int i; - - for (i = 0; i < nr; i++) { - struct buffer_head *bh = bhs[i]; - - if (!trylock_buffer(bh)) - continue; - if (rw == WRITE) { - if (test_clear_buffer_dirty(bh)) { - bh->b_end_io = end_buffer_write_sync; - get_bh(bh); - submit_bh(WRITE, bh); - continue; - } - } else { - if (!buffer_uptodate(bh)) { - bh->b_end_io = end_buffer_read_sync; - get_bh(bh); - submit_bh(rw, bh); - continue; - } - } - unlock_buffer(bh); - } -} -EXPORT_SYMBOL(ll_rw_block); - -void write_dirty_buffer(struct buffer_head *bh, int rw) +void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { @@ -3120,7 +2839,7 @@ void write_dirty_buffer(struct buffer_head *bh, int rw) } bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(rw, bh); + submit_bh(REQ_OP_WRITE | op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); @@ -3129,68 +2848,53 @@ EXPORT_SYMBOL(write_dirty_buffer); * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ -int __sync_dirty_buffer(struct buffer_head *bh, int rw) +int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { - int ret = 0; - WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(rw, bh); + submit_bh(REQ_OP_WRITE | op_flags, bh); wait_on_buffer(bh); - if (!ret && !buffer_uptodate(bh)) - ret = -EIO; + if (!buffer_uptodate(bh)) + return -EIO; } else { unlock_buffer(bh); } - return ret; + return 0; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { - return __sync_dirty_buffer(bh, WRITE_SYNC); + return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); -/* - * try_to_free_buffers() checks if all the buffers on this particular page - * are unused, and releases them if so. - * - * Exclusion against try_to_free_buffers may be obtained by either - * locking the page or by holding its mapping's private_lock. - * - * If the page is dirty but all the buffers are clean then we need to - * be sure to mark the page clean as well. This is because the page - * may be against a block device, and a later reattachment of buffers - * to a dirty page will set *all* buffers dirty. Which would corrupt - * filesystem data on the same device. - * - * The same applies to regular filesystem pages: if all the buffers are - * clean then we set the page clean and proceed. To do that, we require - * total exclusion from __set_page_dirty_buffers(). That is obtained with - * private_lock. - * - * try_to_free_buffers() is non-blocking. - */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } -static int -drop_buffers(struct page *page, struct buffer_head **buffers_to_free) +static bool +drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { - struct buffer_head *head = page_buffers(page); + struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; do { - if (buffer_write_io_error(bh) && page->mapping) - set_bit(AS_EIO, &page->mapping->flags); if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; @@ -3204,47 +2908,71 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = next; } while (bh != head); *buffers_to_free = head; - __clear_page_buffers(page); - return 1; + folio_detach_private(folio); + return true; failed: - return 0; + return false; } -int try_to_free_buffers(struct page *page) +/** + * try_to_free_buffers - Release buffers attached to this folio. + * @folio: The folio. + * + * If any buffers are in use (dirty, under writeback, elevated refcount), + * no buffers will be freed. + * + * If the folio is dirty but all the buffers are clean then we need to + * be sure to mark the folio clean as well. This is because the folio + * may be against a block device, and a later reattachment of buffers + * to a dirty folio will set *all* buffers dirty. Which would corrupt + * filesystem data on the same device. + * + * The same applies to regular filesystem folios: if all the buffers are + * clean then we set the folio clean and proceed. To do that, we require + * total exclusion from block_dirty_folio(). That is obtained with + * i_private_lock. + * + * Exclusion against try_to_free_buffers may be obtained by either + * locking the folio or by holding its mapping's i_private_lock. + * + * Context: Process context. @folio must be locked. Will not sleep. + * Return: true if all buffers attached to this folio were freed. + */ +bool try_to_free_buffers(struct folio *folio) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; - int ret = 0; + bool ret = 0; - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; + BUG_ON(!folio_test_locked(folio)); + if (folio_test_writeback(folio)) + return false; if (mapping == NULL) { /* can this still happen? */ - ret = drop_buffers(page, &buffers_to_free); + ret = drop_buffers(folio, &buffers_to_free); goto out; } - spin_lock(&mapping->private_lock); - ret = drop_buffers(page, &buffers_to_free); + spin_lock(&mapping->i_private_lock); + ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) - * then we can have clean buffers against a dirty page. We - * clean the page here; otherwise the VM will never notice + * then we can have clean buffers against a dirty folio. We + * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all - * the page's buffers clean. We discover that here and clean - * the page also. + * the folio's buffers clean. We discover that here and clean + * the folio also. * - * private_lock must be held over this entire operation in order - * to synchronise against __set_page_dirty_buffers and prevent the + * i_private_lock must be held over this entire operation in order + * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) - cancel_dirty_page(page, PAGE_CACHE_SIZE); - spin_unlock(&mapping->private_lock); + folio_cancel_dirty(folio); + spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; @@ -3260,42 +2988,15 @@ out: EXPORT_SYMBOL(try_to_free_buffers); /* - * There are no bdflush tunables left. But distributions are - * still running obsolete flush daemons, so we terminate them here. - * - * Use of bdflush() is deprecated and will be removed in a future kernel. - * The `flush-X' kernel threads fully replace bdflush daemons and this call. - */ -SYSCALL_DEFINE2(bdflush, int, func, long, data) -{ - static int msg_count; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (msg_count < 5) { - msg_count++; - printk(KERN_INFO - "warning: process `%s' used the obsolete bdflush" - " system call\n", current->comm); - printk(KERN_INFO "Fix your initscripts?\n"); - } - - if (func == 1) - do_exit(0); - return 0; -} - -/* * Buffer-head allocation */ -static struct kmem_cache *bh_cachep __read_mostly; +static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ -static unsigned long max_buffer_heads; +static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; @@ -3324,6 +3025,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); + spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); @@ -3344,7 +3046,7 @@ void free_buffer_head(struct buffer_head *bh) } EXPORT_SYMBOL(free_buffer_head); -static void buffer_exit_cpu(int cpu) +static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); @@ -3355,14 +3057,7 @@ static void buffer_exit_cpu(int cpu) } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; -} - -static int buffer_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) - buffer_exit_cpu((unsigned long)hcpu); - return NOTIFY_OK; + return 0; } /** @@ -3385,44 +3080,83 @@ int bh_uptodate_or_lock(struct buffer_head *bh) EXPORT_SYMBOL(bh_uptodate_or_lock); /** - * bh_submit_read - Submit a locked buffer for reading + * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head + * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ + * @wait: wait until reading finish * - * Returns zero on success and -EIO on error. + * Returns zero on success or don't wait, and -EIO on error. */ -int bh_submit_read(struct buffer_head *bh) +int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { - BUG_ON(!buffer_locked(bh)); + int ret = 0; - if (buffer_uptodate(bh)) { - unlock_buffer(bh); - return 0; - } + BUG_ON(!buffer_locked(bh)); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ, bh); - wait_on_buffer(bh); - if (buffer_uptodate(bh)) - return 0; - return -EIO; + submit_bh(REQ_OP_READ | op_flags, bh); + if (wait) { + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) + ret = -EIO; + } + return ret; } -EXPORT_SYMBOL(bh_submit_read); +EXPORT_SYMBOL(__bh_read); + +/** + * __bh_read_batch - Submit read for a batch of unlocked buffers + * @nr: entry number of the buffer batch + * @bhs: a batch of struct buffer_head + * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ + * @force_lock: force to get a lock on the buffer if set, otherwise drops any + * buffer that cannot lock. + * + * Returns zero on success or don't wait, and -EIO on error. + */ +void __bh_read_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags, bool force_lock) +{ + int i; + + for (i = 0; i < nr; i++) { + struct buffer_head *bh = bhs[i]; + + if (buffer_uptodate(bh)) + continue; + + if (force_lock) + lock_buffer(bh); + else + if (!trylock_buffer(bh)) + continue; + + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + continue; + } + + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + submit_bh(REQ_OP_READ | op_flags, bh); + } +} +EXPORT_SYMBOL(__bh_read_batch); void __init buffer_init(void) { unsigned long nrpages; + int ret; - bh_cachep = kmem_cache_create("buffer_head", - sizeof(struct buffer_head), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD), - NULL); - + bh_cachep = KMEM_CACHE(buffer_head, + SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); - hotcpu_notifier(buffer_cpu_notify, 0); + ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", + NULL, buffer_exit_cpu_dead); + WARN_ON(ret < 0); } |