1 files changed, 154 insertions, 157 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 8c19e705b9c3..838c0c571022 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -157,8 +157,8 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
  */
 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);
 
@@ -176,18 +176,8 @@ 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
- * i_private_lock.
- *
- * Hack idea: for the blockdev mapping, i_private_lock contention
- * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take i_private_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 address_space *bd_mapping = bdev->bd_mapping;
 	const int blkbits = bd_mapping->host->i_blkbits;
@@ -204,10 +194,28 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	if (IS_ERR(folio))
 		goto out;
 
-	spin_lock(&bd_mapping->i_private_lock);
+	/*
+	 * 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;
+	/*
+	 * 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))
@@ -236,7 +244,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 		       1 << blkbits);
 	}
 out_unlock:
-	spin_unlock(&bd_mapping->i_private_lock);
+	if (atomic)
+		spin_unlock(&bd_mapping->i_private_lock);
+	else
+		folio_unlock(folio);
 	folio_put(folio);
 out:
 	return ret;
@@ -258,7 +269,6 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	} else {
 		clear_buffer_uptodate(bh);
 		buffer_io_error(bh, ", async page read");
-		folio_set_error(folio);
 	}
 
 	/*
@@ -287,7 +297,6 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 
 still_busy:
 	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	return;
 }
 
 struct postprocess_bh_ctx {
@@ -391,7 +400,6 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		buffer_io_error(bh, ", lost async page write");
 		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
-		folio_set_error(folio);
 	}
 
 	first = folio_buffers(folio);
@@ -413,7 +421,6 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 
 still_busy:
 	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	return;
 }
 
 /*
@@ -604,9 +611,9 @@ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
 		return err;
 
 	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY_ALL))
+	if (!(inode_state_read_once(inode) & I_DIRTY_ALL))
 		goto out;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+	if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC))
 		goto out;
 
 	err = sync_inode_metadata(inode, 1);
@@ -658,7 +665,9 @@ EXPORT_SYMBOL(generic_buffers_fsync);
 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))
 			write_dirty_buffer(bh, 0);
@@ -738,15 +747,12 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
 	 * Lock out page's memcg migration to keep PageDirty
 	 * synchronized with per-memcg dirty page counters.
 	 */
-	folio_memcg_lock(folio);
 	newly_dirty = !folio_test_set_dirty(folio);
 	spin_unlock(&mapping->i_private_lock);
 
 	if (newly_dirty)
 		__folio_mark_dirty(folio, mapping, 1);
 
-	folio_memcg_unlock(folio);
-
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
@@ -776,12 +782,11 @@ EXPORT_SYMBOL(block_dirty_folio);
 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);
@@ -858,8 +863,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
  * done a sync().  Just drop the buffers from the inode list.
  *
  * NOTE: we take the inode's blockdev's mapping's i_private_lock.  Which
- * assumes that all the buffers are against the blockdev.  Not true
- * for reiserfs.
+ * assumes that all the buffers are against the blockdev.
  */
 void invalidate_inode_buffers(struct inode *inode)
 {
@@ -960,12 +964,9 @@ no_grow:
 }
 EXPORT_SYMBOL_GPL(folio_alloc_buffers);
 
-struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
-				       bool retry)
+struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size)
 {
 	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
-	if (retry)
-		gfp |= __GFP_NOFAIL;
 
 	return folio_alloc_buffers(page_folio(page), size, gfp);
 }
@@ -1119,27 +1120,26 @@ static struct buffer_head *
 __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;
 
-		bh = __find_get_block(bdev, block, size);
-		if (bh)
-			return bh;
-
 		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;
 	}
 }
 
@@ -1200,13 +1200,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
 		struct folio *folio = bh->b_folio;
 		struct address_space *mapping = NULL;
 
-		folio_memcg_lock(folio);
 		if (!folio_test_set_dirty(folio)) {
 			mapping = folio->mapping;
 			if (mapping)
 				__folio_mark_dirty(folio, mapping, 0);
 		}
-		folio_memcg_unlock(folio);
 		if (mapping)
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
@@ -1219,10 +1217,8 @@ void mark_buffer_write_io_error(struct buffer_head *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) {
+	if (bh->b_assoc_map)
 		mapping_set_error(bh->b_assoc_map, -EIO);
-		errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
-	}
 }
 EXPORT_SYMBOL(mark_buffer_write_io_error);
 
@@ -1398,16 +1394,18 @@ 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) {
 		/* __find_get_block_slow will mark the page accessed */
-		bh = __find_get_block_slow(bdev, block);
+		bh = __find_get_block_slow(bdev, block, atomic);
 		if (bh)
 			bh_lru_install(bh);
 	} else
@@ -1415,8 +1413,23 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 
 	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);
 
+/* 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.
@@ -1434,7 +1447,12 @@ EXPORT_SYMBOL(__find_get_block);
 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;
+
+	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)
@@ -1590,8 +1608,8 @@ static void discard_buffer(struct buffer_head * bh)
 	bh->b_bdev = NULL;
 	b_state = READ_ONCE(bh->b_state);
 	do {
-	} while (!try_cmpxchg(&bh->b_state, &b_state,
-			      b_state & ~BUFFER_FLAGS_DISCARD));
+	} while (!try_cmpxchg_relaxed(&bh->b_state, &b_state,
+				      b_state & ~BUFFER_FLAGS_DISCARD));
 	unlock_buffer(bh);
 }
 
@@ -1655,7 +1673,7 @@ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 	if (length == folio_size(folio))
 		filemap_release_folio(folio, 0);
 out:
-	return;
+	folio_clear_mappedtodisk(folio);
 }
 EXPORT_SYMBOL(block_invalidate_folio);
 
@@ -1960,7 +1978,6 @@ recover:
 			clear_buffer_dirty(bh);
 		}
 	} while ((bh = bh->b_this_page) != head);
-	folio_set_error(folio);
 	BUG_ON(folio_test_writeback(folio));
 	mapping_set_error(folio->mapping, err);
 	folio_start_writeback(folio);
@@ -2171,15 +2188,14 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
 	return err;
 }
 
-int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block)
 {
-	return __block_write_begin_int(page_folio(page), pos, len, get_block,
-				       NULL);
+	return __block_write_begin_int(folio, pos, len, get_block, NULL);
 }
 EXPORT_SYMBOL(__block_write_begin);
 
-static void __block_commit_write(struct folio *folio, size_t from, size_t to)
+void block_commit_write(struct folio *folio, size_t from, size_t to)
 {
 	size_t block_start, block_end;
 	bool partial = false;
@@ -2187,6 +2203,8 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
 	struct buffer_head *bh, *head;
 
 	bh = head = folio_buffers(folio);
+	if (!bh)
+		return;
 	blocksize = bh->b_size;
 
 	block_start = 0;
@@ -2215,6 +2233,7 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
 	if (!partial)
 		folio_mark_uptodate(folio);
 }
+EXPORT_SYMBOL(block_commit_write);
 
 /*
  * block_write_begin takes care of the basic task of block allocation and
@@ -2223,33 +2242,32 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
  * The filesystem needs to handle block truncation upon failure.
  */
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-		struct page **pagep, get_block_t *get_block)
+		struct folio **foliop, get_block_t *get_block)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
-	struct page *page;
+	struct folio *folio;
 	int status;
 
-	page = grab_cache_page_write_begin(mapping, index);
-	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);
-		put_page(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 folio *folio = page_folio(page);
 	size_t start = pos - folio_pos(folio);
 
 	if (unlikely(copied < len)) {
@@ -2273,27 +2291,27 @@ int block_write_end(struct file *file, struct address_space *mapping,
 	flush_dcache_folio(folio);
 
 	/* This could be a short (even 0-length) commit */
-	__block_commit_write(folio, 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;
 	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_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) {
@@ -2301,8 +2319,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 		i_size_changed = true;
 	}
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -2372,9 +2390,8 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 {
 	struct inode *inode = folio->mapping->host;
 	sector_t iblock, lblock;
-	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
+	struct buffer_head *bh, *head, *prev = NULL;
 	size_t blocksize;
-	int nr, i;
 	int fully_mapped = 1;
 	bool page_error = false;
 	loff_t limit = i_size_read(inode);
@@ -2383,16 +2400,12 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 	if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
 		limit = inode->i_sb->s_maxbytes;
 
-	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-
 	head = folio_create_buffers(folio, inode, 0);
 	blocksize = head->b_size;
 
 	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))
@@ -2405,13 +2418,11 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 			if (iblock < lblock) {
 				WARN_ON(bh->b_size != blocksize);
 				err = get_block(inode, iblock, bh, 0);
-				if (err) {
-					folio_set_error(folio);
+				if (err)
 					page_error = true;
-				}
 			}
 			if (!buffer_mapped(bh)) {
-				folio_zero_range(folio, i * blocksize,
+				folio_zero_range(folio, bh_offset(bh),
 						blocksize);
 				if (!err)
 					set_buffer_uptodate(bh);
@@ -2424,40 +2435,33 @@ int block_read_full_folio(struct folio *folio, 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)
-		folio_set_mappedtodisk(folio);
-
-	if (!nr) {
-		/*
-		 * All buffers are uptodate or get_block() returned an
-		 * error when trying to map them - we can finish the read.
-		 */
-		folio_end_read(folio, !page_error);
-		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(REQ_OP_READ, bh);
-	}
+	if (prev)
+		submit_bh(REQ_OP_READ, prev);
+	else
+		folio_end_read(folio, !page_error);
+
 	return 0;
 }
 EXPORT_SYMBOL(block_read_full_folio);
@@ -2470,7 +2474,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 {
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	int err;
 
@@ -2478,11 +2482,11 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 	if (err)
 		goto out;
 
-	err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata);
+	err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata);
 	if (err)
 		goto out;
 
-	err = aops->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:
@@ -2490,13 +2494,14 @@ 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;
 	const struct address_space_operations *aops = mapping->a_ops;
 	unsigned int blocksize = i_blocksize(inode);
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	pgoff_t index, curidx;
 	loff_t curpos;
@@ -2514,13 +2519,13 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = PAGE_SIZE - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
-					    &page, &fsdata);
+		err = aops->write_begin(iocb, mapping, curpos, len,
+					    &folio, &fsdata);
 		if (err)
 			goto out;
-		zero_user(page, zerofrom, len);
-		err = aops->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);
@@ -2547,13 +2552,13 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = offset - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
-					    &page, &fsdata);
+		err = aops->write_begin(iocb, mapping, curpos, len,
+					    &folio, &fsdata);
 		if (err)
 			goto out;
-		zero_user(page, zerofrom, len);
-		err = aops->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);
@@ -2567,17 +2572,16 @@ 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,
-			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 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;
 
@@ -2587,17 +2591,10 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 		(*bytes)++;
 	}
 
-	return block_write_begin(mapping, pos, len, pagep, get_block);
+	return block_write_begin(mapping, pos, len, foliop, get_block);
 }
 EXPORT_SYMBOL(cont_write_begin);
 
-void block_commit_write(struct page *page, unsigned from, unsigned to)
-{
-	struct folio *folio = page_folio(page);
-	__block_commit_write(folio, from, to);
-}
-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
@@ -2606,7 +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
@@ -2643,7 +2640,7 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (unlikely(ret))
 		goto out_unlock;
 
-	__block_commit_write(folio, 0, end);
+	block_commit_write(folio, 0, end);
 
 	folio_mark_dirty(folio);
 	folio_wait_stable(folio);
@@ -2726,7 +2723,7 @@ unlock:
 EXPORT_SYMBOL(block_truncate_page);
 
 /*
- * The generic ->writepage function for buffer-backed address_spaces
+ * The generic write folio function for buffer-backed address_spaces
  */
 int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 		void *get_block)
@@ -2735,7 +2732,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 	loff_t i_size = i_size_read(inode);
 
 	/* Is the folio fully inside i_size? */
-	if (folio_pos(folio) + folio_size(folio) <= i_size)
+	if (folio_next_pos(folio) <= i_size)
 		return __block_write_full_folio(inode, folio, get_block, wbc);
 
 	/* Is the folio fully outside i_size? (truncate in progress) */
@@ -2746,7 +2743,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 
 	/*
 	 * The folio straddles i_size.  It must be zeroed out on each and every
-	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * 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
 	 * writes to that region are not written out to the file."
@@ -2811,7 +2808,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_write_hint = write_hint;
 
-	__bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	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;
@@ -2821,7 +2818,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
-		wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
+		wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size);
 	}
 
 	submit_bio(bio);