Merge tag 'folio-5.18d' of git://git.infradead.org/users/willy/pagecache

torvalds · torvalds · commit cda4351252e7 · 2022-04-01T13:50:50.000-07:00
Pull more filesystem folio updates from Matthew Wilcox:
 "A mixture of odd changes that didn't quite make it into the original
  pull and fixes for things that did. Also the readpages changes had to
  wait for the NFS tree to be pulled first.

   - Remove -&gt;readpages infrastructure

   - Remove AOP_FLAG_CONT_EXPAND

   - Move read_descriptor_t to networking code

   - Pass the iocb to generic_perform_write

   - Minor updates to iomap, btrfs, ext4, f2fs, ntfs"

* tag 'folio-5.18d' of git://git.infradead.org/users/willy/pagecache:
  btrfs: Remove a use of PAGE_SIZE in btrfs_invalidate_folio()
  ntfs: Correct mark_ntfs_record_dirty() folio conversion
  f2fs: Get the superblock from the mapping instead of the page
  f2fs: Correct f2fs_dirty_data_folio() conversion
  ext4: Correct ext4_journalled_dirty_folio() conversion
  filemap: Remove AOP_FLAG_CONT_EXPAND
  fs: Pass an iocb to generic_perform_write()
  fs, net: Move read_descriptor_t to net.h
  fs: Remove read_actor_t
  iomap: Simplify is_partially_uptodate a little
  readahead: Update comments
  mm: remove the skip_page argument to read_pages
  mm: remove the pages argument to read_pages
  fs: Remove -&gt;readpages address space operation
  readahead: Remove read_cache_pages()
diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst
@@ -549,7 +549,7 @@ Pagecache
 ~~~~~~~~~
 
 For filesystems using Linux's pagecache, the ``->readpage()`` and
-``->readpages()`` methods must be modified to verify pages before they
+``->readahead()`` methods must be modified to verify pages before they
 are marked Uptodate.  Merely hooking ``->read_iter()`` would be
 insufficient, since ``->read_iter()`` is not used for memory maps.
 
@@ -611,7 +611,7 @@ workqueue, and then the workqueue work does the decryption or
 verification.  Finally, pages where no decryption or verity error
 occurred are marked Uptodate, and the pages are unlocked.
 
-Files on ext4 and f2fs may contain holes.  Normally, ``->readpages()``
+Files on ext4 and f2fs may contain holes.  Normally, ``->readahead()``
 simply zeroes holes and sets the corresponding pages Uptodate; no bios
 are issued.  To prevent this case from bypassing fs-verity, these
 filesystems use fsverity_verify_page() to verify hole pages.
@@ -778,7 +778,7 @@ weren't already directly answered in other parts of this document.
     - To prevent bypassing verification, pages must not be marked
       Uptodate until they've been verified.  Currently, each
       filesystem is responsible for marking pages Uptodate via
-      ``->readpages()``.  Therefore, currently it's not possible for
+      ``->readahead()``.  Therefore, currently it's not possible for
       the VFS to do the verification on its own.  Changing this would
       require significant changes to the VFS and all filesystems.
 
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
@@ -241,8 +241,6 @@ prototypes::
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	bool (*dirty_folio)(struct address_space *, struct folio *folio);
 	void (*readahead)(struct readahead_control *);
-	int (*readpages)(struct file *filp, struct address_space *mapping,
-			struct list_head *pages, unsigned nr_pages);
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata);
@@ -274,7 +272,6 @@ readpage:		yes, unlocks				shared
 writepages:
 dirty_folio		maybe
 readahead:		yes, unlocks				shared
-readpages:		no					shared
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
@@ -300,9 +297,6 @@ completion.
 
 ->readahead() unlocks the pages that I/O is attempted on like ->readpage().
 
-->readpages() populates the pagecache with the passed pages and starts
-I/O against them.  They come unlocked upon I/O completion.
-
 ->writepage() is used for two purposes: for "memory cleansing" and for
 "sync".  These are quite different operations and the behaviour may differ
 depending upon the mode.
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
@@ -726,8 +726,6 @@ cache in your filesystem.  The following members are defined:
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		bool (*dirty_folio)(struct address_space *, struct folio *);
 		void (*readahead)(struct readahead_control *);
-		int (*readpages)(struct file *filp, struct address_space *mapping,
-				 struct list_head *pages, unsigned nr_pages);
 		int (*write_begin)(struct file *, struct address_space *mapping,
 				   loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata);
@@ -817,15 +815,6 @@ cache in your filesystem.  The following members are defined:
 	completes successfully.  Setting PageError on any page will be
 	ignored; simply unlock the page if an I/O error occurs.
 
-``readpages``
-	called by the VM to read pages associated with the address_space
-	object.  This is essentially just a vector version of readpage.
-	Instead of just one page, several pages are requested.
-	readpages is only used for read-ahead, so read errors are
-	ignored.  If anything goes wrong, feel free to give up.
-	This interface is deprecated and will be removed by the end of
-	2020; implement readahead instead.
-
 ``write_begin``
 	Called by the generic buffered write code to ask the filesystem
 	to prepare to write len bytes at the given offset in the file.
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
@@ -8296,7 +8296,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 	 * cover the full folio, like invalidating the last folio, we're
 	 * still safe to wait for ordered extent to finish.
 	 */
-	if (!(offset == 0 && length == PAGE_SIZE)) {
+	if (!(offset == 0 && length == folio_size(folio))) {
 		btrfs_releasepage(&folio->page, GFP_NOFS);
 		return;
 	}
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
@@ -645,7 +645,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 	int ret;
 
 	/*
-	 * Lock destination range to serialize with concurrent readpages() and
+	 * Lock destination range to serialize with concurrent readahead() and
 	 * source range to serialize with relocation.
 	 */
 	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
@@ -739,7 +739,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	}
 
 	/*
-	 * Lock destination range to serialize with concurrent readpages() and
+	 * Lock destination range to serialize with concurrent readahead() and
 	 * source range to serialize with relocation.
 	 */
 	btrfs_double_extent_lock(src, off, inode, destoff, len);
diff --git a/fs/buffer.c b/fs/buffer.c
@@ -2352,8 +2352,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 	if (err)
 		goto out;
 
-	err = pagecache_write_begin(NULL, mapping, size, 0,
-				    AOP_FLAG_CONT_EXPAND, &page, &fsdata);
+	err = pagecache_write_begin(NULL, mapping, size, 0, 0, &page, &fsdata);
 	if (err)
 		goto out;
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
@@ -1869,7 +1869,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		 * are pending vmtruncate. So write and vmtruncate
 		 * can not run at the same time
 		 */
-		written = generic_perform_write(file, from, pos);
+		written = generic_perform_write(iocb, from);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
 		ceph_end_io_write(inode);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
@@ -597,7 +597,7 @@ CIFSSMBNegotiate(const unsigned int xid,
 	set_credits(server, server->maxReq);
 	/* probably no need to store and check maxvcs */
 	server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize);
-	/* set up max_read for readpages check */
+	/* set up max_read for readahead check */
 	server->max_read = server->maxBuf;
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
 	cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
@@ -49,7 +49,7 @@ static void cifs_set_ops(struct inode *inode)
 			inode->i_fop = &cifs_file_ops;
 		}
 
-		/* check if server can support readpages */
+		/* check if server can support readahead */
 		if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read <
 				PAGE_SIZE + MAX_CIFS_HDR_SIZE)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
@@ -248,7 +248,7 @@ EXPORT_SYMBOL(fscrypt_encrypt_block_inplace);
  * which must still be locked and not uptodate.  Normally, blocksize ==
  * PAGE_SIZE and the whole page is decrypted at once.
  *
- * This is for use by the filesystem's ->readpages() method.
+ * This is for use by the filesystem's ->readahead() method.
  *
  * Return: 0 on success; -errno on failure
  */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
@@ -267,7 +267,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 		goto out;
 
 	current->backing_dev_info = inode_to_bdi(inode);
-	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
+	ret = generic_perform_write(iocb, from);
 	current->backing_dev_info = NULL;
 
 out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
@@ -3589,7 +3589,7 @@ const struct iomap_ops ext4_iomap_report_ops = {
 static bool ext4_journalled_dirty_folio(struct address_space *mapping,
 		struct folio *folio)
 {
-	WARN_ON_ONCE(!page_has_buffers(&folio->page));
+	WARN_ON_ONCE(!folio_buffers(folio));
 	folio_set_checked(folio);
 	return filemap_dirty_folio(mapping, folio);
 }
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
@@ -109,7 +109,7 @@ static void verity_work(struct work_struct *work)
 	struct bio *bio = ctx->bio;
 
 	/*
-	 * fsverity_verify_bio() may call readpages() again, and although verity
+	 * fsverity_verify_bio() may call readahead() again, and although verity
 	 * will be disabled for that, decryption may still be needed, causing
 	 * another bio_post_read_ctx to be allocated.  So to guarantee that
 	 * mempool_alloc() never deadlocks we must free the current ctx first.
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
@@ -456,7 +456,7 @@ static bool f2fs_dirty_meta_folio(struct address_space *mapping,
 		folio_mark_uptodate(folio);
 	if (!folio_test_dirty(folio)) {
 		filemap_dirty_folio(mapping, folio);
-		inc_page_count(F2FS_P_SB(&folio->page), F2FS_DIRTY_META);
+		inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_META);
 		set_page_private_reference(&folio->page);
 		return true;
 	}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
@@ -164,7 +164,7 @@ static void f2fs_verify_bio(struct work_struct *work)
 	bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS);
 
 	/*
-	 * fsverity_verify_bio() may call readpages() again, and while verity
+	 * fsverity_verify_bio() may call readahead() again, and while verity
 	 * will be disabled for this, decryption and/or decompression may still
 	 * be needed, resulting in another bio_post_read_ctx being allocated.
 	 * So to prevent deadlocks we need to release the current ctx to the
@@ -2392,7 +2392,7 @@ static void f2fs_readahead(struct readahead_control *rac)
 	if (!f2fs_is_compress_backend_ready(inode))
 		return;
 
-	/* If the file has inline data, skip readpages */
+	/* If the file has inline data, skip readahead */
 	if (f2fs_has_inline_data(inode))
 		return;
 
@@ -3571,7 +3571,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
 		f2fs_update_dirty_folio(inode, folio);
 		return true;
 	}
-	return true;
+	return false;
 }
 
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
@@ -4448,7 +4448,7 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb,
 		return -EOPNOTSUPP;
 
 	current->backing_dev_info = inode_to_bdi(inode);
-	ret = generic_perform_write(file, from, iocb->ki_pos);
+	ret = generic_perform_write(iocb, from);
 	current->backing_dev_info = NULL;
 
 	if (ret > 0) {
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
@@ -2146,11 +2146,11 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping,
 		folio_mark_uptodate(folio);
 #ifdef CONFIG_F2FS_CHECK_FS
 	if (IS_INODE(&folio->page))
-		f2fs_inode_chksum_set(F2FS_P_SB(&folio->page), &folio->page);
+		f2fs_inode_chksum_set(F2FS_M_SB(mapping), &folio->page);
 #endif
 	if (!folio_test_dirty(folio)) {
 		filemap_dirty_folio(mapping, folio);
-		inc_page_count(F2FS_P_SB(&folio->page), F2FS_DIRTY_NODES);
+		inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
 		set_page_private_reference(&folio->page);
 		return true;
 	}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
@@ -627,7 +627,7 @@ struct fuse_conn {
 	/** Connection successful.  Only set in INIT */
 	unsigned conn_init:1;
 
-	/** Do readpages asynchronously?  Only set in INIT */
+	/** Do readahead asynchronously?  Only set in INIT */
 	unsigned async_read:1;
 
 	/** Return an unique read error after abort.  Only set in INIT */
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
@@ -435,18 +435,17 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 {
 	struct iomap_page *iop = to_iomap_page(folio);
 	struct inode *inode = folio->mapping->host;
-	size_t len;
 	unsigned first, last, i;
 
 	if (!iop)
 		return false;
 
-	/* Limit range to this folio */
-	len = min(folio_size(folio) - from, count);
+	/* Caller's range may extend past the end of this folio */
+	count = min(folio_size(folio) - from, count);
 
-	/* First and last blocks in range within page */
+	/* First and last blocks in range within folio */
 	first = from >> inode->i_blkbits;
-	last = (from + len - 1) >> inode->i_blkbits;
+	last = (from + count - 1) >> inode->i_blkbits;
 
 	for (i = first; i <= last; i++)
 		if (!test_bit(i, iop->uptodate))
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
@@ -646,7 +646,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	result = generic_write_checks(iocb, from);
 	if (result > 0) {
 		current->backing_dev_info = inode_to_bdi(inode);
-		result = generic_perform_write(file, from, iocb->ki_pos);
+		result = generic_perform_write(iocb, from);
 		current->backing_dev_info = NULL;
 	}
 	nfs_end_io_write(inode);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
@@ -1746,7 +1746,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 		set_buffer_dirty(bh);
 	} while ((bh = bh->b_this_page) != head);
 	spin_unlock(&mapping->private_lock);
-	block_dirty_folio(mapping, page_folio(page));
+	filemap_dirty_folio(mapping, page_folio(page));
 	if (unlikely(buffers_to_free)) {
 		do {
 			bh = buffers_to_free->b_this_page;
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Data verification functions, i.e. hooks for ->readpages()
+ * Data verification functions, i.e. hooks for ->readahead()
  *
  * Copyright 2019 Google LLC
  */
@@ -214,7 +214,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page);
  * that fail verification are set to the Error state.  Verification is skipped
  * for pages already in the Error state, e.g. due to fscrypt decryption failure.
  *
- * This is a helper function for use by the ->readpages() method of filesystems
+ * This is a helper function for use by the ->readahead() method of filesystems
  * that issue bios to read data directly into the page cache.  Filesystems that
  * populate the page cache without issuing bios (e.g. non block-based
  * filesystems) must instead call fsverity_verify_page() directly on each page.
diff --git a/include/linux/fs.h b/include/linux/fs.h
@@ -275,7 +275,6 @@ enum positive_aop_returns {
 	AOP_TRUNCATED_PAGE	= 0x80001,
 };
 
-#define AOP_FLAG_CONT_EXPAND		0x0001 /* called from cont_expand */
 #define AOP_FLAG_NOFS			0x0002 /* used by filesystem to direct
 						* helper code (eg buffer layer)
 						* to clear GFP_FS from alloc */
@@ -338,28 +337,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 	return kiocb->ki_complete == NULL;
 }
 
-/*
- * "descriptor" for what we're up to with a read.
- * This allows us to use the same read code yet
- * have multiple different users of the data that
- * we read from a file.
- *
- * The simplest case just copies the data to user
- * mode.
- */
-typedef struct {
-	size_t written;
-	size_t count;
-	union {
-		char __user *buf;
-		void *data;
-	} arg;
-	int error;
-} read_descriptor_t;
-
-typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
-		unsigned long, unsigned long);
-
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);
@@ -370,12 +347,6 @@ struct address_space_operations {
 	/* Mark a folio dirty.  Return true if this dirtied it */
 	bool (*dirty_folio)(struct address_space *, struct folio *);
 
-	/*
-	 * Reads in the requested pages. Unlike ->readpage(), this is
-	 * PURELY used for read-ahead!.
-	 */
-	int (*readpages)(struct file *filp, struct address_space *mapping,
-			struct list_head *pages, unsigned nr_pages);
 	void (*readahead)(struct readahead_control *);
 
 	int (*write_begin)(struct file *, struct address_space *mapping,
@@ -3027,7 +2998,7 @@ extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
-extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
+ssize_t generic_perform_write(struct kiocb *, struct iov_iter *);
 
 ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
@@ -221,7 +221,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
  *
  * This checks whether ->i_verity_info has been set.
  *
- * Filesystems call this from ->readpages() to check whether the pages need to
+ * Filesystems call this from ->readahead() to check whether the pages need to
  * be verified or not.  Don't use IS_VERITY() for this purpose; it's subject to
  * a race condition where the file is being read concurrently with
  * FS_IOC_ENABLE_VERITY completing.  (S_VERITY is set before ->i_verity_info.)
diff --git a/include/linux/net.h b/include/linux/net.h
@@ -125,6 +125,25 @@ struct socket {
 	struct socket_wq	wq;
 };
 
+/*
+ * "descriptor" for what we're up to with a read.
+ * This allows us to use the same read code yet
+ * have multiple different users of the data that
+ * we read from a file.
+ *
+ * The simplest case just copies the data to user
+ * mode.
+ */
+typedef struct {
+	size_t written;
+	size_t count;
+	union {
+		char __user *buf;
+		void *data;
+	} arg;
+	int error;
+} read_descriptor_t;
+
 struct vm_area_struct;
 struct page;
 struct sockaddr;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
diff --git a/mm/filemap.c b/mm/filemap.c
diff --git a/mm/readahead.c b/mm/readahead.c

Original file line number	Diff line number	Diff line change
`@@ -8296,7 +8296,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,`
`8296`	`8296`	`* cover the full folio, like invalidating the last folio, we're`
`8297`	`8297`	`* still safe to wait for ordered extent to finish.`
`8298`	`8298`	`*/`
`8299`		`- if (!(offset == 0 && length == PAGE_SIZE)) {`
	`8299`	`+ if (!(offset == 0 && length == folio_size(folio))) {`
`8300`	`8300`	`btrfs_releasepage(&folio->page, GFP_NOFS);`
`8301`	`8301`	`return;`
`8302`	`8302`	`}`
Original file line number	Diff line number	Diff line change
`@@ -49,7 +49,7 @@ static void cifs_set_ops(struct inode *inode)`
`49`	`49`	`inode->i_fop = &cifs_file_ops;`
`50`	`50`	`}`
`51`	`51`
`52`		`- /* check if server can support readpages */`
	`52`	`+ /* check if server can support readahead */`
`53`	`53`	`if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read <`
`54`	`54`	`PAGE_SIZE + MAX_CIFS_HDR_SIZE)`
`55`	`55`	`inode->i_data.a_ops = &cifs_addr_ops_smallbuf;`
Original file line number	Diff line number	Diff line change
`@@ -248,7 +248,7 @@ EXPORT_SYMBOL(fscrypt_encrypt_block_inplace);`
`248`	`248`	`* which must still be locked and not uptodate. Normally, blocksize ==`
`249`	`249`	`* PAGE_SIZE and the whole page is decrypted at once.`
`250`	`250`	`*`
`251`		`- * This is for use by the filesystem's ->readpages() method.`
	`251`	`+ * This is for use by the filesystem's ->readahead() method.`
`252`	`252`	`*`
`253`	`253`	`* Return: 0 on success; -errno on failure`
`254`	`254`	`*/`