Merge tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs iov_iter updates from Al Viro:
 "Part 1 - isolated cleanups and optimizations.

  One of the goals is to reduce the overhead of using ->read_iter() and
  ->write_iter() instead of ->read()/->write().

  new_sync_{read,write}() has a surprising amount of overhead, in
  particular inside iocb_flags(). That's the explanation for the
  beginning of the series is in this pile; it's not directly
  iov_iter-related, but it's a part of the same work..."

* tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  first_iovec_segment(): just return address
  iov_iter: massage calling conventions for first_{iovec,bvec}_segment()
  iov_iter: first_{iovec,bvec}_segment() - simplify a bit
  iov_iter: lift dealing with maxpages out of first_{iovec,bvec}_segment()
  iov_iter_get_pages{,_alloc}(): cap the maxsize with MAX_RW_COUNT
  iov_iter_bvec_advance(): don't bother with bvec_iter
  copy_page_{to,from}_iter(): switch iovec variants to generic
  keep iocb_flags() result cached in struct file
  iocb: delay evaluation of IS_SYNC(...) until we want to check IOCB_DSYNC
  struct file: use anonymous union member for rcuhead and llist
  btrfs: use IOMAP_DIO_NOSYNC
  teach iomap_dio_rw() to suppress dsync
  No need of likely/unlikely on calls of check_copy_size()

10 files changed, 28 insertions, 40 deletions

diff --git a/fs/aio.c b/fs/aio.c
index a1911e86859c..606613e9d1f4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1475,7 +1475,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
 	req->ki_complete = aio_complete_rw;
 	req->private = NULL;
 	req->ki_pos = iocb->aio_offset;
-	req->ki_flags = iocb_flags(req->ki_filp);
+	req->ki_flags = req->ki_filp->f_iocb_flags;
 	if (iocb->aio_flags & IOCB_FLAG_RESFD)
 		req->ki_flags |= IOCB_EVENTFD;
 	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9dfde1af8a64..30e6aef9739f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1848,7 +1848,6 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
 
 static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	const bool is_sync_write = (iocb->ki_flags & IOCB_DSYNC);
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -1902,15 +1901,6 @@ relock:
 	}
 
 	/*
-	 * We remove IOCB_DSYNC so that we don't deadlock when iomap_dio_rw()
-	 * calls generic_write_sync() (through iomap_dio_complete()), because
-	 * that results in calling fsync (btrfs_sync_file()) which will try to
-	 * lock the inode in exclusive/write mode.
-	 */
-	if (is_sync_write)
-		iocb->ki_flags &= ~IOCB_DSYNC;
-
-	/*
 	 * The iov_iter can be mapped to the same file range we are writing to.
 	 * If that's the case, then we will deadlock in the iomap code, because
 	 * it first calls our callback btrfs_dio_iomap_begin(), which will create
@@ -1964,13 +1954,6 @@ again:
 
 	btrfs_inode_unlock(inode, ilock_flags);
 
-	/*
-	 * Add back IOCB_DSYNC. Our caller, btrfs_file_write_iter(), will do
-	 * the fsync (call generic_write_sync()).
-	 */
-	if (is_sync_write)
-		iocb->ki_flags |= IOCB_DSYNC;
-
 	/* If 'err' is -ENOTBLK then it means we must fallback to buffered IO. */
 	if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from))
 		goto out;
@@ -2038,7 +2021,7 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	struct file *file = iocb->ki_filp;
 	struct btrfs_inode *inode = BTRFS_I(file_inode(file));
 	ssize_t num_written, num_sync;
-	const bool sync = iocb->ki_flags & IOCB_DSYNC;
+	const bool sync = iocb_is_dsync(iocb);
 
 	/*
 	 * If the fs flips readonly due to some impossible error, although we
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 11a52db506b3..3867cb0646e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8165,7 +8165,8 @@ ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_befo
 	struct btrfs_dio_data data;
 
 	return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL, &data, done_before);
+			    IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC,
+			    &data, done_before);
 }
 
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 94b71440c332..df5e2d048799 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1216,7 +1216,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 */
 	if (dio->is_async && iov_iter_rw(iter) == WRITE) {
 		retval = 0;
-		if (iocb->ki_flags & IOCB_DSYNC)
+		if (iocb_is_dsync(iocb))
 			retval = dio_set_defer_completion(dio);
 		else if (!dio->inode->i_sb->s_dio_done_wq) {
 			/*
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 34a3faa4886d..146c9ab0cd4b 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -78,6 +78,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	}
 	spin_lock(&filp->f_lock);
 	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
+	filp->f_iocb_flags = iocb_flags(filp);
 	spin_unlock(&filp->f_lock);
 
  out:
diff --git a/fs/file_table.c b/fs/file_table.c
index 5727a63a7b67..99c6796c9f28 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -45,7 +45,7 @@ static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
 static void file_free_rcu(struct rcu_head *head)
 {
-	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
+	struct file *f = container_of(head, struct file, f_rcuhead);
 
 	put_cred(f->f_cred);
 	kmem_cache_free(filp_cachep, f);
@@ -56,7 +56,7 @@ static inline void file_free(struct file *f)
 	security_file_free(f);
 	if (!(f->f_mode & FMODE_NOACCOUNT))
 		percpu_counter_dec(&nr_files);
-	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
+	call_rcu(&f->f_rcuhead, file_free_rcu);
 }
 
 /*
@@ -142,7 +142,7 @@ static struct file *__alloc_file(int flags, const struct cred *cred)
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free_rcu(&f->f_u.fu_rcuhead);
+		file_free_rcu(&f->f_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -243,6 +243,7 @@ static struct file *alloc_file(const struct path *path, int flags,
 	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
 		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_iocb_flags = iocb_flags(file);
 	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
@@ -343,13 +344,13 @@ static void delayed_fput(struct work_struct *unused)
 	struct llist_node *node = llist_del_all(&delayed_fput_list);
 	struct file *f, *t;
 
-	llist_for_each_entry_safe(f, t, node, f_u.fu_llist)
+	llist_for_each_entry_safe(f, t, node, f_llist)
 		__fput(f);
 }
 
 static void ____fput(struct callback_head *work)
 {
-	__fput(container_of(work, struct file, f_u.fu_rcuhead));
+	__fput(container_of(work, struct file, f_rcuhead));
 }
 
 /*
@@ -376,8 +377,8 @@ void fput(struct file *file)
 		struct task_struct *task = current;
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
-			init_task_work(&file->f_u.fu_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME))
+			init_task_work(&file->f_rcuhead, ____fput);
+			if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),
@@ -386,7 +387,7 @@ void fput(struct file *file)
 			 */
 		}
 
-		if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
+		if (llist_add(&file->f_llist, &delayed_fput_list))
 			schedule_delayed_work(&delayed_fput_work, 1);
 	}
 }
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 05caa2b9272e..00fa861aeead 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1042,7 +1042,7 @@ static unsigned int fuse_write_flags(struct kiocb *iocb)
 {
 	unsigned int flags = iocb->ki_filp->f_flags;
 
-	if (iocb->ki_flags & IOCB_DSYNC)
+	if (iocb_is_dsync(iocb))
 		flags |= O_DSYNC;
 	if (iocb->ki_flags & IOCB_SYNC)
 		flags |= O_SYNC;
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 18a3d9357dce..c75d33d5c3ce 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -548,17 +548,18 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		}
 
 		/* for data sync or sync, we need sync completion processing */
-		if (iocb->ki_flags & IOCB_DSYNC)
+		if (iocb_is_dsync(iocb) && !(dio_flags & IOMAP_DIO_NOSYNC)) {
 			dio->flags |= IOMAP_DIO_NEED_SYNC;
 
-		/*
-		 * For datasync only writes, we optimistically try using FUA for
-		 * this IO.  Any non-FUA write that occurs will clear this flag,
-		 * hence we know before completion whether a cache flush is
-		 * necessary.
-		 */
-		if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC)
-			dio->flags |= IOMAP_DIO_WRITE_FUA;
+		       /*
+			* For datasync only writes, we optimistically try
+			* using FUA for this IO.  Any non-FUA write that
+			* occurs will clear this flag, hence we know before
+			* completion whether a cache flush is necessary.
+			*/
+			if (!(iocb->ki_flags & IOCB_SYNC))
+				dio->flags |= IOMAP_DIO_WRITE_FUA;
+		}
 	}
 
 	if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
diff --git a/fs/open.c b/fs/open.c
index 1177e8d1cf83..8a813fa5ca56 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -894,6 +894,7 @@ static int do_dentry_open(struct file *f,
 		f->f_mode |= FMODE_CAN_ODIRECT;
 
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
+	f->f_iocb_flags = iocb_flags(f);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index c5fa8adfb7a6..fcdc4bad95c5 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -779,7 +779,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 			REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS);
 	bio->bi_iter.bi_sector = zi->i_zsector;
 	bio->bi_ioprio = iocb->ki_ioprio;
-	if (iocb->ki_flags & IOCB_DSYNC)
+	if (iocb_is_dsync(iocb))
 		bio->bi_opf |= REQ_FUA;
 
 	ret = bio_iov_iter_get_pages(bio, from);