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()

arch/powerpc/include/asm/uaccess.h

@@ -348,7 +348,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned long size)
 static inline unsigned long __must_check
 copy_mc_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (likely(check_copy_size(from, n, true))) {
+	if (check_copy_size(from, n, true)) {
 		if (access_ok(to, n)) {
 			allow_write_to_user(to, n);
 			n = copy_mc_generic((void *)to, from, n);

arch/s390/include/asm/uaccess.h

@@ -39,7 +39,7 @@ _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned
 static __always_inline unsigned long __must_check
 copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key)
 {
-	if (likely(check_copy_size(to, n, false)))
+	if (check_copy_size(to, n, false))
 		n = _copy_from_user_key(to, from, n, key);
 	return n;
 }
@@ -50,7 +50,7 @@ _copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned l
 static __always_inline unsigned long __must_check
 copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned long key)
 {
-	if (likely(check_copy_size(from, n, true)))
+	if (check_copy_size(from, n, true))
 		n = _copy_to_user_key(to, from, n, key);
 	return n;
 }

block/fops.c

@@ -37,7 +37,7 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
 	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 
 	/* avoid the need for a I/O completion work item */
-	if (iocb->ki_flags & IOCB_DSYNC)
+	if (iocb_is_dsync(iocb))
 		opf |= REQ_FUA;
 	return opf;
 }

drivers/nvme/target/io-cmd-file.c

@@ -112,7 +112,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
-	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
+	iocb->ki_flags = ki_flags | iocb->ki_filp->f_iocb_flags;
 
 	return call_iter(iocb, &iter);
 }

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) {

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);
@@ -1901,15 +1900,6 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 		goto buffered;
 	}
 
-	/*
-	 * 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
@@ -1964,13 +1954,6 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 
 	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

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,

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) {
 			/*

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:

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);
 	}
 }

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;

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) {

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);
 

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);

include/linux/fs.h

@@ -943,9 +943,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 
 struct file {
 	union {
-		struct llist_node	fu_llist;
-		struct rcu_head 	fu_rcuhead;
-	} f_u;
+		struct llist_node	f_llist;
+		struct rcu_head 	f_rcuhead;
+		unsigned int 		f_iocb_flags;
+	};
 	struct path		f_path;
 	struct inode		*f_inode;	/* cached value */
 	const struct file_operations	*f_op;
@@ -2328,13 +2329,11 @@ static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns,
 	       !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode));
 }
 
-static inline int iocb_flags(struct file *file);
-
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
 		.ki_filp = filp,
-		.ki_flags = iocb_flags(filp),
+		.ki_flags = filp->f_iocb_flags,
 		.ki_ioprio = get_current_ioprio(),
 	};
 }
@@ -2850,6 +2849,12 @@ extern int vfs_fsync(struct file *file, int datasync);
 extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
 				unsigned int flags);
 
+static inline bool iocb_is_dsync(const struct kiocb *iocb)
+{
+	return (iocb->ki_flags & IOCB_DSYNC) ||
+		IS_SYNC(iocb->ki_filp->f_mapping->host);
+}
+
 /*
  * Sync the bytes written if this was a synchronous write.  Expect ki_pos
  * to already be updated for the write, and will return either the amount
@@ -2857,7 +2862,7 @@ extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
  */
 static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 {
-	if (iocb->ki_flags & IOCB_DSYNC) {
+	if (iocb_is_dsync(iocb)) {
 		int ret = vfs_fsync_range(iocb->ki_filp,
 				iocb->ki_pos - count, iocb->ki_pos - 1,
 				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
@@ -3380,7 +3385,7 @@ static inline int iocb_flags(struct file *file)
 		res |= IOCB_APPEND;
 	if (file->f_flags & O_DIRECT)
 		res |= IOCB_DIRECT;
-	if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
+	if (file->f_flags & O_DSYNC)
 		res |= IOCB_DSYNC;
 	if (file->f_flags & __O_SYNC)
 		res |= IOCB_SYNC;

include/linux/iomap.h

@@ -347,6 +347,12 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
+/*
+ * The caller will sync the write if needed; do not sync it within
+ * iomap_dio_rw.  Overrides IOMAP_DIO_FORCE_WAIT.
+ */
+#define IOMAP_DIO_NOSYNC		(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);

include/linux/uaccess.h

@@ -148,7 +148,7 @@ _copy_to_user(void __user *, const void *, unsigned long);
 static __always_inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (likely(check_copy_size(to, n, false)))
+	if (check_copy_size(to, n, false))
 		n = _copy_from_user(to, from, n);
 	return n;
 }
@@ -156,7 +156,7 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (likely(check_copy_size(from, n, true)))
+	if (check_copy_size(from, n, true))
 		n = _copy_to_user(to, from, n);
 	return n;
 }

include/linux/uio.h

@@ -156,19 +156,17 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset,
 static __always_inline __must_check
 size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(!check_copy_size(addr, bytes, true)))
-		return 0;
-	else
+	if (check_copy_size(addr, bytes, true))
 		return _copy_to_iter(addr, bytes, i);
+	return 0;
 }
 
 static __always_inline __must_check
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return 0;
-	else
+	if (check_copy_size(addr, bytes, false))
 		return _copy_from_iter(addr, bytes, i);
+	return 0;
 }
 
 static __always_inline __must_check
@@ -184,10 +182,9 @@ bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
 static __always_inline __must_check
 size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return 0;
-	else
+	if (check_copy_size(addr, bytes, false))
 		return _copy_from_iter_nocache(addr, bytes, i);
+	return 0;
 }
 
 static __always_inline __must_check

io_uring/rw.c

@@ -661,7 +661,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	if (!io_req_ffs_set(req))
 		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
 
-	kiocb->ki_flags = iocb_flags(file);
+	kiocb->ki_flags = file->f_iocb_flags;
 	ret = kiocb_set_rw_flags(kiocb, rw->flags);
 	if (unlikely(ret))
 		return ret;