From 4e857c58efeb99393cba5a5d0d8ec7117183137c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Mar 2014 18:06:10 +0100 Subject: arch: Mass conversion of smp_mb__*() Mostly scripted conversion of the smp_mb__* barriers. Signed-off-by: Peter Zijlstra Acked-by: Paul E. McKenney Link: http://lkml.kernel.org/n/tip-55dhyhocezdw1dg7u19hmh1u@git.kernel.org Cc: Linus Torvalds Cc: linux-arch@vger.kernel.org Signed-off-by: Ingo Molnar --- mm/filemap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index a82fbe4c9e8..c73535c914c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -740,7 +740,7 @@ void unlock_page(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); clear_bit_unlock(PG_locked, &page->flags); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_locked); } EXPORT_SYMBOL(unlock_page); @@ -757,7 +757,7 @@ void end_page_writeback(struct page *page) if (!test_clear_page_writeback(page)) BUG(); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); wake_up_page(page, PG_writeback); } EXPORT_SYMBOL(end_page_writeback); -- cgit v1.2.3-70-g09d2 From f8579f8673b7ecdb7a81d5d5bb1d981093d9aa94 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 3 Mar 2014 22:03:20 -0500 Subject: generic_file_direct_write(): switch to iov_iter Signed-off-by: Al Viro --- fs/btrfs/file.c | 6 ++---- fs/fuse/file.c | 6 ++---- fs/ocfs2/file.c | 6 +++--- fs/xfs/xfs_file.c | 5 +++-- include/linux/fs.h | 4 ++-- mm/filemap.c | 15 +++++++-------- 6 files changed, 19 insertions(+), 23 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ae6af072b63..9fe20c2052a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1669,15 +1669,13 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t endbyte; int err; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - count, ocount); + iov_iter_init(&i, iov, nr_segs, count, 0); + written = generic_file_direct_write(iocb, &i, pos, count, ocount); if (written < 0 || written == count) return written; pos += written; - count -= written; - iov_iter_init(&i, iov, nr_segs, count, written); written_buffered = __btrfs_buffered_write(file, &i, pos); if (written_buffered < 0) { err = written_buffered; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 96d513e01a5..126deb5d0a9 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1235,15 +1235,13 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, goto out; if (file->f_flags & O_DIRECT) { - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - count, ocount); + iov_iter_init(&i, iov, nr_segs, count, 0); + written = generic_file_direct_write(iocb, &i, pos, count, ocount); if (written < 0 || written == count) goto out; pos += written; - count -= written; - iov_iter_init(&i, iov, nr_segs, count, written); written_buffered = fuse_perform_write(file, mapping, &i, pos); if (written_buffered < 0) { err = written_buffered; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8970dcf74de..d6d78c2aa96 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2251,6 +2251,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); int unaligned_dio = 0; + struct iov_iter from; trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -2365,16 +2366,15 @@ relock: if (ret) goto out_dio; + iov_iter_init(&from, iov, nr_segs, count, 0); if (direct_io) { - written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos, + written = generic_file_direct_write(iocb, &from, *ppos, count, ocount); if (written < 0) { ret = written; goto out_dio; } } else { - struct iov_iter from; - iov_iter_init(&from, iov, nr_segs, count, 0); current->backing_dev_info = file->f_mapping->backing_dev_info; written = generic_perform_write(file, &from, *ppos); if (likely(written >= 0)) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 951a2321ee0..8617497867c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -641,6 +641,7 @@ xfs_file_dio_aio_write( int iolock; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; + struct iov_iter from; /* DIO must be aligned to device logical sector size */ if ((pos | count) & target->bt_logical_sectormask) @@ -698,8 +699,8 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); - ret = generic_file_direct_write(iocb, iovp, - &nr_segs, pos, count, ocount); + iov_iter_init(&from, iovp, nr_segs, count, 0); + ret = generic_file_direct_write(iocb, &from, pos, count, ocount); out: xfs_rw_iunlock(ip, iolock); diff --git a/include/linux/fs.h b/include/linux/fs.h index 878031227c5..262f96e579b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2407,8 +2407,8 @@ int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isbl extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, - unsigned long *, loff_t, size_t, size_t); +extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, + loff_t, size_t, size_t); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); diff --git a/mm/filemap.c b/mm/filemap.c index 000a220e2a4..a840890ed39 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2385,9 +2385,8 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, EXPORT_SYMBOL(pagecache_write_end); ssize_t -generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long *nr_segs, loff_t pos, - size_t count, size_t ocount) +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, + loff_t pos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -2397,9 +2396,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, pgoff_t end; if (count != ocount) - *nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count); + from->nr_segs = iov_shorten((struct iovec *)from->iov, from->nr_segs, count); - write_len = iov_length(iov, *nr_segs); + write_len = iov_length(from->iov, from->nr_segs); end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); @@ -2426,7 +2425,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, } } - written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs); + written = mapping->a_ops->direct_IO(WRITE, iocb, from->iov, pos, from->nr_segs); /* * Finally, try again to invalidate clean pages which might have been @@ -2443,6 +2442,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, if (written > 0) { pos += written; + iov_iter_advance(from, written); if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); @@ -2645,11 +2645,10 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos, + written = generic_file_direct_write(iocb, &from, pos, count, ocount); if (written < 0 || written == count) goto out; - iov_iter_advance(&from, written); /* * direct-io write to a hole: fall through to buffered I/O -- cgit v1.2.3-70-g09d2 From cb66a7a1f149ff705fa37cad6d1252b046e0ad4f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 4 Mar 2014 15:24:06 -0500 Subject: kill generic_segment_checks() all callers of ->aio_read() and ->aio_write() have iov/nr_segs already checked - generic_segment_checks() done after that is just an odd way to spell iov_length(). Signed-off-by: Al Viro --- drivers/staging/lustre/lustre/llite/file.c | 10 ++---- fs/btrfs/file.c | 7 +--- fs/ceph/file.c | 13 ++------ fs/fuse/file.c | 7 +--- fs/ntfs/file.c | 5 +-- fs/ocfs2/file.c | 7 +--- fs/xfs/xfs_file.c | 9 ++--- include/linux/fs.h | 2 -- mm/filemap.c | 53 ++---------------------------- mm/shmem.c | 7 ++-- 10 files changed, 16 insertions(+), 104 deletions(-) (limited to 'mm/filemap.c') diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c index 8e844a6371e..220bd8390a8 100644 --- a/drivers/staging/lustre/lustre/llite/file.c +++ b/drivers/staging/lustre/lustre/llite/file.c @@ -1180,9 +1180,7 @@ static ssize_t ll_file_aio_read(struct kiocb *iocb, const struct iovec *iov, ssize_t result; int refcheck; - result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (result) - return result; + count = iov_length(iov, nr_segs); env = cl_env_get(&refcheck); if (IS_ERR(env)) @@ -1235,14 +1233,10 @@ static ssize_t ll_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct lu_env *env; struct vvp_io_args *args; - size_t count = 0; + size_t count = iov_length(iov, nr_segs); ssize_t result; int refcheck; - result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (result) - return result; - env = cl_env_get(&refcheck); if (IS_ERR(env)) return PTR_ERR(env); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 1dafe0701da..a0a94a30d85 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1726,12 +1726,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, mutex_lock(&inode->i_mutex); - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) { - mutex_unlock(&inode->i_mutex); - goto out; - } - count = ocount; + count = ocount = iov_length(iov, nr_segs); current->backing_dev_info = inode->i_mapping->backing_dev_info; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ef9115e4a6f..21a56c27b74 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -828,12 +828,8 @@ again: inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); - if (!read) { - ret = generic_segment_checks(iov, &nr_segs, - &len, VERIFY_WRITE); - if (ret) - goto out; - } + if (!read) + len = iov_length(iov, nr_segs); iov_iter_init(&i, iov, nr_segs, len, read); @@ -855,7 +851,6 @@ again: ret = generic_file_aio_read(iocb, iov, nr_segs, pos); } -out: dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); ceph_put_cap_refs(ci, got); @@ -911,9 +906,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); - err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (err) - goto out; + count = iov_length(iov, nr_segs); /* We can write back this queue in page reclaim */ current->backing_dev_info = file->f_mapping->backing_dev_info; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 126deb5d0a9..9c7f346879e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1208,12 +1208,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, WARN_ON(iocb->ki_pos != pos); - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; + count = ocount = iov_length(iov, nr_segs); mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a3172..b6fa457d8d0 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2091,10 +2091,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, size_t count; /* after file limit checks */ ssize_t written, err; - count = 0; - err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (err) - return err; + count = iov_length(iov, nr_segs); pos = *ppos; /* We can write back this queue in page reclaim. */ current->backing_dev_info = mapping->backing_dev_info; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d6d78c2aa96..d33c4ced0ba 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2355,12 +2355,7 @@ relock: /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); - ret = generic_segment_checks(iov, &nr_segs, &ocount, - VERIFY_READ); - if (ret) - goto out_dio; - - count = ocount; + count = ocount = iov_length(iov, nr_segs); ret = generic_write_checks(file, ppos, &count, S_ISBLK(inode->i_mode)); if (ret) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 8617497867c..f0f8084a67b 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -253,9 +253,7 @@ xfs_file_aio_read( if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; - ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE); - if (ret < 0) - return ret; + size = iov_length(iovp, nr_segs); if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = @@ -777,10 +775,7 @@ xfs_file_aio_write( BUG_ON(iocb->ki_pos != pos); - ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ); - if (ret) - return ret; - + ocount = iov_length(iovp, nr_segs); if (ocount == 0) return 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index 262f96e579b..796de742fe4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2412,8 +2412,6 @@ 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); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -extern int generic_segment_checks(const struct iovec *iov, - unsigned long *nr_segs, size_t *count, int access_flags); /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, diff --git a/mm/filemap.c b/mm/filemap.c index a840890ed39..7c1417b0bd7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1663,45 +1663,6 @@ out: return written ? written : error; } -/* - * Performs necessary checks before doing a write - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @count: number of bytes to write - * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE - * - * Adjust number of segments and amount of bytes to write (nr_segs should be - * properly initialized first). Returns appropriate error code that caller - * should return or zero in case that write should be allowed. - */ -int generic_segment_checks(const struct iovec *iov, - unsigned long *nr_segs, size_t *count, int access_flags) -{ - unsigned long seg; - size_t cnt = 0; - for (seg = 0; seg < *nr_segs; seg++) { - const struct iovec *iv = &iov[seg]; - - /* - * If any segment has a negative length, or the cumulative - * length ever wraps negative then return -EINVAL. - */ - cnt += iv->iov_len; - if (unlikely((ssize_t)(cnt|iv->iov_len) < 0)) - return -EINVAL; - if (access_ok(access_flags, iv->iov_base, iv->iov_len)) - continue; - if (seg == 0) - return -EFAULT; - *nr_segs = seg; - cnt -= iv->iov_len; /* This segment is no good */ - break; - } - *count = cnt; - return 0; -} -EXPORT_SYMBOL(generic_segment_checks); - /** * generic_file_aio_read - generic filesystem read routine * @iocb: kernel I/O control block @@ -1717,15 +1678,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; - ssize_t retval; + ssize_t retval = 0; size_t count; loff_t *ppos = &iocb->ki_pos; struct iov_iter i; - count = 0; - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; + count = iov_length(iov, nr_segs); iov_iter_init(&i, iov, nr_segs, count, 0); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ @@ -2615,12 +2573,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t status; struct iov_iter from; - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; + count = ocount = iov_length(iov, nr_segs); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; diff --git a/mm/shmem.c b/mm/shmem.c index 9f70e02111c..2a93e625ada 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1412,14 +1412,11 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb, unsigned long offset; enum sgp_type sgp = SGP_READ; int error = 0; - ssize_t retval; - size_t count; + ssize_t retval = 0; + size_t count = iov_length(iov, nr_segs); loff_t *ppos = &iocb->ki_pos; struct iov_iter iter; - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; iov_iter_init(&iter, iov, nr_segs, count, 0); /* -- cgit v1.2.3-70-g09d2 From d8d3d94b80aa1a1c0ca75c58b8abdc7356f38418 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 4 Mar 2014 21:27:34 -0500 Subject: pass iov_iter to ->direct_IO() unmodified, for now Signed-off-by: Al Viro --- Documentation/filesystems/Locking | 3 +-- Documentation/filesystems/vfs.txt | 3 +-- drivers/staging/lustre/lustre/llite/rw26.c | 17 ++++++++--------- fs/9p/vfs_addr.c | 5 ++--- fs/block_dev.c | 9 +++++---- fs/btrfs/inode.c | 12 ++++++------ fs/ceph/addr.c | 4 ++-- fs/cifs/file.c | 4 ++-- fs/exofs/inode.c | 2 +- fs/ext2/inode.c | 11 ++++++----- fs/ext3/inode.c | 16 +++++++--------- fs/ext4/inode.c | 11 +++++------ fs/f2fs/data.c | 8 ++++---- fs/fat/inode.c | 13 +++++++------ fs/fuse/file.c | 10 +++++----- fs/gfs2/aops.c | 11 +++++------ fs/hfs/inode.c | 8 ++++---- fs/hfsplus/inode.c | 6 +++--- fs/jfs/inode.c | 8 ++++---- fs/nfs/direct.c | 8 ++++---- fs/nilfs2/inode.c | 10 +++++----- fs/ocfs2/aops.c | 7 +++---- fs/reiserfs/inode.c | 9 ++++----- fs/udf/file.c | 4 ++-- fs/udf/inode.c | 8 ++++---- fs/xfs/xfs_aops.c | 15 +++++++-------- include/linux/fs.h | 3 +-- include/linux/nfs_fs.h | 3 +-- mm/filemap.c | 9 ++++----- mm/page_io.c | 6 ++++-- 30 files changed, 117 insertions(+), 126 deletions(-) (limited to 'mm/filemap.c') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index eba79013425..9b0d5a33c8b 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -196,8 +196,7 @@ prototypes: void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - int (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); + int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); int (*migratepage)(struct address_space *, struct page *, struct page *); diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 617f6d70c07..1846374a5ad 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -589,8 +589,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); + ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); struct page* (*get_xip_page)(struct address_space *, sector_t, int); /* migrate the contents of a page to the specified target */ diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c index 7e3e0967993..66e05c6f4d2 100644 --- a/drivers/staging/lustre/lustre/llite/rw26.c +++ b/drivers/staging/lustre/lustre/llite/rw26.c @@ -363,15 +363,14 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io, #define MAX_DIO_SIZE ((MAX_MALLOC / sizeof(struct brw_page) * PAGE_CACHE_SIZE) & \ ~(DT_MAX_BRW_SIZE - 1)) static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t file_offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t file_offset) { struct lu_env *env; struct cl_io *io; struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ccc_object *obj = cl_inode2ccc(inode); - long count = iov_length(iov, nr_segs); + long count = iov_length(iter->iov, iter->nr_segs); long tot_bytes = 0, result = 0; struct ll_inode_info *lli = ll_i2info(inode); unsigned long seg = 0; @@ -392,9 +391,9 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb, MAX_DIO_SIZE >> PAGE_CACHE_SHIFT); /* Check that all user buffers are aligned as well */ - for (seg = 0; seg < nr_segs; seg++) { - if (((unsigned long)iov[seg].iov_base & ~CFS_PAGE_MASK) || - (iov[seg].iov_len & ~CFS_PAGE_MASK)) + for (seg = 0; seg < iter->nr_segs; seg++) { + if (((unsigned long)iter->iov[seg].iov_base & ~CFS_PAGE_MASK) || + (iter->iov[seg].iov_len & ~CFS_PAGE_MASK)) return -EINVAL; } @@ -411,9 +410,9 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb, mutex_lock(&inode->i_mutex); LASSERT(obj->cob_transient_pages == 0); - for (seg = 0; seg < nr_segs; seg++) { - long iov_left = iov[seg].iov_len; - unsigned long user_addr = (unsigned long)iov[seg].iov_base; + for (seg = 0; seg < iter->nr_segs; seg++) { + long iov_left = iter->iov[seg].iov_len; + unsigned long user_addr = (unsigned long)iter->iov[seg].iov_base; if (rw == READ) { if (file_offset >= i_size_read(inode)) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index c71e88602ff..cc1cfae726b 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -259,8 +259,7 @@ static int v9fs_launder_page(struct page *page) * */ static ssize_t -v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t pos, unsigned long nr_segs) +v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { /* * FIXME @@ -269,7 +268,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, */ p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n", iocb->ki_filp->f_path.dentry->d_name.name, - (long long)pos, nr_segs); + (long long)pos, iter->nr_segs); return -EINVAL; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 552a8d13bc3..938fc707d76 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -165,14 +165,15 @@ blkdev_get_block(struct inode *inode, sector_t iblock, } static ssize_t -blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset, - nr_segs, blkdev_get_block, NULL, NULL, 0); + return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter->iov, + offset, iter->nr_segs, blkdev_get_block, + NULL, NULL, 0); } int __sync_blockdev(struct block_device *bdev, int wait) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5f805bc944f..30a6cc51f32 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7433,8 +7433,7 @@ out: } static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -7444,8 +7443,8 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, bool relock = false; ssize_t ret; - if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov, - offset, nr_segs)) + if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter->iov, + offset, iter->nr_segs)) return 0; atomic_inc(&inode->i_dio_count); @@ -7457,7 +7456,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, * we need to flush the dirty pages again to make absolutely sure * that any outstanding dirty pages are on disk. */ - count = iov_length(iov, nr_segs); + count = iov_length(iter->iov, iter->nr_segs); if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) filemap_fdatawrite_range(inode->i_mapping, offset, count); @@ -7484,7 +7483,8 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, ret = __blockdev_direct_IO(rw, iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, - iov, offset, nr_segs, btrfs_get_blocks_direct, NULL, + iter->iov, offset, iter->nr_segs, + btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (rw & WRITE) { if (ret < 0 && ret != -EIOCBQUEUED) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b53278c9fd9..342ca5e423f 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1187,8 +1187,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, * never get called. */ static ssize_t ceph_direct_io(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t pos, unsigned long nr_segs) + struct iov_iter *iter, + loff_t pos) { WARN_ON(1); return -EINVAL; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2900d150654..a4ccc39e6c1 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3702,8 +3702,8 @@ void cifs_oplock_break(struct work_struct *work) * Direct IO is not yet supported in the cached mode. */ static ssize_t -cifs_direct_io(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t pos, unsigned long nr_segs) +cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t pos) { /* * FIXME diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index d1c244d6766..3f9cafd7393 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -964,7 +964,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset, /* TODO: Should be easy enough to do proprly */ static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { return 0; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b1d2a4675d4..47fbe760a7f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -850,18 +850,19 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) } static ssize_t -ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - ext2_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, ext2_get_block); if (ret < 0 && (rw & WRITE)) - ext2_write_failed(mapping, offset + iov_length(iov, nr_segs)); + ext2_write_failed(mapping, offset + + iov_length(iter->iov, iter->nr_segs)); return ret; } diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index f5157d0d1b4..7a5c501dc31 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1820,8 +1820,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * VFS code falls back into buffered path in that case so we are safe. */ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1829,10 +1828,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_length(iter->iov, iter->nr_segs); int retries = 0; - trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); + trace_ext3_direct_IO_enter(inode, offset, count, rw); if (rw == WRITE) { loff_t final_size = offset + count; @@ -1856,15 +1855,15 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } retry: - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - ext3_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, ext3_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) ext3_truncate_failed_direct_write(inode); @@ -1909,8 +1908,7 @@ retry: ret = err; } out: - trace_ext3_direct_IO_exit(inode, offset, - iov_length(iov, nr_segs), rw, ret); + trace_ext3_direct_IO_exit(inode, offset, count, rw, ret); return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7b7462a0e1..f51db730da3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3222,8 +3222,7 @@ retake_lock: } static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -3239,13 +3238,13 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_has_inline_data(inode)) return 0; - trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); + trace_ext4_direct_IO_enter(inode, offset, iov_length(iter->iov, iter->nr_segs), rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); + ret = ext4_ext_direct_IO(rw, iocb, iter->iov, offset, iter->nr_segs); else - ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + ret = ext4_ind_direct_IO(rw, iocb, iter->iov, offset, iter->nr_segs); trace_ext4_direct_IO_exit(inode, offset, - iov_length(iov, nr_segs), rw, ret); + iov_length(iter->iov, iter->nr_segs), rw, ret); return ret; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 45abd60e2bf..3a6ef121c09 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1010,7 +1010,7 @@ static int check_direct_IO(struct inode *inode, int rw, } static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1019,11 +1019,11 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, if (f2fs_has_inline_data(inode)) return 0; - if (check_direct_IO(inode, rw, iov, offset, nr_segs)) + if (check_direct_IO(inode, rw, iter->iov, offset, iter->nr_segs)) return 0; - return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - get_data_block); + return blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, get_data_block); } static void f2fs_invalidate_data_page(struct page *page, unsigned int offset, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index b3361fe2bcb..d5237a19905 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -185,8 +185,8 @@ static int fat_write_end(struct file *file, struct address_space *mapping, } static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -203,7 +203,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * * Return 0, and fallback to normal buffered write. */ - loff_t size = offset + iov_length(iov, nr_segs); + loff_t size = offset + iov_length(iter->iov, iter->nr_segs); if (MSDOS_I(inode)->mmu_private < size) return 0; } @@ -212,10 +212,11 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - fat_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, fat_get_block); if (ret < 0 && (rw & WRITE)) - fat_write_failed(mapping, offset + iov_length(iov, nr_segs)); + fat_write_failed(mapping, offset + + iov_length(iter->iov, iter->nr_segs)); return ret; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 9c7f346879e..17d96f36df1 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2890,8 +2890,8 @@ static inline loff_t fuse_round_up(loff_t off) } static ssize_t -fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { ssize_t ret = 0; struct file *file = iocb->ki_filp; @@ -2900,7 +2900,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_length(iter->iov, iter->nr_segs); struct fuse_io_priv *io; pos = offset; @@ -2944,9 +2944,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, io->async = false; if (rw == WRITE) - ret = __fuse_direct_write(io, iov, nr_segs, &pos); + ret = __fuse_direct_write(io, iter->iov, iter->nr_segs, &pos); else - ret = __fuse_direct_read(io, iov, nr_segs, &pos, count); + ret = __fuse_direct_read(io, iter->iov, iter->nr_segs, &pos, count); if (io->async) { fuse_aio_complete(io, ret < 0 ? ret : 0, -1); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index ce62dcac90b..e84ddaa4210 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1041,8 +1041,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset) static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1082,7 +1081,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, */ if (mapping->nrpages) { loff_t lstart = offset & (PAGE_CACHE_SIZE - 1); - loff_t len = iov_length(iov, nr_segs); + loff_t len = iov_length(iter->iov, iter->nr_segs); loff_t end = PAGE_ALIGN(offset + len) - 1; rv = 0; @@ -1097,9 +1096,9 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, truncate_inode_pages_range(mapping, lstart, end); } - rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, gfs2_get_block_direct, - NULL, NULL, 0); + rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, + iter->iov, offset, iter->nr_segs, + gfs2_get_block_direct, NULL, NULL, 0); out: gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9e2fecd62f6..09cff13528c 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -125,15 +125,15 @@ static int hfs_releasepage(struct page *page, gfp_t mask) } static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - hfs_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, hfs_get_block); /* * In case of error extending write may have instantiated a few @@ -141,7 +141,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + iov_length(iter->iov, iter->nr_segs); if (end > isize) hfs_write_failed(mapping, end); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index a4f45bd88a6..7f894a5b5ea 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -123,14 +123,14 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) } static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, hfsplus_get_block); /* @@ -139,7 +139,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + iov_length(iter->iov, iter->nr_segs); if (end > isize) hfsplus_write_failed(mapping, end); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 6f8fe72c2a7..7052744d510 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -331,15 +331,15 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block) } static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file->f_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - jfs_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, jfs_get_block); /* * In case of error extending write may have instantiated a few @@ -347,7 +347,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + iov_length(iter->iov, iter->nr_segs); if (end > isize) jfs_write_failed(mapping, end); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831..e9cde393500 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -121,20 +121,20 @@ static inline int put_dreq(struct nfs_direct_req *dreq) * shunt off direct read and write requests before the VFS gets them, * so this method is only ever called for swap. */ -ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) +ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", - iocb->ki_filp, (long long) pos, nr_segs); + iocb->ki_filp, (long long) pos, iter->nr_segs); return -EINVAL; #else VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); if (rw == READ || rw == KERNEL_READ) - return nfs_file_direct_read(iocb, iov, nr_segs, pos, + return nfs_file_direct_read(iocb, iter->iov, iter->nr_segs, pos, rw == READ ? true : false); - return nfs_file_direct_write(iocb, iov, nr_segs, pos, + return nfs_file_direct_write(iocb, iter->iov, iter->nr_segs, pos, rw == WRITE ? true : false); #endif /* CONFIG_NFS_SWAP */ } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b9c5726120e..1c0e8fedc09 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -298,8 +298,8 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, } static ssize_t -nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -310,8 +310,8 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, return 0; /* Needs synchronization with the cleaner */ - size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - nilfs_get_block); + size = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, nilfs_get_block); /* * In case of error extending write may have instantiated a few @@ -319,7 +319,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, */ if (unlikely((rw & WRITE) && size < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + iov_length(iter->iov, iter->nr_segs); if (end > isize) nilfs_write_failed(mapping, end); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index d310d12a9ad..799fd0afcb3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -599,9 +599,8 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait) static ssize_t ocfs2_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file)->i_mapping->host; @@ -618,7 +617,7 @@ static ssize_t ocfs2_direct_IO(int rw, return 0; return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, - iov, offset, nr_segs, + iter->iov, offset, iter->nr_segs, ocfs2_direct_IO_get_blocks, ocfs2_dio_end_io, NULL, 0); } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index bc8b8009897..17bf4c41a50 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3083,15 +3083,14 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) /* We thank Mingming Cao for helping us understand in great detail what to do in this section of the code. */ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - reiserfs_get_blocks_direct_io); + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, + iter->nr_segs, reiserfs_get_blocks_direct_io); /* * In case of error extending write may have instantiated a few @@ -3099,7 +3098,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + iov_length(iter->iov, iter->nr_segs); if ((end > isize) && inode_newsize_ok(inode, isize) == 0) { truncate_setsize(inode, isize); diff --git a/fs/udf/file.c b/fs/udf/file.c index d2c170f8b03..ade88640165 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -119,8 +119,8 @@ static int udf_adinicb_write_end(struct file *file, } static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { /* Fallback to buffered I/O. */ return 0; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5d643706212..5b184c7f7dc 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -217,18 +217,18 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, } static ssize_t udf_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, udf_get_block); if (unlikely(ret < 0 && (rw & WRITE))) - udf_write_failed(mapping, offset + iov_length(iov, nr_segs)); + udf_write_failed(mapping, offset + iov_length(iter->iov, iter->nr_segs)); return ret; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 0479c32c5eb..330d7b1c4be 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1449,9 +1449,8 @@ STATIC ssize_t xfs_vm_direct_IO( int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); @@ -1459,7 +1458,7 @@ xfs_vm_direct_IO( ssize_t ret; if (rw & WRITE) { - size_t size = iov_length(iov, nr_segs); + size_t size = iov_length(iter->iov, iter->nr_segs); /* * We cannot preallocate a size update transaction here as we @@ -1471,16 +1470,16 @@ xfs_vm_direct_IO( if (offset + size > XFS_I(inode)->i_d.di_size) ioend->io_isdirect = 1; - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter->iov, + offset, iter->nr_segs, xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); if (ret != -EIOCBQUEUED && iocb->private) goto out_destroy_ioend; } else { - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter->iov, + offset, iter->nr_segs, xfs_get_blocks_direct, NULL, NULL, 0); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 796de742fe4..399a338c92b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -343,8 +343,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); - ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); + ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); /* diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fa6918b0f82..5a0d78ec739 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -459,8 +459,7 @@ extern int nfs3_removexattr (struct dentry *, const char *name); /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, - unsigned long); +extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t); extern ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos, bool uio); diff --git a/mm/filemap.c b/mm/filemap.c index 7c1417b0bd7..139641274f1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1699,10 +1699,9 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); - if (!retval) { - retval = mapping->a_ops->direct_IO(READ, iocb, - iov, pos, nr_segs); - } + if (!retval) + retval = mapping->a_ops->direct_IO(READ, iocb, &i, pos); + if (retval > 0) { *ppos = pos + retval; count -= retval; @@ -2383,7 +2382,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, } } - written = mapping->a_ops->direct_IO(WRITE, iocb, from->iov, pos, from->nr_segs); + written = mapping->a_ops->direct_IO(WRITE, iocb, from, pos); /* * Finally, try again to invalidate clean pages which might have been diff --git a/mm/page_io.c b/mm/page_io.c index 7c59ef68138..0ed0644c73d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -263,16 +263,18 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, .iov_base = kmap(page), .iov_len = PAGE_SIZE, }; + struct iov_iter from; init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); kiocb.ki_nbytes = PAGE_SIZE; + iov_iter_init(&from, &iov, 1, PAGE_SIZE, 0); set_page_writeback(page); unlock_page(page); ret = mapping->a_ops->direct_IO(KERNEL_WRITE, - &kiocb, &iov, - kiocb.ki_pos, 1); + &kiocb, &from, + kiocb.ki_pos); kunmap(page); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); -- cgit v1.2.3-70-g09d2 From a6cbcd4a4a85e2fdb0b3344b88df2e8b3d526b9e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 4 Mar 2014 22:38:00 -0500 Subject: get rid of pointless iov_length() in ->direct_IO() all callers have iov_length(iter->iov, iter->nr_segs) == iov_iter_count(iter) Signed-off-by: Al Viro --- drivers/staging/lustre/lustre/llite/rw26.c | 2 +- fs/btrfs/inode.c | 2 +- fs/ext2/inode.c | 4 ++-- fs/ext3/inode.c | 2 +- fs/ext4/indirect.c | 2 +- fs/ext4/inode.c | 8 ++++---- fs/fat/inode.c | 6 +++--- fs/fuse/file.c | 2 +- fs/gfs2/aops.c | 2 +- fs/hfs/inode.c | 3 ++- fs/hfsplus/inode.c | 3 ++- fs/jfs/inode.c | 3 ++- fs/nfs/direct.c | 10 +++------- fs/nilfs2/inode.c | 3 ++- fs/reiserfs/inode.c | 3 ++- fs/udf/inode.c | 3 ++- fs/xfs/xfs_aops.c | 2 +- mm/filemap.c | 2 +- 18 files changed, 32 insertions(+), 30 deletions(-) (limited to 'mm/filemap.c') diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c index 66e05c6f4d2..38a5b580e7f 100644 --- a/drivers/staging/lustre/lustre/llite/rw26.c +++ b/drivers/staging/lustre/lustre/llite/rw26.c @@ -370,7 +370,7 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ccc_object *obj = cl_inode2ccc(inode); - long count = iov_length(iter->iov, iter->nr_segs); + long count = iov_iter_count(iter); long tot_bytes = 0, result = 0; struct ll_inode_info *lli = ll_i2info(inode); unsigned long seg = 0; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 30a6cc51f32..c46a025d0c4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7456,7 +7456,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, * we need to flush the dirty pages again to make absolutely sure * that any outstanding dirty pages are on disk. */ - count = iov_length(iter->iov, iter->nr_segs); + count = iov_iter_count(iter); if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) filemap_fdatawrite_range(inode->i_mapping, offset, count); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 47fbe760a7f..116e809aa7c 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -856,13 +856,13 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, ext2_get_block); if (ret < 0 && (rw & WRITE)) - ext2_write_failed(mapping, offset + - iov_length(iter->iov, iter->nr_segs)); + ext2_write_failed(mapping, offset + count); return ret; } diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 7a5c501dc31..8582ae2c80b 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1828,7 +1828,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); int retries = 0; trace_ext3_direct_IO_enter(inode, offset, count, rw); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index eb5ae16902d..123898a6af0 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -647,7 +647,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); int retries = 0; if (rw == WRITE) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 29996c1b673..2b993579a96 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3090,7 +3090,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - size_t count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); int overwrite = 0; get_block_t *get_block_func = NULL; int dio_flags = 0; @@ -3225,6 +3225,7 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; /* @@ -3237,13 +3238,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_has_inline_data(inode)) return 0; - trace_ext4_direct_IO_enter(inode, offset, iov_length(iter->iov, iter->nr_segs), rw); + trace_ext4_direct_IO_enter(inode, offset, count, rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_direct_IO(rw, iocb, iter, offset); else ret = ext4_ind_direct_IO(rw, iocb, iter, offset); - trace_ext4_direct_IO_exit(inode, offset, - iov_length(iter->iov, iter->nr_segs), rw, ret); + trace_ext4_direct_IO_exit(inode, offset, count, rw, ret); return ret; } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index d5237a19905..154a6f9d318 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -191,6 +191,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; if (rw == WRITE) { @@ -203,7 +204,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * * Return 0, and fallback to normal buffered write. */ - loff_t size = offset + iov_length(iter->iov, iter->nr_segs); + loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } @@ -215,8 +216,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, fat_get_block); if (ret < 0 && (rw & WRITE)) - fat_write_failed(mapping, offset + - iov_length(iter->iov, iter->nr_segs)); + fat_write_failed(mapping, offset + count); return ret; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 17d96f36df1..36f15f9c1de 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2900,7 +2900,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); struct fuse_io_priv *io; pos = offset; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index e84ddaa4210..228a12d2afa 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1081,7 +1081,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, */ if (mapping->nrpages) { loff_t lstart = offset & (PAGE_CACHE_SIZE - 1); - loff_t len = iov_length(iter->iov, iter->nr_segs); + loff_t len = iov_iter_count(iter); loff_t end = PAGE_ALIGN(offset + len) - 1; rv = 0; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 09cff13528c..dc69e8f3158 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -130,6 +130,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, @@ -141,7 +142,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iter->iov, iter->nr_segs); + loff_t end = offset + count; if (end > isize) hfs_write_failed(mapping, end); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 7f894a5b5ea..e6b1251af47 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -128,6 +128,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, @@ -139,7 +140,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iter->iov, iter->nr_segs); + loff_t end = offset + count; if (end > isize) hfsplus_write_failed(mapping, end); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 7052744d510..6cde5928693 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -336,6 +336,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, @@ -347,7 +348,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iter->iov, iter->nr_segs); + loff_t end = offset + count; if (end > isize) jfs_write_failed(mapping, end); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 21723149668..1d34f454989 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -486,9 +486,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; ssize_t result = -EINVAL; - size_t count; - - count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", @@ -877,7 +875,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, get_dreq(dreq); atomic_inc(&inode->i_dio_count); - NFS_I(dreq->inode)->write_io += iov_length(iter->iov, iter->nr_segs); + NFS_I(dreq->inode)->write_io += iov_iter_count(iter); for (seg = 0; seg < iter->nr_segs; seg++) { const struct iovec *vec = &iter->iov[seg]; result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio); @@ -936,9 +934,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; loff_t end; - size_t count; - - count = iov_length(iter->iov, iter->nr_segs); + size_t count = iov_iter_count(iter); end = (pos + count - 1) >> PAGE_CACHE_SHIFT; nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1c0e8fedc09..7aaf913e870 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -304,6 +304,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t size; if (rw == WRITE) @@ -319,7 +320,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely((rw & WRITE) && size < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iter->iov, iter->nr_segs); + loff_t end = offset + count; if (end > isize) nilfs_write_failed(mapping, end); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 17bf4c41a50..723affe921f 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3087,6 +3087,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, @@ -3098,7 +3099,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iter->iov, iter->nr_segs); + loff_t end = offset + count; if ((end > isize) && inode_newsize_ok(inode, isize) == 0) { truncate_setsize(inode, isize); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5b184c7f7dc..28984baf619 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -223,12 +223,13 @@ static ssize_t udf_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; ret = blockdev_direct_IO(rw, iocb, inode, iter->iov, offset, iter->nr_segs, udf_get_block); if (unlikely(ret < 0 && (rw & WRITE))) - udf_write_failed(mapping, offset + iov_length(iter->iov, iter->nr_segs)); + udf_write_failed(mapping, offset + count); return ret; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 330d7b1c4be..6462b318678 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1458,7 +1458,7 @@ xfs_vm_direct_IO( ssize_t ret; if (rw & WRITE) { - size_t size = iov_length(iter->iov, iter->nr_segs); + size_t size = iov_iter_count(iter); /* * We cannot preallocate a size update transaction here as we diff --git a/mm/filemap.c b/mm/filemap.c index 139641274f1..70c048ea36e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1698,7 +1698,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, goto out; /* skip atime */ size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, pos, - pos + iov_length(iov, nr_segs) - 1); + pos + count - 1); if (!retval) retval = mapping->a_ops->direct_IO(READ, iocb, &i, pos); -- cgit v1.2.3-70-g09d2 From 26978b8b4d83c46f4310b253db70fa9e65149e7c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 10 Mar 2014 14:08:45 -0400 Subject: give ->direct_IO() a copy of iov_iter the thing is, we want to advance what's given to ->direct_IO() as we are forming the request; however, the callers care about the amount of data actually transferred, not the amount we tried to transfer. It's more convenient to allow ->direct_IO() instances do use iov_iter_advance() on the copy of iov_iter, leaving the actual advancing of the original to caller. Signed-off-by: Al Viro --- mm/filemap.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 70c048ea36e..866f4ae8223 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1699,8 +1699,10 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, pos, pos + count - 1); - if (!retval) - retval = mapping->a_ops->direct_IO(READ, iocb, &i, pos); + if (!retval) { + struct iov_iter data = i; + retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos); + } if (retval > 0) { *ppos = pos + retval; @@ -2351,6 +2353,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, ssize_t written; size_t write_len; pgoff_t end; + struct iov_iter data; if (count != ocount) from->nr_segs = iov_shorten((struct iovec *)from->iov, from->nr_segs, count); @@ -2382,7 +2385,8 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, } } - written = mapping->a_ops->direct_IO(WRITE, iocb, from, pos); + data = *from; + written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos); /* * Finally, try again to invalidate clean pages which might have been -- cgit v1.2.3-70-g09d2 From ed978a811ec528dbe40243605c3afab55892f722 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 5 Mar 2014 22:53:04 -0500 Subject: new helper: generic_file_read_iter() iov_iter-using variant of generic_file_aio_read(). Some callers converted. Note that it's still not quite there for use as ->read_iter() - we depend on having zero iter->iov_offset in O_DIRECT case. Fortunately, that's true for all converted callers (and for generic_file_aio_read() itself). Signed-off-by: Al Viro --- fs/ceph/file.c | 15 +----------- fs/nfs/file.c | 2 +- include/linux/fs.h | 1 + mm/filemap.c | 67 +++++++++++++++++++++++++++--------------------------- 4 files changed, 37 insertions(+), 48 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d8f383d5944..910a3022eb2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -833,24 +833,11 @@ again: /* hmm, this isn't really async... */ ret = ceph_sync_read(iocb, &i, &checkeof); } else { - /* - * We can't modify the content of iov, - * so we only read from beginning. - * - * When we switch generic_file_aio_read() to iov_iter, the - * if () below will be removed -- AV - */ - if (read) { - iocb->ki_pos = pos; - len = iocb->ki_nbytes; - read = 0; - iov_iter_init(&i, iov, nr_segs, len, 0); - } dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n", inode, ceph_vinop(inode), pos, (unsigned)len, ceph_cap_string(got)); - ret = generic_file_aio_read(iocb, iov, nr_segs, pos); + ret = generic_file_read_iter(iocb, &i); } dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 3d01b152894..a352bc6d613 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -184,7 +184,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); if (!result) { - result = generic_file_aio_read(iocb, iov, nr_segs, pos); + result = generic_file_read_iter(iocb, &to); if (result > 0) nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 946a9484844..d096ebc7f34 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2404,6 +2404,7 @@ extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, unsigned long size, pgoff_t pgoff); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, diff --git a/mm/filemap.c b/mm/filemap.c index 866f4ae8223..a7f79e90209 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1663,55 +1663,34 @@ out: return written ? written : error; } -/** - * generic_file_aio_read - generic filesystem read routine - * @iocb: kernel I/O control block - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @pos: current file position - * - * This is the "read()" routine for all filesystems - * that can use the page cache directly. - */ ssize_t -generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct file *filp = iocb->ki_filp; + struct file *file = iocb->ki_filp; ssize_t retval = 0; - size_t count; loff_t *ppos = &iocb->ki_pos; - struct iov_iter i; - - count = iov_length(iov, nr_segs); - iov_iter_init(&i, iov, nr_segs, count, 0); + loff_t pos = *ppos; /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ - if (filp->f_flags & O_DIRECT) { + if (file->f_flags & O_DIRECT) { + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); loff_t size; - struct address_space *mapping; - struct inode *inode; - mapping = filp->f_mapping; - inode = mapping->host; if (!count) goto out; /* skip atime */ size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (!retval) { - struct iov_iter data = i; + struct iov_iter data = *iter; retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos); } if (retval > 0) { *ppos = pos + retval; - count -= retval; - /* - * If we did a short DIO read we need to skip the - * section of the iov that we've already read data into. - */ - iov_iter_advance(&i, retval); + iov_iter_advance(iter, retval); } /* @@ -1722,16 +1701,38 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, * and return. Otherwise fallthrough to buffered io for * the rest of the read. */ - if (retval < 0 || !count || *ppos >= size) { - file_accessed(filp); + if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) { + file_accessed(file); goto out; } } - retval = do_generic_file_read(filp, ppos, &i, retval); + retval = do_generic_file_read(file, ppos, iter, retval); out: return retval; } +EXPORT_SYMBOL(generic_file_read_iter); + +/** + * generic_file_aio_read - generic filesystem read routine + * @iocb: kernel I/O control block + * @iov: io vector request + * @nr_segs: number of segments in the iovec + * @pos: current file position + * + * This is the "read()" routine for all filesystems + * that can use the page cache directly. + */ +ssize_t +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + size_t count = iov_length(iov, nr_segs); + struct iov_iter i; + + iov_iter_init(&i, iov, nr_segs, count, 0); + return generic_file_read_iter(iocb, &i); +} EXPORT_SYMBOL(generic_file_aio_read); #ifdef CONFIG_MMU -- cgit v1.2.3-70-g09d2 From 71d8e532b1549a478e6a6a8a44f309d050294d00 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 5 Mar 2014 19:28:09 -0500 Subject: start adding the tag to iov_iter For now, just use the same thing we pass to ->direct_IO() - it's all iovec-based at the moment. Pass it explicitly to iov_iter_init() and account for kvec vs. iovec in there, by the same kludge NFS ->direct_IO() uses. Signed-off-by: Al Viro --- fs/btrfs/file.c | 2 +- fs/ceph/file.c | 8 ++++---- fs/cifs/file.c | 4 ++-- fs/fuse/file.c | 6 +++--- fs/nfs/file.c | 4 ++-- fs/ocfs2/file.c | 2 +- fs/pipe.c | 2 +- fs/splice.c | 2 +- fs/xfs/xfs_file.c | 4 ++-- include/linux/uio.h | 15 +++------------ mm/filemap.c | 4 ++-- mm/iov_iter.c | 15 +++++++++++++++ mm/page_io.c | 2 +- mm/process_vm_access.c | 4 ++-- mm/shmem.c | 2 +- 15 files changed, 41 insertions(+), 35 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a0a94a30d85..f8cee205618 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1740,7 +1740,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, goto out; } - iov_iter_init(&i, iov, nr_segs, count, 0); + iov_iter_init(&i, WRITE, iov, nr_segs, count); err = file_remove_suid(file); if (err) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 910a3022eb2..5b93cadedfb 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -582,7 +582,7 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE; - iov_iter_init(&i, iov, nr_segs, count, 0); + iov_iter_init(&i, WRITE, iov, nr_segs, count); while (iov_iter_count(&i) > 0) { void __user *data = i.iov->iov_base + i.iov_offset; @@ -703,7 +703,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov, CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ACK; - iov_iter_init(&i, iov, nr_segs, count, 0); + iov_iter_init(&i, WRITE, iov, nr_segs, count); while ((len = iov_iter_count(&i)) > 0) { size_t left; @@ -808,7 +808,7 @@ static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov, int checkeof = 0, read = 0; struct iov_iter i; - iov_iter_init(&i, iov, nr_segs, len, 0); + iov_iter_init(&i, READ, iov, nr_segs, len); again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", @@ -961,7 +961,7 @@ retry_snap: * are pending vmtruncate. So write and vmtruncate * can not run at the same time */ - iov_iter_init(&from, iov, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iov, nr_segs, count); written = generic_perform_write(file, &from, pos); if (likely(written >= 0)) iocb->ki_pos = pos + written; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a4ccc39e6c1..15201c21ac8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2424,7 +2424,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, else pid = current->tgid; - iov_iter_init(&it, iov, nr_segs, len, 0); + iov_iter_init(&it, WRITE, iov, nr_segs, len); do { size_t save_len; @@ -2854,7 +2854,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov, if (!len) return 0; - iov_iter_init(&to, iov, nr_segs, len, 0); + iov_iter_init(&to, READ, iov, nr_segs, len); INIT_LIST_HEAD(&rdata_list); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index fc54d04a41e..4a5519ca253 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1217,7 +1217,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; - iov_iter_init(&i, iov, nr_segs, count, 0); + iov_iter_init(&i, WRITE, iov, nr_segs, count); if (count == 0) goto out; @@ -1386,7 +1386,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, struct fuse_req *req; struct iov_iter ii; - iov_iter_init(&ii, iov, nr_segs, count, 0); + iov_iter_init(&ii, write ? WRITE : READ, iov, nr_segs, count); if (io->async) req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii)); @@ -2367,7 +2367,7 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov, if (!bytes) return 0; - iov_iter_init(&ii, iov, nr_segs, bytes, 0); + iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes); while (iov_iter_count(&ii)) { struct page *page = pages[page_idx++]; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index a352bc6d613..ead8f44f797 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -173,7 +173,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, ssize_t result; struct iov_iter to; - iov_iter_init(&to, iov, nr_segs, count, 0); + iov_iter_init(&to, READ, iov, nr_segs, count); if (iocb->ki_filp->f_flags & O_DIRECT) return nfs_file_direct_read(iocb, &to, pos, true); @@ -648,7 +648,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, ssize_t result; size_t count = iov_length(iov, nr_segs); struct iov_iter from; - iov_iter_init(&from, iov, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iov, nr_segs, count); result = nfs_key_timeout_notify(file, inode); if (result) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d33c4ced0ba..9ce9ed7615c 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2361,7 +2361,7 @@ relock: if (ret) goto out_dio; - iov_iter_init(&from, iov, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iov, nr_segs, count); if (direct_io) { written = generic_file_direct_write(iocb, &from, *ppos, count, ocount); diff --git a/fs/pipe.c b/fs/pipe.c index 034bffac3f9..cd4ccf07e77 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -287,7 +287,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, if (unlikely(total_len == 0)) return 0; - iov_iter_init(&iter, iov, nr_segs, total_len, 0); + iov_iter_init(&iter, READ, iov, nr_segs, total_len); do_wakeup = 0; ret = 0; diff --git a/fs/splice.c b/fs/splice.c index 9bc07d2b53c..f99e420744c 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1548,7 +1548,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov, if (ret <= 0) return ret; - iov_iter_init(&iter, iov, nr_segs, count, 0); + iov_iter_init(&iter, READ, iov, nr_segs, count); sd.len = 0; sd.total_len = count; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f0f8084a67b..762bb3e148a 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -697,7 +697,7 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); - iov_iter_init(&from, iovp, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iovp, nr_segs, count); ret = generic_file_direct_write(iocb, &from, pos, count, ocount); out: @@ -731,7 +731,7 @@ xfs_file_buffered_aio_write( if (ret) goto out; - iov_iter_init(&from, iovp, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iovp, nr_segs, count); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; diff --git a/include/linux/uio.h b/include/linux/uio.h index 4ee17413fe1..b80bbe197d1 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -20,6 +20,7 @@ struct kvec { }; struct iov_iter { + int type; const struct iovec *iov; unsigned long nr_segs; size_t iov_offset; @@ -68,18 +69,8 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); unsigned long iov_iter_alignment(const struct iov_iter *i); - -static inline void iov_iter_init(struct iov_iter *i, - const struct iovec *iov, unsigned long nr_segs, - size_t count, size_t written) -{ - i->iov = iov; - i->nr_segs = nr_segs; - i->iov_offset = 0; - i->count = count + written; - - iov_iter_advance(i, written); -} +void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, + unsigned long nr_segs, size_t count); static inline size_t iov_iter_count(struct iov_iter *i) { diff --git a/mm/filemap.c b/mm/filemap.c index a7f79e90209..3aeaf2df413 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1730,7 +1730,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, size_t count = iov_length(iov, nr_segs); struct iov_iter i; - iov_iter_init(&i, iov, nr_segs, count, 0); + iov_iter_init(&i, READ, iov, nr_segs, count); return generic_file_read_iter(iocb, &i); } EXPORT_SYMBOL(generic_file_aio_read); @@ -2596,7 +2596,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; - iov_iter_init(&from, iov, nr_segs, count, 0); + iov_iter_init(&from, WRITE, iov, nr_segs, count); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { diff --git a/mm/iov_iter.c b/mm/iov_iter.c index 2f762cc2108..e2c9a2db435 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -220,3 +220,18 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) return res; } EXPORT_SYMBOL(iov_iter_alignment); + +void iov_iter_init(struct iov_iter *i, int direction, + const struct iovec *iov, unsigned long nr_segs, + size_t count) +{ + /* It will get better. Eventually... */ + if (segment_eq(get_fs(), KERNEL_DS)) + direction |= REQ_KERNEL; + i->type = direction; + i->iov = iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_init); diff --git a/mm/page_io.c b/mm/page_io.c index 0ed0644c73d..313bfedb75d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -268,7 +268,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); kiocb.ki_nbytes = PAGE_SIZE; - iov_iter_init(&from, &iov, 1, PAGE_SIZE, 0); + iov_iter_init(&from, KERNEL_WRITE, &iov, 1, PAGE_SIZE); set_page_writeback(page); unlock_page(page); diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index f32b1fbbfe6..5077afcd9e1 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -274,7 +274,7 @@ static ssize_t process_vm_rw(pid_t pid, if (rc <= 0) goto free_iovecs; - iov_iter_init(&iter, iov_l, liovcnt, rc, 0); + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); @@ -337,7 +337,7 @@ compat_process_vm_rw(compat_pid_t pid, &iov_l); if (rc <= 0) goto free_iovecs; - iov_iter_init(&iter, iov_l, liovcnt, rc, 0); + iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); diff --git a/mm/shmem.c b/mm/shmem.c index 2a93e625ada..e0b76696c3f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1417,7 +1417,7 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb, loff_t *ppos = &iocb->ki_pos; struct iov_iter iter; - iov_iter_init(&iter, iov, nr_segs, count, 0); + iov_iter_init(&iter, READ, iov, nr_segs, count); /* * Might this read be for a stacking filesystem? Then when reading -- cgit v1.2.3-70-g09d2 From 0c949334a9e2581646c6ff0d1470a805b1e5be99 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Mar 2014 06:51:37 -0400 Subject: iov_iter_truncate() Now It Can Be Done(tm) - we don't need to do iov_shorten() in generic_file_direct_write() anymore, now that all ->direct_IO() instances are converted to proper iov_iter methods and honour iter->count and iter->iov_offset properly. Get rid of count/ocount arguments of generic_file_direct_write(), while we are at it. Signed-off-by: Al Viro --- fs/btrfs/file.c | 17 ++++++++--------- fs/fuse/file.c | 18 ++++++++---------- fs/ocfs2/file.c | 10 +++++----- fs/xfs/xfs_file.c | 9 +++++---- include/linux/fs.h | 3 +-- include/linux/uio.h | 6 ++++++ mm/filemap.c | 19 +++++++------------ 7 files changed, 40 insertions(+), 42 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f8cee205618..ea63a51c148 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1659,8 +1659,7 @@ again: static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from, - loff_t pos, - size_t count, size_t ocount) + loff_t pos) { struct file *file = iocb->ki_filp; ssize_t written; @@ -1668,9 +1667,9 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t endbyte; int err; - written = generic_file_direct_write(iocb, from, pos, count, ocount); + written = generic_file_direct_write(iocb, from, pos); - if (written < 0 || written == count) + if (written < 0 || !iov_iter_count(from)) return written; pos += written; @@ -1720,13 +1719,14 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, u64 end_pos; ssize_t num_written = 0; ssize_t err = 0; - size_t count, ocount; + size_t count; bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); struct iov_iter i; mutex_lock(&inode->i_mutex); - count = ocount = iov_length(iov, nr_segs); + count = iov_length(iov, nr_segs); + iov_iter_init(&i, WRITE, iov, nr_segs, count); current->backing_dev_info = inode->i_mapping->backing_dev_info; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); @@ -1740,7 +1740,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, goto out; } - iov_iter_init(&i, WRITE, iov, nr_segs, count); + iov_iter_truncate(&i, count); err = file_remove_suid(file); if (err) { @@ -1783,8 +1783,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, atomic_inc(&BTRFS_I(inode)->sync_writers); if (unlikely(file->f_flags & O_DIRECT)) { - num_written = __btrfs_direct_write(iocb, &i, - pos, count, ocount); + num_written = __btrfs_direct_write(iocb, &i, pos); } else { num_written = __btrfs_buffered_write(file, &i, pos); if (num_written > 0) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 7026014717b..66d2d5de19d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1188,8 +1188,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - size_t count = 0; - size_t ocount = 0; + size_t count; ssize_t written = 0; ssize_t written_buffered = 0; struct inode *inode = mapping->host; @@ -1208,7 +1207,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, WARN_ON(iocb->ki_pos != pos); - count = ocount = iov_length(iov, nr_segs); + count = iov_length(iov, nr_segs); + iov_iter_init(&i, WRITE, iov, nr_segs, count); mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ @@ -1217,11 +1217,11 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; - iov_iter_init(&i, WRITE, iov, nr_segs, count); if (count == 0) goto out; + iov_iter_truncate(&i, count); err = file_remove_suid(file); if (err) goto out; @@ -1231,8 +1231,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, goto out; if (file->f_flags & O_DIRECT) { - written = generic_file_direct_write(iocb, &i, pos, count, ocount); - if (written < 0 || written == count) + written = generic_file_direct_write(iocb, &i, pos); + if (written < 0 || !iov_iter_count(&i)) goto out; pos += written; @@ -1469,8 +1469,7 @@ static ssize_t __fuse_direct_write(struct fuse_io_priv *io, res = generic_write_checks(file, ppos, &count, 0); if (!res) { - if (iter->count > count) - iter->count = count; + iov_iter_truncate(iter, count); res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE); } @@ -2896,8 +2895,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, if (offset >= i_size) return 0; count = min_t(loff_t, count, fuse_round_up(i_size - offset)); - if (iter->count > count) - iter->count = count; + iov_iter_truncate(iter, count); } io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9ce9ed7615c..06b6a16d977 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2241,7 +2241,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, int ret, direct_io, appending, rw_level, have_alloc_sem = 0; int can_do_direct, has_refcount = 0; ssize_t written = 0; - size_t ocount; /* original count */ size_t count; /* after file limit checks */ loff_t old_size, *ppos = &iocb->ki_pos; u32 old_clusters; @@ -2253,6 +2252,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, int unaligned_dio = 0; struct iov_iter from; + count = iov_length(iov, nr_segs); + iov_iter_init(&from, WRITE, iov, nr_segs, count); + trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, file->f_path.dentry->d_name.len, @@ -2355,16 +2357,14 @@ relock: /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); - count = ocount = iov_length(iov, nr_segs); ret = generic_write_checks(file, ppos, &count, S_ISBLK(inode->i_mode)); if (ret) goto out_dio; - iov_iter_init(&from, WRITE, iov, nr_segs, count); + iov_iter_truncate(&from, count); if (direct_io) { - written = generic_file_direct_write(iocb, &from, *ppos, - count, ocount); + written = generic_file_direct_write(iocb, &from, *ppos); if (written < 0) { ret = written; goto out_dio; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 762bb3e148a..c997aa2751b 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -626,7 +626,7 @@ xfs_file_dio_aio_write( const struct iovec *iovp, unsigned long nr_segs, loff_t pos, - size_t ocount) + size_t count) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -634,7 +634,6 @@ xfs_file_dio_aio_write( struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0; - size_t count = ocount; int unaligned_io = 0; int iolock; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? @@ -645,6 +644,8 @@ xfs_file_dio_aio_write( if ((pos | count) & target->bt_logical_sectormask) return -XFS_ERROR(EINVAL); + iov_iter_init(&from, WRITE, iovp, nr_segs, count); + /* "unaligned" here means not aligned to a filesystem block */ if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask)) unaligned_io = 1; @@ -676,6 +677,7 @@ xfs_file_dio_aio_write( ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); if (ret) goto out; + iov_iter_truncate(&from, count); if (mapping->nrpages) { ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, @@ -697,8 +699,7 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); - iov_iter_init(&from, WRITE, iovp, nr_segs, count); - ret = generic_file_direct_write(iocb, &from, pos, count, ocount); + ret = generic_file_direct_write(iocb, &from, pos); out: xfs_rw_iunlock(ip, iolock); diff --git a/include/linux/fs.h b/include/linux/fs.h index d096ebc7f34..8153396d19b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2407,8 +2407,7 @@ extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsig extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, - loff_t, size_t, size_t); +extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); diff --git a/include/linux/uio.h b/include/linux/uio.h index 4876e9f2a58..532f59d0adb 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -82,6 +82,12 @@ static inline size_t iov_iter_count(struct iov_iter *i) return i->count; } +static inline void iov_iter_truncate(struct iov_iter *i, size_t count) +{ + if (i->count > count) + i->count = count; +} + int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); diff --git a/mm/filemap.c b/mm/filemap.c index 3aeaf2df413..c0404b763a1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2345,8 +2345,7 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, EXPORT_SYMBOL(pagecache_write_end); ssize_t -generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, - loff_t pos, size_t count, size_t ocount) +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -2356,10 +2355,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, pgoff_t end; struct iov_iter data; - if (count != ocount) - from->nr_segs = iov_shorten((struct iovec *)from->iov, from->nr_segs, count); - - write_len = iov_length(from->iov, from->nr_segs); + write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); @@ -2568,7 +2564,6 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; - size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; @@ -2577,7 +2572,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t status; struct iov_iter from; - count = ocount = iov_length(iov, nr_segs); + count = iov_length(iov, nr_segs); + iov_iter_init(&from, WRITE, iov, nr_segs, count); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; @@ -2588,6 +2584,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(&from, count); + err = file_remove_suid(file); if (err) goto out; @@ -2596,14 +2594,11 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; - iov_iter_init(&from, WRITE, iov, nr_segs, count); - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - written = generic_file_direct_write(iocb, &from, pos, - count, ocount); + written = generic_file_direct_write(iocb, &from, pos); if (written < 0 || written == count) goto out; -- cgit v1.2.3-70-g09d2 From 8174202b34c30e0c07231bf63f18ab29af634f0b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 3 Apr 2014 03:17:43 -0400 Subject: write_iter variants of {__,}generic_file_aio_write() Signed-off-by: Al Viro --- fs/9p/vfs_file.c | 8 +++---- fs/adfs/file.c | 4 ++-- fs/affs/file.c | 4 ++-- fs/bfs/file.c | 4 ++-- fs/ecryptfs/file.c | 4 ++-- fs/exofs/file.c | 4 ++-- fs/ext2/file.c | 4 ++-- fs/ext3/file.c | 4 ++-- fs/f2fs/file.c | 4 ++-- fs/fat/file.c | 4 ++-- fs/hfs/inode.c | 4 ++-- fs/hfsplus/inode.c | 4 ++-- fs/hostfs/hostfs_kern.c | 4 ++-- fs/hpfs/file.c | 4 ++-- fs/jffs2/file.c | 4 ++-- fs/jfs/file.c | 4 ++-- fs/logfs/file.c | 4 ++-- fs/minix/file.c | 4 ++-- fs/nilfs2/file.c | 4 ++-- fs/omfs/file.c | 4 ++-- fs/ramfs/file-mmu.c | 4 ++-- fs/ramfs/file-nommu.c | 4 ++-- fs/reiserfs/file.c | 4 ++-- fs/sysv/file.c | 4 ++-- fs/ufs/file.c | 4 ++-- include/linux/fs.h | 2 ++ mm/filemap.c | 61 ++++++++++++++++++++++++++++++------------------- mm/shmem.c | 4 ++-- mm/vmscan.c | 2 +- 29 files changed, 94 insertions(+), 79 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 47e0597d1e9..b9b5f979a2c 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -763,7 +763,7 @@ err_out: buff_write: mutex_unlock(&inode->i_mutex); - return do_sync_write(filp, data, count, offsetp); + return new_sync_write(filp, data, count, offsetp); } /** @@ -781,7 +781,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, if (filp->f_flags & O_DIRECT) return v9fs_direct_write(filp, data, count, offset); - return do_sync_write(filp, data, count, offset); + return new_sync_write(filp, data, count, offset); } @@ -851,7 +851,7 @@ const struct file_operations v9fs_cached_file_operations = { .read = v9fs_cached_file_read, .write = v9fs_cached_file_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, @@ -864,7 +864,7 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .read = v9fs_cached_file_read, .write = v9fs_cached_file_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock_dotl, diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 3bfc9efa29b..07c9edce5aa 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -27,8 +27,8 @@ const struct file_operations adfs_file_operations = { .read_iter = generic_file_read_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .splice_read = generic_file_splice_read, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 982853f17af..9df23175e28 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -29,8 +29,8 @@ const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = affs_file_open, .release = affs_file_release, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 0aa788892f9..e7f88ace1a2 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -25,8 +25,8 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, }; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b32827c917e..db0fad3269c 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -353,8 +353,8 @@ const struct file_operations ecryptfs_main_fops = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = ecryptfs_read_update_atime, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .iterate = ecryptfs_readdir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 90d394da747..5b7f6be5a2d 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -68,9 +68,9 @@ static int exofs_flush(struct file *file, fl_owner_t id) const struct file_operations exofs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = generic_file_open, .release = exofs_release_file, diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 40730507259..970c6aca15c 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -63,9 +63,9 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 5439d2f0141..c833b1226d4 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -51,9 +51,9 @@ static int ext3_release_file (struct inode * inode, struct file * filp) const struct file_operations ext3_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .unlocked_ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0e01fb0bc97..22f4900dd8e 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -680,9 +680,9 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .open = generic_file_open, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, diff --git a/fs/fat/file.c b/fs/fat/file.c index 29285e990c9..85f79a89e74 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -171,9 +171,9 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = fat_file_release, .unlocked_ioctl = fat_generic_ioctl, diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 6d4055aff10..d0929bc8178 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -676,8 +676,8 @@ static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, .fsync = hfs_file_fsync, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index cccc89e47cb..0cf786f2d04 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -343,8 +343,8 @@ static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, .fsync = hfsplus_file_fsync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index ce0005d8ffe..bb529f3b7f2 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -381,8 +381,8 @@ static const struct file_operations hostfs_file_fops = { .read = new_sync_read, .splice_read = generic_file_splice_read, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, - .write = do_sync_write, + .write_iter = generic_file_write_iter, + .write = new_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, .release = hostfs_file_release, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index bacb478a499..7f54e5f76ce 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -199,8 +199,8 @@ const struct file_operations hpfs_file_ops = .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 9192127d591..64989ca9ba9 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -53,8 +53,8 @@ const struct file_operations jffs2_file_operations = .open = generic_file_open, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .unlocked_ioctl=jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index a5d8299b220..cc744ecaf51 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -151,10 +151,10 @@ const struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = do_sync_write, + .write = new_sync_write, .read = new_sync_read, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 1ca8026dc66..8538752df2f 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -265,14 +265,14 @@ const struct inode_operations logfs_reg_iops = { const struct file_operations logfs_reg_fops = { .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .fsync = logfs_fsync, .unlocked_ioctl = logfs_ioctl, .llseek = generic_file_llseek, .mmap = generic_file_readonly_mmap, .open = generic_file_open, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, }; const struct address_space_operations logfs_reg_aops = { diff --git a/fs/minix/file.c b/fs/minix/file.c index 607b4714532..a967de085ac 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -16,8 +16,8 @@ const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index dcb1b0e8b43..24978153c0c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -153,9 +153,9 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) const struct file_operations nilfs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .unlocked_ioctl = nilfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = nilfs_compat_ioctl, diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 3bf28da9f0d..902e88527fc 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -338,9 +338,9 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block) const struct file_operations omfs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 30ffb367bc0..6ea0b9718a9 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -33,8 +33,8 @@ const struct file_operations ramfs_file_operations = { .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = noop_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 416db04f846..9ed420f8f3c 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -39,8 +39,8 @@ const struct file_operations ramfs_file_operations = { .get_unmapped_area = ramfs_nommu_get_unmapped_area, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 7592d681fd8..7c8ecd6468d 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -236,7 +236,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, const struct file_operations reiserfs_file_operations = { .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, @@ -246,7 +246,7 @@ const struct file_operations reiserfs_file_operations = { .release = reiserfs_file_release, .fsync = reiserfs_sync_file, .read_iter = generic_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, .llseek = generic_file_llseek, diff --git a/fs/sysv/file.c b/fs/sysv/file.c index d99be887738..b00811c75b2 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -23,8 +23,8 @@ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/ufs/file.c b/fs/ufs/file.c index b6b402989e6..c84ec010a67 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -37,8 +37,8 @@ const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, .read = new_sync_read, .read_iter = generic_file_read_iter, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = generic_file_open, .fsync = generic_file_fsync, diff --git a/include/linux/fs.h b/include/linux/fs.h index 17535e0a454..4b221637f09 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2414,7 +2414,9 @@ int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isbl extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); +extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); diff --git a/mm/filemap.c b/mm/filemap.c index c0404b763a1..d2d9eeec8bf 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2542,10 +2542,9 @@ again: EXPORT_SYMBOL(generic_perform_write); /** - * __generic_file_aio_write - write data to a file + * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) - * @iov: vector with data to write - * @nr_segs: number of segments in the vector + * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates @@ -2559,21 +2558,16 @@ EXPORT_SYMBOL(generic_perform_write); * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. */ -ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs) +ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; - size_t count; /* after file limit checks */ struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written = 0; ssize_t err; ssize_t status; - struct iov_iter from; - - count = iov_length(iov, nr_segs); - iov_iter_init(&from, WRITE, iov, nr_segs, count); + size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; @@ -2584,7 +2578,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - iov_iter_truncate(&from, count); + iov_iter_truncate(from, count); err = file_remove_suid(file); if (err) @@ -2598,7 +2592,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - written = generic_file_direct_write(iocb, &from, pos); + written = generic_file_direct_write(iocb, from, pos); if (written < 0 || written == count) goto out; @@ -2609,7 +2603,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos += written; count -= written; - status = generic_perform_write(file, &from, pos); + status = generic_perform_write(file, from, pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were @@ -2641,7 +2635,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, */ } } else { - written = generic_perform_write(file, &from, pos); + written = generic_perform_write(file, from, pos); if (likely(written >= 0)) iocb->ki_pos = pos + written; } @@ -2649,30 +2643,36 @@ out: current->backing_dev_info = NULL; return written ? written : err; } +EXPORT_SYMBOL(__generic_file_write_iter); + +ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs) +{ + size_t count = iov_length(iov, nr_segs); + struct iov_iter from; + + iov_iter_init(&from, WRITE, iov, nr_segs, count); + return __generic_file_write_iter(iocb, &from); +} EXPORT_SYMBOL(__generic_file_aio_write); /** - * generic_file_aio_write - write data to a file + * generic_file_write_iter - write data to a file * @iocb: IO state structure - * @iov: vector with data to write - * @nr_segs: number of segments in the vector - * @pos: position in file where to write + * @from: iov_iter with data to write * - * This is a wrapper around __generic_file_aio_write() to be used by most + * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. */ -ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - BUG_ON(iocb->ki_pos != pos); - mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write(iocb, iov, nr_segs); + ret = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (ret > 0) { @@ -2684,6 +2684,19 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } return ret; } +EXPORT_SYMBOL(generic_file_write_iter); + +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + size_t count = iov_length(iov, nr_segs); + struct iov_iter from; + + BUG_ON(iocb->ki_pos != pos); + + iov_iter_init(&from, WRITE, iov, nr_segs, count); + return generic_file_write_iter(iocb, &from); +} EXPORT_SYMBOL(generic_file_aio_write); /** diff --git a/mm/shmem.c b/mm/shmem.c index edc6c7e817e..d3e5c6fc313 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2618,9 +2618,9 @@ static const struct file_operations shmem_file_operations = { #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read = new_sync_read, - .write = do_sync_write, + .write = new_sync_write, .read_iter = shmem_file_read_iter, - .aio_write = generic_file_aio_write, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = shmem_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/mm/vmscan.c b/mm/vmscan.c index 32c661d66a4..9c2dba6ac68 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -458,7 +458,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * stalls if we need to run get_block(). We could test * PagePrivate for that. * - * If this process is currently in __generic_file_aio_write() against + * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * -- cgit v1.2.3-70-g09d2 From a8f3550cd228b6edc5d17fce1a9af8cc7004f185 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 3 Apr 2014 03:32:25 -0400 Subject: bury __generic_file_aio_write() all users converted to __generic_file_write_iter() now Signed-off-by: Al Viro --- include/linux/fs.h | 1 - mm/filemap.c | 11 ----------- 2 files changed, 12 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1b9b6c59abd..99817c9e665 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2413,7 +2413,6 @@ extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); -extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index d2d9eeec8bf..7dcdb9db710 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2645,17 +2645,6 @@ out: } EXPORT_SYMBOL(__generic_file_write_iter); -ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs) -{ - size_t count = iov_length(iov, nr_segs); - struct iov_iter from; - - iov_iter_init(&from, WRITE, iov, nr_segs, count); - return __generic_file_write_iter(iocb, &from); -} -EXPORT_SYMBOL(__generic_file_aio_write); - /** * generic_file_write_iter - write data to a file * @iocb: IO state structure -- cgit v1.2.3-70-g09d2 From 6abd232274fd652e4a57f486d14e52ffee6f72e9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 4 Apr 2014 14:20:57 -0400 Subject: bury generic_file_aio_{read,write} no callers left Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- mm/filemap.c | 43 ++++++++----------------------------------- 2 files changed, 8 insertions(+), 37 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 99817c9e665..a6448849dbc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2411,10 +2411,8 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, unsigned long size, pgoff_t pgoff); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); 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_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); diff --git a/mm/filemap.c b/mm/filemap.c index 7dcdb9db710..2f724e3cdf2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1663,6 +1663,14 @@ out: return written ? written : error; } +/** + * generic_file_read_iter - generic filesystem read routine + * @iocb: kernel I/O control block + * @iter: destination for the data read + * + * This is the "read_iter()" routine for all filesystems + * that can use the page cache directly. + */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { @@ -1713,28 +1721,6 @@ out: } EXPORT_SYMBOL(generic_file_read_iter); -/** - * generic_file_aio_read - generic filesystem read routine - * @iocb: kernel I/O control block - * @iov: io vector request - * @nr_segs: number of segments in the iovec - * @pos: current file position - * - * This is the "read()" routine for all filesystems - * that can use the page cache directly. - */ -ssize_t -generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - size_t count = iov_length(iov, nr_segs); - struct iov_iter i; - - iov_iter_init(&i, READ, iov, nr_segs, count); - return generic_file_read_iter(iocb, &i); -} -EXPORT_SYMBOL(generic_file_aio_read); - #ifdef CONFIG_MMU /** * page_cache_read - adds requested page to the page cache if not already there @@ -2675,19 +2661,6 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) } EXPORT_SYMBOL(generic_file_write_iter); -ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - size_t count = iov_length(iov, nr_segs); - struct iov_iter from; - - BUG_ON(iocb->ki_pos != pos); - - iov_iter_init(&from, WRITE, iov, nr_segs, count); - return generic_file_write_iter(iocb, &from); -} -EXPORT_SYMBOL(generic_file_aio_write); - /** * try_to_release_page() - release old fs-specific metadata on a page * -- cgit v1.2.3-70-g09d2 From 7fcbbaf18392f0b17c95e2f033c8ccf87eecde1d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 May 2014 11:54:16 -0700 Subject: mm/filemap.c: avoid always dirtying mapping->flags on O_DIRECT In some testing I ran today (some fio jobs that spread over two nodes), we end up spending 40% of the time in filemap_check_errors(). That smells fishy. Looking further, this is basically what happens: blkdev_aio_read() generic_file_aio_read() filemap_write_and_wait_range() if (!mapping->nr_pages) filemap_check_errors() and filemap_check_errors() always attempts two test_and_clear_bit() on the mapping flags, thus dirtying it for every single invocation. The patch below tests each of these bits before clearing them, avoiding this issue. In my test case (4-socket box), performance went from 1.7M IOPS to 4.0M IOPS. Signed-off-by: Jens Axboe Acked-by: Jeff Moyer Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 000a220e2a4..088358c8006 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -257,9 +257,11 @@ static int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } -- cgit v1.2.3-70-g09d2 From 57d998456ae8680ed446aa1993f45f4d8a9a5973 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:45 -0700 Subject: fs/mpage.c: factor page_endio() out of mpage_end_io() page_endio() takes care of updating all the appropriate page flags once I/O has finished to a page. Switch to using mapping_set_error() instead of setting AS_EIO directly; this will handle thin-provisioned devices correctly. Signed-off-by: Matthew Wilcox Cc: Dave Chinner Cc: Dheeraj Reddy Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mpage.c | 18 +----------------- include/linux/pagemap.h | 2 ++ mm/filemap.c | 25 +++++++++++++++++++++++++ 3 files changed, 28 insertions(+), 17 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/mpage.c b/fs/mpage.c index 4cc9c5d079f..10da0da7301 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -48,23 +48,7 @@ static void mpage_end_io(struct bio *bio, int err) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - - if (bio_data_dir(bio) == READ) { - if (!err) { - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); - } else { /* bio_data_dir(bio) == WRITE */ - if (err) { - SetPageError(page); - if (page->mapping) - set_bit(AS_EIO, &page->mapping->flags); - } - end_page_writeback(page); - } + page_endio(page, bio_data_dir(bio), err); } bio_put(bio); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 45598f1e9aa..718214c5584 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -425,6 +425,8 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); +void page_endio(struct page *page, int rw, int err); + /* * Add an arbitrary waiter to a page's wait queue */ diff --git a/mm/filemap.c b/mm/filemap.c index 021056c324e..47d235b357a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -764,6 +764,31 @@ void end_page_writeback(struct page *page) } EXPORT_SYMBOL(end_page_writeback); +/* + * After completing I/O on a page, call this routine to update the page + * flags appropriately + */ +void page_endio(struct page *page, int rw, int err) +{ + if (rw == READ) { + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } else { /* rw == WRITE */ + if (err) { + SetPageError(page); + if (page->mapping) + mapping_set_error(page->mapping, err); + } + end_page_writeback(page); + } +} +EXPORT_SYMBOL_GPL(page_endio); + /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock -- cgit v1.2.3-70-g09d2 From 2457aec63745e235bcafb7ef312b182d8682f0fc Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:31 -0700 Subject: mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Tested-by: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/extent_io.c | 11 +-- fs/btrfs/file.c | 5 +- fs/buffer.c | 7 +- fs/ext4/mballoc.c | 14 ++-- fs/f2fs/checkpoint.c | 3 - fs/f2fs/node.c | 2 - fs/fuse/file.c | 2 - fs/gfs2/aops.c | 1 - fs/gfs2/meta_io.c | 4 +- fs/ntfs/attrib.c | 1 - fs/ntfs/file.c | 1 - include/linux/page-flags.h | 1 + include/linux/pagemap.h | 107 ++++++++++++++++++++++-- include/linux/swap.h | 1 + mm/filemap.c | 202 +++++++++++++++++---------------------------- mm/shmem.c | 6 +- mm/swap.c | 11 +++ 17 files changed, 217 insertions(+), 162 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f29a54e454d..4cd0ac983f9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4510,7 +4510,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4519,7 +4520,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4533,7 +4535,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4581,7 +4583,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4596,7 +4598,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ae6af072b63..74272a3f9d9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -470,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } diff --git a/fs/buffer.c b/fs/buffer.c index 0d3e8d5a229..eba6e4f621c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) 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); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c8238a26818..afe8a133e3d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 4aa521aa9bc..c405b8f1705 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -69,7 +69,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } @@ -137,13 +136,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type) if (!page) continue; if (PageUptodate(page)) { - mark_page_accessed(page); f2fs_put_page(page, 1); continue; } f2fs_submit_page_mbio(sbi, page, blk_addr, &fio); - mark_page_accessed(page); f2fs_put_page(page, 0); } out: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a161e955c4c..57caa6eaf47 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -967,7 +967,6 @@ repeat: goto repeat; } got_it: - mark_page_accessed(page); return page; } @@ -1022,7 +1021,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f680d2c44e9..903cbc9cd6b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1089,8 +1089,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 5a49b037da8..492123cda64 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -577,7 +577,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 2cf09b63a6b..b984a6e190b 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -136,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -153,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fecefa..250ed5b20c8 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a3172..86ddab916b6 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d4b39ab234..2093eb72785 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c16fb6d06e3..0a97b583ee8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -259,12 +259,109 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t page_cache_prev_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan); +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask, gfp_mask & GFP_RECLAIM_MASK); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping), + GFP_NOFS); +} + struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_get_page(struct address_space *mapping, pgoff_t offset); struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset); -struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, - gfp_t gfp_mask); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); @@ -287,8 +384,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, diff --git a/include/linux/swap.h b/include/linux/swap.h index 97cf16164c4..4348d95e571 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -311,6 +311,7 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); diff --git a/mm/filemap.c b/mm/filemap.c index 47d235b357a..0fcd792103f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -981,26 +981,6 @@ out: } EXPORT_SYMBOL(find_get_entry); -/** - * find_get_page - find and get a page reference - * @mapping: the address_space to search - * @offset: the page index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned with an increased refcount. - * - * Otherwise, %NULL is returned. - */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_get_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_get_page); - /** * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search @@ -1038,66 +1018,84 @@ repeat: EXPORT_SYMBOL(find_lock_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use if a page is to be allocated * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. - * - * Otherwise, %NULL is returned. - * - * find_lock_page() may sleep. - */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_lock_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_lock_page); - -/** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * Looks up the page cache slot at @mapping & @offset. * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. + * PCG flags modify how the page is returned * - * If the page is not present, a new page is allocated using @gfp_mask - * and added to the page cache and the VM's LRU list. The page is - * returned locked and with an increased refcount. + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * - * On memory exhaustion, %NULL is returned. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an - * atomic allocation! + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp_mask); + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON_PAGE(page->index != offset, page); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + cache_gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) { + cache_gfp_mask &= ~__GFP_FS; + radix_gfp_mask &= ~__GFP_FS; + } + + page = __page_cache_alloc(cache_gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -1105,9 +1103,10 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup @@ -1404,39 +1403,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -2406,7 +2372,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2488,34 +2453,18 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping), + GFP_KERNEL); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2564,7 +2513,7 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) @@ -2573,7 +2522,6 @@ again: copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/shmem.c b/mm/shmem.c index f47fb38c488..5402481c28d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1372,9 +1372,13 @@ shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + if (ret == 0 && *pagep) + init_page_accessed(*pagep); + return ret; } static int diff --git a/mm/swap.c b/mm/swap.c index 1fb25f8bb15..9e8e3472248 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -614,6 +614,17 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); +/* + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops + */ +void init_page_accessed(struct page *page) +{ + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); -- cgit v1.2.3-70-g09d2 From 888cf2db475a256fb0cda042140f73d7881f81fe Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:34 -0700 Subject: mm: avoid unnecessary atomic operations during end_page_writeback() If a page is marked for immediate reclaim then it is moved to the tail of the LRU list. This occurs when the system is under enough memory pressure for pages under writeback to reach the end of the LRU but we test for this using atomic operations on every writeback. This patch uses an optimistic non-atomic test first. It'll miss some pages in rare cases but the consequences are not severe enough to warrant such a penalty. While the function does not dominate profiles during a simple dd test the cost of it is reduced. 73048 0.7428 vmlinux-3.15.0-rc5-mmotm-20140513 end_page_writeback 23740 0.2409 vmlinux-3.15.0-rc5-lessatomic end_page_writeback Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 0fcd792103f..7fadf1c6283 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -753,8 +753,17 @@ EXPORT_SYMBOL(unlock_page); */ void end_page_writeback(struct page *page) { - if (TestClearPageReclaim(page)) + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); rotate_reclaimable_page(page); + } if (!test_clear_page_writeback(page)) BUG(); -- cgit v1.2.3-70-g09d2