diff options
Diffstat (limited to 'fs/xfs/xfs_file.c')
| -rw-r--r-- | fs/xfs/xfs_file.c | 756 |
1 files changed, 445 insertions, 311 deletions
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index b8a4a3f29b36..e462d39c840e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,45 +25,46 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" +#include <linux/dax.h> #include <linux/falloc.h> #include <linux/backing-dev.h> #include <linux/mman.h> #include <linux/fadvise.h> +#include <linux/mount.h> static const struct vm_operations_struct xfs_file_vm_ops; -int -xfs_update_prealloc_flags( +/* + * Decide if the given file range is aligned to the size of the fundamental + * allocation unit for the file. + */ +static bool +xfs_is_falloc_aligned( struct xfs_inode *ip, - enum xfs_prealloc_flags flags) + loff_t pos, + long long int len) { - struct xfs_trans *tp; - int error; - - error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid, - 0, 0, 0, &tp); - if (error) - return error; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - - if (!(flags & XFS_PREALLOC_INVISIBLE)) { - VFS_I(ip)->i_mode &= ~S_ISUID; - if (VFS_I(ip)->i_mode & S_IXGRP) - VFS_I(ip)->i_mode &= ~S_ISGID; - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + struct xfs_mount *mp = ip->i_mount; + uint64_t mask; + + if (XFS_IS_REALTIME_INODE(ip)) { + if (!is_power_of_2(mp->m_sb.sb_rextsize)) { + u64 rextbytes; + u32 mod; + + rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + div_u64_rem(pos, rextbytes, &mod); + if (mod) + return false; + div_u64_rem(len, rextbytes, &mod); + return mod == 0; + } + mask = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize) - 1; + } else { + mask = mp->m_sb.sb_blocksize - 1; } - if (flags & XFS_PREALLOC_SET) - ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; - if (flags & XFS_PREALLOC_CLEAR) - ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; - - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (flags & XFS_PREALLOC_SYNC) - xfs_trans_set_sync(tp); - return xfs_trans_commit(tp); + return !((pos | len) & mask); } /* @@ -80,19 +81,57 @@ xfs_dir_fsync( int datasync) { struct xfs_inode *ip = XFS_I(file->f_mapping->host); - struct xfs_mount *mp = ip->i_mount; - xfs_lsn_t lsn = 0; trace_xfs_dir_fsync(ip); + return xfs_log_force_inode(ip); +} + +static xfs_csn_t +xfs_fsync_seq( + struct xfs_inode *ip, + bool datasync) +{ + if (!xfs_ipincount(ip)) + return 0; + if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) + return 0; + return ip->i_itemp->ili_commit_seq; +} + +/* + * All metadata updates are logged, which means that we just have to flush the + * log up to the latest LSN that touched the inode. + * + * If we have concurrent fsync/fdatasync() calls, we need them to all block on + * the log force before we clear the ili_fsync_fields field. This ensures that + * we don't get a racing sync operation that does not wait for the metadata to + * hit the journal before returning. If we race with clearing ili_fsync_fields, + * then all that will happen is the log force will do nothing as the lsn will + * already be on disk. We can't race with setting ili_fsync_fields because that + * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock + * shared until after the ili_fsync_fields is cleared. + */ +static int +xfs_fsync_flush_log( + struct xfs_inode *ip, + bool datasync, + int *log_flushed) +{ + int error = 0; + xfs_csn_t seq; xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) - lsn = ip->i_itemp->ili_last_lsn; - xfs_iunlock(ip, XFS_ILOCK_SHARED); + seq = xfs_fsync_seq(ip, datasync); + if (seq) { + error = xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, + log_flushed); - if (!lsn) - return 0; - return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL); + spin_lock(&ip->i_itemp->ili_lock); + ip->i_itemp->ili_fsync_fields = 0; + spin_unlock(&ip->i_itemp->ili_lock); + } + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return error; } STATIC int @@ -102,12 +141,10 @@ xfs_file_fsync( loff_t end, int datasync) { - struct inode *inode = file->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); + struct xfs_inode *ip = XFS_I(file->f_mapping->host); struct xfs_mount *mp = ip->i_mount; - int error = 0; + int error, err2; int log_flushed = 0; - xfs_lsn_t lsn = 0; trace_xfs_file_fsync(ip); @@ -115,7 +152,7 @@ xfs_file_fsync( if (error) return error; - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; xfs_iflags_clear(ip, XFS_ITRUNCATED); @@ -127,36 +164,22 @@ xfs_file_fsync( * inode size in case of an extending write. */ if (XFS_IS_REALTIME_INODE(ip)) - xfs_blkdev_issue_flush(mp->m_rtdev_targp); + error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); else if (mp->m_logdev_targp != mp->m_ddev_targp) - xfs_blkdev_issue_flush(mp->m_ddev_targp); + error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); /* - * All metadata updates are logged, which means that we just have to - * flush the log up to the latest LSN that touched the inode. If we have - * concurrent fsync/fdatasync() calls, we need them to all block on the - * log force before we clear the ili_fsync_fields field. This ensures - * that we don't get a racing sync operation that does not wait for the - * metadata to hit the journal before returning. If we race with - * clearing the ili_fsync_fields, then all that will happen is the log - * force will do nothing as the lsn will already be on disk. We can't - * race with setting ili_fsync_fields because that is done under - * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared - * until after the ili_fsync_fields is cleared. + * Any inode that has dirty modifications in the log is pinned. The + * racy check here for a pinned inode will not catch modifications + * that happen concurrently to the fsync call, but fsync semantics + * only require to sync previously completed I/O. */ - xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_ipincount(ip)) { - if (!datasync || - (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) - lsn = ip->i_itemp->ili_last_lsn; + err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed); + if (err2 && !error) + error = err2; } - if (lsn) { - error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed); - ip->i_itemp->ili_fsync_fields = 0; - } - xfs_iunlock(ip, XFS_ILOCK_SHARED); - /* * If we only have a single device, and the log force about was * a no-op we might have to flush the data device cache here. @@ -165,36 +188,51 @@ xfs_file_fsync( * commit. */ if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) && - mp->m_logdev_targp == mp->m_ddev_targp) - xfs_blkdev_issue_flush(mp->m_ddev_targp); + mp->m_logdev_targp == mp->m_ddev_targp) { + err2 = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); + if (err2 && !error) + error = err2; + } return error; } +static int +xfs_ilock_iocb( + struct kiocb *iocb, + unsigned int lock_mode) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, lock_mode)) + return -EAGAIN; + } else { + xfs_ilock(ip, lock_mode); + } + + return 0; +} + STATIC ssize_t -xfs_file_dio_aio_read( +xfs_file_dio_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); - size_t count = iov_iter_count(to); ssize_t ret; - trace_xfs_file_direct_read(ip, count, iocb->ki_pos); + trace_xfs_file_direct_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ file_accessed(iocb->ki_filp); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, - is_sync_kiocb(iocb)); + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; + ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, NULL, 0); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -206,21 +244,16 @@ xfs_file_dax_read( struct iov_iter *to) { struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host); - size_t count = iov_iter_count(to); ssize_t ret = 0; - trace_xfs_file_dax_read(ip, count, iocb->ki_pos); + trace_xfs_file_dax_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = dax_iomap_rw(iocb, to, &xfs_read_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -229,21 +262,18 @@ xfs_file_dax_read( } STATIC ssize_t -xfs_file_buffered_aio_read( +xfs_file_buffered_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); ssize_t ret; - trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); + trace_xfs_file_buffered_read(iocb, to); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = generic_file_read_iter(iocb, to); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -261,15 +291,15 @@ xfs_file_read_iter( XFS_STATS_INC(mp, xs_read_calls); - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; if (IS_DAX(inode)) ret = xfs_file_dax_read(iocb, to); else if (iocb->ki_flags & IOCB_DIRECT) - ret = xfs_file_dio_aio_read(iocb, to); + ret = xfs_file_dio_read(iocb, to); else - ret = xfs_file_buffered_aio_read(iocb, to); + ret = xfs_file_buffered_read(iocb, to); if (ret > 0) XFS_STATS_ADD(mp, xs_read_bytes, ret); @@ -284,10 +314,10 @@ xfs_file_read_iter( * if called for a direct write beyond i_size. */ STATIC ssize_t -xfs_file_aio_write_checks( +xfs_file_write_checks( struct kiocb *iocb, struct iov_iter *from, - int *iolock) + unsigned int *iolock) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -302,7 +332,14 @@ restart: if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + if (iocb->ki_flags & IOCB_NOWAIT) { + error = break_layout(inode, false); + if (error == -EWOULDBLOCK) + error = -EAGAIN; + } else { + error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + } + if (error) return error; @@ -313,28 +350,45 @@ restart: if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) { xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_ilock(ip, *iolock); + error = xfs_ilock_iocb(iocb, *iolock); + if (error) { + *iolock = 0; + return error; + } goto restart; } + /* * If the offset is beyond the size of the file, we need to zero any * blocks that fall between the existing EOF and the start of this - * write. If zeroing is needed and we are currently holding the - * iolock shared, we need to update it to exclusive which implies - * having to redo all checks before. + * write. If zeroing is needed and we are currently holding the iolock + * shared, we need to update it to exclusive which implies having to + * redo all checks before. + * + * We need to serialise against EOF updates that occur in IO completions + * here. We want to make sure that nobody is changing the size while we + * do this check until we have placed an IO barrier (i.e. hold the + * XFS_IOLOCK_EXCL) that prevents new IO from being dispatched. The + * spinlock effectively forms a memory barrier once we have the + * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value and + * hence be able to correctly determine if we need to run zeroing. * - * We need to serialise against EOF updates that occur in IO - * completions here. We want to make sure that nobody is changing the - * size while we do this check until we have placed an IO barrier (i.e. - * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched. - * The spinlock effectively forms a memory barrier once we have the - * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value - * and hence be able to correctly determine if we need to run zeroing. + * We can do an unlocked check here safely as IO completion can only + * extend EOF. Truncate is locked out at this point, so the EOF can + * not move backwards, only forwards. Hence we only need to take the + * slow path and spin locks when we are at or beyond the current EOF. */ + if (iocb->ki_pos <= i_size_read(inode)) + goto out; + spin_lock(&ip->i_flags_lock); isize = i_size_read(inode); if (iocb->ki_pos > isize) { spin_unlock(&ip->i_flags_lock); + + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_iunlock(ip, *iolock); @@ -354,22 +408,16 @@ restart: drained_dio = true; goto restart; } - + trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize); - error = iomap_zero_range(inode, isize, iocb->ki_pos - isize, - NULL, &xfs_buffered_write_iomap_ops); + error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL); if (error) return error; } else spin_unlock(&ip->i_flags_lock); - /* - * Updating the timestamps will grab the ilock again from - * xfs_fs_dirty_inode, so we have to call it after dropping the - * lock above. Eventually we should look into a way to avoid - * the pointless lock roundtrip. - */ - return file_modified(file); +out: + return kiocb_modified(iocb); } static int @@ -386,7 +434,7 @@ xfs_dio_write_end_io( trace_xfs_end_io_direct_write(ip, offset, size); - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + if (xfs_is_shutdown(ip->i_mount)) return -EIO; if (error) @@ -434,7 +482,17 @@ xfs_dio_write_end_io( * other IO completions here to update the EOF. Failing to serialise * here can result in EOF moving backwards and Bad Things Happen when * that occurs. + * + * As IO completion only ever extends EOF, we can do an unlocked check + * here to avoid taking the spinlock. If we land within the current EOF, + * then we do not need to do an extending update at all, and we don't + * need to take the lock to check this. If we race with an update moving + * EOF, then we'll either still be beyond EOF and need to take the lock, + * or we'll be within EOF and we don't need to take it at all. */ + if (offset + size <= i_size_read(inode)) + goto out; + spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); @@ -454,122 +512,149 @@ static const struct iomap_dio_ops xfs_dio_write_ops = { }; /* - * xfs_file_dio_aio_write - handle direct IO writes - * - * Lock the inode appropriately to prepare for and issue a direct IO write. - * By separating it from the buffered write path we remove all the tricky to - * follow locking changes and looping. - * - * If there are cached pages or we're extending the file, we need IOLOCK_EXCL - * until we're sure the bytes at the new EOF have been zeroed and/or the cached - * pages are flushed out. - * - * In most cases the direct IO writes will be done holding IOLOCK_SHARED - * allowing them to be done in parallel with reads and other direct IO writes. - * However, if the IO is not aligned to filesystem blocks, the direct IO layer - * needs to do sub-block zeroing and that requires serialisation against other - * direct IOs to the same block. In this case we need to serialise the - * submission of the unaligned IOs so that we don't get racing block zeroing in - * the dio layer. To avoid the problem with aio, we also need to wait for - * outstanding IOs to complete so that unwritten extent conversion is completed - * before we try to map the overlapping block. This is currently implemented by - * hitting it with a big hammer (i.e. inode_dio_wait()). - * - * Returns with locks held indicated by @iolock and errors indicated by - * negative return values. + * Handle block aligned direct I/O writes */ -STATIC ssize_t -xfs_file_dio_aio_write( +static noinline ssize_t +xfs_file_dio_write_aligned( + struct xfs_inode *ip, struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - ssize_t ret = 0; - int unaligned_io = 0; - int iolock; - size_t count = iov_iter_count(from); - struct xfs_buftarg *target = xfs_inode_buftarg(ip); + unsigned int iolock = XFS_IOLOCK_SHARED; + ssize_t ret; - /* DIO must be aligned to device logical sector size */ - if ((iocb->ki_pos | count) & target->bt_logical_sectormask) - return -EINVAL; + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; /* - * Don't take the exclusive iolock here unless the I/O is unaligned to - * the file system block size. We don't need to consider the EOF - * extension case here because xfs_file_aio_write_checks() will relock - * the inode as necessary for EOF zeroing cases and fill out the new - * inode size as appropriate. + * We don't need to hold the IOLOCK exclusively across the IO, so demote + * the iolock back to shared if we had to take the exclusive lock in + * xfs_file_write_checks() for other reasons. */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) { - unaligned_io = 1; - - /* - * We can't properly handle unaligned direct I/O to reflink - * files yet, as we can't unshare a partial block. - */ - if (xfs_is_cow_inode(ip)) { - trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count); - return -EREMCHG; - } - iolock = XFS_IOLOCK_EXCL; - } else { + if (iolock == XFS_IOLOCK_EXCL) { + xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } + trace_xfs_file_direct_write(iocb, from); + ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, + &xfs_dio_write_ops, 0, NULL, 0); +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); + return ret; +} - if (iocb->ki_flags & IOCB_NOWAIT) { - /* unaligned dio always waits, bail */ - if (unaligned_io) - return -EAGAIN; - if (!xfs_ilock_nowait(ip, iolock)) +/* + * Handle block unaligned direct I/O writes + * + * In most cases direct I/O writes will be done holding IOLOCK_SHARED, allowing + * them to be done in parallel with reads and other direct I/O writes. However, + * if the I/O is not aligned to filesystem blocks, the direct I/O layer may need + * to do sub-block zeroing and that requires serialisation against other direct + * I/O to the same block. In this case we need to serialise the submission of + * the unaligned I/O so that we don't get racing block zeroing in the dio layer. + * In the case where sub-block zeroing is not required, we can do concurrent + * sub-block dios to the same block successfully. + * + * Optimistically submit the I/O using the shared lock first, but use the + * IOMAP_DIO_OVERWRITE_ONLY flag to tell the lower layers to return -EAGAIN + * if block allocation or partial block zeroing would be required. In that case + * we try again with the exclusive lock. + */ +static noinline ssize_t +xfs_file_dio_write_unaligned( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from) +{ + size_t isize = i_size_read(VFS_I(ip)); + size_t count = iov_iter_count(from); + unsigned int iolock = XFS_IOLOCK_SHARED; + unsigned int flags = IOMAP_DIO_OVERWRITE_ONLY; + ssize_t ret; + + /* + * Extending writes need exclusivity because of the sub-block zeroing + * that the DIO code always does for partial tail blocks beyond EOF, so + * don't even bother trying the fast path in this case. + */ + if (iocb->ki_pos > isize || iocb->ki_pos + count >= isize) { + if (iocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; - } else { - xfs_ilock(ip, iolock); +retry_exclusive: + iolock = XFS_IOLOCK_EXCL; + flags = IOMAP_DIO_FORCE_WAIT; } - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); if (ret) - goto out; - count = iov_iter_count(from); + return ret; /* - * If we are doing unaligned IO, we can't allow any other overlapping IO - * in-flight at the same time or we risk data corruption. Wait for all - * other IO to drain before we submit. If the IO is aligned, demote the - * iolock if we had to take the exclusive lock in - * xfs_file_aio_write_checks() for other reasons. + * We can't properly handle unaligned direct I/O to reflink files yet, + * as we can't unshare a partial block. */ - if (unaligned_io) { - inode_dio_wait(inode); - } else if (iolock == XFS_IOLOCK_EXCL) { - xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); - iolock = XFS_IOLOCK_SHARED; + if (xfs_is_cow_inode(ip)) { + trace_xfs_reflink_bounce_dio_write(iocb, from); + ret = -ENOTBLK; + goto out_unlock; } - trace_xfs_file_direct_write(ip, count, iocb->ki_pos); + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; + /* - * If unaligned, this is the only IO in-flight. Wait on it before we - * release the iolock to prevent subsequent overlapping IO. + * If we are doing exclusive unaligned I/O, this must be the only I/O + * in-flight. Otherwise we risk data corruption due to unwritten extent + * conversions from the AIO end_io handler. Wait for all other I/O to + * drain first. */ + if (flags & IOMAP_DIO_FORCE_WAIT) + inode_dio_wait(VFS_I(ip)); + + trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, - is_sync_kiocb(iocb) || unaligned_io); -out: - xfs_iunlock(ip, iolock); + &xfs_dio_write_ops, flags, NULL, 0); /* - * No fallback to buffered IO on errors for XFS, direct IO will either - * complete fully or fail. + * Retry unaligned I/O with exclusive blocking semantics if the DIO + * layer rejected it for mapping or locking reasons. If we are doing + * nonblocking user I/O, propagate the error. */ - ASSERT(ret < 0 || ret == count); + if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT)) { + ASSERT(flags & IOMAP_DIO_OVERWRITE_ONLY); + xfs_iunlock(ip, iolock); + goto retry_exclusive; + } + +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); return ret; } +static ssize_t +xfs_file_dio_write( + struct kiocb *iocb, + struct iov_iter *from) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + size_t count = iov_iter_count(from); + + /* direct I/O must be aligned to device logical sector size */ + if ((iocb->ki_pos | count) & target->bt_logical_sectormask) + return -EINVAL; + if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) + return xfs_file_dio_write_unaligned(ip, iocb, from); + return xfs_file_dio_write_aligned(ip, iocb, from); +} + static noinline ssize_t xfs_file_dax_write( struct kiocb *iocb, @@ -577,33 +662,28 @@ xfs_file_dax_write( { struct inode *inode = iocb->ki_filp->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); - int iolock = XFS_IOLOCK_EXCL; + unsigned int iolock = XFS_IOLOCK_EXCL; ssize_t ret, error = 0; - size_t count; loff_t pos; - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, iolock)) - return -EAGAIN; - } else { - xfs_ilock(ip, iolock); - } - - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; pos = iocb->ki_pos; - count = iov_iter_count(from); - trace_xfs_file_dax_write(ip, count, pos); - ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); + trace_xfs_file_dax_write(iocb, from); + ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); } out: - xfs_iunlock(ip, iolock); + if (iolock) + xfs_iunlock(ip, iolock); if (error) return error; @@ -617,33 +697,30 @@ out: } STATIC ssize_t -xfs_file_buffered_aio_write( +xfs_file_buffered_write( struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = iocb->ki_filp->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t ret; - int enospc = 0; - int iolock; - - if (iocb->ki_flags & IOCB_NOWAIT) - return -EOPNOTSUPP; + bool cleared_space = false; + unsigned int iolock; write_retry: iolock = XFS_IOLOCK_EXCL; - xfs_ilock(ip, iolock); + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos); + trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, &xfs_buffered_write_iomap_ops); if (likely(ret >= 0)) @@ -656,27 +733,23 @@ write_retry: * metadata space. This reduces the chances that the eofblocks scan * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this * also behaves as a filter to prevent too many eofblocks scans from - * running at the same time. + * running at the same time. Use a synchronous scan to increase the + * effectiveness of the scan. */ - if (ret == -EDQUOT && !enospc) { + if (ret == -EDQUOT && !cleared_space) { xfs_iunlock(ip, iolock); - enospc = xfs_inode_free_quota_eofblocks(ip); - if (enospc) - goto write_retry; - enospc = xfs_inode_free_quota_cowblocks(ip); - if (enospc) - goto write_retry; - iolock = 0; - } else if (ret == -ENOSPC && !enospc) { - struct xfs_eofblocks eofb = {0}; - - enospc = 1; + xfs_blockgc_free_quota(ip, XFS_ICWALK_FLAG_SYNC); + cleared_space = true; + goto write_retry; + } else if (ret == -ENOSPC && !cleared_space) { + struct xfs_icwalk icw = {0}; + + cleared_space = true; xfs_flush_inodes(ip->i_mount); xfs_iunlock(ip, iolock); - eofb.eof_flags = XFS_EOF_FLAGS_SYNC; - xfs_icache_free_eofblocks(ip->i_mount, &eofb); - xfs_icache_free_cowblocks(ip->i_mount, &eofb); + icw.icw_flags = XFS_ICWALK_FLAG_SYNC; + xfs_blockgc_free_space(ip->i_mount, &icw); goto write_retry; } @@ -698,9 +771,7 @@ xfs_file_write_iter( struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = iocb->ki_filp->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t ret; size_t ocount = iov_iter_count(from); @@ -710,7 +781,7 @@ xfs_file_write_iter( if (ocount == 0) return 0; - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + if (xfs_is_shutdown(ip->i_mount)) return -EIO; if (IS_DAX(inode)) @@ -723,12 +794,12 @@ xfs_file_write_iter( * CoW. In all other directio scenarios we do not * allow an operation to fall back to buffered mode. */ - ret = xfs_file_dio_aio_write(iocb, from); - if (ret != -EREMCHG) + ret = xfs_file_dio_write(iocb, from); + if (ret != -ENOTBLK) return ret; } - return xfs_file_buffered_aio_write(iocb, from); + return xfs_file_buffered_write(iocb, from); } static void @@ -742,7 +813,7 @@ xfs_wait_dax_page( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } -static int +int xfs_break_dax_layouts( struct inode *inode, bool *retry) @@ -779,7 +850,7 @@ xfs_break_layouts( error = xfs_break_dax_layouts(inode, &retry); if (error || retry) break; - /* fall through */ + fallthrough; case BREAK_WRITE: error = xfs_break_leased_layouts(inode, iolock, &retry); break; @@ -792,6 +863,21 @@ xfs_break_layouts( return error; } +/* Does this file, inode, or mount want synchronous writes? */ +static inline bool xfs_file_sync_writes(struct file *filp) +{ + struct xfs_inode *ip = XFS_I(file_inode(filp)); + + if (xfs_has_wsync(ip->i_mount)) + return true; + if (filp->f_flags & (__O_SYNC | O_DSYNC)) + return true; + if (IS_SYNC(file_inode(filp))) + return true; + + return false; +} + #define XFS_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ @@ -807,7 +893,6 @@ xfs_file_fallocate( struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; - enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -852,14 +937,16 @@ xfs_file_fallocate( goto out_unlock; } + error = file_modified(file); + if (error) + goto out_unlock; + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) goto out_unlock; } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - unsigned int blksize_mask = i_blocksize(inode) - 1; - - if (offset & blksize_mask || len & blksize_mask) { + if (!xfs_is_falloc_aligned(ip, offset, len)) { error = -EINVAL; goto out_unlock; } @@ -879,10 +966,9 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_INSERT_RANGE) { - unsigned int blksize_mask = i_blocksize(inode) - 1; loff_t isize = i_size_read(inode); - if (offset & blksize_mask || len & blksize_mask) { + if (!xfs_is_falloc_aligned(ip, offset, len)) { error = -EINVAL; goto out_unlock; } @@ -904,8 +990,6 @@ xfs_file_fallocate( } do_file_insert = true; } else { - flags |= XFS_PREALLOC_SET; - if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -951,27 +1035,20 @@ xfs_file_fallocate( } if (!xfs_is_always_cow_inode(ip)) { - error = xfs_alloc_file_space(ip, offset, len, - XFS_BMAPI_PREALLOC); + error = xfs_alloc_file_space(ip, offset, len); if (error) goto out_unlock; } } - if (file->f_flags & O_DSYNC) - flags |= XFS_PREALLOC_SYNC; - - error = xfs_update_prealloc_flags(ip, flags); - if (error) - goto out_unlock; - /* Change file size if needed */ if (new_size) { struct iattr iattr; iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_vn_setattr_size(file_dentry(file), &iattr); + error = xfs_vn_setattr_size(file_mnt_user_ns(file), + file_dentry(file), &iattr); if (error) goto out_unlock; } @@ -982,8 +1059,14 @@ xfs_file_fallocate( * leave shifted extents past EOF and hence losing access to * the data that is contained within them. */ - if (do_file_insert) + if (do_file_insert) { error = xfs_insert_file_space(ip, offset, len); + if (error) + goto out_unlock; + } + + if (xfs_file_sync_writes(file)) + error = xfs_log_force_inode(ip); out_unlock: xfs_iunlock(ip, iolock); @@ -1036,16 +1119,16 @@ xfs_file_remap_range( if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; - if (!xfs_sb_version_hasreflink(&mp->m_sb)) + if (!xfs_has_reflink(mp)) return -EOPNOTSUPP; - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; /* Prepare and then clone file data. */ ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out, &len, remap_flags); - if (ret < 0 || len == 0) + if (ret || len == 0) return ret; trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); @@ -1062,16 +1145,20 @@ xfs_file_remap_range( */ cowextsize = 0; if (pos_in == 0 && len == i_size_read(inode_in) && - (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && + (src->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && pos_out == 0 && len >= i_size_read(inode_out) && - !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) - cowextsize = src->i_d.di_cowextsize; + !(dest->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)) + cowextsize = src->i_cowextsize; ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, remap_flags); + if (ret) + goto out_unlock; + if (xfs_file_sync_writes(file_in) || xfs_file_sync_writes(file_out)) + xfs_log_force_inode(dest); out_unlock: - xfs_reflink_remap_unlock(file_in, file_out); + xfs_iunlock2_io_mmap(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); return remapped > 0 ? remapped : ret; @@ -1082,12 +1169,10 @@ xfs_file_open( struct inode *inode, struct file *file) { - if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) - return -EFBIG; - if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb))) + if (xfs_is_shutdown(XFS_M(inode->i_sb))) return -EIO; - file->f_mode |= FMODE_NOWAIT; - return 0; + file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC; + return generic_file_open(inode, file); } STATIC int @@ -1096,7 +1181,7 @@ xfs_dir_open( struct file *file) { struct xfs_inode *ip = XFS_I(inode); - int mode; + unsigned int mode; int error; error = xfs_file_open(inode, file); @@ -1108,7 +1193,7 @@ xfs_dir_open( * certain to have the next operation be a read there. */ mode = xfs_ilock_data_map_shared(ip); - if (ip->i_d.di_nextents > 0) + if (ip->i_df.if_nextents > 0) error = xfs_dir3_data_readahead(ip, 0, 0); xfs_iunlock(ip, mode); return error; @@ -1143,7 +1228,7 @@ xfs_file_readdir( * point we can change the ->readdir prototype to include the * buffer size. For now we use the current glibc buffer size. */ - bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_d.di_size); + bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_disk_size); return xfs_readdir(NULL, ip, ctx, bufsize); } @@ -1156,7 +1241,7 @@ xfs_file_llseek( { struct inode *inode = file->f_mapping->host; - if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount)) + if (xfs_is_shutdown(XFS_I(inode)->i_mount)) return -EIO; switch (whence) { @@ -1175,13 +1260,39 @@ xfs_file_llseek( return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } +#ifdef CONFIG_FS_DAX +static inline vm_fault_t +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return dax_iomap_fault(vmf, pe_size, pfn, NULL, + (write_fault && !vmf->cow_page) ? + &xfs_dax_write_iomap_ops : + &xfs_read_iomap_ops); +} +#else +static inline vm_fault_t +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + ASSERT(0); + return VM_FAULT_SIGBUS; +} +#endif + /* * Locking for serialisation of IO during page faults. This results in a lock * ordering of: * - * mmap_sem (MM) + * mmap_lock (MM) * sb_start_pagefault(vfs, freeze) - * i_mmaplock (XFS - truncate serialisation) + * invalidate_lock (vfs/XFS_MMAPLOCK - truncate serialisation) * page_lock (MM) * i_lock (XFS - extent map serialisation) */ @@ -1202,30 +1313,38 @@ __xfs_filemap_fault( file_update_time(vmf->vma->vm_file); } - xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) { pfn_t pfn; - ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, - (write_fault && !vmf->cow_page) ? - &xfs_direct_write_iomap_ops : - &xfs_read_iomap_ops); + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn); if (ret & VM_FAULT_NEEDDSYNC) ret = dax_finish_sync_fault(vmf, pe_size, pfn); + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); } else { - if (write_fault) + if (write_fault) { + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops); - else + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + } else { ret = filemap_fault(vmf); + } } - xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (write_fault) sb_end_pagefault(inode->i_sb); return ret; } +static inline bool +xfs_is_write_fault( + struct vm_fault *vmf) +{ + return (vmf->flags & FAULT_FLAG_WRITE) && + (vmf->vma->vm_flags & VM_SHARED); +} + static vm_fault_t xfs_filemap_fault( struct vm_fault *vmf) @@ -1233,7 +1352,7 @@ xfs_filemap_fault( /* DAX can shortcut the normal fault path on write faults! */ return __xfs_filemap_fault(vmf, PE_SIZE_PTE, IS_DAX(file_inode(vmf->vma->vm_file)) && - (vmf->flags & FAULT_FLAG_WRITE)); + xfs_is_write_fault(vmf)); } static vm_fault_t @@ -1246,7 +1365,7 @@ xfs_filemap_huge_fault( /* DAX can shortcut the normal fault path on write faults! */ return __xfs_filemap_fault(vmf, pe_size, - (vmf->flags & FAULT_FLAG_WRITE)); + xfs_is_write_fault(vmf)); } static vm_fault_t @@ -1269,10 +1388,25 @@ xfs_filemap_pfn_mkwrite( return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } +static vm_fault_t +xfs_filemap_map_pages( + struct vm_fault *vmf, + pgoff_t start_pgoff, + pgoff_t end_pgoff) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + vm_fault_t ret; + + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + ret = filemap_map_pages(vmf, start_pgoff, end_pgoff); + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + return ret; +} + static const struct vm_operations_struct xfs_file_vm_ops = { .fault = xfs_filemap_fault, .huge_fault = xfs_filemap_huge_fault, - .map_pages = filemap_map_pages, + .map_pages = xfs_filemap_map_pages, .page_mkwrite = xfs_filemap_page_mkwrite, .pfn_mkwrite = xfs_filemap_pfn_mkwrite, }; @@ -1305,7 +1439,7 @@ const struct file_operations xfs_file_operations = { .write_iter = xfs_file_write_iter, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, .unlocked_ioctl = xfs_file_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = xfs_file_compat_ioctl, |