From 453eac8a9aa417878a38bdfbccafd5f7ce4e8e4e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 11 Jan 2010 11:49:58 +0000 Subject: xfs: Don't wake the aild once per second Now that the AIL push algorithm is traversal safe, we don't need a watchdog function in the xfsaild to catch pushes that fail to make progress. Remove the watchdog timeout and make pushes purely driven by demand. This will remove the once-per-second wakeup that is seen when the filesystem is idle and make laptop power misers happy. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_super.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 77414db10dc..9f2e398a561 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -877,12 +877,11 @@ xfsaild( { struct xfs_ail *ailp = data; xfs_lsn_t last_pushed_lsn = 0; - long tout = 0; + long tout = 0; /* milliseconds */ while (!kthread_should_stop()) { - if (tout) - schedule_timeout_interruptible(msecs_to_jiffies(tout)); - tout = 1000; + schedule_timeout_interruptible(tout ? + msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT); /* swsusp */ try_to_freeze(); -- cgit v1.2.3-70-g09d2 From cbe132a8bdcff0f9afd9060948fb50597c7400b8 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 26 Jan 2010 15:08:49 +1100 Subject: xfs: don't hold onto reserved blocks on remount,ro If we hold onto reserved blocks when doing a remount,ro we end up writing the blocks used count to disk that includes the reserved blocks. Reserved blocks are not actually used, so this results in the values in the superblock being incorrect. Hence if we run xfs_check or xfs_repair -n while the filesystem is mounted remount,ro we end up with an inconsistent filesystem being reported. Also, running xfs_copy on the remount,ro filesystem will result in an inconsistent image being generated. To fix this, unreserve the blocks when doing the remount,ro, and reserved them again on remount,rw. This way a remount,ro filesystem will appear consistent on disk to all utilities. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/linux-2.6/xfs_super.c | 28 ++++++++++++++++++++++++++++ fs/xfs/xfs_mount.h | 1 + 2 files changed, 29 insertions(+) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 9f2e398a561..e9c21454b9e 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1318,6 +1318,8 @@ xfs_fs_remount( /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { + __uint64_t resblks; + mp->m_flags &= ~XFS_MOUNT_RDONLY; if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_mountfs_check_barriers(mp); @@ -1335,11 +1337,37 @@ xfs_fs_remount( } mp->m_update_flags = 0; } + + /* + * Fill out the reserve pool if it is empty. Use the stashed + * value if it is non-zero, otherwise go with the default. + */ + if (mp->m_resblks_save) { + resblks = mp->m_resblks_save; + mp->m_resblks_save = 0; + } else { + resblks = mp->m_sb.sb_dblocks; + do_div(resblks, 20); + resblks = min_t(__uint64_t, resblks, 1024); + } + xfs_reserve_blocks(mp, &resblks, NULL); } /* rw -> ro */ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) { + /* + * After we have synced the data but before we sync the + * metadata, we need to free up the reserve block pool so that + * the used block count in the superblock on disk is correct at + * the end of the remount. Stash the current reserve pool size + * so that if we get remounted rw, we can return it to the same + * size. + */ + __uint64_t resblks = 0; + xfs_quiesce_data(mp); + mp->m_resblks_save = mp->m_resblks; + xfs_reserve_blocks(mp, &resblks, NULL); xfs_quiesce_attr(mp); mp->m_flags |= XFS_MOUNT_RDONLY; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f4d1441f3f1..02d45f213e5 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -225,6 +225,7 @@ typedef struct xfs_mount { __uint64_t m_maxioffset; /* maximum inode offset */ __uint64_t m_resblks; /* total reserved blocks */ __uint64_t m_resblks_avail;/* available reserved blocks */ + __uint64_t m_resblks_save; /* reserved blks @ remount,ro */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ int m_sinoalign; /* stripe unit inode alignment */ -- cgit v1.2.3-70-g09d2 From d5db0f97fbbeff11c88dec1aaf1536a975afbaeb Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 5 Feb 2010 22:59:53 +0000 Subject: xfs: more reserved blocks fixups This mangles the reserved blocks counts a little more. 1) add a helper function for the default reserved count 2) add helper functions to save/restore counts on ro/rw 3) save/restore reserved blocks on freeze/thaw 4) disallow changing reserved count while readonly V2: changed field name to match Dave's changes Signed-off-by: Eric Sandeen Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_ioctl.c | 3 +++ fs/xfs/linux-2.6/xfs_super.c | 51 ++++++++++++++++++++++++++++++++------------ fs/xfs/xfs_mount.c | 34 +++++++++++++++++++---------- fs/xfs/xfs_mount.h | 1 + 4 files changed, 64 insertions(+), 25 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 3906e85abfd..4ea1ee18ade 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -1431,6 +1431,9 @@ xfs_file_ioctl( if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (mp->m_flags & XFS_MOUNT_RDONLY) + return -XFS_ERROR(EROFS); + if (copy_from_user(&inout, arg, sizeof(inout))) return -XFS_ERROR(EFAULT); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index e9c21454b9e..6ce828e0e17 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1256,6 +1256,29 @@ xfs_fs_statfs( return 0; } +STATIC void +xfs_save_resvblks(struct xfs_mount *mp) +{ + __uint64_t resblks = 0; + + mp->m_resblks_save = mp->m_resblks; + xfs_reserve_blocks(mp, &resblks, NULL); +} + +STATIC void +xfs_restore_resvblks(struct xfs_mount *mp) +{ + __uint64_t resblks; + + if (mp->m_resblks_save) { + resblks = mp->m_resblks_save; + mp->m_resblks_save = 0; + } else + resblks = xfs_default_resblks(mp); + + xfs_reserve_blocks(mp, &resblks, NULL); +} + STATIC int xfs_fs_remount( struct super_block *sb, @@ -1318,8 +1341,6 @@ xfs_fs_remount( /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { - __uint64_t resblks; - mp->m_flags &= ~XFS_MOUNT_RDONLY; if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_mountfs_check_barriers(mp); @@ -1342,15 +1363,7 @@ xfs_fs_remount( * Fill out the reserve pool if it is empty. Use the stashed * value if it is non-zero, otherwise go with the default. */ - if (mp->m_resblks_save) { - resblks = mp->m_resblks_save; - mp->m_resblks_save = 0; - } else { - resblks = mp->m_sb.sb_dblocks; - do_div(resblks, 20); - resblks = min_t(__uint64_t, resblks, 1024); - } - xfs_reserve_blocks(mp, &resblks, NULL); + xfs_restore_resvblks(mp); } /* rw -> ro */ @@ -1363,11 +1376,9 @@ xfs_fs_remount( * so that if we get remounted rw, we can return it to the same * size. */ - __uint64_t resblks = 0; xfs_quiesce_data(mp); - mp->m_resblks_save = mp->m_resblks; - xfs_reserve_blocks(mp, &resblks, NULL); + xfs_save_resvblks(mp); xfs_quiesce_attr(mp); mp->m_flags |= XFS_MOUNT_RDONLY; } @@ -1386,10 +1397,21 @@ xfs_fs_freeze( { struct xfs_mount *mp = XFS_M(sb); + xfs_save_resvblks(mp); xfs_quiesce_attr(mp); return -xfs_fs_log_dummy(mp); } +STATIC int +xfs_fs_unfreeze( + struct super_block *sb) +{ + struct xfs_mount *mp = XFS_M(sb); + + xfs_restore_resvblks(mp); + return 0; +} + STATIC int xfs_fs_show_options( struct seq_file *m, @@ -1612,6 +1634,7 @@ static const struct super_operations xfs_super_operations = { .put_super = xfs_fs_put_super, .sync_fs = xfs_fs_sync_fs, .freeze_fs = xfs_fs_freeze, + .unfreeze_fs = xfs_fs_unfreeze, .statfs = xfs_fs_statfs, .remount_fs = xfs_fs_remount, .show_options = xfs_fs_show_options, diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 7f81ed72c87..5061149b2cc 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1091,6 +1091,22 @@ xfs_mount_reset_sbqflags( return xfs_trans_commit(tp, 0); } +__uint64_t +xfs_default_resblks(xfs_mount_t *mp) +{ + __uint64_t resblks; + + /* + * We default to 5% or 1024 fsbs of space reserved, whichever is smaller. + * This may drive us straight to ENOSPC on mount, but that implies + * we were already there on the last unmount. Warn if this occurs. + */ + resblks = mp->m_sb.sb_dblocks; + do_div(resblks, 20); + resblks = min_t(__uint64_t, resblks, 1024); + return resblks; +} + /* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct @@ -1401,18 +1417,14 @@ xfs_mountfs( * when at ENOSPC. This is needed for operations like create with * attr, unwritten extent conversion at ENOSPC, etc. Data allocations * are not allowed to use this reserved space. - * - * We default to 5% or 1024 fsbs of space reserved, whichever is smaller. - * This may drive us straight to ENOSPC on mount, but that implies - * we were already there on the last unmount. Warn if this occurs. */ - resblks = mp->m_sb.sb_dblocks; - do_div(resblks, 20); - resblks = min_t(__uint64_t, resblks, 1024); - error = xfs_reserve_blocks(mp, &resblks, NULL); - if (error) - cmn_err(CE_WARN, "XFS: Unable to allocate reserve blocks. " - "Continuing without a reserve pool."); + if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { + resblks = xfs_default_resblks(mp); + error = xfs_reserve_blocks(mp, &resblks, NULL); + if (error) + cmn_err(CE_WARN, "XFS: Unable to allocate reserve " + "blocks. Continuing without a reserve pool."); + } return 0; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 02d45f213e5..70504fcf14c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -421,6 +421,7 @@ typedef struct xfs_mod_sb { } xfs_mod_sb_t; extern int xfs_log_sbcount(xfs_mount_t *, uint); +extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern void xfs_unmountfs(xfs_mount_t *); -- cgit v1.2.3-70-g09d2 From c854363e80b49dd04a4de18ebc379eb8c8806674 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 6 Feb 2010 12:39:36 +1100 Subject: xfs: Use delayed write for inodes rather than async V2 We currently do background inode flush asynchronously, resulting in inodes being written in whatever order the background writeback issues them. Not only that, there are also blocking and non-blocking asynchronous inode flushes, depending on where the flush comes from. This patch completely removes asynchronous inode writeback. It removes all the strange writeback modes and replaces them with either a synchronous flush or a non-blocking delayed write flush. That is, inode flushes will only issue IO directly if they are synchronous, and background flushing may do nothing if the operation would block (e.g. on a pinned inode or buffer lock). Delayed write flushes will now result in the inode buffer sitting in the delwri queue of the buffer cache to be flushed by either an AIL push or by the xfsbufd timing out the buffer. This will allow accumulation of dirty inode buffers in memory and allow optimisation of inode cluster writeback at the xfsbufd level where we have much greater queue depths than the block layer elevators. We will also get adjacent inode cluster buffer IO merging for free when a later patch in the series allows sorting of the delayed write buffers before dispatch. This effectively means that any inode that is written back by background writeback will be seen as flush locked during AIL pushing, and will result in the buffers being pushed from there. This writeback path is currently non-optimal, but the next patch in the series will fix that problem. A side effect of this delayed write mechanism is that background inode reclaim will no longer directly flush inodes, nor can it wait on the flush lock. The result is that inode reclaim must leave the inode in the reclaimable state until it is clean. Hence attempts to reclaim a dirty inode in the background will simply skip the inode until it is clean and this allows other mechanisms (i.e. xfsbufd) to do more optimal writeback of the dirty buffers. As a result, the inode reclaim code has been rewritten so that it no longer relies on the ambiguous return values of xfs_iflush() to determine whether it is safe to reclaim an inode. Portions of this patch are derived from patches by Christoph Hellwig. Version 2: - cleanup reclaim code as suggested by Christoph - log background reclaim inode flush errors - just pass sync flags to xfs_iflush Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/linux-2.6/xfs_super.c | 4 +- fs/xfs/linux-2.6/xfs_sync.c | 105 +++++++++++++++++++++++++++++++------------ fs/xfs/xfs_inode.c | 75 +++---------------------------- fs/xfs/xfs_inode.h | 10 ----- fs/xfs/xfs_inode_item.c | 10 +++-- fs/xfs/xfs_mount.c | 13 +++++- 6 files changed, 102 insertions(+), 115 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 6ce828e0e17..3b5b46b8e3b 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1064,7 +1064,7 @@ xfs_fs_write_inode( xfs_ilock(ip, XFS_ILOCK_SHARED); xfs_iflock(ip); - error = xfs_iflush(ip, XFS_IFLUSH_SYNC); + error = xfs_iflush(ip, SYNC_WAIT); } else { error = EAGAIN; if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) @@ -1072,7 +1072,7 @@ xfs_fs_write_inode( if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) goto out_unlock; - error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK); + error = xfs_iflush(ip, 0); } out_unlock: diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 525260c7617..a9f6d20aff4 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -270,8 +270,7 @@ xfs_sync_inode_attr( goto out_unlock; } - error = xfs_iflush(ip, (flags & SYNC_WAIT) ? - XFS_IFLUSH_SYNC : XFS_IFLUSH_DELWRI); + error = xfs_iflush(ip, flags); out_unlock: xfs_iunlock(ip, XFS_ILOCK_SHARED); @@ -460,16 +459,18 @@ xfs_quiesce_fs( { int count = 0, pincount; + xfs_reclaim_inodes(mp, 0); xfs_flush_buftarg(mp->m_ddev_targp, 0); - xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC); /* * This loop must run at least twice. The first instance of the loop * will flush most meta data but that will generate more meta data * (typically directory updates). Which then must be flushed and - * logged before we can write the unmount record. + * logged before we can write the unmount record. We also so sync + * reclaim of inodes to catch any that the above delwri flush skipped. */ do { + xfs_reclaim_inodes(mp, SYNC_WAIT); xfs_sync_attr(mp, SYNC_WAIT); pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1); if (!pincount) { @@ -585,7 +586,7 @@ xfs_sync_worker( if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { xfs_log_force(mp, 0); - xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC); + xfs_reclaim_inodes(mp, 0); /* dgc: errors ignored here */ error = xfs_qm_sync(mp, SYNC_TRYLOCK); error = xfs_sync_fsdata(mp, SYNC_TRYLOCK); @@ -719,21 +720,42 @@ __xfs_inode_clear_reclaim_tag( * shutdown EIO unpin and reclaim * clean, unpinned 0 reclaim * stale, unpinned 0 reclaim - * clean, pinned(*) 0 unpin and reclaim - * stale, pinned 0 unpin and reclaim - * dirty, async 0 block on flush lock, reclaim - * dirty, sync flush 0 block on flush lock, reclaim + * clean, pinned(*) 0 requeue + * stale, pinned EAGAIN requeue + * dirty, delwri ok 0 requeue + * dirty, delwri blocked EAGAIN requeue + * dirty, sync flush 0 reclaim * * (*) dgc: I don't think the clean, pinned state is possible but it gets * handled anyway given the order of checks implemented. * + * As can be seen from the table, the return value of xfs_iflush() is not + * sufficient to correctly decide the reclaim action here. The checks in + * xfs_iflush() might look like duplicates, but they are not. + * + * Also, because we get the flush lock first, we know that any inode that has + * been flushed delwri has had the flush completed by the time we check that + * the inode is clean. The clean inode check needs to be done before flushing + * the inode delwri otherwise we would loop forever requeuing clean inodes as + * we cannot tell apart a successful delwri flush and a clean inode from the + * return value of xfs_iflush(). + * + * Note that because the inode is flushed delayed write by background + * writeback, the flush lock may already be held here and waiting on it can + * result in very long latencies. Hence for sync reclaims, where we wait on the + * flush lock, the caller should push out delayed write inodes first before + * trying to reclaim them to minimise the amount of time spent waiting. For + * background relaim, we just requeue the inode for the next pass. + * * Hence the order of actions after gaining the locks should be: * bad => reclaim * shutdown => unpin and reclaim - * pinned => unpin + * pinned, delwri => requeue + * pinned, sync => unpin * stale => reclaim * clean => reclaim - * dirty => flush, wait and reclaim + * dirty, delwri => flush and requeue + * dirty, sync => flush, wait and reclaim */ STATIC int xfs_reclaim_inode( @@ -741,7 +763,7 @@ xfs_reclaim_inode( struct xfs_perag *pag, int sync_mode) { - int error; + int error = 0; /* * The radix tree lock here protects a thread in xfs_iget from racing @@ -761,7 +783,11 @@ xfs_reclaim_inode( write_unlock(&pag->pag_ici_lock); xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_iflock(ip); + if (!xfs_iflock_nowait(ip)) { + if (!(sync_mode & SYNC_WAIT)) + goto out; + xfs_iflock(ip); + } if (is_bad_inode(VFS_I(ip))) goto reclaim; @@ -769,8 +795,13 @@ xfs_reclaim_inode( xfs_iunpin_wait(ip); goto reclaim; } - if (xfs_ipincount(ip)) + if (xfs_ipincount(ip)) { + if (!(sync_mode & SYNC_WAIT)) { + xfs_ifunlock(ip); + goto out; + } xfs_iunpin_wait(ip); + } if (xfs_iflags_test(ip, XFS_ISTALE)) goto reclaim; if (xfs_inode_clean(ip)) @@ -778,27 +809,43 @@ xfs_reclaim_inode( /* Now we have an inode that needs flushing */ error = xfs_iflush(ip, sync_mode); - if (!error) { - switch(sync_mode) { - case XFS_IFLUSH_DELWRI_ELSE_ASYNC: - case XFS_IFLUSH_DELWRI: - case XFS_IFLUSH_ASYNC: - case XFS_IFLUSH_DELWRI_ELSE_SYNC: - case XFS_IFLUSH_SYNC: - /* IO issued, synchronise with IO completion */ - xfs_iflock(ip); - break; - default: - ASSERT(0); - break; - } + if (sync_mode & SYNC_WAIT) { + xfs_iflock(ip); + goto reclaim; } + /* + * When we have to flush an inode but don't have SYNC_WAIT set, we + * flush the inode out using a delwri buffer and wait for the next + * call into reclaim to find it in a clean state instead of waiting for + * it now. We also don't return errors here - if the error is transient + * then the next reclaim pass will flush the inode, and if the error + * is permanent then the next sync reclaim will relcaim the inode and + * pass on the error. + */ + if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_WARN, ip->i_mount, + "inode 0x%llx background reclaim flush failed with %d", + (long long)ip->i_ino, error); + } +out: + xfs_iflags_clear(ip, XFS_IRECLAIM); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + /* + * We could return EAGAIN here to make reclaim rescan the inode tree in + * a short while. However, this just burns CPU time scanning the tree + * waiting for IO to complete and xfssyncd never goes back to the idle + * state. Instead, return 0 to let the next scheduled background reclaim + * attempt to reclaim the inode again. + */ + return 0; + reclaim: xfs_ifunlock(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_ireclaim(ip); - return 0; + return error; + } int diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 8d0666dd170..fa31360046d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2835,8 +2835,6 @@ xfs_iflush( xfs_dinode_t *dip; xfs_mount_t *mp; int error; - int noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK); - enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) }; XFS_STATS_INC(xs_iflush_count); @@ -2859,7 +2857,7 @@ xfs_iflush( * in the same cluster are dirty, they will probably write the inode * out for us if they occur after the log force completes. */ - if (noblock && xfs_ipincount(ip)) { + if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) { xfs_iunpin_nowait(ip); xfs_ifunlock(ip); return EAGAIN; @@ -2892,61 +2890,11 @@ xfs_iflush( return XFS_ERROR(EIO); } - /* - * Decide how buffer will be flushed out. This is done before - * the call to xfs_iflush_int because this field is zeroed by it. - */ - if (iip != NULL && iip->ili_format.ilf_fields != 0) { - /* - * Flush out the inode buffer according to the directions - * of the caller. In the cases where the caller has given - * us a choice choose the non-delwri case. This is because - * the inode is in the AIL and we need to get it out soon. - */ - switch (flags) { - case XFS_IFLUSH_SYNC: - case XFS_IFLUSH_DELWRI_ELSE_SYNC: - flags = 0; - break; - case XFS_IFLUSH_ASYNC_NOBLOCK: - case XFS_IFLUSH_ASYNC: - case XFS_IFLUSH_DELWRI_ELSE_ASYNC: - flags = INT_ASYNC; - break; - case XFS_IFLUSH_DELWRI: - flags = INT_DELWRI; - break; - default: - ASSERT(0); - flags = 0; - break; - } - } else { - switch (flags) { - case XFS_IFLUSH_DELWRI_ELSE_SYNC: - case XFS_IFLUSH_DELWRI_ELSE_ASYNC: - case XFS_IFLUSH_DELWRI: - flags = INT_DELWRI; - break; - case XFS_IFLUSH_ASYNC_NOBLOCK: - case XFS_IFLUSH_ASYNC: - flags = INT_ASYNC; - break; - case XFS_IFLUSH_SYNC: - flags = 0; - break; - default: - ASSERT(0); - flags = 0; - break; - } - } - /* * Get the buffer containing the on-disk inode. */ error = xfs_itobp(mp, NULL, ip, &dip, &bp, - noblock ? XBF_TRYLOCK : XBF_LOCK); + (flags & SYNC_WAIT) ? XBF_LOCK : XBF_TRYLOCK); if (error || !bp) { xfs_ifunlock(ip); return error; @@ -2974,13 +2922,10 @@ xfs_iflush( if (error) goto cluster_corrupt_out; - if (flags & INT_DELWRI) { - xfs_bdwrite(mp, bp); - } else if (flags & INT_ASYNC) { - error = xfs_bawrite(mp, bp); - } else { + if (flags & SYNC_WAIT) error = xfs_bwrite(mp, bp); - } + else + xfs_bdwrite(mp, bp); return error; corrupt_out: @@ -3015,16 +2960,6 @@ xfs_iflush_int( iip = ip->i_itemp; mp = ip->i_mount; - - /* - * If the inode isn't dirty, then just release the inode - * flush lock and do nothing. - */ - if (xfs_inode_clean(ip)) { - xfs_ifunlock(ip); - return 0; - } - /* set *dip = inode's place in the buffer */ dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 8b618ea4d69..6c912b02759 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -419,16 +419,6 @@ static inline void xfs_ifunlock(xfs_inode_t *ip) #define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT) #define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT) -/* - * Flags for xfs_iflush() - */ -#define XFS_IFLUSH_DELWRI_ELSE_SYNC 1 -#define XFS_IFLUSH_DELWRI_ELSE_ASYNC 2 -#define XFS_IFLUSH_SYNC 3 -#define XFS_IFLUSH_ASYNC 4 -#define XFS_IFLUSH_DELWRI 5 -#define XFS_IFLUSH_ASYNC_NOBLOCK 6 - /* * Flags for xfs_itruncate_start(). */ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 48ec1c0b23c..207553e8295 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -866,10 +866,14 @@ xfs_inode_item_push( iip->ili_format.ilf_fields != 0); /* - * Write out the inode. The completion routine ('iflush_done') will - * pull it from the AIL, mark it clean, unlock the flush lock. + * Push the inode to it's backing buffer. This will not remove the + * inode from the AIL - a further push will be required to trigger a + * buffer push. However, this allows all the dirty inodes to be pushed + * to the buffer before it is pushed to disk. THe buffer IO completion + * will pull th einode from the AIL, mark it clean and unlock the flush + * lock. */ - (void) xfs_iflush(ip, XFS_IFLUSH_ASYNC); + (void) xfs_iflush(ip, 0); xfs_iunlock(ip, XFS_ILOCK_SHARED); return; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 5061149b2cc..6afaaeb2950 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1468,7 +1468,18 @@ xfs_unmountfs( * need to force the log first. */ xfs_log_force(mp, XFS_LOG_SYNC); - xfs_reclaim_inodes(mp, XFS_IFLUSH_ASYNC); + + /* + * Do a delwri reclaim pass first so that as many dirty inodes are + * queued up for IO as possible. Then flush the buffers before making + * a synchronous path to catch all the remaining inodes are reclaimed. + * This makes the reclaim process as quick as possible by avoiding + * synchronous writeout and blocking on inodes already in the delwri + * state as much as possible. + */ + xfs_reclaim_inodes(mp, 0); + XFS_bflush(mp->m_ddev_targp); + xfs_reclaim_inodes(mp, SYNC_WAIT); xfs_qm_unmount(mp); -- cgit v1.2.3-70-g09d2 From 07fec73625dc0db6f9aed68019918208a2ca53f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Feb 2010 11:43:49 +1100 Subject: xfs: log changed inodes instead of writing them synchronously When an inode has already be flushed delayed write, xfs_inode_clean() returns true and hence xfs_fs_write_inode() can return on a synchronous inode write without having written the inode. Currently these sycnhronous writes only come sync(1), unmount, a sycnhronous NFS export and cachefiles so should be relatively rare and out of common performance paths. Realistically, a synchronous inode write is not necessary here; we can avoid writing the inode by logging any non-transactional changes that are pending. This needs to be done with synchronous transactions, but it avoids seeking between the log and inode clusters as we do now. We don't force the log if the inode is pinned, though, so this differs from the fsync case. For normal sys_sync and unmount behaviour this is fine because we do a synchronous log force in xfs_sync_data which is called from the ->sync_fs code. It does however break the NFS synchronous export guarantees for now, but work is under way to fix this at a higher level or for the higher level to provide an additional flag in the writeback control to tell us that a log force is needed. Portions of this patch are based on work from Dave Chinner. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Alex Elder --- fs/xfs/linux-2.6/xfs_super.c | 111 ++++++++++++++++++++++++++++++++----------- 1 file changed, 82 insertions(+), 29 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 3b5b46b8e3b..25ea2408118 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1021,12 +1021,45 @@ xfs_fs_dirty_inode( XFS_I(inode)->i_update_core = 1; } -/* - * Attempt to flush the inode, this will actually fail - * if the inode is pinned, but we dirty the inode again - * at the point when it is unpinned after a log write, - * since this is when the inode itself becomes flushable. - */ +STATIC int +xfs_log_inode( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + + xfs_iunlock(ip, XFS_ILOCK_SHARED); + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0); + + if (error) { + xfs_trans_cancel(tp, 0); + /* we need to return with the lock hold shared */ + xfs_ilock(ip, XFS_ILOCK_SHARED); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + + /* + * Note - it's possible that we might have pushed ourselves out of the + * way during trans_reserve which would flush the inode. But there's + * no guarantee that the inode buffer has actually gone out yet (it's + * delwri). Plus the buffer could be pinned anyway if it's part of + * an inode in another recent transaction. So we play it safe and + * fire off the transaction anyway. + */ + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + xfs_trans_ihold(tp, ip); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + xfs_trans_set_sync(tp); + error = xfs_trans_commit(tp, 0); + xfs_ilock_demote(ip, XFS_ILOCK_EXCL); + + return error; +} + STATIC int xfs_fs_write_inode( struct inode *inode, @@ -1034,7 +1067,7 @@ xfs_fs_write_inode( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - int error = 0; + int error = EAGAIN; xfs_itrace_entry(ip); @@ -1045,35 +1078,55 @@ xfs_fs_write_inode( error = xfs_wait_on_pages(ip, 0, -1); if (error) goto out; - } - - /* - * Bypass inodes which have already been cleaned by - * the inode flush clustering code inside xfs_iflush - */ - if (xfs_inode_clean(ip)) - goto out; - /* - * We make this non-blocking if the inode is contended, return - * EAGAIN to indicate to the caller that they did not succeed. - * This prevents the flush path from blocking on inodes inside - * another operation right now, they get caught later by xfs_sync. - */ - if (sync) { + /* + * Make sure the inode has hit stable storage. By using the + * log and the fsync transactions we reduce the IOs we have + * to do here from two (log and inode) to just the log. + * + * Note: We still need to do a delwri write of the inode after + * this to flush it to the backing buffer so that bulkstat + * works properly if this is the first time the inode has been + * written. Because we hold the ilock atomically over the + * transaction commit and the inode flush we are guaranteed + * that the inode is not pinned when it returns. If the flush + * lock is already held, then the inode has already been + * flushed once and we don't need to flush it again. Hence + * the code will only flush the inode if it isn't already + * being flushed. + */ xfs_ilock(ip, XFS_ILOCK_SHARED); - xfs_iflock(ip); - - error = xfs_iflush(ip, SYNC_WAIT); + if (ip->i_update_core) { + error = xfs_log_inode(ip); + if (error) + goto out_unlock; + } } else { - error = EAGAIN; + /* + * We make this non-blocking if the inode is contended, return + * EAGAIN to indicate to the caller that they did not succeed. + * This prevents the flush path from blocking on inodes inside + * another operation right now, they get caught later by xfs_sync. + */ if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) goto out; - if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) - goto out_unlock; + } + + if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) + goto out_unlock; - error = xfs_iflush(ip, 0); + /* + * Now we have the flush lock and the inode is not pinned, we can check + * if the inode is really clean as we know that there are no pending + * transaction completions, it is not waiting on the delayed write + * queue and there is no IO in progress. + */ + if (xfs_inode_clean(ip)) { + xfs_ifunlock(ip); + error = 0; + goto out_unlock; } + error = xfs_iflush(ip, 0); out_unlock: xfs_iunlock(ip, XFS_ILOCK_SHARED); -- cgit v1.2.3-70-g09d2 From 26821ed40b4230259e770c9911180f38fcaa6f59 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Mar 2010 09:21:21 +0100 Subject: make sure data is on disk before calling ->write_inode Similar to the fsync issue fixed a while ago in commit 2daea67e966dc0c42067ebea015ddac6834cef88 we need to write for data to actually hit the disk before writing out the metadata to guarantee data integrity for filesystems that modify the inode in the data I/O completion path. Currently XFS and NFS handle this manually, and AFS has a write_inode method that does nothing but waiting for data, while others are possibly missing out on this. Fortunately this change has a lot less impact than the fsync change as none of the write_inode methods starts data writeout of any form by itself. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/afs/internal.h | 1 - fs/afs/super.c | 1 - fs/afs/write.c | 21 --------------------- fs/fs-writeback.c | 15 ++++++++++----- fs/nfs/inode.c | 7 +------ fs/xfs/linux-2.6/xfs_super.c | 4 ---- 6 files changed, 11 insertions(+), 38 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 6ece2a13bf7..c54dad4e606 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -733,7 +733,6 @@ extern int afs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata); extern int afs_writepage(struct page *, struct writeback_control *); extern int afs_writepages(struct address_space *, struct writeback_control *); -extern int afs_write_inode(struct inode *, int); extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); diff --git a/fs/afs/super.c b/fs/afs/super.c index e1ea1c240b6..14f6431598a 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -48,7 +48,6 @@ struct file_system_type afs_fs_type = { static const struct super_operations afs_super_ops = { .statfs = afs_statfs, .alloc_inode = afs_alloc_inode, - .write_inode = afs_write_inode, .destroy_inode = afs_destroy_inode, .clear_inode = afs_clear_inode, .put_super = afs_put_super, diff --git a/fs/afs/write.c b/fs/afs/write.c index 5e15a21dbf9..3bed54a294d 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -584,27 +584,6 @@ int afs_writepages(struct address_space *mapping, return ret; } -/* - * write an inode back - */ -int afs_write_inode(struct inode *inode, int sync) -{ - struct afs_vnode *vnode = AFS_FS_I(inode); - int ret; - - _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode); - - ret = 0; - if (sync) { - ret = filemap_fdatawait(inode->i_mapping); - if (ret < 0) - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - } - - _leave(" = %d", ret); - return ret; -} - /* * completion of write to server */ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1a7c42c64ff..5f2721b1e4b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -461,15 +461,20 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) ret = do_writepages(mapping, wbc); - /* Don't write the inode if only I_DIRTY_PAGES was set */ - if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - int err = write_inode(inode, wait); + /* + * Make sure to wait on the data before writing out the metadata. + * This is important for filesystems that modify metadata on data + * I/O completion. + */ + if (wait) { + int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } - if (wait) { - int err = filemap_fdatawait(mapping); + /* Don't write the inode if only I_DIRTY_PAGES was set */ + if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + int err = write_inode(inode, wait); if (ret == 0) ret = err; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7570573bdb3..5ecd952cae1 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -101,12 +101,7 @@ int nfs_write_inode(struct inode *inode, int sync) { int ret; - if (sync) { - ret = filemap_fdatawait(inode->i_mapping); - if (ret == 0) - ret = nfs_commit_inode(inode, FLUSH_SYNC); - } else - ret = nfs_commit_inode(inode, 0); + ret = nfs_commit_inode(inode, sync ? FLUSH_SYNC : 0); if (ret >= 0) return 0; __mark_inode_dirty(inode, I_DIRTY_DATASYNC); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 25ea2408118..8f117db6070 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1075,10 +1075,6 @@ xfs_fs_write_inode( return XFS_ERROR(EIO); if (sync) { - error = xfs_wait_on_pages(ip, 0, -1); - if (error) - goto out; - /* * Make sure the inode has hit stable storage. By using the * log and the fsync transactions we reduce the IOs we have -- cgit v1.2.3-70-g09d2 From a9185b41a4f84971b930c519f0c63bd450c4810d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Mar 2010 09:21:37 +0100 Subject: pass writeback_control to ->write_inode This gives the filesystem more information about the writeback that is happening. Trond requested this for the NFS unstable write handling, and other filesystems might benefit from this too by beeing able to distinguish between the different callers in more detail. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/adfs/adfs.h | 2 +- fs/adfs/inode.c | 5 +++-- fs/affs/affs.h | 3 ++- fs/affs/inode.c | 2 +- fs/bfs/inode.c | 5 +++-- fs/btrfs/ctree.h | 2 +- fs/btrfs/inode.c | 4 ++-- fs/exofs/exofs.h | 2 +- fs/exofs/inode.c | 4 ++-- fs/ext2/ext2.h | 2 +- fs/ext2/inode.c | 11 +++++++++-- fs/ext3/inode.c | 4 ++-- fs/ext4/ext4.h | 2 +- fs/ext4/inode.c | 6 +++--- fs/fat/inode.c | 9 +++++++-- fs/fs-writeback.c | 11 +++++------ fs/gfs2/super.c | 5 +++-- fs/hfs/hfs_fs.h | 2 +- fs/hfs/inode.c | 2 +- fs/hfsplus/super.c | 3 ++- fs/jfs/inode.c | 5 ++++- fs/jfs/jfs_inode.h | 2 +- fs/minix/inode.c | 8 +++++--- fs/nfs/inode.c | 5 +++-- fs/nfs/internal.h | 2 +- fs/ntfs/dir.c | 2 +- fs/ntfs/file.c | 2 +- fs/ntfs/inode.c | 2 +- fs/ntfs/inode.h | 4 ++-- fs/ntfs/super.c | 8 ++++++++ fs/omfs/inode.c | 10 ++++++++-- fs/reiserfs/inode.c | 4 ++-- fs/sysv/inode.c | 10 ++++++++-- fs/sysv/sysv.h | 2 +- fs/ubifs/dir.c | 2 +- fs/ubifs/file.c | 8 ++++---- fs/ubifs/super.c | 2 +- fs/udf/inode.c | 4 ++-- fs/udf/udfdecl.h | 2 +- fs/ufs/inode.c | 5 +++-- fs/ufs/ufs.h | 2 +- fs/xfs/linux-2.6/xfs_super.c | 4 ++-- include/linux/ext3_fs.h | 2 +- include/linux/fs.h | 2 +- include/linux/reiserfs_fs.h | 2 +- 45 files changed, 115 insertions(+), 72 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_super.c') diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index 9cc18775b83..2ff622f6f54 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -121,7 +121,7 @@ struct adfs_discmap { /* Inode stuff */ struct inode *adfs_iget(struct super_block *sb, struct object_info *obj); -int adfs_write_inode(struct inode *inode,int unused); +int adfs_write_inode(struct inode *inode, struct writeback_control *wbc); int adfs_notify_change(struct dentry *dentry, struct iattr *attr); /* map.c */ diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 3f57ce4bee5..0f5e3097813 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -9,6 +9,7 @@ */ #include #include +#include #include "adfs.h" /* @@ -360,7 +361,7 @@ out: * The adfs-specific inode data has already been updated by * adfs_notify_change() */ -int adfs_write_inode(struct inode *inode, int wait) +int adfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct super_block *sb = inode->i_sb; struct object_info obj; @@ -375,7 +376,7 @@ int adfs_write_inode(struct inode *inode, int wait) obj.attr = ADFS_I(inode)->attr; obj.size = inode->i_size; - ret = adfs_dir_update(sb, &obj, wait); + ret = adfs_dir_update(sb, &obj, wbc->sync_mode == WB_SYNC_ALL); unlock_kernel(); return ret; } diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 0e40caaba45..861dae68ac1 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -175,7 +175,8 @@ extern void affs_delete_inode(struct inode *inode); extern void affs_clear_inode(struct inode *inode); extern struct inode *affs_iget(struct super_block *sb, unsigned long ino); -extern int affs_write_inode(struct inode *inode, int); +extern int affs_write_inode(struct inode *inode, + struct writeback_control *wbc); extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s32 type); /* file.c */ diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 3c4ec7d864c..c9744d771d9 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -166,7 +166,7 @@ bad_inode: } int -affs_write_inode(struct inode *inode, int unused) +affs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct super_block *sb = inode->i_sb; struct buffer_head *bh; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 8f3d9fd8960..f22a7d3dc36 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "bfs.h" @@ -98,7 +99,7 @@ error: return ERR_PTR(-EIO); } -static int bfs_write_inode(struct inode *inode, int wait) +static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct bfs_sb_info *info = BFS_SB(inode->i_sb); unsigned int ino = (u16)inode->i_ino; @@ -147,7 +148,7 @@ static int bfs_write_inode(struct inode *inode, int wait) di->i_eoffset = cpu_to_le32(i_sblock * BFS_BSIZE + inode->i_size - 1); mark_buffer_dirty(bh); - if (wait) { + if (wbc->sync_mode == WB_SYNC_ALL) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) err = -EIO; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2aa8ec6a098..8b5cfdd4bfc 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2326,7 +2326,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_delete_inode(struct inode *inode); void btrfs_put_inode(struct inode *inode); -int btrfs_write_inode(struct inode *inode, int wait); +int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); void btrfs_dirty_inode(struct inode *inode); struct inode *btrfs_alloc_inode(struct super_block *sb); void btrfs_destroy_inode(struct inode *inode); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4deb280f896..c41db6d45ab 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3968,7 +3968,7 @@ err: return ret; } -int btrfs_write_inode(struct inode *inode, int wait) +int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; @@ -3977,7 +3977,7 @@ int btrfs_write_inode(struct inode *inode, int wait) if (root->fs_info->btree_inode == inode) return 0; - if (wait) { + if (wbc->sync_mode == WB_SYNC_ALL) { trans = btrfs_join_transaction(root, 1); btrfs_set_trans_block_group(trans, inode); ret = btrfs_commit_transaction(trans, root); diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index 59b8bf2825c..8442e353309 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -261,7 +261,7 @@ int exofs_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata); extern struct inode *exofs_iget(struct super_block *, unsigned long); struct inode *exofs_new_inode(struct inode *, int); -extern int exofs_write_inode(struct inode *, int); +extern int exofs_write_inode(struct inode *, struct writeback_control *wbc); extern void exofs_delete_inode(struct inode *); /* dir.c: */ diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 5514f3c2c2f..a17e4b733e3 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1280,9 +1280,9 @@ out: return ret; } -int exofs_write_inode(struct inode *inode, int wait) +int exofs_write_inode(struct inode *inode, struct writeback_control *wbc) { - return exofs_update_inode(inode, wait); + return exofs_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } /* diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 061914add3c..0b038e47ad2 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -118,7 +118,7 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned); /* inode.c */ extern struct inode *ext2_iget (struct super_block *, unsigned long); -extern int ext2_write_inode (struct inode *, int); +extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_delete_inode (struct inode *); extern int ext2_sync_inode (struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 71b032c65a0..36ae1cac767 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -41,6 +41,8 @@ MODULE_AUTHOR("Remy Card and others"); MODULE_DESCRIPTION("Second Extended Filesystem"); MODULE_LICENSE("GPL"); +static int __ext2_write_inode(struct inode *inode, int do_sync); + /* * Test whether an inode is a fast symlink. */ @@ -64,7 +66,7 @@ void ext2_delete_inode (struct inode * inode) goto no_delete; EXT2_I(inode)->i_dtime = get_seconds(); mark_inode_dirty(inode); - ext2_write_inode(inode, inode_needs_sync(inode)); + __ext2_write_inode(inode, inode_needs_sync(inode)); inode->i_size = 0; if (inode->i_blocks) @@ -1335,7 +1337,7 @@ bad_inode: return ERR_PTR(ret); } -int ext2_write_inode(struct inode *inode, int do_sync) +static int __ext2_write_inode(struct inode *inode, int do_sync) { struct ext2_inode_info *ei = EXT2_I(inode); struct super_block *sb = inode->i_sb; @@ -1440,6 +1442,11 @@ int ext2_write_inode(struct inode *inode, int do_sync) return err; } +int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + int ext2_sync_inode(struct inode *inode) { struct writeback_control wbc = { diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 455e6e6e5cb..7aca55fcc97 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3096,7 +3096,7 @@ out_brelse: * `stuff()' is running, and the new i_size will be lost. Plus the inode * will no longer be on the superblock's dirty inode list. */ -int ext3_write_inode(struct inode *inode, int wait) +int ext3_write_inode(struct inode *inode, struct writeback_control *wbc) { if (current->flags & PF_MEMALLOC) return 0; @@ -3107,7 +3107,7 @@ int ext3_write_inode(struct inode *inode, int wait) return -EIO; } - if (!wait) + if (wbc->sync_mode != WB_SYNC_ALL) return 0; return ext3_force_commit(inode->i_sb); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4cedc91ec59..50af1a2c65e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1416,7 +1416,7 @@ int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); extern struct inode *ext4_iget(struct super_block *, unsigned long); -extern int ext4_write_inode(struct inode *, int); +extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e11952404e0..d01a6cdbf85 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5177,7 +5177,7 @@ out_brelse: * `stuff()' is running, and the new i_size will be lost. Plus the inode * will no longer be on the superblock's dirty inode list. */ -int ext4_write_inode(struct inode *inode, int wait) +int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; @@ -5191,7 +5191,7 @@ int ext4_write_inode(struct inode *inode, int wait) return -EIO; } - if (!wait) + if (wbc->sync_mode != WB_SYNC_ALL) return 0; err = ext4_force_commit(inode->i_sb); @@ -5201,7 +5201,7 @@ int ext4_write_inode(struct inode *inode, int wait) err = ext4_get_inode_loc(inode, &iloc); if (err) return err; - if (wait) + if (wbc->sync_mode == WB_SYNC_ALL) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { ext4_error(inode->i_sb, __func__, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 14da530b05c..fbeecdc194d 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -577,7 +577,7 @@ static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi, return i_pos; } -static int fat_write_inode(struct inode *inode, int wait) +static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); @@ -634,9 +634,14 @@ retry: return err; } +static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + int fat_sync_inode(struct inode *inode) { - return fat_write_inode(inode, 1); + return __fat_write_inode(inode, 1); } EXPORT_SYMBOL_GPL(fat_sync_inode); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 5f2721b1e4b..76fc4d594ac 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -381,10 +381,10 @@ static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this) move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this); } -static int write_inode(struct inode *inode, int sync) +static int write_inode(struct inode *inode, struct writeback_control *wbc) { if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) - return inode->i_sb->s_op->write_inode(inode, sync); + return inode->i_sb->s_op->write_inode(inode, wbc); return 0; } @@ -421,7 +421,6 @@ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; - int wait = wbc->sync_mode == WB_SYNC_ALL; unsigned dirty; int ret; @@ -439,7 +438,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * We'll have another go at writing back this inode when we * completed a full scan of b_io. */ - if (!wait) { + if (wbc->sync_mode != WB_SYNC_ALL) { requeue_io(inode); return 0; } @@ -466,7 +465,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * This is important for filesystems that modify metadata on data * I/O completion. */ - if (wait) { + if (wbc->sync_mode == WB_SYNC_ALL) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; @@ -474,7 +473,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - int err = write_inode(inode, wait); + int err = write_inode(inode, wbc); if (ret == 0) ret = err; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index e5e22629da6..ca87598ead7 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "gfs2.h" #include "incore.h" @@ -711,7 +712,7 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp) * Returns: errno */ -static int gfs2_write_inode(struct inode *inode, int sync) +static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -745,7 +746,7 @@ static int gfs2_write_inode(struct inode *inode, int sync) do_unlock: gfs2_glock_dq_uninit(&gh); do_flush: - if (sync != 0) + if (wbc->sync_mode == WB_SYNC_ALL) gfs2_log_flush(GFS2_SB(inode), ip->i_gl); return ret; } diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 052387e1167..fe35e3b626c 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -188,7 +188,7 @@ extern const struct address_space_operations hfs_btree_aops; extern struct inode *hfs_new_inode(struct inode *, struct qstr *, int); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); -extern int hfs_write_inode(struct inode *, int); +extern int hfs_write_inode(struct inode *, struct writeback_control *); extern int hfs_inode_setattr(struct dentry *, struct iattr *); extern void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, __be32 log_size, __be32 phys_size, u32 clump_size); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index a1cbff2b4d9..14f5cb1b9fd 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -381,7 +381,7 @@ void hfs_inode_write_fork(struct inode *inode, struct hfs_extent *ext, HFS_SB(inode->i_sb)->alloc_blksz); } -int hfs_write_inode(struct inode *inode, int unused) +int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct inode *main_inode = inode; struct hfs_find_data fd; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 43022f3d514..74b473a8ef9 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -87,7 +87,8 @@ bad_inode: return ERR_PTR(err); } -static int hfsplus_write_inode(struct inode *inode, int unused) +static int hfsplus_write_inode(struct inode *inode, + struct writeback_control *wbc) { struct hfsplus_vh *vhdr; int ret = 0; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index b2ae190a77b..182b78cc3e6 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" @@ -120,8 +121,10 @@ int jfs_commit_inode(struct inode *inode, int wait) return rc; } -int jfs_write_inode(struct inode *inode, int wait) +int jfs_write_inode(struct inode *inode, struct writeback_control *wbc) { + int wait = wbc->sync_mode == WB_SYNC_ALL; + if (test_cflag(COMMIT_Nolink, inode)) return 0; /* diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 1eff7db34d6..15902b03c2a 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -26,7 +26,7 @@ extern long jfs_ioctl(struct file *, unsigned int, unsigned long); extern long jfs_compat_ioctl(struct file *, unsigned int, unsigned long); extern struct inode *jfs_iget(struct super_block *, unsigned long); extern int jfs_commit_inode(struct inode *, int); -extern int jfs_write_inode(struct inode*, int); +extern int jfs_write_inode(struct inode *, struct writeback_control *); extern void jfs_delete_inode(struct inode *); extern void jfs_dirty_inode(struct inode *); extern void jfs_truncate(struct inode *); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 74ea82d7216..756f8c93780 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -17,8 +17,10 @@ #include #include #include +#include -static int minix_write_inode(struct inode * inode, int wait); +static int minix_write_inode(struct inode *inode, + struct writeback_control *wbc); static int minix_statfs(struct dentry *dentry, struct kstatfs *buf); static int minix_remount (struct super_block * sb, int * flags, char * data); @@ -552,7 +554,7 @@ static struct buffer_head * V2_minix_update_inode(struct inode * inode) return bh; } -static int minix_write_inode(struct inode *inode, int wait) +static int minix_write_inode(struct inode *inode, struct writeback_control *wbc) { int err = 0; struct buffer_head *bh; @@ -563,7 +565,7 @@ static int minix_write_inode(struct inode *inode, int wait) bh = V2_minix_update_inode(inode); if (!bh) return -EIO; - if (wait && buffer_dirty(bh)) { + if (wbc->sync_mode == WB_SYNC_ALL && buffer_dirty(bh)) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) { printk("IO error syncing minix inode [%s:%08lx]\n", diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 5ecd952cae1..7f9ecc46f3f 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -97,11 +97,12 @@ u64 nfs_compat_user_ino64(u64 fileid) return ino; } -int nfs_write_inode(struct inode *inode, int sync) +int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; - ret = nfs_commit_inode(inode, sync ? FLUSH_SYNC : 0); + ret = nfs_commit_inode(inode, + wbc->sync_mode == WB_SYNC_ALL ? FLUSH_SYNC : 0); if (ret >= 0) return 0; __mark_inode_dirty(inode, I_DIRTY_DATASYNC); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 29e464d23b3..11f82f03c5d 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -211,7 +211,7 @@ extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask); extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_destroy_inode(struct inode *); -extern int nfs_write_inode(struct inode *,int); +extern int nfs_write_inode(struct inode *, struct writeback_control *); extern void nfs_clear_inode(struct inode *); #ifdef CONFIG_NFS_V4 extern void nfs4_clear_inode(struct inode *); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 5a9e34475e3..9173e82a45d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1545,7 +1545,7 @@ static int ntfs_dir_fsync(struct file *filp, struct dentry *dentry, write_inode_now(bmp_vi, !datasync); iput(bmp_vi); } - ret = ntfs_write_inode(vi, 1); + ret = __ntfs_write_inode(vi, 1); write_inode_now(vi, !datasync); err = sync_blockdev(vi->i_sb->s_bdev); if (unlikely(err && !ret)) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 43179ddd336..b681c71d706 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2182,7 +2182,7 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, ntfs_debug("Entering for inode 0x%lx.", vi->i_ino); BUG_ON(S_ISDIR(vi->i_mode)); if (!datasync || !NInoNonResident(NTFS_I(vi))) - ret = ntfs_write_inode(vi, 1); + ret = __ntfs_write_inode(vi, 1); write_inode_now(vi, !datasync); /* * NOTE: If we were to use mapping->private_list (see ext2 and diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index dc2505abb6d..4b57fb1eac2 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2957,7 +2957,7 @@ out: * * Return 0 on success and -errno on error. */ -int ntfs_write_inode(struct inode *vi, int sync) +int __ntfs_write_inode(struct inode *vi, int sync) { sle64 nt; ntfs_inode *ni = NTFS_I(vi); diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h index 117eaf8032a..9a113544605 100644 --- a/fs/ntfs/inode.h +++ b/fs/ntfs/inode.h @@ -307,12 +307,12 @@ extern void ntfs_truncate_vfs(struct inode *vi); extern int ntfs_setattr(struct dentry *dentry, struct iattr *attr); -extern int ntfs_write_inode(struct inode *vi, int sync); +extern int __ntfs_write_inode(struct inode *vi, int sync); static inline void ntfs_commit_inode(struct inode *vi) { if (!is_bad_inode(vi)) - ntfs_write_inode(vi, 1); + __ntfs_write_inode(vi, 1); return; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 80b04770e8e..1cf39dfaee7 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -39,6 +39,7 @@ #include "dir.h" #include "debug.h" #include "index.h" +#include "inode.h" #include "aops.h" #include "layout.h" #include "malloc.h" @@ -2662,6 +2663,13 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs) return 0; } +#ifdef NTFS_RW +static int ntfs_write_inode(struct inode *vi, struct writeback_control *wbc) +{ + return __ntfs_write_inode(vi, wbc->sync_mode == WB_SYNC_ALL); +} +#endif + /** * The complete super operations. */ diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index f3b7c1541f3..75d9b5ba1d4 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "omfs.h" @@ -89,7 +90,7 @@ static void omfs_update_checksums(struct omfs_inode *oi) oi->i_head.h_check_xor = xor; } -static int omfs_write_inode(struct inode *inode, int wait) +static int __omfs_write_inode(struct inode *inode, int wait) { struct omfs_inode *oi; struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb); @@ -162,9 +163,14 @@ out: return ret; } +static int omfs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return __omfs_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + int omfs_sync_inode(struct inode *inode) { - return omfs_write_inode(inode, 1); + return __omfs_write_inode(inode, 1); } /* diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 2df0f5c7c60..0d651f980a8 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1615,7 +1615,7 @@ int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, ** to properly mark inodes for datasync and such, but only actually ** does something when called for a synchronous update. */ -int reiserfs_write_inode(struct inode *inode, int do_sync) +int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct reiserfs_transaction_handle th; int jbegin_count = 1; @@ -1627,7 +1627,7 @@ int reiserfs_write_inode(struct inode *inode, int do_sync) ** inode needs to reach disk for safety, and they can safely be ** ignored because the altered inode has already been logged. */ - if (do_sync && !(current->flags & PF_MEMALLOC)) { + if (wbc->sync_mode == WB_SYNC_ALL && !(current->flags & PF_MEMALLOC)) { reiserfs_write_lock(inode->i_sb); if (!journal_begin(&th, inode->i_sb, jbegin_count)) { reiserfs_update_sd(&th, inode); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 9824743832a..4573734d723 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include "sysv.h" @@ -246,7 +247,7 @@ bad_inode: return ERR_PTR(-EIO); } -int sysv_write_inode(struct inode *inode, int wait) +static int __sysv_write_inode(struct inode *inode, int wait) { struct super_block * sb = inode->i_sb; struct sysv_sb_info * sbi = SYSV_SB(sb); @@ -296,9 +297,14 @@ int sysv_write_inode(struct inode *inode, int wait) return 0; } +int sysv_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return __sysv_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + int sysv_sync_inode(struct inode *inode) { - return sysv_write_inode(inode, 1); + return __sysv_write_inode(inode, 1); } static void sysv_delete_inode(struct inode *inode) diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index 53786eb5cf6..94cb9b4d76c 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -142,7 +142,7 @@ extern int __sysv_write_begin(struct file *file, struct address_space *mapping, /* inode.c */ extern struct inode *sysv_iget(struct super_block *, unsigned int); -extern int sysv_write_inode(struct inode *, int); +extern int sysv_write_inode(struct inode *, struct writeback_control *wbc); extern int sysv_sync_inode(struct inode *); extern void sysv_set_inode(struct inode *, dev_t); extern int sysv_getattr(struct vfsmount *, struct dentry *, struct kstat *); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 552fb0111ff..401e503d44a 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1120,7 +1120,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, if (release) ubifs_release_budget(c, &ino_req); if (IS_SYNC(old_inode)) - err = old_inode->i_sb->s_op->write_inode(old_inode, 1); + err = old_inode->i_sb->s_op->write_inode(old_inode, NULL); return err; out_cancel: diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 16a6444330e..e26c02ab6cd 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1011,7 +1011,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) /* Is the page fully inside @i_size? */ if (page->index < end_index) { if (page->index >= synced_i_size >> PAGE_CACHE_SHIFT) { - err = inode->i_sb->s_op->write_inode(inode, 1); + err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) goto out_unlock; /* @@ -1039,7 +1039,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) kunmap_atomic(kaddr, KM_USER0); if (i_size > synced_i_size) { - err = inode->i_sb->s_op->write_inode(inode, 1); + err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) goto out_unlock; } @@ -1242,7 +1242,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, if (release) ubifs_release_budget(c, &req); if (IS_SYNC(inode)) - err = inode->i_sb->s_op->write_inode(inode, 1); + err = inode->i_sb->s_op->write_inode(inode, NULL); return err; out: @@ -1316,7 +1316,7 @@ int ubifs_fsync(struct file *file, struct dentry *dentry, int datasync) * the inode unless this is a 'datasync()' call. */ if (!datasync || (inode->i_state & I_DIRTY_DATASYNC)) { - err = inode->i_sb->s_op->write_inode(inode, 1); + err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) return err; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 43f9d19a6f3..4d2f2157dd3 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -283,7 +283,7 @@ static void ubifs_destroy_inode(struct inode *inode) /* * Note, Linux write-back code calls this without 'i_mutex'. */ -static int ubifs_write_inode(struct inode *inode, int wait) +static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) { int err = 0; struct ubifs_info *c = inode->i_sb->s_fs_info; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 378a7592257..b0208924729 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1373,12 +1373,12 @@ static mode_t udf_convert_permissions(struct fileEntry *fe) return mode; } -int udf_write_inode(struct inode *inode, int sync) +int udf_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; lock_kernel(); - ret = udf_update_inode(inode, sync); + ret = udf_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); unlock_kernel(); return ret; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 8d46f4294ee..4223ac855da 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -142,7 +142,7 @@ extern void udf_truncate(struct inode *); extern void udf_read_inode(struct inode *); extern void udf_delete_inode(struct inode *); extern void udf_clear_inode(struct inode *); -extern int udf_write_inode(struct inode *, int); +extern int udf_write_inode(struct inode *, struct writeback_control *wbc); extern long udf_block_map(struct inode *, sector_t); extern int udf_extend_file(struct inode *, struct extent_position *, struct kernel_long_ad *, sector_t); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 7cf33379fd4..0a627e08610 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "ufs_fs.h" #include "ufs.h" @@ -890,11 +891,11 @@ static int ufs_update_inode(struct inode * inode, int do_sync) return 0; } -int ufs_write_inode (struct inode * inode, int wait) +int ufs_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; lock_kernel(); - ret = ufs_update_inode (inode, wait); + ret = ufs_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL); unlock_kernel(); return ret; } diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 01d0e2a3b23..43f9f5d5670 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -106,7 +106,7 @@ extern struct inode * ufs_new_inode (struct inode *, int); /* inode.c */ extern struct inode *ufs_iget(struct super_block *, unsigned long); -extern int ufs_write_inode (struct inode *, int); +extern int ufs_write_inode (struct inode *, struct writeback_control *); extern int ufs_sync_inode (struct inode *); extern void ufs_delete_inode (struct inode *); extern struct buffer_head * ufs_bread (struct inode *, unsigned, int, int *); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 8f117db6070..71345a370d9 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1063,7 +1063,7 @@ xfs_log_inode( STATIC int xfs_fs_write_inode( struct inode *inode, - int sync) + struct writeback_control *wbc) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1074,7 +1074,7 @@ xfs_fs_write_inode( if (XFS_FORCED_SHUTDOWN(mp)) return XFS_ERROR(EIO); - if (sync) { + if (wbc->sync_mode == WB_SYNC_ALL) { /* * Make sure the inode has hit stable storage. By using the * log and the fsync transactions we reduce the IOs we have diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 6b049030fbe..deac2566450 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -877,7 +877,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, int create); extern struct inode *ext3_iget(struct super_block *, unsigned long); -extern int ext3_write_inode (struct inode *, int); +extern int ext3_write_inode (struct inode *, struct writeback_control *); extern int ext3_setattr (struct dentry *, struct iattr *); extern void ext3_delete_inode (struct inode *); extern int ext3_sync_inode (handle_t *, struct inode *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 5b3182c7eb5..45689621a85 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1557,7 +1557,7 @@ struct super_operations { void (*destroy_inode)(struct inode *); void (*dirty_inode) (struct inode *); - int (*write_inode) (struct inode *, int); + int (*write_inode) (struct inode *, struct writeback_control *wbc); void (*drop_inode) (struct inode *); void (*delete_inode) (struct inode *); void (*put_super) (struct super_block *); diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 1ba3cf6edfb..3b603f47418 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2034,7 +2034,7 @@ void reiserfs_read_locked_inode(struct inode *inode, int reiserfs_find_actor(struct inode *inode, void *p); int reiserfs_init_locked_inode(struct inode *inode, void *p); void reiserfs_delete_inode(struct inode *inode); -int reiserfs_write_inode(struct inode *inode, int); +int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc); int reiserfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create); struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid, -- cgit v1.2.3-70-g09d2