From 9c2c703929e4c41210cfa6e3f599514421bab8dc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:06:22 -0400 Subject: ->permission() sanitizing: pass MAY_NOT_BLOCK to ->check_acl() Signed-off-by: Al Viro --- fs/xfs/linux-2.6/xfs_acl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 39f4f809bb68..278e6736135a 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -235,7 +235,7 @@ xfs_check_acl(struct inode *inode, int mask, unsigned int flags) if (!XFS_IFORK_Q(ip)) return -EAGAIN; - if (flags & IPERM_FLAG_RCU) { + if (mask & MAY_NOT_BLOCK) { if (!negative_cached_acl(inode, ACL_TYPE_ACCESS)) return -ECHILD; return -EAGAIN; -- cgit v1.2.1 From 7e40145eb111a5192e6d819f764db9d6828d1abb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Jun 2011 19:12:17 -0400 Subject: ->permission() sanitizing: don't pass flags to ->check_acl() not used in the instances anymore. Signed-off-by: Al Viro --- fs/xfs/linux-2.6/xfs_acl.c | 2 +- fs/xfs/xfs_acl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 278e6736135a..a5dcd6a0f1b5 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -219,7 +219,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) } int -xfs_check_acl(struct inode *inode, int mask, unsigned int flags) +xfs_check_acl(struct inode *inode, int mask) { struct xfs_inode *ip; struct posix_acl *acl; diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 11dd72070cbb..0135e2a669d7 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -42,7 +42,7 @@ struct xfs_acl { #define SGI_ACL_DEFAULT_SIZE (sizeof(SGI_ACL_DEFAULT)-1) #ifdef CONFIG_XFS_POSIX_ACL -extern int xfs_check_acl(struct inode *inode, int mask, unsigned int flags); +extern int xfs_check_acl(struct inode *inode, int mask); extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_inherit_acl(struct inode *inode, struct posix_acl *default_acl); extern int xfs_acl_chmod(struct inode *inode); -- cgit v1.2.1 From 8daaa83145ef1f0a146680618328dbbd0fa76939 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 8 Jul 2011 14:14:46 +1000 Subject: xfs: make use of new shrinker callout for the inode cache Convert the inode reclaim shrinker to use the new per-sb shrinker operations. This allows much bigger reclaim batches to be used, and allows the XFS inode cache to be shrunk in proportion with the VFS dentry and inode caches. This avoids the problem of the VFS caches being shrunk significantly before the XFS inode cache is shrunk resulting in imbalances in the caches during reclaim. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- fs/xfs/linux-2.6/xfs_super.c | 26 ++++++++++------ fs/xfs/linux-2.6/xfs_sync.c | 71 +++++++++++++++++--------------------------- fs/xfs/linux-2.6/xfs_sync.h | 5 ++-- 3 files changed, 46 insertions(+), 56 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index a1a881e68a9a..a9c6ccff7b48 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1025,11 +1025,6 @@ xfs_fs_put_super( { struct xfs_mount *mp = XFS_M(sb); - /* - * Unregister the memory shrinker before we tear down the mount - * structure so we don't have memory reclaim racing with us here. - */ - xfs_inode_shrinker_unregister(mp); xfs_syncd_stop(mp); /* @@ -1416,8 +1411,6 @@ xfs_fs_fill_super( if (error) goto out_filestream_unmount; - xfs_inode_shrinker_register(mp); - error = xfs_mountfs(mp); if (error) goto out_syncd_stop; @@ -1440,7 +1433,6 @@ xfs_fs_fill_super( return 0; out_syncd_stop: - xfs_inode_shrinker_unregister(mp); xfs_syncd_stop(mp); out_filestream_unmount: xfs_filestream_unmount(mp); @@ -1465,7 +1457,6 @@ xfs_fs_fill_super( } fail_unmount: - xfs_inode_shrinker_unregister(mp); xfs_syncd_stop(mp); /* @@ -1491,6 +1482,21 @@ xfs_fs_mount( return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super); } +static int +xfs_fs_nr_cached_objects( + struct super_block *sb) +{ + return xfs_reclaim_inodes_count(XFS_M(sb)); +} + +static void +xfs_fs_free_cached_objects( + struct super_block *sb, + int nr_to_scan) +{ + xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan); +} + static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, @@ -1504,6 +1510,8 @@ static const struct super_operations xfs_super_operations = { .statfs = xfs_fs_statfs, .remount_fs = xfs_fs_remount, .show_options = xfs_fs_show_options, + .nr_cached_objects = xfs_fs_nr_cached_objects, + .free_cached_objects = xfs_fs_free_cached_objects, }; static struct file_system_type xfs_fs_type = { diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 8ecad5ff9f9b..9bd7e895a4e2 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -179,6 +179,8 @@ restart: if (error == EFSCORRUPTED) break; + cond_resched(); + } while (nr_found && !done); if (skipped) { @@ -986,6 +988,8 @@ restart: *nr_to_scan -= XFS_LOOKUP_BATCH; + cond_resched(); + } while (nr_found && !done && *nr_to_scan > 0); if (trylock && !done) @@ -1003,7 +1007,7 @@ restart: * ensure that when we get more reclaimers than AGs we block rather * than spin trying to execute reclaim. */ - if (trylock && skipped && *nr_to_scan > 0) { + if (skipped && (flags & SYNC_WAIT) && *nr_to_scan > 0) { trylock = 0; goto restart; } @@ -1021,44 +1025,38 @@ xfs_reclaim_inodes( } /* - * Inode cache shrinker. + * Scan a certain number of inodes for reclaim. * * When called we make sure that there is a background (fast) inode reclaim in - * progress, while we will throttle the speed of reclaim via doiing synchronous + * progress, while we will throttle the speed of reclaim via doing synchronous * reclaim of inodes. That means if we come across dirty inodes, we wait for * them to be cleaned, which we hope will not be very long due to the * background walker having already kicked the IO off on those dirty inodes. */ -static int -xfs_reclaim_inode_shrink( - struct shrinker *shrink, - struct shrink_control *sc) +void +xfs_reclaim_inodes_nr( + struct xfs_mount *mp, + int nr_to_scan) { - struct xfs_mount *mp; - struct xfs_perag *pag; - xfs_agnumber_t ag; - int reclaimable; - int nr_to_scan = sc->nr_to_scan; - gfp_t gfp_mask = sc->gfp_mask; - - mp = container_of(shrink, struct xfs_mount, m_inode_shrink); - if (nr_to_scan) { - /* kick background reclaimer and push the AIL */ - xfs_syncd_queue_reclaim(mp); - xfs_ail_push_all(mp->m_ail); + /* kick background reclaimer and push the AIL */ + xfs_syncd_queue_reclaim(mp); + xfs_ail_push_all(mp->m_ail); - if (!(gfp_mask & __GFP_FS)) - return -1; + xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan); +} - xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, - &nr_to_scan); - /* terminate if we don't exhaust the scan */ - if (nr_to_scan > 0) - return -1; - } +/* + * Return the number of reclaimable inodes in the filesystem for + * the shrinker to determine how much to reclaim. + */ +int +xfs_reclaim_inodes_count( + struct xfs_mount *mp) +{ + struct xfs_perag *pag; + xfs_agnumber_t ag = 0; + int reclaimable = 0; - reclaimable = 0; - ag = 0; while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) { ag = pag->pag_agno + 1; reclaimable += pag->pag_ici_reclaimable; @@ -1067,18 +1065,3 @@ xfs_reclaim_inode_shrink( return reclaimable; } -void -xfs_inode_shrinker_register( - struct xfs_mount *mp) -{ - mp->m_inode_shrink.shrink = xfs_reclaim_inode_shrink; - mp->m_inode_shrink.seeks = DEFAULT_SEEKS; - register_shrinker(&mp->m_inode_shrink); -} - -void -xfs_inode_shrinker_unregister( - struct xfs_mount *mp) -{ - unregister_shrinker(&mp->m_inode_shrink); -} diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index e3a6ad27415f..2e1568597764 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -43,6 +43,8 @@ void xfs_quiesce_attr(struct xfs_mount *mp); void xfs_flush_inodes(struct xfs_inode *ip); int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); +int xfs_reclaim_inodes_count(struct xfs_mount *mp); +void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip); @@ -54,7 +56,4 @@ int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), int flags); -void xfs_inode_shrinker_register(struct xfs_mount *mp); -void xfs_inode_shrinker_unregister(struct xfs_mount *mp); - #endif -- cgit v1.2.1 From 72c5052ddc3956d847f21c2b8d55c93664a51b2c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:48 -0400 Subject: fs: move inode_dio_done to the end_io handler For filesystems that delay their end_io processing we should keep our i_dio_count until the the processing is done. Enable this by moving the inode_dio_done call to the end_io handler if one exist. Note that the actual move to the workqueue for ext4 and XFS is not done in this patch yet, but left to the filesystem maintainers. At least for XFS it's not needed yet either as XFS has an internal equivalent to i_dio_count. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/xfs/linux-2.6/xfs_aops.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 79ce38be15a1..b3b418f519f3 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -1339,6 +1339,9 @@ xfs_end_io_direct_write( } else { xfs_finish_ioend_sync(ioend); } + + /* XXX: probably should move into the real I/O completion handler */ + inode_dio_done(ioend->io_inode); } STATIC ssize_t -- cgit v1.2.1 From 02c24a82187d5a628c68edfe71ae60dc135cd178 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Sat, 16 Jul 2011 20:44:56 -0400 Subject: fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers Btrfs needs to be able to control how filemap_write_and_wait_range() is called in fsync to make it less of a painful operation, so push down taking i_mutex and the calling of filemap_write_and_wait() down into the ->fsync() handlers. Some file systems can drop taking the i_mutex altogether it seems, like ext3 and ocfs2. For correctness sake I just pushed everything down in all cases to make sure that we keep the current behavior the same for everybody, and then each individual fs maintainer can make up their mind about what to do from there. Thanks, Acked-by: Jan Kara Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- fs/xfs/linux-2.6/xfs_file.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 7f782af286bf..fbbf657df0cd 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -127,6 +127,8 @@ xfs_iozero( STATIC int xfs_file_fsync( struct file *file, + loff_t start, + loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; @@ -138,6 +140,10 @@ xfs_file_fsync( trace_xfs_file_fsync(ip); + error = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (error) + return error; + if (XFS_FORCED_SHUTDOWN(mp)) return -XFS_ERROR(EIO); @@ -875,18 +881,11 @@ xfs_file_aio_write( /* Handle various SYNC-type writes */ if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) { loff_t end = pos + ret - 1; - int error, error2; xfs_rw_iunlock(ip, iolock); - error = filemap_write_and_wait_range(mapping, pos, end); + ret = -xfs_file_fsync(file, pos, end, + (file->f_flags & __O_SYNC) ? 0 : 1); xfs_rw_ilock(ip, iolock); - - error2 = -xfs_file_fsync(file, - (file->f_flags & __O_SYNC) ? 0 : 1); - if (error) - ret = error; - else if (error2) - ret = error2; } out_unlock: -- cgit v1.2.1