From 97db39a1f6f69e906e98118392400de5217aa33a Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sun, 26 Jul 2009 21:52:01 -0500 Subject: xfs: reduce bmv_count in xfs_vn_fiemap commit 6321e3ed2acf3ee9643cdd403e1c88605d7944ba caused the full bmv_count's worth of getbmapx structures to get allocated; telling it to do MAXEXTNUM was a bit insane, resulting in ENOMEM every time. Chop it down to something reasonable, the number of slots in the caller's input buffer. If this is too large the caller may get ENOMEM but the reason should not be a mystery, and they can try again with something smaller. We add 1 to the value because in the normal getbmap world, bmv_count includes the header and xfs_getbmap does: nex = bmv->bmv_count - 1; if (nex <= 0) return XFS_ERROR(EINVAL); Signed-off-by: Eric Sandeen Reviewed-by: Olaf Weber Reviewed-by: Christoph Hellwig Signed-off-by: Felix Blyakher --- fs/xfs/linux-2.6/xfs_iops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 58973bb4603..8070b34cc28 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -680,8 +680,8 @@ xfs_vn_fiemap( else bm.bmv_length = BTOBB(length); - /* our formatter will tell xfs_getbmap when to stop. */ - bm.bmv_count = MAXEXTNUM; + /* We add one because in getbmap world count includes the header */ + bm.bmv_count = fieinfo->fi_extents_max + 1; bm.bmv_iflags = BMV_IF_PREALLOC; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) bm.bmv_iflags |= BMV_IF_ATTRFORK; -- cgit v1.2.3-70-g09d2 From c8a4051c3731b6db224482218cfd535ab9393ff8 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 31 Jul 2009 00:02:17 -0500 Subject: xfs: bump up nr_to_write in xfs_vm_writepage VM calculation for nr_to_write seems off. Bump it way up, this gets simple streaming writes zippy again. To be reviewed again after Jens' writeback changes. Signed-off-by: Christoph Hellwig Signed-off-by: Eric Sandeen Cc: Chris Mason Reviewed-by: Felix Blyakher Signed-off-by: Felix Blyakher --- fs/xfs/linux-2.6/xfs_aops.c | 8 ++++++++ 1 file changed, 8 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 7ec89fc05b2..aecf2519db7 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -1268,6 +1268,14 @@ xfs_vm_writepage( if (!page_has_buffers(page)) create_empty_buffers(page, 1 << inode->i_blkbits, 0); + + /* + * VM calculation for nr_to_write seems off. Bump it way + * up, this gets simple streaming writes zippy again. + * To be reviewed again after Jens' writeback changes. + */ + wbc->nr_to_write *= 4; + /* * Convert delayed allocate, unwritten or unmapped space * to real space and flush out to disk. -- cgit v1.2.3-70-g09d2 From 54e346215e4fe2ca8c94c54e546cc61902060510 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Aug 2009 14:38:25 -0300 Subject: vfs: fix inode_init_always calling convention Currently inode_init_always calls into ->destroy_inode if the additional initialization fails. That's not only counter-intuitive because inode_init_always did not allocate the inode structure, but in case of XFS it's actively harmful as ->destroy_inode might delete the inode from a radix-tree that has never been added. This in turn might end up deleting the inode for the same inum that has been instanciated by another process and cause lots of cause subtile problems. Also in the case of re-initializing a reclaimable inode in XFS it would free an inode we still want to keep alive. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Sandeen --- fs/inode.c | 30 +++++++++++++++++------------- fs/xfs/xfs_iget.c | 17 +++++------------ include/linux/fs.h | 2 +- 3 files changed, 23 insertions(+), 26 deletions(-) (limited to 'fs/xfs') diff --git a/fs/inode.c b/fs/inode.c index 901bad1e5f1..af2c05235cc 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -120,12 +120,11 @@ static void wake_up_inode(struct inode *inode) * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ -struct inode *inode_init_always(struct super_block *sb, struct inode *inode) +int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct address_space_operations empty_aops; static struct inode_operations empty_iops; static const struct file_operations empty_fops; - struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; @@ -152,7 +151,7 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->dirtied_when = 0; if (security_inode_alloc(inode)) - goto out_free_inode; + goto out; /* allocate and initialize an i_integrity */ if (ima_inode_alloc(inode)) @@ -198,16 +197,12 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif - return inode; + return 0; out_free_security: security_inode_free(inode); -out_free_inode: - if (inode->i_sb->s_op->destroy_inode) - inode->i_sb->s_op->destroy_inode(inode); - else - kmem_cache_free(inode_cachep, (inode)); - return NULL; +out: + return -ENOMEM; } EXPORT_SYMBOL(inode_init_always); @@ -220,9 +215,18 @@ static struct inode *alloc_inode(struct super_block *sb) else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); - if (inode) - return inode_init_always(sb, inode); - return NULL; + if (!inode) + return NULL; + + if (unlikely(inode_init_always(sb, inode))) { + if (inode->i_sb->s_op->destroy_inode) + inode->i_sb->s_op->destroy_inode(inode); + else + kmem_cache_free(inode_cachep, inode); + return NULL; + } + + return inode; } void destroy_inode(struct inode *inode) diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 5fcec6f020a..719c85b155f 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -64,6 +64,10 @@ xfs_inode_alloc( ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP); if (!ip) return NULL; + if (inode_init_always(mp->m_super, VFS_I(ip))) { + kmem_zone_free(xfs_inode_zone, ip); + return NULL; + } ASSERT(atomic_read(&ip->i_iocount) == 0); ASSERT(atomic_read(&ip->i_pincount) == 0); @@ -105,17 +109,6 @@ xfs_inode_alloc( #ifdef XFS_DIR2_TRACE ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS); #endif - /* - * Now initialise the VFS inode. We do this after the xfs_inode - * initialisation as internal failures will result in ->destroy_inode - * being called and that will pass down through the reclaim path and - * free the XFS inode. This path requires the XFS inode to already be - * initialised. Hence if this call fails, the xfs_inode has already - * been freed and we should not reference it at all in the error - * handling. - */ - if (!inode_init_always(mp->m_super, VFS_I(ip))) - return NULL; /* prevent anyone from using this yet */ VFS_I(ip)->i_state = I_NEW|I_LOCK; @@ -167,7 +160,7 @@ xfs_iget_cache_hit( * errors cleanly, then tag it so it can be set up correctly * later. */ - if (!inode_init_always(mp->m_super, VFS_I(ip))) { + if (inode_init_always(mp->m_super, VFS_I(ip))) { error = ENOMEM; goto out_error; } diff --git a/include/linux/fs.h b/include/linux/fs.h index a36ffa5a77a..0c3b5e58a98 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2137,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin); extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); -extern struct inode * inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void inode_add_to_lists(struct super_block *, struct inode *); extern void iput(struct inode *); -- cgit v1.2.3-70-g09d2 From b36ec0428a06fcbdb67d61e9e664154e5dd9a8c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Aug 2009 14:38:34 -0300 Subject: xfs: fix freeing of inodes not yet added to the inode cache When freeing an inode that lost race getting added to the inode cache we must not call into ->destroy_inode, because that would delete the inode that won the race from the inode cache radix tree. This patch uses splits a new xfs_inode_free helper out of xfs_ireclaim and uses that plus __destroy_inode to make sure we really only free the memory allocted for the inode that lost the race, and not mess with the inode cache state. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Sandeen Reported-by: Alex Samad Reported-by: Andrew Randrianasulu Reported-by: Stephane Reported-by: Tommy Reported-by: Miah Gregory Reported-by: Gabriel Barazer Reported-by: Leandro Lucarella Reported-by: Daniel Burr Reported-by: Nickolay Reported-by: Michael Guntsche Reported-by: Dan Carley Reported-by: Michael Ole Olsen Reported-by: Michael Weissenbacher Reported-by: Martin Spott Reported-by: Christian Kujau Tested-by: Michael Guntsche Tested-by: Dan Carley Tested-by: Christian Kujau --- fs/xfs/xfs_iget.c | 125 +++++++++++++++++++++++++++++------------------------ fs/xfs/xfs_inode.h | 17 -------- 2 files changed, 68 insertions(+), 74 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 719c85b155f..34ec86923f7 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -116,6 +116,71 @@ xfs_inode_alloc( return ip; } +STATIC void +xfs_inode_free( + struct xfs_inode *ip) +{ + switch (ip->i_d.di_mode & S_IFMT) { + case S_IFREG: + case S_IFDIR: + case S_IFLNK: + xfs_idestroy_fork(ip, XFS_DATA_FORK); + break; + } + + if (ip->i_afp) + xfs_idestroy_fork(ip, XFS_ATTR_FORK); + +#ifdef XFS_INODE_TRACE + ktrace_free(ip->i_trace); +#endif +#ifdef XFS_BMAP_TRACE + ktrace_free(ip->i_xtrace); +#endif +#ifdef XFS_BTREE_TRACE + ktrace_free(ip->i_btrace); +#endif +#ifdef XFS_RW_TRACE + ktrace_free(ip->i_rwtrace); +#endif +#ifdef XFS_ILOCK_TRACE + ktrace_free(ip->i_lock_trace); +#endif +#ifdef XFS_DIR2_TRACE + ktrace_free(ip->i_dir_trace); +#endif + + if (ip->i_itemp) { + /* + * Only if we are shutting down the fs will we see an + * inode still in the AIL. If it is there, we should remove + * it to prevent a use-after-free from occurring. + */ + xfs_log_item_t *lip = &ip->i_itemp->ili_item; + struct xfs_ail *ailp = lip->li_ailp; + + ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) || + XFS_FORCED_SHUTDOWN(ip->i_mount)); + if (lip->li_flags & XFS_LI_IN_AIL) { + spin_lock(&ailp->xa_lock); + if (lip->li_flags & XFS_LI_IN_AIL) + xfs_trans_ail_delete(ailp, lip); + else + spin_unlock(&ailp->xa_lock); + } + xfs_inode_item_destroy(ip); + ip->i_itemp = NULL; + } + + /* asserts to verify all state is correct here */ + ASSERT(atomic_read(&ip->i_iocount) == 0); + ASSERT(atomic_read(&ip->i_pincount) == 0); + ASSERT(!spin_is_locked(&ip->i_flags_lock)); + ASSERT(completion_done(&ip->i_flush)); + + kmem_zone_free(xfs_inode_zone, ip); +} + /* * Check the validity of the inode we just found it the cache */ @@ -292,7 +357,8 @@ out_preload_end: if (lock_flags) xfs_iunlock(ip, lock_flags); out_destroy: - xfs_destroy_inode(ip); + __destroy_inode(VFS_I(ip)); + xfs_inode_free(ip); return error; } @@ -497,62 +563,7 @@ xfs_ireclaim( xfs_qm_dqdetach(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); - switch (ip->i_d.di_mode & S_IFMT) { - case S_IFREG: - case S_IFDIR: - case S_IFLNK: - xfs_idestroy_fork(ip, XFS_DATA_FORK); - break; - } - - if (ip->i_afp) - xfs_idestroy_fork(ip, XFS_ATTR_FORK); - -#ifdef XFS_INODE_TRACE - ktrace_free(ip->i_trace); -#endif -#ifdef XFS_BMAP_TRACE - ktrace_free(ip->i_xtrace); -#endif -#ifdef XFS_BTREE_TRACE - ktrace_free(ip->i_btrace); -#endif -#ifdef XFS_RW_TRACE - ktrace_free(ip->i_rwtrace); -#endif -#ifdef XFS_ILOCK_TRACE - ktrace_free(ip->i_lock_trace); -#endif -#ifdef XFS_DIR2_TRACE - ktrace_free(ip->i_dir_trace); -#endif - if (ip->i_itemp) { - /* - * Only if we are shutting down the fs will we see an - * inode still in the AIL. If it is there, we should remove - * it to prevent a use-after-free from occurring. - */ - xfs_log_item_t *lip = &ip->i_itemp->ili_item; - struct xfs_ail *ailp = lip->li_ailp; - - ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) || - XFS_FORCED_SHUTDOWN(ip->i_mount)); - if (lip->li_flags & XFS_LI_IN_AIL) { - spin_lock(&ailp->xa_lock); - if (lip->li_flags & XFS_LI_IN_AIL) - xfs_trans_ail_delete(ailp, lip); - else - spin_unlock(&ailp->xa_lock); - } - xfs_inode_item_destroy(ip); - ip->i_itemp = NULL; - } - /* asserts to verify all state is correct here */ - ASSERT(atomic_read(&ip->i_iocount) == 0); - ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(completion_done(&ip->i_flush)); - kmem_zone_free(xfs_inode_zone, ip); + xfs_inode_free(ip); } /* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 1804f866a71..65f24a3cc99 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -309,23 +309,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip) return &ip->i_vnode; } -/* - * Get rid of a partially initialized inode. - * - * We have to go through destroy_inode to make sure allocations - * from init_inode_always like the security data are undone. - * - * We mark the inode bad so that it takes the short cut in - * the reclaim path instead of going through the flush path - * which doesn't make sense for an inode that has never seen the - * light of day. - */ -static inline void xfs_destroy_inode(struct xfs_inode *ip) -{ - make_bad_inode(VFS_I(ip)); - return destroy_inode(VFS_I(ip)); -} - /* * i_flags helper functions */ -- cgit v1.2.3-70-g09d2