From 23fffa925ea2c9a2bcb1a4453e2c542635aa3545 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Sat, 12 Apr 2014 09:56:41 -0400 Subject: fs: move falloc collapse range check into the filesystem methods Currently in do_fallocate in collapse range case we're checking whether offset + len is not bigger than i_size. However there is nothing which would prevent i_size from changing so the check is pointless. It should be done in the file system itself and the file system needs to make sure that i_size is not going to change. The i_size check for the other fallocate modes are also done in the filesystems. As it is now we can easily crash the kernel by having two processes doing truncate and fallocate collapse range at the same time. This can be reproduced on ext4 and it is theoretically possible on xfs even though I was not able to trigger it with this simple test. This commit removes the check from do_fallocate and adds it to the file system. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" Acked-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_file.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f7abff8c16ca..3cb528c4f27c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -840,7 +840,15 @@ xfs_file_fallocate( goto out_unlock; } - ASSERT(offset + len < i_size_read(inode)); + /* + * There is no need to overlap collapse range with EOF, + * in which case it is effectively a truncate operation + */ + if (offset + len >= i_size_read(inode)) { + error = -EINVAL; + goto out_unlock; + } + new_size = i_size_read(inode) - len; error = xfs_collapse_file_space(ip, offset, len); -- cgit v1.2.3 From c99d609a16506602a7398eea7d12b13513f3d889 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 5 May 2014 16:18:37 +1000 Subject: xfs: fully support v5 format filesystems We have had this code in the kernel for over a year now and have shaken all the known issues out of the code over the past few releases. It's now time to remove the experimental warnings during mount and fully support the new filesystem format in production systems. Remove the experimental warning, and add a version number to the initial "mounting filesystem" message to tell use what type of filesystem is being mounted. Also, remove the temporary inode cluster size output at mount time now we know that this code works fine. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_log.c | 10 ++++++---- fs/xfs/xfs_mount.c | 2 -- fs/xfs/xfs_sb.c | 4 ---- 3 files changed, 6 insertions(+), 10 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 08624dc67317..a5f8bd9899d3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -616,11 +616,13 @@ xfs_log_mount( int error = 0; int min_logfsbs; - if (!(mp->m_flags & XFS_MOUNT_NORECOVERY)) - xfs_notice(mp, "Mounting Filesystem"); - else { + if (!(mp->m_flags & XFS_MOUNT_NORECOVERY)) { + xfs_notice(mp, "Mounting V%d Filesystem", + XFS_SB_VERSION_NUM(&mp->m_sb)); + } else { xfs_notice(mp, -"Mounting filesystem in no-recovery mode. Filesystem will be inconsistent."); +"Mounting V%d filesystem in no-recovery mode. Filesystem will be inconsistent.", + XFS_SB_VERSION_NUM(&mp->m_sb)); ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 993cb19e7d39..944f3d9456a8 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -743,8 +743,6 @@ xfs_mountfs( new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) mp->m_inode_cluster_size = new_size; - xfs_info(mp, "Using inode cluster size of %d bytes", - mp->m_inode_cluster_size); } /* diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 0c0e41bbe4e3..8baf61afae1d 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -201,10 +201,6 @@ xfs_mount_validate_sb( * write validation, we don't need to check feature masks. */ if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) { - xfs_alert(mp, -"Version 5 superblock detected. This kernel has EXPERIMENTAL support enabled!\n" -"Use of these features in this kernel is at your own risk!"); - if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) { xfs_warn(mp, -- cgit v1.2.3 From d540e43b0ab134b22f015f725ce6e070d12b0244 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Tue, 6 May 2014 07:34:28 +1000 Subject: xfs: initialize default acls for ->tmpfile() The current tmpfile handler does not initialize default ACLs. Doing so within xfs_vn_tmpfile() makes it roughly equivalent to xfs_vn_mknod(), which is already used as a common create handler. xfs_vn_mknod() does not currently have a mechanism to determine whether to link the file into the namespace. Therefore, further abstract xfs_vn_mknod() into a new xfs_generic_create() handler with a tmpfile parameter. This new handler calls xfs_create_tmpfile() and d_tmpfile() on the dentry when called via ->tmpfile(). Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_iops.c | 55 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 26 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index ef1ca010f417..301ecbfcc0be 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -124,15 +124,15 @@ xfs_cleanup_inode( xfs_dentry_to_name(&teardown, dentry, 0); xfs_remove(XFS_I(dir), &teardown, XFS_I(inode)); - iput(inode); } STATIC int -xfs_vn_mknod( +xfs_generic_create( struct inode *dir, struct dentry *dentry, umode_t mode, - dev_t rdev) + dev_t rdev, + bool tmpfile) /* unnamed file */ { struct inode *inode; struct xfs_inode *ip = NULL; @@ -156,8 +156,12 @@ xfs_vn_mknod( if (error) return error; - xfs_dentry_to_name(&name, dentry, mode); - error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); + if (!tmpfile) { + xfs_dentry_to_name(&name, dentry, mode); + error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); + } else { + error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip); + } if (unlikely(error)) goto out_free_acl; @@ -180,7 +184,11 @@ xfs_vn_mknod( } #endif - d_instantiate(dentry, inode); + if (tmpfile) + d_tmpfile(dentry, inode); + else + d_instantiate(dentry, inode); + out_free_acl: if (default_acl) posix_acl_release(default_acl); @@ -189,10 +197,22 @@ xfs_vn_mknod( return -error; out_cleanup_inode: - xfs_cleanup_inode(dir, inode, dentry); + if (!tmpfile) + xfs_cleanup_inode(dir, inode, dentry); + iput(inode); goto out_free_acl; } +STATIC int +xfs_vn_mknod( + struct inode *dir, + struct dentry *dentry, + umode_t mode, + dev_t rdev) +{ + return xfs_generic_create(dir, dentry, mode, rdev, false); +} + STATIC int xfs_vn_create( struct inode *dir, @@ -353,6 +373,7 @@ xfs_vn_symlink( out_cleanup_inode: xfs_cleanup_inode(dir, inode, dentry); + iput(inode); out: return -error; } @@ -1053,25 +1074,7 @@ xfs_vn_tmpfile( struct dentry *dentry, umode_t mode) { - int error; - struct xfs_inode *ip; - struct inode *inode; - - error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip); - if (unlikely(error)) - return -error; - - inode = VFS_I(ip); - - error = xfs_init_security(inode, dir, &dentry->d_name); - if (unlikely(error)) { - iput(inode); - return -error; - } - - d_tmpfile(dentry, inode); - - return 0; + return xfs_generic_create(dir, dentry, mode, 0, true); } static const struct inode_operations xfs_inode_operations = { -- cgit v1.2.3 From 8275cdd0e7ac550dcce2b3ef6d2fb3b808c1ae59 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 6 May 2014 07:37:31 +1000 Subject: xfs: remote attribute overwrite causes transaction overrun Commit e461fcb ("xfs: remote attribute lookups require the value length") passes the remote attribute length in the xfs_da_args structure on lookup so that CRC calculations and validity checking can be performed correctly by related code. This, unfortunately has the side effect of changing the args->valuelen parameter in cases where it shouldn't. That is, when we replace a remote attribute, the incoming replacement stores the value and length in args->value and args->valuelen, but then the lookup which finds the existing remote attribute overwrites args->valuelen with the length of the remote attribute being replaced. Hence when we go to create the new attribute, we create it of the size of the existing remote attribute, not the size it is supposed to be. When the new attribute is much smaller than the old attribute, this results in a transaction overrun and an ASSERT() failure on a debug kernel: XFS: Assertion failed: tp->t_blk_res_used <= tp->t_blk_res, file: fs/xfs/xfs_trans.c, line: 331 Fix this by keeping the remote attribute value length separate to the attribute value length in the xfs_da_args structure. The enables us to pass the length of the remote attribute to be removed without overwriting the new attribute's length. Also, ensure that when we save remote block contexts for a later rename we zero the original state variables so that we don't confuse the state of the attribute to be removes with the state of the new attribute that we just added. [Spotted by Brain Foster.] Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_attr.c | 24 +++++++++++++++++++++++- fs/xfs/xfs_attr_leaf.c | 21 +++++++++++---------- fs/xfs/xfs_attr_list.c | 1 + fs/xfs/xfs_attr_remote.c | 8 +++++--- fs/xfs/xfs_da_btree.h | 2 ++ 5 files changed, 42 insertions(+), 14 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index 01b6a0102fbd..abda1124a70f 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -213,7 +213,7 @@ xfs_attr_calc_size( * Out of line attribute, cannot double split, but * make room for the attribute value itself. */ - uint dblocks = XFS_B_TO_FSB(mp, valuelen); + uint dblocks = xfs_attr3_rmt_blocks(mp, valuelen); nblks += dblocks; nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK); } @@ -698,11 +698,22 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) trace_xfs_attr_leaf_replace(args); + /* save the attribute state for later removal*/ args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */ args->blkno2 = args->blkno; /* set 2nd entry info*/ args->index2 = args->index; args->rmtblkno2 = args->rmtblkno; args->rmtblkcnt2 = args->rmtblkcnt; + args->rmtvaluelen2 = args->rmtvaluelen; + + /* + * clear the remote attr state now that it is saved so that the + * values reflect the state of the attribute we are about to + * add, not the attribute we just found and will remove later. + */ + args->rmtblkno = 0; + args->rmtblkcnt = 0; + args->rmtvaluelen = 0; } /* @@ -794,6 +805,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) args->blkno = args->blkno2; args->rmtblkno = args->rmtblkno2; args->rmtblkcnt = args->rmtblkcnt2; + args->rmtvaluelen = args->rmtvaluelen2; if (args->rmtblkno) { error = xfs_attr_rmtval_remove(args); if (error) @@ -999,13 +1011,22 @@ restart: trace_xfs_attr_node_replace(args); + /* save the attribute state for later removal*/ args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */ args->blkno2 = args->blkno; /* set 2nd entry info*/ args->index2 = args->index; args->rmtblkno2 = args->rmtblkno; args->rmtblkcnt2 = args->rmtblkcnt; + args->rmtvaluelen2 = args->rmtvaluelen; + + /* + * clear the remote attr state now that it is saved so that the + * values reflect the state of the attribute we are about to + * add, not the attribute we just found and will remove later. + */ args->rmtblkno = 0; args->rmtblkcnt = 0; + args->rmtvaluelen = 0; } retval = xfs_attr3_leaf_add(blk->bp, state->args); @@ -1133,6 +1154,7 @@ restart: args->blkno = args->blkno2; args->rmtblkno = args->rmtblkno2; args->rmtblkcnt = args->rmtblkcnt2; + args->rmtvaluelen = args->rmtvaluelen2; if (args->rmtblkno) { error = xfs_attr_rmtval_remove(args); if (error) diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index fe9587fab17a..511c283459b1 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -1229,6 +1229,7 @@ xfs_attr3_leaf_add_work( name_rmt->valueblk = 0; args->rmtblkno = 1; args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); + args->rmtvaluelen = args->valuelen; } xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index), @@ -2167,11 +2168,11 @@ xfs_attr3_leaf_lookup_int( if (!xfs_attr_namesp_match(args->flags, entry->flags)) continue; args->index = probe; - args->valuelen = be32_to_cpu(name_rmt->valuelen); + args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen); args->rmtblkno = be32_to_cpu(name_rmt->valueblk); args->rmtblkcnt = xfs_attr3_rmt_blocks( args->dp->i_mount, - args->valuelen); + args->rmtvaluelen); return XFS_ERROR(EEXIST); } } @@ -2220,19 +2221,19 @@ xfs_attr3_leaf_getvalue( name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); ASSERT(name_rmt->namelen == args->namelen); ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0); - valuelen = be32_to_cpu(name_rmt->valuelen); + args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen); args->rmtblkno = be32_to_cpu(name_rmt->valueblk); args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount, - valuelen); + args->rmtvaluelen); if (args->flags & ATTR_KERNOVAL) { - args->valuelen = valuelen; + args->valuelen = args->rmtvaluelen; return 0; } - if (args->valuelen < valuelen) { - args->valuelen = valuelen; + if (args->valuelen < args->rmtvaluelen) { + args->valuelen = args->rmtvaluelen; return XFS_ERROR(ERANGE); } - args->valuelen = valuelen; + args->valuelen = args->rmtvaluelen; } return 0; } @@ -2519,7 +2520,7 @@ xfs_attr3_leaf_clearflag( ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0); name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); - name_rmt->valuelen = cpu_to_be32(args->valuelen); + name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt))); } @@ -2677,7 +2678,7 @@ xfs_attr3_leaf_flipflags( ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0); name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); - name_rmt->valuelen = cpu_to_be32(args->valuelen); + name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen); xfs_trans_log_buf(args->trans, bp1, XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt))); } diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 01db96f60cf0..833fe5d98d80 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -447,6 +447,7 @@ xfs_attr3_leaf_list_int( args.dp = context->dp; args.whichfork = XFS_ATTR_FORK; args.valuelen = valuelen; + args.rmtvaluelen = valuelen; args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS); args.rmtblkno = be32_to_cpu(name_rmt->valueblk); args.rmtblkcnt = xfs_attr3_rmt_blocks( diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c index 6e37823e2932..d2e6e948cec7 100644 --- a/fs/xfs/xfs_attr_remote.c +++ b/fs/xfs/xfs_attr_remote.c @@ -337,7 +337,7 @@ xfs_attr_rmtval_get( struct xfs_buf *bp; xfs_dablk_t lblkno = args->rmtblkno; __uint8_t *dst = args->value; - int valuelen = args->valuelen; + int valuelen; int nmap; int error; int blkcnt = args->rmtblkcnt; @@ -347,7 +347,9 @@ xfs_attr_rmtval_get( trace_xfs_attr_rmtval_get(args); ASSERT(!(args->flags & ATTR_KERNOVAL)); + ASSERT(args->rmtvaluelen == args->valuelen); + valuelen = args->rmtvaluelen; while (valuelen > 0) { nmap = ATTR_RMTVALUE_MAPSIZE; error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno, @@ -415,7 +417,7 @@ xfs_attr_rmtval_set( * attributes have headers, we can't just do a straight byte to FSB * conversion and have to take the header space into account. */ - blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); + blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen); error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff, XFS_ATTR_FORK); if (error) @@ -480,7 +482,7 @@ xfs_attr_rmtval_set( */ lblkno = args->rmtblkno; blkcnt = args->rmtblkcnt; - valuelen = args->valuelen; + valuelen = args->rmtvaluelen; while (valuelen > 0) { struct xfs_buf *bp; xfs_daddr_t dblkno; diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h index 6e95ea79f5d7..201c6091d26a 100644 --- a/fs/xfs/xfs_da_btree.h +++ b/fs/xfs/xfs_da_btree.h @@ -60,10 +60,12 @@ typedef struct xfs_da_args { int index; /* index of attr of interest in blk */ xfs_dablk_t rmtblkno; /* remote attr value starting blkno */ int rmtblkcnt; /* remote attr value block count */ + int rmtvaluelen; /* remote attr value length in bytes */ xfs_dablk_t blkno2; /* blkno of 2nd attr leaf of interest */ int index2; /* index of 2nd attr in blk */ xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */ int rmtblkcnt2; /* remote attr value block count */ + int rmtvaluelen2; /* remote attr value length in bytes */ int op_flags; /* operation flags */ enum xfs_dacmp cmpresult; /* name compare result for lookups */ } xfs_da_args_t; -- cgit v1.2.3