From fecc01126d7a244b7e9b563c80663ffdca35343b Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 12 Nov 2008 15:16:38 -0800 Subject: ocfs2: turn __ocfs2_remove_inode_range() into ocfs2_remove_btree_range() This patch genericizes the high level handling of extent removal. ocfs2_remove_btree_range() is nearly identical to __ocfs2_remove_inode_range(), except that extent tree operations have been used where necessary. We update ocfs2_remove_inode_range() to use the generic helper. Now extent tree based structures have an easy way to truncate ranges. Signed-off-by: Mark Fasheh Acked-by: Joel Becker --- fs/ocfs2/file.c | 85 ++++----------------------------------------------------- 1 file changed, 5 insertions(+), 80 deletions(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index e2570a3bc2b2..360549161e20 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1226,83 +1226,6 @@ out: return ret; } -static int __ocfs2_remove_inode_range(struct inode *inode, - struct buffer_head *di_bh, - u32 cpos, u32 phys_cpos, u32 len, - struct ocfs2_cached_dealloc_ctxt *dealloc) -{ - int ret; - u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - struct inode *tl_inode = osb->osb_tl_inode; - handle_t *handle; - struct ocfs2_alloc_context *meta_ac = NULL; - struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; - struct ocfs2_extent_tree et; - - ocfs2_init_dinode_extent_tree(&et, inode, di_bh); - - ret = ocfs2_lock_allocators(inode, &et, 0, 1, NULL, &meta_ac); - if (ret) { - mlog_errno(ret); - return ret; - } - - mutex_lock(&tl_inode->i_mutex); - - if (ocfs2_truncate_log_needs_flush(osb)) { - ret = __ocfs2_flush_truncate_log(osb); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - } - - handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - mlog_errno(ret); - goto out; - } - - ret = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - - ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, meta_ac, - dealloc); - if (ret) { - mlog_errno(ret); - goto out_commit; - } - - OCFS2_I(inode)->ip_clusters -= len; - di->i_clusters = cpu_to_le32(OCFS2_I(inode)->ip_clusters); - - ret = ocfs2_journal_dirty(handle, di_bh); - if (ret) { - mlog_errno(ret); - goto out_commit; - } - - ret = ocfs2_truncate_log_append(osb, handle, phys_blkno, len); - if (ret) - mlog_errno(ret); - -out_commit: - ocfs2_commit_trans(osb, handle); -out: - mutex_unlock(&tl_inode->i_mutex); - - if (meta_ac) - ocfs2_free_alloc_context(meta_ac); - - return ret; -} - /* * Truncate a byte range, avoiding pages within partial clusters. This * preserves those pages for the zeroing code to write to. @@ -1402,7 +1325,9 @@ static int ocfs2_remove_inode_range(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_cached_dealloc_ctxt dealloc; struct address_space *mapping = inode->i_mapping; + struct ocfs2_extent_tree et; + ocfs2_init_dinode_extent_tree(&et, inode, di_bh); ocfs2_init_dealloc_ctxt(&dealloc); if (byte_len == 0) @@ -1458,9 +1383,9 @@ static int ocfs2_remove_inode_range(struct inode *inode, /* Only do work for non-holes */ if (phys_cpos != 0) { - ret = __ocfs2_remove_inode_range(inode, di_bh, cpos, - phys_cpos, alloc_size, - &dealloc); + ret = ocfs2_remove_btree_range(inode, &et, cpos, + phys_cpos, alloc_size, + &dealloc); if (ret) { mlog_errno(ret); goto out; -- cgit v1.2.1 From 23fc2702bea686569281708ad519b41a11d0a2f4 Mon Sep 17 00:00:00 2001 From: Tiger Yang Date: Fri, 14 Nov 2008 11:17:18 +0800 Subject: ocfs2: add ocfs2_check_acl This function is used to enhance permission checking with POSIX ACLs. Signed-off-by: Tiger Yang Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 360549161e20..7bad7d9b9a2c 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -56,6 +56,7 @@ #include "suballoc.h" #include "super.h" #include "xattr.h" +#include "acl.h" #include "buffer_head_io.h" @@ -1035,7 +1036,7 @@ int ocfs2_permission(struct inode *inode, int mask) goto out; } - ret = generic_permission(inode, mask, NULL); + ret = generic_permission(inode, mask, ocfs2_check_acl); ocfs2_inode_unlock(inode, 0); out: -- cgit v1.2.1 From 060bc66dd5017460076d9e808e2198cd532c943d Mon Sep 17 00:00:00 2001 From: Tiger Yang Date: Fri, 14 Nov 2008 11:17:29 +0800 Subject: ocfs2: add ocfs2_acl_chmod This function is used to update acl xattrs during file mode changes. Signed-off-by: Tiger Yang Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 7bad7d9b9a2c..4636aa6b0117 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -990,6 +990,12 @@ bail_unlock_rw: bail: brelse(bh); + if (!status && attr->ia_valid & ATTR_MODE) { + status = ocfs2_acl_chmod(inode); + if (status < 0) + mlog_errno(status); + } + mlog_exit(status); return status; } -- cgit v1.2.1 From b657c95c11088d77fc1bfc9c84d940f778bf9d12 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Thu, 13 Nov 2008 14:49:11 -0800 Subject: ocfs2: Wrap inode block reads in a dedicated function. The ocfs2 code currently reads inodes off disk with a simple ocfs2_read_block() call. Each place that does this has a different set of sanity checks it performs. Some check only the signature. A couple validate the block number (the block read vs di->i_blkno). A couple others check for VALID_FL. Only one place validates i_fs_generation. A couple check nothing. Even when an error is found, they don't all do the same thing. We wrap inode reading into ocfs2_read_inode_block(). This will validate all the above fields, going readonly if they are invalid (they never should be). ocfs2_read_inode_block_full() is provided for the places that want to pass read_block flags. Every caller is passing a struct inode with a valid ip_blkno, so we don't need a separate blkno argument either. We will remove the validation checks from the rest of the code in a later commit, as they are no longer necessary. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 4636aa6b0117..41001d515fae 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -402,12 +402,9 @@ static int ocfs2_truncate_file(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)new_i_size); + /* We trust di_bh because it comes from ocfs2_inode_lock(), which + * already validated it */ fe = (struct ocfs2_dinode *) di_bh->b_data; - if (!OCFS2_IS_VALID_DINODE(fe)) { - OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe); - status = -EIO; - goto bail; - } mlog_bug_on_msg(le64_to_cpu(fe->i_size) != i_size_read(inode), "Inode %llu, inode i_size = %lld != di " @@ -546,18 +543,12 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, */ BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb)); - status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &bh); + status = ocfs2_read_inode_block(inode, &bh); if (status < 0) { mlog_errno(status); goto leave; } - fe = (struct ocfs2_dinode *) bh->b_data; - if (!OCFS2_IS_VALID_DINODE(fe)) { - OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe); - status = -EIO; - goto leave; - } restart_all: BUG_ON(le32_to_cpu(fe->i_clusters) != OCFS2_I(inode)->ip_clusters); @@ -1135,9 +1126,8 @@ static int ocfs2_write_remove_suid(struct inode *inode) { int ret; struct buffer_head *bh = NULL; - struct ocfs2_inode_info *oi = OCFS2_I(inode); - ret = ocfs2_read_block(inode, oi->ip_blkno, &bh); + ret = ocfs2_read_inode_block(inode, &bh); if (ret < 0) { mlog_errno(ret); goto out; @@ -1163,8 +1153,7 @@ static int ocfs2_allocate_unwritten_extents(struct inode *inode, struct buffer_head *di_bh = NULL; if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { - ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, - &di_bh); + ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; -- cgit v1.2.1 From 9e33d69f553aaf11377307e8d6f82deb3385e351 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 25 Aug 2008 19:56:50 +0200 Subject: ocfs2: Implementation of local and global quota file handling For each quota type each node has local quota file. In this file it stores changes users have made to disk usage via this node. Once in a while this information is synced to global file (and thus with other nodes) so that limits enforcement at least aproximately works. Global quota files contain all the information about usage and limits. It's mostly handled by the generic VFS code (which implements a trie of structures inside a quota file). We only have to provide functions to convert structures from on-disk format to in-memory one. We also have to provide wrappers for various quota functions starting transactions and acquiring necessary cluster locks before the actual IO is really started. Signed-off-by: Jan Kara Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 41001d515fae..372d96505a79 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -304,9 +304,9 @@ bail: return status; } -static int ocfs2_simple_size_update(struct inode *inode, - struct buffer_head *di_bh, - u64 new_i_size) +int ocfs2_simple_size_update(struct inode *inode, + struct buffer_head *di_bh, + u64 new_i_size) { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); -- cgit v1.2.1 From a90714c150e3ce677c57a9dac3ab1ec342c75a95 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 9 Oct 2008 19:38:40 +0200 Subject: ocfs2: Add quota calls for allocation and freeing of inodes and space Add quota calls for allocation and freeing of inodes and space, also update estimates on number of needed credits for a transaction. Move out inode allocation from ocfs2_mknod_locked() because vfs_dq_init() must be called outside of a transaction. Signed-off-by: Jan Kara Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 67 insertions(+), 5 deletions(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 372d96505a79..9374d374a264 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -35,6 +35,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_INODE #include @@ -57,6 +58,7 @@ #include "super.h" #include "xattr.h" #include "acl.h" +#include "quota.h" #include "buffer_head_io.h" @@ -534,6 +536,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, enum ocfs2_alloc_restarted why; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_extent_tree et; + int did_quota = 0; mlog_entry("(clusters_to_add = %u)\n", clusters_to_add); @@ -577,6 +580,13 @@ restart_all: } restarted_transaction: + if (vfs_dq_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, + clusters_to_add))) { + status = -EDQUOT; + goto leave; + } + did_quota = 1; + /* reserve a write to the file entry early on - that we if we * run out of credits in the allocation path, we can still * update i_size. */ @@ -614,6 +624,10 @@ restarted_transaction: spin_lock(&OCFS2_I(inode)->ip_lock); clusters_to_add -= (OCFS2_I(inode)->ip_clusters - prev_clusters); spin_unlock(&OCFS2_I(inode)->ip_lock); + /* Release unused quota reservation */ + vfs_dq_free_space(inode, + ocfs2_clusters_to_bytes(osb->sb, clusters_to_add)); + did_quota = 0; if (why != RESTART_NONE && clusters_to_add) { if (why == RESTART_META) { @@ -646,6 +660,9 @@ restarted_transaction: OCFS2_I(inode)->ip_clusters, (long long)i_size_read(inode)); leave: + if (status < 0 && did_quota) + vfs_dq_free_space(inode, + ocfs2_clusters_to_bytes(osb->sb, clusters_to_add)); if (handle) { ocfs2_commit_trans(osb, handle); handle = NULL; @@ -877,6 +894,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) struct ocfs2_super *osb = OCFS2_SB(sb); struct buffer_head *bh = NULL; handle_t *handle = NULL; + int locked[MAXQUOTAS] = {0, 0}; + int credits, qtype; + struct ocfs2_mem_dqinfo *oinfo; mlog_entry("(0x%p, '%.*s')\n", dentry, dentry->d_name.len, dentry->d_name.name); @@ -947,11 +967,47 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } } - handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto bail_unlock; + if ((attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || + (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + credits = OCFS2_INODE_UPDATE_CREDITS; + if (attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid + && OCFS2_HAS_RO_COMPAT_FEATURE(sb, + OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) { + oinfo = sb_dqinfo(sb, USRQUOTA)->dqi_priv; + status = ocfs2_lock_global_qf(oinfo, 1); + if (status < 0) + goto bail_unlock; + credits += ocfs2_calc_qinit_credits(sb, USRQUOTA) + + ocfs2_calc_qdel_credits(sb, USRQUOTA); + locked[USRQUOTA] = 1; + } + if (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid + && OCFS2_HAS_RO_COMPAT_FEATURE(sb, + OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) { + oinfo = sb_dqinfo(sb, GRPQUOTA)->dqi_priv; + status = ocfs2_lock_global_qf(oinfo, 1); + if (status < 0) + goto bail_unlock; + credits += ocfs2_calc_qinit_credits(sb, GRPQUOTA) + + ocfs2_calc_qdel_credits(sb, GRPQUOTA); + locked[GRPQUOTA] = 1; + } + handle = ocfs2_start_trans(osb, credits); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto bail_unlock; + } + status = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0; + if (status < 0) + goto bail_commit; + } else { + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto bail_unlock; + } } /* @@ -974,6 +1030,12 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock: + for (qtype = 0; qtype < MAXQUOTAS; qtype++) { + if (!locked[qtype]) + continue; + oinfo = sb_dqinfo(sb, qtype)->dqi_priv; + ocfs2_unlock_global_qf(oinfo, 1); + } ocfs2_inode_unlock(inode, 1); bail_unlock_rw: if (size_change) -- cgit v1.2.1 From 13723d00e374c2a6d6ccb5af6de965e89c3e1b01 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Fri, 17 Oct 2008 19:25:01 -0700 Subject: ocfs2: Use metadata-specific ocfs2_journal_access_*() functions. The per-metadata-type ocfs2_journal_access_*() functions hook up jbd2 commit triggers and allow us to compute metadata ecc right before the buffers are written out. This commit provides ecc for inodes, extent blocks, group descriptors, and quota blocks. It is not safe to use extened attributes and metaecc at the same time yet. The ocfs2_extent_tree and ocfs2_path abstractions in alloc.c both hide the type of block at their root. Before, it didn't matter, but now the root block must use the appropriate ocfs2_journal_access_*() function. To keep this abstract, the structures now have a pointer to the matching journal_access function and a wrapper call to call it. A few places use naked ocfs2_write_block() calls instead of adding the blocks to the journal. We make sure to calculate their checksum and ecc before the write. Since we pass around the journal_access functions. Let's typedef them in ocfs2.h. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/file.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'fs/ocfs2/file.c') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9374d374a264..e8f795f978aa 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -256,8 +256,8 @@ int ocfs2_update_inode_atime(struct inode *inode, goto out; } - ret = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; @@ -353,8 +353,8 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb, goto out; } - status = ocfs2_journal_access(handle, inode, fe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, inode, fe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; @@ -590,8 +590,8 @@ restarted_transaction: /* reserve a write to the file entry early on - that we if we * run out of credits in the allocation path, we can still * update i_size. */ - status = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, inode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; @@ -1121,8 +1121,8 @@ static int __ocfs2_write_remove_suid(struct inode *inode, goto out; } - ret = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out_trans; -- cgit v1.2.1