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/dir.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 026e6eb8518..5777045f1a6 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -231,7 +231,7 @@ static struct buffer_head *ocfs2_find_entry_id(const char *name, struct ocfs2_dinode *di; struct ocfs2_inline_data *data; - ret = ocfs2_read_block(dir, OCFS2_I(dir)->ip_blkno, &di_bh); + ret = ocfs2_read_inode_block(dir, &di_bh); if (ret) { mlog_errno(ret); goto out; @@ -458,7 +458,7 @@ static inline int ocfs2_delete_entry_id(handle_t *handle, struct ocfs2_dinode *di; struct ocfs2_inline_data *data; - ret = ocfs2_read_block(dir, OCFS2_I(dir)->ip_blkno, &di_bh); + ret = ocfs2_read_inode_block(dir, &di_bh); if (ret) { mlog_errno(ret); goto out; @@ -636,7 +636,7 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode, struct ocfs2_inline_data *data; struct ocfs2_dir_entry *de; - ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &di_bh); + ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog(ML_ERROR, "Unable to read inode block for dir %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); -- cgit v1.2.3-70-g09d2 From a22305cc693254a2aa651e797875669112ef8635 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Thu, 13 Nov 2008 14:49:17 -0800 Subject: ocfs2: Wrap dirblock reads in a dedicated function. We have ocfs2_bread() as a vestige of the original ext-based dir code. It's only used by directories, though. Turn it into ocfs2_read_dir_block(), with a prototype matching the other metadata read functions. It's set up to validate dirblocks when the time comes. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dir.c | 150 +++++++++++++++++++++++++++++++++------------------------ 1 file changed, 88 insertions(+), 62 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 5777045f1a6..c2f3fd93be5 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -82,49 +82,6 @@ static int ocfs2_do_extend_dir(struct super_block *sb, struct ocfs2_alloc_context *meta_ac, struct buffer_head **new_bh); -static struct buffer_head *ocfs2_bread(struct inode *inode, - int block, int *err, int reada) -{ - struct buffer_head *bh = NULL; - int tmperr; - u64 p_blkno; - int readflags = 0; - - if (reada) - readflags |= OCFS2_BH_READAHEAD; - - if (((u64)block << inode->i_sb->s_blocksize_bits) >= - i_size_read(inode)) { - BUG_ON(!reada); - return NULL; - } - - down_read(&OCFS2_I(inode)->ip_alloc_sem); - tmperr = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, - NULL); - up_read(&OCFS2_I(inode)->ip_alloc_sem); - if (tmperr < 0) { - mlog_errno(tmperr); - goto fail; - } - - tmperr = ocfs2_read_blocks(inode, p_blkno, 1, &bh, readflags); - if (tmperr < 0) - goto fail; - - tmperr = 0; - - *err = 0; - return bh; - -fail: - brelse(bh); - bh = NULL; - - *err = -EIO; - return NULL; -} - /* * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. @@ -250,6 +207,76 @@ out: return NULL; } +static int ocfs2_validate_dir_block(struct super_block *sb, + struct buffer_head *bh) +{ + /* + * Nothing yet. We don't validate dirents here, that's handled + * in-place when the code walks them. + */ + + return 0; +} + +/* + * This function forces all errors to -EIO for consistency with its + * predecessor, ocfs2_bread(). We haven't audited what returning the + * real error codes would do to callers. We log the real codes with + * mlog_errno() before we squash them. + */ +static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, + struct buffer_head **bh, int flags) +{ + int rc = 0; + struct buffer_head *tmp = *bh; + u64 p_blkno; + + if (((u64)v_block << inode->i_sb->s_blocksize_bits) >= + i_size_read(inode)) { + BUG_ON(!(flags & OCFS2_BH_READAHEAD)); + goto out; + } + + down_read(&OCFS2_I(inode)->ip_alloc_sem); + rc = ocfs2_extent_map_get_blocks(inode, v_block, &p_blkno, NULL, + NULL); + up_read(&OCFS2_I(inode)->ip_alloc_sem); + if (rc) { + mlog_errno(rc); + goto out; + } + + if (!p_blkno) { + rc = -EIO; + mlog(ML_ERROR, + "Directory #%llu contains a hole at offset %llu\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno, + (unsigned long long)v_block << inode->i_sb->s_blocksize_bits); + goto out; + } + + rc = ocfs2_read_blocks(inode, p_blkno, 1, &tmp, flags); + if (rc) { + mlog_errno(rc); + goto out; + } + + if (!(flags & OCFS2_BH_READAHEAD)) { + rc = ocfs2_validate_dir_block(inode->i_sb, tmp); + if (rc) { + brelse(tmp); + goto out; + } + } + + /* If ocfs2_read_blocks() got us a new bh, pass it up. */ + if (!*bh) + *bh = tmp; + +out: + return rc ? -EIO : 0; +} + static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_entry **res_dir) @@ -296,15 +323,17 @@ restart: } num++; - bh = ocfs2_bread(dir, b++, &err, 1); + bh = NULL; + err = ocfs2_read_dir_block(dir, b++, &bh, + OCFS2_BH_READAHEAD); bh_use[ra_max] = bh; } } if ((bh = bh_use[ra_ptr++]) == NULL) goto next; - if (ocfs2_read_block(dir, block, &bh)) { + if (ocfs2_read_dir_block(dir, block, &bh, 0)) { /* read error, skip block & hope for the best. - * ocfs2_read_block() has released the bh. */ + * ocfs2_read_dir_block() has released the bh. */ ocfs2_error(dir->i_sb, "reading directory %llu, " "offset %lu\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, @@ -724,7 +753,6 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, int i, stored; struct buffer_head * bh, * tmp; struct ocfs2_dir_entry * de; - int err; struct super_block * sb = inode->i_sb; unsigned int ra_sectors = 16; @@ -735,12 +763,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, while (!error && !stored && *f_pos < i_size_read(inode)) { blk = (*f_pos) >> sb->s_blocksize_bits; - bh = ocfs2_bread(inode, blk, &err, 0); - if (!bh) { - mlog(ML_ERROR, - "directory #%llu contains a hole at offset %lld\n", - (unsigned long long)OCFS2_I(inode)->ip_blkno, - *f_pos); + if (ocfs2_read_dir_block(inode, blk, &bh, 0)) { + /* Skip the corrupt dirblock and keep trying */ *f_pos += sb->s_blocksize - offset; continue; } @@ -754,8 +778,10 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, || (((last_ra_blk - blk) << 9) <= (ra_sectors / 2))) { for (i = ra_sectors >> (sb->s_blocksize_bits - 9); i > 0; i--) { - tmp = ocfs2_bread(inode, ++blk, &err, 1); - brelse(tmp); + tmp = NULL; + if (!ocfs2_read_dir_block(inode, ++blk, &tmp, + OCFS2_BH_READAHEAD)) + brelse(tmp); } last_ra_blk = blk; ra_sectors = 8; @@ -828,6 +854,7 @@ revalidate: } offset = 0; brelse(bh); + bh = NULL; } stored = 0; @@ -1680,8 +1707,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, struct super_block *sb = dir->i_sb; int status; - bh = ocfs2_bread(dir, 0, &status, 0); - if (!bh) { + status = ocfs2_read_dir_block(dir, 0, &bh, 0); + if (status) { mlog_errno(status); goto bail; } @@ -1702,11 +1729,10 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, status = -ENOSPC; goto bail; } - bh = ocfs2_bread(dir, - offset >> sb->s_blocksize_bits, - &status, - 0); - if (!bh) { + status = ocfs2_read_dir_block(dir, + offset >> sb->s_blocksize_bits, + &bh, 0); + if (status) { mlog_errno(status); goto bail; } -- cgit v1.2.3-70-g09d2 From 970e4936d7d15f35d00fd15a14f5343ba78b2fc8 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Thu, 13 Nov 2008 14:49:19 -0800 Subject: ocfs2: Validate metadata only when it's read from disk. Add an optional validation hook to ocfs2_read_blocks(). Now the validation function is only called when a block was actually read off of disk. It is not called when the buffer was in cache. We add a buffer state bit BH_NeedsValidate to flag these buffers. It must always be one higher than the last JBD2 buffer state bit. The dinode, dirblock, extent_block, and xattr_block validators are lifted to this scheme directly. The group_descriptor validator needs to be split into two pieces. The first part only needs the gd buffer and is passed to ocfs2_read_block(). The second part requires the dinode as well, and is called every time. It's only 3 compares, so it's tiny. This also allows us to clean up the non-fatal gd check used by resize.c. It now has no magic argument. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/alloc.c | 17 ++++----- fs/ocfs2/buffer_head_io.c | 33 ++++++++++++++++- fs/ocfs2/buffer_head_io.h | 27 ++++++++------ fs/ocfs2/dir.c | 13 +++---- fs/ocfs2/inode.c | 18 +++------- fs/ocfs2/resize.c | 2 +- fs/ocfs2/slot_map.c | 4 +-- fs/ocfs2/suballoc.c | 91 +++++++++++++++++++++++++++++++++-------------- fs/ocfs2/suballoc.h | 15 ++++---- fs/ocfs2/xattr.c | 26 +++++++------- 10 files changed, 149 insertions(+), 97 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index f430cc6e0f3..e823a27ba34 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -684,6 +684,9 @@ static int ocfs2_validate_extent_block(struct super_block *sb, struct ocfs2_extent_block *eb = (struct ocfs2_extent_block *)bh->b_data; + mlog(0, "Validating extent block %llu\n", + (unsigned long long)bh->b_blocknr); + if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) { ocfs2_error(sb, "Extent block #%llu has bad signature %.*s", @@ -719,21 +722,13 @@ int ocfs2_read_extent_block(struct inode *inode, u64 eb_blkno, int rc; struct buffer_head *tmp = *bh; - rc = ocfs2_read_block(inode, eb_blkno, &tmp); - if (rc) - goto out; - - rc = ocfs2_validate_extent_block(inode->i_sb, tmp); - if (rc) { - brelse(tmp); - goto out; - } + rc = ocfs2_read_block(inode, eb_blkno, &tmp, + ocfs2_validate_extent_block); /* If ocfs2_read_block() got us a new bh, pass it up. */ - if (!*bh) + if (!rc && !*bh) *bh = tmp; -out: return rc; } diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 3a178ec48d7..0e9eed0c223 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -39,6 +39,19 @@ #include "buffer_head_io.h" +/* + * Bits on bh->b_state used by ocfs2. + * + * These MUST be after the JBD2 bits. Currently BH_Unshadow is the last + * JBD2 bit. + */ +enum ocfs2_state_bits { + BH_NeedsValidate = BH_Unshadow + 1, +}; + +/* Expand the magic b_state functions */ +BUFFER_FNS(NeedsValidate, needs_validate); + int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, struct inode *inode) { @@ -166,7 +179,9 @@ bail: } int ocfs2_read_blocks(struct inode *inode, u64 block, int nr, - struct buffer_head *bhs[], int flags) + struct buffer_head *bhs[], int flags, + int (*validate)(struct super_block *sb, + struct buffer_head *bh)) { int status = 0; int i, ignore_cache = 0; @@ -298,6 +313,8 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr, clear_buffer_uptodate(bh); get_bh(bh); /* for end_buffer_read_sync() */ + if (validate) + set_buffer_needs_validate(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(READ, bh); continue; @@ -328,6 +345,20 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr, bhs[i] = NULL; continue; } + + if (buffer_needs_validate(bh)) { + /* We never set NeedsValidate if the + * buffer was held by the journal, so + * that better not have changed */ + BUG_ON(buffer_jbd(bh)); + clear_buffer_needs_validate(bh); + status = validate(inode->i_sb, bh); + if (status) { + put_bh(bh); + bhs[i] = NULL; + continue; + } + } } /* Always set the buffer in the cache, even if it was diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h index 75e1dcb1ade..c75d682dadd 100644 --- a/fs/ocfs2/buffer_head_io.h +++ b/fs/ocfs2/buffer_head_io.h @@ -31,21 +31,24 @@ void ocfs2_end_buffer_io_sync(struct buffer_head *bh, int uptodate); -static inline int ocfs2_read_block(struct inode *inode, - u64 off, - struct buffer_head **bh); - int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, struct inode *inode); -int ocfs2_read_blocks(struct inode *inode, - u64 block, - int nr, - struct buffer_head *bhs[], - int flags); int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, unsigned int nr, struct buffer_head *bhs[]); +/* + * If not NULL, validate() will be called on a buffer that is freshly + * read from disk. It will not be called if the buffer was in cache. + * Note that if validate() is being used for this buffer, it needs to + * be set even for a READAHEAD call, as it marks the buffer for later + * validation. + */ +int ocfs2_read_blocks(struct inode *inode, u64 block, int nr, + struct buffer_head *bhs[], int flags, + int (*validate)(struct super_block *sb, + struct buffer_head *bh)); + int ocfs2_write_super_or_backup(struct ocfs2_super *osb, struct buffer_head *bh); @@ -53,7 +56,9 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb, #define OCFS2_BH_READAHEAD 8 static inline int ocfs2_read_block(struct inode *inode, u64 off, - struct buffer_head **bh) + struct buffer_head **bh, + int (*validate)(struct super_block *sb, + struct buffer_head *bh)) { int status = 0; @@ -63,7 +68,7 @@ static inline int ocfs2_read_block(struct inode *inode, u64 off, goto bail; } - status = ocfs2_read_blocks(inode, off, 1, bh, 0); + status = ocfs2_read_blocks(inode, off, 1, bh, 0, validate); bail: return status; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index c2f3fd93be5..7e863d40380 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -214,6 +214,8 @@ static int ocfs2_validate_dir_block(struct super_block *sb, * Nothing yet. We don't validate dirents here, that's handled * in-place when the code walks them. */ + mlog(0, "Validating dirblock %llu\n", + (unsigned long long)bh->b_blocknr); return 0; } @@ -255,20 +257,13 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, goto out; } - rc = ocfs2_read_blocks(inode, p_blkno, 1, &tmp, flags); + rc = ocfs2_read_blocks(inode, p_blkno, 1, &tmp, flags, + ocfs2_validate_dir_block); if (rc) { mlog_errno(rc); goto out; } - if (!(flags & OCFS2_BH_READAHEAD)) { - rc = ocfs2_validate_dir_block(inode->i_sb, tmp); - if (rc) { - brelse(tmp); - goto out; - } - } - /* If ocfs2_read_blocks() got us a new bh, pass it up. */ if (!*bh) *bh = tmp; diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 9eb701b8646..ec3497bafda 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1255,6 +1255,9 @@ int ocfs2_validate_inode_block(struct super_block *sb, int rc = -EINVAL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data; + mlog(0, "Validating dinode %llu\n", + (unsigned long long)bh->b_blocknr); + BUG_ON(!buffer_uptodate(bh)); if (!OCFS2_IS_VALID_DINODE(di)) { @@ -1300,23 +1303,12 @@ int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh, struct buffer_head *tmp = *bh; rc = ocfs2_read_blocks(inode, OCFS2_I(inode)->ip_blkno, 1, &tmp, - flags); - if (rc) - goto out; - - if (!(flags & OCFS2_BH_READAHEAD)) { - rc = ocfs2_validate_inode_block(inode->i_sb, tmp); - if (rc) { - brelse(tmp); - goto out; - } - } + flags, ocfs2_validate_inode_block); /* If ocfs2_read_blocks() got us a new bh, pass it up. */ - if (!*bh) + if (!rc && !*bh) *bh = tmp; -out: return rc; } diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 252baff5eb8..867de3ebfca 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -394,7 +394,7 @@ static int ocfs2_check_new_group(struct inode *inode, (struct ocfs2_group_desc *)group_bh->b_data; u16 cl_bpc = le16_to_cpu(di->id2.i_chain.cl_bpc); - ret = ocfs2_validate_group_descriptor(inode->i_sb, di, group_bh, 1); + ret = ocfs2_check_group_descriptor(inode->i_sb, di, group_bh); if (ret) goto out; diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index bdda2d8f850..40661e7824e 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -151,7 +151,7 @@ int ocfs2_refresh_slot_info(struct ocfs2_super *osb) * this is not true, the read of -1 (UINT64_MAX) will fail. */ ret = ocfs2_read_blocks(si->si_inode, -1, si->si_blocks, si->si_bh, - OCFS2_BH_IGNORE_CACHE); + OCFS2_BH_IGNORE_CACHE, NULL); if (ret == 0) { spin_lock(&osb->osb_lock); ocfs2_update_slot_info(si); @@ -405,7 +405,7 @@ static int ocfs2_map_slot_buffers(struct ocfs2_super *osb, bh = NULL; /* Acquire a fresh bh */ status = ocfs2_read_blocks(si->si_inode, blkno, 1, &bh, - OCFS2_BH_IGNORE_CACHE); + OCFS2_BH_IGNORE_CACHE, NULL); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 766a00b2644..226fe21f260 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -145,14 +145,6 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl) return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc); } -int ocfs2_validate_group_descriptor(struct super_block *sb, - struct ocfs2_dinode *di, - struct buffer_head *bh, - int clean_error) -{ - unsigned int max_bits; - struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; - #define do_error(fmt, ...) \ do{ \ if (clean_error) \ @@ -161,6 +153,12 @@ int ocfs2_validate_group_descriptor(struct super_block *sb, ocfs2_error(sb, fmt, ##__VA_ARGS__); \ } while (0) +static int ocfs2_validate_gd_self(struct super_block *sb, + struct buffer_head *bh, + int clean_error) +{ + struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; + if (!OCFS2_IS_VALID_GROUP_DESC(gd)) { do_error("Group descriptor #%llu has bad signature %.*s", (unsigned long long)bh->b_blocknr, 7, @@ -184,6 +182,35 @@ int ocfs2_validate_group_descriptor(struct super_block *sb, return -EINVAL; } + if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) { + do_error("Group descriptor #%llu has bit count %u but " + "claims that %u are free", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_bits), + le16_to_cpu(gd->bg_free_bits_count)); + return -EINVAL; + } + + if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) { + do_error("Group descriptor #%llu has bit count %u but " + "max bitmap bits of %u", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_bits), + 8 * le16_to_cpu(gd->bg_size)); + return -EINVAL; + } + + return 0; +} + +static int ocfs2_validate_gd_parent(struct super_block *sb, + struct ocfs2_dinode *di, + struct buffer_head *bh, + int clean_error) +{ + unsigned int max_bits; + struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; + if (di->i_blkno != gd->bg_parent_dinode) { do_error("Group descriptor #%llu has bad parent " "pointer (%llu, expected %llu)", @@ -209,26 +236,35 @@ int ocfs2_validate_group_descriptor(struct super_block *sb, return -EINVAL; } - if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) { - do_error("Group descriptor #%llu has bit count %u but " - "claims that %u are free", - (unsigned long long)bh->b_blocknr, - le16_to_cpu(gd->bg_bits), - le16_to_cpu(gd->bg_free_bits_count)); - return -EINVAL; - } + return 0; +} - if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) { - do_error("Group descriptor #%llu has bit count %u but " - "max bitmap bits of %u", - (unsigned long long)bh->b_blocknr, - le16_to_cpu(gd->bg_bits), - 8 * le16_to_cpu(gd->bg_size)); - return -EINVAL; - } #undef do_error - return 0; +/* + * This version only prints errors. It does not fail the filesystem, and + * exists only for resize. + */ +int ocfs2_check_group_descriptor(struct super_block *sb, + struct ocfs2_dinode *di, + struct buffer_head *bh) +{ + int rc; + + rc = ocfs2_validate_gd_self(sb, bh, 1); + if (!rc) + rc = ocfs2_validate_gd_parent(sb, di, bh, 1); + + return rc; +} + +static int ocfs2_validate_group_descriptor(struct super_block *sb, + struct buffer_head *bh) +{ + mlog(0, "Validating group descriptor %llu\n", + (unsigned long long)bh->b_blocknr); + + return ocfs2_validate_gd_self(sb, bh, 0); } int ocfs2_read_group_descriptor(struct inode *inode, struct ocfs2_dinode *di, @@ -237,11 +273,12 @@ int ocfs2_read_group_descriptor(struct inode *inode, struct ocfs2_dinode *di, int rc; struct buffer_head *tmp = *bh; - rc = ocfs2_read_block(inode, gd_blkno, &tmp); + rc = ocfs2_read_block(inode, gd_blkno, &tmp, + ocfs2_validate_group_descriptor); if (rc) goto out; - rc = ocfs2_validate_group_descriptor(inode->i_sb, di, tmp, 0); + rc = ocfs2_validate_gd_parent(inode->i_sb, di, tmp, 0); if (rc) { brelse(tmp); goto out; diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index 43de4fd826d..e3c13c77f9e 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -165,16 +165,15 @@ void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac); u64 ocfs2_which_cluster_group(struct inode *inode, u32 cluster); /* - * By default, ocfs2_validate_group_descriptor() calls ocfs2_error() when it + * By default, ocfs2_read_group_descriptor() calls ocfs2_error() when it * finds a problem. A caller that wants to check a group descriptor - * without going readonly passes a nonzero clean_error. This is only - * resize, really. Everyone else should be using - * ocfs2_read_group_descriptor(). + * without going readonly should read the block with ocfs2_read_block[s]() + * and then checking it with this function. This is only resize, really. + * Everyone else should be using ocfs2_read_group_descriptor(). */ -int ocfs2_validate_group_descriptor(struct super_block *sb, - struct ocfs2_dinode *di, - struct buffer_head *bh, - int clean_error); +int ocfs2_check_group_descriptor(struct super_block *sb, + struct ocfs2_dinode *di, + struct buffer_head *bh); /* * Read a group descriptor block into *bh. If *bh is NULL, a bh will be * allocated. This is a cached read. The descriptor will be validated with diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index ef4aa5482d0..8af29b3bd6d 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -266,7 +266,8 @@ static int ocfs2_read_xattr_bucket(struct ocfs2_xattr_bucket *bucket, int rc; rc = ocfs2_read_blocks(bucket->bu_inode, xb_blkno, - bucket->bu_blocks, bucket->bu_bhs, 0); + bucket->bu_blocks, bucket->bu_bhs, 0, + NULL); if (rc) ocfs2_xattr_bucket_relse(bucket); return rc; @@ -359,12 +360,8 @@ static int ocfs2_read_xattr_block(struct inode *inode, u64 xb_blkno, int rc; struct buffer_head *tmp = *bh; - rc = ocfs2_read_block(inode, xb_blkno, &tmp); - if (!rc) { - rc = ocfs2_validate_xattr_block(inode->i_sb, tmp); - if (rc) - brelse(tmp); - } + rc = ocfs2_read_block(inode, xb_blkno, &tmp, + ocfs2_validate_xattr_block); /* If ocfs2_read_block() got us a new bh, pass it up. */ if (!rc && !*bh) @@ -925,7 +922,7 @@ static int ocfs2_xattr_get_value_outside(struct inode *inode, blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster); /* Copy ocfs2_xattr_value */ for (i = 0; i < num_clusters * bpc; i++, blkno++) { - ret = ocfs2_read_block(inode, blkno, &bh); + ret = ocfs2_read_block(inode, blkno, &bh, NULL); if (ret) { mlog_errno(ret); goto out; @@ -1174,7 +1171,7 @@ static int __ocfs2_xattr_set_value_outside(struct inode *inode, blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster); for (i = 0; i < num_clusters * bpc; i++, blkno++) { - ret = ocfs2_read_block(inode, blkno, &bh); + ret = ocfs2_read_block(inode, blkno, &bh, NULL); if (ret) { mlog_errno(ret); goto out; @@ -2206,7 +2203,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, base = xis->base; credits += OCFS2_INODE_UPDATE_CREDITS; } else { - int i, block_off; + int i, block_off = 0; xb = (struct ocfs2_xattr_block *)xbs->xattr_bh->b_data; xe = xbs->here; name_offset = le16_to_cpu(xe->xe_name_offset); @@ -2840,6 +2837,7 @@ static int ocfs2_find_xe_in_bucket(struct inode *inode, break; } + xe_name = bucket_block(bucket, block_off) + new_offset; if (!memcmp(name, xe_name, name_len)) { *xe_index = i; @@ -3598,7 +3596,7 @@ static int ocfs2_mv_xattr_bucket_cross_cluster(struct inode *inode, goto out; } - ret = ocfs2_read_block(inode, prev_blkno, &old_bh); + ret = ocfs2_read_block(inode, prev_blkno, &old_bh, NULL); if (ret < 0) { mlog_errno(ret); brelse(new_bh); @@ -3990,7 +3988,7 @@ static int ocfs2_cp_xattr_cluster(struct inode *inode, ocfs2_journal_dirty(handle, first_bh); /* update the new bucket header. */ - ret = ocfs2_read_block(inode, to_blk_start, &bh); + ret = ocfs2_read_block(inode, to_blk_start, &bh, NULL); if (ret < 0) { mlog_errno(ret); goto out; @@ -4337,7 +4335,7 @@ static int ocfs2_add_new_xattr_bucket(struct inode *inode, goto out; } - ret = ocfs2_read_block(inode, p_blkno, &first_bh); + ret = ocfs2_read_block(inode, p_blkno, &first_bh, NULL); if (ret) { mlog_errno(ret); goto out; @@ -4635,7 +4633,7 @@ static int ocfs2_xattr_bucket_value_truncate(struct inode *inode, BUG_ON(value_blk != (offset + OCFS2_XATTR_ROOT_SIZE - 1) / blocksize); value_blk += header_bh->b_blocknr; - ret = ocfs2_read_block(inode, value_blk, &value_bh); + ret = ocfs2_read_block(inode, value_blk, &value_bh, NULL); if (ret) { mlog_errno(ret); goto out; -- cgit v1.2.3-70-g09d2 From 511308d90b53479b194cd067715f44dc99d39b08 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Thu, 13 Nov 2008 14:49:21 -0800 Subject: ocfs2: Convert ocfs2_read_dir_block() to ocfs2_read_virt_blocks() Now that we've centralized the ocfs2_read_virt_blocks() code, let's use it in ocfs2_read_dir_block(). Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dir.c | 38 +++++--------------------------------- 1 file changed, 5 insertions(+), 33 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 7e863d40380..d83cff95759 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -231,44 +231,16 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, { int rc = 0; struct buffer_head *tmp = *bh; - u64 p_blkno; - if (((u64)v_block << inode->i_sb->s_blocksize_bits) >= - i_size_read(inode)) { - BUG_ON(!(flags & OCFS2_BH_READAHEAD)); - goto out; - } - - down_read(&OCFS2_I(inode)->ip_alloc_sem); - rc = ocfs2_extent_map_get_blocks(inode, v_block, &p_blkno, NULL, - NULL); - up_read(&OCFS2_I(inode)->ip_alloc_sem); - if (rc) { + rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags, + ocfs2_validate_dir_block); + if (rc) mlog_errno(rc); - goto out; - } - if (!p_blkno) { - rc = -EIO; - mlog(ML_ERROR, - "Directory #%llu contains a hole at offset %llu\n", - (unsigned long long)OCFS2_I(inode)->ip_blkno, - (unsigned long long)v_block << inode->i_sb->s_blocksize_bits); - goto out; - } - - rc = ocfs2_read_blocks(inode, p_blkno, 1, &tmp, flags, - ocfs2_validate_dir_block); - if (rc) { - mlog_errno(rc); - goto out; - } - - /* If ocfs2_read_blocks() got us a new bh, pass it up. */ - if (!*bh) + /* If ocfs2_read_virt_blocks() got us a new bh, pass it up. */ + if (!rc && !*bh) *bh = tmp; -out: return rc ? -EIO : 0; } -- cgit v1.2.3-70-g09d2 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/alloc.c | 20 +++++++++++-- fs/ocfs2/aops.c | 16 +++++++++-- fs/ocfs2/dir.c | 24 ++++++++++++++-- fs/ocfs2/file.c | 72 ++++++++++++++++++++++++++++++++++++++++++---- fs/ocfs2/inode.c | 10 +++++-- fs/ocfs2/journal.h | 84 ++++++++++++++++++++++++++++++++++++++++++++---------- fs/ocfs2/namei.c | 44 +++++++++++++++++++++++++--- fs/ocfs2/xattr.c | 14 +++++---- 8 files changed, 245 insertions(+), 39 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 69d67ab069b..84a7bd4db5d 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -28,6 +28,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_DISK_ALLOC #include @@ -5322,7 +5323,7 @@ int ocfs2_remove_btree_range(struct inode *inode, } } - handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS); + handle = ocfs2_start_trans(osb, ocfs2_remove_extent_credits(osb->sb)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); @@ -6552,6 +6553,8 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb, goto bail; } + vfs_dq_free_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, clusters_to_del)); spin_lock(&OCFS2_I(inode)->ip_lock); OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters) - clusters_to_del; @@ -6860,6 +6863,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, struct page **pages = NULL; loff_t end = osb->s_clustersize; struct ocfs2_extent_tree et; + int did_quota = 0; has_data = i_size_read(inode) ? 1 : 0; @@ -6879,7 +6883,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } } - handle = ocfs2_start_trans(osb, OCFS2_INLINE_TO_EXTENTS_CREDITS); + handle = ocfs2_start_trans(osb, + ocfs2_inline_to_extents_credits(osb->sb)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); @@ -6898,6 +6903,13 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, unsigned int page_end; u64 phys; + if (vfs_dq_alloc_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, 1))) { + ret = -EDQUOT; + goto out_commit; + } + did_quota = 1; + ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, &num); if (ret) { @@ -6971,6 +6983,10 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } out_commit: + if (ret < 0 && did_quota) + vfs_dq_free_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, 1)); + ocfs2_commit_trans(osb, handle); out_unlock: diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 6af79adb2ec..6b647ec87bb 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -27,6 +27,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_FILE_IO #include @@ -1730,6 +1731,11 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, wc->w_handle = handle; + if (clusters_to_alloc && vfs_dq_alloc_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc))) { + ret = -EDQUOT; + goto out_commit; + } /* * We don't want this to fail in ocfs2_write_end(), so do it * here. @@ -1738,7 +1744,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); - goto out_commit; + goto out_quota; } /* @@ -1751,14 +1757,14 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, mmap_page); if (ret) { mlog_errno(ret); - goto out_commit; + goto out_quota; } ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos, len); if (ret) { mlog_errno(ret); - goto out_commit; + goto out_quota; } if (data_ac) @@ -1770,6 +1776,10 @@ success: *pagep = wc->w_target_page; *fsdata = wc; return 0; +out_quota: + if (clusters_to_alloc) + vfs_dq_free_space(inode, + ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc)); out_commit: ocfs2_commit_trans(osb, handle); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index d83cff95759..3708fe482e3 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -40,6 +40,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_NAMEI #include @@ -1210,9 +1211,9 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, unsigned int blocks_wanted, struct buffer_head **first_block_bh) { - int ret, credits = OCFS2_INLINE_TO_EXTENTS_CREDITS; u32 alloc, bit_off, len; struct super_block *sb = dir->i_sb; + int ret, credits = ocfs2_inline_to_extents_credits(sb); u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(dir); @@ -1221,6 +1222,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; handle_t *handle; struct ocfs2_extent_tree et; + int did_quota = 0; ocfs2_init_dinode_extent_tree(&et, dir, di_bh); @@ -1258,6 +1260,12 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, goto out_sem; } + if (vfs_dq_alloc_space_nodirty(dir, + ocfs2_clusters_to_bytes(osb->sb, alloc))) { + ret = -EDQUOT; + goto out_commit; + } + did_quota = 1; /* * Try to claim as many clusters as the bitmap can give though * if we only get one now, that's enough to continue. The rest @@ -1380,6 +1388,9 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, dirdata_bh = NULL; out_commit: + if (ret < 0 && did_quota) + vfs_dq_free_space_nodirty(dir, + ocfs2_clusters_to_bytes(osb->sb, 2)); ocfs2_commit_trans(osb, handle); out_sem: @@ -1404,7 +1415,7 @@ static int ocfs2_do_extend_dir(struct super_block *sb, struct buffer_head **new_bh) { int status; - int extend; + int extend, did_quota = 0; u64 p_blkno, v_blkno; spin_lock(&OCFS2_I(dir)->ip_lock); @@ -1414,6 +1425,13 @@ static int ocfs2_do_extend_dir(struct super_block *sb, if (extend) { u32 offset = OCFS2_I(dir)->ip_clusters; + if (vfs_dq_alloc_space_nodirty(dir, + ocfs2_clusters_to_bytes(sb, 1))) { + status = -EDQUOT; + goto bail; + } + did_quota = 1; + status = ocfs2_add_inode_data(OCFS2_SB(sb), dir, &offset, 1, 0, parent_fe_bh, handle, data_ac, meta_ac, NULL); @@ -1439,6 +1457,8 @@ static int ocfs2_do_extend_dir(struct super_block *sb, } status = 0; bail: + if (did_quota && status < 0) + vfs_dq_free_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1)); mlog_exit(status); return status; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 372d96505a7..9374d374a26 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) diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 50dbc486ef7..288512c9dbc 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -28,6 +28,7 @@ #include #include #include +#include #include @@ -603,7 +604,8 @@ static int ocfs2_remove_inode(struct inode *inode, goto bail; } - handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS); + handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS + + ocfs2_quota_trans_credits(inode->i_sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); @@ -635,6 +637,7 @@ static int ocfs2_remove_inode(struct inode *inode, } ocfs2_remove_from_cache(inode, di_bh); + vfs_dq_free_inode(inode); status = ocfs2_free_dinode(handle, inode_alloc_inode, inode_alloc_bh, di); @@ -917,7 +920,10 @@ void ocfs2_delete_inode(struct inode *inode) mlog_entry("(inode->i_ino = %lu)\n", inode->i_ino); - if (is_bad_inode(inode)) { + /* When we fail in read_inode() we mark inode as bad. The second test + * catches the case when inode allocation fails before allocating + * a block for inode. */ + if (is_bad_inode(inode) || !OCFS2_I(inode)->ip_blkno) { mlog(0, "Skipping delete of bad inode\n"); goto bail; } diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 8203980fefe..ee08e9c1fc1 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -284,6 +284,37 @@ int ocfs2_journal_dirty(handle_t *handle, /* extended attribute block update */ #define OCFS2_XATTR_BLOCK_UPDATE_CREDITS 1 +/* global quotafile inode update, data block */ +#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1) + +/* + * The two writes below can accidentally see global info dirty due + * to set_info() quotactl so make them prepared for the writes. + */ +/* quota data block, global info */ +/* Write to local quota file */ +#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + 1) + +/* global quota data block, local quota data block, global quota inode, + * global quota info */ +#define OCFS2_QSYNC_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 3) + +static inline int ocfs2_quota_trans_credits(struct super_block *sb) +{ + int credits = 0; + + if (OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) + credits += OCFS2_QWRITE_CREDITS; + if (OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) + credits += OCFS2_QWRITE_CREDITS; + return credits; +} + +/* Number of credits needed for removing quota structure from file */ +int ocfs2_calc_qdel_credits(struct super_block *sb, int type); +/* Number of credits needed for initialization of new quota structure */ +int ocfs2_calc_qinit_credits(struct super_block *sb, int type); + /* group extend. inode update and last group update. */ #define OCFS2_GROUP_EXTEND_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1) @@ -294,8 +325,11 @@ int ocfs2_journal_dirty(handle_t *handle, * prev. group desc. if we relink. */ #define OCFS2_SUBALLOC_ALLOC (3) -#define OCFS2_INLINE_TO_EXTENTS_CREDITS (OCFS2_SUBALLOC_ALLOC \ - + OCFS2_INODE_UPDATE_CREDITS) +static inline int ocfs2_inline_to_extents_credits(struct super_block *sb) +{ + return OCFS2_SUBALLOC_ALLOC + OCFS2_INODE_UPDATE_CREDITS + + ocfs2_quota_trans_credits(sb); +} /* dinode + group descriptor update. We don't relink on free yet. */ #define OCFS2_SUBALLOC_FREE (2) @@ -304,16 +338,23 @@ int ocfs2_journal_dirty(handle_t *handle, #define OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC (OCFS2_SUBALLOC_FREE \ + OCFS2_TRUNCATE_LOG_UPDATE) -#define OCFS2_REMOVE_EXTENT_CREDITS (OCFS2_TRUNCATE_LOG_UPDATE + OCFS2_INODE_UPDATE_CREDITS) +static inline int ocfs2_remove_extent_credits(struct super_block *sb) +{ + return OCFS2_TRUNCATE_LOG_UPDATE + OCFS2_INODE_UPDATE_CREDITS + + ocfs2_quota_trans_credits(sb); +} /* data block for new dir/symlink, 2 for bitmap updates (bitmap fe + * bitmap block for the new bit) */ #define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2) /* parent fe, parent block, new file entry, inode alloc fe, inode alloc - * group descriptor + mkdir/symlink blocks */ -#define OCFS2_MKNOD_CREDITS (3 + OCFS2_SUBALLOC_ALLOC \ - + OCFS2_DIR_LINK_ADDITIONAL_CREDITS) + * group descriptor + mkdir/symlink blocks + quota update */ +static inline int ocfs2_mknod_credits(struct super_block *sb) +{ + return 3 + OCFS2_SUBALLOC_ALLOC + OCFS2_DIR_LINK_ADDITIONAL_CREDITS + + ocfs2_quota_trans_credits(sb); +} /* local alloc metadata change + main bitmap updates */ #define OCFS2_WINDOW_MOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS \ @@ -323,13 +364,21 @@ int ocfs2_journal_dirty(handle_t *handle, * for the dinode, one for the new block. */ #define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2) -/* file update (nlink, etc) + directory mtime/ctime + dir entry block */ -#define OCFS2_LINK_CREDITS (2*OCFS2_INODE_UPDATE_CREDITS + 1) +/* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota + * update on dir */ +static inline int ocfs2_link_credits(struct super_block *sb) +{ + return 2*OCFS2_INODE_UPDATE_CREDITS + 1 + + ocfs2_quota_trans_credits(sb); +} /* inode + dir inode (if we unlink a dir), + dir entry block + orphan * dir inode link */ -#define OCFS2_UNLINK_CREDITS (2 * OCFS2_INODE_UPDATE_CREDITS + 1 \ - + OCFS2_LINK_CREDITS) +static inline int ocfs2_unlink_credits(struct super_block *sb) +{ + /* The quota update from ocfs2_link_credits is unused here... */ + return 2 * OCFS2_INODE_UPDATE_CREDITS + 1 + ocfs2_link_credits(sb); +} /* dinode + orphan dir dinode + inode alloc dinode + orphan dir entry + * inode alloc group descriptor */ @@ -338,8 +387,10 @@ int ocfs2_journal_dirty(handle_t *handle, /* dinode update, old dir dinode update, new dir dinode update, old * dir dir entry, new dir dir entry, dir entry update for renaming * directory + target unlink */ -#define OCFS2_RENAME_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 3 \ - + OCFS2_UNLINK_CREDITS) +static inline int ocfs2_rename_credits(struct super_block *sb) +{ + return 3 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_unlink_credits(sb); +} /* global bitmap dinode, group desc., relinked group, * suballocator dinode, group desc., relinked group, @@ -377,18 +428,19 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb, * credit for the dinode there. */ extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth); - return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks; + return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks + + ocfs2_quota_trans_credits(sb); } static inline int ocfs2_calc_symlink_credits(struct super_block *sb) { - int blocks = OCFS2_MKNOD_CREDITS; + int blocks = ocfs2_mknod_credits(sb); /* links can be longer than one block so we may update many * within our single allocated extent. */ blocks += ocfs2_clusters_to_blocks(sb, 1); - return blocks; + return blocks + ocfs2_quota_trans_credits(sb); } static inline int ocfs2_calc_group_alloc_credits(struct super_block *sb, @@ -425,6 +477,8 @@ static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb, /* update to the truncate log. */ credits += OCFS2_TRUNCATE_LOG_UPDATE; + credits += ocfs2_quota_trans_credits(sb); + return credits; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 0134bafdab9..6173807ba23 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -40,6 +40,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_NAMEI #include @@ -212,6 +213,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, int mode) } else inode->i_gid = current_fsgid(); inode->i_mode = mode; + vfs_dq_init(inode); return inode; } @@ -236,6 +238,7 @@ static int ocfs2_mknod(struct inode *dir, struct ocfs2_security_xattr_info si = { .enable = 1, }; + int did_quota_inode = 0; mlog_entry("(0x%p, 0x%p, %d, %lu, '%.*s')\n", dir, dentry, mode, (unsigned long)dev, dentry->d_name.len, @@ -323,7 +326,8 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - handle = ocfs2_start_trans(osb, OCFS2_MKNOD_CREDITS + xattr_credits); + handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb) + + xattr_credits); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; @@ -331,6 +335,15 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + /* We don't use standard VFS wrapper because we don't want vfs_dq_init + * to be called. */ + if (sb_any_quota_active(osb->sb) && + osb->sb->dq_op->alloc_inode(inode, 1) == NO_QUOTA) { + status = -EDQUOT; + goto leave; + } + did_quota_inode = 1; + /* do the real work now. */ status = ocfs2_mknod_locked(osb, dir, inode, dentry, dev, &new_fe_bh, parent_fe_bh, handle, @@ -399,6 +412,8 @@ static int ocfs2_mknod(struct inode *dir, d_instantiate(dentry, inode); status = 0; leave: + if (status < 0 && did_quota_inode) + vfs_dq_free_inode(inode); if (handle) ocfs2_commit_trans(osb, handle); @@ -641,7 +656,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto out_unlock_inode; } - handle = ocfs2_start_trans(osb, OCFS2_LINK_CREDITS); + handle = ocfs2_start_trans(osb, ocfs2_link_credits(osb->sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); handle = NULL; @@ -828,7 +843,7 @@ static int ocfs2_unlink(struct inode *dir, } } - handle = ocfs2_start_trans(osb, OCFS2_UNLINK_CREDITS); + handle = ocfs2_start_trans(osb, ocfs2_unlink_credits(osb->sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; @@ -1234,7 +1249,7 @@ static int ocfs2_rename(struct inode *old_dir, } } - handle = ocfs2_start_trans(osb, OCFS2_RENAME_CREDITS); + handle = ocfs2_start_trans(osb, ocfs2_rename_credits(osb->sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; @@ -1555,6 +1570,7 @@ static int ocfs2_symlink(struct inode *dir, struct ocfs2_security_xattr_info si = { .enable = 1, }; + int did_quota = 0, did_quota_inode = 0; mlog_entry("(0x%p, 0x%p, symname='%s' actual='%.*s')\n", dir, dentry, symname, dentry->d_name.len, dentry->d_name.name); @@ -1648,6 +1664,15 @@ static int ocfs2_symlink(struct inode *dir, goto bail; } + /* We don't use standard VFS wrapper because we don't want vfs_dq_init + * to be called. */ + if (sb_any_quota_active(osb->sb) && + osb->sb->dq_op->alloc_inode(inode, 1) == NO_QUOTA) { + status = -EDQUOT; + goto bail; + } + did_quota_inode = 1; + status = ocfs2_mknod_locked(osb, dir, inode, dentry, 0, &new_fe_bh, parent_fe_bh, handle, inode_ac); @@ -1663,6 +1688,12 @@ static int ocfs2_symlink(struct inode *dir, u32 offset = 0; inode->i_op = &ocfs2_symlink_inode_operations; + if (vfs_dq_alloc_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, 1))) { + status = -EDQUOT; + goto bail; + } + did_quota = 1; status = ocfs2_add_inode_data(osb, inode, &offset, 1, 0, new_fe_bh, handle, data_ac, NULL, @@ -1728,6 +1759,11 @@ static int ocfs2_symlink(struct inode *dir, dentry->d_op = &ocfs2_dentry_ops; d_instantiate(dentry, inode); bail: + if (status < 0 && did_quota) + vfs_dq_free_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, 1)); + if (status < 0 && did_quota_inode) + vfs_dq_free_inode(inode); if (handle) ocfs2_commit_trans(osb, handle); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 9cb71e1c7c6..3b9634c7d29 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1665,7 +1665,8 @@ static int ocfs2_remove_value_outside(struct inode*inode, ocfs2_init_dealloc_ctxt(&ctxt.dealloc); - ctxt.handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS); + ctxt.handle = ocfs2_start_trans(osb, + ocfs2_remove_extent_credits(osb->sb)); if (IS_ERR(ctxt.handle)) { ret = PTR_ERR(ctxt.handle); mlog_errno(ret); @@ -2233,7 +2234,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, */ if (!xi->value) { if (!ocfs2_xattr_is_local(xe)) - credits += OCFS2_REMOVE_EXTENT_CREDITS; + credits += ocfs2_remove_extent_credits(inode->i_sb); goto out; } @@ -2250,7 +2251,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, */ if (ocfs2_xattr_can_be_in_inode(inode, xi, xis)) { clusters_add += new_clusters; - credits += OCFS2_REMOVE_EXTENT_CREDITS + + credits += ocfs2_remove_extent_credits(inode->i_sb) + OCFS2_INODE_UPDATE_CREDITS; if (!ocfs2_xattr_is_local(xe)) credits += ocfs2_calc_extend_credits( @@ -2275,7 +2276,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, xv = &def_xv.xv; if (old_clusters >= new_clusters) { - credits += OCFS2_REMOVE_EXTENT_CREDITS; + credits += ocfs2_remove_extent_credits(inode->i_sb); goto out; } else { meta_add += ocfs2_extend_meta_needed(&xv->xr_list); @@ -4750,7 +4751,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode, } } - handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS); + handle = ocfs2_start_trans(osb, ocfs2_remove_extent_credits(osb->sb)); if (IS_ERR(handle)) { ret = -ENOMEM; mlog_errno(ret); @@ -5109,7 +5110,8 @@ static int ocfs2_delete_xattr_in_bucket(struct inode *inode, ocfs2_init_dealloc_ctxt(&ctxt.dealloc); - ctxt.handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS); + ctxt.handle = ocfs2_start_trans(osb, + ocfs2_remove_extent_credits(osb->sb)); if (IS_ERR(ctxt.handle)) { ret = PTR_ERR(ctxt.handle); mlog_errno(ret); -- cgit v1.2.3-70-g09d2 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/alloc.c | 233 ++++++++++++++++++++++++++++-------------------- fs/ocfs2/alloc.h | 5 +- fs/ocfs2/aops.c | 8 +- fs/ocfs2/dir.c | 48 ++++++---- fs/ocfs2/file.c | 16 ++-- fs/ocfs2/inode.c | 17 ++-- fs/ocfs2/journal.c | 2 + fs/ocfs2/journal.h | 3 +- fs/ocfs2/localalloc.c | 18 ++-- fs/ocfs2/namei.c | 38 ++++---- fs/ocfs2/ocfs2.h | 4 + fs/ocfs2/quota_global.c | 2 +- fs/ocfs2/quota_local.c | 18 ++-- fs/ocfs2/resize.c | 16 ++-- fs/ocfs2/suballoc.c | 58 ++++++------ 15 files changed, 280 insertions(+), 206 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index c22ff49b5e3..6e58fd557e5 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -298,11 +298,13 @@ static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = { static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et, struct inode *inode, struct buffer_head *bh, + ocfs2_journal_access_func access, void *obj, struct ocfs2_extent_tree_operations *ops) { et->et_ops = ops; et->et_root_bh = bh; + et->et_root_journal_access = access; if (!obj) obj = (void *)bh->b_data; et->et_object = obj; @@ -318,15 +320,16 @@ void ocfs2_init_dinode_extent_tree(struct ocfs2_extent_tree *et, struct inode *inode, struct buffer_head *bh) { - __ocfs2_init_extent_tree(et, inode, bh, NULL, &ocfs2_dinode_et_ops); + __ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access_di, + NULL, &ocfs2_dinode_et_ops); } void ocfs2_init_xattr_tree_extent_tree(struct ocfs2_extent_tree *et, struct inode *inode, struct buffer_head *bh) { - __ocfs2_init_extent_tree(et, inode, bh, NULL, - &ocfs2_xattr_tree_et_ops); + __ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access_xb, + NULL, &ocfs2_xattr_tree_et_ops); } void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et, @@ -334,7 +337,7 @@ void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et, struct buffer_head *bh, struct ocfs2_xattr_value_root *xv) { - __ocfs2_init_extent_tree(et, inode, bh, xv, + __ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access, xv, &ocfs2_xattr_value_et_ops); } @@ -356,6 +359,15 @@ static inline void ocfs2_et_update_clusters(struct inode *inode, et->et_ops->eo_update_clusters(inode, et, clusters); } +static inline int ocfs2_et_root_journal_access(handle_t *handle, + struct inode *inode, + struct ocfs2_extent_tree *et, + int type) +{ + return et->et_root_journal_access(handle, inode, et->et_root_bh, + type); +} + static inline int ocfs2_et_insert_check(struct inode *inode, struct ocfs2_extent_tree *et, struct ocfs2_extent_rec *rec) @@ -396,12 +408,14 @@ struct ocfs2_path_item { #define OCFS2_MAX_PATH_DEPTH 5 struct ocfs2_path { - int p_tree_depth; - struct ocfs2_path_item p_node[OCFS2_MAX_PATH_DEPTH]; + int p_tree_depth; + ocfs2_journal_access_func p_root_access; + struct ocfs2_path_item p_node[OCFS2_MAX_PATH_DEPTH]; }; #define path_root_bh(_path) ((_path)->p_node[0].bh) #define path_root_el(_path) ((_path)->p_node[0].el) +#define path_root_access(_path)((_path)->p_root_access) #define path_leaf_bh(_path) ((_path)->p_node[(_path)->p_tree_depth].bh) #define path_leaf_el(_path) ((_path)->p_node[(_path)->p_tree_depth].el) #define path_num_items(_path) ((_path)->p_tree_depth + 1) @@ -434,6 +448,8 @@ static void ocfs2_reinit_path(struct ocfs2_path *path, int keep_root) */ if (keep_root) depth = le16_to_cpu(path_root_el(path)->l_tree_depth); + else + path_root_access(path) = NULL; path->p_tree_depth = depth; } @@ -459,6 +475,7 @@ static void ocfs2_cp_path(struct ocfs2_path *dest, struct ocfs2_path *src) BUG_ON(path_root_bh(dest) != path_root_bh(src)); BUG_ON(path_root_el(dest) != path_root_el(src)); + BUG_ON(path_root_access(dest) != path_root_access(src)); ocfs2_reinit_path(dest, 1); @@ -480,6 +497,7 @@ static void ocfs2_mv_path(struct ocfs2_path *dest, struct ocfs2_path *src) int i; BUG_ON(path_root_bh(dest) != path_root_bh(src)); + BUG_ON(path_root_access(dest) != path_root_access(src)); for(i = 1; i < OCFS2_MAX_PATH_DEPTH; i++) { brelse(dest->p_node[i].bh); @@ -515,7 +533,8 @@ static inline void ocfs2_path_insert_eb(struct ocfs2_path *path, int index, } static struct ocfs2_path *ocfs2_new_path(struct buffer_head *root_bh, - struct ocfs2_extent_list *root_el) + struct ocfs2_extent_list *root_el, + ocfs2_journal_access_func access) { struct ocfs2_path *path; @@ -527,6 +546,7 @@ static struct ocfs2_path *ocfs2_new_path(struct buffer_head *root_bh, get_bh(root_bh); path_root_bh(path) = root_bh; path_root_el(path) = root_el; + path_root_access(path) = access; } return path; @@ -534,12 +554,38 @@ static struct ocfs2_path *ocfs2_new_path(struct buffer_head *root_bh, static struct ocfs2_path *ocfs2_new_path_from_path(struct ocfs2_path *path) { - return ocfs2_new_path(path_root_bh(path), path_root_el(path)); + return ocfs2_new_path(path_root_bh(path), path_root_el(path), + path_root_access(path)); } static struct ocfs2_path *ocfs2_new_path_from_et(struct ocfs2_extent_tree *et) { - return ocfs2_new_path(et->et_root_bh, et->et_root_el); + return ocfs2_new_path(et->et_root_bh, et->et_root_el, + et->et_root_journal_access); +} + +/* + * Journal the buffer at depth idx. All idx>0 are extent_blocks, + * otherwise it's the root_access function. + * + * I don't like the way this function's name looks next to + * ocfs2_journal_access_path(), but I don't have a better one. + */ +static int ocfs2_path_bh_journal_access(handle_t *handle, + struct inode *inode, + struct ocfs2_path *path, + int idx) +{ + ocfs2_journal_access_func access = path_root_access(path); + + if (!access) + access = ocfs2_journal_access; + + if (idx) + access = ocfs2_journal_access_eb; + + return access(handle, inode, path->p_node[idx].bh, + OCFS2_JOURNAL_ACCESS_WRITE); } /* @@ -554,8 +600,7 @@ static int ocfs2_journal_access_path(struct inode *inode, handle_t *handle, goto out; for(i = 0; i < path_num_items(path); i++) { - ret = ocfs2_journal_access(handle, inode, path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, path, i); if (ret < 0) { mlog_errno(ret); goto out; @@ -708,8 +753,11 @@ static int ocfs2_validate_extent_block(struct super_block *sb, * local to this block. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &eb->h_check); - if (rc) + if (rc) { + mlog(ML_ERROR, "Checksum failed for extent block %llu\n", + (unsigned long long)bh->b_blocknr); return rc; + } /* * Errors after here are fatal. @@ -842,8 +890,8 @@ static int ocfs2_create_new_meta_bhs(struct ocfs2_super *osb, } ocfs2_set_new_buffer_uptodate(inode, bhs[i]); - status = ocfs2_journal_access(handle, inode, bhs[i], - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_eb(handle, inode, bhs[i], + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; @@ -986,8 +1034,8 @@ static int ocfs2_add_branch(struct ocfs2_super *osb, BUG_ON(!OCFS2_IS_VALID_EXTENT_BLOCK(eb)); eb_el = &eb->h_list; - status = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_eb(handle, inode, bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; @@ -1026,21 +1074,21 @@ static int ocfs2_add_branch(struct ocfs2_super *osb, * journal_dirty erroring as it won't unless we've aborted the * handle (in which case we would never be here) so reserving * the write with journal_access is all we need to do. */ - status = ocfs2_journal_access(handle, inode, *last_eb_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_eb(handle, inode, *last_eb_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } - status = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } if (eb_bh) { - status = ocfs2_journal_access(handle, inode, eb_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_eb(handle, inode, eb_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -1129,8 +1177,8 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb, eb_el = &eb->h_list; root_el = et->et_root_el; - status = ocfs2_journal_access(handle, inode, new_eb_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_eb(handle, inode, new_eb_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; @@ -1148,8 +1196,8 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb, goto bail; } - status = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -1918,25 +1966,23 @@ static int ocfs2_rotate_subtree_right(struct inode *inode, root_bh = left_path->p_node[subtree_index].bh; BUG_ON(root_bh != right_path->p_node[subtree_index].bh); - ret = ocfs2_journal_access(handle, inode, root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, right_path, + subtree_index); if (ret) { mlog_errno(ret); goto out; } for(i = subtree_index + 1; i < path_num_items(right_path); i++) { - ret = ocfs2_journal_access(handle, inode, - right_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + right_path, i); if (ret) { mlog_errno(ret); goto out; } - ret = ocfs2_journal_access(handle, inode, - left_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + left_path, i); if (ret) { mlog_errno(ret); goto out; @@ -2455,9 +2501,9 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle, return -EAGAIN; if (le16_to_cpu(right_leaf_el->l_next_free_rec) > 1) { - ret = ocfs2_journal_access(handle, inode, - path_leaf_bh(right_path), - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_eb(handle, inode, + path_leaf_bh(right_path), + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -2474,8 +2520,8 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle, * We have to update i_last_eb_blk during the meta * data delete. */ - ret = ocfs2_journal_access(handle, inode, et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -2490,25 +2536,23 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle, */ BUG_ON(right_has_empty && !del_right_subtree); - ret = ocfs2_journal_access(handle, inode, root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, right_path, + subtree_index); if (ret) { mlog_errno(ret); goto out; } for(i = subtree_index + 1; i < path_num_items(right_path); i++) { - ret = ocfs2_journal_access(handle, inode, - right_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + right_path, i); if (ret) { mlog_errno(ret); goto out; } - ret = ocfs2_journal_access(handle, inode, - left_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + left_path, i); if (ret) { mlog_errno(ret); goto out; @@ -2653,16 +2697,17 @@ out: static int ocfs2_rotate_rightmost_leaf_left(struct inode *inode, handle_t *handle, - struct buffer_head *bh, - struct ocfs2_extent_list *el) + struct ocfs2_path *path) { int ret; + struct buffer_head *bh = path_leaf_bh(path); + struct ocfs2_extent_list *el = path_leaf_el(path); if (!ocfs2_is_empty_extent(&el->l_recs[0])) return 0; - ret = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, path, + path_num_items(path) - 1); if (ret) { mlog_errno(ret); goto out; @@ -2744,9 +2789,8 @@ static int __ocfs2_rotate_tree_left(struct inode *inode, * Caller might still want to make changes to the * tree root, so re-add it to the journal here. */ - ret = ocfs2_journal_access(handle, inode, - path_root_bh(left_path), - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + left_path, 0); if (ret) { mlog_errno(ret); goto out; @@ -2929,8 +2973,7 @@ rightmost_no_delete: * it up front. */ ret = ocfs2_rotate_rightmost_leaf_left(inode, handle, - path_leaf_bh(path), - path_leaf_el(path)); + path); if (ret) mlog_errno(ret); goto out; @@ -3164,8 +3207,8 @@ static int ocfs2_merge_rec_right(struct inode *inode, root_bh = left_path->p_node[subtree_index].bh; BUG_ON(root_bh != right_path->p_node[subtree_index].bh); - ret = ocfs2_journal_access(handle, inode, root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, right_path, + subtree_index); if (ret) { mlog_errno(ret); goto out; @@ -3173,17 +3216,15 @@ static int ocfs2_merge_rec_right(struct inode *inode, for (i = subtree_index + 1; i < path_num_items(right_path); i++) { - ret = ocfs2_journal_access(handle, inode, - right_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + right_path, i); if (ret) { mlog_errno(ret); goto out; } - ret = ocfs2_journal_access(handle, inode, - left_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + left_path, i); if (ret) { mlog_errno(ret); goto out; @@ -3195,8 +3236,8 @@ static int ocfs2_merge_rec_right(struct inode *inode, right_rec = &el->l_recs[index + 1]; } - ret = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, left_path, + path_num_items(left_path) - 1); if (ret) { mlog_errno(ret); goto out; @@ -3335,8 +3376,8 @@ static int ocfs2_merge_rec_left(struct inode *inode, root_bh = left_path->p_node[subtree_index].bh; BUG_ON(root_bh != right_path->p_node[subtree_index].bh); - ret = ocfs2_journal_access(handle, inode, root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, right_path, + subtree_index); if (ret) { mlog_errno(ret); goto out; @@ -3344,17 +3385,15 @@ static int ocfs2_merge_rec_left(struct inode *inode, for (i = subtree_index + 1; i < path_num_items(right_path); i++) { - ret = ocfs2_journal_access(handle, inode, - right_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + right_path, i); if (ret) { mlog_errno(ret); goto out; } - ret = ocfs2_journal_access(handle, inode, - left_path->p_node[i].bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, + left_path, i); if (ret) { mlog_errno(ret); goto out; @@ -3366,8 +3405,8 @@ static int ocfs2_merge_rec_left(struct inode *inode, has_empty_extent = 1; } - ret = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_path_bh_journal_access(handle, inode, left_path, + path_num_items(left_path) - 1); if (ret) { mlog_errno(ret); goto out; @@ -4009,8 +4048,8 @@ static int ocfs2_do_insert_extent(struct inode *inode, el = et->et_root_el; - ret = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -4071,8 +4110,8 @@ static int ocfs2_do_insert_extent(struct inode *inode, * ocfs2_rotate_tree_right() might have extended the * transaction without re-journaling our tree root. */ - ret = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -4593,9 +4632,9 @@ int ocfs2_add_clusters_in_btree(struct ocfs2_super *osb, BUG_ON(num_bits > clusters_to_add); - /* reserve our write early -- insert_extent may update the inode */ - status = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + /* reserve our write early -- insert_extent may update the tree root */ + status = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; @@ -5347,8 +5386,8 @@ int ocfs2_remove_btree_range(struct inode *inode, goto out; } - ret = ocfs2_journal_access(handle, inode, et->et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_et_root_journal_access(handle, inode, et, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -5461,8 +5500,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb, goto bail; } - status = ocfs2_journal_access(handle, tl_inode, tl_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, tl_inode, tl_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -5523,8 +5562,8 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, while (i >= 0) { /* Caller has given us at least enough credits to * update the truncate log dinode */ - status = ocfs2_journal_access(handle, tl_inode, tl_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, tl_inode, tl_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -5780,6 +5819,7 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb, * tl_used. */ tl->tl_used = 0; + ocfs2_compute_meta_ecc(osb->sb, tl_bh->b_data, &di->i_check); status = ocfs2_write_block(osb, tl_bh, tl_inode); if (status < 0) { mlog_errno(status); @@ -6546,8 +6586,8 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb, } if (last_eb_bh) { - status = ocfs2_journal_access(handle, inode, last_eb_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_eb(handle, inode, last_eb_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -6908,8 +6948,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, goto out_unlock; } - ret = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; @@ -7043,7 +7083,8 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb, new_highest_cpos = ocfs2_clusters_for_bytes(osb->sb, i_size_read(inode)); - path = ocfs2_new_path(fe_bh, &di->id2.i_list); + path = ocfs2_new_path(fe_bh, &di->id2.i_list, + ocfs2_journal_access_di); if (!path) { status = -ENOMEM; mlog_errno(status); @@ -7276,8 +7317,8 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, goto out; } - ret = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 59d37d1b7d4..4b6fea22748 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -45,7 +45,9 @@ * * ocfs2_extent_tree contains info for the root of the b-tree, it must have a * root ocfs2_extent_list and a root_bh so that they can be used in the b-tree - * functions. + * functions. With metadata ecc, we now call different journal_access + * functions for each type of metadata, so it must have the + * root_journal_access function. * ocfs2_extent_tree_operations abstract the normal operations we do for * the root of extent b-tree. */ @@ -54,6 +56,7 @@ struct ocfs2_extent_tree { struct ocfs2_extent_tree_operations *et_ops; struct buffer_head *et_root_bh; struct ocfs2_extent_list *et_root_el; + ocfs2_journal_access_func et_root_journal_access; void *et_object; unsigned int et_max_leaf_clusters; }; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 6b647ec87bb..a067a6cffb0 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1512,8 +1512,8 @@ static int ocfs2_write_begin_inline(struct address_space *mapping, goto out; } - ret = ocfs2_journal_access(handle, inode, wc->w_di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { ocfs2_commit_trans(osb, handle); @@ -1740,8 +1740,8 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, * We don't want this to fail in ocfs2_write_end(), so do it * here. */ - ret = ocfs2_journal_access(handle, inode, wc->w_di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_quota; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 3708fe482e3..45e4e03d8f7 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -378,14 +378,18 @@ int ocfs2_update_entry(struct inode *dir, handle_t *handle, struct inode *new_entry_inode) { int ret; + ocfs2_journal_access_func access = ocfs2_journal_access_db; /* * The same code works fine for both inline-data and extent - * based directories, so no need to split this up. + * based directories, so no need to split this up. The only + * difference is the journal_access function. */ - ret = ocfs2_journal_access(handle, dir, de_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + access = ocfs2_journal_access_di; + + ret = access(handle, dir, de_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -407,9 +411,13 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, { struct ocfs2_dir_entry *de, *pde; int i, status = -ENOENT; + ocfs2_journal_access_func access = ocfs2_journal_access_db; mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh); + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + access = ocfs2_journal_access_di; + i = 0; pde = NULL; de = (struct ocfs2_dir_entry *) first_de; @@ -420,8 +428,8 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, goto bail; } if (de == de_del) { - status = ocfs2_journal_access(handle, dir, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = access(handle, dir, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { status = -EIO; mlog_errno(status); @@ -581,8 +589,14 @@ int __ocfs2_add_entry(handle_t *handle, goto bail; } - status = ocfs2_journal_access(handle, dir, insert_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + if (insert_bh == parent_fe_bh) + status = ocfs2_journal_access_di(handle, dir, + insert_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + else + status = ocfs2_journal_access_db(handle, dir, + insert_bh, + OCFS2_JOURNAL_ACCESS_WRITE); /* By now the buffer is marked for journaling */ offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { @@ -1081,8 +1095,8 @@ static int ocfs2_fill_new_dir_id(struct ocfs2_super *osb, struct ocfs2_inline_data *data = &di->id2.i_data; unsigned int size = le16_to_cpu(data->id_count); - ret = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -1129,8 +1143,8 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, ocfs2_set_new_buffer_uptodate(inode, new_bh); - status = ocfs2_journal_access(handle, inode, new_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_db(handle, inode, new_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; @@ -1292,8 +1306,8 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, ocfs2_set_new_buffer_uptodate(dir, dirdata_bh); - ret = ocfs2_journal_access(handle, dir, dirdata_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + ret = ocfs2_journal_access_db(handle, dir, dirdata_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out_commit; @@ -1319,8 +1333,8 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, * We let the later dirent insert modify c/mtime - to the user * the data hasn't changed. */ - ret = ocfs2_journal_access(handle, dir, di_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + ret = ocfs2_journal_access_di(handle, dir, di_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out_commit; @@ -1583,8 +1597,8 @@ do_extend: ocfs2_set_new_buffer_uptodate(dir, new_bh); - status = ocfs2_journal_access(handle, dir, new_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_db(handle, dir, new_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9374d374a26..e8f795f978a 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; diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 9370b652ab9..229e707bc05 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -537,8 +537,8 @@ static int ocfs2_truncate_for_delete(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; @@ -621,8 +621,8 @@ static int ocfs2_remove_inode(struct inode *inode, } /* set the inodes dtime */ - status = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail_commit; @@ -1190,8 +1190,8 @@ int ocfs2_mark_inode_dirty(handle_t *handle, mlog_entry("(inode %llu)\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); - 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; @@ -1277,8 +1277,11 @@ int ocfs2_validate_inode_block(struct super_block *sb, * local to this block. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check); - if (rc) + if (rc) { + mlog(ML_ERROR, "Checksum failed for dinode %llu\n", + (unsigned long long)bh->b_blocknr); goto bail; + } /* * Errors after here are fatal. diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 2daa5848faf..3b54dba0f74 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -752,6 +752,7 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb, if (replayed) ocfs2_bump_recovery_generation(fe); + ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &fe->i_check); status = ocfs2_write_block(osb, bh, journal->j_inode); if (status < 0) mlog_errno(status); @@ -1486,6 +1487,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, osb->slot_recovery_generations[slot_num] = ocfs2_get_recovery_generation(fe); + ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &fe->i_check); status = ocfs2_write_block(osb, bh, inode); if (status < 0) mlog_errno(status); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index bca370dab02..3c3532e1307 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -247,9 +247,10 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks); #define OCFS2_JOURNAL_ACCESS_WRITE 1 #define OCFS2_JOURNAL_ACCESS_UNDO 2 + /* ocfs2_inode */ int ocfs2_journal_access_di(handle_t *handle, struct inode *inode, - struct buffer_head *bh, int type); + struct buffer_head *bh, int type); /* ocfs2_extent_block */ int ocfs2_journal_access_eb(handle_t *handle, struct inode *inode, struct buffer_head *bh, int type); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 19cfb1b9ce0..ec70cdbe77f 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -36,6 +36,7 @@ #include "ocfs2.h" #include "alloc.h" +#include "blockcheck.h" #include "dlmglue.h" #include "inode.h" #include "journal.h" @@ -382,8 +383,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) } memcpy(alloc_copy, alloc, bh->b_size); - status = ocfs2_journal_access(handle, local_alloc_inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, local_alloc_inode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; @@ -476,6 +477,7 @@ int ocfs2_begin_local_alloc_recovery(struct ocfs2_super *osb, alloc = (struct ocfs2_dinode *) alloc_bh->b_data; ocfs2_clear_local_alloc(alloc); + ocfs2_compute_meta_ecc(osb->sb, alloc_bh->b_data, &alloc->i_check); status = ocfs2_write_block(osb, alloc_bh, inode); if (status < 0) mlog_errno(status); @@ -762,9 +764,9 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, * delete bits from it! */ *num_bits = bits_wanted; - status = ocfs2_journal_access(handle, local_alloc_inode, - osb->local_alloc_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, local_alloc_inode, + osb->local_alloc_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -1240,9 +1242,9 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, } memcpy(alloc_copy, alloc, osb->local_alloc_bh->b_size); - status = ocfs2_journal_access(handle, local_alloc_inode, - osb->local_alloc_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, local_alloc_inode, + osb->local_alloc_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 6173807ba23..084aba86c3b 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -361,8 +361,8 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = ocfs2_journal_access(handle, dir, parent_fe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, dir, parent_fe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; @@ -493,8 +493,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, } ocfs2_set_new_buffer_uptodate(inode, *new_fe_bh); - status = ocfs2_journal_access(handle, inode, *new_fe_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_di(handle, inode, *new_fe_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto leave; @@ -664,8 +664,8 @@ static int ocfs2_link(struct dentry *old_dentry, goto out_unlock_inode; } - err = ocfs2_journal_access(handle, inode, fe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + err = ocfs2_journal_access_di(handle, inode, fe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (err < 0) { mlog_errno(err); goto out_commit; @@ -851,8 +851,8 @@ static int ocfs2_unlink(struct inode *dir, goto leave; } - 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 leave; @@ -1265,8 +1265,8 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } } - status = ocfs2_journal_access(handle, new_inode, newfe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, new_inode, newfe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -1312,8 +1312,8 @@ static int ocfs2_rename(struct inode *old_dir, old_inode->i_ctime = CURRENT_TIME; mark_inode_dirty(old_inode); - status = ocfs2_journal_access(handle, old_inode, old_inode_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, old_inode, old_inode_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status >= 0) { old_di = (struct ocfs2_dinode *) old_inode_bh->b_data; @@ -1389,9 +1389,9 @@ static int ocfs2_rename(struct inode *old_dir, (int)old_dir_nlink, old_dir->i_nlink); } else { struct ocfs2_dinode *fe; - status = ocfs2_journal_access(handle, old_dir, - old_dir_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, old_dir, + old_dir_bh, + OCFS2_JOURNAL_ACCESS_WRITE); fe = (struct ocfs2_dinode *) old_dir_bh->b_data; fe->i_links_count = cpu_to_le16(old_dir->i_nlink); status = ocfs2_journal_dirty(handle, old_dir_bh); @@ -1898,8 +1898,8 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, goto leave; } - status = ocfs2_journal_access(handle, orphan_dir_inode, orphan_dir_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, orphan_dir_inode, orphan_dir_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; @@ -1986,8 +1986,8 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, goto leave; } - status = ocfs2_journal_access(handle,orphan_dir_inode, orphan_dir_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle,orphan_dir_inode, orphan_dir_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 2bb389fe739..bad87d0a03c 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -339,6 +339,10 @@ struct ocfs2_super #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) +/* Useful typedef for passing around journal access functions */ +typedef int (*ocfs2_journal_access_func)(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int type); + static inline int ocfs2_should_order_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index a0b8b14cca8..444aa5a467f 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -244,7 +244,7 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type, set_buffer_uptodate(bh); unlock_buffer(bh); ocfs2_set_buffer_uptodate(gqinode, bh); - err = ocfs2_journal_access(handle, gqinode, bh, ja_type); + err = ocfs2_journal_access_dq(handle, gqinode, bh, ja_type); if (err < 0) { brelse(bh); goto out; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index d451b715aef..07deec5e972 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -106,8 +106,8 @@ static int ocfs2_modify_bh(struct inode *inode, struct buffer_head *bh, mlog_errno(status); return status; } - status = ocfs2_journal_access(handle, inode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_dq(handle, inode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); ocfs2_commit_trans(OCFS2_SB(sb), handle); @@ -506,7 +506,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, goto out_commit; } /* Release local quota file entry */ - status = ocfs2_journal_access(handle, lqinode, + status = ocfs2_journal_access_dq(handle, lqinode, qbh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); @@ -614,8 +614,8 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, mlog_errno(status); goto out_bh; } - status = ocfs2_journal_access(handle, lqinode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_dq(handle, lqinode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_trans; @@ -981,8 +981,8 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( goto out; } - status = ocfs2_journal_access(handle, lqinode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_dq(handle, lqinode, bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_trans; @@ -1074,7 +1074,7 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( mlog_errno(status); goto out; } - status = ocfs2_journal_access(handle, lqinode, chunk->qc_headerbh, + status = ocfs2_journal_access_dq(handle, lqinode, chunk->qc_headerbh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); @@ -1207,7 +1207,7 @@ static int ocfs2_local_release_dquot(struct dquot *dquot) goto out; } - status = ocfs2_journal_access(handle, sb_dqopt(sb)->files[type], + status = ocfs2_journal_access_dq(handle, sb_dqopt(sb)->files[type], od->dq_chunk->qc_headerbh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 867de3ebfca..424adaa5f90 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -106,8 +106,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, mlog_entry("(new_clusters=%d, first_new_cluster = %u)\n", new_clusters, first_new_cluster); - ret = ocfs2_journal_access(handle, bm_inode, group_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_gd(handle, bm_inode, group_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out; @@ -141,8 +141,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, } /* update the inode accordingly. */ - ret = ocfs2_journal_access(handle, bm_inode, bm_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, bm_inode, bm_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out_rollback; @@ -536,8 +536,8 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) cl = &fe->id2.i_chain; cr = &cl->cl_recs[input->chain]; - ret = ocfs2_journal_access(handle, main_bm_inode, group_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_gd(handle, main_bm_inode, group_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out_commit; @@ -552,8 +552,8 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) goto out_commit; } - ret = ocfs2_journal_access(handle, main_bm_inode, main_bm_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, main_bm_inode, main_bm_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out_commit; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 78755766c32..a69628603e1 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -261,7 +261,11 @@ int ocfs2_check_group_descriptor(struct super_block *sb, * local to this block. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &gd->bg_check); - if (!rc) + if (rc) { + mlog(ML_ERROR, + "Checksum failed for group descriptor %llu\n", + (unsigned long long)bh->b_blocknr); + } else rc = ocfs2_validate_gd_self(sb, bh, 1); if (!rc) rc = ocfs2_validate_gd_parent(sb, di, bh, 1); @@ -343,10 +347,10 @@ static int ocfs2_block_group_fill(handle_t *handle, goto bail; } - status = ocfs2_journal_access(handle, - alloc_inode, - bg_bh, - OCFS2_JOURNAL_ACCESS_CREATE); + status = ocfs2_journal_access_gd(handle, + alloc_inode, + bg_bh, + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; @@ -476,8 +480,8 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg = (struct ocfs2_group_desc *) bg_bh->b_data; - status = ocfs2_journal_access(handle, alloc_inode, - bh, OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, alloc_inode, + bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -986,10 +990,10 @@ static inline int ocfs2_block_group_set_bits(handle_t *handle, if (ocfs2_is_cluster_bitmap(alloc_inode)) journal_type = OCFS2_JOURNAL_ACCESS_UNDO; - status = ocfs2_journal_access(handle, - alloc_inode, - group_bh, - journal_type); + status = ocfs2_journal_access_gd(handle, + alloc_inode, + group_bh, + journal_type); if (status < 0) { mlog_errno(status); goto bail; @@ -1060,8 +1064,8 @@ static int ocfs2_relink_block_group(handle_t *handle, bg_ptr = le64_to_cpu(bg->bg_next_group); prev_bg_ptr = le64_to_cpu(prev_bg->bg_next_group); - status = ocfs2_journal_access(handle, alloc_inode, prev_bg_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_gd(handle, alloc_inode, prev_bg_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_rollback; @@ -1075,8 +1079,8 @@ static int ocfs2_relink_block_group(handle_t *handle, goto out_rollback; } - status = ocfs2_journal_access(handle, alloc_inode, bg_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_gd(handle, alloc_inode, bg_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_rollback; @@ -1090,8 +1094,8 @@ static int ocfs2_relink_block_group(handle_t *handle, goto out_rollback; } - status = ocfs2_journal_access(handle, alloc_inode, fe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, alloc_inode, fe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_rollback; @@ -1242,8 +1246,8 @@ static int ocfs2_alloc_dinode_update_counts(struct inode *inode, struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain; - ret = ocfs2_journal_access(handle, inode, di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out; @@ -1414,10 +1418,10 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, /* Ok, claim our bits now: set the info on dinode, chainlist * and then the group */ - status = ocfs2_journal_access(handle, - alloc_inode, - ac->ac_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, + alloc_inode, + ac->ac_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; @@ -1824,8 +1828,8 @@ static inline int ocfs2_block_group_clear_bits(handle_t *handle, if (ocfs2_is_cluster_bitmap(alloc_inode)) journal_type = OCFS2_JOURNAL_ACCESS_UNDO; - status = ocfs2_journal_access(handle, alloc_inode, group_bh, - journal_type); + status = ocfs2_journal_access_gd(handle, alloc_inode, group_bh, + journal_type); if (status < 0) { mlog_errno(status); goto bail; @@ -1900,8 +1904,8 @@ int ocfs2_free_suballoc_bits(handle_t *handle, goto bail; } - status = ocfs2_journal_access(handle, alloc_inode, alloc_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + status = ocfs2_journal_access_di(handle, alloc_inode, alloc_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; -- cgit v1.2.3-70-g09d2 From 87d35a74b15ec703910a63e0667692fb5e267be0 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 10 Dec 2008 17:36:25 -0800 Subject: ocfs2: Add directory block trailers. Future ocfs2 features metaecc and indexed directories need to store a little bit of data in each dirblock. For compatibility, we place this in a trailer at the end of the dirblock. The trailer plays itself as an empty dirent, so that if the features are turned off, it can be reused without requiring a tunefs scan. This code adds the trailer and validates it when the block is read in. [ Mark is the original author, but I reinserted this code before his dir index work. -- Joel ] Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dir.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++++---- fs/ocfs2/ocfs2.h | 3 + fs/ocfs2/ocfs2_fs.h | 29 ++++++++ 3 files changed, 215 insertions(+), 14 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 45e4e03d8f7..1efd0ab680c 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -83,6 +83,63 @@ static int ocfs2_do_extend_dir(struct super_block *sb, struct ocfs2_alloc_context *meta_ac, struct buffer_head **new_bh); +/* + * These are distinct checks because future versions of the file system will + * want to have a trailing dirent structure independent of indexing. + */ +static int ocfs2_dir_has_trailer(struct inode *dir) +{ + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return 0; + + return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb)); +} + +static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb) +{ + return ocfs2_meta_ecc(osb); +} + +static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb) +{ + return sb->s_blocksize - sizeof(struct ocfs2_dir_block_trailer); +} + +#define ocfs2_trailer_from_bh(_bh, _sb) ((struct ocfs2_dir_block_trailer *) ((_bh)->b_data + ocfs2_dir_trailer_blk_off((_sb)))) + +/* + * XXX: This is executed once on every dirent. We should consider optimizing + * it. + */ +static int ocfs2_skip_dir_trailer(struct inode *dir, + struct ocfs2_dir_entry *de, + unsigned long offset, + unsigned long blklen) +{ + unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer); + + if (!ocfs2_dir_has_trailer(dir)) + return 0; + + if (offset != toff) + return 0; + + return 1; +} + +static void ocfs2_init_dir_trailer(struct inode *inode, + struct buffer_head *bh) +{ + struct ocfs2_dir_block_trailer *trailer; + + trailer = ocfs2_trailer_from_bh(bh, inode->i_sb); + strcpy(trailer->db_signature, OCFS2_DIR_TRAILER_SIGNATURE); + trailer->db_compat_rec_len = + cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer)); + trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); + trailer->db_blkno = cpu_to_le64(bh->b_blocknr); +} + /* * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. @@ -232,16 +289,60 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, { int rc = 0; struct buffer_head *tmp = *bh; + struct ocfs2_dir_block_trailer *trailer; rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags, ocfs2_validate_dir_block); - if (rc) + if (rc) { mlog_errno(rc); + goto out; + } + + /* + * We check the trailer here rather than in + * ocfs2_validate_dir_block() because that function doesn't have + * the inode to test. + */ + if (!(flags & OCFS2_BH_READAHEAD) && + ocfs2_dir_has_trailer(inode)) { + trailer = ocfs2_trailer_from_bh(tmp, inode->i_sb); + if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) { + rc = -EINVAL; + ocfs2_error(inode->i_sb, + "Invalid dirblock #%llu: " + "signature = %.*s\n", + (unsigned long long)tmp->b_blocknr, 7, + trailer->db_signature); + goto out; + } + if (le64_to_cpu(trailer->db_blkno) != tmp->b_blocknr) { + rc = -EINVAL; + ocfs2_error(inode->i_sb, + "Directory block #%llu has an invalid " + "db_blkno of %llu", + (unsigned long long)tmp->b_blocknr, + (unsigned long long)le64_to_cpu(trailer->db_blkno)); + goto out; + } + if (le64_to_cpu(trailer->db_parent_dinode) != + OCFS2_I(inode)->ip_blkno) { + rc = -EINVAL; + ocfs2_error(inode->i_sb, + "Directory block #%llu on dinode " + "#%llu has an invalid parent_dinode " + "of %llu", + (unsigned long long)tmp->b_blocknr, + (unsigned long long)OCFS2_I(inode)->ip_blkno, + (unsigned long long)le64_to_cpu(trailer->db_blkno)); + goto out; + } + } /* If ocfs2_read_virt_blocks() got us a new bh, pass it up. */ - if (!rc && !*bh) + if (!*bh) *bh = tmp; +out: return rc ? -EIO : 0; } @@ -581,6 +682,16 @@ int __ocfs2_add_entry(handle_t *handle, goto bail; } + /* We're guaranteed that we should have space, so we + * can't possibly have hit the trailer...right? */ + mlog_bug_on_msg(ocfs2_skip_dir_trailer(dir, de, offset, size), + "Hit dir trailer trying to insert %.*s " + "(namelen %d) into directory %llu. " + "offset is %lu, trailer offset is %d\n", + namelen, name, namelen, + (unsigned long long)parent_fe_bh->b_blocknr, + offset, ocfs2_dir_trailer_blk_off(dir->i_sb)); + if (ocfs2_dirent_would_fit(de, rec_len)) { dir->i_mtime = dir->i_ctime = CURRENT_TIME; retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); @@ -622,6 +733,7 @@ int __ocfs2_add_entry(handle_t *handle, retval = 0; goto bail; } + offset += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len)); } @@ -1059,9 +1171,15 @@ int ocfs2_empty_dir(struct inode *inode) return !priv.seen_other; } -static void ocfs2_fill_initial_dirents(struct inode *inode, - struct inode *parent, - char *start, unsigned int size) +/* + * Fills "." and ".." dirents in a new directory block. Returns dirent for + * "..", which might be used during creation of a directory with a trailing + * header. It is otherwise safe to ignore the return code. + */ +static struct ocfs2_dir_entry *ocfs2_fill_initial_dirents(struct inode *inode, + struct inode *parent, + char *start, + unsigned int size) { struct ocfs2_dir_entry *de = (struct ocfs2_dir_entry *)start; @@ -1078,6 +1196,8 @@ static void ocfs2_fill_initial_dirents(struct inode *inode, de->name_len = 2; strcpy(de->name, ".."); ocfs2_set_de_type(de, S_IFDIR); + + return de; } /* @@ -1130,10 +1250,15 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, struct ocfs2_alloc_context *data_ac) { int status; + unsigned int size = osb->sb->s_blocksize; struct buffer_head *new_bh = NULL; + struct ocfs2_dir_entry *de; mlog_entry_void(); + if (ocfs2_supports_dir_trailer(osb)) + size = ocfs2_dir_trailer_blk_off(parent->i_sb); + status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh, data_ac, NULL, &new_bh); if (status < 0) { @@ -1151,8 +1276,9 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, } memset(new_bh->b_data, 0, osb->sb->s_blocksize); - ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, - osb->sb->s_blocksize); + de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size); + if (ocfs2_supports_dir_trailer(osb)) + ocfs2_init_dir_trailer(inode, new_bh); status = ocfs2_journal_dirty(handle, new_bh); if (status < 0) { @@ -1193,13 +1319,27 @@ int ocfs2_fill_new_dir(struct ocfs2_super *osb, data_ac); } +/* + * Expand rec_len of the rightmost dirent in a directory block so that it + * contains the end of our valid space for dirents. We do this during + * expansion from an inline directory to one with extents. The first dir block + * in that case is taken from the inline data portion of the inode block. + * + * We add the dir trailer if this filesystem wants it. + */ static void ocfs2_expand_last_dirent(char *start, unsigned int old_size, - unsigned int new_size) + struct super_block *sb) { struct ocfs2_dir_entry *de; struct ocfs2_dir_entry *prev_de; char *de_buf, *limit; - unsigned int bytes = new_size - old_size; + unsigned int new_size = sb->s_blocksize; + unsigned int bytes; + + if (ocfs2_supports_dir_trailer(OCFS2_SB(sb))) + new_size = ocfs2_dir_trailer_blk_off(sb); + + bytes = new_size - old_size; limit = start + old_size; de_buf = start; @@ -1316,8 +1456,9 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir)); memset(dirdata_bh->b_data + i_size_read(dir), 0, sb->s_blocksize - i_size_read(dir)); - ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), - sb->s_blocksize); + ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), sb); + if (ocfs2_supports_dir_trailer(osb)) + ocfs2_init_dir_trailer(dir, dirdata_bh); ret = ocfs2_journal_dirty(handle, dirdata_bh); if (ret) { @@ -1604,9 +1745,15 @@ do_extend: goto bail; } memset(new_bh->b_data, 0, sb->s_blocksize); + de = (struct ocfs2_dir_entry *) new_bh->b_data; de->inode = 0; - de->rec_len = cpu_to_le16(sb->s_blocksize); + if (ocfs2_dir_has_trailer(dir)) { + de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb)); + ocfs2_init_dir_trailer(dir, new_bh); + } else { + de->rec_len = cpu_to_le16(sb->s_blocksize); + } status = ocfs2_journal_dirty(handle, new_bh); if (status < 0) { mlog_errno(status); @@ -1648,11 +1795,21 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, unsigned int *blocks_wanted) { int ret; + struct super_block *sb = dir->i_sb; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_dir_entry *de, *last_de = NULL; char *de_buf, *limit; unsigned long offset = 0; - unsigned int rec_len, new_rec_len; + unsigned int rec_len, new_rec_len, free_space = dir->i_sb->s_blocksize; + + /* + * This calculates how many free bytes we'd have in block zero, should + * this function force expansion to an extent tree. + */ + if (ocfs2_supports_dir_trailer(OCFS2_SB(sb))) + free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir); + else + free_space = dir->i_sb->s_blocksize - i_size_read(dir); de_buf = di->id2.i_data.id_data; limit = de_buf + i_size_read(dir); @@ -1669,6 +1826,11 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, ret = -EEXIST; goto out; } + /* + * No need to check for a trailing dirent record here as + * they're not used for inline dirs. + */ + if (ocfs2_dirent_would_fit(de, rec_len)) { /* Ok, we found a spot. Return this bh and let * the caller actually fill it in. */ @@ -1689,7 +1851,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, * dirent can be found. */ *blocks_wanted = 1; - new_rec_len = le16_to_cpu(last_de->rec_len) + (dir->i_sb->s_blocksize - i_size_read(dir)); + new_rec_len = le16_to_cpu(last_de->rec_len) + free_space; if (new_rec_len < (rec_len + OCFS2_DIR_REC_LEN(last_de->name_len))) *blocks_wanted = 2; @@ -1707,6 +1869,7 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, struct ocfs2_dir_entry *de; struct super_block *sb = dir->i_sb; int status; + int blocksize = dir->i_sb->s_blocksize; status = ocfs2_read_dir_block(dir, 0, &bh, 0); if (status) { @@ -1748,6 +1911,11 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, status = -EEXIST; goto bail; } + + if (ocfs2_skip_dir_trailer(dir, de, offset % blocksize, + blocksize)) + goto next; + if (ocfs2_dirent_would_fit(de, rec_len)) { /* Ok, we found a spot. Return this bh and let * the caller actually fill it in. */ @@ -1756,6 +1924,7 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, status = 0; goto bail; } +next: offset += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len)); } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index bad87d0a03c..ad5c24a29ed 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -470,6 +470,9 @@ static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb) #define OCFS2_IS_VALID_XATTR_BLOCK(ptr) \ (!strcmp((ptr)->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE)) +#define OCFS2_IS_VALID_DIR_TRAILER(ptr) \ + (!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE)) + static inline unsigned long ino_from_blkno(struct super_block *sb, u64 blkno) { diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 290fa26fba6..af0013b9c17 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -65,6 +65,7 @@ #define OCFS2_EXTENT_BLOCK_SIGNATURE "EXBLK01" #define OCFS2_GROUP_DESC_SIGNATURE "GROUP01" #define OCFS2_XATTR_BLOCK_SIGNATURE "XATTR01" +#define OCFS2_DIR_TRAILER_SIGNATURE "DIRTRL1" /* Compatibility flags */ #define OCFS2_HAS_COMPAT_FEATURE(sb,mask) \ @@ -751,6 +752,34 @@ struct ocfs2_dir_entry { /* Actual on-disk length specified by rec_len */ } __attribute__ ((packed)); +/* + * Per-block record for the unindexed directory btree. This is carefully + * crafted so that the rec_len and name_len records of an ocfs2_dir_entry are + * mirrored. That way, the directory manipulation code needs a minimal amount + * of update. + * + * NOTE: Keep this structure aligned to a multiple of 4 bytes. + */ +struct ocfs2_dir_block_trailer { +/*00*/ __le64 db_compat_inode; /* Always zero. Was inode */ + + __le16 db_compat_rec_len; /* Backwards compatible with + * ocfs2_dir_entry. */ + __u8 db_compat_name_len; /* Always zero. Was name_len */ + __u8 db_reserved0; + __le16 db_reserved1; + __le16 db_free_rec_len; /* Size of largest empty hole + * in this block. (unused) */ +/*10*/ __u8 db_signature[8]; /* Signature for verification */ + __le64 db_reserved2; + __le64 db_free_next; /* Next block in list (unused) */ +/*20*/ __le64 db_blkno; /* Offset on disk, in blocks */ + __le64 db_parent_dinode; /* dinode which owns me, in + blocks */ +/*30*/ __le64 db_check; /* Error checking */ +/*40*/ +}; + /* * On disk allocator group structure for OCFS2 */ -- cgit v1.2.3-70-g09d2 From c175a518b4a1d514483abf61813ce5d855917164 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Wed, 10 Dec 2008 17:58:22 -0800 Subject: ocfs2: Checksum and ECC for directory blocks. Use the db_check field of ocfs2_dir_block_trailer to crc/ecc the dirblocks. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dir.c | 37 +++++++++++++++++++++++++++++++++++-- fs/ocfs2/dir.h | 2 ++ fs/ocfs2/journal.c | 31 +++++++++++++++++++++++++++++-- fs/ocfs2/ocfs2_fs.h | 2 +- 4 files changed, 67 insertions(+), 5 deletions(-) (limited to 'fs/ocfs2/dir.c') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 1efd0ab680c..f2c4098cf33 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -48,6 +48,7 @@ #include "ocfs2.h" #include "alloc.h" +#include "blockcheck.h" #include "dir.h" #include "dlmglue.h" #include "extent_map.h" @@ -107,6 +108,17 @@ static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb) #define ocfs2_trailer_from_bh(_bh, _sb) ((struct ocfs2_dir_block_trailer *) ((_bh)->b_data + ocfs2_dir_trailer_blk_off((_sb)))) +/* XXX ocfs2_block_dqtrailer() is similar but not quite - can we make + * them more consistent? */ +struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize, + void *data) +{ + char *p = data; + + p += blocksize - sizeof(struct ocfs2_dir_block_trailer); + return (struct ocfs2_dir_block_trailer *)p; +} + /* * XXX: This is executed once on every dirent. We should consider optimizing * it. @@ -268,14 +280,35 @@ out: static int ocfs2_validate_dir_block(struct super_block *sb, struct buffer_head *bh) { + int rc; + struct ocfs2_dir_block_trailer *trailer = + ocfs2_trailer_from_bh(bh, sb); + + /* - * Nothing yet. We don't validate dirents here, that's handled + * We don't validate dirents here, that's handled * in-place when the code walks them. */ mlog(0, "Validating dirblock %llu\n", (unsigned long long)bh->b_blocknr); - return 0; + BUG_ON(!buffer_uptodate(bh)); + + /* + * If the ecc fails, we return the error but otherwise + * leave the filesystem running. We know any error is + * local to this block. + * + * Note that we are safe to call this even if the directory + * doesn't have a trailer. Filesystems without metaecc will do + * nothing, and filesystems with it will have one. + */ + rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &trailer->db_check); + if (rc) + mlog(ML_ERROR, "Checksum failed for dinode %llu\n", + (unsigned long long)bh->b_blocknr); + + return rc; } /* diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h index ce48b9080d8..c511e2e18e9 100644 --- a/fs/ocfs2/dir.h +++ b/fs/ocfs2/dir.h @@ -83,4 +83,6 @@ int ocfs2_fill_new_dir(struct ocfs2_super *osb, struct buffer_head *fe_bh, struct ocfs2_alloc_context *data_ac); +struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize, + void *data); #endif /* OCFS2_DIR_H */ diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 3b54dba0f74..57d7d25a2b9 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -415,6 +415,26 @@ static void ocfs2_dq_commit_trigger(struct jbd2_buffer_trigger_type *triggers, ocfs2_block_check_compute(data, size, &dqt->dq_check); } +/* + * Directory blocks also have their own trigger because the + * struct ocfs2_block_check offset depends on the blocksize. + */ +static void ocfs2_db_commit_trigger(struct jbd2_buffer_trigger_type *triggers, + struct buffer_head *bh, + void *data, size_t size) +{ + struct ocfs2_dir_block_trailer *trailer = + ocfs2_dir_trailer_from_size(size, data); + + /* + * We aren't guaranteed to have the superblock here, so we + * must unconditionally compute the ecc data. + * __ocfs2_journal_access() will only set the triggers if + * metaecc is enabled. + */ + ocfs2_block_check_compute(data, size, &trailer->db_check); +} + static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh) { @@ -454,6 +474,13 @@ static struct ocfs2_triggers gd_triggers = { .ot_offset = offsetof(struct ocfs2_group_desc, bg_check), }; +static struct ocfs2_triggers db_triggers = { + .ot_triggers = { + .t_commit = ocfs2_db_commit_trigger, + .t_abort = ocfs2_abort_trigger, + }, +}; + static struct ocfs2_triggers xb_triggers = { .ot_triggers = { .t_commit = ocfs2_commit_trigger, @@ -555,8 +582,8 @@ int ocfs2_journal_access_gd(handle_t *handle, struct inode *inode, int ocfs2_journal_access_db(handle_t *handle, struct inode *inode, struct buffer_head *bh, int type) { - /* Right now, nothing for dirblocks */ - return __ocfs2_journal_access(handle, inode, bh, NULL, type); + return __ocfs2_journal_access(handle, inode, bh, &db_triggers, + type); } int ocfs2_journal_access_xb(handle_t *handle, struct inode *inode, diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index af0013b9c17..698ef3d2712 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -776,7 +776,7 @@ struct ocfs2_dir_block_trailer { /*20*/ __le64 db_blkno; /* Offset on disk, in blocks */ __le64 db_parent_dinode; /* dinode which owns me, in blocks */ -/*30*/ __le64 db_check; /* Error checking */ +/*30*/ struct ocfs2_block_check db_check; /* Error checking */ /*40*/ }; -- cgit v1.2.3-70-g09d2