From 1cd9f0976aa4606db8d6e3dc3edd0aca8019372a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 31 Aug 2011 11:54:51 -0400 Subject: ext2,ext3,ext4: don't inherit APPEND_FL or IMMUTABLE_FL for new inodes This doesn't make much sense, and it exposes a bug in the kernel where attempts to create a new file in an append-only directory using O_CREAT will fail (but still leave a zero-length file). This was discovered when xfstests #79 was generalized so it could run on all file systems. Signed-off-by: "Theodore Ts'o" Cc:stable@kernel.org --- fs/ext4/ext4.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b7d7bd0f066e..5c38120c389c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -358,8 +358,7 @@ struct flex_groups { /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ - EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\ - EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ + EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) -- cgit v1.2.3 From 4e96b2dbbf1d7e81f22047a50f862555a6cb87cb Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Sat, 3 Sep 2011 11:51:09 -0400 Subject: ext4: Add new ext4_discard_partial_page_buffers routines This patch adds two new routines: ext4_discard_partial_page_buffers and ext4_discard_partial_page_buffers_no_lock. The ext4_discard_partial_page_buffers routine is a wrapper function to ext4_discard_partial_page_buffers_no_lock. The wrapper function locks the page and passes it to ext4_discard_partial_page_buffers_no_lock. Calling functions that already have the page locked can call ext4_discard_partial_page_buffers_no_lock directly. The ext4_discard_partial_page_buffers_no_lock function zeros a specified range in a page, and unmaps the corresponding buffer heads. Only block aligned regions of the page will have their buffer heads unmapped. Unblock aligned regions will be mapped if needed so that they can be updated with the partial zero out. This function is meant to be used to update a page and its buffer heads to be zeroed and unmapped when the corresponding blocks have been released or will be released. This routine is used in the following scenarios: * A hole is punched and the non page aligned regions of the head and tail of the hole need to be discarded * The file is truncated and the partial page beyond EOF needs to be discarded * The end of a hole is in the same page as EOF. After the page is flushed, the partial page beyond EOF needs to be discarded. * A write operation begins or ends inside a hole and the partial page appearing before or after the write needs to be discarded * A write operation extends EOF and the partial page beyond EOF needs to be discarded This function takes a flag EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED which is used when a write operation begins or ends in a hole. When the EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED flag is used, only buffer heads that are already unmapped will have the corresponding regions of the page zeroed. Signed-off-by: Allison Henderson Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 11 +++ fs/ext4/inode.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 235 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5c38120c389c..ccfa81f33bb0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -528,6 +528,11 @@ struct ext4_new_group_data { #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 +/* + * Flags used by ext4_discard_partial_page_buffers + */ +#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001 + /* * ioctl commands */ @@ -1838,6 +1843,12 @@ extern int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from); extern int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length); +extern int ext4_discard_partial_page_buffers(handle_t *handle, + struct address_space *mapping, loff_t from, + loff_t length, int flags); +extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, + struct inode *inode, struct page *page, loff_t from, + loff_t length, int flags); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b84f127c085d..d1b1ef71e5b7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2966,6 +2966,230 @@ void ext4_set_aops(struct inode *inode) inode->i_mapping->a_ops = &ext4_journalled_aops; } + +/* + * ext4_discard_partial_page_buffers() + * Wrapper function for ext4_discard_partial_page_buffers_no_lock. + * This function finds and locks the page containing the offset + * "from" and passes it to ext4_discard_partial_page_buffers_no_lock. + * Calling functions that already have the page locked should call + * ext4_discard_partial_page_buffers_no_lock directly. + */ +int ext4_discard_partial_page_buffers(handle_t *handle, + struct address_space *mapping, loff_t from, + loff_t length, int flags) +{ + struct inode *inode = mapping->host; + struct page *page; + int err = 0; + + page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, + mapping_gfp_mask(mapping) & ~__GFP_FS); + if (!page) + return -EINVAL; + + err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page, + from, length, flags); + + unlock_page(page); + page_cache_release(page); + return err; +} + +/* + * ext4_discard_partial_page_buffers_no_lock() + * Zeros a page range of length 'length' starting from offset 'from'. + * Buffer heads that correspond to the block aligned regions of the + * zeroed range will be unmapped. Unblock aligned regions + * will have the corresponding buffer head mapped if needed so that + * that region of the page can be updated with the partial zero out. + * + * This function assumes that the page has already been locked. The + * The range to be discarded must be contained with in the given page. + * If the specified range exceeds the end of the page it will be shortened + * to the end of the page that corresponds to 'from'. This function is + * appropriate for updating a page and it buffer heads to be unmapped and + * zeroed for blocks that have been either released, or are going to be + * released. + * + * handle: The journal handle + * inode: The files inode + * page: A locked page that contains the offset "from" + * from: The starting byte offset (from the begining of the file) + * to begin discarding + * len: The length of bytes to discard + * flags: Optional flags that may be used: + * + * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED + * Only zero the regions of the page whose buffer heads + * have already been unmapped. This flag is appropriate + * for updateing the contents of a page whose blocks may + * have already been released, and we only want to zero + * out the regions that correspond to those released blocks. + * + * Returns zero on sucess or negative on failure. + */ +int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, + struct inode *inode, struct page *page, loff_t from, + loff_t length, int flags) +{ + ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; + unsigned int offset = from & (PAGE_CACHE_SIZE-1); + unsigned int blocksize, max, pos; + unsigned int end_of_block, range_to_discard; + ext4_lblk_t iblock; + struct buffer_head *bh; + int err = 0; + + blocksize = inode->i_sb->s_blocksize; + max = PAGE_CACHE_SIZE - offset; + + if (index != page->index) + return -EINVAL; + + /* + * correct length if it does not fall between + * 'from' and the end of the page + */ + if (length > max || length < 0) + length = max; + + iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + + if (!page_has_buffers(page)) { + /* + * If the range to be discarded covers a partial block + * we need to get the page buffers. This is because + * partial blocks cannot be released and the page needs + * to be updated with the contents of the block before + * we write the zeros on top of it. + */ + if (!(from & (blocksize - 1)) || + !((from + length) & (blocksize - 1))) { + create_empty_buffers(page, blocksize, 0); + } else { + /* + * If there are no partial blocks, + * there is nothing to update, + * so we can return now + */ + return 0; + } + } + + /* Find the buffer that contains "offset" */ + bh = page_buffers(page); + pos = blocksize; + while (offset >= pos) { + bh = bh->b_this_page; + iblock++; + pos += blocksize; + } + + pos = offset; + while (pos < offset + length) { + err = 0; + + /* The length of space left to zero and unmap */ + range_to_discard = offset + length - pos; + + /* The length of space until the end of the block */ + end_of_block = blocksize - (pos & (blocksize-1)); + + /* + * Do not unmap or zero past end of block + * for this buffer head + */ + if (range_to_discard > end_of_block) + range_to_discard = end_of_block; + + + /* + * Skip this buffer head if we are only zeroing unampped + * regions of the page + */ + if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED && + buffer_mapped(bh)) + goto next; + + /* If the range is block aligned, unmap */ + if (range_to_discard == blocksize) { + clear_buffer_dirty(bh); + bh->b_bdev = NULL; + clear_buffer_mapped(bh); + clear_buffer_req(bh); + clear_buffer_new(bh); + clear_buffer_delay(bh); + clear_buffer_unwritten(bh); + clear_buffer_uptodate(bh); + zero_user(page, pos, range_to_discard); + BUFFER_TRACE(bh, "Buffer discarded"); + goto next; + } + + /* + * If this block is not completely contained in the range + * to be discarded, then it is not going to be released. Because + * we need to keep this block, we need to make sure this part + * of the page is uptodate before we modify it by writeing + * partial zeros on it. + */ + if (!buffer_mapped(bh)) { + /* + * Buffer head must be mapped before we can read + * from the block + */ + BUFFER_TRACE(bh, "unmapped"); + ext4_get_block(inode, iblock, bh, 0); + /* unmapped? It's a hole - nothing to do */ + if (!buffer_mapped(bh)) { + BUFFER_TRACE(bh, "still unmapped"); + goto next; + } + } + + /* Ok, it's mapped. Make sure it's up-to-date */ + if (PageUptodate(page)) + set_buffer_uptodate(bh); + + if (!buffer_uptodate(bh)) { + err = -EIO; + ll_rw_block(READ, 1, &bh); + wait_on_buffer(bh); + /* Uhhuh. Read error. Complain and punt.*/ + if (!buffer_uptodate(bh)) + goto next; + } + + if (ext4_should_journal_data(inode)) { + BUFFER_TRACE(bh, "get write access"); + err = ext4_journal_get_write_access(handle, bh); + if (err) + goto next; + } + + zero_user(page, pos, range_to_discard); + + err = 0; + if (ext4_should_journal_data(inode)) { + err = ext4_handle_dirty_metadata(handle, inode, bh); + } else { + if (ext4_should_order_data(inode) && + EXT4_I(inode)->jinode) + err = ext4_jbd2_file_inode(handle, inode); + mark_buffer_dirty(bh); + } + + BUFFER_TRACE(bh, "Partial buffer zeroed"); +next: + bh = bh->b_this_page; + iblock++; + pos += range_to_discard; + } + + return err; +} + /* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. -- cgit v1.2.3 From 56889787cfa77dfd96f0b3a3e6a4f26c2e4a5134 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 3 Sep 2011 18:22:38 -0400 Subject: ext4: improve handling of conflicting mount options If the user explicitly specifies conflicting mount options for delalloc or dioread_nolock and data=journal, fail the mount, instead of printing a warning and continuing (since many user's won't look at dmesg and notice the warning). Also, print a single warning that data=journal implies that delayed allocation is not on by default (since it's not supported), and furthermore that O_DIRECT is not supported. Improve the text in Documentation/filesystems/ext4.txt so this is clear there as well. Similarly, if the dioread_nolock mount option is specified when the file system block size != PAGE_SIZE, fail the mount instead of printing a warning message and ignoring the mount option. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 8 +++--- fs/ext4/ext4.h | 3 +++ fs/ext4/super.c | 50 ++++++++++++++++++++++---------------- 3 files changed, 37 insertions(+), 24 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 232a575a0c48..168242b5c045 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -160,7 +160,9 @@ noload if the filesystem was not unmounted cleanly, lead to any number of problems. data=journal All data are committed into the journal prior to being - written into the main file system. + written into the main file system. Enabling + this mode will disable delayed allocation and + O_DIRECT support. data=ordered (*) All data are forced directly out to the main file system prior to its metadata being committed to the @@ -419,8 +421,8 @@ written to the journal first, and then to its final location. In the event of a crash, the journal can be replayed, bringing both data and metadata into a consistent state. This mode is the slowest except when data needs to be read from and written to disk at the same time where it -outperforms all others modes. Currently ext4 does not have delayed -allocation support if this data journalling mode is selected. +outperforms all others modes. Enabling this mode will disable delayed +allocation and O_DIRECT support. /proc entries ============= diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ccfa81f33bb0..48ae98819d35 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -922,6 +922,9 @@ struct ext4_inode_info { #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ #define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ +#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly + specified delalloc */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt #define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 44d0c8db2239..ee2f74a7084d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1801,6 +1801,7 @@ set_qf_format: break; case Opt_nodelalloc: clear_opt(sb, DELALLOC); + clear_opt2(sb, EXPLICIT_DELALLOC); break; case Opt_mblk_io_submit: set_opt(sb, MBLK_IO_SUBMIT); @@ -1817,6 +1818,7 @@ set_qf_format: break; case Opt_delalloc: set_opt(sb, DELALLOC); + set_opt2(sb, EXPLICIT_DELALLOC); break; case Opt_block_validity: set_opt(sb, BLOCK_VALIDITY); @@ -3224,6 +3226,33 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) &journal_ioprio, NULL, 0)) goto failed_mount; + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting " + "with data=journal disables delayed " + "allocation and O_DIRECT support!\n"); + if (test_opt2(sb, EXPLICIT_DELALLOC)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and delalloc"); + goto failed_mount; + } + if (test_opt(sb, DIOREAD_NOLOCK)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and delalloc"); + goto failed_mount; + } + if (test_opt(sb, DELALLOC)) + clear_opt(sb, DELALLOC); + } + + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + if (test_opt(sb, DIOREAD_NOLOCK)) { + if (blocksize < PAGE_SIZE) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "dioread_nolock if block size != PAGE_SIZE"); + goto failed_mount; + } + } + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0); @@ -3265,8 +3294,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY))) goto failed_mount; - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, @@ -3679,25 +3706,6 @@ no_journal: "available"); } - if (test_opt(sb, DELALLOC) && - (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { - ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - " - "requested data journaling mode"); - clear_opt(sb, DELALLOC); - } - if (test_opt(sb, DIOREAD_NOLOCK)) { - if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock " - "option - requested data journaling mode"); - clear_opt(sb, DIOREAD_NOLOCK); - } - if (sb->s_blocksize < PAGE_SIZE) { - ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock " - "option - block size is too small"); - clear_opt(sb, DIOREAD_NOLOCK); - } - } - err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " -- cgit v1.2.3 From 281b59959707dfae03ce038cdf231bf4904e170c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:34:51 -0400 Subject: ext4: read-only support for bigalloc file systems This adds supports for bigalloc file systems. It teaches the mount code just enough about bigalloc superblock fields that it will mount the file system without freaking out that the number of blocks per group is too big. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 17 ++++++++++++++--- fs/ext4/super.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 64 insertions(+), 11 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 48ae98819d35..f7257aa6bf81 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -239,8 +239,11 @@ struct ext4_io_submit { # define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) #endif #define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32)) +#define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \ + EXT4_SB(s)->s_cluster_bits) #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +# define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits) #else # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) #endif @@ -306,6 +309,7 @@ struct flex_groups { #define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) #ifdef __KERNEL__ # define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) +# define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) # define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) # define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) @@ -975,9 +979,9 @@ struct ext4_super_block { /*10*/ __le32 s_free_inodes_count; /* Free inodes count */ __le32 s_first_data_block; /* First Data Block */ __le32 s_log_block_size; /* Block size */ - __le32 s_obso_log_frag_size; /* Obsoleted fragment size */ + __le32 s_log_cluster_size; /* Allocation cluster size */ /*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ - __le32 s_obso_frags_per_group; /* Obsoleted fragments per group */ + __le32 s_clusters_per_group; /* # Clusters per group */ __le32 s_inodes_per_group; /* # Inodes per group */ __le32 s_mtime; /* Mount time */ /*30*/ __le32 s_wtime; /* Write time */ @@ -1073,7 +1077,10 @@ struct ext4_super_block { __u8 s_last_error_func[32]; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; - __le32 s_reserved[112]; /* Padding to the end of the block */ + __le32 s_usr_quota_inum; /* inode for tracking user quota */ + __le32 s_grp_quota_inum; /* inode for tracking group quota */ + __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ + __le32 s_reserved[109]; /* Padding to the end of the block */ }; #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START) @@ -1093,6 +1100,7 @@ struct ext4_sb_info { unsigned long s_desc_size; /* Size of a group descriptor in bytes */ unsigned long s_inodes_per_block;/* Number of inodes per block */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_clusters_per_group; /* Number of clusters in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ unsigned long s_gdb_count; /* Number of group descriptor blocks */ @@ -1101,6 +1109,8 @@ struct ext4_sb_info { ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ unsigned long s_overhead_last; /* Last calculated overhead */ unsigned long s_blocks_last; /* Last seen block count */ + unsigned int s_cluster_ratio; /* Number of blocks per cluster */ + unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ @@ -1367,6 +1377,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100 +#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5dcd0dacc591..823e7d9deee2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1953,7 +1953,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, res = MS_RDONLY; } if (read_only) - return res; + goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); @@ -1984,6 +1984,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); ext4_commit_super(sb, 1); +done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", @@ -3105,10 +3106,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) char *cp; const char *descr; int ret = -ENOMEM; - int blocksize; + int blocksize, clustersize; unsigned int db_count; unsigned int i; - int needs_recovery, has_huge_files; + int needs_recovery, has_huge_files, has_bigalloc; __u64 blocks_count; int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; @@ -3412,12 +3413,53 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_dirt = 1; } - if (sbi->s_blocks_per_group > blocksize * 8) { - ext4_msg(sb, KERN_ERR, - "#blocks per group too big: %lu", - sbi->s_blocks_per_group); - goto failed_mount; + /* Handle clustersize */ + clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); + has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC); + if (has_bigalloc) { + if (clustersize < blocksize) { + ext4_msg(sb, KERN_ERR, + "cluster size (%d) smaller than " + "block size (%d)", clustersize, blocksize); + goto failed_mount; + } + sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - + le32_to_cpu(es->s_log_block_size); + sbi->s_clusters_per_group = + le32_to_cpu(es->s_clusters_per_group); + if (sbi->s_clusters_per_group > blocksize * 8) { + ext4_msg(sb, KERN_ERR, + "#clusters per group too big: %lu", + sbi->s_clusters_per_group); + goto failed_mount; + } + if (sbi->s_blocks_per_group != + (sbi->s_clusters_per_group * (clustersize / blocksize))) { + ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and " + "clusters per group (%lu) inconsistent", + sbi->s_blocks_per_group, + sbi->s_clusters_per_group); + goto failed_mount; + } + } else { + if (clustersize != blocksize) { + ext4_warning(sb, "fragment/cluster size (%d) != " + "block size (%d)", clustersize, + blocksize); + clustersize = blocksize; + } + if (sbi->s_blocks_per_group > blocksize * 8) { + ext4_msg(sb, KERN_ERR, + "#blocks per group too big: %lu", + sbi->s_blocks_per_group); + goto failed_mount; + } + sbi->s_clusters_per_group = sbi->s_blocks_per_group; + sbi->s_cluster_bits = 0; } + sbi->s_cluster_ratio = clustersize / blocksize; + if (sbi->s_inodes_per_group > blocksize * 8) { ext4_msg(sb, KERN_ERR, "#inodes per group too big: %lu", -- cgit v1.2.3 From fd034a84e1ea5c8c8d159cd2089c32e792c269b0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:42:51 -0400 Subject: ext4: split out ext4_free_blocks_after_init() The function ext4_free_blocks_after_init() used to be a #define of ext4_init_block_bitmap(). This actually made it difficult to understand how the function worked, and made it hard make changes to support clusters. So as an initial cleanup, I've separated out the functionality of initializing block bitmap from calculating the number of free blocks in the new block group. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 105 +++++++++++++++++++++++++++---------------------------- fs/ext4/ext4.h | 13 +++---- fs/ext4/ialloc.c | 20 ++++------- 3 files changed, 66 insertions(+), 72 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 8573e2bfb78a..735d9fcc72e6 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -102,74 +102,73 @@ static unsigned int num_blocks_in_group(struct super_block *sb, return EXT4_BLOCKS_PER_GROUP(sb); } -/* Initializes an uninitialized block bitmap if given, and returns the - * number of blocks free in the group. */ -unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, - ext4_group_t block_group, struct ext4_group_desc *gdp) +/* Initializes an uninitialized block bitmap */ +void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { unsigned int bit, bit_max = num_base_meta_blocks(sb, block_group); - ext4_group_t ngroups = ext4_get_groups_count(sb); - unsigned group_blocks = num_blocks_in_group(sb, block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); - - if (bh) { - J_ASSERT_BH(bh, buffer_locked(bh)); - - /* If checksum is bad mark all blocks used to prevent allocation - * essentially implementing a per-group read-only flag. */ - if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", - block_group); - ext4_free_blks_set(sb, gdp, 0); - ext4_free_inodes_set(sb, gdp, 0); - ext4_itable_unused_set(sb, gdp, 0); - memset(bh->b_data, 0xff, sb->s_blocksize); - return 0; - } - memset(bh->b_data, 0, sb->s_blocksize); + ext4_fsblk_t start, tmp; + int flex_bg = 0; + + J_ASSERT_BH(bh, buffer_locked(bh)); + + /* If checksum is bad mark all blocks used to prevent allocation + * essentially implementing a per-group read-only flag. */ + if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + ext4_error(sb, "Checksum bad for group %u", block_group); + ext4_free_blks_set(sb, gdp, 0); + ext4_free_inodes_set(sb, gdp, 0); + ext4_itable_unused_set(sb, gdp, 0); + memset(bh->b_data, 0xff, sb->s_blocksize); + return; } + memset(bh->b_data, 0, sb->s_blocksize); - if (bh) { - ext4_fsblk_t start, tmp; - int flex_bg = 0; + for (bit = 0; bit < bit_max; bit++) + ext4_set_bit(bit, bh->b_data); - for (bit = 0; bit < bit_max; bit++) - ext4_set_bit(bit, bh->b_data); + start = ext4_group_first_block_no(sb, block_group); - start = ext4_group_first_block_no(sb, block_group); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + flex_bg = 1; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_FLEX_BG)) - flex_bg = 1; + /* Set bits for block and inode bitmaps, and inode table */ + tmp = ext4_block_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); - /* Set bits for block and inode bitmaps, and inode table */ - tmp = ext4_block_bitmap(sb, gdp); - if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) - ext4_set_bit(tmp - start, bh->b_data); + tmp = ext4_inode_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); - tmp = ext4_inode_bitmap(sb, gdp); + tmp = ext4_inode_table(sb, gdp); + for (; tmp < ext4_inode_table(sb, gdp) + + sbi->s_itb_per_group; tmp++) { if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(tmp - start, bh->b_data); - - tmp = ext4_inode_table(sb, gdp); - for (; tmp < ext4_inode_table(sb, gdp) + - sbi->s_itb_per_group; tmp++) { - if (!flex_bg || - ext4_block_in_group(sb, tmp, block_group)) - ext4_set_bit(tmp - start, bh->b_data); - } - /* - * Also if the number of blocks within the group is - * less than the blocksize * 8 ( which is the size - * of bitmap ), set rest of the block bitmap to 1 - */ - ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8, - bh->b_data); } - return group_blocks - bit_max - - ext4_group_used_meta_blocks(sb, block_group, gdp); + /* + * Also if the number of blocks within the group is less than + * the blocksize * 8 ( which is the size of bitmap ), set rest + * of the block bitmap to 1 + */ + ext4_mark_bitmap_end(num_blocks_in_group(sb, block_group), + sb->s_blocksize * 8, bh->b_data); } +/* Return the number of free blocks in a block group. It is used when + * the block bitmap is uninitialized, so we can't just count the bits + * in the bitmap. */ +unsigned ext4_free_blocks_after_init(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp) +{ + return num_blocks_in_group(sb, block_group) - + num_base_meta_blocks(sb, block_group) - + ext4_group_used_meta_blocks(sb, block_group, gdp); +} /* * The free blocks are managed by bitmaps. A file system contains several diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f7257aa6bf81..b0b7b67e439d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1763,12 +1763,13 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group); -extern unsigned ext4_init_block_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -#define ext4_free_blocks_after_init(sb, group, desc) \ - ext4_init_block_bitmap(sb, NULL, group, desc) +extern void ext4_init_block_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t group, + struct ext4_group_desc *desc); +extern unsigned ext4_free_blocks_after_init(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); /* dir.c */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 9c63f273b550..b7a8130d0af4 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -816,7 +816,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, int ret2, err = 0; struct inode *ret; ext4_group_t i; - int free = 0; static int once = 1; ext4_group_t flex_group; @@ -950,26 +949,21 @@ got: goto fail; } - free = 0; - ext4_lock_group(sb, group); + BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); + err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh); + brelse(block_bitmap_bh); + /* recheck and clear flag under lock if we still need to */ + ext4_lock_group(sb, group); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - free = ext4_free_blocks_after_init(sb, group, gdp); gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_blks_set(sb, gdp, free); + ext4_free_blks_set(sb, gdp, + ext4_free_blocks_after_init(sb, group, gdp)); gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); } ext4_unlock_group(sb, group); - /* Don't need to dirty bitmap block if we didn't change it */ - if (free) { - BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); - err = ext4_handle_dirty_metadata(handle, - NULL, block_bitmap_bh); - } - - brelse(block_bitmap_bh); if (err) goto fail; } -- cgit v1.2.3 From d5b8f31007a93777cfb0603b665858fb7aebebfc Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:44:51 -0400 Subject: ext4: bigalloc changes to block bitmap initialization functions Add bigalloc support to ext4_init_block_bitmap() and ext4_free_blocks_after_init(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 131 ++++++++++++++++++++++++++++++++++++++----------------- fs/ext4/ext4.h | 13 ++++++ 2 files changed, 103 insertions(+), 41 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 735d9fcc72e6..1c6d777b35a2 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -23,9 +23,6 @@ #include -static unsigned int num_base_meta_blocks(struct super_block *sb, - ext4_group_t block_group); - /* * balloc.c contains the blocks allocation and deallocation routines */ @@ -58,37 +55,87 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, return 0; } -static int ext4_group_used_meta_blocks(struct super_block *sb, - ext4_group_t block_group, - struct ext4_group_desc *gdp) +/* Return the number of clusters used for file system metadata; this + * represents the overhead needed by the file system. + */ +unsigned ext4_num_overhead_clusters(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { - ext4_fsblk_t tmp; + unsigned num_clusters; + int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c; + ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group); + ext4_fsblk_t itbl_blk; struct ext4_sb_info *sbi = EXT4_SB(sb); - /* block bitmap, inode bitmap, and inode table blocks */ - int used_blocks = sbi->s_itb_per_group + 2; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { - if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), - block_group)) - used_blocks--; - - if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), - block_group)) - used_blocks--; - - tmp = ext4_inode_table(sb, gdp); - for (; tmp < ext4_inode_table(sb, gdp) + - sbi->s_itb_per_group; tmp++) { - if (!ext4_block_in_group(sb, tmp, block_group)) - used_blocks -= 1; + /* This is the number of clusters used by the superblock, + * block group descriptors, and reserved block group + * descriptor blocks */ + num_clusters = ext4_num_base_meta_clusters(sb, block_group); + + /* + * For the allocation bitmaps and inode table, we first need + * to check to see if the block is in the block group. If it + * is, then check to see if the cluster is already accounted + * for in the clusters used for the base metadata cluster, or + * if we can increment the base metadata cluster to include + * that block. Otherwise, we will have to track the cluster + * used for the allocation bitmap or inode table explicitly. + * Normally all of these blocks are contiguous, so the special + * case handling shouldn't be necessary except for *very* + * unusual file system layouts. + */ + if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) { + block_cluster = EXT4_B2C(sbi, (start - + ext4_block_bitmap(sb, gdp))); + if (block_cluster < num_clusters) + block_cluster = -1; + else if (block_cluster == num_clusters) { + num_clusters++; + block_cluster = -1; + } + } + + if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) { + inode_cluster = EXT4_B2C(sbi, + start - ext4_inode_bitmap(sb, gdp)); + if (inode_cluster < num_clusters) + inode_cluster = -1; + else if (inode_cluster == num_clusters) { + num_clusters++; + inode_cluster = -1; + } + } + + itbl_blk = ext4_inode_table(sb, gdp); + for (i = 0; i < sbi->s_itb_per_group; i++) { + if (ext4_block_in_group(sb, itbl_blk + i, block_group)) { + c = EXT4_B2C(sbi, start - itbl_blk + i); + if ((c < num_clusters) || (c == inode_cluster) || + (c == block_cluster) || (c == itbl_cluster)) + continue; + if (c == num_clusters) { + num_clusters++; + continue; + } + num_clusters++; + itbl_cluster = c; } } - return used_blocks; + + if (block_cluster != -1) + num_clusters++; + if (inode_cluster != -1) + num_clusters++; + + return num_clusters; } -static unsigned int num_blocks_in_group(struct super_block *sb, - ext4_group_t block_group) +static unsigned int num_clusters_in_group(struct super_block *sb, + ext4_group_t block_group) { + unsigned int blocks; + if (block_group == ext4_get_groups_count(sb) - 1) { /* * Even though mke2fs always initializes the first and @@ -96,10 +143,11 @@ static unsigned int num_blocks_in_group(struct super_block *sb, * we need to make sure we calculate the right free * blocks. */ - return ext4_blocks_count(EXT4_SB(sb)->s_es) - + blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) - ext4_group_first_block_no(sb, block_group); } else - return EXT4_BLOCKS_PER_GROUP(sb); + blocks = EXT4_BLOCKS_PER_GROUP(sb); + return EXT4_NUM_B2C(EXT4_SB(sb), blocks); } /* Initializes an uninitialized block bitmap */ @@ -107,7 +155,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) { - unsigned int bit, bit_max = num_base_meta_blocks(sb, block_group); + unsigned int bit, bit_max; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; int flex_bg = 0; @@ -126,6 +174,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, } memset(bh->b_data, 0, sb->s_blocksize); + bit_max = ext4_num_base_meta_clusters(sb, block_group); for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); @@ -137,24 +186,25 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, /* Set bits for block and inode bitmaps, and inode table */ tmp = ext4_block_bitmap(sb, gdp); if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) - ext4_set_bit(tmp - start, bh->b_data); + ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_bitmap(sb, gdp); if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) - ext4_set_bit(tmp - start, bh->b_data); + ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_table(sb, gdp); for (; tmp < ext4_inode_table(sb, gdp) + sbi->s_itb_per_group; tmp++) { if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) - ext4_set_bit(tmp - start, bh->b_data); + ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); } + /* * Also if the number of blocks within the group is less than * the blocksize * 8 ( which is the size of bitmap ), set rest * of the block bitmap to 1 */ - ext4_mark_bitmap_end(num_blocks_in_group(sb, block_group), + ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group), sb->s_blocksize * 8, bh->b_data); } @@ -165,9 +215,8 @@ unsigned ext4_free_blocks_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { - return num_blocks_in_group(sb, block_group) - - num_base_meta_blocks(sb, block_group) - - ext4_group_used_meta_blocks(sb, block_group, gdp); + return num_clusters_in_group(sb, block_group) - + ext4_num_overhead_clusters(sb, block_group, gdp); } /* @@ -611,14 +660,14 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) } /* - * This function returns the number of file system metadata blocks at + * This function returns the number of file system metadata clusters at * the beginning of a block group, including the reserved gdt blocks. */ -static unsigned int num_base_meta_blocks(struct super_block *sb, - ext4_group_t block_group) +unsigned ext4_num_base_meta_clusters(struct super_block *sb, + ext4_group_t block_group) { struct ext4_sb_info *sbi = EXT4_SB(sb); - int num; + unsigned num; /* Check for superblock and gdt backups in this group */ num = ext4_bg_has_super(sb, block_group); @@ -633,7 +682,7 @@ static unsigned int num_base_meta_blocks(struct super_block *sb, } else { /* For META_BG_BLOCK_GROUPS */ num += ext4_bg_num_gdb(sb, block_group); } - return num; + return EXT4_NUM_B2C(sbi, num); } /** * ext4_inode_to_goal_block - return a hint for block allocation diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b0b7b67e439d..803cfa42e1e8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -261,6 +261,14 @@ struct ext4_io_submit { #endif #define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) +/* Translate a block number to a cluster number */ +#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits) +/* Translate a cluster number to a block number */ +#define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits) +/* Translate # of blks to # of clusters */ +#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \ + (sbi)->s_cluster_bits) + /* * Structure of a blocks group descriptor */ @@ -1770,6 +1778,11 @@ extern void ext4_init_block_bitmap(struct super_block *sb, extern unsigned ext4_free_blocks_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp); +extern unsigned ext4_num_base_meta_clusters(struct super_block *sb, + ext4_group_t block_group); +extern unsigned ext4_num_overhead_clusters(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); /* dir.c */ -- cgit v1.2.3 From 84130193e0e6568dfdfb823f0e1e19aec80aff6e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:50:51 -0400 Subject: ext4: teach ext4_free_blocks() about bigalloc and clusters The ext4_free_blocks() function now has two new flags that indicate whether a partial cluster at the beginning or the end of the block extents should be freed or not. That will be up the caller (i.e., truncate), who can figure out whether partial clusters at the beginning or the end of a block range can be freed. We also have to update the ext4_mb_free_metadata() and release_blocks_on_commit() machinery to be cluster-based, since it is used by ext4_free_blocks(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ fs/ext4/mballoc.c | 86 +++++++++++++++++++++++++++++++++++++++---------------- fs/ext4/mballoc.h | 2 +- 3 files changed, 65 insertions(+), 25 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 803cfa42e1e8..030bfc1cb59d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -539,6 +539,8 @@ struct ext4_new_group_data { #define EXT4_FREE_BLOCKS_FORGET 0x0002 #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 +#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 +#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 /* * Flags used by ext4_discard_partial_page_buffers diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8765f2512f13..57ce6960e940 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2602,11 +2602,13 @@ int ext4_mb_release(struct super_block *sb) } static inline int ext4_issue_discard(struct super_block *sb, - ext4_group_t block_group, ext4_grpblk_t block, int count) + ext4_group_t block_group, ext4_grpblk_t cluster, int count) { ext4_fsblk_t discard_block; - discard_block = block + ext4_group_first_block_no(sb, block_group); + discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + + ext4_group_first_block_no(sb, block_group)); + count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); @@ -2633,7 +2635,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) if (test_opt(sb, DISCARD)) ext4_issue_discard(sb, entry->group, - entry->start_blk, entry->count); + entry->start_cluster, entry->count); err = ext4_mb_load_buddy(sb, entry->group, &e4b); /* we expect to find existing buddy because it's pinned */ @@ -2646,7 +2648,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) ext4_lock_group(sb, entry->group); /* Take it out of per group rb tree */ rb_erase(&entry->node, &(db->bb_free_root)); - mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count); + mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count); /* * Clear the trimmed flag for the group so that the next @@ -3300,7 +3302,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, node); - ext4_set_bits(bitmap, entry->start_blk, entry->count); + ext4_set_bits(bitmap, entry->start_cluster, entry->count); n = rb_next(n); } return; @@ -4401,7 +4403,7 @@ static int can_merge(struct ext4_free_data *entry1, { if ((entry1->t_tid == entry2->t_tid) && (entry1->group == entry2->group) && - ((entry1->start_blk + entry1->count) == entry2->start_blk)) + ((entry1->start_cluster + entry1->count) == entry2->start_cluster)) return 1; return 0; } @@ -4411,7 +4413,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; - ext4_grpblk_t block; + ext4_grpblk_t cluster; struct ext4_free_data *entry; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; @@ -4424,7 +4426,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, BUG_ON(e4b->bd_buddy_page == NULL); new_node = &new_entry->node; - block = new_entry->start_blk; + cluster = new_entry->start_cluster; if (!*n) { /* first free block exent. We need to @@ -4438,13 +4440,14 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, node); - if (block < entry->start_blk) + if (cluster < entry->start_cluster) n = &(*n)->rb_left; - else if (block >= (entry->start_blk + entry->count)) + else if (cluster >= (entry->start_cluster + entry->count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, - ext4_group_first_block_no(sb, group) + block, + ext4_group_first_block_no(sb, group) + + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); return 0; } @@ -4458,7 +4461,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, if (node) { entry = rb_entry(node, struct ext4_free_data, node); if (can_merge(entry, new_entry)) { - new_entry->start_blk = entry->start_blk; + new_entry->start_cluster = entry->start_cluster; new_entry->count += entry->count; rb_erase(node, &(db->bb_free_root)); spin_lock(&sbi->s_md_lock); @@ -4509,6 +4512,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; + unsigned int count_clusters; int err = 0; int ret; @@ -4557,6 +4561,38 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, if (!ext4_should_writeback_data(inode)) flags |= EXT4_FREE_BLOCKS_METADATA; + /* + * If the extent to be freed does not begin on a cluster + * boundary, we need to deal with partial clusters at the + * beginning and end of the extent. Normally we will free + * blocks at the beginning or the end unless we are explicitly + * requested to avoid doing so. + */ + overflow = block & (sbi->s_cluster_ratio - 1); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { + overflow = sbi->s_cluster_ratio - overflow; + block += overflow; + if (count > overflow) + count -= overflow; + else + return; + } else { + block -= overflow; + count += overflow; + } + } + overflow = count & (sbi->s_cluster_ratio - 1); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { + if (count > overflow) + count -= overflow; + else + return; + } else + count += sbi->s_cluster_ratio - overflow; + } + do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -4565,10 +4601,12 @@ do_more: * Check to see if we are freeing blocks across a group * boundary. */ - if (bit + count > EXT4_CLUSTERS_PER_GROUP(sb)) { - overflow = bit + count - EXT4_CLUSTERS_PER_GROUP(sb); + if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { + overflow = EXT4_C2B(sbi, bit) + count - + EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; } + count_clusters = EXT4_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (!bitmap_bh) { err = -EIO; @@ -4583,9 +4621,9 @@ do_more: if (in_range(ext4_block_bitmap(sb, gdp), block, count) || in_range(ext4_inode_bitmap(sb, gdp), block, count) || in_range(block, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group) || + EXT4_SB(sb)->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group)) { + EXT4_SB(sb)->s_itb_per_group)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); @@ -4610,11 +4648,11 @@ do_more: #ifdef AGGRESSIVE_CHECK { int i; - for (i = 0; i < count; i++) + for (i = 0; i < count_clusters; i++) BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); } #endif - trace_ext4_mballoc_free(sb, inode, block_group, bit, count); + trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) @@ -4631,13 +4669,13 @@ do_more: err = -ENOMEM; goto error_return; } - new_entry->start_blk = bit; + new_entry->start_cluster = bit; new_entry->group = block_group; - new_entry->count = count; + new_entry->count = count_clusters; new_entry->t_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count); + mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { /* need to update group_info->bb_free and bitmap @@ -4645,11 +4683,11 @@ do_more: * them with group lock_held */ ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count); - mb_free_blocks(inode, &e4b, bit, count); + mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); + mb_free_blocks(inode, &e4b, bit, count_clusters); } - ret = ext4_free_blks_count(sb, gdp) + count; + ret = ext4_free_blks_count(sb, gdp) + count_clusters; ext4_free_blks_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 1641f4b57439..dc99930d4cb5 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -106,7 +106,7 @@ struct ext4_free_data { ext4_group_t group; /* free block extent */ - ext4_grpblk_t start_blk; + ext4_grpblk_t start_cluster; ext4_grpblk_t count; /* transaction which freed this extent */ -- cgit v1.2.3 From 5704265188ffe4290ed73b3cb685206c3ed8209d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:56:51 -0400 Subject: ext4: convert s_{dirty,free}blocks_counter to s_{dirty,free}clusters_counter Convert the percpu counters s_dirtyblocks_counter and s_freeblocks_counter in struct ext4_super_info to be s_dirtyclusters_counter and s_freeclusters_counter. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 10 +++++----- fs/ext4/ext4.h | 5 +++-- fs/ext4/ialloc.c | 3 ++- fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/mballoc.c | 12 +++++++----- fs/ext4/resize.c | 4 ++-- fs/ext4/super.c | 29 +++++++++++++++-------------- 7 files changed, 44 insertions(+), 37 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 89abf1f7b253..9080a857cda9 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -414,16 +414,16 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags) { s64 free_blocks, dirty_blocks, root_blocks; - struct percpu_counter *fbc = &sbi->s_freeblocks_counter; - struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter; + struct percpu_counter *fcc = &sbi->s_freeclusters_counter; + struct percpu_counter *dbc = &sbi->s_dirtyclusters_counter; - free_blocks = percpu_counter_read_positive(fbc); + free_blocks = percpu_counter_read_positive(fcc); dirty_blocks = percpu_counter_read_positive(dbc); root_blocks = ext4_r_blocks_count(sbi->s_es); if (free_blocks - (nblocks + root_blocks + dirty_blocks) < EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = percpu_counter_sum_positive(fbc); + free_blocks = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); dirty_blocks = percpu_counter_sum_positive(dbc); } /* Check whether we have space after @@ -449,7 +449,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags) { if (ext4_has_free_blocks(sbi, nblocks, flags)) { - percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks); + percpu_counter_add(&sbi->s_dirtyclusters_counter, nblocks); return 0; } else return -ENOSPC; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 030bfc1cb59d..c7588366471c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -855,6 +855,7 @@ struct ext4_inode_info { ext4_group_t i_last_alloc_group; /* allocation reservation info for delalloc */ + /* In case of bigalloc, these refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; unsigned int i_reserved_meta_blocks; unsigned int i_allocated_meta_blocks; @@ -1144,10 +1145,10 @@ struct ext4_sb_info { u32 s_hash_seed[4]; int s_def_hash_version; int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ - struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeclusters_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; - struct percpu_counter s_dirtyblocks_counter; + struct percpu_counter s_dirtyclusters_counter; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b7a8130d0af4..58115bad163f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -490,7 +490,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; - freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + freeb = EXT4_C2B(sbi, + percpu_counter_read_positive(&sbi->s_freeclusters_counter)); avefreeb = freeb; do_div(avefreeb, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 904a9a623dab..40f51aae42fe 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -281,7 +281,7 @@ void ext4_da_update_reserve_space(struct inode *inode, /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, used + ei->i_allocated_meta_blocks); ei->i_allocated_meta_blocks = 0; @@ -291,7 +291,7 @@ void ext4_da_update_reserve_space(struct inode *inode, * only when we have written all of the delayed * allocation blocks. */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; @@ -1119,14 +1119,14 @@ static void ext4_da_release_space(struct inode *inode, int to_free) * only when we have written all of the delayed * allocation blocks. */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; } /* update fs dirty data blocks counter */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free); + percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); @@ -1349,9 +1349,10 @@ static void ext4_print_free_blocks(struct inode *inode) ext4_count_free_blocks(inode->i_sb)); printk(KERN_CRIT "Free/Dirty block details\n"); printk(KERN_CRIT "free_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_freeblocks_counter)); + (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + percpu_counter_sum(&sbi->s_freeclusters_counter))); printk(KERN_CRIT "dirty_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + (long long) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); printk(KERN_CRIT "Block reservation details\n"); printk(KERN_CRIT "i_reserved_data_blocks=%u\n", EXT4_I(inode)->i_reserved_data_blocks); @@ -2226,8 +2227,9 @@ static int ext4_nonda_switch(struct super_block *sb) * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ - free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); - dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter); + free_blocks = EXT4_C2B(sbi, + percpu_counter_read_positive(&sbi->s_freeclusters_counter)); + dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); if (2 * free_blocks < 3 * dirty_blocks || free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) { /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 57ce6960e940..4a38b65bd564 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2834,13 +2834,14 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); - percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); + percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_clstrs); + percpu_counter_sub(&sbi->s_dirtyclusters_counter, + reserv_clstrs); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, @@ -4384,7 +4385,7 @@ out: if (!ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } @@ -4691,7 +4692,7 @@ do_more: ext4_free_blks_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); ext4_unlock_group(sb, block_group); - percpu_counter_add(&sbi->s_freeblocks_counter, count); + percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); @@ -4833,7 +4834,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_free_blks_set(sb, desc, blk_free_count); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); ext4_unlock_group(sb, block_group); - percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed); + percpu_counter_add(&sbi->s_freeclusters_counter, + EXT4_B2C(sbi, blocks_freed)); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 707d3f16f7ce..a324a537f2dc 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -937,8 +937,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) input->reserved_blocks); /* Update the free space counts */ - percpu_counter_add(&sbi->s_freeblocks_counter, - input->free_blocks_count); + percpu_counter_add(&sbi->s_freeclusters_counter, + EXT4_B2C(sbi, input->free_blocks_count)); percpu_counter_add(&sbi->s_freeinodes_counter, EXT4_INODES_PER_GROUP(sb)); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 25a4bfe3f39f..f81e7e791655 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -837,10 +837,10 @@ static void ext4_put_super(struct super_block *sb) brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); ext4_kvfree(sbi->s_flex_groups); - percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); + percpu_counter_destroy(&sbi->s_dirtyclusters_counter); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) @@ -2473,7 +2473,7 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, char *buf) { return snprintf(buf, PAGE_SIZE, "%llu\n", - (s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + (s64) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); } static ssize_t session_write_kbytes_show(struct ext4_attr *a, @@ -3575,7 +3575,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.function = print_daily_error_info; sbi->s_err_report.data = (unsigned long) sb; - err = percpu_counter_init(&sbi->s_freeblocks_counter, + err = percpu_counter_init(&sbi->s_freeclusters_counter, ext4_count_free_blocks(sb)); if (!err) { err = percpu_counter_init(&sbi->s_freeinodes_counter, @@ -3586,7 +3586,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_count_dirs(sb)); } if (!err) { - err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); + err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0); } if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); @@ -3701,13 +3701,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * The journal may have updated the bg summary counts, so we * need to update the global counters. */ - percpu_counter_set(&sbi->s_freeblocks_counter, + percpu_counter_set(&sbi->s_freeclusters_counter, ext4_count_free_blocks(sb)); percpu_counter_set(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); percpu_counter_set(&sbi->s_dirs_counter, ext4_count_dirs(sb)); - percpu_counter_set(&sbi->s_dirtyblocks_counter, 0); + percpu_counter_set(&sbi->s_dirtyclusters_counter, 0); no_journal: /* @@ -3847,10 +3847,10 @@ failed_mount3: del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); - percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); + percpu_counter_destroy(&sbi->s_dirtyclusters_counter); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: @@ -4173,8 +4173,9 @@ static int ext4_commit_super(struct super_block *sb, int sync) else es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); - ext4_free_blocks_count_set(es, percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeblocks_counter)); + ext4_free_blocks_count_set(es, + EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( + &EXT4_SB(sb)->s_freeclusters_counter))); es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); @@ -4629,10 +4630,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; - bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) - - percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter); + bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - + percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ - buf->f_bfree = max_t(s64, bfree, 0); + buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); if (buf->f_bfree < ext4_r_blocks_count(es)) buf->f_bavail = 0; -- cgit v1.2.3 From 24aaa8ef4e2b5764ada1fc69787e2fbd4f6276e5 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:58:51 -0400 Subject: ext4: convert the free_blocks field in s_flex_groups to be free_clusters Convert the free_blocks to be free_clusters to make the final revised bigalloc changes easier to read/understand. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 +- fs/ext4/ialloc.c | 40 +++++++++++++++++++++------------------- fs/ext4/mballoc.c | 9 +++++---- fs/ext4/resize.c | 4 ++-- fs/ext4/super.c | 2 +- 5 files changed, 30 insertions(+), 27 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c7588366471c..d2584224c89a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -300,7 +300,7 @@ struct ext4_group_desc struct flex_groups { atomic_t free_inodes; - atomic_t free_blocks; + atomic_t free_clusters; atomic_t used_dirs; }; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 58115bad163f..0be5862313f0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -346,7 +346,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, int flex_size = ext4_flex_bg_size(sbi); ext4_group_t best_flex = parent_fbg_group; int blocks_per_flex = sbi->s_blocks_per_group * flex_size; - int flexbg_free_blocks; + int flexbg_free_clusters; int flex_freeb_ratio; ext4_group_t n_fbg_groups; ext4_group_t i; @@ -355,8 +355,9 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, sbi->s_log_groups_per_flex; find_close_to_parent: - flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks); - flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; + flexbg_free_clusters = atomic_read(&flex_group[best_flex].free_clusters); + flex_freeb_ratio = EXT4_C2B(sbi, flexbg_free_clusters) * 100 / + blocks_per_flex; if (atomic_read(&flex_group[best_flex].free_inodes) && flex_freeb_ratio > free_block_ratio) goto found_flexbg; @@ -370,8 +371,9 @@ find_close_to_parent: if (i == parent_fbg_group || i == parent_fbg_group - 1) continue; - flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks); - flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; + flexbg_free_clusters = atomic_read(&flex_group[i].free_clusters); + flex_freeb_ratio = EXT4_C2B(sbi, flexbg_free_clusters) * 100 / + blocks_per_flex; if (flex_freeb_ratio > free_block_ratio && (atomic_read(&flex_group[i].free_inodes))) { @@ -380,14 +382,14 @@ find_close_to_parent: } if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) || - ((atomic_read(&flex_group[i].free_blocks) > - atomic_read(&flex_group[best_flex].free_blocks)) && + ((atomic_read(&flex_group[i].free_clusters) > + atomic_read(&flex_group[best_flex].free_clusters)) && atomic_read(&flex_group[i].free_inodes))) best_flex = i; } if (!atomic_read(&flex_group[best_flex].free_inodes) || - !atomic_read(&flex_group[best_flex].free_blocks)) + !atomic_read(&flex_group[best_flex].free_clusters)) return -1; found_flexbg: @@ -407,7 +409,7 @@ out: struct orlov_stats { __u32 free_inodes; - __u32 free_blocks; + __u32 free_clusters; __u32 used_dirs; }; @@ -424,7 +426,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, if (flex_size > 1) { stats->free_inodes = atomic_read(&flex_group[g].free_inodes); - stats->free_blocks = atomic_read(&flex_group[g].free_blocks); + stats->free_clusters = atomic_read(&flex_group[g].free_clusters); stats->used_dirs = atomic_read(&flex_group[g].used_dirs); return; } @@ -432,11 +434,11 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, desc = ext4_get_group_desc(sb, g, NULL); if (desc) { stats->free_inodes = ext4_free_inodes_count(sb, desc); - stats->free_blocks = ext4_free_blks_count(sb, desc); + stats->free_clusters = ext4_free_blks_count(sb, desc); stats->used_dirs = ext4_used_dirs_count(sb, desc); } else { stats->free_inodes = 0; - stats->free_blocks = 0; + stats->free_clusters = 0; stats->used_dirs = 0; } } @@ -471,10 +473,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei; - ext4_fsblk_t freeb, avefreeb; + ext4_fsblk_t freeb, avefreec; unsigned int ndirs; int max_dirs, min_inodes; - ext4_grpblk_t min_blocks; + ext4_grpblk_t min_clusters; ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; struct orlov_stats stats; @@ -492,8 +494,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, avefreei = freei / ngroups; freeb = EXT4_C2B(sbi, percpu_counter_read_positive(&sbi->s_freeclusters_counter)); - avefreeb = freeb; - do_div(avefreeb, ngroups); + avefreec = freeb; + do_div(avefreec, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); if (S_ISDIR(mode) && @@ -519,7 +521,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, continue; if (stats.free_inodes < avefreei) continue; - if (stats.free_blocks < avefreeb) + if (stats.free_clusters < avefreec) continue; grp = g; ret = 0; @@ -557,7 +559,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; - min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4; + min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4; /* * Start looking in the flex group where we last allocated an @@ -576,7 +578,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, continue; if (stats.free_inodes < min_inodes) continue; - if (stats.free_blocks < min_blocks) + if (stats.free_clusters < min_clusters) continue; goto found_flex_bg; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4a38b65bd564..f8e37cf2c2dd 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2847,7 +2847,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic_sub(ac->ac_b_ex.fe_len, - &sbi->s_flex_groups[flex_group].free_blocks); + &sbi->s_flex_groups[flex_group].free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4696,7 +4696,8 @@ do_more: if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks); + atomic_add(count_clusters, + &sbi->s_flex_groups[flex_group].free_clusters); } ext4_mb_unload_buddy(&e4b); @@ -4839,8 +4840,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic_add(blocks_freed, - &sbi->s_flex_groups[flex_group].free_blocks); + atomic_add(EXT4_B2C(sbi, blocks_freed), + &sbi->s_flex_groups[flex_group].free_clusters); } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index a324a537f2dc..95a09ddca3b9 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -946,8 +946,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) sbi->s_log_groups_per_flex) { ext4_group_t flex_group; flex_group = ext4_flex_group(sbi, input->group); - atomic_add(input->free_blocks_count, - &sbi->s_flex_groups[flex_group].free_blocks); + atomic_add(EXT4_B2C(sbi, input->free_blocks_count), + &sbi->s_flex_groups[flex_group].free_clusters); atomic_add(EXT4_INODES_PER_GROUP(sb), &sbi->s_flex_groups[flex_group].free_inodes); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f81e7e791655..d7e0e045b11b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2035,7 +2035,7 @@ static int ext4_fill_flex_info(struct super_block *sb) atomic_add(ext4_free_inodes_count(sb, gdp), &sbi->s_flex_groups[flex_group].free_inodes); atomic_add(ext4_free_blks_count(sb, gdp), - &sbi->s_flex_groups[flex_group].free_blocks); + &sbi->s_flex_groups[flex_group].free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &sbi->s_flex_groups[flex_group].used_dirs); } -- cgit v1.2.3 From 7b415bf60f6afb0499fd3dc0ee33444f54e28567 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:04:51 -0400 Subject: ext4: Fix bigalloc quota accounting and i_blocks value With bigalloc changes, the i_blocks value was not correctly set (it was still set to number of blocks being used, but in case of bigalloc, we want i_blocks to represent the number of clusters being used). Since the quota subsystem sets the i_blocks value, this patch fixes the quota accounting and makes sure that the i_blocks value is set correctly. Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 5 +- fs/ext4/ext4.h | 16 ++- fs/ext4/ext4_extents.h | 2 + fs/ext4/extents.c | 306 ++++++++++++++++++++++++++++++++++++++++++++++++- fs/ext4/inode.c | 54 ++++++--- fs/ext4/mballoc.c | 5 +- fs/ext4/super.c | 3 +- 7 files changed, 366 insertions(+), 25 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 9080a857cda9..bf42b3219e3c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -485,7 +485,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) - * @count: pointer to total number of blocks needed + * @count: pointer to total number of clusters needed * @errp: error code * * Return 1st allocated block number on success, *count stores total account @@ -517,7 +517,8 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, spin_lock(&EXT4_I(inode)->i_block_reservation_lock); EXT4_I(inode)->i_allocated_meta_blocks += ar.len; spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - dquot_alloc_block_nofail(inode, ar.len); + dquot_alloc_block_nofail(inode, + EXT4_C2B(EXT4_SB(inode->i_sb), ar.len)); } return ret; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d2584224c89a..a6307f7c9807 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -144,9 +144,17 @@ struct ext4_allocation_request { #define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten) #define EXT4_MAP_BOUNDARY (1 << BH_Boundary) #define EXT4_MAP_UNINIT (1 << BH_Uninit) +/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of + * ext4_map_blocks wants to know whether or not the underlying cluster has + * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that + * the requested mapping was from previously mapped (or delayed allocated) + * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster + * should never appear on buffer_head's state flags. + */ +#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ - EXT4_MAP_UNINIT) + EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER) struct ext4_map_blocks { ext4_fsblk_t m_pblk; @@ -1884,6 +1892,7 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); +extern int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2284,6 +2293,11 @@ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); enum ext4_state_bits { BH_Uninit /* blocks are allocated but uninitialized on disk */ = BH_JBDPrivateStart, + BH_AllocFromCluster, /* allocated blocks were part of already + * allocated cluster. Note that this flag will + * never, ever appear in a buffer_head's state + * flag. See EXT4_MAP_FROM_CLUSTER to see where + * this is used. */ }; BUFFER_FNS(Uninit, uninit) diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 095c36f3b612..a52db3a69a30 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -290,5 +290,7 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path *); extern void ext4_ext_drop_refs(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); +extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, + int search_hint_reverse); #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index cd4479c08031..c4e005864534 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2686,6 +2686,21 @@ again: } } + /* If we still have something in the partial cluster and we have removed + * even the first extent, then we should free the blocks in the partial + * cluster as well. */ + if (partial_cluster && path->p_hdr->eh_entries == 0) { + int flags = EXT4_FREE_BLOCKS_FORGET; + + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + flags |= EXT4_FREE_BLOCKS_METADATA; + + ext4_free_blocks(handle, inode, NULL, + EXT4_C2B(EXT4_SB(sb), partial_cluster), + EXT4_SB(sb)->s_cluster_ratio, flags); + partial_cluster = 0; + } + /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* @@ -3233,6 +3248,195 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode, return ext4_mark_inode_dirty(handle, inode); } +/** + * ext4_find_delalloc_range: find delayed allocated block in the given range. + * + * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns + * whether there are any buffers marked for delayed allocation. It returns '1' + * on the first delalloc'ed buffer head found. If no buffer head in the given + * range is marked for delalloc, it returns 0. + * lblk_start should always be <= lblk_end. + * search_hint_reverse is to indicate that searching in reverse from lblk_end to + * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed + * block sooner). This is useful when blocks are truncated sequentially from + * lblk_start towards lblk_end. + */ +static int ext4_find_delalloc_range(struct inode *inode, + ext4_lblk_t lblk_start, + ext4_lblk_t lblk_end, + int search_hint_reverse) +{ + struct address_space *mapping = inode->i_mapping; + struct buffer_head *head, *bh = NULL; + struct page *page; + ext4_lblk_t i, pg_lblk; + pgoff_t index; + + /* reverse search wont work if fs block size is less than page size */ + if (inode->i_blkbits < PAGE_CACHE_SHIFT) + search_hint_reverse = 0; + + if (search_hint_reverse) + i = lblk_end; + else + i = lblk_start; + + index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + + while ((i >= lblk_start) && (i <= lblk_end)) { + page = find_get_page(mapping, index); + if (!page || !PageDirty(page)) + goto nextpage; + + if (PageWriteback(page)) { + /* + * This might be a race with allocation and writeout. In + * this case we just assume that the rest of the range + * will eventually be written and there wont be any + * delalloc blocks left. + * TODO: the above assumption is troublesome, but might + * work better in practice. other option could be note + * somewhere that the cluster is getting written out and + * detect that here. + */ + page_cache_release(page); + return 0; + } + + if (!page_has_buffers(page)) + goto nextpage; + + head = page_buffers(page); + if (!head) + goto nextpage; + + bh = head; + pg_lblk = index << (PAGE_CACHE_SHIFT - + inode->i_blkbits); + do { + if (unlikely(pg_lblk < lblk_start)) { + /* + * This is possible when fs block size is less + * than page size and our cluster starts/ends in + * middle of the page. So we need to skip the + * initial few blocks till we reach the 'lblk' + */ + pg_lblk++; + continue; + } + + if (buffer_delay(bh)) { + page_cache_release(page); + return 1; + } + if (search_hint_reverse) + i--; + else + i++; + } while ((i >= lblk_start) && (i <= lblk_end) && + ((bh = bh->b_this_page) != head)); +nextpage: + if (page) + page_cache_release(page); + /* + * Move to next page. 'i' will be the first lblk in the next + * page. + */ + if (search_hint_reverse) + index--; + else + index++; + i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + } + + return 0; +} + +int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, + int search_hint_reverse) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t lblk_start, lblk_end; + lblk_start = lblk & (~(sbi->s_cluster_ratio - 1)); + lblk_end = lblk_start + sbi->s_cluster_ratio - 1; + + return ext4_find_delalloc_range(inode, lblk_start, lblk_end, + search_hint_reverse); +} + +/** + * Determines how many complete clusters (out of those specified by the 'map') + * are under delalloc and were reserved quota for. + * This function is called when we are writing out the blocks that were + * originally written with their allocation delayed, but then the space was + * allocated using fallocate() before the delayed allocation could be resolved. + * The cases to look for are: + * ('=' indicated delayed allocated blocks + * '-' indicates non-delayed allocated blocks) + * (a) partial clusters towards beginning and/or end outside of allocated range + * are not delalloc'ed. + * Ex: + * |----c---=|====c====|====c====|===-c----| + * |++++++ allocated ++++++| + * ==> 4 complete clusters in above example + * + * (b) partial cluster (outside of allocated range) towards either end is + * marked for delayed allocation. In this case, we will exclude that + * cluster. + * Ex: + * |----====c========|========c========| + * |++++++ allocated ++++++| + * ==> 1 complete clusters in above example + * + * Ex: + * |================c================| + * |++++++ allocated ++++++| + * ==> 0 complete clusters in above example + * + * The ext4_da_update_reserve_space will be called only if we + * determine here that there were some "entire" clusters that span + * this 'allocated' range. + * In the non-bigalloc case, this function will just end up returning num_blks + * without ever calling ext4_find_delalloc_range. + */ +static unsigned int +get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, + unsigned int num_blks) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t alloc_cluster_start, alloc_cluster_end; + ext4_lblk_t lblk_from, lblk_to, c_offset; + unsigned int allocated_clusters = 0; + + alloc_cluster_start = EXT4_B2C(sbi, lblk_start); + alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1); + + /* max possible clusters for this allocation */ + allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1; + + /* Check towards left side */ + c_offset = lblk_start & (sbi->s_cluster_ratio - 1); + if (c_offset) { + lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1)); + lblk_to = lblk_from + c_offset - 1; + + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + allocated_clusters--; + } + + /* Now check towards right. */ + c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1); + if (allocated_clusters && c_offset) { + lblk_from = lblk_start + num_blks; + lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; + + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + allocated_clusters--; + } + + return allocated_clusters; +} + static int ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3338,8 +3542,15 @@ out: * But fallocate would have already updated quota and block * count for this offset. So cancel these reservation */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_da_update_reserve_space(inode, allocated, 0); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + unsigned int reserved_clusters; + reserved_clusters = get_reserved_cluster_alloc(inode, + map->m_lblk, map->m_len); + if (reserved_clusters) + ext4_da_update_reserve_space(inode, + reserved_clusters, + 0); + } map_out: map->m_flags |= EXT4_MAP_MAPPED; @@ -3484,6 +3695,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock = 0; int free_on_err = 0, err = 0, depth, ret; unsigned int allocated = 0, offset = 0; + unsigned int allocated_clusters = 0, reserved_clusters = 0; unsigned int punched_out = 0; unsigned int result = 0; struct ext4_allocation_request ar; @@ -3499,6 +3711,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) && ext4_ext_in_cache(inode, map->m_lblk, &newex)) { if (!newex.ee_start_lo && !newex.ee_start_hi) { + if ((sbi->s_cluster_ratio > 1) && + ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * block isn't allocated yet and @@ -3509,6 +3725,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* we should allocate requested block */ } else { /* block is already allocated */ + if (sbi->s_cluster_ratio > 1) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; newblock = map->m_lblk - le32_to_cpu(newex.ee_block) + ext4_ext_pblock(&newex); @@ -3665,6 +3883,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, } } + if ((sbi->s_cluster_ratio > 1) && + ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; + /* * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero @@ -3681,6 +3903,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* * Okay, we need to do block allocation. */ + map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1); @@ -3692,6 +3915,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(sbi, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; + map->m_flags |= EXT4_MAP_FROM_CLUSTER; goto got_allocated_blocks; } @@ -3712,6 +3936,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(sbi, map, ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; + map->m_flags |= EXT4_MAP_FROM_CLUSTER; goto got_allocated_blocks; } @@ -3765,6 +3990,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext_debug("allocate new block: goal %llu, found %llu/%u\n", ar.goal, newblock, allocated); free_on_err = 1; + allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; if (ar.len > allocated) ar.len = allocated; @@ -3822,8 +4048,80 @@ got_allocated_blocks: * Update reserved blocks/metadata blocks after successful * block allocation which had been deferred till now. */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_da_update_reserve_space(inode, allocated, 1); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + /* + * Check how many clusters we had reserved this allocted range. + */ + reserved_clusters = get_reserved_cluster_alloc(inode, + map->m_lblk, allocated); + if (map->m_flags & EXT4_MAP_FROM_CLUSTER) { + if (reserved_clusters) { + /* + * We have clusters reserved for this range. + * But since we are not doing actual allocation + * and are simply using blocks from previously + * allocated cluster, we should release the + * reservation and not claim quota. + */ + ext4_da_update_reserve_space(inode, + reserved_clusters, 0); + } + } else { + BUG_ON(allocated_clusters < reserved_clusters); + /* We will claim quota for all newly allocated blocks.*/ + ext4_da_update_reserve_space(inode, allocated_clusters, + 1); + if (reserved_clusters < allocated_clusters) { + int reservation = allocated_clusters - + reserved_clusters; + /* + * It seems we claimed few clusters outside of + * the range of this allocation. We should give + * it back to the reservation pool. This can + * happen in the following case: + * + * * Suppose s_cluster_ratio is 4 (i.e., each + * cluster has 4 blocks. Thus, the clusters + * are [0-3],[4-7],[8-11]... + * * First comes delayed allocation write for + * logical blocks 10 & 11. Since there were no + * previous delayed allocated blocks in the + * range [8-11], we would reserve 1 cluster + * for this write. + * * Next comes write for logical blocks 3 to 8. + * In this case, we will reserve 2 clusters + * (for [0-3] and [4-7]; and not for [8-11] as + * that range has a delayed allocated blocks. + * Thus total reserved clusters now becomes 3. + * * Now, during the delayed allocation writeout + * time, we will first write blocks [3-8] and + * allocate 3 clusters for writing these + * blocks. Also, we would claim all these + * three clusters above. + * * Now when we come here to writeout the + * blocks [10-11], we would expect to claim + * the reservation of 1 cluster we had made + * (and we would claim it since there are no + * more delayed allocated blocks in the range + * [8-11]. But our reserved cluster count had + * already gone to 0. + * + * Thus, at the step 4 above when we determine + * that there are still some unwritten delayed + * allocated blocks outside of our current + * block range, we should increment the + * reserved clusters count so that when the + * remaining blocks finally gets written, we + * could claim them. + */ + while (reservation) { + ext4_da_reserve_space(inode, + map->m_lblk); + reservation--; + } + } + } + } /* * Cache the extent and update transaction to commit on fdatasync only diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 40f51aae42fe..d1c17e47c1c6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -300,14 +300,14 @@ void ext4_da_update_reserve_space(struct inode *inode, /* Update quota subsystem for data blocks */ if (quota_claim) - dquot_claim_block(inode, used); + dquot_claim_block(inode, EXT4_C2B(sbi, used)); else { /* * We did fallocate with an offset that is already delayed * allocated. So on delayed allocated writeback we should * not re-claim the quota for fallocated blocks. */ - dquot_release_reservation_block(inode, used); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, used)); } /* @@ -1037,14 +1037,14 @@ static int ext4_journalled_write_end(struct file *file, } /* - * Reserve a single block located at lblock + * Reserve a single cluster located at lblock */ -static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long md_needed; + unsigned int md_needed; int ret; /* @@ -1054,7 +1054,8 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) */ repeat: spin_lock(&ei->i_block_reservation_lock); - md_needed = ext4_calc_metadata_amount(inode, lblock); + md_needed = EXT4_NUM_B2C(sbi, + ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); spin_unlock(&ei->i_block_reservation_lock); @@ -1063,7 +1064,7 @@ repeat: * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ - ret = dquot_reserve_block(inode, 1); + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); if (ret) return ret; /* @@ -1071,7 +1072,7 @@ repeat: * we cannot afford to run out of free blocks. */ if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) { - dquot_release_reservation_block(inode, 1); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; @@ -1118,6 +1119,8 @@ static void ext4_da_release_space(struct inode *inode, int to_free) * We can release all of the reserved metadata blocks * only when we have written all of the delayed * allocation blocks. + * Note that in case of bigalloc, i_reserved_meta_blocks, + * i_reserved_data_blocks, etc. refer to number of clusters. */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); @@ -1130,7 +1133,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free) spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - dquot_release_reservation_block(inode, to_free); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } static void ext4_da_page_release_reservation(struct page *page, @@ -1139,6 +1142,9 @@ static void ext4_da_page_release_reservation(struct page *page, int to_release = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; + struct inode *inode = page->mapping->host; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int num_clusters; head = page_buffers(page); bh = head; @@ -1151,7 +1157,20 @@ static void ext4_da_page_release_reservation(struct page *page, } curr_off = next_off; } while ((bh = bh->b_this_page) != head); - ext4_da_release_space(page->mapping->host, to_release); + + /* If we have released all the blocks belonging to a cluster, then we + * need to release the reserved space for that cluster. */ + num_clusters = EXT4_NUM_B2C(sbi, to_release); + while (num_clusters > 0) { + ext4_fsblk_t lblk; + lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + + ((num_clusters - 1) << sbi->s_cluster_bits); + if (sbi->s_cluster_ratio == 1 || + !ext4_find_delalloc_cluster(inode, lblk, 1)) + ext4_da_release_space(inode, 1); + + num_clusters--; + } } /* @@ -1352,7 +1371,8 @@ static void ext4_print_free_blocks(struct inode *inode) (long long) EXT4_C2B(EXT4_SB(inode->i_sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); printk(KERN_CRIT "dirty_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); + (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); printk(KERN_CRIT "Block reservation details\n"); printk(KERN_CRIT "i_reserved_data_blocks=%u\n", EXT4_I(inode)->i_reserved_data_blocks); @@ -1626,10 +1646,14 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, /* * XXX: __block_write_begin() unmaps passed block, is it OK? */ - ret = ext4_da_reserve_space(inode, iblock); - if (ret) - /* not enough space to reserve */ - return ret; + /* If the block was allocated from previously allocated cluster, + * then we dont need to reserve it again. */ + if (!(map.m_flags & EXT4_MAP_FROM_CLUSTER)) { + ret = ext4_da_reserve_space(inode, iblock); + if (ret) + /* not enough space to reserve */ + return ret; + } map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 63dd56703342..5e1215d38331 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4718,6 +4718,9 @@ do_more: freed += count; + if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) + dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); + /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4736,8 +4739,6 @@ do_more: } ext4_mark_super_dirty(sb); error_return: - if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) - dquot_free_block(inode, freed); brelse(bitmap_bh); ext4_std_error(sb, err); return; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6810957e0ac7..66b8cfa15636 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2473,7 +2473,8 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, char *buf) { return snprintf(buf, PAGE_SIZE, "%llu\n", - (s64) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); + (s64) EXT4_C2B(sbi, + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); } static ssize_t session_write_kbytes_show(struct ext4_attr *a, -- cgit v1.2.3 From 6f16b60690ba04cf476480a6f19b204e4b95b4a6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:06:51 -0400 Subject: ext4: enable mounting bigalloc as read/write Now that we have implemented all of the changes needed for bigalloc, we can finally enable it! Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a6307f7c9807..a5a7e369f719 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1439,7 +1439,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ - EXT4_FEATURE_RO_COMPAT_HUGE_FILE) + EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ + EXT4_FEATURE_RO_COMPAT_BIGALLOC) /* * Default values for user and/or group using reserved blocks -- cgit v1.2.3 From 021b65bb1e4e4b625c80bbb82651e5e155721ef3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:08:51 -0400 Subject: ext4: Rename ext4_free_blks_{count,set}() to refer to clusters The field bg_free_blocks_count_{lo,high} in the block group descriptor has been repurposed to hold the number of free clusters for bigalloc functions. So rename the functions so it makes it easier to read and audit the block allocation and block freeing code. Note: at this point in bigalloc development we doesn't support online resize, so this also makes it really obvious all of the places we need to fix up to add support for online resize. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 8 ++++---- fs/ext4/ext4.h | 9 +++++---- fs/ext4/ialloc.c | 14 +++++++------- fs/ext4/mballoc.c | 22 +++++++++++----------- fs/ext4/resize.c | 2 +- fs/ext4/super.c | 10 +++++----- 6 files changed, 33 insertions(+), 32 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index bf42b3219e3c..84dc3d62b40c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -168,7 +168,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); - ext4_free_blks_set(sb, gdp, 0); + ext4_free_group_clusters_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); @@ -550,7 +550,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; - desc_count += ext4_free_blks_count(sb, gdp); + desc_count += ext4_free_group_clusters(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_block_bitmap(sb, i); if (bitmap_bh == NULL) @@ -558,7 +558,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) x = ext4_count_free(bitmap_bh, sb->s_blocksize); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", - i, ext4_free_blks_count(sb, gdp), x); + i, ext4_free_group_clusters(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); @@ -572,7 +572,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; - desc_count += ext4_free_blks_count(sb, gdp); + desc_count += ext4_free_group_clusters(sb, gdp); } return desc_count; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a5a7e369f719..db279c362017 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1978,8 +1978,8 @@ extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg); -extern __u32 ext4_free_blks_count(struct super_block *sb, - struct ext4_group_desc *bg); +extern __u32 ext4_free_group_clusters(struct super_block *sb, + struct ext4_group_desc *bg); extern __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_used_dirs_count(struct super_block *sb, @@ -1992,8 +1992,9 @@ extern void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); -extern void ext4_free_blks_set(struct super_block *sb, - struct ext4_group_desc *bg, __u32 count); +extern void ext4_free_group_clusters_set(struct super_block *sb, + struct ext4_group_desc *bg, + __u32 count); extern void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_used_dirs_set(struct super_block *sb, diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 0be5862313f0..71a9c8f3dece 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -78,7 +78,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); - ext4_free_blks_set(sb, gdp, 0); + ext4_free_group_clusters_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); @@ -322,8 +322,8 @@ static int find_group_dir(struct super_block *sb, struct inode *parent, if (ext4_free_inodes_count(sb, desc) < avefreei) continue; if (!best_desc || - (ext4_free_blks_count(sb, desc) > - ext4_free_blks_count(sb, best_desc))) { + (ext4_free_group_clusters(sb, desc) > + ext4_free_group_clusters(sb, best_desc))) { *best_group = group; best_desc = desc; ret = 0; @@ -434,7 +434,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, desc = ext4_get_group_desc(sb, g, NULL); if (desc) { stats->free_inodes = ext4_free_inodes_count(sb, desc); - stats->free_clusters = ext4_free_blks_count(sb, desc); + stats->free_clusters = ext4_free_group_clusters(sb, desc); stats->used_dirs = ext4_used_dirs_count(sb, desc); } else { stats->free_inodes = 0; @@ -662,7 +662,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, *group = parent_group; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && - ext4_free_blks_count(sb, desc)) + ext4_free_group_clusters(sb, desc)) return 0; /* @@ -686,7 +686,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, *group -= ngroups; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && - ext4_free_blks_count(sb, desc)) + ext4_free_group_clusters(sb, desc)) return 0; } @@ -960,7 +960,7 @@ got: ext4_lock_group(sb, group); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_blks_set(sb, gdp, + ext4_free_group_clusters_set(sb, gdp, ext4_free_blocks_after_init(sb, group, gdp)); gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5e1215d38331..76db2f12107f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2256,7 +2256,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, ext4_free_blocks_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = - ext4_free_blks_count(sb, desc); + ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); @@ -2799,7 +2799,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, goto out_err; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, - ext4_free_blks_count(sb, gdp)); + ext4_free_group_clusters(sb, gdp)); err = ext4_journal_get_write_access(handle, gdp_bh); if (err) @@ -2839,12 +2839,12 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ac->ac_b_ex.fe_len); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_blks_set(sb, gdp, - ext4_free_blocks_after_init(sb, - ac->ac_b_ex.fe_group, gdp)); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_blocks_after_init(sb, + ac->ac_b_ex.fe_group, gdp)); } - len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len; - ext4_free_blks_set(sb, gdp, len); + len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; + ext4_free_group_clusters_set(sb, gdp, len); gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); @@ -4702,8 +4702,8 @@ do_more: mb_free_blocks(inode, &e4b, bit, count_clusters); } - ret = ext4_free_blks_count(sb, gdp) + count_clusters; - ext4_free_blks_set(sb, gdp, ret); + ret = ext4_free_group_clusters(sb, gdp) + count_clusters; + ext4_free_group_clusters_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); @@ -4846,8 +4846,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count); mb_free_blocks(NULL, &e4b, bit, count); - blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc); - ext4_free_blks_set(sb, desc, blk_free_count); + blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc); + ext4_free_group_clusters_set(sb, desc, blk_free_count); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 95a09ddca3b9..996780ab4f4e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -875,7 +875,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */ ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */ ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */ - ext4_free_blks_set(sb, gdp, input->free_blocks_count); + ext4_free_group_clusters_set(sb, gdp, input->free_blocks_count); ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED); gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 66b8cfa15636..30cf0e1bd89c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -163,8 +163,8 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb, (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } -__u32 ext4_free_blks_count(struct super_block *sb, - struct ext4_group_desc *bg) +__u32 ext4_free_group_clusters(struct super_block *sb, + struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? @@ -219,8 +219,8 @@ void ext4_inode_table_set(struct super_block *sb, bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } -void ext4_free_blks_set(struct super_block *sb, - struct ext4_group_desc *bg, __u32 count) +void ext4_free_group_clusters_set(struct super_block *sb, + struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) @@ -2034,7 +2034,7 @@ static int ext4_fill_flex_info(struct super_block *sb) flex_group = ext4_flex_group(sbi, i); atomic_add(ext4_free_inodes_count(sb, gdp), &sbi->s_flex_groups[flex_group].free_inodes); - atomic_add(ext4_free_blks_count(sb, gdp), + atomic_add(ext4_free_group_clusters(sb, gdp), &sbi->s_flex_groups[flex_group].free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &sbi->s_flex_groups[flex_group].used_dirs); -- cgit v1.2.3 From 5dee54372c1ea15ab482b959634cda8c01b042bd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:10:51 -0400 Subject: ext4: rename ext4_count_free_blocks() to ext4_count_free_clusters() This function really counts the free clusters reported in the block group descriptors, so rename it to reduce confusion. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 11 ++++++----- fs/ext4/ext4.h | 2 +- fs/ext4/inode.c | 6 +++--- fs/ext4/super.c | 7 ++++--- 4 files changed, 14 insertions(+), 12 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 84dc3d62b40c..4f303809e076 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -524,12 +524,12 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, } /** - * ext4_count_free_blocks() -- count filesystem free blocks + * ext4_count_free_clusters() -- count filesystem free clusters * @sb: superblock * - * Adds up the number of free blocks from each block group. + * Adds up the number of free clusters from each block group. */ -ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) +ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) { ext4_fsblk_t desc_count; struct ext4_group_desc *gdp; @@ -562,8 +562,9 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) bitmap_count += x; } brelse(bitmap_bh); - printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu" - ", computed = %llu, %llu\n", ext4_free_blocks_count(es), + printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu" + ", computed = %llu, %llu\n", + EXT4_B2C(sbi, ext4_free_blocks_count(es)), desc_count, bitmap_count); return bitmap_count; #else diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index db279c362017..f6963cd7f709 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1775,7 +1775,7 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, int *errp); extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags); -extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *); +extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d1c17e47c1c6..f9198d7875cc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1365,7 +1365,8 @@ static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); printk(KERN_CRIT "Total free blocks count %lld\n", - ext4_count_free_blocks(inode->i_sb)); + EXT4_C2B(EXT4_SB(inode->i_sb), + ext4_count_free_clusters(inode->i_sb))); printk(KERN_CRIT "Free/Dirty block details\n"); printk(KERN_CRIT "free_blocks=%lld\n", (long long) EXT4_C2B(EXT4_SB(inode->i_sb), @@ -1451,8 +1452,7 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) if (err == -EAGAIN) goto submit_io; - if (err == -ENOSPC && - ext4_count_free_blocks(sb)) { + if (err == -ENOSPC && ext4_count_free_clusters(sb)) { mpd->retval = err; goto submit_io; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 30cf0e1bd89c..07f3de341452 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2153,7 +2153,8 @@ static int ext4_check_descriptors(struct super_block *sb, if (NULL != first_not_zeroed) *first_not_zeroed = grp; - ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); + ext4_free_blocks_count_set(sbi->s_es, + EXT4_C2B(sbi, ext4_count_free_clusters(sb))); sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } @@ -3577,7 +3578,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.data = (unsigned long) sb; err = percpu_counter_init(&sbi->s_freeclusters_counter, - ext4_count_free_blocks(sb)); + ext4_count_free_clusters(sb)); if (!err) { err = percpu_counter_init(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); @@ -3703,7 +3704,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * need to update the global counters. */ percpu_counter_set(&sbi->s_freeclusters_counter, - ext4_count_free_blocks(sb)); + ext4_count_free_clusters(sb)); percpu_counter_set(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); percpu_counter_set(&sbi->s_dirs_counter, -- cgit v1.2.3 From cff1dfd767d1ee3c773fd8b57fe310957e5f8abb Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:12:51 -0400 Subject: ext4: rename ext4_free_blocks_after_init() to ext4_free_clusters_after_init() This function really returns the number of clusters after initializing an uninitalized block bitmap has been initialized. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 6 +++--- fs/ext4/ext4.h | 6 +++--- fs/ext4/ialloc.c | 2 +- fs/ext4/mballoc.c | 4 ++-- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 4f303809e076..3d07c35c7089 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -213,9 +213,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, /* Return the number of free blocks in a block group. It is used when * the block bitmap is uninitialized, so we can't just count the bits * in the bitmap. */ -unsigned ext4_free_blocks_after_init(struct super_block *sb, - ext4_group_t block_group, - struct ext4_group_desc *gdp) +unsigned ext4_free_clusters_after_init(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { return num_clusters_in_group(sb, block_group) - ext4_num_overhead_clusters(sb, block_group, gdp); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f6963cd7f709..1473c06e4c94 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1787,9 +1787,9 @@ extern void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t group, struct ext4_group_desc *desc); -extern unsigned ext4_free_blocks_after_init(struct super_block *sb, - ext4_group_t block_group, - struct ext4_group_desc *gdp); +extern unsigned ext4_free_clusters_after_init(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp); extern unsigned ext4_num_base_meta_clusters(struct super_block *sb, ext4_group_t block_group); extern unsigned ext4_num_overhead_clusters(struct super_block *sb, diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 71a9c8f3dece..d50a7d5e4726 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -961,7 +961,7 @@ got: if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, - ext4_free_blocks_after_init(sb, group, gdp)); + ext4_free_clusters_after_init(sb, group, gdp)); gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 76db2f12107f..90a3ed7c565c 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2253,7 +2253,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, */ if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { meta_group_info[i]->bb_free = - ext4_free_blocks_after_init(sb, group, desc); + ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); @@ -2840,7 +2840,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, - ext4_free_blocks_after_init(sb, + ext4_free_clusters_after_init(sb, ac->ac_b_ex.fe_group, gdp)); } len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; -- cgit v1.2.3 From e7d5f3156e6827970f75ab27ad7eb0155826eb0b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:14:51 -0400 Subject: ext4: rename ext4_claim_free_blocks() to ext4_claim_free_clusters() This function really claims a number of free clusters, not blocks, so rename it so it's clearer what's going on. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 8 ++++---- fs/ext4/ext4.h | 4 ++-- fs/ext4/inode.c | 2 +- fs/ext4/mballoc.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 3d07c35c7089..af0c5357e35a 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -445,11 +445,11 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, return 0; } -int ext4_claim_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags) +int ext4_claim_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags) { - if (ext4_has_free_blocks(sbi, nblocks, flags)) { - percpu_counter_add(&sbi->s_dirtyclusters_counter, nblocks); + if (ext4_has_free_blocks(sbi, nclusters, flags)) { + percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters); return 0; } else return -ENOSPC; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1473c06e4c94..f97638634e34 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1773,8 +1773,8 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, unsigned int flags, unsigned long *count, int *errp); -extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags); +extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags); extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f9198d7875cc..557c34ffa05b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1071,7 +1071,7 @@ repeat: * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ - if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) { + if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 90a3ed7c565c..1c83161090f8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4297,7 +4297,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, * and verify allocation doesn't exceed the quota limits. */ while (ar->len && - ext4_claim_free_blocks(sbi, ar->len, ar->flags)) { + ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ yield(); -- cgit v1.2.3 From df55c99dc8ee4c3c886a5edc8a4aa6b131c95afc Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:16:51 -0400 Subject: ext4: rename ext4_has_free_blocks() to ext4_has_free_clusters() Rename the function so it is more clear what is going on. Also rename the various variables so it's clearer what's happening. Also fix a missing blocks to cluster conversion when reading the number of reserved blocks for root. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 43 ++++++++++++++++++++++--------------------- fs/ext4/ext4.h | 8 ++++---- fs/ext4/inode.c | 2 +- 3 files changed, 27 insertions(+), 26 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index af0c5357e35a..f6dba4505f1c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -403,42 +403,43 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) } /** - * ext4_has_free_blocks() + * ext4_has_free_clusters() * @sbi: in-core super block structure. - * @nblocks: number of needed blocks + * @nclusters: number of needed blocks + * @flags: flags from ext4_mb_new_blocks() * - * Check if filesystem has nblocks free & available for allocation. + * Check if filesystem has nclusters free & available for allocation. * On success return 1, return 0 on failure. */ -static int ext4_has_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags) +static int ext4_has_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags) { - s64 free_blocks, dirty_blocks, root_blocks; + s64 free_clusters, dirty_clusters, root_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; - struct percpu_counter *dbc = &sbi->s_dirtyclusters_counter; + struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; - free_blocks = percpu_counter_read_positive(fcc); - dirty_blocks = percpu_counter_read_positive(dbc); - root_blocks = ext4_r_blocks_count(sbi->s_es); + free_clusters = percpu_counter_read_positive(fcc); + dirty_clusters = percpu_counter_read_positive(dcc); + root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es)); - if (free_blocks - (nblocks + root_blocks + dirty_blocks) < - EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); - dirty_blocks = percpu_counter_sum_positive(dbc); + if (free_clusters - (nclusters + root_clusters + dirty_clusters) < + EXT4_FREECLUSTERS_WATERMARK) { + free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); + dirty_clusters = percpu_counter_sum_positive(dcc); } - /* Check whether we have space after - * accounting for current dirty blocks & root reserved blocks. + /* Check whether we have space after accounting for current + * dirty clusters & root reserved clusters. */ - if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks)) + if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters)) return 1; - /* Hm, nope. Are (enough) root reserved blocks available? */ + /* Hm, nope. Are (enough) root reserved clusters available? */ if (sbi->s_resuid == current_fsuid() || ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || (flags & EXT4_MB_USE_ROOT_BLOCKS)) { - if (free_blocks >= (nblocks + dirty_blocks)) + if (free_clusters >= (nclusters + dirty_clusters)) return 1; } @@ -448,7 +449,7 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { - if (ext4_has_free_blocks(sbi, nclusters, flags)) { + if (ext4_has_free_clusters(sbi, nclusters, flags)) { percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters); return 0; } else @@ -469,7 +470,7 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, */ int ext4_should_retry_alloc(struct super_block *sb, int *retries) { - if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) || + if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) || (*retries)++ > 3 || !EXT4_SB(sb)->s_journal) return 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f97638634e34..21ea65d8bd46 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2103,13 +2103,13 @@ do { \ } while (0) #ifdef CONFIG_SMP -/* Each CPU can accumulate percpu_counter_batch blocks in their local - * counters. So we need to make sure we have free blocks more +/* Each CPU can accumulate percpu_counter_batch clusters in their local + * counters. So we need to make sure we have free clusters more * than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times. */ -#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) +#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) #else -#define EXT4_FREEBLOCKS_WATERMARK 0 +#define EXT4_FREECLUSTERS_WATERMARK 0 #endif static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 557c34ffa05b..88dc63a01756 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2255,7 +2255,7 @@ static int ext4_nonda_switch(struct super_block *sb) percpu_counter_read_positive(&sbi->s_freeclusters_counter)); dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); if (2 * free_blocks < 3 * dirty_blocks || - free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) { + free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark -- cgit v1.2.3 From d8990240d8c911064447f8aa5a440f9345a6d692 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:18:51 -0400 Subject: ext4: add some tracepoints in ext4/extents.c This patch adds some tracepoints in ext4/extents.c and updates a tracepoint in ext4/inode.c. Tested: Built and ran the kernel and verified that these tracepoints work. Also ran xfstests. Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 + fs/ext4/extents.c | 44 ++++- fs/ext4/inode.c | 3 +- fs/ext4/migrate.c | 1 - fs/ext4/move_extent.c | 1 - include/trace/events/ext4.h | 398 +++++++++++++++++++++++++++++++++++++++++++- 6 files changed, 433 insertions(+), 16 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 21ea65d8bd46..751277a4890c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2339,4 +2339,6 @@ extern void ext4_resize_end(struct super_block *sb); #endif /* __KERNEL__ */ +#include "ext4_extents.h" + #endif /* _EXT4_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c4e005864534..9b119308daea 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -42,7 +42,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" #include @@ -1969,6 +1968,7 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block, struct ext4_ext_cache *cex; BUG_ON(len == 0); spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + trace_ext4_ext_put_in_cache(inode, block, len, start); cex = &EXT4_I(inode)->i_cached_extent; cex->ec_block = block; cex->ec_len = len; @@ -2070,6 +2070,7 @@ errout: sbi->extent_cache_misses++; else sbi->extent_cache_hits++; + trace_ext4_ext_in_cache(inode, block, ret); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); return ret; } @@ -2137,6 +2138,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, if (err) return err; ext_debug("index is empty, remove it, free block %llu\n", leaf); + trace_ext4_ext_rm_idx(inode, leaf); + ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return err; @@ -2222,6 +2225,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; + trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster); /* * If we have a partial cluster, and it's different from the * cluster of the last block, we need to explicitly free the @@ -2336,6 +2340,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); + trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster); + while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { @@ -2591,6 +2597,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start) again: ext4_ext_invalidate_cache(inode); + trace_ext4_ext_remove_space(inode, start, depth); + /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. @@ -2686,6 +2694,9 @@ again: } } + trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster, + path->p_hdr->eh_entries); + /* If we still have something in the partial cluster and we have removed * even the first extent, then we should free the blocks in the partial * cluster as well. */ @@ -3300,6 +3311,10 @@ static int ext4_find_delalloc_range(struct inode *inode, * detect that here. */ page_cache_release(page); + trace_ext4_find_delalloc_range(inode, + lblk_start, lblk_end, + search_hint_reverse, + 0, i); return 0; } @@ -3327,6 +3342,10 @@ static int ext4_find_delalloc_range(struct inode *inode, if (buffer_delay(bh)) { page_cache_release(page); + trace_ext4_find_delalloc_range(inode, + lblk_start, lblk_end, + search_hint_reverse, + 1, i); return 1; } if (search_hint_reverse) @@ -3349,6 +3368,8 @@ nextpage: i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); } + trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end, + search_hint_reverse, 0, 0); return 0; } @@ -3414,6 +3435,8 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, /* max possible clusters for this allocation */ allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1; + trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks); + /* Check towards left side */ c_offset = lblk_start & (sbi->s_cluster_ratio - 1); if (c_offset) { @@ -3453,6 +3476,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); + trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated, + newblock); + /* get_block() before submit the IO, split the extent */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { ret = ext4_split_unwritten_extents(handle, inode, map, @@ -3572,7 +3598,7 @@ out2: * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. - * @sbi The ext4-specific superblock structure + * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation @@ -3609,11 +3635,12 @@ out2: * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ -static int get_implied_cluster_alloc(struct ext4_sb_info *sbi, +static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { + struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start, rr_cluster_end; @@ -3662,8 +3689,12 @@ static int get_implied_cluster_alloc(struct ext4_sb_info *sbi, ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } + + trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } + + trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } @@ -3772,6 +3803,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); + + trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); + /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { ext4_fsblk_t partial_cluster = 0; @@ -3912,7 +3946,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * by ext4_ext_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && - get_implied_cluster_alloc(sbi, map, ex, path)) { + get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; map->m_flags |= EXT4_MAP_FROM_CLUSTER; @@ -3933,7 +3967,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && ex2 && - get_implied_cluster_alloc(sbi, map, ex2, path)) { + get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; map->m_flags |= EXT4_MAP_FROM_CLUSTER; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 88dc63a01756..2dcd4fed96ec 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -42,7 +42,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "ext4_extents.h" #include "truncate.h" #include @@ -268,7 +267,7 @@ void ext4_da_update_reserve_space(struct inode *inode, struct ext4_inode_info *ei = EXT4_I(inode); spin_lock(&ei->i_block_reservation_lock); - trace_ext4_da_update_reserve_space(inode, used); + trace_ext4_da_update_reserve_space(inode, used, quota_claim); if (unlikely(used > ei->i_reserved_data_blocks)) { ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d " "with only %d reserved data blocks\n", diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b57b98fb44d1..6f07a06f2437 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -15,7 +15,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" /* * The contiguous blocks details which can be diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index f57455a1b1b2..c5826c623e7a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -17,7 +17,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" #include "ext4.h" /** diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b50a54736242..c9a341e385a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -12,6 +12,8 @@ struct ext4_allocation_request; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; +struct ext4_map_blocks; +struct ext4_extent; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) @@ -1032,9 +1034,9 @@ TRACE_EVENT(ext4_forget, ); TRACE_EVENT(ext4_da_update_reserve_space, - TP_PROTO(struct inode *inode, int used_blocks), + TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), - TP_ARGS(inode, used_blocks), + TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( dev_t, dev ) @@ -1045,6 +1047,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, __field( int, reserved_data_blocks ) __field( int, reserved_meta_blocks ) __field( int, allocated_meta_blocks ) + __field( int, quota_claim ) ), TP_fast_assign( @@ -1053,19 +1056,24 @@ TRACE_EVENT(ext4_da_update_reserve_space, __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; - __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; - __entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; - __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; + __entry->reserved_data_blocks = + EXT4_I(inode)->i_reserved_data_blocks; + __entry->reserved_meta_blocks = + EXT4_I(inode)->i_reserved_meta_blocks; + __entry->allocated_meta_blocks = + EXT4_I(inode)->i_allocated_meta_blocks; + __entry->quota_claim = quota_claim; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d reserved_meta_blocks %d " - "allocated_meta_blocks %d", + "allocated_meta_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, - __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) + __entry->reserved_meta_blocks, __entry->allocated_meta_blocks, + __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, @@ -1589,6 +1597,382 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free, TP_ARGS(sb, group, start, len) ); +TRACE_EVENT(ext4_ext_handle_uninitialized_extents, + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, + unsigned int allocated, ext4_fsblk_t newblock), + + TP_ARGS(inode, map, allocated, newblock), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned int, len ) + __field( int, flags ) + __field( unsigned int, allocated ) + __field( ext4_fsblk_t, newblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = map->m_lblk; + __entry->pblk = map->m_pblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; + __entry->allocated = allocated; + __entry->newblk = newblock; + ), + + TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d" + "allocated %d newblock %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->flags, + (unsigned int) __entry->allocated, + (unsigned long long) __entry->newblk) +); + +TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, + TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret), + + TP_ARGS(sb, map, ret), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned int, len ) + __field( unsigned int, flags ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->lblk = map->m_lblk; + __entry->pblk = map->m_pblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->flags, __entry->ret) +); + +TRACE_EVENT(ext4_ext_put_in_cache, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len, + ext4_fsblk_t start), + + TP_ARGS(inode, lblk, len, start), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned int, len ) + __field( ext4_fsblk_t, start ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + __entry->start = start; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u start %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->len, + (unsigned long long) __entry->start) +); + +TRACE_EVENT(ext4_ext_in_cache, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, int ret), + + TP_ARGS(inode, lblk, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu lblk %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->ret) + +); + +TRACE_EVENT(ext4_find_delalloc_range, + TP_PROTO(struct inode *inode, ext4_lblk_t from, ext4_lblk_t to, + int reverse, int found, ext4_lblk_t found_blk), + + TP_ARGS(inode, from, to, reverse, found, found_blk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, from ) + __field( ext4_lblk_t, to ) + __field( int, reverse ) + __field( int, found ) + __field( ext4_lblk_t, found_blk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->from = from; + __entry->to = to; + __entry->reverse = reverse; + __entry->found = found; + __entry->found_blk = found_blk; + ), + + TP_printk("dev %d,%d ino %lu from %u to %u reverse %d found %d " + "(blk = %u)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->from, (unsigned) __entry->to, + __entry->reverse, __entry->found, + (unsigned) __entry->found_blk) +); + +TRACE_EVENT(ext4_get_reserved_cluster_alloc, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len), + + TP_ARGS(inode, lblk, len), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned int, len ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->len) +); + +TRACE_EVENT(ext4_ext_show_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, + unsigned short len), + + TP_ARGS(inode, lblk, pblk, len), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned short, len ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + (unsigned long long) __entry->pblk, + (unsigned short) __entry->len) +); + +TRACE_EVENT(ext4_remove_blocks, + TP_PROTO(struct inode *inode, struct ext4_extent *ex, + ext4_lblk_t from, ext4_fsblk_t to, + ext4_fsblk_t partial_cluster), + + TP_ARGS(inode, ex, from, to, partial_cluster), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, ee_lblk ) + __field( ext4_fsblk_t, ee_pblk ) + __field( unsigned short, ee_len ) + __field( ext4_lblk_t, from ) + __field( ext4_lblk_t, to ) + __field( ext4_fsblk_t, partial ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->ee_lblk = cpu_to_le32(ex->ee_block); + __entry->ee_pblk = ext4_ext_pblock(ex); + __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->from = from; + __entry->to = to; + __entry->partial = partial_cluster; + ), + + TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" + "from %u to %u partial_cluster %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->ee_lblk, + (unsigned long long) __entry->ee_pblk, + (unsigned short) __entry->ee_len, + (unsigned) __entry->from, + (unsigned) __entry->to, + (unsigned) __entry->partial) +); + +TRACE_EVENT(ext4_ext_rm_leaf, + TP_PROTO(struct inode *inode, ext4_lblk_t start, + struct ext4_extent *ex, ext4_fsblk_t partial_cluster), + + TP_ARGS(inode, start, ex, partial_cluster), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( ext4_lblk_t, ee_lblk ) + __field( ext4_fsblk_t, ee_pblk ) + __field( short, ee_len ) + __field( ext4_fsblk_t, partial ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->ee_lblk = le32_to_cpu(ex->ee_block); + __entry->ee_pblk = ext4_ext_pblock(ex); + __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->partial = partial_cluster; + ), + + TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" + "partial_cluster %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + (unsigned) __entry->ee_lblk, + (unsigned long long) __entry->ee_pblk, + (unsigned short) __entry->ee_len, + (unsigned) __entry->partial) +); + +TRACE_EVENT(ext4_ext_rm_idx, + TP_PROTO(struct inode *inode, ext4_fsblk_t pblk), + + TP_ARGS(inode, pblk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_fsblk_t, pblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pblk = pblk; + ), + + TP_printk("dev %d,%d ino %lu index_pblk %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pblk) +); + +TRACE_EVENT(ext4_ext_remove_space, + TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth), + + TP_ARGS(inode, start, depth), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( int, depth ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->depth = depth; + ), + + TP_printk("dev %d,%d ino %lu since %u depth %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + __entry->depth) +); + +TRACE_EVENT(ext4_ext_remove_space_done, + TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth, + ext4_lblk_t partial, unsigned short eh_entries), + + TP_ARGS(inode, start, depth, partial, eh_entries), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( int, depth ) + __field( ext4_lblk_t, partial ) + __field( unsigned short, eh_entries ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->depth = depth; + __entry->partial = partial; + __entry->eh_entries = eh_entries; + ), + + TP_printk("dev %d,%d ino %lu since %u depth %d partial %u " + "remaining_entries %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + __entry->depth, + (unsigned) __entry->partial, + (unsigned short) __entry->eh_entries) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 5356f2615cd558c57a1f7d7528d1ad4de3640d96 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:20:51 -0400 Subject: ext4: attempt to fix race in bigalloc code path Currently, there exists a race between delayed allocated writes and the writeback when bigalloc feature is in use. The race was because we wanted to determine what blocks in a cluster are under delayed allocation and we were using buffer_delayed(bh) check for it. But, the writeback codepath clears this bit without any synchronization which resulted in a race and an ext4 warning similar to: EXT4-fs (ram1): ext4_da_update_reserve_space: ino 13, used 1 with only 0 reserved data blocks The race existed in two places. (1) between ext4_find_delalloc_range() and ext4_map_blocks() when called from writeback code path. (2) between ext4_find_delalloc_range() and ext4_da_get_block_prep() (where buffer_delayed(bh) is set. To fix (1), this patch introduces a new buffer_head state bit - BH_Da_Mapped. This bit is set under the protection of EXT4_I(inode)->i_data_sem when we have actually mapped the delayed allocated blocks during the writeout time. We can now reliably check for this bit inside ext4_find_delalloc_range() to determine whether the reservation for the blocks have already been claimed or not. To fix (2), it was necessary to set buffer_delay(bh) under the protection of i_data_sem. So, I extracted the very beginning of ext4_map_blocks into a new function - ext4_da_map_blocks() - and performed the required setting of bh_delay bit and the quota reservation under the protection of i_data_sem. These two fixes makes the checking of buffer_delay(bh) and buffer_da_mapped(bh) consistent, thus removing the race. Tested: I was able to reproduce the problem by running 'dd' and 'fsync' in parallel. Also, xfstests sometimes used to reproduce this race. After the fix both my test and xfstests were successful and no race (warning message) was observed. Google-Bug-Id: 4997027 Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 5 +- fs/ext4/extents.c | 38 +++++--------- fs/ext4/inode.c | 146 +++++++++++++++++++++++++++++++++++++++++++----------- 3 files changed, 134 insertions(+), 55 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 751277a4890c..1bbd2caebe7f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1893,7 +1893,6 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); -extern int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2300,10 +2299,14 @@ enum ext4_state_bits { * never, ever appear in a buffer_head's state * flag. See EXT4_MAP_FROM_CLUSTER to see where * this is used. */ + BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This + * flag is set when ext4_map_blocks is called on a + * delayed allocated block to get its real mapping. */ }; BUFFER_FNS(Uninit, uninit) TAS_BUFFER_FNS(Uninit, uninit) +BUFFER_FNS(Da_Mapped, da_mapped) /* * Add new method to test wether block and inode bitmaps are properly diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9b119308daea..ad39627c1fbc 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3296,28 +3296,9 @@ static int ext4_find_delalloc_range(struct inode *inode, while ((i >= lblk_start) && (i <= lblk_end)) { page = find_get_page(mapping, index); - if (!page || !PageDirty(page)) + if (!page) goto nextpage; - if (PageWriteback(page)) { - /* - * This might be a race with allocation and writeout. In - * this case we just assume that the rest of the range - * will eventually be written and there wont be any - * delalloc blocks left. - * TODO: the above assumption is troublesome, but might - * work better in practice. other option could be note - * somewhere that the cluster is getting written out and - * detect that here. - */ - page_cache_release(page); - trace_ext4_find_delalloc_range(inode, - lblk_start, lblk_end, - search_hint_reverse, - 0, i); - return 0; - } - if (!page_has_buffers(page)) goto nextpage; @@ -3340,7 +3321,11 @@ static int ext4_find_delalloc_range(struct inode *inode, continue; } - if (buffer_delay(bh)) { + /* Check if the buffer is delayed allocated and that it + * is not yet mapped. (when da-buffers are mapped during + * their writeout, their da_mapped bit is set.) + */ + if (buffer_delay(bh) && !buffer_da_mapped(bh)) { page_cache_release(page); trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end, @@ -4106,6 +4091,7 @@ got_allocated_blocks: ext4_da_update_reserve_space(inode, allocated_clusters, 1); if (reserved_clusters < allocated_clusters) { + struct ext4_inode_info *ei = EXT4_I(inode); int reservation = allocated_clusters - reserved_clusters; /* @@ -4148,11 +4134,11 @@ got_allocated_blocks: * remaining blocks finally gets written, we * could claim them. */ - while (reservation) { - ext4_da_reserve_space(inode, - map->m_lblk); - reservation--; - } + dquot_reserve_block(inode, + EXT4_C2B(sbi, reservation)); + spin_lock(&ei->i_block_reservation_lock); + ei->i_reserved_data_blocks += reservation; + spin_unlock(&ei->i_block_reservation_lock); } } } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2dcd4fed96ec..1380cd29c312 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -397,6 +397,49 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, return num; } +/* + * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map. + */ +static void set_buffers_da_mapped(struct inode *inode, + struct ext4_map_blocks *map) +{ + struct address_space *mapping = inode->i_mapping; + struct pagevec pvec; + int i, nr_pages; + pgoff_t index, end; + + index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + end = (map->m_lblk + map->m_len - 1) >> + (PAGE_CACHE_SHIFT - inode->i_blkbits); + + pagevec_init(&pvec, 0); + while (index <= end) { + nr_pages = pagevec_lookup(&pvec, mapping, index, + min(end - index + 1, + (pgoff_t)PAGEVEC_SIZE)); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + struct buffer_head *bh, *head; + + if (unlikely(page->mapping != mapping) || + !PageDirty(page)) + break; + + if (page_has_buffers(page)) { + bh = head = page_buffers(page); + do { + set_buffer_da_mapped(bh); + bh = bh->b_this_page; + } while (bh != head); + } + index++; + } + pagevec_release(&pvec); + } +} + /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -516,9 +559,17 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) ext4_da_update_reserve_space(inode, retval, 1); } - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); + /* If we have successfully mapped the delayed allocated blocks, + * set the BH_Da_Mapped bit on them. Its important to do this + * under the protection of i_data_sem. + */ + if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) + set_buffers_da_mapped(inode, map); + } + up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); @@ -1038,7 +1089,7 @@ static int ext4_journalled_write_end(struct file *file, /* * Reserve a single cluster located at lblock */ -int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -1153,6 +1204,7 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; clear_buffer_delay(bh); + clear_buffer_da_mapped(bh); } curr_off = next_off; } while ((bh = bh->b_this_page) != head); @@ -1271,6 +1323,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, clear_buffer_delay(bh); bh->b_blocknr = pblock; } + if (buffer_da_mapped(bh)) + clear_buffer_da_mapped(bh); if (buffer_unwritten(bh) || buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -1603,6 +1657,66 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } +/* + * This function is grabs code from the very beginning of + * ext4_map_blocks, but assumes that the caller is from delayed write + * time. This function looks up the requested blocks and sets the + * buffer delay bit under the protection of i_data_sem. + */ +static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, + struct ext4_map_blocks *map, + struct buffer_head *bh) +{ + int retval; + sector_t invalid_block = ~((sector_t) 0xffff); + + if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) + invalid_block = ~0; + + map->m_flags = 0; + ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," + "logical block %lu\n", inode->i_ino, map->m_len, + (unsigned long) map->m_lblk); + /* + * Try to see if we can get the block without requesting a new + * file system block. + */ + down_read((&EXT4_I(inode)->i_data_sem)); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + retval = ext4_ext_map_blocks(NULL, inode, map, 0); + else + retval = ext4_ind_map_blocks(NULL, inode, map, 0); + + if (retval == 0) { + /* + * XXX: __block_prepare_write() unmaps passed block, + * is it OK? + */ + /* If the block was allocated from previously allocated cluster, + * then we dont need to reserve it again. */ + if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) { + retval = ext4_da_reserve_space(inode, iblock); + if (retval) + /* not enough space to reserve */ + goto out_unlock; + } + + /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served + * and it should not appear on the bh->b_state. + */ + map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; + + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); + } + +out_unlock: + up_read((&EXT4_I(inode)->i_data_sem)); + + return retval; +} + /* * This is a special get_blocks_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or @@ -1620,10 +1734,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, { struct ext4_map_blocks map; int ret = 0; - sector_t invalid_block = ~((sector_t) 0xffff); - - if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) - invalid_block = ~0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); @@ -1636,29 +1746,9 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) + ret = ext4_da_map_blocks(inode, iblock, &map, bh); + if (ret <= 0) return ret; - if (ret == 0) { - if (buffer_delay(bh)) - return 0; /* Not sure this could or should happen */ - /* - * XXX: __block_write_begin() unmaps passed block, is it OK? - */ - /* If the block was allocated from previously allocated cluster, - * then we dont need to reserve it again. */ - if (!(map.m_flags & EXT4_MAP_FROM_CLUSTER)) { - ret = ext4_da_reserve_space(inode, iblock); - if (ret) - /* not enough space to reserve */ - return ret; - } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - return 0; - } map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; -- cgit v1.2.3 From 4113c4caa4f355b8ff8b7ff0510c29c9d00d30b3 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Sat, 8 Oct 2011 14:34:47 -0400 Subject: ext4: remove deprecated oldalloc For a long time now orlov is the default block allocator in the ext4. It performs better than the old one and no one seems to claim otherwise so we can safely drop it and make oldalloc and orlov mount option deprecated. This is a part of the effort to reduce number of ext4 options hence the test matrix. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 8 --- fs/ext4/ext4.h | 1 - fs/ext4/ialloc.c | 138 +------------------------------------ fs/ext4/super.c | 8 +-- 4 files changed, 7 insertions(+), 148 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index a53040193967..4917cf24a5e0 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -203,14 +203,6 @@ inode_readahead_blks=n This tuning parameter controls the maximum table readahead algorithm will pre-read into the buffer cache. The default value is 32 blocks. -orlov (*) This enables the new Orlov block allocator. It is - enabled by default. - -oldalloc This disables the Orlov block allocator and enables - the old block allocator. Orlov should have better - performance - we'd like to get some feedback if it's - the contrary for you. - nouser_xattr Disables Extended User Attributes. If you have extended attribute support enabled in the kernel configuration (CONFIG_EXT4_FS_XATTR), extended attribute support diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1bbd2caebe7f..61b0b5cd4aa2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -913,7 +913,6 @@ struct ext4_inode_info { /* * Mount flags */ -#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index d50a7d5e4726..04219988e75f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -293,120 +293,6 @@ error_return: ext4_std_error(sb, fatal); } -/* - * There are two policies for allocating an inode. If the new inode is - * a directory, then a forward search is made for a block group with both - * free space and a low directory-to-inode ratio; if that fails, then of - * the groups with above-average free space, that group with the fewest - * directories already is chosen. - * - * For other inodes, search forward from the parent directory\'s block - * group to find a free inode. - */ -static int find_group_dir(struct super_block *sb, struct inode *parent, - ext4_group_t *best_group) -{ - ext4_group_t ngroups = ext4_get_groups_count(sb); - unsigned int freei, avefreei; - struct ext4_group_desc *desc, *best_desc = NULL; - ext4_group_t group; - int ret = -1; - - freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter); - avefreei = freei / ngroups; - - for (group = 0; group < ngroups; group++) { - desc = ext4_get_group_desc(sb, group, NULL); - if (!desc || !ext4_free_inodes_count(sb, desc)) - continue; - if (ext4_free_inodes_count(sb, desc) < avefreei) - continue; - if (!best_desc || - (ext4_free_group_clusters(sb, desc) > - ext4_free_group_clusters(sb, best_desc))) { - *best_group = group; - best_desc = desc; - ret = 0; - } - } - return ret; -} - -#define free_block_ratio 10 - -static int find_group_flex(struct super_block *sb, struct inode *parent, - ext4_group_t *best_group) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_group_desc *desc; - struct flex_groups *flex_group = sbi->s_flex_groups; - ext4_group_t parent_group = EXT4_I(parent)->i_block_group; - ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); - ext4_group_t ngroups = ext4_get_groups_count(sb); - int flex_size = ext4_flex_bg_size(sbi); - ext4_group_t best_flex = parent_fbg_group; - int blocks_per_flex = sbi->s_blocks_per_group * flex_size; - int flexbg_free_clusters; - int flex_freeb_ratio; - ext4_group_t n_fbg_groups; - ext4_group_t i; - - n_fbg_groups = (ngroups + flex_size - 1) >> - sbi->s_log_groups_per_flex; - -find_close_to_parent: - flexbg_free_clusters = atomic_read(&flex_group[best_flex].free_clusters); - flex_freeb_ratio = EXT4_C2B(sbi, flexbg_free_clusters) * 100 / - blocks_per_flex; - if (atomic_read(&flex_group[best_flex].free_inodes) && - flex_freeb_ratio > free_block_ratio) - goto found_flexbg; - - if (best_flex && best_flex == parent_fbg_group) { - best_flex--; - goto find_close_to_parent; - } - - for (i = 0; i < n_fbg_groups; i++) { - if (i == parent_fbg_group || i == parent_fbg_group - 1) - continue; - - flexbg_free_clusters = atomic_read(&flex_group[i].free_clusters); - flex_freeb_ratio = EXT4_C2B(sbi, flexbg_free_clusters) * 100 / - blocks_per_flex; - - if (flex_freeb_ratio > free_block_ratio && - (atomic_read(&flex_group[i].free_inodes))) { - best_flex = i; - goto found_flexbg; - } - - if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) || - ((atomic_read(&flex_group[i].free_clusters) > - atomic_read(&flex_group[best_flex].free_clusters)) && - atomic_read(&flex_group[i].free_inodes))) - best_flex = i; - } - - if (!atomic_read(&flex_group[best_flex].free_inodes) || - !atomic_read(&flex_group[best_flex].free_clusters)) - return -1; - -found_flexbg: - for (i = best_flex * flex_size; i < ngroups && - i < (best_flex + 1) * flex_size; i++) { - desc = ext4_get_group_desc(sb, i, NULL); - if (ext4_free_inodes_count(sb, desc)) { - *best_group = i; - goto out; - } - } - - return -1; -out: - return 0; -} - struct orlov_stats { __u32 free_inodes; __u32 free_clusters; @@ -819,7 +705,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, int ret2, err = 0; struct inode *ret; ext4_group_t i; - static int once = 1; ext4_group_t flex_group; /* Cannot create files in a deleted directory */ @@ -845,26 +730,9 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, goto got_group; } - if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) { - ret2 = find_group_flex(sb, dir, &group); - if (ret2 == -1) { - ret2 = find_group_other(sb, dir, &group, mode); - if (ret2 == 0 && once) { - once = 0; - printk(KERN_NOTICE "ext4: find_group_flex " - "failed, fallback succeeded dir %lu\n", - dir->i_ino); - } - } - goto got_group; - } - - if (S_ISDIR(mode)) { - if (test_opt(sb, OLDALLOC)) - ret2 = find_group_dir(sb, dir, &group); - else - ret2 = find_group_orlov(sb, dir, &group, mode, qstr); - } else + if (S_ISDIR(mode)) + ret2 = find_group_orlov(sb, dir, &group, mode, qstr); + else ret2 = find_group_other(sb, dir, &group, mode); got_group: diff --git a/fs/ext4/super.c b/fs/ext4/super.c index db2cd3f21074..42f76c64df8c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1073,8 +1073,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",nouid32"); if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG)) seq_puts(seq, ",debug"); - if (test_opt(sb, OLDALLOC)) - seq_puts(seq, ",oldalloc"); #ifdef CONFIG_EXT4_FS_XATTR if (test_opt(sb, XATTR_USER)) seq_puts(seq, ",user_xattr"); @@ -1583,10 +1581,12 @@ static int parse_options(char *options, struct super_block *sb, set_opt(sb, DEBUG); break; case Opt_oldalloc: - set_opt(sb, OLDALLOC); + ext4_msg(sb, KERN_WARNING, + "Ignoring deprecated oldalloc option"); break; case Opt_orlov: - clear_opt(sb, OLDALLOC); + ext4_msg(sb, KERN_WARNING, + "Ignoring deprecated orlov option"); break; #ifdef CONFIG_EXT4_FS_XATTR case Opt_user_xattr: -- cgit v1.2.3 From 7fd59c83b05dc1b8af2be4d991ee376f782cd8b0 Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Sat, 8 Oct 2011 15:56:35 -0400 Subject: ext4: remove the obsolete/broken EXT4_IOC_WAIT_FOR_READONLY ioctl There are no users of the EXT4_IOC_WAIT_FOR_READONLY ioctl, and it is also broken. No one sets the set_ro_timer, no one wakes up us and our state is set to TASK_INTERRUPTIBLE not RUNNING. So remove it. Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 10 ---------- fs/ext4/ioctl.c | 28 ---------------------------- 2 files changed, 38 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 61b0b5cd4aa2..4546da4f26c4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -564,9 +564,6 @@ struct ext4_new_group_data { #define EXT4_IOC_SETVERSION _IOW('f', 4, long) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION #define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION -#ifdef CONFIG_JBD2_DEBUG -#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) -#endif #define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) #define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) #define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) @@ -589,9 +586,6 @@ struct ext4_new_group_data { #define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) #define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) #define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input) -#ifdef CONFIG_JBD2_DEBUG -#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) -#endif #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION #define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION #endif @@ -1171,10 +1165,6 @@ struct ext4_sb_info { u32 s_max_batch_time; u32 s_min_batch_time; struct block_device *journal_bdev; -#ifdef CONFIG_JBD2_DEBUG - struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ - wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ -#endif #ifdef CONFIG_QUOTA char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ int s_jquota_fmt; /* Format of quota to use */ diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2046d699b4a7..8f7ea6905421 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -174,29 +174,6 @@ setversion_out: mnt_drop_write(filp->f_path.mnt); return err; } -#ifdef CONFIG_JBD2_DEBUG - case EXT4_IOC_WAIT_FOR_READONLY: - /* - * This is racy - by the time we're woken up and running, - * the superblock could be released. And the module could - * have been unloaded. So sue me. - * - * Returns 1 if it slept, else zero. - */ - { - DECLARE_WAITQUEUE(wait, current); - int ret = 0; - - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait); - if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) { - schedule(); - ret = 1; - } - remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait); - return ret; - } -#endif case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; int err, err2=0; @@ -421,11 +398,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC32_SETVERSION_OLD: cmd = EXT4_IOC_SETVERSION_OLD; break; -#ifdef CONFIG_JBD2_DEBUG - case EXT4_IOC32_WAIT_FOR_READONLY: - cmd = EXT4_IOC_WAIT_FOR_READONLY; - break; -#endif case EXT4_IOC32_GETRSVSZ: cmd = EXT4_IOC_GETRSVSZ; break; -- cgit v1.2.3 From a4e5d88b1b24827f4f6a3cba43228936a67d81ba Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Tue, 25 Oct 2011 08:15:12 -0400 Subject: ext4: update EOFBLOCKS flag on fallocate properly EOFBLOCK_FL should be updated if called w/o FALLOCATE_FL_KEEP_SIZE Currently it happens only if new extent was allocated. TESTCASE: fallocate test_file -n -l4096 fallocate test_file -l4096 Last fallocate cmd has updated size, but keept EOFBLOCK_FL set. And fsck will complain about that. Also remove ping pong in ext4_fallocate() in case of new extents, where ext4_ext_map_blocks() clear EOFBLOCKS bit, and later ext4_falloc_update_inode() restore it again. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ fs/ext4/extents.c | 28 +++++++++++++++++----------- fs/ext4/inode.c | 6 ++++-- 3 files changed, 23 insertions(+), 13 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4546da4f26c4..3647ae0b21ab 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -539,6 +539,8 @@ struct ext4_new_group_data { #define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 + /* Request will not result in inode size update (user for fallocate) */ +#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 /* * Flags used by ext4_free_blocks diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d0e3f333d3f0..8686eb756b38 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3432,14 +3432,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, /* buffered write, writepage time, convert*/ ret = ext4_ext_convert_to_initialized(handle, inode, map, path); - if (ret >= 0) { + if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, - map->m_len); - if (err < 0) - goto out2; - } - out: if (ret <= 0) { err = ret; @@ -3480,6 +3474,12 @@ out: map_out: map->m_flags |= EXT4_MAP_MAPPED; + if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) { + err = check_eofblocks_fl(handle, inode, map->m_lblk, path, + map->m_len); + if (err < 0) + goto out2; + } out1: if (allocated > map->m_len) allocated = map->m_len; @@ -3955,7 +3955,10 @@ got_allocated_blocks: map->m_flags |= EXT4_MAP_UNINIT; } - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len); + err = 0; + if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) + err = check_eofblocks_fl(handle, inode, map->m_lblk, + path, ar.len); if (!err) err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); @@ -4214,6 +4217,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) int ret = 0; int ret2 = 0; int retries = 0; + int flags; struct ext4_map_blocks map; unsigned int credits, blkbits = inode->i_blkbits; @@ -4250,6 +4254,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); return ret; } + flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT | + EXT4_GET_BLOCKS_NO_NORMALIZE; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; retry: while (ret >= 0 && ret < max_blocks) { map.m_lblk = map.m_lblk + ret; @@ -4259,9 +4267,7 @@ retry: ret = PTR_ERR(handle); break; } - ret = ext4_map_blocks(handle, inode, &map, - EXT4_GET_BLOCKS_CREATE_UNINIT_EXT | - EXT4_GET_BLOCKS_NO_NORMALIZE); + ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ff6aace0bb3c..87ec615f0fd6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -477,9 +477,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, */ down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, 0); + retval = ext4_ext_map_blocks(handle, inode, map, flags & + EXT4_GET_BLOCKS_KEEP_SIZE); } else { - retval = ext4_ind_map_blocks(handle, inode, map, 0); + retval = ext4_ind_map_blocks(handle, inode, map, flags & + EXT4_GET_BLOCKS_KEEP_SIZE); } up_read((&EXT4_I(inode)->i_data_sem)); -- cgit v1.2.3 From 5cb81dabcc28863e7d04e6fd9ede154bd8459c14 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Oct 2011 09:05:00 -0400 Subject: ext4: fix quota accounting during migration The tmp_inode should have same uid/gid as the original inode. Otherwise new metadata blocks will be accounted to wrong quota-id, which will result in a quota leak after the inode migration is completed. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 ++- fs/ext4/ialloc.c | 9 ++++++--- fs/ext4/migrate.c | 7 +++++-- fs/ext4/namei.c | 8 ++++---- 4 files changed, 17 insertions(+), 10 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3647ae0b21ab..657e82649fa5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1811,7 +1811,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct /* ialloc.c */ extern struct inode *ext4_new_inode(handle_t *, struct inode *, int, - const struct qstr *qstr, __u32 goal); + const struct qstr *qstr, __u32 goal, + uid_t *owner); extern void ext4_free_inode(handle_t *, struct inode *); extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index e007fecdaedc..acdde93b74d7 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -691,7 +691,7 @@ err_ret: * group to find a free inode. */ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, - const struct qstr *qstr, __u32 goal) + const struct qstr *qstr, __u32 goal, uid_t *owner) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; @@ -852,8 +852,11 @@ got: flex_group = ext4_flex_group(sbi, group); atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); } - - if (test_opt(sb, GRPID)) { + if (owner) { + inode->i_mode = mode; + inode->i_uid = owner[0]; + inode->i_gid = owner[1]; + } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 8a9a0912fdae..f729377bf043 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -439,6 +439,7 @@ int ext4_ext_migrate(struct inode *inode) struct migrate_struct lb; unsigned long max_entries; __u32 goal; + uid_t owner[2]; /* * If the filesystem does not support extents, or the inode @@ -466,10 +467,12 @@ int ext4_ext_migrate(struct inode *inode) } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; + owner[0] = inode->i_uid; + owner[1] = inode->i_gid; tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, - S_IFREG, NULL, goal); + S_IFREG, NULL, goal, owner); if (IS_ERR(tmp_inode)) { - retval = -ENOMEM; + retval = PTR_ERR(inode); ext4_journal_stop(handle); return retval; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 4a550aa07614..f73d582e89f9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1754,7 +1754,7 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0); + inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL); err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; @@ -1790,7 +1790,7 @@ retry: if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0); + inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL); err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); @@ -1830,7 +1830,7 @@ retry: ext4_handle_sync(handle); inode = ext4_new_inode(handle, dir, S_IFDIR | mode, - &dentry->d_name, 0); + &dentry->d_name, 0, NULL); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_stop; @@ -2277,7 +2277,7 @@ retry: ext4_handle_sync(handle); inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO, - &dentry->d_name, 0); + &dentry->d_name, 0, NULL); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_stop; -- cgit v1.2.3 From 0edeb71dc9133bfb505d3bf59642e07cd936613e Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Mon, 31 Oct 2011 17:30:44 -0400 Subject: ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten EXT4_IO_END_UNWRITTEN flag set and the increase of i_aiodio_unwritten should be done simultaneously since ext4_end_io_nolock always clear the flag and decrease the counter in the same time. We have found some bugs that the flag is set while leaving i_aiodio_unwritten unchanged(commit 32c80b32c053d). So this patch just tries to create a helper function to wrap them to avoid any future bug. The idea is inspired by Eric. Cc: Eric Sandeen Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 9 +++++++++ fs/ext4/extents.c | 18 ++++++------------ fs/ext4/inode.c | 5 +---- fs/ext4/page-io.c | 6 ++---- 4 files changed, 18 insertions(+), 20 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 657e82649fa5..604c200216c1 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1275,6 +1275,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } +static inline void ext4_set_io_unwritten_flag(struct inode *inode, + struct ext4_io_end *io_end) +{ + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } +} + /* * Inode dynamic state flags */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 36a0f177ecad..a5c8caaaa099 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3472,12 +3472,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, * that this IO needs to conversion to written when IO is * completed */ - if (io) { - if (!(io->flag & EXT4_IO_END_UNWRITTEN)) { - io->flag = EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } - } else + if (io) + ext4_set_io_unwritten_flag(inode, io); + else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; @@ -4030,12 +4027,9 @@ got_allocated_blocks: * that we need to perform conversion when IO is done. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) { - if (!(io->flag & EXT4_IO_END_UNWRITTEN)) { - io->flag = EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } - } else + if (io) + ext4_set_io_unwritten_flag(inode, io); + else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e4b26faac5ff..60af5126eb05 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2831,10 +2831,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) * but being more careful is always safe for the future change. */ inode = io_end->inode; - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } + ext4_set_io_unwritten_flag(inode, io_end); /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9eebf44646f6..7ce1d0b19c94 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -336,10 +336,8 @@ submit_and_retry: if ((io_end->num_io_pages >= MAX_IO_PAGES) && (io_end->pages[io_end->num_io_pages-1] != io_page)) goto submit_and_retry; - if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } + if (buffer_uninit(bh)) + ext4_set_io_unwritten_flag(inode, io_end); io->io_end->size += bh->b_size; io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); -- cgit v1.2.3