diff options
author | Steve French <sfrench@us.ibm.com> | 2008-03-01 18:29:55 +0000 |
---|---|---|
committer | Steve French <sfrench@us.ibm.com> | 2008-03-01 18:29:55 +0000 |
commit | 0dbd888936a23514716b8d944775bc56f731363a (patch) | |
tree | a2c60cdc45bdcbed47680731fa8188bffe58c098 /fs | |
parent | 0b442d2c28479332610c46e1a74e5638ab63a97d (diff) | |
parent | d395991c117d43bfca97101a931a41d062a93852 (diff) | |
download | op-kernel-dev-0dbd888936a23514716b8d944775bc56f731363a.zip op-kernel-dev-0dbd888936a23514716b8d944775bc56f731363a.tar.gz |
Merge branch 'master' of /pub/scm/linux/kernel/git/torvalds/linux-2.6
Diffstat (limited to 'fs')
40 files changed, 606 insertions, 468 deletions
@@ -903,7 +903,7 @@ void bio_set_pages_dirty(struct bio *bio) } } -void bio_release_pages(struct bio *bio) +static void bio_release_pages(struct bio *bio) { struct bio_vec *bvec = bio->bi_io_vec; int i; diff --git a/fs/block_dev.c b/fs/block_dev.c index 67fe72c..7d822fa 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -31,6 +31,8 @@ struct bdev_inode { struct inode vfs_inode; }; +static const struct address_space_operations def_blk_aops; + static inline struct bdev_inode *BDEV_I(struct inode *inode) { return container_of(inode, struct bdev_inode, vfs_inode); @@ -171,203 +173,6 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, iov, offset, nr_segs, blkdev_get_blocks, NULL); } -#if 0 -static void blk_end_aio(struct bio *bio, int error) -{ - struct kiocb *iocb = bio->bi_private; - atomic_t *bio_count = &iocb->ki_bio_count; - - if (bio_data_dir(bio) == READ) - bio_check_pages_dirty(bio); - else { - bio_release_pages(bio); - bio_put(bio); - } - - /* iocb->ki_nbytes stores error code from LLDD */ - if (error) - iocb->ki_nbytes = -EIO; - - if (atomic_dec_and_test(bio_count)) { - if ((long)iocb->ki_nbytes < 0) - aio_complete(iocb, iocb->ki_nbytes, 0); - else - aio_complete(iocb, iocb->ki_left, 0); - } - - return 0; -} - -#define VEC_SIZE 16 -struct pvec { - unsigned short nr; - unsigned short idx; - struct page *page[VEC_SIZE]; -}; - -#define PAGES_SPANNED(addr, len) \ - (DIV_ROUND_UP((addr) + (len), PAGE_SIZE) - (addr) / PAGE_SIZE); - -/* - * get page pointer for user addr, we internally cache struct page array for - * (addr, count) range in pvec to avoid frequent call to get_user_pages. If - * internal page list is exhausted, a batch count of up to VEC_SIZE is used - * to get next set of page struct. - */ -static struct page *blk_get_page(unsigned long addr, size_t count, int rw, - struct pvec *pvec) -{ - int ret, nr_pages; - if (pvec->idx == pvec->nr) { - nr_pages = PAGES_SPANNED(addr, count); - nr_pages = min(nr_pages, VEC_SIZE); - down_read(¤t->mm->mmap_sem); - ret = get_user_pages(current, current->mm, addr, nr_pages, - rw == READ, 0, pvec->page, NULL); - up_read(¤t->mm->mmap_sem); - if (ret < 0) - return ERR_PTR(ret); - pvec->nr = ret; - pvec->idx = 0; - } - return pvec->page[pvec->idx++]; -} - -/* return a page back to pvec array */ -static void blk_unget_page(struct page *page, struct pvec *pvec) -{ - pvec->page[--pvec->idx] = page; -} - -static ssize_t -blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t pos, unsigned long nr_segs) -{ - struct inode *inode = iocb->ki_filp->f_mapping->host; - unsigned blkbits = blksize_bits(bdev_hardsect_size(I_BDEV(inode))); - unsigned blocksize_mask = (1 << blkbits) - 1; - unsigned long seg = 0; /* iov segment iterator */ - unsigned long nvec; /* number of bio vec needed */ - unsigned long cur_off; /* offset into current page */ - unsigned long cur_len; /* I/O len of current page, up to PAGE_SIZE */ - - unsigned long addr; /* user iovec address */ - size_t count; /* user iovec len */ - size_t nbytes = iocb->ki_nbytes = iocb->ki_left; /* total xfer size */ - loff_t size; /* size of block device */ - struct bio *bio; - atomic_t *bio_count = &iocb->ki_bio_count; - struct page *page; - struct pvec pvec; - - pvec.nr = 0; - pvec.idx = 0; - - if (pos & blocksize_mask) - return -EINVAL; - - size = i_size_read(inode); - if (pos + nbytes > size) { - nbytes = size - pos; - iocb->ki_left = nbytes; - } - - /* - * check first non-zero iov alignment, the remaining - * iov alignment is checked inside bio loop below. - */ - do { - addr = (unsigned long) iov[seg].iov_base; - count = min(iov[seg].iov_len, nbytes); - if (addr & blocksize_mask || count & blocksize_mask) - return -EINVAL; - } while (!count && ++seg < nr_segs); - atomic_set(bio_count, 1); - - while (nbytes) { - /* roughly estimate number of bio vec needed */ - nvec = (nbytes + PAGE_SIZE - 1) / PAGE_SIZE; - nvec = max(nvec, nr_segs - seg); - nvec = min(nvec, (unsigned long) BIO_MAX_PAGES); - - /* bio_alloc should not fail with GFP_KERNEL flag */ - bio = bio_alloc(GFP_KERNEL, nvec); - bio->bi_bdev = I_BDEV(inode); - bio->bi_end_io = blk_end_aio; - bio->bi_private = iocb; - bio->bi_sector = pos >> blkbits; -same_bio: - cur_off = addr & ~PAGE_MASK; - cur_len = PAGE_SIZE - cur_off; - if (count < cur_len) - cur_len = count; - - page = blk_get_page(addr, count, rw, &pvec); - if (unlikely(IS_ERR(page))) - goto backout; - - if (bio_add_page(bio, page, cur_len, cur_off)) { - pos += cur_len; - addr += cur_len; - count -= cur_len; - nbytes -= cur_len; - - if (count) - goto same_bio; - while (++seg < nr_segs) { - addr = (unsigned long) iov[seg].iov_base; - count = iov[seg].iov_len; - if (!count) - continue; - if (unlikely(addr & blocksize_mask || - count & blocksize_mask)) { - page = ERR_PTR(-EINVAL); - goto backout; - } - count = min(count, nbytes); - goto same_bio; - } - } else { - blk_unget_page(page, &pvec); - } - - /* bio is ready, submit it */ - if (rw == READ) - bio_set_pages_dirty(bio); - atomic_inc(bio_count); - submit_bio(rw, bio); - } - -completion: - iocb->ki_left -= nbytes; - nbytes = iocb->ki_left; - iocb->ki_pos += nbytes; - - blk_run_address_space(inode->i_mapping); - if (atomic_dec_and_test(bio_count)) - aio_complete(iocb, nbytes, 0); - - return -EIOCBQUEUED; - -backout: - /* - * back out nbytes count constructed so far for this bio, - * we will throw away current bio. - */ - nbytes += bio->bi_size; - bio_release_pages(bio); - bio_put(bio); - - /* - * if no bio was submmitted, return the error code. - * otherwise, proceed with pending I/O completion. - */ - if (atomic_read(bio_count) == 1) - return PTR_ERR(page); - goto completion; -} -#endif - static int blkdev_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, blkdev_get_block, wbc); @@ -1334,7 +1139,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); } -const struct address_space_operations def_blk_aops = { +static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .writepage = blkdev_writepage, .sync_page = block_sync_page, diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index 035e6f9..67522c2 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -215,6 +215,8 @@ int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len) ls->ls_recover_nodeid = nodeid; if (nodeid == dlm_our_nodeid()) { + ls->ls_recover_buf->rc_header.h_length = + dlm_config.ci_buffer_size; dlm_copy_master_names(ls, last_name, last_len, ls->ls_recover_buf->rc_buf, max_size, nodeid); diff --git a/fs/efs/dir.c b/fs/efs/dir.c index dfb5cb4..49308a2 100644 --- a/fs/efs/dir.c +++ b/fs/efs/dir.c @@ -5,8 +5,8 @@ */ #include <linux/buffer_head.h> -#include <linux/efs_fs.h> #include <linux/smp_lock.h> +#include "efs.h" static int efs_readdir(struct file *, void *, filldir_t); diff --git a/fs/efs/efs.h b/fs/efs/efs.h new file mode 100644 index 0000000..d8305b5 --- /dev/null +++ b/fs/efs/efs.h @@ -0,0 +1,140 @@ +/* + * Copyright (c) 1999 Al Smith + * + * Portions derived from work (c) 1995,1996 Christian Vogelgsang. + * Portions derived from IRIX header files (c) 1988 Silicon Graphics + */ +#ifndef _EFS_EFS_H_ +#define _EFS_EFS_H_ + +#include <linux/fs.h> +#include <asm/uaccess.h> + +#define EFS_VERSION "1.0a" + +static const char cprt[] = "EFS: "EFS_VERSION" - (c) 1999 Al Smith <Al.Smith@aeschi.ch.eu.org>"; + + +/* 1 block is 512 bytes */ +#define EFS_BLOCKSIZE_BITS 9 +#define EFS_BLOCKSIZE (1 << EFS_BLOCKSIZE_BITS) + +typedef int32_t efs_block_t; +typedef uint32_t efs_ino_t; + +#define EFS_DIRECTEXTENTS 12 + +/* + * layout of an extent, in memory and on disk. 8 bytes exactly. + */ +typedef union extent_u { + unsigned char raw[8]; + struct extent_s { + unsigned int ex_magic:8; /* magic # (zero) */ + unsigned int ex_bn:24; /* basic block */ + unsigned int ex_length:8; /* numblocks in this extent */ + unsigned int ex_offset:24; /* logical offset into file */ + } cooked; +} efs_extent; + +typedef struct edevs { + __be16 odev; + __be32 ndev; +} efs_devs; + +/* + * extent based filesystem inode as it appears on disk. The efs inode + * is exactly 128 bytes long. + */ +struct efs_dinode { + __be16 di_mode; /* mode and type of file */ + __be16 di_nlink; /* number of links to file */ + __be16 di_uid; /* owner's user id */ + __be16 di_gid; /* owner's group id */ + __be32 di_size; /* number of bytes in file */ + __be32 di_atime; /* time last accessed */ + __be32 di_mtime; /* time last modified */ + __be32 di_ctime; /* time created */ + __be32 di_gen; /* generation number */ + __be16 di_numextents; /* # of extents */ + u_char di_version; /* version of inode */ + u_char di_spare; /* spare - used by AFS */ + union di_addr { + efs_extent di_extents[EFS_DIRECTEXTENTS]; + efs_devs di_dev; /* device for IFCHR/IFBLK */ + } di_u; +}; + +/* efs inode storage in memory */ +struct efs_inode_info { + int numextents; + int lastextent; + + efs_extent extents[EFS_DIRECTEXTENTS]; + struct inode vfs_inode; +}; + +#include <linux/efs_fs_sb.h> + +#define EFS_DIRBSIZE_BITS EFS_BLOCKSIZE_BITS +#define EFS_DIRBSIZE (1 << EFS_DIRBSIZE_BITS) + +struct efs_dentry { + __be32 inode; + unsigned char namelen; + char name[3]; +}; + +#define EFS_DENTSIZE (sizeof(struct efs_dentry) - 3 + 1) +#define EFS_MAXNAMELEN ((1 << (sizeof(char) * 8)) - 1) + +#define EFS_DIRBLK_HEADERSIZE 4 +#define EFS_DIRBLK_MAGIC 0xbeef /* moo */ + +struct efs_dir { + __be16 magic; + unsigned char firstused; + unsigned char slots; + + unsigned char space[EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE]; +}; + +#define EFS_MAXENTS \ + ((EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE) / \ + (EFS_DENTSIZE + sizeof(char))) + +#define EFS_SLOTAT(dir, slot) EFS_REALOFF((dir)->space[slot]) + +#define EFS_REALOFF(offset) ((offset << 1)) + + +static inline struct efs_inode_info *INODE_INFO(struct inode *inode) +{ + return container_of(inode, struct efs_inode_info, vfs_inode); +} + +static inline struct efs_sb_info *SUPER_INFO(struct super_block *sb) +{ + return sb->s_fs_info; +} + +struct statfs; +struct fid; + +extern const struct inode_operations efs_dir_inode_operations; +extern const struct file_operations efs_dir_operations; +extern const struct address_space_operations efs_symlink_aops; + +extern struct inode *efs_iget(struct super_block *, unsigned long); +extern efs_block_t efs_map_block(struct inode *, efs_block_t); +extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int); + +extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +extern struct dentry *efs_get_parent(struct dentry *); +extern int efs_bmap(struct inode *, int); + +#endif /* _EFS_EFS_H_ */ diff --git a/fs/efs/file.c b/fs/efs/file.c index 5db2012..1ccb364 100644 --- a/fs/efs/file.c +++ b/fs/efs/file.c @@ -7,7 +7,7 @@ */ #include <linux/buffer_head.h> -#include <linux/efs_fs.h> +#include "efs.h" int efs_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 627c302..79e19e5 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -7,11 +7,11 @@ * and from work (c) 1998 Mike Shaver. */ -#include <linux/efs_fs.h> -#include <linux/efs_fs_sb.h> #include <linux/buffer_head.h> #include <linux/module.h> #include <linux/fs.h> +#include "efs.h" +#include <linux/efs_fs_sb.h> static int efs_readpage(struct file *file, struct page *page) { diff --git a/fs/efs/namei.c b/fs/efs/namei.c index e267047..3a404e7 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -8,9 +8,9 @@ #include <linux/buffer_head.h> #include <linux/string.h> -#include <linux/efs_fs.h> #include <linux/smp_lock.h> #include <linux/exportfs.h> +#include "efs.h" static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) { diff --git a/fs/efs/super.c b/fs/efs/super.c index 1408240..d733531 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -8,14 +8,15 @@ #include <linux/init.h> #include <linux/module.h> -#include <linux/efs_fs.h> -#include <linux/efs_vh.h> -#include <linux/efs_fs_sb.h> #include <linux/exportfs.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> +#include "efs.h" +#include <linux/efs_vh.h> +#include <linux/efs_fs_sb.h> + static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); static int efs_fill_super(struct super_block *s, void *d, int silent); diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index 1d30d2f..41911ec 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -7,10 +7,10 @@ */ #include <linux/string.h> -#include <linux/efs_fs.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/smp_lock.h> +#include "efs.h" static int efs_symlink_readpage(struct file *file, struct page *page) { diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 33888bb..2c23bad 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -46,7 +46,7 @@ const struct file_operations ext4_dir_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif - .fsync = ext4_sync_file, /* BKL held */ + .fsync = ext4_sync_file, .release = ext4_release_dir, }; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bc7081f..9ae6e67 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -148,6 +148,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, { struct ext4_inode_info *ei = EXT4_I(inode); ext4_fsblk_t bg_start; + ext4_fsblk_t last_block; ext4_grpblk_t colour; int depth; @@ -169,8 +170,13 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, /* OK. use inode's group */ bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) + le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block); - colour = (current->pid % 16) * + last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; + + if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) + colour = (current->pid % 16) * (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + else + colour = (current->pid % 16) * ((last_block - bg_start) / 16); return bg_start + colour + block; } @@ -349,7 +355,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) #define ext4_ext_show_leaf(inode,path) #endif -static void ext4_ext_drop_refs(struct ext4_ext_path *path) +void ext4_ext_drop_refs(struct ext4_ext_path *path) { int depth = path->p_depth; int i; @@ -2168,6 +2174,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, newblock = iblock - ee_block + ext_pblock(ex); ex2 = ex; + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + /* ex1: ee_block to iblock - 1 : uninitialized */ if (iblock > ee_block) { ex1 = ex; @@ -2200,16 +2210,20 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, newdepth = ext_depth(inode); if (newdepth != depth) { depth = newdepth; - path = ext4_ext_find_extent(inode, iblock, NULL); + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, iblock, path); if (IS_ERR(path)) { err = PTR_ERR(path); - path = NULL; goto out; } eh = path[depth].p_hdr; ex = path[depth].p_ext; if (ex2 != &newex) ex2 = ex; + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; } allocated = max_blocks; } @@ -2230,9 +2244,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ex2->ee_len = cpu_to_le16(allocated); if (ex2 != ex) goto insert; - err = ext4_ext_get_access(handle, inode, path + depth); - if (err) - goto out; /* * New (initialized) extent starts from the first block * in the current extent. i.e., ex2 == ex @@ -2276,9 +2287,22 @@ out: } /* + * Block allocation/map/preallocation routine for extents based files + * + * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) + * + * return > 0, number of of blocks already mapped/allocated + * if create == 0 and these are pre-allocated blocks + * buffer head is unmapped + * otherwise blocks are mapped + * + * return = 0, if plain look up failed (blocks have not been allocated) + * buffer head is unmapped + * + * return < 0, error case. */ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, @@ -2623,7 +2647,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) * modify 1 super block, 1 block bitmap and 1 group descriptor. */ credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3; - down_write((&EXT4_I(inode)->i_data_sem)); + mutex_lock(&inode->i_mutex); retry: while (ret >= 0 && ret < max_blocks) { block = block + ret; @@ -2634,16 +2658,17 @@ retry: break; } - ret = ext4_ext_get_blocks(handle, inode, block, + ret = ext4_get_blocks_wrap(handle, inode, block, max_blocks, &map_bh, EXT4_CREATE_UNINITIALIZED_EXT, 0); - WARN_ON(ret <= 0); if (ret <= 0) { - ext4_error(inode->i_sb, "ext4_fallocate", - "ext4_ext_get_blocks returned error: " - "inode#%lu, block=%u, max_blocks=%lu", +#ifdef EXT4FS_DEBUG + WARN_ON(ret <= 0); + printk(KERN_ERR "%s: ext4_ext_get_blocks " + "returned error inode#%lu, block=%u, " + "max_blocks=%lu", __func__, inode->i_ino, block, max_blocks); - ret = -EIO; +#endif ext4_mark_inode_dirty(handle, inode); ret2 = ext4_journal_stop(handle); break; @@ -2680,7 +2705,6 @@ retry: if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; - up_write((&EXT4_I(inode)->i_data_sem)); /* * Time to update the file size. * Update only when preallocation was requested beyond the file size. @@ -2692,21 +2716,18 @@ retry: * if no error, we assume preallocation succeeded * completely */ - mutex_lock(&inode->i_mutex); i_size_write(inode, offset + len); EXT4_I(inode)->i_disksize = i_size_read(inode); - mutex_unlock(&inode->i_mutex); } else if (ret < 0 && nblocks) { /* Handle partial allocation scenario */ loff_t newsize; - mutex_lock(&inode->i_mutex); newsize = (nblocks << blkbits) + i_size_read(inode); i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits)); EXT4_I(inode)->i_disksize = i_size_read(inode); - mutex_unlock(&inode->i_mutex); } } + mutex_unlock(&inode->i_mutex); return ret > 0 ? ret2 : ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index da18a74..8036b9b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -702,7 +702,12 @@ got: ei->i_dir_start_lookup = 0; ei->i_disksize = 0; - ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL; + /* + * Don't inherit extent flag from directory. We set extent flag on + * newly created directory and file only if -o extent mount option is + * specified + */ + ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL); if (S_ISLNK(mode)) ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL); /* dirsync only applies to directories */ @@ -745,12 +750,15 @@ got: goto fail_free_drop; } if (test_opt(sb, EXTENTS)) { - EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; - ext4_ext_tree_init(handle, inode); - err = ext4_update_incompat_feature(handle, sb, - EXT4_FEATURE_INCOMPAT_EXTENTS); - if (err) - goto fail; + /* set extent flag only for directory and file */ + if (S_ISDIR(mode) || S_ISREG(mode)) { + EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; + ext4_ext_tree_init(handle, inode); + err = ext4_update_incompat_feature(handle, sb, + EXT4_FEATURE_INCOMPAT_EXTENTS); + if (err) + goto fail; + } } ext4_debug("allocating inode %lu\n", inode->i_ino); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7dd9b50..945cbf6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -403,6 +403,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data; __le32 *p; ext4_fsblk_t bg_start; + ext4_fsblk_t last_block; ext4_grpblk_t colour; /* Try to find previous block */ @@ -420,8 +421,13 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * into the same cylinder group then. */ bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group); - colour = (current->pid % 16) * + last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; + + if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) + colour = (current->pid % 16) * (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + else + colour = (current->pid % 16) * ((last_block - bg_start) / 16); return bg_start + colour; } @@ -768,7 +774,6 @@ err_out: * * `handle' can be NULL if create == 0. * - * The BKL may not be held on entry here. Be sure to take it early. * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. @@ -903,11 +908,38 @@ out: */ #define DIO_CREDITS 25 + +/* + * + * + * ext4_ext4 get_block() wrapper function + * It will do a look up first, and returns if the blocks already mapped. + * Otherwise it takes the write lock of the i_data_sem and allocate blocks + * and store the allocated blocks in the result buffer head and mark it + * mapped. + * + * If file type is extents based, it will call ext4_ext_get_blocks(), + * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping + * based files + * + * On success, it returns the number of blocks being mapped or allocate. + * if create==0 and the blocks are pre-allocated and uninitialized block, + * the result buffer head is unmapped. If the create ==1, it will make sure + * the buffer head is mapped. + * + * It returns 0 if plain look up failed (blocks have not been allocated), in + * that casem, buffer head is unmapped + * + * It returns the error in case of allocation failure. + */ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, int create, int extend_disksize) { int retval; + + clear_buffer_mapped(bh); + /* * Try to see if we can get the block without requesting * for new file system block. @@ -921,12 +953,26 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, inode, block, max_blocks, bh, 0, 0); } up_read((&EXT4_I(inode)->i_data_sem)); - if (!create || (retval > 0)) + + /* If it is only a block(s) look up */ + if (!create) + return retval; + + /* + * Returns if the blocks have already allocated + * + * Note that if blocks have been preallocated + * ext4_ext_get_block() returns th create = 0 + * with buffer head unmapped. + */ + if (retval > 0 && buffer_mapped(bh)) return retval; /* - * We need to allocate new blocks which will result - * in i_data update + * New blocks allocate and/or writing to uninitialized extent + * will possibly result in updating i_data, so we take + * the write lock of i_data_sem, and call get_blocks() + * with create == 1 flag. */ down_write((&EXT4_I(inode)->i_data_sem)); /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index dd0fcfc..ef97f19 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -627,21 +627,19 @@ static ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb, return block; } +static inline void *mb_correct_addr_and_bit(int *bit, void *addr) +{ #if BITS_PER_LONG == 64 -#define mb_correct_addr_and_bit(bit, addr) \ -{ \ - bit += ((unsigned long) addr & 7UL) << 3; \ - addr = (void *) ((unsigned long) addr & ~7UL); \ -} + *bit += ((unsigned long) addr & 7UL) << 3; + addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 -#define mb_correct_addr_and_bit(bit, addr) \ -{ \ - bit += ((unsigned long) addr & 3UL) << 3; \ - addr = (void *) ((unsigned long) addr & ~3UL); \ -} + *bit += ((unsigned long) addr & 3UL) << 3; + addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif + return addr; +} static inline int mb_test_bit(int bit, void *addr) { @@ -649,34 +647,54 @@ static inline int mb_test_bit(int bit, void *addr) * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ - mb_correct_addr_and_bit(bit, addr); + addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { - mb_correct_addr_and_bit(bit, addr); + addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr) { - mb_correct_addr_and_bit(bit, addr); + addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit_atomic(lock, bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { - mb_correct_addr_and_bit(bit, addr); + addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr) { - mb_correct_addr_and_bit(bit, addr); + addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit_atomic(lock, bit, addr); } +static inline int mb_find_next_zero_bit(void *addr, int max, int start) +{ + int fix = 0; + addr = mb_correct_addr_and_bit(&fix, addr); + max += fix; + start += fix; + + return ext4_find_next_zero_bit(addr, max, start) - fix; +} + +static inline int mb_find_next_bit(void *addr, int max, int start) +{ + int fix = 0; + addr = mb_correct_addr_and_bit(&fix, addr); + max += fix; + start += fix; + + return ext4_find_next_bit(addr, max, start) - fix; +} + static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; @@ -906,7 +924,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, unsigned short chunk; unsigned short border; - BUG_ON(len >= EXT4_BLOCKS_PER_GROUP(sb)); + BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; @@ -946,12 +964,12 @@ static void ext4_mb_generate_buddy(struct super_block *sb, /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ - i = ext4_find_next_zero_bit(bitmap, max, 0); + i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; - i = ext4_find_next_bit(bitmap, max, i); + i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) @@ -959,7 +977,7 @@ static void ext4_mb_generate_buddy(struct super_block *sb, else grp->bb_counters[0]++; if (i < max) - i = ext4_find_next_zero_bit(bitmap, max, i); + i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; @@ -967,6 +985,10 @@ static void ext4_mb_generate_buddy(struct super_block *sb, ext4_error(sb, __FUNCTION__, "EXT4-fs: group %lu: %u blocks in bitmap, %u in gd\n", group, free, grp->bb_free); + /* + * If we intent to continue, we consider group descritor + * corrupt and update bb_free using bitmap value + */ grp->bb_free = free; } @@ -1778,7 +1800,7 @@ static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, buddy = mb_find_buddy(e4b, i, &max); BUG_ON(buddy == NULL); - k = ext4_find_next_zero_bit(buddy, max, 0); + k = mb_find_next_zero_bit(buddy, max, 0); BUG_ON(k >= max); ac->ac_found++; @@ -1818,11 +1840,11 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { - i = ext4_find_next_zero_bit(bitmap, + i = mb_find_next_zero_bit(bitmap, EXT4_BLOCKS_PER_GROUP(sb), i); if (i >= EXT4_BLOCKS_PER_GROUP(sb)) { /* - * IF we corrupt the bitmap we won't find any + * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * we have free blocks */ @@ -1838,6 +1860,12 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, ext4_error(sb, __FUNCTION__, "%d free blocks as per " "group info. But got %d blocks\n", free, ex.fe_len); + /* + * The number of free blocks differs. This mostly + * indicate that the bitmap is corrupt. So exit + * without claiming the space. + */ + break; } ext4_mb_measure_extent(ac, &ex, e4b); @@ -3740,10 +3768,10 @@ static int ext4_mb_release_inode_pa(struct ext4_buddy *e4b, } while (bit < end) { - bit = ext4_find_next_zero_bit(bitmap_bh->b_data, end, bit); + bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; - next = ext4_find_next_bit(bitmap_bh->b_data, end, bit); + next = mb_find_next_bit(bitmap_bh->b_data, end, bit); if (next > end) next = end; start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit + @@ -3771,6 +3799,10 @@ static int ext4_mb_release_inode_pa(struct ext4_buddy *e4b, (unsigned long) pa->pa_len); ext4_error(sb, __FUNCTION__, "free %u, pa_free %u\n", free, pa->pa_free); + /* + * pa is already deleted so we use the value obtained + * from the bitmap and continue. + */ } atomic_add(free, &sbi->s_mb_discarded); if (ac) diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 8c6c685..5c1e27d 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -43,6 +43,7 @@ static int finish_range(handle_t *handle, struct inode *inode, if (IS_ERR(path)) { retval = PTR_ERR(path); + path = NULL; goto err_out; } @@ -74,6 +75,10 @@ static int finish_range(handle_t *handle, struct inode *inode, } retval = ext4_ext_insert_extent(handle, inode, path, &newext); err_out: + if (path) { + ext4_ext_drop_refs(path); + kfree(path); + } lb->first_pblock = 0; return retval; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a9347fb..28aa2ed 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1804,12 +1804,8 @@ retry: inode->i_fop = &ext4_dir_operations; inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; dir_block = ext4_bread (handle, inode, 0, 1, &err); - if (!dir_block) { - ext4_dec_count(handle, inode); /* is this nlink == 0? */ - ext4_mark_inode_dirty(handle, inode); - iput (inode); - goto out_stop; - } + if (!dir_block) + goto out_clear_inode; BUFFER_TRACE(dir_block, "get_write_access"); ext4_journal_get_write_access(handle, dir_block); de = (struct ext4_dir_entry_2 *) dir_block->b_data; @@ -1832,7 +1828,8 @@ retry: ext4_mark_inode_dirty(handle, inode); err = ext4_add_entry (handle, dentry, inode); if (err) { - inode->i_nlink = 0; +out_clear_inode: + clear_nlink(inode); ext4_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -2164,7 +2161,7 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry) dir->i_ctime = dir->i_mtime = ext4_current_time(dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); - ext4_dec_count(handle, inode); + drop_nlink(inode); if (!inode->i_nlink) ext4_orphan_add(handle, inode); inode->i_ctime = ext4_current_time(inode); @@ -2214,7 +2211,7 @@ retry: err = __page_symlink(inode, symname, l, mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); if (err) { - ext4_dec_count(handle, inode); + clear_nlink(inode); ext4_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -2223,7 +2220,6 @@ retry: inode->i_op = &ext4_fast_symlink_inode_operations; memcpy((char*)&EXT4_I(inode)->i_data,symname,l); inode->i_size = l-1; - EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL; } EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_add_nondir(handle, dentry, inode); @@ -2407,7 +2403,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry, ext4_dec_count(handle, old_dir); if (new_inode) { /* checked empty_dir above, can't have another parent, - * ext3_dec_count() won't work for many-linked dirs */ + * ext4_dec_count() won't work for many-linked dirs */ new_inode->i_nlink = 0; } else { ext4_inc_count(handle, new_dir); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9477a2b..e29efa0 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1037,6 +1037,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_warning(sb, __FUNCTION__, "multiple resizers run on filesystem!"); unlock_super(sb); + ext4_journal_stop(handle); err = -EBUSY; goto exit_put; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 7fb514b..c4807b3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -906,7 +906,7 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) } if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { - int err = generic_permission(inode, mask, NULL); + err = generic_permission(inode, mask, NULL); /* If permission is denied, try to refresh file attributes. This is also needed, because the root diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 0822646..1ed8bd4 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -153,7 +153,7 @@ lockd(struct svc_rqst *rqstp) */ while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid) { long timeout = MAX_SCHEDULE_TIMEOUT; - char buf[RPC_MAX_ADDRBUFLEN]; + RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); if (signalled()) { flush_signals(current); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index ecc06c6..66648dd 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -93,6 +93,7 @@ static void nfs_callback_svc(struct svc_rqst *rqstp) svc_process(rqstp); } + flush_signals(current); svc_exit_thread(rqstp); nfs_callback_info.pid = 0; complete(&nfs_callback_info.stopped); @@ -171,7 +172,7 @@ void nfs_callback_down(void) static int nfs_callback_authenticate(struct svc_rqst *rqstp) { struct nfs_client *clp; - char buf[RPC_MAX_ADDRBUFLEN]; + RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); /* Don't talk to strangers */ clp = nfs_find_client(svc_addr(rqstp), 4); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c63eb72..13619d2 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -254,7 +254,7 @@ static __be32 encode_attr_change(struct xdr_stream *xdr, const uint32_t *bitmap, if (!(bitmap[0] & FATTR4_WORD0_CHANGE)) return 0; p = xdr_reserve_space(xdr, 8); - if (unlikely(p == 0)) + if (unlikely(!p)) return htonl(NFS4ERR_RESOURCE); p = xdr_encode_hyper(p, change); return 0; @@ -267,7 +267,7 @@ static __be32 encode_attr_size(struct xdr_stream *xdr, const uint32_t *bitmap, u if (!(bitmap[0] & FATTR4_WORD0_SIZE)) return 0; p = xdr_reserve_space(xdr, 8); - if (unlikely(p == 0)) + if (unlikely(!p)) return htonl(NFS4ERR_RESOURCE); p = xdr_encode_hyper(p, size); return 0; @@ -278,7 +278,7 @@ static __be32 encode_attr_time(struct xdr_stream *xdr, const struct timespec *ti __be32 *p; p = xdr_reserve_space(xdr, 12); - if (unlikely(p == 0)) + if (unlikely(!p)) return htonl(NFS4ERR_RESOURCE); p = xdr_encode_hyper(p, time->tv_sec); *p = htonl(time->tv_nsec); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index b9eadd1..00a5e44 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -49,7 +49,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ struct file_lock *fl; int status; - for (fl = inode->i_flock; fl != 0; fl = fl->fl_next) { + for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file) != ctx) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 8ae5dba..86147b0 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -309,7 +309,7 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h, mutex_lock(&idmap->idmap_im_lock); he = idmap_lookup_id(h, id); - if (he != 0) { + if (he) { memcpy(name, he->ih_name, he->ih_namelen); ret = he->ih_namelen; goto out; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 6233eb5..b962397 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -785,7 +785,7 @@ static int nfs4_reclaim_locks(struct nfs4_state_recovery_ops *ops, struct nfs4_s struct file_lock *fl; int status = 0; - for (fl = inode->i_flock; fl != 0; fl = fl->fl_next) { + for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file)->state != state) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 0130b34..1eb771d 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -101,7 +101,7 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, { /* Check if the request originated from a secure port. */ if (!rqstp->rq_secure && EX_SECURE(exp)) { - char buf[RPC_MAX_ADDRBUFLEN]; + RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk(KERN_WARNING "nfsd: request from insecure port %s!\n", svc_print_addr(rqstp, buf, sizeof(buf))); diff --git a/fs/proc/base.c b/fs/proc/base.c index 88f8edf..91a1bd6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -314,9 +314,12 @@ static int proc_pid_schedstat(struct task_struct *task, char *buffer) static int lstats_show_proc(struct seq_file *m, void *v) { int i; - struct task_struct *task = m->private; - seq_puts(m, "Latency Top version : v0.1\n"); + struct inode *inode = m->private; + struct task_struct *task = get_proc_task(inode); + if (!task) + return -ESRCH; + seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < 32; i++) { if (task->latency_record[i].backtrace[0]) { int q; @@ -341,32 +344,24 @@ static int lstats_show_proc(struct seq_file *m, void *v) } } + put_task_struct(task); return 0; } static int lstats_open(struct inode *inode, struct file *file) { - int ret; - struct seq_file *m; - struct task_struct *task = get_proc_task(inode); - - ret = single_open(file, lstats_show_proc, NULL); - if (!ret) { - m = file->private_data; - m->private = task; - } - return ret; + return single_open(file, lstats_show_proc, inode); } static ssize_t lstats_write(struct file *file, const char __user *buf, size_t count, loff_t *offs) { - struct seq_file *m; - struct task_struct *task; + struct task_struct *task = get_proc_task(file->f_dentry->d_inode); - m = file->private_data; - task = m->private; + if (!task) + return -ESRCH; clear_all_latency_tracing(task); + put_task_struct(task); return count; } @@ -416,6 +411,7 @@ static const struct limit_names lnames[RLIM_NLIMITS] = { [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, [RLIMIT_NICE] = {"Max nice priority", NULL}, [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, + [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, }; /* Display limits for a process */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 49958cf..6dc0334 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -531,7 +531,7 @@ struct pagemapread { #define PM_RESERVED_BITS 3 #define PM_RESERVED_OFFSET (64 - PM_RESERVED_BITS) #define PM_RESERVED_MASK (((1LL<<PM_RESERVED_BITS)-1) << PM_RESERVED_OFFSET) -#define PM_SPECIAL(nr) (((nr) << PM_RESERVED_OFFSET) | PM_RESERVED_MASK) +#define PM_SPECIAL(nr) (((nr) << PM_RESERVED_OFFSET) & PM_RESERVED_MASK) #define PM_NOT_PRESENT PM_SPECIAL(1LL) #define PM_SWAP PM_SPECIAL(2LL) #define PM_END_OF_BUFFER 1 diff --git a/fs/ufs/util.h b/fs/ufs/util.h index b26fc4d..23ceed8 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -58,7 +58,7 @@ ufs_set_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1, { switch (UFS_SB(sb)->s_flags & UFS_ST_MASK) { case UFS_ST_SUNOS: - if (fs32_to_cpu(sb, usb3->fs_postblformat == UFS_42POSTBLFMT)) { + if (fs32_to_cpu(sb, usb3->fs_postblformat) == UFS_42POSTBLFMT) { usb1->fs_u0.fs_sun.fs_state = cpu_to_fs32(sb, value); break; } diff --git a/fs/xfs/Kbuild b/fs/xfs/Kbuild deleted file mode 100644 index 2566e96..0000000 --- a/fs/xfs/Kbuild +++ /dev/null @@ -1,6 +0,0 @@ -# -# The xfs people like to share Makefile with 2.6 and 2.4. -# Utilise file named Kbuild file which has precedence over Makefile. -# - -include $(srctree)/$(obj)/Makefile-linux-2.6 diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 49e3e7e..36ec614 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -1 +1,117 @@ -include $(TOPDIR)/fs/xfs/Makefile-linux-$(VERSION).$(PATCHLEVEL) +# +# Copyright (c) 2000-2005 Silicon Graphics, Inc. +# All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write the Free Software Foundation, +# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA +# + +EXTRA_CFLAGS += -I$(src) -I$(src)/linux-2.6 -funsigned-char + +XFS_LINUX := linux-2.6 + +ifeq ($(CONFIG_XFS_DEBUG),y) + EXTRA_CFLAGS += -g +endif + +obj-$(CONFIG_XFS_FS) += xfs.o + +xfs-$(CONFIG_XFS_QUOTA) += $(addprefix quota/, \ + xfs_dquot.o \ + xfs_dquot_item.o \ + xfs_trans_dquot.o \ + xfs_qm_syscalls.o \ + xfs_qm_bhv.o \ + xfs_qm.o) + +ifeq ($(CONFIG_XFS_QUOTA),y) +xfs-$(CONFIG_PROC_FS) += quota/xfs_qm_stats.o +endif + +xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o +xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o +xfs-$(CONFIG_PROC_FS) += $(XFS_LINUX)/xfs_stats.o +xfs-$(CONFIG_SYSCTL) += $(XFS_LINUX)/xfs_sysctl.o +xfs-$(CONFIG_COMPAT) += $(XFS_LINUX)/xfs_ioctl32.o + + +xfs-y += xfs_alloc.o \ + xfs_alloc_btree.o \ + xfs_attr.o \ + xfs_attr_leaf.o \ + xfs_bit.o \ + xfs_bmap.o \ + xfs_bmap_btree.o \ + xfs_btree.o \ + xfs_buf_item.o \ + xfs_da_btree.o \ + xfs_dir2.o \ + xfs_dir2_block.o \ + xfs_dir2_data.o \ + xfs_dir2_leaf.o \ + xfs_dir2_node.o \ + xfs_dir2_sf.o \ + xfs_error.o \ + xfs_extfree_item.o \ + xfs_filestream.o \ + xfs_fsops.o \ + xfs_ialloc.o \ + xfs_ialloc_btree.o \ + xfs_iget.o \ + xfs_inode.o \ + xfs_inode_item.o \ + xfs_iomap.o \ + xfs_itable.o \ + xfs_dfrag.o \ + xfs_log.o \ + xfs_log_recover.o \ + xfs_mount.o \ + xfs_mru_cache.o \ + xfs_rename.o \ + xfs_trans.o \ + xfs_trans_ail.o \ + xfs_trans_buf.o \ + xfs_trans_extfree.o \ + xfs_trans_inode.o \ + xfs_trans_item.o \ + xfs_utils.o \ + xfs_vfsops.o \ + xfs_vnodeops.o \ + xfs_rw.o \ + xfs_dmops.o \ + xfs_qmops.o + +xfs-$(CONFIG_XFS_TRACE) += xfs_dir2_trace.o + +# Objects in linux/ +xfs-y += $(addprefix $(XFS_LINUX)/, \ + kmem.o \ + xfs_aops.o \ + xfs_buf.o \ + xfs_export.o \ + xfs_file.o \ + xfs_fs_subr.o \ + xfs_globals.o \ + xfs_ioctl.o \ + xfs_iops.o \ + xfs_lrw.o \ + xfs_super.o \ + xfs_vnode.o) + +# Objects in support/ +xfs-y += $(addprefix support/, \ + debug.o \ + uuid.o) + +xfs-$(CONFIG_XFS_TRACE) += support/ktrace.o + diff --git a/fs/xfs/Makefile-linux-2.6 b/fs/xfs/Makefile-linux-2.6 deleted file mode 100644 index 9731645..0000000 --- a/fs/xfs/Makefile-linux-2.6 +++ /dev/null @@ -1,117 +0,0 @@ -# -# Copyright (c) 2000-2005 Silicon Graphics, Inc. -# All Rights Reserved. -# -# This program is free software; you can redistribute it and/or -# modify it under the terms of the GNU General Public License as -# published by the Free Software Foundation. -# -# This program is distributed in the hope that it would be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write the Free Software Foundation, -# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA -# - -EXTRA_CFLAGS += -Ifs/xfs -Ifs/xfs/linux-2.6 -funsigned-char - -XFS_LINUX := linux-2.6 - -ifeq ($(CONFIG_XFS_DEBUG),y) - EXTRA_CFLAGS += -g -endif - -obj-$(CONFIG_XFS_FS) += xfs.o - -xfs-$(CONFIG_XFS_QUOTA) += $(addprefix quota/, \ - xfs_dquot.o \ - xfs_dquot_item.o \ - xfs_trans_dquot.o \ - xfs_qm_syscalls.o \ - xfs_qm_bhv.o \ - xfs_qm.o) - -ifeq ($(CONFIG_XFS_QUOTA),y) -xfs-$(CONFIG_PROC_FS) += quota/xfs_qm_stats.o -endif - -xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o -xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o -xfs-$(CONFIG_PROC_FS) += $(XFS_LINUX)/xfs_stats.o -xfs-$(CONFIG_SYSCTL) += $(XFS_LINUX)/xfs_sysctl.o -xfs-$(CONFIG_COMPAT) += $(XFS_LINUX)/xfs_ioctl32.o - - -xfs-y += xfs_alloc.o \ - xfs_alloc_btree.o \ - xfs_attr.o \ - xfs_attr_leaf.o \ - xfs_bit.o \ - xfs_bmap.o \ - xfs_bmap_btree.o \ - xfs_btree.o \ - xfs_buf_item.o \ - xfs_da_btree.o \ - xfs_dir2.o \ - xfs_dir2_block.o \ - xfs_dir2_data.o \ - xfs_dir2_leaf.o \ - xfs_dir2_node.o \ - xfs_dir2_sf.o \ - xfs_error.o \ - xfs_extfree_item.o \ - xfs_filestream.o \ - xfs_fsops.o \ - xfs_ialloc.o \ - xfs_ialloc_btree.o \ - xfs_iget.o \ - xfs_inode.o \ - xfs_inode_item.o \ - xfs_iomap.o \ - xfs_itable.o \ - xfs_dfrag.o \ - xfs_log.o \ - xfs_log_recover.o \ - xfs_mount.o \ - xfs_mru_cache.o \ - xfs_rename.o \ - xfs_trans.o \ - xfs_trans_ail.o \ - xfs_trans_buf.o \ - xfs_trans_extfree.o \ - xfs_trans_inode.o \ - xfs_trans_item.o \ - xfs_utils.o \ - xfs_vfsops.o \ - xfs_vnodeops.o \ - xfs_rw.o \ - xfs_dmops.o \ - xfs_qmops.o - -xfs-$(CONFIG_XFS_TRACE) += xfs_dir2_trace.o - -# Objects in linux/ -xfs-y += $(addprefix $(XFS_LINUX)/, \ - kmem.o \ - xfs_aops.o \ - xfs_buf.o \ - xfs_export.o \ - xfs_file.o \ - xfs_fs_subr.o \ - xfs_globals.o \ - xfs_ioctl.o \ - xfs_iops.o \ - xfs_lrw.o \ - xfs_super.o \ - xfs_vnode.o) - -# Objects in support/ -xfs-y += $(addprefix support/, \ - debug.o \ - uuid.o) - -xfs-$(CONFIG_XFS_TRACE) += support/ktrace.o - diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 21dfc9d..8831d95 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -171,7 +171,7 @@ xfs_parseargs( char *this_char, *value, *eov; int dsunit, dswidth, vol_dsunit, vol_dswidth; int iosize; - int ikeep = 0; + int dmapi_implies_ikeep = 1; args->flags |= XFSMNT_BARRIER; args->flags2 |= XFSMNT2_COMPAT_IOSIZE; @@ -302,10 +302,10 @@ xfs_parseargs( } else if (!strcmp(this_char, MNTOPT_NOBARRIER)) { args->flags &= ~XFSMNT_BARRIER; } else if (!strcmp(this_char, MNTOPT_IKEEP)) { - ikeep = 1; - args->flags &= ~XFSMNT_IDELETE; + args->flags |= XFSMNT_IKEEP; } else if (!strcmp(this_char, MNTOPT_NOIKEEP)) { - args->flags |= XFSMNT_IDELETE; + dmapi_implies_ikeep = 0; + args->flags &= ~XFSMNT_IKEEP; } else if (!strcmp(this_char, MNTOPT_LARGEIO)) { args->flags2 &= ~XFSMNT2_COMPAT_IOSIZE; } else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) { @@ -410,8 +410,8 @@ xfs_parseargs( * Note that if "ikeep" or "noikeep" mount options are * supplied, then they are honored. */ - if (!(args->flags & XFSMNT_DMAPI) && !ikeep) - args->flags |= XFSMNT_IDELETE; + if ((args->flags & XFSMNT_DMAPI) && dmapi_implies_ikeep) + args->flags |= XFSMNT_IKEEP; if ((args->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) { if (dsunit) { @@ -446,6 +446,7 @@ xfs_showargs( { static struct proc_xfs_info xfs_info_set[] = { /* the few simple ones we can get from the mount struct */ + { XFS_MOUNT_IKEEP, "," MNTOPT_IKEEP }, { XFS_MOUNT_WSYNC, "," MNTOPT_WSYNC }, { XFS_MOUNT_INO64, "," MNTOPT_INO64 }, { XFS_MOUNT_NOALIGN, "," MNTOPT_NOALIGN }, @@ -461,7 +462,6 @@ xfs_showargs( }; static struct proc_xfs_info xfs_info_unset[] = { /* the few simple ones we can get from the mount struct */ - { XFS_MOUNT_IDELETE, "," MNTOPT_IKEEP }, { XFS_MOUNT_COMPAT_IOSIZE, "," MNTOPT_LARGEIO }, { XFS_MOUNT_BARRIER, "," MNTOPT_NOBARRIER }, { XFS_MOUNT_SMALL_INUMS, "," MNTOPT_64BITINODE }, diff --git a/fs/xfs/xfs_bit.c b/fs/xfs/xfs_bit.c index 4822884..fab0b6d 100644 --- a/fs/xfs/xfs_bit.c +++ b/fs/xfs/xfs_bit.c @@ -25,6 +25,109 @@ * XFS bit manipulation routines, used in non-realtime code. */ +#ifndef HAVE_ARCH_HIGHBIT +/* + * Index of high bit number in byte, -1 for none set, 0..7 otherwise. + */ +static const char xfs_highbit[256] = { + -1, 0, 1, 1, 2, 2, 2, 2, /* 00 .. 07 */ + 3, 3, 3, 3, 3, 3, 3, 3, /* 08 .. 0f */ + 4, 4, 4, 4, 4, 4, 4, 4, /* 10 .. 17 */ + 4, 4, 4, 4, 4, 4, 4, 4, /* 18 .. 1f */ + 5, 5, 5, 5, 5, 5, 5, 5, /* 20 .. 27 */ + 5, 5, 5, 5, 5, 5, 5, 5, /* 28 .. 2f */ + 5, 5, 5, 5, 5, 5, 5, 5, /* 30 .. 37 */ + 5, 5, 5, 5, 5, 5, 5, 5, /* 38 .. 3f */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 40 .. 47 */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 48 .. 4f */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 50 .. 57 */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 58 .. 5f */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 60 .. 67 */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 68 .. 6f */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 70 .. 77 */ + 6, 6, 6, 6, 6, 6, 6, 6, /* 78 .. 7f */ + 7, 7, 7, 7, 7, 7, 7, 7, /* 80 .. 87 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* 88 .. 8f */ + 7, 7, 7, 7, 7, 7, 7, 7, /* 90 .. 97 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* 98 .. 9f */ + 7, 7, 7, 7, 7, 7, 7, 7, /* a0 .. a7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* a8 .. af */ + 7, 7, 7, 7, 7, 7, 7, 7, /* b0 .. b7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* b8 .. bf */ + 7, 7, 7, 7, 7, 7, 7, 7, /* c0 .. c7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* c8 .. cf */ + 7, 7, 7, 7, 7, 7, 7, 7, /* d0 .. d7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* d8 .. df */ + 7, 7, 7, 7, 7, 7, 7, 7, /* e0 .. e7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* e8 .. ef */ + 7, 7, 7, 7, 7, 7, 7, 7, /* f0 .. f7 */ + 7, 7, 7, 7, 7, 7, 7, 7, /* f8 .. ff */ +}; +#endif + +/* + * xfs_highbit32: get high bit set out of 32-bit argument, -1 if none set. + */ +inline int +xfs_highbit32( + __uint32_t v) +{ +#ifdef HAVE_ARCH_HIGHBIT + return highbit32(v); +#else + int i; + + if (v & 0xffff0000) + if (v & 0xff000000) + i = 24; + else + i = 16; + else if (v & 0x0000ffff) + if (v & 0x0000ff00) + i = 8; + else + i = 0; + else + return -1; + return i + xfs_highbit[(v >> i) & 0xff]; +#endif +} + +/* + * xfs_lowbit64: get low bit set out of 64-bit argument, -1 if none set. + */ +int +xfs_lowbit64( + __uint64_t v) +{ + __uint32_t w = (__uint32_t)v; + int n = 0; + + if (w) { /* lower bits */ + n = ffs(w); + } else { /* upper bits */ + w = (__uint32_t)(v >> 32); + if (w && (n = ffs(w))) + n += 32; + } + return n - 1; +} + +/* + * xfs_highbit64: get high bit set out of 64-bit argument, -1 if none set. + */ +int +xfs_highbit64( + __uint64_t v) +{ + __uint32_t h = (__uint32_t)(v >> 32); + + if (h) + return xfs_highbit32(h) + 32; + return xfs_highbit32((__uint32_t)v); +} + + /* * Return whether bitmap is empty. * Size is number of words in the bitmap, which is padded to word boundary diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h index 325a007..082641a 100644 --- a/fs/xfs/xfs_bit.h +++ b/fs/xfs/xfs_bit.h @@ -47,30 +47,13 @@ static inline __uint64_t xfs_mask64lo(int n) } /* Get high bit set out of 32-bit argument, -1 if none set */ -static inline int xfs_highbit32(__uint32_t v) -{ - return fls(v) - 1; -} - -/* Get high bit set out of 64-bit argument, -1 if none set */ -static inline int xfs_highbit64(__uint64_t v) -{ - return fls64(v) - 1; -} - -/* Get low bit set out of 32-bit argument, -1 if none set */ -static inline int xfs_lowbit32(__uint32_t v) -{ - __uint32_t t = v; - return (t) ? find_first_bit((unsigned long *)&t, 32) : -1; -} +extern int xfs_highbit32(__uint32_t v); /* Get low bit set out of 64-bit argument, -1 if none set */ -static inline int xfs_lowbit64(__uint64_t v) -{ - __uint64_t t = v; - return (t) ? find_first_bit((unsigned long *)&t, 64) : -1; -} +extern int xfs_lowbit64(__uint64_t v); + +/* Get high bit set out of 64-bit argument, -1 if none set */ +extern int xfs_highbit64(__uint64_t); /* Return whether bitmap is empty (1 == empty) */ extern int xfs_bitmap_empty(uint *map, uint size); diff --git a/fs/xfs/xfs_clnt.h b/fs/xfs/xfs_clnt.h index d16c1b9..d5d1e60 100644 --- a/fs/xfs/xfs_clnt.h +++ b/fs/xfs/xfs_clnt.h @@ -86,7 +86,7 @@ struct xfs_mount_args { #define XFSMNT_NOUUID 0x01000000 /* Ignore fs uuid */ #define XFSMNT_DMAPI 0x02000000 /* enable dmapi/xdsm */ #define XFSMNT_BARRIER 0x04000000 /* use write barriers */ -#define XFSMNT_IDELETE 0x08000000 /* inode cluster delete */ +#define XFSMNT_IKEEP 0x08000000 /* inode cluster delete */ #define XFSMNT_SWALLOC 0x10000000 /* turn on stripe width * allocation */ #define XFSMNT_DIRSYNC 0x40000000 /* sync creat,link,unlink,rename diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index c5836b9..db9d5fa 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -1053,7 +1053,7 @@ xfs_difree( /* * When an inode cluster is free, it becomes eligible for removal */ - if ((mp->m_flags & XFS_MOUNT_IDELETE) && + if (!(mp->m_flags & XFS_MOUNT_IKEEP) && (rec.ir_freecount == XFS_IALLOC_INODES(mp))) { *delete = 1; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f7c620e..1d8a472 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -366,7 +366,7 @@ typedef struct xfs_mount { #define XFS_MOUNT_SMALL_INUMS (1ULL << 15) /* users wants 32bit inodes */ #define XFS_MOUNT_NOUUID (1ULL << 16) /* ignore uuid during mount */ #define XFS_MOUNT_BARRIER (1ULL << 17) -#define XFS_MOUNT_IDELETE (1ULL << 18) /* delete empty inode clusters*/ +#define XFS_MOUNT_IKEEP (1ULL << 18) /* keep empty inode clusters*/ #define XFS_MOUNT_SWALLOC (1ULL << 19) /* turn on stripe width * allocation */ #define XFS_MOUNT_RDONLY (1ULL << 20) /* read-only fs */ diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index ca83ddf..47082c0 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -73,6 +73,18 @@ STATIC int xfs_rtmodify_summary(xfs_mount_t *, xfs_trans_t *, int, */ /* + * xfs_lowbit32: get low bit set out of 32-bit argument, -1 if none set. + */ +STATIC int +xfs_lowbit32( + __uint32_t v) +{ + if (v) + return ffs(v) - 1; + return -1; +} + +/* * Allocate space to the bitmap or summary file, and zero it, for growfs. */ STATIC int /* error */ @@ -432,7 +444,6 @@ xfs_rtallocate_extent_near( } bbno = XFS_BITTOBLOCK(mp, bno); i = 0; - ASSERT(minlen != 0); log2len = xfs_highbit32(minlen); /* * Loop over all bitmap blocks (bbno + i is current block). @@ -601,8 +612,6 @@ xfs_rtallocate_extent_size( xfs_suminfo_t sum; /* summary information for extents */ ASSERT(minlen % prod == 0 && maxlen % prod == 0); - ASSERT(maxlen != 0); - /* * Loop over all the levels starting with maxlen. * At each level, look at all the bitmap blocks, to see if there @@ -660,9 +669,6 @@ xfs_rtallocate_extent_size( *rtblock = NULLRTBLOCK; return 0; } - ASSERT(minlen != 0); - ASSERT(maxlen != 0); - /* * Loop over sizes, from maxlen down to minlen. * This time, when we do the allocations, allow smaller ones @@ -1948,7 +1954,6 @@ xfs_growfs_rt( nsbp->sb_blocksize * nsbp->sb_rextsize); nsbp->sb_rextents = nsbp->sb_rblocks; do_div(nsbp->sb_rextents, nsbp->sb_rextsize); - ASSERT(nsbp->sb_rextents != 0); nsbp->sb_rextslog = xfs_highbit32(nsbp->sb_rextents); nrsumlevels = nmp->m_rsumlevels = nsbp->sb_rextslog + 1; nrsumsize = diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c index 413587f..7321304 100644 --- a/fs/xfs/xfs_vfsops.c +++ b/fs/xfs/xfs_vfsops.c @@ -281,8 +281,8 @@ xfs_start_flags( mp->m_readio_log = mp->m_writeio_log = ap->iosizelog; } - if (ap->flags & XFSMNT_IDELETE) - mp->m_flags |= XFS_MOUNT_IDELETE; + if (ap->flags & XFSMNT_IKEEP) + mp->m_flags |= XFS_MOUNT_IKEEP; if (ap->flags & XFSMNT_DIRSYNC) mp->m_flags |= XFS_MOUNT_DIRSYNC; if (ap->flags & XFSMNT_ATTR2) |