diff options
Diffstat (limited to 'fs')
70 files changed, 1015 insertions, 458 deletions
diff --git a/fs/9p/conv.c b/fs/9p/conv.c index 1e89814..56d88c1 100644 --- a/fs/9p/conv.c +++ b/fs/9p/conv.c @@ -673,8 +673,10 @@ struct v9fs_fcall *v9fs_create_tcreate(u32 fid, char *name, u32 perm, u8 mode, struct cbuf *bufp = &buffer; size = 4 + 2 + strlen(name) + 4 + 1; /* fid[4] name[s] perm[4] mode[1] */ - if (extended && extension!=NULL) - size += 2 + strlen(extension); /* extension[s] */ + if (extended) { + size += 2 + /* extension[s] */ + (extension == NULL ? 0 : strlen(extension)); + } fc = v9fs_create_common(bufp, size, TCREATE); if (IS_ERR(fc)) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 2f580a1..eae50c9 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -434,11 +434,11 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) result = v9fs_t_remove(v9ses, fid, &fcall); if (result < 0) { PRINT_FCALL_ERROR("remove fails", fcall); - } else { - v9fs_put_idpool(fid, &v9ses->fidpool); - v9fs_fid_destroy(v9fid); } + v9fs_put_idpool(fid, &v9ses->fidpool); + v9fs_fid_destroy(v9fid); + kfree(fcall); return result; } diff --git a/fs/adfs/super.c b/fs/adfs/super.c index ba1c88a..8201101 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -308,7 +308,7 @@ static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_di if (adfs_checkmap(sb, dm)) return dm; - adfs_error(sb, NULL, "map corrupted"); + adfs_error(sb, "map corrupted"); error_free: while (--zone >= 0) diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index fcaeead..50cfca5 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -512,7 +512,11 @@ befs_utf2nls(struct super_block *sb, const char *in, wchar_t uni; int unilen, utflen; char *result; - int maxlen = in_len; /* The utf8->nls conversion can't make more chars */ + /* The utf8->nls conversion won't make the final nls string bigger + * than the utf one, but if the string is pure ascii they'll have the + * same width and an extra char is needed to save the additional \0 + */ + int maxlen = in_len + 1; befs_debug(sb, "---> utf2nls()"); @@ -588,7 +592,10 @@ befs_nls2utf(struct super_block *sb, const char *in, wchar_t uni; int unilen, utflen; char *result; - int maxlen = 3 * in_len; + /* There're nls characters that will translate to 3-chars-wide UTF-8 + * characters, a additional byte is needed to save the final \0 + * in special cases */ + int maxlen = (3 * in_len) + 1; befs_debug(sb, "---> nls2utf()\n"); diff --git a/fs/block_dev.c b/fs/block_dev.c index 3753457..045f988 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -884,6 +884,61 @@ void bd_set_size(struct block_device *bdev, loff_t size) } EXPORT_SYMBOL(bd_set_size); +static int __blkdev_put(struct block_device *bdev, unsigned int subclass) +{ + int ret = 0; + struct inode *bd_inode = bdev->bd_inode; + struct gendisk *disk = bdev->bd_disk; + + mutex_lock_nested(&bdev->bd_mutex, subclass); + lock_kernel(); + if (!--bdev->bd_openers) { + sync_blockdev(bdev); + kill_bdev(bdev); + } + if (bdev->bd_contains == bdev) { + if (disk->fops->release) + ret = disk->fops->release(bd_inode, NULL); + } else { + mutex_lock_nested(&bdev->bd_contains->bd_mutex, + subclass + 1); + bdev->bd_contains->bd_part_count--; + mutex_unlock(&bdev->bd_contains->bd_mutex); + } + if (!bdev->bd_openers) { + struct module *owner = disk->fops->owner; + + put_disk(disk); + module_put(owner); + + if (bdev->bd_contains != bdev) { + kobject_put(&bdev->bd_part->kobj); + bdev->bd_part = NULL; + } + bdev->bd_disk = NULL; + bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; + if (bdev != bdev->bd_contains) + __blkdev_put(bdev->bd_contains, subclass + 1); + bdev->bd_contains = NULL; + } + unlock_kernel(); + mutex_unlock(&bdev->bd_mutex); + bdput(bdev); + return ret; +} + +int blkdev_put(struct block_device *bdev) +{ + return __blkdev_put(bdev, BD_MUTEX_NORMAL); +} +EXPORT_SYMBOL(blkdev_put); + +int blkdev_put_partition(struct block_device *bdev) +{ + return __blkdev_put(bdev, BD_MUTEX_PARTITION); +} +EXPORT_SYMBOL(blkdev_put_partition); + static int blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags); @@ -980,7 +1035,7 @@ out_first: bdev->bd_disk = NULL; bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; if (bdev != bdev->bd_contains) - blkdev_put(bdev->bd_contains); + __blkdev_put(bdev->bd_contains, BD_MUTEX_WHOLE); bdev->bd_contains = NULL; put_disk(disk); module_put(owner); @@ -1079,63 +1134,6 @@ static int blkdev_open(struct inode * inode, struct file * filp) return res; } -static int __blkdev_put(struct block_device *bdev, unsigned int subclass) -{ - int ret = 0; - struct inode *bd_inode = bdev->bd_inode; - struct gendisk *disk = bdev->bd_disk; - - mutex_lock_nested(&bdev->bd_mutex, subclass); - lock_kernel(); - if (!--bdev->bd_openers) { - sync_blockdev(bdev); - kill_bdev(bdev); - } - if (bdev->bd_contains == bdev) { - if (disk->fops->release) - ret = disk->fops->release(bd_inode, NULL); - } else { - mutex_lock_nested(&bdev->bd_contains->bd_mutex, - subclass + 1); - bdev->bd_contains->bd_part_count--; - mutex_unlock(&bdev->bd_contains->bd_mutex); - } - if (!bdev->bd_openers) { - struct module *owner = disk->fops->owner; - - put_disk(disk); - module_put(owner); - - if (bdev->bd_contains != bdev) { - kobject_put(&bdev->bd_part->kobj); - bdev->bd_part = NULL; - } - bdev->bd_disk = NULL; - bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; - if (bdev != bdev->bd_contains) - __blkdev_put(bdev->bd_contains, subclass + 1); - bdev->bd_contains = NULL; - } - unlock_kernel(); - mutex_unlock(&bdev->bd_mutex); - bdput(bdev); - return ret; -} - -int blkdev_put(struct block_device *bdev) -{ - return __blkdev_put(bdev, BD_MUTEX_NORMAL); -} - -EXPORT_SYMBOL(blkdev_put); - -int blkdev_put_partition(struct block_device *bdev) -{ - return __blkdev_put(bdev, BD_MUTEX_PARTITION); -} - -EXPORT_SYMBOL(blkdev_put_partition); - static int blkdev_close(struct inode * inode, struct file * filp) { struct block_device *bdev = I_BDEV(filp->f_mapping->host); diff --git a/fs/buffer.c b/fs/buffer.c index 3660dcb..71649ef 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -470,13 +470,18 @@ out: pass does the actual I/O. */ void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) { + struct address_space *mapping = bdev->bd_inode->i_mapping; + + if (mapping->nrpages == 0) + return; + invalidate_bh_lrus(); /* * FIXME: what about destroy_dirty_buffers? * We really want to use invalidate_inode_pages2() for * that, but not until that's cleaned up. */ - invalidate_inode_pages(bdev->bd_inode->i_mapping); + invalidate_inode_pages(mapping); } /* diff --git a/fs/coda/file.c b/fs/coda/file.c index cc66c68..dbfbcfa 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -136,10 +136,8 @@ int coda_open(struct inode *coda_inode, struct file *coda_file) coda_vfs_stat.open++; cfi = kmalloc(sizeof(struct coda_file_info), GFP_KERNEL); - if (!cfi) { - unlock_kernel(); + if (!cfi) return -ENOMEM; - } lock_kernel(); diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index e249cf7..1d30d2f 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -22,7 +22,7 @@ static int efs_symlink_readpage(struct file *file, struct page *page) err = -ENAMETOOLONG; if (size > 2 * EFS_BLOCKSIZE) - goto fail; + goto fail_notlocked; lock_kernel(); /* read first 512 bytes of link target */ @@ -47,6 +47,7 @@ static int efs_symlink_readpage(struct file *file, struct page *page) return 0; fail: unlock_kernel(); +fail_notlocked: SetPageError(page); kunmap(page); unlock_page(page); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 19ffb04..3a35674 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1168,7 +1168,7 @@ static int ep_unlink(struct eventpoll *ep, struct epitem *epi) eexit_1: DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n", - current, ep, epi->file, error)); + current, ep, epi->ffd.file, error)); return error; } @@ -1236,7 +1236,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k struct eventpoll *ep = epi->ep; DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n", - current, epi->file, epi, ep)); + current, epi->ffd.file, epi, ep)); write_lock_irqsave(&ep->lock, flags); @@ -486,8 +486,6 @@ struct file *open_exec(const char *name) if (!(nd.mnt->mnt_flags & MNT_NOEXEC) && S_ISREG(inode->i_mode)) { int err = vfs_permission(&nd, MAY_EXEC); - if (!err && !(inode->i_mode & 0111)) - err = -EACCES; file = ERR_PTR(err); if (!err) { file = nameidata_to_filp(&nd, O_RDONLY); @@ -753,7 +751,7 @@ no_thread_group: write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); - spin_lock(&newsighand->siglock); + spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING); rcu_assign_pointer(current->sighand, newsighand); recalc_sigpending(); @@ -922,12 +920,6 @@ int prepare_binprm(struct linux_binprm *bprm) int retval; mode = inode->i_mode; - /* - * Check execute perms again - if the caller has CAP_DAC_OVERRIDE, - * generic_permission lets a non-executable through - */ - if (!(mode & 0111)) /* with at least _one_ execute bit set */ - return -EACCES; if (bprm->file->f_op == NULL) return -EACCES; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index f2702cd..681dea8 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -775,7 +775,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (EXT2_INODE_SIZE(sb) == 0) goto cantfind_ext2; sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); - if (sbi->s_inodes_per_block == 0) + if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0) goto cantfind_ext2; sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index a504a40..063d994 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -1269,12 +1269,12 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode, goal = le32_to_cpu(es->s_first_data_block); group_no = (goal - le32_to_cpu(es->s_first_data_block)) / EXT3_BLOCKS_PER_GROUP(sb); + goal_group = group_no; +retry_alloc: gdp = ext3_get_group_desc(sb, group_no, &gdp_bh); if (!gdp) goto io_error; - goal_group = group_no; -retry: free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); /* * if there is not enough free blocks to make a new resevation @@ -1349,7 +1349,7 @@ retry: if (my_rsv) { my_rsv = NULL; group_no = goal_group; - goto retry; + goto retry_alloc; } /* No space left on the device */ *errp = -ENOSPC; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index f804d5e..c5ee9f0 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1158,7 +1158,7 @@ retry: ret = PTR_ERR(handle); goto out; } - if (test_opt(inode->i_sb, NOBH)) + if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_prepare_write(page, from, to, ext3_get_block); else ret = block_prepare_write(page, from, to, ext3_get_block); @@ -1244,7 +1244,7 @@ static int ext3_writeback_commit_write(struct file *file, struct page *page, if (new_i_size > EXT3_I(inode)->i_disksize) EXT3_I(inode)->i_disksize = new_i_size; - if (test_opt(inode->i_sb, NOBH)) + if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_commit_write(file, page, from, to); else ret = generic_commit_write(file, page, from, to); @@ -1494,7 +1494,7 @@ static int ext3_writeback_writepage(struct page *page, goto out_fail; } - if (test_opt(inode->i_sb, NOBH)) + if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_writepage(page, ext3_get_block, wbc); else ret = block_write_full_page(page, ext3_get_block, wbc); @@ -2402,14 +2402,15 @@ static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb, struct buffer_head *bh; struct ext3_group_desc * gdp; - - if ((ino != EXT3_ROOT_INO && ino != EXT3_JOURNAL_INO && - ino != EXT3_RESIZE_INO && ino < EXT3_FIRST_INO(sb)) || - ino > le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count)) { - ext3_error(sb, "ext3_get_inode_block", - "bad inode number: %lu", ino); + if (!ext3_valid_inum(sb, ino)) { + /* + * This error is already checked for in namei.c unless we are + * looking at an NFS filehandle, in which case no error + * report is needed + */ return 0; } + block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb); if (block_group >= EXT3_SB(sb)->s_groups_count) { ext3_error(sb,"ext3_get_inode_block","group >= groups count"); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index d9176db..2aa7101 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1000,7 +1000,12 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str if (bh) { unsigned long ino = le32_to_cpu(de->inode); brelse (bh); - inode = iget(dir->i_sb, ino); + if (!ext3_valid_inum(dir->i_sb, ino)) { + ext3_error(dir->i_sb, "ext3_lookup", + "bad inode number: %lu", ino); + inode = NULL; + } else + inode = iget(dir->i_sb, ino); if (!inode) return ERR_PTR(-EACCES); @@ -1028,7 +1033,13 @@ struct dentry *ext3_get_parent(struct dentry *child) return ERR_PTR(-ENOENT); ino = le32_to_cpu(de->inode); brelse(bh); - inode = iget(child->d_inode->i_sb, ino); + + if (!ext3_valid_inum(child->d_inode->i_sb, ino)) { + ext3_error(child->d_inode->i_sb, "ext3_get_parent", + "bad inode number: %lu", ino); + inode = NULL; + } else + inode = iget(child->d_inode->i_sb, ino); if (!inode) return ERR_PTR(-EACCES); diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 29cce45..43886fa 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -246,6 +246,8 @@ vxfs_readdir(struct file *fp, void *retp, filldir_t filler) u_long page, npages, block, pblocks, nblocks, offset; loff_t pos; + lock_kernel(); + switch ((long)fp->f_pos) { case 0: if (filler(retp, ".", 1, fp->f_pos, ip->i_ino, DT_DIR) < 0) diff --git a/fs/fuse/control.c b/fs/fuse/control.c index a3bce3a..46fe60b 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -105,7 +105,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, /* * Add a connection to the control filesystem (if it exists). Caller - * must host fuse_mutex + * must hold fuse_mutex */ int fuse_ctl_add_conn(struct fuse_conn *fc) { @@ -139,7 +139,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) /* * Remove a connection from the control filesystem (if it exists). - * Caller must host fuse_mutex + * Caller must hold fuse_mutex */ void fuse_ctl_remove_conn(struct fuse_conn *fc) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 72a74cd..409ce6a 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -14,6 +14,33 @@ #include <linux/sched.h> #include <linux/namei.h> +#if BITS_PER_LONG >= 64 +static inline void fuse_dentry_settime(struct dentry *entry, u64 time) +{ + entry->d_time = time; +} + +static inline u64 fuse_dentry_time(struct dentry *entry) +{ + return entry->d_time; +} +#else +/* + * On 32 bit archs store the high 32 bits of time in d_fsdata + */ +static void fuse_dentry_settime(struct dentry *entry, u64 time) +{ + entry->d_time = time; + entry->d_fsdata = (void *) (unsigned long) (time >> 32); +} + +static u64 fuse_dentry_time(struct dentry *entry) +{ + return (u64) entry->d_time + + ((u64) (unsigned long) entry->d_fsdata << 32); +} +#endif + /* * FUSE caches dentries and attributes with separate timeout. The * time in jiffies until the dentry/attributes are valid is stored in @@ -23,10 +50,13 @@ /* * Calculate the time in jiffies until a dentry/attributes are valid */ -static unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec) +static u64 time_to_jiffies(unsigned long sec, unsigned long nsec) { - struct timespec ts = {sec, nsec}; - return jiffies + timespec_to_jiffies(&ts); + if (sec || nsec) { + struct timespec ts = {sec, nsec}; + return get_jiffies_64() + timespec_to_jiffies(&ts); + } else + return 0; } /* @@ -35,7 +65,8 @@ static unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec) */ static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) { - entry->d_time = time_to_jiffies(o->entry_valid, o->entry_valid_nsec); + fuse_dentry_settime(entry, + time_to_jiffies(o->entry_valid, o->entry_valid_nsec)); if (entry->d_inode) get_fuse_inode(entry->d_inode)->i_time = time_to_jiffies(o->attr_valid, o->attr_valid_nsec); @@ -47,7 +78,7 @@ static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) */ void fuse_invalidate_attr(struct inode *inode) { - get_fuse_inode(inode)->i_time = jiffies - 1; + get_fuse_inode(inode)->i_time = 0; } /* @@ -60,7 +91,7 @@ void fuse_invalidate_attr(struct inode *inode) */ static void fuse_invalidate_entry_cache(struct dentry *entry) { - entry->d_time = jiffies - 1; + fuse_dentry_settime(entry, 0); } /* @@ -102,7 +133,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) if (inode && is_bad_inode(inode)) return 0; - else if (time_after(jiffies, entry->d_time)) { + else if (fuse_dentry_time(entry) < get_jiffies_64()) { int err; struct fuse_entry_out outarg; struct fuse_conn *fc; @@ -666,7 +697,7 @@ static int fuse_revalidate(struct dentry *entry) if (!fuse_allow_task(fc, current)) return -EACCES; if (get_node_id(inode) != FUSE_ROOT_ID && - time_before_eq(jiffies, fi->i_time)) + fi->i_time >= get_jiffies_64()) return 0; return fuse_do_getattr(inode); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 63614ed..5c4fcd1 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -395,14 +395,16 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, struct fuse_readpages_data data; int err; + err = -EIO; if (is_bad_inode(inode)) - return -EIO; + goto clean_pages_up; data.file = file; data.inode = inode; data.req = fuse_get_req(fc); + err = PTR_ERR(data.req); if (IS_ERR(data.req)) - return PTR_ERR(data.req); + goto clean_pages_up; err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data); if (!err) { @@ -412,6 +414,10 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, fuse_put_request(fc, data.req); } return err; + +clean_pages_up: + put_pages_list(pages); + return err; } static size_t fuse_send_write(struct fuse_req *req, struct file *file, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 0dbf966..69c7750 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -59,7 +59,7 @@ struct fuse_inode { struct fuse_req *forget_req; /** Time in jiffies until the file attributes are valid */ - unsigned long i_time; + u64 i_time; }; /** FUSE specific file data */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index dcaaabd..7d25092 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -51,7 +51,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) return NULL; fi = get_fuse_inode(inode); - fi->i_time = jiffies - 1; + fi->i_time = 0; fi->nodeid = 0; fi->nlookup = 0; fi->forget_req = fuse_request_alloc(); diff --git a/fs/inotify_user.c b/fs/inotify_user.c index f238644..017cb0f 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -187,7 +187,7 @@ static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie, { struct inotify_kernel_event *kevent; - kevent = kmem_cache_alloc(event_cachep, GFP_KERNEL); + kevent = kmem_cache_alloc(event_cachep, GFP_NOFS); if (unlikely(!kevent)) return NULL; diff --git a/fs/ioprio.c b/fs/ioprio.c index 93aa571..78b1dea 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -44,6 +44,9 @@ static int set_task_ioprio(struct task_struct *task, int ioprio) task->ioprio = ioprio; ioc = task->io_context; + /* see wmb() in current_io_context() */ + smp_read_barrier_depends(); + if (ioc && ioc->set_ioprio) ioc->set_ioprio(ioc, ioprio); @@ -111,9 +114,9 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) continue; ret = set_task_ioprio(p, ioprio); if (ret) - break; + goto free_uid; } while_each_thread(g, p); - +free_uid: if (who) free_uid(user); break; @@ -137,6 +140,29 @@ out: return ret; } +int ioprio_best(unsigned short aprio, unsigned short bprio) +{ + unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); + unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); + + if (!ioprio_valid(aprio)) + return bprio; + if (!ioprio_valid(bprio)) + return aprio; + + if (aclass == IOPRIO_CLASS_NONE) + aclass = IOPRIO_CLASS_BE; + if (bclass == IOPRIO_CLASS_NONE) + bclass = IOPRIO_CLASS_BE; + + if (aclass == bclass) + return min(aprio, bprio); + if (aclass > bclass) + return bprio; + else + return aprio; +} + asmlinkage long sys_ioprio_get(int which, int who) { struct task_struct *g, *p; diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 0971814..42da607 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -261,7 +261,7 @@ void journal_commit_transaction(journal_t *journal) struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } @@ -745,14 +745,14 @@ restart_loop: * Otherwise, we can just throw away the frozen data now. */ if (jh->b_committed_data) { - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; if (jh->b_frozen_data) { jh->b_committed_data = jh->b_frozen_data; jh->b_frozen_data = NULL; } } else if (jh->b_frozen_data) { - kfree(jh->b_frozen_data); + jbd_slab_free(jh->b_frozen_data, bh->b_size); jh->b_frozen_data = NULL; } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 8c9b28d..f66724c 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -84,6 +84,7 @@ EXPORT_SYMBOL(journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); +static int journal_create_jbd_slab(size_t slab_size); /* * Helper function used to manage commit timeouts @@ -328,10 +329,10 @@ repeat: char *tmp; jbd_unlock_bh_state(bh_in); - tmp = jbd_rep_kmalloc(bh_in->b_size, GFP_NOFS); + tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS); jbd_lock_bh_state(bh_in); if (jh_in->b_frozen_data) { - kfree(tmp); + jbd_slab_free(tmp, bh_in->b_size); goto repeat; } @@ -1069,17 +1070,17 @@ static int load_superblock(journal_t *journal) int journal_load(journal_t *journal) { int err; + journal_superblock_t *sb; err = load_superblock(journal); if (err) return err; + sb = journal->j_superblock; /* If this is a V2 superblock, then we have to check the * features flags on it. */ if (journal->j_format_version >= 2) { - journal_superblock_t *sb = journal->j_superblock; - if ((sb->s_feature_ro_compat & ~cpu_to_be32(JFS_KNOWN_ROCOMPAT_FEATURES)) || (sb->s_feature_incompat & @@ -1090,6 +1091,13 @@ int journal_load(journal_t *journal) } } + /* + * Create a slab for this blocksize + */ + err = journal_create_jbd_slab(cpu_to_be32(sb->s_blocksize)); + if (err) + return err; + /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (journal_recover(journal)) @@ -1612,6 +1620,77 @@ void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry) } /* + * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed + * and allocate frozen and commit buffers from these slabs. + * + * Reason for doing this is to avoid, SLAB_DEBUG - since it could + * cause bh to cross page boundary. + */ + +#define JBD_MAX_SLABS 5 +#define JBD_SLAB_INDEX(size) (size >> 11) + +static kmem_cache_t *jbd_slab[JBD_MAX_SLABS]; +static const char *jbd_slab_names[JBD_MAX_SLABS] = { + "jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k" +}; + +static void journal_destroy_jbd_slabs(void) +{ + int i; + + for (i = 0; i < JBD_MAX_SLABS; i++) { + if (jbd_slab[i]) + kmem_cache_destroy(jbd_slab[i]); + jbd_slab[i] = NULL; + } +} + +static int journal_create_jbd_slab(size_t slab_size) +{ + int i = JBD_SLAB_INDEX(slab_size); + + BUG_ON(i >= JBD_MAX_SLABS); + + /* + * Check if we already have a slab created for this size + */ + if (jbd_slab[i]) + return 0; + + /* + * Create a slab and force alignment to be same as slabsize - + * this will make sure that allocations won't cross the page + * boundary. + */ + jbd_slab[i] = kmem_cache_create(jbd_slab_names[i], + slab_size, slab_size, 0, NULL, NULL); + if (!jbd_slab[i]) { + printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n"); + return -ENOMEM; + } + return 0; +} + +void * jbd_slab_alloc(size_t size, gfp_t flags) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL); +} + +void jbd_slab_free(void *ptr, size_t size) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + kmem_cache_free(jbd_slab[idx], ptr); +} + +/* * Journal_head storage management */ static kmem_cache_t *journal_head_cache; @@ -1799,13 +1878,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh) printk(KERN_WARNING "%s: freeing " "b_frozen_data\n", __FUNCTION__); - kfree(jh->b_frozen_data); + jbd_slab_free(jh->b_frozen_data, bh->b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing " "b_committed_data\n", __FUNCTION__); - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); } bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ @@ -1961,6 +2040,7 @@ static void journal_destroy_caches(void) journal_destroy_revoke_caches(); journal_destroy_journal_head_cache(); journal_destroy_handle_cache(); + journal_destroy_jbd_slabs(); } static int __init journal_init(void) diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 508b2ea..de2e4cb 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -666,8 +666,9 @@ repeat: if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); jbd_unlock_bh_state(bh); - frozen_buffer = jbd_kmalloc(jh2bh(jh)->b_size, - GFP_NOFS); + frozen_buffer = + jbd_slab_alloc(jh2bh(jh)->b_size, + GFP_NOFS); if (!frozen_buffer) { printk(KERN_EMERG "%s: OOM for frozen_buffer\n", @@ -879,7 +880,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh) repeat: if (!jh->b_committed_data) { - committed_data = jbd_kmalloc(jh2bh(jh)->b_size, GFP_NOFS); + committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { printk(KERN_EMERG "%s: No memory for committed data\n", __FUNCTION__); @@ -906,7 +907,7 @@ repeat: out: journal_put_journal_head(jh); if (unlikely(committed_data)) - kfree(committed_data); + jbd_slab_free(committed_data, bh->b_size); return err; } diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 43e3f56..a223cf4 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -168,16 +168,15 @@ void jfs_dirty_inode(struct inode *inode) set_cflag(COMMIT_Dirty, inode); } -static int -jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks, - struct buffer_head *bh_result, int create) +int jfs_get_block(struct inode *ip, sector_t lblock, + struct buffer_head *bh_result, int create) { s64 lblock64 = lblock; int rc = 0; xad_t xad; s64 xaddr; int xflag; - s32 xlen = max_blocks; + s32 xlen = bh_result->b_size >> ip->i_blkbits; /* * Take appropriate lock on inode @@ -188,7 +187,7 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks, IREAD_LOCK(ip); if (((lblock64 << ip->i_sb->s_blocksize_bits) < ip->i_size) && - (!xtLookup(ip, lblock64, max_blocks, &xflag, &xaddr, &xlen, 0)) && + (!xtLookup(ip, lblock64, xlen, &xflag, &xaddr, &xlen, 0)) && xaddr) { if (xflag & XAD_NOTRECORDED) { if (!create) @@ -255,13 +254,6 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks, return rc; } -static int jfs_get_block(struct inode *ip, sector_t lblock, - struct buffer_head *bh_result, int create) -{ - return jfs_get_blocks(ip, lblock, bh_result->b_size >> ip->i_blkbits, - bh_result, create); -} - static int jfs_writepage(struct page *page, struct writeback_control *wbc) { return nobh_writepage(page, jfs_get_block, wbc); diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index b5c7da6..1fc48df 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -32,6 +32,7 @@ extern void jfs_truncate_nolock(struct inode *, loff_t); extern void jfs_free_zero_link(struct inode *); extern struct dentry *jfs_get_parent(struct dentry *dentry); extern void jfs_set_inode_flags(struct inode *); +extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int); extern const struct address_space_operations jfs_aops; extern struct inode_operations jfs_dir_inode_operations; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4f6cfeb..143bcd1 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -26,6 +26,7 @@ #include <linux/moduleparam.h> #include <linux/kthread.h> #include <linux/posix_acl.h> +#include <linux/buffer_head.h> #include <asm/uaccess.h> #include <linux/seq_file.h> @@ -298,7 +299,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, break; } -#if defined(CONFIG_QUOTA) +#ifdef CONFIG_QUOTA case Opt_quota: case Opt_usrquota: *flag |= JFS_USRQUOTA; @@ -597,7 +598,7 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs) if (sbi->flag & JFS_NOINTEGRITY) seq_puts(seq, ",nointegrity"); -#if defined(CONFIG_QUOTA) +#ifdef CONFIG_QUOTA if (sbi->flag & JFS_USRQUOTA) seq_puts(seq, ",usrquota"); @@ -608,6 +609,113 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs) return 0; } +#ifdef CONFIG_QUOTA + +/* Read data from quotafile - avoid pagecache and such because we cannot afford + * acquiring the locks... As quota files are never truncated and quota code + * itself serializes the operations (and noone else should touch the files) + * we don't have to be afraid of races */ +static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data, + size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> sb->s_blocksize_bits; + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t toread; + struct buffer_head tmp_bh; + struct buffer_head *bh; + loff_t i_size = i_size_read(inode); + + if (off > i_size) + return 0; + if (off+len > i_size) + len = i_size-off; + toread = len; + while (toread > 0) { + tocopy = sb->s_blocksize - offset < toread ? + sb->s_blocksize - offset : toread; + + tmp_bh.b_state = 0; + tmp_bh.b_size = 1 << inode->i_blkbits; + err = jfs_get_block(inode, blk, &tmp_bh, 0); + if (err) + return err; + if (!buffer_mapped(&tmp_bh)) /* A hole? */ + memset(data, 0, tocopy); + else { + bh = sb_bread(sb, tmp_bh.b_blocknr); + if (!bh) + return -EIO; + memcpy(data, bh->b_data+offset, tocopy); + brelse(bh); + } + offset = 0; + toread -= tocopy; + data += tocopy; + blk++; + } + return len; +} + +/* Write to quotafile */ +static ssize_t jfs_quota_write(struct super_block *sb, int type, + const char *data, size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> sb->s_blocksize_bits; + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t towrite = len; + struct buffer_head tmp_bh; + struct buffer_head *bh; + + mutex_lock(&inode->i_mutex); + while (towrite > 0) { + tocopy = sb->s_blocksize - offset < towrite ? + sb->s_blocksize - offset : towrite; + + tmp_bh.b_state = 0; + tmp_bh.b_size = 1 << inode->i_blkbits; + err = jfs_get_block(inode, blk, &tmp_bh, 1); + if (err) + goto out; + if (offset || tocopy != sb->s_blocksize) + bh = sb_bread(sb, tmp_bh.b_blocknr); + else + bh = sb_getblk(sb, tmp_bh.b_blocknr); + if (!bh) { + err = -EIO; + goto out; + } + lock_buffer(bh); + memcpy(bh->b_data+offset, data, tocopy); + flush_dcache_page(bh->b_page); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + brelse(bh); + offset = 0; + towrite -= tocopy; + data += tocopy; + blk++; + } +out: + if (len == towrite) + return err; + if (inode->i_size < off+len-towrite) + i_size_write(inode, off+len-towrite); + inode->i_version++; + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + mutex_unlock(&inode->i_mutex); + return len - towrite; +} + +#endif + static struct super_operations jfs_super_operations = { .alloc_inode = jfs_alloc_inode, .destroy_inode = jfs_destroy_inode, @@ -621,7 +729,11 @@ static struct super_operations jfs_super_operations = { .unlockfs = jfs_unlockfs, .statfs = jfs_statfs, .remount_fs = jfs_remount, - .show_options = jfs_show_options + .show_options = jfs_show_options, +#ifdef CONFIG_QUOTA + .quota_read = jfs_quota_read, + .quota_write = jfs_quota_write, +#endif }; static struct export_operations jfs_export_operations = { diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index baf5ae5..c9d4197 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -638,9 +638,6 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data) if (task->tk_status < 0) { /* RPC error: Re-insert for retransmission */ timeout = 10 * HZ; - } else if (block->b_done) { - /* Block already removed, kill it for real */ - timeout = 0; } else { /* Call was successful, now wait for client callback */ timeout = 60 * HZ; @@ -709,13 +706,10 @@ nlmsvc_retry_blocked(void) break; if (time_after(block->b_when,jiffies)) break; - dprintk("nlmsvc_retry_blocked(%p, when=%ld, done=%d)\n", - block, block->b_when, block->b_done); + dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n", + block, block->b_when); kref_get(&block->b_count); - if (block->b_done) - nlmsvc_unlink_block(block); - else - nlmsvc_grant_blocked(block); + nlmsvc_grant_blocked(block); nlmsvc_release_block(block); } diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 2a4df9b..01b4db9e 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -237,19 +237,22 @@ static int nlm_traverse_files(struct nlm_host *host, int action) { struct nlm_file *file, **fp; - int i; + int i, ret = 0; mutex_lock(&nlm_file_mutex); for (i = 0; i < FILE_NRHASH; i++) { fp = nlm_files + i; while ((file = *fp) != NULL) { + file->f_count++; + mutex_unlock(&nlm_file_mutex); + /* Traverse locks, blocks and shares of this file * and update file->f_locks count */ - if (nlm_inspect_file(host, file, action)) { - mutex_unlock(&nlm_file_mutex); - return 1; - } + if (nlm_inspect_file(host, file, action)) + ret = 1; + mutex_lock(&nlm_file_mutex); + file->f_count--; /* No more references to this file. Let go of it. */ if (!file->f_blocks && !file->f_locks && !file->f_shares && !file->f_count) { @@ -262,7 +265,7 @@ nlm_traverse_files(struct nlm_host *host, int action) } } mutex_unlock(&nlm_file_mutex); - return 0; + return ret; } /* @@ -1421,8 +1421,9 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp) if (!leases_enable) goto out; - error = lease_alloc(filp, arg, &fl); - if (error) + error = -ENOMEM; + fl = locks_alloc_lock(); + if (fl == NULL) goto out; locks_copy_lock(fl, lease); @@ -1430,6 +1431,7 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp) locks_insert_lock(before, fl); *flp = fl; + error = 0; out: return error; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 9ea91c5..330ff9f 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -204,6 +204,8 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) /* * Allocate the buffer map to keep the superblock small. */ + if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) + goto out_illegal_sb; i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh); map = kmalloc(i, GFP_KERNEL); if (!map) @@ -263,7 +265,7 @@ out_no_root: out_no_bitmap: printk("MINIX-fs: bad superblock or unable to read bitmaps\n"); - out_freemap: +out_freemap: for (i = 0; i < sbi->s_imap_blocks; i++) brelse(sbi->s_imap[i]); for (i = 0; i < sbi->s_zmap_blocks; i++) @@ -276,11 +278,16 @@ out_no_map: printk("MINIX-fs: can't allocate map\n"); goto out_release; +out_illegal_sb: + if (!silent) + printk("MINIX-fs: bad superblock\n"); + goto out_release; + out_no_fs: if (!silent) printk("VFS: Can't find a Minix or Minix V2 filesystem " "on device %s\n", s->s_id); - out_release: +out_release: brelse(bh); goto out; @@ -290,7 +297,7 @@ out_bad_hblock: out_bad_sb: printk("MINIX-fs: unable to read superblock\n"); - out: +out: s->s_fs_info = NULL; kfree(sbi); return -EINVAL; @@ -159,7 +159,7 @@ char * getname(const char __user * filename) #ifdef CONFIG_AUDITSYSCALL void putname(const char *name) { - if (unlikely(current->audit_context)) + if (unlikely(!audit_dummy_context())) audit_putname(name); else __putname(name); @@ -227,10 +227,10 @@ int generic_permission(struct inode *inode, int mask, int permission(struct inode *inode, int mask, struct nameidata *nd) { + umode_t mode = inode->i_mode; int retval, submask; if (mask & MAY_WRITE) { - umode_t mode = inode->i_mode; /* * Nobody gets write access to a read-only fs. @@ -247,6 +247,13 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) } + /* + * MAY_EXEC on regular files requires special handling: We override + * filesystem execute permissions if the mode bits aren't set. + */ + if ((mask & MAY_EXEC) && S_ISREG(mode) && !(mode & S_IXUGO)) + return -EACCES; + /* Ordinary permission routines do not understand MAY_APPEND. */ submask = mask & ~MAY_APPEND; if (inode->i_op && inode->i_op->permission) @@ -1125,7 +1132,7 @@ static int fastcall do_path_lookup(int dfd, const char *name, retval = link_path_walk(name, nd); out: if (likely(retval == 0)) { - if (unlikely(current->audit_context && nd && nd->dentry && + if (unlikely(!audit_dummy_context() && nd && nd->dentry && nd->dentry->d_inode)) audit_inode(name, nd->dentry->d_inode); } @@ -1357,7 +1364,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir) return -ENOENT; BUG_ON(victim->d_parent->d_inode != dir); - audit_inode_child(victim->d_name.name, victim->d_inode, dir->i_ino); + audit_inode_child(victim->d_name.name, victim->d_inode, dir); error = permission(dir,MAY_WRITE | MAY_EXEC, NULL); if (error) @@ -1659,6 +1666,7 @@ do_last: * It already exists. */ mutex_unlock(&dir->d_inode->i_mutex); + audit_inode_update(path.dentry->d_inode); error = -EEXIST; if (flag & O_EXCL) @@ -1669,6 +1677,7 @@ do_last: if (flag & O_NOFOLLOW) goto exit_dput; } + error = -ENOENT; if (!path.dentry->d_inode) goto exit_dput; @@ -1765,6 +1774,8 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir) if (nd->last_type != LAST_NORM) goto fail; nd->flags &= ~LOOKUP_PARENT; + nd->flags |= LOOKUP_CREATE; + nd->intent.open.flags = O_EXCL; /* * Do the final lookup. diff --git a/fs/nfs/file.c b/fs/nfs/file.c index cc2b874..48e8928 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -312,7 +312,13 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset) static int nfs_release_page(struct page *page, gfp_t gfp) { - return !nfs_wb_page(page->mapping->host, page); + if (gfp & __GFP_FS) + return !nfs_wb_page(page->mapping->host, page); + else + /* + * Avoid deadlock on nfs_wait_on_request(). + */ + return 0; } const struct address_space_operations nfs_file_aops = { diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b81e7ed..07a5dd5 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -130,9 +130,7 @@ nfs_idmap_delete(struct nfs4_client *clp) if (!idmap) return; - dput(idmap->idmap_dentry); - idmap->idmap_dentry = NULL; - rpc_unlink(idmap->idmap_path); + rpc_unlink(idmap->idmap_dentry); clp->cl_idmap = NULL; kfree(idmap); } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 19b98ca..86b3169 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -51,7 +51,7 @@ char *nfs_path(const char *base, const struct dentry *dentry, namelen = dentry->d_name.len; buflen -= namelen + 1; if (buflen < 0) - goto Elong; + goto Elong_unlock; end -= namelen; memcpy(end, dentry->d_name.name, namelen); *--end = '/'; @@ -68,6 +68,8 @@ char *nfs_path(const char *base, const struct dentry *dentry, end -= namelen; memcpy(end, base, namelen); return end; +Elong_unlock: + spin_unlock(&dcache_lock); Elong: return ERR_PTR(-ENAMETOOLONG); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e6ee97f..153898e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2668,7 +2668,7 @@ out: nfs4_set_cached_acl(inode, acl); } -static inline ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) { struct page *pages[NFS4ACL_MAXPAGES]; struct nfs_getaclargs args = { @@ -2721,6 +2721,19 @@ out_free: return ret; } +static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +{ + struct nfs4_exception exception = { }; + ssize_t ret; + do { + ret = __nfs4_get_acl_uncached(inode, buf, buflen); + if (ret >= 0) + break; + ret = nfs4_handle_exception(NFS_SERVER(inode), ret, &exception); + } while (exception.retry); + return ret; +} + static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); @@ -2737,7 +2750,7 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen) return nfs4_get_acl_uncached(inode, buf, buflen); } -static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); struct page *pages[NFS4ACL_MAXPAGES]; @@ -2763,6 +2776,18 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen return ret; } +static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(NFS_SERVER(inode), + __nfs4_proc_set_acl(inode, buf, buflen), + &exception); + } while (exception.retry); + return err; +} + static int nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1750d99..730ec8f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3355,7 +3355,7 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n struct kvec *iov = rcvbuf->head; unsigned int nr, pglen = rcvbuf->page_len; uint32_t *end, *entry, *p, *kaddr; - uint32_t len, attrlen; + uint32_t len, attrlen, xlen; int hdrlen, recvd, status; status = decode_op_hdr(xdr, OP_READDIR); @@ -3377,10 +3377,10 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n BUG_ON(pglen + readdir->pgbase > PAGE_CACHE_SIZE); kaddr = p = (uint32_t *) kmap_atomic(page, KM_USER0); - end = (uint32_t *) ((char *)p + pglen + readdir->pgbase); + end = p + ((pglen + readdir->pgbase) >> 2); entry = p; for (nr = 0; *p++; nr++) { - if (p + 3 > end) + if (end - p < 3) goto short_pkt; dprintk("cookie = %Lu, ", *((unsigned long long *)p)); p += 2; /* cookie */ @@ -3389,18 +3389,19 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n printk(KERN_WARNING "NFS: giant filename in readdir (len 0x%x)\n", len); goto err_unmap; } - dprintk("filename = %*s\n", len, (char *)p); - p += XDR_QUADLEN(len); - if (p + 1 > end) + xlen = XDR_QUADLEN(len); + if (end - p < xlen + 1) goto short_pkt; + dprintk("filename = %*s\n", len, (char *)p); + p += xlen; len = ntohl(*p++); /* bitmap length */ - p += len; - if (p + 1 > end) + if (end - p < len + 1) goto short_pkt; + p += len; attrlen = XDR_QUADLEN(ntohl(*p++)); - p += attrlen; /* attributes */ - if (p + 2 > end) + if (end - p < attrlen + 2) goto short_pkt; + p += attrlen; /* attributes */ entry = p; } if (!nr && (entry[0] != 0 || entry[1] == 0)) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 52bf634..da9cf11 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -63,7 +63,7 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) return p; } -void nfs_readdata_free(struct nfs_read_data *p) +static void nfs_readdata_free(struct nfs_read_data *p) { if (p && (p->pagevec != &p->page_array[0])) kfree(p->pagevec); @@ -116,10 +116,17 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; base &= ~PAGE_CACHE_MASK; pglen = PAGE_CACHE_SIZE - base; - if (pglen < remainder) + for (;;) { + if (remainder <= pglen) { + memclear_highpage_flush(*pages, base, remainder); + break; + } memclear_highpage_flush(*pages, base, pglen); - else - memclear_highpage_flush(*pages, base, remainder); + pages++; + remainder -= pglen; + pglen = PAGE_CACHE_SIZE; + base = 0; + } } /* @@ -476,6 +483,8 @@ static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) unsigned int base = data->args.pgbase; struct page **pages; + if (data->res.eof) + count = data->args.count; if (unlikely(count == 0)) return; pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; @@ -483,11 +492,7 @@ static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) count += base; for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) SetPageUptodate(*pages); - /* - * Was this an eof or a short read? If the latter, don't mark the page - * as uptodate yet. - */ - if (count > 0 && (data->res.eof || data->args.count == data->res.count)) + if (count != 0) SetPageUptodate(*pages); } @@ -502,6 +507,8 @@ static void nfs_readpage_set_pages_error(struct nfs_read_data *data) count += base; for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) SetPageError(*pages); + if (count != 0) + SetPageError(*pages); } /* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 86bac6a..5077499 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -137,7 +137,7 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) return p; } -void nfs_writedata_free(struct nfs_write_data *p) +static void nfs_writedata_free(struct nfs_write_data *p) { if (p && (p->pagevec != &p->page_array[0])) kfree(p->pagevec); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index ecc439d..501d838 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -187,6 +187,11 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) goto out; } + /* Set user creds for this exportpoint */ + error = nfserrno(nfsd_setuser(rqstp, exp)); + if (error) + goto out; + /* * Look up the dentry using the NFS file handle. */ @@ -241,16 +246,17 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) dprintk("nfsd: fh_verify - just checking\n"); dentry = fhp->fh_dentry; exp = fhp->fh_export; + /* Set user creds for this exportpoint; necessary even + * in the "just checking" case because this may be a + * filehandle that was created by fh_compose, and that + * is about to be used in another nfsv4 compound + * operation */ + error = nfserrno(nfsd_setuser(rqstp, exp)); + if (error) + goto out; } cache_get(&exp->h); - /* Set user creds for this exportpoint; necessary even in the "just - * checking" case because this may be a filehandle that was created by - * fh_compose, and that is about to be used in another nfsv4 compound - * operation */ - error = nfserrno(nfsd_setuser(rqstp, exp)); - if (error) - goto out; error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type); if (error) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 1b8346d..9503240 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2375,7 +2375,6 @@ leave: mlog(0, "returning %d\n", ret); return ret; } -EXPORT_SYMBOL_GPL(dlm_migrate_lockres); int dlm_lock_basts_flushed(struct dlm_ctxt *dlm, struct dlm_lock *lock) { diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index b0c3134..37be4b2 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -155,7 +155,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, else status = dlm_get_unlock_actions(dlm, res, lock, lksb, &actions); - if (status != DLM_NORMAL) + if (status != DLM_NORMAL && (status != DLM_CANCELGRANT || !master_node)) goto leave; /* By now this has been masked out of cancel requests. */ @@ -183,8 +183,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, spin_lock(&lock->spinlock); /* if the master told us the lock was already granted, * let the ast handle all of these actions */ - if (status == DLM_NORMAL && - lksb->status == DLM_CANCELGRANT) { + if (status == DLM_CANCELGRANT) { actions &= ~(DLM_UNLOCK_REMOVE_LOCK| DLM_UNLOCK_REGRANT_LOCK| DLM_UNLOCK_CLEAR_CONVERT_TYPE); @@ -349,14 +348,9 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm, vec, veclen, owner, &status); if (tmpret >= 0) { // successfully sent and received - if (status == DLM_CANCELGRANT) - ret = DLM_NORMAL; - else if (status == DLM_FORWARD) { + if (status == DLM_FORWARD) mlog(0, "master was in-progress. retry\n"); - ret = DLM_FORWARD; - } else - ret = status; - lksb->status = status; + ret = status; } else { mlog_errno(tmpret); if (dlm_is_host_down(tmpret)) { @@ -372,7 +366,6 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm, /* something bad. this will BUG in ocfs2 */ ret = dlm_err_to_dlm_status(tmpret); } - lksb->status = ret; } return ret; @@ -483,6 +476,10 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data) /* lock was found on queue */ lksb = lock->lksb; + if (flags & (LKM_VALBLK|LKM_PUT_LVB) && + lock->ml.type != LKM_EXMODE) + flags &= ~(LKM_VALBLK|LKM_PUT_LVB); + /* unlockast only called on originating node */ if (flags & LKM_PUT_LVB) { lksb->flags |= DLM_LKSB_PUT_LVB; @@ -507,11 +504,8 @@ not_found: "cookie=%u:%llu\n", dlm_get_lock_cookie_node(unlock->cookie), dlm_get_lock_cookie_seq(unlock->cookie)); - else { - /* send the lksb->status back to the other node */ - status = lksb->status; + else dlm_lock_put(lock); - } leave: if (res) @@ -533,26 +527,22 @@ static enum dlm_status dlm_get_cancel_actions(struct dlm_ctxt *dlm, if (dlm_lock_on_list(&res->blocked, lock)) { /* cancel this outright */ - lksb->status = DLM_NORMAL; status = DLM_NORMAL; *actions = (DLM_UNLOCK_CALL_AST | DLM_UNLOCK_REMOVE_LOCK); } else if (dlm_lock_on_list(&res->converting, lock)) { /* cancel the request, put back on granted */ - lksb->status = DLM_NORMAL; status = DLM_NORMAL; *actions = (DLM_UNLOCK_CALL_AST | DLM_UNLOCK_REMOVE_LOCK | DLM_UNLOCK_REGRANT_LOCK | DLM_UNLOCK_CLEAR_CONVERT_TYPE); } else if (dlm_lock_on_list(&res->granted, lock)) { - /* too late, already granted. DLM_CANCELGRANT */ - lksb->status = DLM_CANCELGRANT; - status = DLM_NORMAL; + /* too late, already granted. */ + status = DLM_CANCELGRANT; *actions = DLM_UNLOCK_CALL_AST; } else { mlog(ML_ERROR, "lock to cancel is not on any list!\n"); - lksb->status = DLM_IVLOCKID; status = DLM_IVLOCKID; *actions = 0; } @@ -569,13 +559,11 @@ static enum dlm_status dlm_get_unlock_actions(struct dlm_ctxt *dlm, /* unlock request */ if (!dlm_lock_on_list(&res->granted, lock)) { - lksb->status = DLM_DENIED; status = DLM_DENIED; dlm_error(status); *actions = 0; } else { /* unlock granted lock */ - lksb->status = DLM_NORMAL; status = DLM_NORMAL; *actions = (DLM_UNLOCK_FREE_LOCK | DLM_UNLOCK_CALL_AST | @@ -632,6 +620,8 @@ retry: spin_lock(&res->spinlock); is_master = (res->owner == dlm->node_num); + if (flags & LKM_VALBLK && lock->ml.type != LKM_EXMODE) + flags &= ~LKM_VALBLK; spin_unlock(&res->spinlock); if (is_master) { @@ -665,7 +655,7 @@ retry: } if (call_ast) { - mlog(0, "calling unlockast(%p, %d)\n", data, lksb->status); + mlog(0, "calling unlockast(%p, %d)\n", data, status); if (is_master) { /* it is possible that there is one last bast * pending. make sure it is flushed, then @@ -677,9 +667,12 @@ retry: wait_event(dlm->ast_wq, dlm_lock_basts_flushed(dlm, lock)); } - (*unlockast)(data, lksb->status); + (*unlockast)(data, status); } + if (status == DLM_CANCELGRANT) + status = DLM_NORMAL; + if (status == DLM_NORMAL) { mlog(0, "kicking the thread\n"); dlm_kick_thread(dlm, res); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 0d1973e..1f17a4d 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -840,6 +840,12 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, mlog(0, "Allocating %u clusters for a new window.\n", ocfs2_local_alloc_window_bits(osb)); + + /* Instruct the allocation code to try the most recently used + * cluster group. We'll re-record the group used this pass + * below. */ + ac->ac_last_group = osb->la_last_gd; + /* we used the generic suballoc reserve function, but we set * everything up nicely, so there's no reason why we can't use * the more specific cluster api to claim bits. */ @@ -852,6 +858,8 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, goto bail; } + osb->la_last_gd = ac->ac_last_group; + la->la_bm_off = cpu_to_le32(cluster_off); alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count); /* just in case... In the future when we find space ourselves, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index cd4a6f2..0462a7f 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -197,7 +197,6 @@ struct ocfs2_super struct ocfs2_node_map recovery_map; struct ocfs2_node_map umount_map; - u32 num_clusters; u64 root_blkno; u64 system_dir_blkno; u64 bitmap_blkno; @@ -237,6 +236,7 @@ struct ocfs2_super enum ocfs2_local_alloc_state local_alloc_state; struct buffer_head *local_alloc_bh; + u64 la_last_gd; /* Next two fields are for local node slot recovery during * mount. */ diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 1955230..9d91e66 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -70,12 +70,6 @@ static int ocfs2_block_group_search(struct inode *inode, struct buffer_head *group_bh, u32 bits_wanted, u32 min_bits, u16 *bit_off, u16 *bits_found); -static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, - u32 bits_wanted, - u32 min_bits, - u16 *bit_off, - unsigned int *num_bits, - u64 *bg_blkno); static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, struct ocfs2_alloc_context *ac, u32 bits_wanted, @@ -85,11 +79,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, u64 *bg_blkno); static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, int nr); -static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, - struct buffer_head *bg_bh, - unsigned int bits_wanted, - u16 *bit_off, - u16 *bits_found); static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle, struct inode *alloc_inode, struct ocfs2_group_desc *bg, @@ -143,6 +132,64 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl) return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc); } +/* somewhat more expensive than our other checks, so use sparingly. */ +static int ocfs2_check_group_descriptor(struct super_block *sb, + struct ocfs2_dinode *di, + struct ocfs2_group_desc *gd) +{ + unsigned int max_bits; + + if (!OCFS2_IS_VALID_GROUP_DESC(gd)) { + OCFS2_RO_ON_INVALID_GROUP_DESC(sb, gd); + return -EIO; + } + + if (di->i_blkno != gd->bg_parent_dinode) { + ocfs2_error(sb, "Group descriptor # %llu has bad parent " + "pointer (%llu, expected %llu)", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + (unsigned long long)le64_to_cpu(gd->bg_parent_dinode), + (unsigned long long)le64_to_cpu(di->i_blkno)); + return -EIO; + } + + max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc); + if (le16_to_cpu(gd->bg_bits) > max_bits) { + ocfs2_error(sb, "Group descriptor # %llu has bit count of %u", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + le16_to_cpu(gd->bg_bits)); + return -EIO; + } + + if (le16_to_cpu(gd->bg_chain) >= + le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) { + ocfs2_error(sb, "Group descriptor # %llu has bad chain %u", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + le16_to_cpu(gd->bg_chain)); + return -EIO; + } + + if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) { + ocfs2_error(sb, "Group descriptor # %llu has bit count %u but " + "claims that %u are free", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + le16_to_cpu(gd->bg_bits), + le16_to_cpu(gd->bg_free_bits_count)); + return -EIO; + } + + if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) { + ocfs2_error(sb, "Group descriptor # %llu has bit count %u but " + "max bitmap bits of %u", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + le16_to_cpu(gd->bg_bits), + 8 * le16_to_cpu(gd->bg_size)); + return -EIO; + } + + return 0; +} + static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle, struct inode *alloc_inode, struct buffer_head *bg_bh, @@ -663,6 +710,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, struct buffer_head *bg_bh, unsigned int bits_wanted, + unsigned int total_bits, u16 *bit_off, u16 *bits_found) { @@ -679,10 +727,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, found = start = best_offset = best_size = 0; bitmap = bg->bg_bitmap; - while((offset = ocfs2_find_next_zero_bit(bitmap, - le16_to_cpu(bg->bg_bits), - start)) != -1) { - if (offset == le16_to_cpu(bg->bg_bits)) + while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) { + if (offset == total_bits) break; if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) { @@ -911,14 +957,35 @@ static int ocfs2_cluster_group_search(struct inode *inode, { int search = -ENOSPC; int ret; - struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) group_bh->b_data; + struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data; u16 tmp_off, tmp_found; + unsigned int max_bits, gd_cluster_off; BUG_ON(!ocfs2_is_cluster_bitmap(inode)); - if (bg->bg_free_bits_count) { + if (gd->bg_free_bits_count) { + max_bits = le16_to_cpu(gd->bg_bits); + + /* Tail groups in cluster bitmaps which aren't cpg + * aligned are prone to partial extention by a failed + * fs resize. If the file system resize never got to + * update the dinode cluster count, then we don't want + * to trust any clusters past it, regardless of what + * the group descriptor says. */ + gd_cluster_off = ocfs2_blocks_to_clusters(inode->i_sb, + le64_to_cpu(gd->bg_blkno)); + if ((gd_cluster_off + max_bits) > + OCFS2_I(inode)->ip_clusters) { + max_bits = OCFS2_I(inode)->ip_clusters - gd_cluster_off; + mlog(0, "Desc %llu, bg_bits %u, clusters %u, use %u\n", + (unsigned long long)le64_to_cpu(gd->bg_blkno), + le16_to_cpu(gd->bg_bits), + OCFS2_I(inode)->ip_clusters, max_bits); + } + ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), group_bh, bits_wanted, + max_bits, &tmp_off, &tmp_found); if (ret) return ret; @@ -951,17 +1018,109 @@ static int ocfs2_block_group_search(struct inode *inode, if (bg->bg_free_bits_count) ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), group_bh, bits_wanted, + le16_to_cpu(bg->bg_bits), bit_off, bits_found); return ret; } +static int ocfs2_alloc_dinode_update_counts(struct inode *inode, + struct ocfs2_journal_handle *handle, + struct buffer_head *di_bh, + u32 num_bits, + u16 chain) +{ + int ret; + u32 tmp_used; + struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; + struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain; + + ret = ocfs2_journal_access(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + tmp_used = le32_to_cpu(di->id1.bitmap1.i_used); + di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used); + le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits); + + ret = ocfs2_journal_dirty(handle, di_bh); + if (ret < 0) + mlog_errno(ret); + +out: + return ret; +} + +static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac, + u32 bits_wanted, + u32 min_bits, + u16 *bit_off, + unsigned int *num_bits, + u64 gd_blkno, + u16 *bits_left) +{ + int ret; + u16 found; + struct buffer_head *group_bh = NULL; + struct ocfs2_group_desc *gd; + struct inode *alloc_inode = ac->ac_inode; + struct ocfs2_journal_handle *handle = ac->ac_handle; + + ret = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb), gd_blkno, + &group_bh, OCFS2_BH_CACHED, alloc_inode); + if (ret < 0) { + mlog_errno(ret); + return ret; + } + + gd = (struct ocfs2_group_desc *) group_bh->b_data; + if (!OCFS2_IS_VALID_GROUP_DESC(gd)) { + OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, gd); + ret = -EIO; + goto out; + } + + ret = ac->ac_group_search(alloc_inode, group_bh, bits_wanted, min_bits, + bit_off, &found); + if (ret < 0) { + if (ret != -ENOSPC) + mlog_errno(ret); + goto out; + } + + *num_bits = found; + + ret = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, ac->ac_bh, + *num_bits, + le16_to_cpu(gd->bg_chain)); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh, + *bit_off, *num_bits); + if (ret < 0) + mlog_errno(ret); + + *bits_left = le16_to_cpu(gd->bg_free_bits_count); + +out: + brelse(group_bh); + + return ret; +} + static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, u32 bits_wanted, u32 min_bits, u16 *bit_off, unsigned int *num_bits, - u64 *bg_blkno) + u64 *bg_blkno, + u16 *bits_left) { int status; u16 chain, tmp_bits; @@ -988,9 +1147,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, goto bail; } bg = (struct ocfs2_group_desc *) group_bh->b_data; - if (!OCFS2_IS_VALID_GROUP_DESC(bg)) { - OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg); - status = -EIO; + status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg); + if (status) { + mlog_errno(status); goto bail; } @@ -1018,9 +1177,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, goto bail; } bg = (struct ocfs2_group_desc *) group_bh->b_data; - if (!OCFS2_IS_VALID_GROUP_DESC(bg)) { - OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg); - status = -EIO; + status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg); + if (status) { + mlog_errno(status); goto bail; } } @@ -1099,6 +1258,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, (unsigned long long)fe->i_blkno); *bg_blkno = le64_to_cpu(bg->bg_blkno); + *bits_left = le16_to_cpu(bg->bg_free_bits_count); bail: if (group_bh) brelse(group_bh); @@ -1120,6 +1280,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, { int status; u16 victim, i; + u16 bits_left = 0; + u64 hint_blkno = ac->ac_last_group; struct ocfs2_chain_list *cl; struct ocfs2_dinode *fe; @@ -1146,6 +1308,28 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, goto bail; } + if (hint_blkno) { + /* Attempt to short-circuit the usual search mechanism + * by jumping straight to the most recently used + * allocation group. This helps us mantain some + * contiguousness across allocations. */ + status = ocfs2_search_one_group(ac, bits_wanted, min_bits, + bit_off, num_bits, + hint_blkno, &bits_left); + if (!status) { + /* Be careful to update *bg_blkno here as the + * caller is expecting it to be filled in, and + * ocfs2_search_one_group() won't do that for + * us. */ + *bg_blkno = hint_blkno; + goto set_hint; + } + if (status < 0 && status != -ENOSPC) { + mlog_errno(status); + goto bail; + } + } + cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; victim = ocfs2_find_victim_chain(cl); @@ -1153,9 +1337,9 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ac->ac_allow_chain_relink = 1; status = ocfs2_search_chain(ac, bits_wanted, min_bits, bit_off, - num_bits, bg_blkno); + num_bits, bg_blkno, &bits_left); if (!status) - goto bail; + goto set_hint; if (status < 0 && status != -ENOSPC) { mlog_errno(status); goto bail; @@ -1177,8 +1361,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ac->ac_chain = i; status = ocfs2_search_chain(ac, bits_wanted, min_bits, - bit_off, num_bits, - bg_blkno); + bit_off, num_bits, bg_blkno, + &bits_left); if (!status) break; if (status < 0 && status != -ENOSPC) { @@ -1186,8 +1370,19 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, goto bail; } } -bail: +set_hint: + if (status != -ENOSPC) { + /* If the next search of this group is not likely to + * yield a suitable extent, then we reset the last + * group hint so as to not waste a disk read */ + if (bits_left < min_bits) + ac->ac_last_group = 0; + else + ac->ac_last_group = *bg_blkno; + } + +bail: mlog_exit(status); return status; } @@ -1341,7 +1536,7 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb, { int status; unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; - u64 bg_blkno; + u64 bg_blkno = 0; u16 bg_bit_off; mlog_entry_void(); @@ -1494,9 +1689,9 @@ static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle, } group = (struct ocfs2_group_desc *) group_bh->b_data; - if (!OCFS2_IS_VALID_GROUP_DESC(group)) { - OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, group); - status = -EIO; + status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, group); + if (status) { + mlog_errno(status); goto bail; } BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits)); diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index a76c82a..c787838 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -49,6 +49,8 @@ struct ocfs2_alloc_context { u16 ac_chain; int ac_allow_chain_relink; group_search_t *ac_group_search; + + u64 ac_last_group; }; void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 382706a..d17e33e 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1442,8 +1442,13 @@ static int ocfs2_initialize_super(struct super_block *sb, osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno; + /* We don't have a cluster lock on the bitmap here because + * we're only interested in static information and the extra + * complexity at mount time isn't worht it. Don't pass the + * inode in to the read function though as we don't want it to + * be put in the cache. */ status = ocfs2_read_block(osb, osb->bitmap_blkno, &bitmap_bh, 0, - inode); + NULL); iput(inode); if (status < 0) { mlog_errno(status); @@ -1452,7 +1457,6 @@ static int ocfs2_initialize_super(struct super_block *sb, di = (struct ocfs2_dinode *) bitmap_bh->b_data; osb->bitmap_cpg = le16_to_cpu(di->id2.i_chain.cl_cpg); - osb->num_clusters = le32_to_cpu(di->id1.bitmap1.i_total); brelse(bitmap_bh); mlog(0, "cluster bitmap inode: %llu, clusters per group: %u\n", (unsigned long long)osb->bitmap_blkno, osb->bitmap_cpg); diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig index c9a4780..e478f19 100644 --- a/fs/partitions/Kconfig +++ b/fs/partitions/Kconfig @@ -99,7 +99,7 @@ config IBM_PARTITION config MAC_PARTITION bool "Macintosh partition map support" if PARTITION_ADVANCED - default y if MAC + default y if (MAC || PPC_PMAC) help Say Y here if you would like to use hard disks under Linux which were partitioned on a Macintosh. diff --git a/fs/partitions/sun.c b/fs/partitions/sun.c index abe91ca..0a5927c 100644 --- a/fs/partitions/sun.c +++ b/fs/partitions/sun.c @@ -74,7 +74,7 @@ int sun_partition(struct parsed_partitions *state, struct block_device *bdev) spc = be16_to_cpu(label->ntrks) * be16_to_cpu(label->nsect); for (i = 0; i < 8; i++, p++) { unsigned long st_sector; - int num_sectors; + unsigned int num_sectors; st_sector = be32_to_cpu(p->start_cylinder) * spc; num_sectors = be32_to_cpu(p->num_sectors); diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 9f2cfc3..9421562 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -169,7 +169,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off, "Mapped: %8lu kB\n" "Slab: %8lu kB\n" "PageTables: %8lu kB\n" - "NFS Unstable: %8lu kB\n" + "NFS_Unstable: %8lu kB\n" "Bounce: %8lu kB\n" "CommitLimit: %8lu kB\n" "Committed_AS: %8lu kB\n" diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index f318b58..1627edd 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -48,8 +48,8 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp) return 0; } - reiserfs_write_lock(inode->i_sb); mutex_lock(&inode->i_mutex); + reiserfs_write_lock(inode->i_sb); /* freeing preallocation only involves relogging blocks that * are already in the current transaction. preallocation gets * freed at the end of each transaction, so it is impossible for diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 12dfdcf..52f1e21 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -39,14 +39,10 @@ void reiserfs_delete_inode(struct inode *inode) /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */ if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */ - mutex_lock(&inode->i_mutex); - reiserfs_delete_xattrs(inode); - if (journal_begin(&th, inode->i_sb, jbegin_count)) { - mutex_unlock(&inode->i_mutex); + if (journal_begin(&th, inode->i_sb, jbegin_count)) goto out; - } reiserfs_update_inode_transaction(inode); err = reiserfs_delete_object(&th, inode); @@ -57,12 +53,8 @@ void reiserfs_delete_inode(struct inode *inode) if (!err) DQUOT_FREE_INODE(inode); - if (journal_end(&th, inode->i_sb, jbegin_count)) { - mutex_unlock(&inode->i_mutex); + if (journal_end(&th, inode->i_sb, jbegin_count)) goto out; - } - - mutex_unlock(&inode->i_mutex); /* check return value from reiserfs_delete_object after * ending the transaction @@ -2348,6 +2340,7 @@ static int reiserfs_write_full_page(struct page *page, unsigned long end_index = inode->i_size >> PAGE_CACHE_SHIFT; int error = 0; unsigned long block; + sector_t last_block; struct buffer_head *head, *bh; int partial = 0; int nr = 0; @@ -2395,10 +2388,19 @@ static int reiserfs_write_full_page(struct page *page, } bh = head; block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits); + last_block = (i_size_read(inode) - 1) >> inode->i_blkbits; /* first map all the buffers, logging any direct items we find */ do { - if ((checked || buffer_dirty(bh)) && (!buffer_mapped(bh) || - (buffer_mapped(bh) + if (block > last_block) { + /* + * This can happen when the block size is less than + * the page size. The corresponding bytes in the page + * were zero filled above + */ + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + } else if ((checked || buffer_dirty(bh)) && + (!buffer_mapped(bh) || (buffer_mapped(bh) && bh->b_blocknr == 0))) { /* not mapped yet, or it points to a direct item, search diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 745c881..a986b5e 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -116,12 +116,12 @@ static int reiserfs_unpack(struct inode *inode, struct file *filp) if (REISERFS_I(inode)->i_flags & i_nopack_mask) { return 0; } - reiserfs_write_lock(inode->i_sb); /* we need to make sure nobody is changing the file size beneath ** us */ mutex_lock(&inode->i_mutex); + reiserfs_write_lock(inode->i_sb); write_from = inode->i_size & (blocksize - 1); /* if we are on a block boundary, we are already unpacked. */ diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 39fedaa..d935fb9 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -424,7 +424,7 @@ int xattr_readdir(struct file *file, filldir_t filler, void *buf) int res = -ENOTDIR; if (!file->f_op || !file->f_op->readdir) goto out; - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&inode->i_mutex, I_MUTEX_XATTR); // down(&inode->i_zombie); res = -ENOENT; if (!IS_DEADDIR(inode)) { diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 3873c67..3332347 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -75,6 +75,12 @@ struct inode * udf_new_inode (struct inode *dir, int mode, int * err) } *err = -ENOSPC; + UDF_I_UNIQUE(inode) = 0; + UDF_I_LENEXTENTS(inode) = 0; + UDF_I_NEXT_ALLOC_BLOCK(inode) = 0; + UDF_I_NEXT_ALLOC_GOAL(inode) = 0; + UDF_I_STRAT4096(inode) = 0; + block = udf_new_block(dir->i_sb, NULL, UDF_I_LOCATION(dir).partitionReferenceNum, start, err); if (*err) @@ -84,11 +90,6 @@ struct inode * udf_new_inode (struct inode *dir, int mode, int * err) } mutex_lock(&sbi->s_alloc_mutex); - UDF_I_UNIQUE(inode) = 0; - UDF_I_LENEXTENTS(inode) = 0; - UDF_I_NEXT_ALLOC_BLOCK(inode) = 0; - UDF_I_NEXT_ALLOC_GOAL(inode) = 0; - UDF_I_STRAT4096(inode) = 0; if (UDF_SB_LVIDBH(sb)) { struct logicalVolHeaderDesc *lvhd; diff --git a/fs/udf/super.c b/fs/udf/super.c index 4df822c..fcce1a2 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -115,6 +115,13 @@ static struct inode *udf_alloc_inode(struct super_block *sb) ei = (struct udf_inode_info *)kmem_cache_alloc(udf_inode_cachep, SLAB_KERNEL); if (!ei) return NULL; + + ei->i_unique = 0; + ei->i_lenExtents = 0; + ei->i_next_alloc_block = 0; + ei->i_next_alloc_goal = 0; + ei->i_strat4096 = 0; + return &ei->vfs_inode; } @@ -1652,7 +1659,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) iput(inode); goto error_out; } - sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_maxbytes = 1<<30; return 0; error_out: diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index e1b0e8c..0abd66c 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -239,37 +239,51 @@ void udf_truncate_extents(struct inode * inode) { if (offset) { - extoffset -= adsize; - etype = udf_next_aext(inode, &bloc, &extoffset, &eloc, &elen, &bh, 1); - if (etype == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) - { - extoffset -= adsize; - elen = EXT_NOT_RECORDED_NOT_ALLOCATED | (elen + offset); - udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 0); + /* + * OK, there is not extent covering inode->i_size and + * no extent above inode->i_size => truncate is + * extending the file by 'offset'. + */ + if ((!bh && extoffset == udf_file_entry_alloc_offset(inode)) || + (bh && extoffset == sizeof(struct allocExtDesc))) { + /* File has no extents at all! */ + memset(&eloc, 0x00, sizeof(kernel_lb_addr)); + elen = EXT_NOT_RECORDED_NOT_ALLOCATED | offset; + udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 1); } - else if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) - { - kernel_lb_addr neloc = { 0, 0 }; + else { extoffset -= adsize; - nelen = EXT_NOT_RECORDED_NOT_ALLOCATED | - ((elen + offset + inode->i_sb->s_blocksize - 1) & - ~(inode->i_sb->s_blocksize - 1)); - udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 1); - udf_add_aext(inode, &bloc, &extoffset, eloc, (etype << 30) | elen, &bh, 1); - } - else - { - if (elen & (inode->i_sb->s_blocksize - 1)) + etype = udf_next_aext(inode, &bloc, &extoffset, &eloc, &elen, &bh, 1); + if (etype == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30)) + { + extoffset -= adsize; + elen = EXT_NOT_RECORDED_NOT_ALLOCATED | (elen + offset); + udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 0); + } + else if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { + kernel_lb_addr neloc = { 0, 0 }; extoffset -= adsize; - elen = EXT_RECORDED_ALLOCATED | - ((elen + inode->i_sb->s_blocksize - 1) & + nelen = EXT_NOT_RECORDED_NOT_ALLOCATED | + ((elen + offset + inode->i_sb->s_blocksize - 1) & ~(inode->i_sb->s_blocksize - 1)); - udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 1); + udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 1); + udf_add_aext(inode, &bloc, &extoffset, eloc, (etype << 30) | elen, &bh, 1); + } + else + { + if (elen & (inode->i_sb->s_blocksize - 1)) + { + extoffset -= adsize; + elen = EXT_RECORDED_ALLOCATED | + ((elen + inode->i_sb->s_blocksize - 1) & + ~(inode->i_sb->s_blocksize - 1)); + udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 1); + } + memset(&eloc, 0x00, sizeof(kernel_lb_addr)); + elen = EXT_NOT_RECORDED_NOT_ALLOCATED | offset; + udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 1); } - memset(&eloc, 0x00, sizeof(kernel_lb_addr)); - elen = EXT_NOT_RECORDED_NOT_ALLOCATED | offset; - udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 1); } } } diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index b01804b..b823814 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -248,7 +248,7 @@ static void ufs_change_blocknr(struct inode *inode, unsigned int baseblk, if (likely(cur_index != index)) { page = ufs_get_locked_page(mapping, index); - if (IS_ERR(page)) + if (!page || IS_ERR(page)) /* it was truncated or EIO */ continue; } else page = locked_page; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index e7c8615..30c6e8a9 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -169,18 +169,20 @@ static void ufs_clear_frag(struct inode *inode, struct buffer_head *bh) static struct buffer_head * ufs_clear_frags(struct inode *inode, sector_t beg, - unsigned int n) + unsigned int n, sector_t want) { - struct buffer_head *res, *bh; + struct buffer_head *res = NULL, *bh; sector_t end = beg + n; - res = sb_getblk(inode->i_sb, beg); - ufs_clear_frag(inode, res); - for (++beg; beg < end; ++beg) { + for (; beg < end; ++beg) { bh = sb_getblk(inode->i_sb, beg); ufs_clear_frag(inode, bh); - brelse(bh); + if (want != beg) + brelse(bh); + else + res = bh; } + BUG_ON(!res); return res; } @@ -265,7 +267,9 @@ repeat: lastfrag = ufsi->i_lastfrag; } - goal = fs32_to_cpu(sb, ufsi->i_u1.i_data[lastblock]) + uspi->s_fpb; + tmp = fs32_to_cpu(sb, ufsi->i_u1.i_data[lastblock]); + if (tmp) + goal = tmp + uspi->s_fpb; tmp = ufs_new_fragments (inode, p, fragment - blockoff, goal, required + blockoff, err, locked_page); @@ -277,13 +281,15 @@ repeat: tmp = ufs_new_fragments(inode, p, fragment - (blockoff - lastblockoff), fs32_to_cpu(sb, *p), required + (blockoff - lastblockoff), err, locked_page); - } + } else /* (lastblock > block) */ { /* * We will allocate new block before last allocated block */ - else /* (lastblock > block) */ { - if (lastblock && (tmp = fs32_to_cpu(sb, ufsi->i_u1.i_data[lastblock-1]))) - goal = tmp + uspi->s_fpb; + if (block) { + tmp = fs32_to_cpu(sb, ufsi->i_u1.i_data[block-1]); + if (tmp) + goal = tmp + uspi->s_fpb; + } tmp = ufs_new_fragments(inode, p, fragment - blockoff, goal, uspi->s_fpb, err, locked_page); } @@ -296,7 +302,7 @@ repeat: } if (!phys) { - result = ufs_clear_frags(inode, tmp + blockoff, required); + result = ufs_clear_frags(inode, tmp, required, tmp + blockoff); } else { *phys = tmp + blockoff; result = NULL; @@ -383,7 +389,7 @@ repeat: } } - if (block && (tmp = fs32_to_cpu(sb, ((__fs32*)bh->b_data)[block-1]) + uspi->s_fpb)) + if (block && (tmp = fs32_to_cpu(sb, ((__fs32*)bh->b_data)[block-1]))) goal = tmp + uspi->s_fpb; else goal = bh->b_blocknr + uspi->s_fpb; @@ -397,7 +403,8 @@ repeat: if (!phys) { - result = ufs_clear_frags(inode, tmp + blockoff, uspi->s_fpb); + result = ufs_clear_frags(inode, tmp, uspi->s_fpb, + tmp + blockoff); } else { *phys = tmp + blockoff; *new = 1; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index abd5f23..d344b41 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -129,7 +129,7 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, struct inode * inode; if (l > sb->s_blocksize) - goto out; + goto out_notlocked; lock_kernel(); inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO); @@ -155,6 +155,7 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, err = ufs_add_nondir(dentry, inode); out: unlock_kernel(); +out_notlocked: return err; out_fail: diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index c9b5587..ea11d04 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -375,17 +375,15 @@ static int ufs_alloc_lastblock(struct inode *inode) int err = 0; struct address_space *mapping = inode->i_mapping; struct ufs_sb_private_info *uspi = UFS_SB(inode->i_sb)->s_uspi; - struct ufs_inode_info *ufsi = UFS_I(inode); unsigned lastfrag, i, end; struct page *lastpage; struct buffer_head *bh; lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift; - if (!lastfrag) { - ufsi->i_lastfrag = 0; + if (!lastfrag) goto out; - } + lastfrag--; lastpage = ufs_get_locked_page(mapping, lastfrag >> @@ -400,25 +398,25 @@ static int ufs_alloc_lastblock(struct inode *inode) for (i = 0; i < end; ++i) bh = bh->b_this_page; - if (!buffer_mapped(bh)) { - err = ufs_getfrag_block(inode, lastfrag, bh, 1); - - if (unlikely(err)) - goto out_unlock; - - if (buffer_new(bh)) { - clear_buffer_new(bh); - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); - /* - * we do not zeroize fragment, because of - * if it maped to hole, it already contains zeroes - */ - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - set_page_dirty(lastpage); - } + + err = ufs_getfrag_block(inode, lastfrag, bh, 1); + + if (unlikely(err)) + goto out_unlock; + + if (buffer_new(bh)) { + clear_buffer_new(bh); + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + /* + * we do not zeroize fragment, because of + * if it maped to hole, it already contains zeroes + */ + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + set_page_dirty(lastpage); } + out_unlock: ufs_put_locked_page(lastpage); out: @@ -440,23 +438,11 @@ int ufs_truncate(struct inode *inode, loff_t old_i_size) if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; - if (inode->i_size > old_i_size) { - /* - * if we expand file we should care about - * allocation of block for last byte first of all - */ - err = ufs_alloc_lastblock(inode); + err = ufs_alloc_lastblock(inode); - if (err) { - i_size_write(inode, old_i_size); - goto out; - } - /* - * go away, because of we expand file, and we do not - * need free blocks, and zeroizes page - */ - lock_kernel(); - goto almost_end; + if (err) { + i_size_write(inode, old_i_size); + goto out; } block_truncate_page(inode->i_mapping, inode->i_size, ufs_getfrag_block); @@ -477,21 +463,8 @@ int ufs_truncate(struct inode *inode, loff_t old_i_size) yield(); } - if (inode->i_size < old_i_size) { - /* - * now we should have enough space - * to allocate block for last byte - */ - err = ufs_alloc_lastblock(inode); - if (err) - /* - * looks like all the same - we have no space, - * but we truncate file already - */ - inode->i_size = (ufsi->i_lastfrag - 1) * uspi->s_fsize; - } -almost_end: inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + ufsi->i_lastfrag = DIRECT_FRAGMENT; unlock_kernel(); mark_inode_dirty(inode); out: diff --git a/fs/ufs/util.c b/fs/ufs/util.c index 337cf2c..22f820a 100644 --- a/fs/ufs/util.c +++ b/fs/ufs/util.c @@ -251,12 +251,12 @@ struct page *ufs_get_locked_page(struct address_space *mapping, { struct page *page; -try_again: page = find_lock_page(mapping, index); if (!page) { page = read_cache_page(mapping, index, (filler_t*)mapping->a_ops->readpage, NULL); + if (IS_ERR(page)) { printk(KERN_ERR "ufs_change_blocknr: " "read_cache_page error: ino %lu, index: %lu\n", @@ -266,6 +266,14 @@ try_again: lock_page(page); + if (unlikely(page->mapping == NULL)) { + /* Truncate got there first */ + unlock_page(page); + page_cache_release(page); + page = NULL; + goto out; + } + if (!PageUptodate(page) || PageError(page)) { unlock_page(page); page_cache_release(page); @@ -275,15 +283,8 @@ try_again: mapping->host->i_ino, index); page = ERR_PTR(-EIO); - goto out; } } - - if (unlikely(!page->mapping || !page_has_buffers(page))) { - unlock_page(page); - page_cache_release(page); - goto try_again;/*we really need these buffers*/ - } out: return page; } diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index ceda3a2..7858703 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -246,8 +246,8 @@ extern void xfs_buf_trace(xfs_buf_t *, char *, void *, void *); #define BUF_BUSY XBF_DONT_BLOCK #define XFS_BUF_BFLAGS(bp) ((bp)->b_flags) -#define XFS_BUF_ZEROFLAGS(bp) \ - ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI)) +#define XFS_BUF_ZEROFLAGS(bp) ((bp)->b_flags &= \ + ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI|XBF_ORDERED)) #define XFS_BUF_STALE(bp) ((bp)->b_flags |= XFS_B_STALE) #define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XFS_B_STALE) diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 9bdef9d..4754f34 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -314,6 +314,13 @@ xfs_mountfs_check_barriers(xfs_mount_t *mp) return; } + if (xfs_readonly_buftarg(mp->m_ddev_targp)) { + xfs_fs_cmn_err(CE_NOTE, mp, + "Disabling barriers, underlying device is readonly"); + mp->m_flags &= ~XFS_MOUNT_BARRIER; + return; + } + error = xfs_barrier_test(mp); if (error) { xfs_fs_cmn_err(CE_NOTE, mp, diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c index e95e99f..f137856 100644 --- a/fs/xfs/quota/xfs_qm_bhv.c +++ b/fs/xfs/quota/xfs_qm_bhv.c @@ -217,17 +217,24 @@ xfs_qm_statvfs( return 0; dp = &dqp->q_core; - limit = dp->d_blk_softlimit ? dp->d_blk_softlimit : dp->d_blk_hardlimit; + limit = dp->d_blk_softlimit ? + be64_to_cpu(dp->d_blk_softlimit) : + be64_to_cpu(dp->d_blk_hardlimit); if (limit && statp->f_blocks > limit) { statp->f_blocks = limit; - statp->f_bfree = (statp->f_blocks > dp->d_bcount) ? - (statp->f_blocks - dp->d_bcount) : 0; + statp->f_bfree = + (statp->f_blocks > be64_to_cpu(dp->d_bcount)) ? + (statp->f_blocks - be64_to_cpu(dp->d_bcount)) : 0; } - limit = dp->d_ino_softlimit ? dp->d_ino_softlimit : dp->d_ino_hardlimit; + + limit = dp->d_ino_softlimit ? + be64_to_cpu(dp->d_ino_softlimit) : + be64_to_cpu(dp->d_ino_hardlimit); if (limit && statp->f_files > limit) { statp->f_files = limit; - statp->f_ffree = (statp->f_files > dp->d_icount) ? - (statp->f_ffree - dp->d_icount) : 0; + statp->f_ffree = + (statp->f_files > be64_to_cpu(dp->d_icount)) ? + (statp->f_ffree - be64_to_cpu(dp->d_icount)) : 0; } xfs_qm_dqput(dqp); diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index eef6763..d2bbcd8 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1835,40 +1835,47 @@ xfs_alloc_fix_freelist( &agbp))) return error; if (!pag->pagf_init) { + ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK); + ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); args->agbp = NULL; return 0; } } else agbp = NULL; - /* If this is a metadata preferred pag and we are user data + /* + * If this is a metadata preferred pag and we are user data * then try somewhere else if we are not being asked to * try harder at this point */ - if (pag->pagf_metadata && args->userdata && flags) { + if (pag->pagf_metadata && args->userdata && + (flags & XFS_ALLOC_FLAG_TRYLOCK)) { + ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); args->agbp = NULL; return 0; } - need = XFS_MIN_FREELIST_PAG(pag, mp); - delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0; - /* - * If it looks like there isn't a long enough extent, or enough - * total blocks, reject it. - */ - longest = (pag->pagf_longest > delta) ? - (pag->pagf_longest - delta) : - (pag->pagf_flcount > 0 || pag->pagf_longest > 0); - if (args->minlen + args->alignment + args->minalignslop - 1 > longest || - (!(flags & XFS_ALLOC_FLAG_FREEING) && - (int)(pag->pagf_freeblks + pag->pagf_flcount - - need - args->total) < - (int)args->minleft)) { - if (agbp) - xfs_trans_brelse(tp, agbp); - args->agbp = NULL; - return 0; + if (!(flags & XFS_ALLOC_FLAG_FREEING)) { + need = XFS_MIN_FREELIST_PAG(pag, mp); + delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0; + /* + * If it looks like there isn't a long enough extent, or enough + * total blocks, reject it. + */ + longest = (pag->pagf_longest > delta) ? + (pag->pagf_longest - delta) : + (pag->pagf_flcount > 0 || pag->pagf_longest > 0); + if ((args->minlen + args->alignment + args->minalignslop - 1) > + longest || + ((int)(pag->pagf_freeblks + pag->pagf_flcount - + need - args->total) < (int)args->minleft)) { + if (agbp) + xfs_trans_brelse(tp, agbp); + args->agbp = NULL; + return 0; + } } + /* * Get the a.g. freespace buffer. * Can fail if we're not blocking on locks, and it's held. @@ -1878,6 +1885,8 @@ xfs_alloc_fix_freelist( &agbp))) return error; if (agbp == NULL) { + ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK); + ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); args->agbp = NULL; return 0; } @@ -1887,22 +1896,24 @@ xfs_alloc_fix_freelist( */ agf = XFS_BUF_TO_AGF(agbp); need = XFS_MIN_FREELIST(agf, mp); - delta = need > be32_to_cpu(agf->agf_flcount) ? - (need - be32_to_cpu(agf->agf_flcount)) : 0; /* * If there isn't enough total or single-extent, reject it. */ - longest = be32_to_cpu(agf->agf_longest); - longest = (longest > delta) ? (longest - delta) : - (be32_to_cpu(agf->agf_flcount) > 0 || longest > 0); - if (args->minlen + args->alignment + args->minalignslop - 1 > longest || - (!(flags & XFS_ALLOC_FLAG_FREEING) && - (int)(be32_to_cpu(agf->agf_freeblks) + - be32_to_cpu(agf->agf_flcount) - need - args->total) < - (int)args->minleft)) { - xfs_trans_brelse(tp, agbp); - args->agbp = NULL; - return 0; + if (!(flags & XFS_ALLOC_FLAG_FREEING)) { + delta = need > be32_to_cpu(agf->agf_flcount) ? + (need - be32_to_cpu(agf->agf_flcount)) : 0; + longest = be32_to_cpu(agf->agf_longest); + longest = (longest > delta) ? (longest - delta) : + (be32_to_cpu(agf->agf_flcount) > 0 || longest > 0); + if ((args->minlen + args->alignment + args->minalignslop - 1) > + longest || + ((int)(be32_to_cpu(agf->agf_freeblks) + + be32_to_cpu(agf->agf_flcount) - need - args->total) < + (int)args->minleft)) { + xfs_trans_brelse(tp, agbp); + args->agbp = NULL; + return 0; + } } /* * Make the freelist shorter if it's too long. @@ -1950,12 +1961,11 @@ xfs_alloc_fix_freelist( * on a completely full ag. */ if (targs.agbno == NULLAGBLOCK) { - if (!(flags & XFS_ALLOC_FLAG_FREEING)) { - xfs_trans_brelse(tp, agflbp); - args->agbp = NULL; - return 0; - } - break; + if (flags & XFS_ALLOC_FLAG_FREEING) + break; + xfs_trans_brelse(tp, agflbp); + args->agbp = NULL; + return 0; } /* * Put each allocated block on the list. @@ -2442,31 +2452,26 @@ xfs_free_extent( xfs_fsblock_t bno, /* starting block number of extent */ xfs_extlen_t len) /* length of extent */ { -#ifdef DEBUG - xfs_agf_t *agf; /* a.g. freespace header */ -#endif - xfs_alloc_arg_t args; /* allocation argument structure */ + xfs_alloc_arg_t args; int error; ASSERT(len != 0); + memset(&args, 0, sizeof(xfs_alloc_arg_t)); args.tp = tp; args.mp = tp->t_mountp; args.agno = XFS_FSB_TO_AGNO(args.mp, bno); ASSERT(args.agno < args.mp->m_sb.sb_agcount); args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno); - args.alignment = 1; - args.minlen = args.minleft = args.minalignslop = 0; down_read(&args.mp->m_peraglock); args.pag = &args.mp->m_perag[args.agno]; if ((error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING))) goto error0; #ifdef DEBUG ASSERT(args.agbp != NULL); - agf = XFS_BUF_TO_AGF(args.agbp); - ASSERT(args.agbno + len <= be32_to_cpu(agf->agf_length)); + ASSERT((args.agbno + len) <= + be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)); #endif - error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, - len, 0); + error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0); error0: up_read(&args.mp->m_peraglock); return error; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 86c1bf0..1f8ecff 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -334,10 +334,9 @@ xfs_itobp( #if !defined(__KERNEL__) ni = 0; #elif defined(DEBUG) - ni = (imap_flags & XFS_IMAP_BULKSTAT) ? 0 : - (BBTOB(imap.im_len) >> mp->m_sb.sb_inodelog); + ni = BBTOB(imap.im_len) >> mp->m_sb.sb_inodelog; #else /* usual case */ - ni = (imap_flags & XFS_IMAP_BULKSTAT) ? 0 : 1; + ni = 1; #endif for (i = 0; i < ni; i++) { @@ -348,11 +347,15 @@ xfs_itobp( (i << mp->m_sb.sb_inodelog)); di_ok = INT_GET(dip->di_core.di_magic, ARCH_CONVERT) == XFS_DINODE_MAGIC && XFS_DINODE_GOOD_VERSION(INT_GET(dip->di_core.di_version, ARCH_CONVERT)); - if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, - XFS_RANDOM_ITOBP_INOTOBP))) { + if (unlikely(XFS_TEST_ERROR(!di_ok, mp, + XFS_ERRTAG_ITOBP_INOTOBP, + XFS_RANDOM_ITOBP_INOTOBP))) { + if (imap_flags & XFS_IMAP_BULKSTAT) { + xfs_trans_brelse(tp, bp); + return XFS_ERROR(EINVAL); + } #ifdef DEBUG - if (!(imap_flags & XFS_IMAP_BULKSTAT)) - cmn_err(CE_ALERT, + cmn_err(CE_ALERT, "Device %s - bad inode magic/vsn " "daddr %lld #%d (magic=%x)", XFS_BUFTARG_NAME(mp->m_ddev_targp), diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index e730328..21ac1a6 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1413,7 +1413,7 @@ xlog_sync(xlog_t *log, ops = iclog->ic_header.h_num_logops; INT_SET(iclog->ic_header.h_num_logops, ARCH_CONVERT, ops); - bp = iclog->ic_bp; + bp = iclog->ic_bp; ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long)1); XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2); XFS_BUF_SET_ADDR(bp, BLOCK_LSN(INT_GET(iclog->ic_header.h_lsn, ARCH_CONVERT))); @@ -1430,15 +1430,14 @@ xlog_sync(xlog_t *log, } XFS_BUF_SET_PTR(bp, (xfs_caddr_t) &(iclog->ic_header), count); XFS_BUF_SET_FSPRIVATE(bp, iclog); /* save for later */ + XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); /* * Do an ordered write for the log block. - * - * It may not be needed to flush the first split block in the log wrap - * case, but do it anyways to be safe -AK + * Its unnecessary to flush the first split block in the log wrap case. */ - if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) + if (!split && (log->l_mp->m_flags & XFS_MOUNT_BARRIER)) XFS_BUF_ORDERED(bp); ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); @@ -1460,7 +1459,7 @@ xlog_sync(xlog_t *log, return error; } if (split) { - bp = iclog->ic_log->l_xbuf; + bp = iclog->ic_log->l_xbuf; ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long)1); XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2); @@ -1468,6 +1467,7 @@ xlog_sync(xlog_t *log, XFS_BUF_SET_PTR(bp, (xfs_caddr_t)((__psint_t)&(iclog->ic_header)+ (__psint_t)count), split); XFS_BUF_SET_FSPRIVATE(bp, iclog); + XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c index 6c96391..b427d22 100644 --- a/fs/xfs/xfs_vfsops.c +++ b/fs/xfs/xfs_vfsops.c @@ -515,7 +515,7 @@ xfs_mount( if (error) goto error2; - if ((mp->m_flags & XFS_MOUNT_BARRIER) && !(vfsp->vfs_flag & VFS_RDONLY)) + if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_mountfs_check_barriers(mp); error = XFS_IOINIT(vfsp, args, flags); |
