diff options
Diffstat (limited to 'fs')
106 files changed, 6604 insertions, 3637 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index e9cb57f..9a1d426 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -182,11 +182,11 @@ int v9fs_set_create_acl(struct dentry *dentry, return 0; } -int v9fs_acl_mode(struct inode *dir, mode_t *modep, +int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl) { int retval = 0; - mode_t mode = *modep; + umode_t mode = *modep; struct posix_acl *acl = NULL; if (!S_ISLNK(mode)) { @@ -319,7 +319,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; retval = posix_acl_equiv_mode(acl, &mode); if (retval < 0) goto err_out; diff --git a/fs/9p/acl.h b/fs/9p/acl.h index ddb7ae1..5595564 100644 --- a/fs/9p/acl.h +++ b/fs/9p/acl.h @@ -20,7 +20,7 @@ extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type); extern int v9fs_acl_chmod(struct dentry *); extern int v9fs_set_create_acl(struct dentry *, struct posix_acl **, struct posix_acl **); -extern int v9fs_acl_mode(struct inode *dir, mode_t *modep, +extern int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl); #else #define v9fs_iop_get_acl NULL @@ -38,7 +38,7 @@ static inline int v9fs_set_create_acl(struct dentry *dentry, { return 0; } -static inline int v9fs_acl_mode(struct inode *dir, mode_t *modep, +static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl) { diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 9a26dce..b6c8ed2 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -206,7 +206,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode, int err = 0; gid_t gid; int flags; - mode_t mode; + umode_t mode; char *name = NULL; struct file *filp; struct p9_qid qid; @@ -348,7 +348,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct p9_fid *fid = NULL, *dfid = NULL; gid_t gid; char *name; - mode_t mode; + umode_t mode; struct inode *inode; struct p9_qid qid; struct dentry *dir_dentry; @@ -751,7 +751,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode, int err; gid_t gid; char *name; - mode_t mode; + umode_t mode; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; struct inode *inode; @@ -127,14 +127,21 @@ config TMPFS_POSIX_ACL select TMPFS_XATTR select GENERIC_ACL help - POSIX Access Control Lists (ACLs) support permissions for users and - groups beyond the owner/group/world scheme. + POSIX Access Control Lists (ACLs) support additional access rights + for users and groups beyond the standard owner/group/world scheme, + and this option selects support for ACLs specifically for tmpfs + filesystems. + + If you've selected TMPFS, it's possible that you'll also need + this option as there are a number of Linux distros that require + POSIX ACL support under /dev for certain features to work properly. + For example, some distros need this feature for ALSA-related /dev + files for sound to work properly. In short, if you're not sure, + say Y. To learn more about Access Control Lists, visit the POSIX ACLs for Linux website <http://acl.bestbits.at/>. - If you don't know what Access Control Lists are, say N. - config TMPFS_XATTR bool "Tmpfs extended attributes" depends on TMPFS diff --git a/fs/block_dev.c b/fs/block_dev.c index f55aad4..ff77262 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -387,6 +387,10 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) struct inode *bd_inode = filp->f_mapping->host; struct block_device *bdev = I_BDEV(bd_inode); int error; + + error = filemap_write_and_wait_range(filp->f_mapping, start, end); + if (error) + return error; /* * There is no need to serialise calls to blkdev_issue_flush with @@ -552,6 +556,7 @@ struct block_device *bdget(dev_t dev) if (inode->i_state & I_NEW) { bdev->bd_contains = NULL; + bdev->bd_super = NULL; bdev->bd_inode = inode; bdev->bd_block_size = (1 << inode->i_blkbits); bdev->bd_part_count = 0; diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 9b72dcf..40e6ac0 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -6,5 +6,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ transaction.o inode.o file.o tree-defrag.o \ extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \ extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ - export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \ + export.o tree-log.o free-space-cache.o zlib.o lzo.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o + +btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 65a735d..eb159aa 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -28,8 +28,6 @@ #include "btrfs_inode.h" #include "xattr.h" -#ifdef CONFIG_BTRFS_FS_POSIX_ACL - struct posix_acl *btrfs_get_acl(struct inode *inode, int type) { int size; @@ -111,7 +109,6 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans, int ret, size = 0; const char *name; char *value = NULL; - mode_t mode; if (acl) { ret = posix_acl_valid(acl); @@ -122,13 +119,11 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: - mode = inode->i_mode; name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &mode); + ret = posix_acl_equiv_mode(acl, &inode->i_mode); if (ret < 0) return ret; - inode->i_mode = mode; } ret = 0; break; @@ -222,19 +217,16 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans, } if (IS_POSIXACL(dir) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_DEFAULT); if (ret) goto failed; } - ret = posix_acl_create(&acl, GFP_NOFS, &mode); + ret = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (ret < 0) return ret; - inode->i_mode = mode; if (ret > 0) { /* we need an acl */ ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS); @@ -282,18 +274,3 @@ const struct xattr_handler btrfs_xattr_acl_access_handler = { .get = btrfs_xattr_acl_get, .set = btrfs_xattr_acl_set, }; - -#else /* CONFIG_BTRFS_FS_POSIX_ACL */ - -int btrfs_acl_chmod(struct inode *inode) -{ - return 0; -} - -int btrfs_init_acl(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir) -{ - return 0; -} - -#endif /* CONFIG_BTRFS_FS_POSIX_ACL */ diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index bfe42b0..8ec5d86 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -338,6 +338,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, u64 first_byte = disk_start; struct block_device *bdev; int ret; + int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; WARN_ON(start & ((u64)PAGE_CACHE_SIZE - 1)); cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS); @@ -392,8 +393,11 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); BUG_ON(ret); - ret = btrfs_csum_one_bio(root, inode, bio, start, 1); - BUG_ON(ret); + if (!skip_sum) { + ret = btrfs_csum_one_bio(root, inode, bio, + start, 1); + BUG_ON(ret); + } ret = btrfs_map_bio(root, WRITE, bio, 0, 1); BUG_ON(ret); @@ -418,8 +422,10 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); BUG_ON(ret); - ret = btrfs_csum_one_bio(root, inode, bio, start, 1); - BUG_ON(ret); + if (!skip_sum) { + ret = btrfs_csum_one_bio(root, inode, bio, start, 1); + BUG_ON(ret); + } ret = btrfs_map_bio(root, WRITE, bio, 0, 1); BUG_ON(ret); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 365c4e1..0469263 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2406,8 +2406,8 @@ int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct btrfs_root_item *item, struct btrfs_key *key); int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid); int btrfs_find_orphan_roots(struct btrfs_root *tree_root); -int btrfs_set_root_node(struct btrfs_root_item *item, - struct extent_buffer *node); +void btrfs_set_root_node(struct btrfs_root_item *item, + struct extent_buffer *node); void btrfs_check_and_init_root_item(struct btrfs_root_item *item); /* dir-item.c */ @@ -2523,6 +2523,14 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag #define PageChecked PageFsMisc #endif +/* This forces readahead on a given range of bytes in an inode */ +static inline void btrfs_force_ra(struct address_space *mapping, + struct file_ra_state *ra, struct file *file, + pgoff_t offset, unsigned long req_size) +{ + page_cache_sync_readahead(mapping, ra, file, offset, req_size); +} + struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, @@ -2551,9 +2559,6 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, int btrfs_merge_bio_hook(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); -unsigned long btrfs_force_ra(struct address_space *mapping, - struct file_ra_state *ra, struct file *file, - pgoff_t offset, pgoff_t last_index); int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); @@ -2648,12 +2653,21 @@ do { \ /* acl.c */ #ifdef CONFIG_BTRFS_FS_POSIX_ACL struct posix_acl *btrfs_get_acl(struct inode *inode, int type); -#else -#define btrfs_get_acl NULL -#endif int btrfs_init_acl(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir); int btrfs_acl_chmod(struct inode *inode); +#else +#define btrfs_get_acl NULL +static inline int btrfs_init_acl(struct btrfs_trans_handle *trans, + struct inode *inode, struct inode *dir) +{ + return 0; +} +static inline int btrfs_acl_chmod(struct inode *inode) +{ + return 0; +} +#endif /* relocation.c */ int btrfs_relocate_block_group(struct btrfs_root *root, u64 group_start); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index c360a84..31d84e7 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -198,8 +198,6 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_key key; int ins_len = mod < 0 ? -1 : 0; int cow = mod != 0; - struct btrfs_key found_key; - struct extent_buffer *leaf; key.objectid = dir; btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY); @@ -209,18 +207,7 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); if (ret < 0) return ERR_PTR(ret); - if (ret > 0) { - if (path->slots[0] == 0) - return NULL; - path->slots[0]--; - } - - leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - - if (found_key.objectid != dir || - btrfs_key_type(&found_key) != BTRFS_DIR_ITEM_KEY || - found_key.offset != key.offset) + if (ret > 0) return NULL; return btrfs_match_dir_item_name(root, path, name, name_len); @@ -315,8 +302,6 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, struct btrfs_key key; int ins_len = mod < 0 ? -1 : 0; int cow = mod != 0; - struct btrfs_key found_key; - struct extent_buffer *leaf; key.objectid = dir; btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY); @@ -324,18 +309,7 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); if (ret < 0) return ERR_PTR(ret); - if (ret > 0) { - if (path->slots[0] == 0) - return NULL; - path->slots[0]--; - } - - leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - - if (found_key.objectid != dir || - btrfs_key_type(&found_key) != BTRFS_XATTR_ITEM_KEY || - found_key.offset != key.offset) + if (ret > 0) return NULL; return btrfs_match_dir_item_name(root, path, name, name_len); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4d08ed7..66bac22 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -663,7 +663,9 @@ int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len) struct btrfs_path *path; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; + key.objectid = start; key.offset = len; btrfs_set_key_type(&key, BTRFS_EXTENT_ITEM_KEY); @@ -3272,6 +3274,9 @@ again: } ret = btrfs_alloc_chunk(trans, extent_root, flags); + if (ret < 0 && ret != -ENOSPC) + goto out; + spin_lock(&space_info->lock); if (ret) space_info->full = 1; @@ -3281,6 +3286,7 @@ again: space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); +out: mutex_unlock(&extent_root->fs_info->chunk_mutex); return ret; } @@ -4456,7 +4462,9 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, printk(KERN_ERR "umm, got %d back from search" ", was looking for %llu\n", ret, (unsigned long long)bytenr); - btrfs_print_leaf(extent_root, path->nodes[0]); + if (ret > 0) + btrfs_print_leaf(extent_root, + path->nodes[0]); } BUG_ON(ret); extent_slot = path->slots[0]; @@ -5073,7 +5081,9 @@ have_block_group: * group is does point to and try again */ if (!last_ptr_loop && last_ptr->block_group && - last_ptr->block_group != block_group) { + last_ptr->block_group != block_group && + index <= + get_block_group_index(last_ptr->block_group)) { btrfs_put_block_group(block_group); block_group = last_ptr->block_group; @@ -5501,7 +5511,8 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, u32 size = sizeof(*extent_item) + sizeof(*block_info) + sizeof(*iref); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path, @@ -6272,10 +6283,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int level; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; wc = kzalloc(sizeof(*wc), GFP_NOFS); - BUG_ON(!wc); + if (!wc) { + btrfs_free_path(path); + return -ENOMEM; + } trans = btrfs_start_transaction(tree_root, 0); BUG_ON(IS_ERR(trans)); @@ -6538,8 +6553,6 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache, int force) u64 min_allocable_bytes; int ret = -ENOSPC; - if (cache->ro) - return 0; /* * We need some metadata space and system metadata space for @@ -6555,6 +6568,12 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache, int force) spin_lock(&sinfo->lock); spin_lock(&cache->lock); + + if (cache->ro) { + ret = 0; + goto out; + } + num_bytes = cache->key.offset - cache->reserved - cache->pinned - cache->bytes_super - btrfs_block_group_used(&cache->item); @@ -6568,7 +6587,7 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache, int force) cache->ro = 1; ret = 0; } - +out: spin_unlock(&cache->lock); spin_unlock(&sinfo->lock); return ret; @@ -7183,11 +7202,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cluster->refill_lock); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) { + ret = -ENOMEM; + goto out; + } inode = lookup_free_space_inode(root, block_group, path); if (!IS_ERR(inode)) { - btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, inode); + BUG_ON(ret); clear_nlink(inode); /* One for the block groups ref */ spin_lock(&block_group->lock); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 067b174..d418164 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -254,14 +254,14 @@ static void merge_cb(struct extent_io_tree *tree, struct extent_state *new, * * This should be called with the tree lock held. */ -static int merge_state(struct extent_io_tree *tree, - struct extent_state *state) +static void merge_state(struct extent_io_tree *tree, + struct extent_state *state) { struct extent_state *other; struct rb_node *other_node; if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) - return 0; + return; other_node = rb_prev(&state->rb_node); if (other_node) { @@ -287,19 +287,13 @@ static int merge_state(struct extent_io_tree *tree, free_extent_state(other); } } - - return 0; } -static int set_state_cb(struct extent_io_tree *tree, +static void set_state_cb(struct extent_io_tree *tree, struct extent_state *state, int *bits) { - if (tree->ops && tree->ops->set_bit_hook) { - return tree->ops->set_bit_hook(tree->mapping->host, - state, bits); - } - - return 0; + if (tree->ops && tree->ops->set_bit_hook) + tree->ops->set_bit_hook(tree->mapping->host, state, bits); } static void clear_state_cb(struct extent_io_tree *tree, @@ -309,6 +303,9 @@ static void clear_state_cb(struct extent_io_tree *tree, tree->ops->clear_bit_hook(tree->mapping->host, state, bits); } +static void set_state_bits(struct extent_io_tree *tree, + struct extent_state *state, int *bits); + /* * insert an extent_state struct into the tree. 'bits' are set on the * struct before it is inserted. @@ -324,8 +321,6 @@ static int insert_state(struct extent_io_tree *tree, int *bits) { struct rb_node *node; - int bits_to_set = *bits & ~EXTENT_CTLBITS; - int ret; if (end < start) { printk(KERN_ERR "btrfs end < start %llu %llu\n", @@ -335,13 +330,9 @@ static int insert_state(struct extent_io_tree *tree, } state->start = start; state->end = end; - ret = set_state_cb(tree, state, bits); - if (ret) - return ret; - if (bits_to_set & EXTENT_DIRTY) - tree->dirty_bytes += end - start + 1; - state->state |= bits_to_set; + set_state_bits(tree, state, bits); + node = tree_insert(&tree->state, end, &state->rb_node); if (node) { struct extent_state *found; @@ -357,13 +348,11 @@ static int insert_state(struct extent_io_tree *tree, return 0; } -static int split_cb(struct extent_io_tree *tree, struct extent_state *orig, +static void split_cb(struct extent_io_tree *tree, struct extent_state *orig, u64 split) { if (tree->ops && tree->ops->split_extent_hook) - return tree->ops->split_extent_hook(tree->mapping->host, - orig, split); - return 0; + tree->ops->split_extent_hook(tree->mapping->host, orig, split); } /* @@ -659,34 +648,25 @@ again: if (start > end) break; - if (need_resched()) { - spin_unlock(&tree->lock); - cond_resched(); - spin_lock(&tree->lock); - } + cond_resched_lock(&tree->lock); } out: spin_unlock(&tree->lock); return 0; } -static int set_state_bits(struct extent_io_tree *tree, +static void set_state_bits(struct extent_io_tree *tree, struct extent_state *state, int *bits) { - int ret; int bits_to_set = *bits & ~EXTENT_CTLBITS; - ret = set_state_cb(tree, state, bits); - if (ret) - return ret; + set_state_cb(tree, state, bits); if ((bits_to_set & EXTENT_DIRTY) && !(state->state & EXTENT_DIRTY)) { u64 range = state->end - state->start + 1; tree->dirty_bytes += range; } state->state |= bits_to_set; - - return 0; } static void cache_state(struct extent_state *state, @@ -779,9 +759,7 @@ hit_next: goto out; } - err = set_state_bits(tree, state, &bits); - if (err) - goto out; + set_state_bits(tree, state, &bits); cache_state(state, cached_state); merge_state(tree, state); @@ -830,9 +808,7 @@ hit_next: if (err) goto out; if (state->end <= end) { - err = set_state_bits(tree, state, &bits); - if (err) - goto out; + set_state_bits(tree, state, &bits); cache_state(state, cached_state); merge_state(tree, state); if (last_end == (u64)-1) @@ -893,11 +869,7 @@ hit_next: err = split_state(tree, state, prealloc, end + 1); BUG_ON(err == -EEXIST); - err = set_state_bits(tree, prealloc, &bits); - if (err) { - prealloc = NULL; - goto out; - } + set_state_bits(tree, prealloc, &bits); cache_state(prealloc, cached_state); merge_state(tree, prealloc); prealloc = NULL; @@ -1059,46 +1031,6 @@ static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end) return 0; } -/* - * find the first offset in the io tree with 'bits' set. zero is - * returned if we find something, and *start_ret and *end_ret are - * set to reflect the state struct that was found. - * - * If nothing was found, 1 is returned, < 0 on error - */ -int find_first_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, int bits) -{ - struct rb_node *node; - struct extent_state *state; - int ret = 1; - - spin_lock(&tree->lock); - /* - * this search will find all the extents that end after - * our range starts. - */ - node = tree_search(tree, start); - if (!node) - goto out; - - while (1) { - state = rb_entry(node, struct extent_state, rb_node); - if (state->end >= start && (state->state & bits)) { - *start_ret = state->start; - *end_ret = state->end; - ret = 0; - break; - } - node = rb_next(node); - if (!node) - break; - } -out: - spin_unlock(&tree->lock); - return ret; -} - /* find the first state struct with 'bits' set after 'start', and * return it. tree->lock must be held. NULL will returned if * nothing was found after 'start' @@ -1131,6 +1063,30 @@ out: } /* + * find the first offset in the io tree with 'bits' set. zero is + * returned if we find something, and *start_ret and *end_ret are + * set to reflect the state struct that was found. + * + * If nothing was found, 1 is returned, < 0 on error + */ +int find_first_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, int bits) +{ + struct extent_state *state; + int ret = 1; + + spin_lock(&tree->lock); + state = find_first_extent_bit_state(tree, start, bits); + if (state) { + *start_ret = state->start; + *end_ret = state->end; + ret = 0; + } + spin_unlock(&tree->lock); + return ret; +} + +/* * find a contiguous range of bytes in the file marked as delalloc, not * more than 'max_bytes'. start and end are used to return the range, * @@ -2546,7 +2502,6 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page, struct writeback_control *wbc) { int ret; - struct address_space *mapping = page->mapping; struct extent_page_data epd = { .bio = NULL, .tree = tree, @@ -2554,17 +2509,9 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page, .extent_locked = 0, .sync_io = wbc->sync_mode == WB_SYNC_ALL, }; - struct writeback_control wbc_writepages = { - .sync_mode = wbc->sync_mode, - .nr_to_write = 64, - .range_start = page_offset(page) + PAGE_CACHE_SIZE, - .range_end = (loff_t)-1, - }; ret = __extent_writepage(page, wbc, &epd); - extent_write_cache_pages(tree, mapping, &wbc_writepages, - __extent_writepage, &epd, flush_write_bio); flush_epd_write_bio(&epd); return ret; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 21a7ca9..7b2f0c3 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -76,15 +76,15 @@ struct extent_io_ops { struct extent_state *state); int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); - int (*set_bit_hook)(struct inode *inode, struct extent_state *state, - int *bits); - int (*clear_bit_hook)(struct inode *inode, struct extent_state *state, - int *bits); - int (*merge_extent_hook)(struct inode *inode, - struct extent_state *new, - struct extent_state *other); - int (*split_extent_hook)(struct inode *inode, - struct extent_state *orig, u64 split); + void (*set_bit_hook)(struct inode *inode, struct extent_state *state, + int *bits); + void (*clear_bit_hook)(struct inode *inode, struct extent_state *state, + int *bits); + void (*merge_extent_hook)(struct inode *inode, + struct extent_state *new, + struct extent_state *other); + void (*split_extent_hook)(struct inode *inode, + struct extent_state *orig, u64 split); int (*write_cache_pages_lock_hook)(struct page *page); }; @@ -108,8 +108,6 @@ struct extent_state { wait_queue_head_t wq; atomic_t refs; unsigned long state; - u64 split_start; - u64 split_end; /* for use by the FS */ u64 private; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 2d04103..7c97b33 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -183,22 +183,10 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next) return 0; } -int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len) +static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) { - int ret = 0; struct extent_map *merge = NULL; struct rb_node *rb; - struct extent_map *em; - - write_lock(&tree->lock); - em = lookup_extent_mapping(tree, start, len); - - WARN_ON(!em || em->start != start); - - if (!em) - goto out; - - clear_bit(EXTENT_FLAG_PINNED, &em->flags); if (em->start != 0) { rb = rb_prev(&em->rb_node); @@ -225,6 +213,24 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len) merge->in_tree = 0; free_extent_map(merge); } +} + +int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len) +{ + int ret = 0; + struct extent_map *em; + + write_lock(&tree->lock); + em = lookup_extent_mapping(tree, start, len); + + WARN_ON(!em || em->start != start); + + if (!em) + goto out; + + clear_bit(EXTENT_FLAG_PINNED, &em->flags); + + try_merge_map(tree, em); free_extent_map(em); out: @@ -247,7 +253,6 @@ int add_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) { int ret = 0; - struct extent_map *merge = NULL; struct rb_node *rb; struct extent_map *exist; @@ -263,30 +268,8 @@ int add_extent_mapping(struct extent_map_tree *tree, goto out; } atomic_inc(&em->refs); - if (em->start != 0) { - rb = rb_prev(&em->rb_node); - if (rb) - merge = rb_entry(rb, struct extent_map, rb_node); - if (rb && mergable_maps(merge, em)) { - em->start = merge->start; - em->len += merge->len; - em->block_len += merge->block_len; - em->block_start = merge->block_start; - merge->in_tree = 0; - rb_erase(&merge->rb_node, &tree->map); - free_extent_map(merge); - } - } - rb = rb_next(&em->rb_node); - if (rb) - merge = rb_entry(rb, struct extent_map, rb_node); - if (rb && mergable_maps(em, merge)) { - em->len += merge->len; - em->block_len += merge->len; - rb_erase(&merge->rb_node, &tree->map); - merge->in_tree = 0; - free_extent_map(merge); - } + + try_merge_map(tree, em); out: return ret; } @@ -299,19 +282,8 @@ static u64 range_end(u64 start, u64 len) return start + len; } -/** - * lookup_extent_mapping - lookup extent_map - * @tree: tree to lookup in - * @start: byte offset to start the search - * @len: length of the lookup range - * - * Find and return the first extent_map struct in @tree that intersects the - * [start, len] range. There may be additional objects in the tree that - * intersect, so check the object returned carefully to make sure that no - * additional lookups are needed. - */ -struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, - u64 start, u64 len) +struct extent_map *__lookup_extent_mapping(struct extent_map_tree *tree, + u64 start, u64 len, int strict) { struct extent_map *em; struct rb_node *rb_node; @@ -320,38 +292,42 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, u64 end = range_end(start, len); rb_node = __tree_search(&tree->map, start, &prev, &next); - if (!rb_node && prev) { - em = rb_entry(prev, struct extent_map, rb_node); - if (end > em->start && start < extent_map_end(em)) - goto found; - } - if (!rb_node && next) { - em = rb_entry(next, struct extent_map, rb_node); - if (end > em->start && start < extent_map_end(em)) - goto found; - } if (!rb_node) { - em = NULL; - goto out; - } - if (IS_ERR(rb_node)) { - em = ERR_CAST(rb_node); - goto out; + if (prev) + rb_node = prev; + else if (next) + rb_node = next; + else + return NULL; } + em = rb_entry(rb_node, struct extent_map, rb_node); - if (end > em->start && start < extent_map_end(em)) - goto found; - em = NULL; - goto out; + if (strict && !(end > em->start && start < extent_map_end(em))) + return NULL; -found: atomic_inc(&em->refs); -out: return em; } /** + * lookup_extent_mapping - lookup extent_map + * @tree: tree to lookup in + * @start: byte offset to start the search + * @len: length of the lookup range + * + * Find and return the first extent_map struct in @tree that intersects the + * [start, len] range. There may be additional objects in the tree that + * intersect, so check the object returned carefully to make sure that no + * additional lookups are needed. + */ +struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, + u64 start, u64 len) +{ + return __lookup_extent_mapping(tree, start, len, 1); +} + +/** * search_extent_mapping - find a nearby extent map * @tree: tree to lookup in * @start: byte offset to start the search @@ -365,38 +341,7 @@ out: struct extent_map *search_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len) { - struct extent_map *em; - struct rb_node *rb_node; - struct rb_node *prev = NULL; - struct rb_node *next = NULL; - - rb_node = __tree_search(&tree->map, start, &prev, &next); - if (!rb_node && prev) { - em = rb_entry(prev, struct extent_map, rb_node); - goto found; - } - if (!rb_node && next) { - em = rb_entry(next, struct extent_map, rb_node); - goto found; - } - if (!rb_node) { - em = NULL; - goto out; - } - if (IS_ERR(rb_node)) { - em = ERR_CAST(rb_node); - goto out; - } - em = rb_entry(rb_node, struct extent_map, rb_node); - goto found; - - em = NULL; - goto out; - -found: - atomic_inc(&em->refs); -out: - return em; + return __lookup_extent_mapping(tree, start, len, 0); } /** diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 08bcfa9..b910694 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -291,7 +291,8 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, u16 csum_size = btrfs_super_csum_size(&root->fs_info->super_copy); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; if (search_commit) { path->skip_locking = 1; @@ -677,7 +678,9 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, btrfs_super_csum_size(&root->fs_info->super_copy); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; + sector_sum = sums->sums; again: next_offset = (u64)-1; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a35e51c..658d669 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -74,7 +74,7 @@ struct inode_defrag { * If an existing record is found the defrag item you * pass in is freed */ -static int __btrfs_add_inode_defrag(struct inode *inode, +static void __btrfs_add_inode_defrag(struct inode *inode, struct inode_defrag *defrag) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -106,11 +106,11 @@ static int __btrfs_add_inode_defrag(struct inode *inode, BTRFS_I(inode)->in_defrag = 1; rb_link_node(&defrag->rb_node, parent, p); rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes); - return 0; + return; exists: kfree(defrag); - return 0; + return; } @@ -123,7 +123,6 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, { struct btrfs_root *root = BTRFS_I(inode)->root; struct inode_defrag *defrag; - int ret = 0; u64 transid; if (!btrfs_test_opt(root, AUTO_DEFRAG)) @@ -150,9 +149,9 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->defrag_inodes_lock); if (!BTRFS_I(inode)->in_defrag) - ret = __btrfs_add_inode_defrag(inode, defrag); + __btrfs_add_inode_defrag(inode, defrag); spin_unlock(&root->fs_info->defrag_inodes_lock); - return ret; + return 0; } /* @@ -855,7 +854,8 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, btrfs_drop_extent_cache(inode, start, end - 1, 0); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; again: recow = 0; split = start; @@ -1059,7 +1059,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos) static noinline int prepare_pages(struct btrfs_root *root, struct file *file, struct page **pages, size_t num_pages, loff_t pos, unsigned long first_index, - unsigned long last_index, size_t write_bytes) + size_t write_bytes) { struct extent_state *cached_state = NULL; int i; @@ -1159,7 +1159,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; unsigned long first_index; - unsigned long last_index; size_t num_written = 0; int nrptrs; int ret = 0; @@ -1172,7 +1171,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, return -ENOMEM; first_index = pos >> PAGE_CACHE_SHIFT; - last_index = (pos + iov_iter_count(i)) >> PAGE_CACHE_SHIFT; while (iov_iter_count(i) > 0) { size_t offset = pos & (PAGE_CACHE_SIZE - 1); @@ -1206,8 +1204,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * contents of pages from loop to loop */ ret = prepare_pages(root, file, pages, num_pages, - pos, first_index, last_index, - write_bytes); + pos, first_index, write_bytes); if (ret) { btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 13e6255..15fceef 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1061,7 +1061,8 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; nolock = btrfs_is_free_space_inode(root, inode); @@ -1282,17 +1283,16 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, return ret; } -static int btrfs_split_extent_hook(struct inode *inode, - struct extent_state *orig, u64 split) +static void btrfs_split_extent_hook(struct inode *inode, + struct extent_state *orig, u64 split) { /* not delalloc, ignore it */ if (!(orig->state & EXTENT_DELALLOC)) - return 0; + return; spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - return 0; } /* @@ -1301,18 +1301,17 @@ static int btrfs_split_extent_hook(struct inode *inode, * extents, such as when we are doing sequential writes, so we can properly * account for the metadata space we'll need. */ -static int btrfs_merge_extent_hook(struct inode *inode, - struct extent_state *new, - struct extent_state *other) +static void btrfs_merge_extent_hook(struct inode *inode, + struct extent_state *new, + struct extent_state *other) { /* not delalloc, ignore it */ if (!(other->state & EXTENT_DELALLOC)) - return 0; + return; spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents--; spin_unlock(&BTRFS_I(inode)->lock); - return 0; } /* @@ -1320,8 +1319,8 @@ static int btrfs_merge_extent_hook(struct inode *inode, * bytes in this file, and to maintain the list of inodes that * have pending delalloc work to be done. */ -static int btrfs_set_bit_hook(struct inode *inode, - struct extent_state *state, int *bits) +static void btrfs_set_bit_hook(struct inode *inode, + struct extent_state *state, int *bits) { /* @@ -1351,14 +1350,13 @@ static int btrfs_set_bit_hook(struct inode *inode, } spin_unlock(&root->fs_info->delalloc_lock); } - return 0; } /* * extent_io.c clear_bit_hook, see set_bit_hook for why */ -static int btrfs_clear_bit_hook(struct inode *inode, - struct extent_state *state, int *bits) +static void btrfs_clear_bit_hook(struct inode *inode, + struct extent_state *state, int *bits) { /* * set_bit and clear bit hooks normally require _irqsave/restore @@ -1395,7 +1393,6 @@ static int btrfs_clear_bit_hook(struct inode *inode, } spin_unlock(&root->fs_info->delalloc_lock); } - return 0; } /* @@ -1645,7 +1642,8 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, int ret; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; path->leave_spinning = 1; @@ -2215,7 +2213,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) if (!root->orphan_block_rsv) { block_rsv = btrfs_alloc_block_rsv(root); - BUG_ON(!block_rsv); + if (!block_rsv) + return -ENOMEM; } spin_lock(&root->orphan_lock); @@ -2517,7 +2516,9 @@ static void btrfs_read_locked_inode(struct inode *inode) filled = true; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + goto make_bad; + path->leave_spinning = 1; memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); @@ -2998,13 +2999,16 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode, dentry->d_name.name, dentry->d_name.len); - BUG_ON(ret); + if (ret) + goto out; if (inode->i_nlink == 0) { ret = btrfs_orphan_add(trans, inode); - BUG_ON(ret); + if (ret) + goto out; } +out: nr = trans->blocks_used; __unlink_end_trans(trans, root); btrfs_btree_balance_dirty(root, nr); @@ -3147,6 +3151,11 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY); + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + path->reada = -1; + if (root->ref_cows || root == root->fs_info->tree_root) btrfs_drop_extent_cache(inode, new_size & (~mask), (u64)-1, 0); @@ -3159,10 +3168,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, if (min_type == 0 && root == BTRFS_I(inode)->root) btrfs_kill_delayed_inode_items(inode); - path = btrfs_alloc_path(); - BUG_ON(!path); - path->reada = -1; - key.objectid = ino; key.offset = (u64)-1; key.type = (u8)-1; @@ -3690,7 +3695,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, int ret = 0; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(dir), name, namelen, 0); @@ -3946,6 +3952,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *new) { struct inode *inode; + int bad_inode = 0; inode = btrfs_iget_locked(s, location->objectid, root); if (!inode) @@ -3955,10 +3962,19 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, BTRFS_I(inode)->root = root; memcpy(&BTRFS_I(inode)->location, location, sizeof(*location)); btrfs_read_locked_inode(inode); - inode_tree_add(inode); - unlock_new_inode(inode); - if (new) - *new = 1; + if (!is_bad_inode(inode)) { + inode_tree_add(inode); + unlock_new_inode(inode); + if (new) + *new = 1; + } else { + bad_inode = 1; + } + } + + if (bad_inode) { + iput(inode); + inode = ERR_PTR(-ESTALE); } return inode; @@ -3993,12 +4009,19 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) struct btrfs_root *sub_root = root; struct btrfs_key location; int index; - int ret; + int ret = 0; if (dentry->d_name.len > BTRFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ret = btrfs_inode_by_name(dir, dentry, &location); + if (unlikely(d_need_lookup(dentry))) { + memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key)); + kfree(dentry->d_fsdata); + dentry->d_fsdata = NULL; + d_clear_need_lookup(dentry); + } else { + ret = btrfs_inode_by_name(dir, dentry, &location); + } if (ret < 0) return ERR_PTR(ret); @@ -4053,6 +4076,12 @@ static int btrfs_dentry_delete(const struct dentry *dentry) return 0; } +static void btrfs_dentry_release(struct dentry *dentry) +{ + if (dentry->d_fsdata) + kfree(dentry->d_fsdata); +} + static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { @@ -4075,6 +4104,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, struct btrfs_path *path; struct list_head ins_list; struct list_head del_list; + struct qstr q; int ret; struct extent_buffer *leaf; int slot; @@ -4164,6 +4194,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, while (di_cur < di_total) { struct btrfs_key location; + struct dentry *tmp; if (verify_dir_item(root, leaf, di)) break; @@ -4184,6 +4215,33 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)]; btrfs_dir_item_key_to_cpu(leaf, di, &location); + q.name = name_ptr; + q.len = name_len; + q.hash = full_name_hash(q.name, q.len); + tmp = d_lookup(filp->f_dentry, &q); + if (!tmp) { + struct btrfs_key *newkey; + + newkey = kzalloc(sizeof(struct btrfs_key), + GFP_NOFS); + if (!newkey) + goto no_dentry; + tmp = d_alloc(filp->f_dentry, &q); + if (!tmp) { + kfree(newkey); + dput(tmp); + goto no_dentry; + } + memcpy(newkey, &location, + sizeof(struct btrfs_key)); + tmp->d_fsdata = newkey; + tmp->d_flags |= DCACHE_NEED_LOOKUP; + d_rehash(tmp); + dput(tmp); + } else { + dput(tmp); + } +no_dentry: /* is this a reference to our own snapshot? If so * skip it */ @@ -4409,7 +4467,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, int owner; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return ERR_PTR(-ENOMEM); inode = new_inode(root->fs_info->sb); if (!inode) { @@ -6669,19 +6728,6 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, return 0; } -/* helper function for file defrag and space balancing. This - * forces readahead on a given range of bytes in an inode - */ -unsigned long btrfs_force_ra(struct address_space *mapping, - struct file_ra_state *ra, struct file *file, - pgoff_t offset, pgoff_t last_index) -{ - pgoff_t req_size = last_index - offset + 1; - - page_cache_sync_readahead(mapping, ra, file, offset, req_size); - return offset + req_size; -} - struct inode *btrfs_alloc_inode(struct super_block *sb) { struct btrfs_inode *ei; @@ -7164,7 +7210,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, goto out_unlock; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) { + err = -ENOMEM; + drop_inode = 1; + goto out_unlock; + } key.objectid = btrfs_ino(inode); key.offset = 0; btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY); @@ -7430,4 +7480,5 @@ static const struct inode_operations btrfs_symlink_inode_operations = { const struct dentry_operations btrfs_dentry_operations = { .d_delete = btrfs_dentry_delete, + .d_release = btrfs_dentry_release, }; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0b980af..7cf0133 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1749,11 +1749,10 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid; - } if (ptr < name) goto out; - memcpy(name, ptr, total_len); + memmove(name, ptr, total_len); name[total_len]='\0'; ret = 0; out: diff --git a/fs/btrfs/ref-cache.c b/fs/btrfs/ref-cache.c deleted file mode 100644 index 82d569c..0000000 --- a/fs/btrfs/ref-cache.c +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Copyright (C) 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License v2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - */ - -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/sort.h> -#include "ctree.h" -#include "ref-cache.h" -#include "transaction.h" - -static struct rb_node *tree_insert(struct rb_root *root, u64 bytenr, - struct rb_node *node) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct btrfs_leaf_ref *entry; - - while (*p) { - parent = *p; - entry = rb_entry(parent, struct btrfs_leaf_ref, rb_node); - - if (bytenr < entry->bytenr) - p = &(*p)->rb_left; - else if (bytenr > entry->bytenr) - p = &(*p)->rb_right; - else - return parent; - } - - entry = rb_entry(node, struct btrfs_leaf_ref, rb_node); - rb_link_node(node, parent, p); - rb_insert_color(node, root); - return NULL; -} - -static struct rb_node *tree_search(struct rb_root *root, u64 bytenr) -{ - struct rb_node *n = root->rb_node; - struct btrfs_leaf_ref *entry; - - while (n) { - entry = rb_entry(n, struct btrfs_leaf_ref, rb_node); - WARN_ON(!entry->in_tree); - - if (bytenr < entry->bytenr) - n = n->rb_left; - else if (bytenr > entry->bytenr) - n = n->rb_right; - else - return n; - } - return NULL; -} diff --git a/fs/btrfs/ref-cache.h b/fs/btrfs/ref-cache.h deleted file mode 100644 index 24f7001..0000000 --- a/fs/btrfs/ref-cache.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright (C) 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License v2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - */ -#ifndef __REFCACHE__ -#define __REFCACHE__ - -struct btrfs_extent_info { - /* bytenr and num_bytes find the extent in the extent allocation tree */ - u64 bytenr; - u64 num_bytes; - - /* objectid and offset find the back reference for the file */ - u64 objectid; - u64 offset; -}; - -struct btrfs_leaf_ref { - struct rb_node rb_node; - struct btrfs_leaf_ref_tree *tree; - int in_tree; - atomic_t usage; - - u64 root_gen; - u64 bytenr; - u64 owner; - u64 generation; - int nritems; - - struct list_head list; - struct btrfs_extent_info extents[]; -}; - -static inline size_t btrfs_leaf_ref_size(int nr_extents) -{ - return sizeof(struct btrfs_leaf_ref) + - sizeof(struct btrfs_extent_info) * nr_extents; -} -#endif diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index ebe4544..f409990 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -71,13 +71,12 @@ out: return ret; } -int btrfs_set_root_node(struct btrfs_root_item *item, - struct extent_buffer *node) +void btrfs_set_root_node(struct btrfs_root_item *item, + struct extent_buffer *node) { btrfs_set_root_bytenr(item, node->start); btrfs_set_root_level(item, btrfs_header_level(node)); btrfs_set_root_generation(item, btrfs_header_generation(node)); - return 0; } /* diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index eb55863..7dc36fa 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -216,17 +216,11 @@ static void wait_current_trans(struct btrfs_root *root) spin_lock(&root->fs_info->trans_lock); cur_trans = root->fs_info->running_transaction; if (cur_trans && cur_trans->blocked) { - DEFINE_WAIT(wait); atomic_inc(&cur_trans->use_count); spin_unlock(&root->fs_info->trans_lock); - while (1) { - prepare_to_wait(&root->fs_info->transaction_wait, &wait, - TASK_UNINTERRUPTIBLE); - if (!cur_trans->blocked) - break; - schedule(); - } - finish_wait(&root->fs_info->transaction_wait, &wait); + + wait_event(root->fs_info->transaction_wait, + !cur_trans->blocked); put_transaction(cur_trans); } else { spin_unlock(&root->fs_info->trans_lock); @@ -357,19 +351,10 @@ struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root } /* wait for a transaction commit to be fully complete */ -static noinline int wait_for_commit(struct btrfs_root *root, +static noinline void wait_for_commit(struct btrfs_root *root, struct btrfs_transaction *commit) { - DEFINE_WAIT(wait); - while (!commit->commit_done) { - prepare_to_wait(&commit->commit_wait, &wait, - TASK_UNINTERRUPTIBLE); - if (commit->commit_done) - break; - schedule(); - } - finish_wait(&commit->commit_wait, &wait); - return 0; + wait_event(commit->commit_wait, commit->commit_done); } int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) @@ -1085,22 +1070,7 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info) static void wait_current_trans_commit_start(struct btrfs_root *root, struct btrfs_transaction *trans) { - DEFINE_WAIT(wait); - - if (trans->in_commit) - return; - - while (1) { - prepare_to_wait(&root->fs_info->transaction_blocked_wait, &wait, - TASK_UNINTERRUPTIBLE); - if (trans->in_commit) { - finish_wait(&root->fs_info->transaction_blocked_wait, - &wait); - break; - } - schedule(); - finish_wait(&root->fs_info->transaction_blocked_wait, &wait); - } + wait_event(root->fs_info->transaction_blocked_wait, trans->in_commit); } /* @@ -1110,24 +1080,8 @@ static void wait_current_trans_commit_start(struct btrfs_root *root, static void wait_current_trans_commit_start_and_unblock(struct btrfs_root *root, struct btrfs_transaction *trans) { - DEFINE_WAIT(wait); - - if (trans->commit_done || (trans->in_commit && !trans->blocked)) - return; - - while (1) { - prepare_to_wait(&root->fs_info->transaction_wait, &wait, - TASK_UNINTERRUPTIBLE); - if (trans->commit_done || - (trans->in_commit && !trans->blocked)) { - finish_wait(&root->fs_info->transaction_wait, - &wait); - break; - } - schedule(); - finish_wait(&root->fs_info->transaction_wait, - &wait); - } + wait_event(root->fs_info->transaction_wait, + trans->commit_done || (trans->in_commit && !trans->blocked)); } /* @@ -1234,8 +1188,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, atomic_inc(&cur_trans->use_count); btrfs_end_transaction(trans, root); - ret = wait_for_commit(root, cur_trans); - BUG_ON(ret); + wait_for_commit(root, cur_trans); put_transaction(cur_trans); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ac278dd..babee65 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1617,7 +1617,8 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, return 0; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; nritems = btrfs_header_nritems(eb); for (i = 0; i < nritems; i++) { @@ -1723,7 +1724,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, return -ENOMEM; if (*level == 1) { - wc->process_func(root, next, wc, ptr_gen); + ret = wc->process_func(root, next, wc, ptr_gen); + if (ret) + return ret; path->slots[*level]++; if (wc->free) { @@ -1788,8 +1791,11 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, parent = path->nodes[*level + 1]; root_owner = btrfs_header_owner(parent); - wc->process_func(root, path->nodes[*level], wc, + ret = wc->process_func(root, path->nodes[*level], wc, btrfs_header_generation(path->nodes[*level])); + if (ret) + return ret; + if (wc->free) { struct extent_buffer *next; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b89e372..53875ae73 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1037,7 +1037,8 @@ static noinline int find_next_chunk(struct btrfs_root *root, struct btrfs_key found_key; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; key.objectid = objectid; key.offset = (u64)-1; @@ -2061,8 +2062,10 @@ int btrfs_balance(struct btrfs_root *dev_root) /* step two, relocate all the chunks */ path = btrfs_alloc_path(); - BUG_ON(!path); - + if (!path) { + ret = -ENOMEM; + goto error; + } key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_CHUNK_ITEM_KEY; @@ -2661,7 +2664,8 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, ret = find_next_chunk(fs_info->chunk_root, BTRFS_FIRST_CHUNK_TREE_OBJECTID, &chunk_offset); - BUG_ON(ret); + if (ret) + return ret; alloc_profile = BTRFS_BLOCK_GROUP_METADATA | (fs_info->metadata_alloc_profile & diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 8d8f28c..6873bb6 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -141,10 +141,11 @@ char *cifs_compose_mount_options(const char *sb_mountdata, rc = dns_resolve_server_name_to_ip(*devname, &srvIP); if (rc < 0) { - cERROR(1, "%s: Failed to resolve server part of %s to IP: %d", - __func__, *devname, rc); + cFYI(1, "%s: Failed to resolve server part of %s to IP: %d", + __func__, *devname, rc); goto compose_mount_options_err; } + /* md_len = strlen(...) + 12 for 'sep+prefixpath=' * assuming that we have 'unc=' and 'ip=' in * the original sb_mountdata diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 259991b..e76bfeb 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -87,9 +87,15 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, if ((cifs_pdu == NULL) || (server == NULL)) return -EINVAL; - if ((cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) == 0) + if (!(cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) || + server->tcpStatus == CifsNeedNegotiate) return rc; + if (!server->session_estab) { + strncpy(cifs_pdu->Signature.SecuritySignature, "BSRSPYL", 8); + return rc; + } + cifs_pdu->Signature.Sequence.SequenceNumber = cpu_to_le32(server->sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; @@ -178,9 +184,15 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, if ((cifs_pdu == NULL) || (server == NULL)) return -EINVAL; - if ((cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) == 0) + if (!(cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) || + server->tcpStatus == CifsNeedNegotiate) return rc; + if (!server->session_estab) { + strncpy(cifs_pdu->Signature.SecuritySignature, "BSRSPYL", 8); + return rc; + } + cifs_pdu->Signature.Sequence.SequenceNumber = cpu_to_le32(server->sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8655174..f93eb94 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -86,24 +86,6 @@ extern mempool_t *cifs_sm_req_poolp; extern mempool_t *cifs_req_poolp; extern mempool_t *cifs_mid_poolp; -void -cifs_sb_active(struct super_block *sb) -{ - struct cifs_sb_info *server = CIFS_SB(sb); - - if (atomic_inc_return(&server->active) == 1) - atomic_inc(&sb->s_active); -} - -void -cifs_sb_deactive(struct super_block *sb) -{ - struct cifs_sb_info *server = CIFS_SB(sb); - - if (atomic_dec_and_test(&server->active)) - deactivate_super(sb); -} - static int cifs_read_super(struct super_block *sb) { @@ -581,6 +563,10 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) mutex_unlock(&dir->i_mutex); dput(dentry); dentry = child; + if (!dentry->d_inode) { + dput(dentry); + dentry = ERR_PTR(-ENOENT); + } } while (!IS_ERR(dentry)); _FreeXid(xid); kfree(full_path); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index fbd050c..cb71dc1 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -41,10 +41,6 @@ extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; extern const struct address_space_operations cifs_addr_ops_smallbuf; -/* Functions related to super block operations */ -extern void cifs_sb_active(struct super_block *sb); -extern void cifs_sb_deactive(struct super_block *sb); - /* Functions related to inodes */ extern const struct inode_operations cifs_dir_inode_ops; extern struct inode *cifs_root_iget(struct super_block *); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 1fcf4e5..38ce6d4 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -942,8 +942,6 @@ GLOBAL_EXTERN spinlock_t siduidlock; GLOBAL_EXTERN spinlock_t sidgidlock; void cifs_oplock_break(struct work_struct *work); -void cifs_oplock_break_get(struct cifsFileInfo *cfile); -void cifs_oplock_break_put(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 1a9fe7f..aac37d9 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -107,7 +107,7 @@ static void mark_open_files_invalid(struct cifs_tcon *pTcon) static int cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) { - int rc = 0; + int rc; struct cifs_ses *ses; struct TCP_Server_Info *server; struct nls_table *nls_codepage; @@ -5720,6 +5720,7 @@ CIFSSMBQAllEAs(const int xid, struct cifs_tcon *tcon, char *temp_ptr; char *end_of_smb; __u16 params, byte_count, data_offset; + unsigned int ea_name_len = ea_name ? strlen(ea_name) : 0; cFYI(1, "In Query All EAs path %s", searchName); QAllEAsRetry: @@ -5837,7 +5838,8 @@ QAllEAsRetry: } if (ea_name) { - if (strncmp(ea_name, temp_ptr, name_len) == 0) { + if (ea_name_len == name_len && + strncmp(ea_name, temp_ptr, name_len) == 0) { temp_ptr += name_len + 1; rc = value_len; if (buf_size == 0) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e66297b..80c2e3a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -319,25 +319,328 @@ requeue_echo: queue_delayed_work(system_nrt_wq, &server->echo, SMB_ECHO_INTERVAL); } +static bool +allocate_buffers(char **bigbuf, char **smallbuf, unsigned int size, + bool is_large_buf) +{ + char *bbuf = *bigbuf, *sbuf = *smallbuf; + + if (bbuf == NULL) { + bbuf = (char *)cifs_buf_get(); + if (!bbuf) { + cERROR(1, "No memory for large SMB response"); + msleep(3000); + /* retry will check if exiting */ + return false; + } + } else if (is_large_buf) { + /* we are reusing a dirty large buf, clear its start */ + memset(bbuf, 0, size); + } + + if (sbuf == NULL) { + sbuf = (char *)cifs_small_buf_get(); + if (!sbuf) { + cERROR(1, "No memory for SMB response"); + msleep(1000); + /* retry will check if exiting */ + return false; + } + /* beginning of smb buffer is cleared in our buf_get */ + } else { + /* if existing small buf clear beginning */ + memset(sbuf, 0, size); + } + + *bigbuf = bbuf; + *smallbuf = sbuf; + + return true; +} + +static int +read_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg, + struct kvec *iov, unsigned int to_read, + unsigned int *ptotal_read, bool is_header_read) +{ + int length, rc = 0; + unsigned int total_read; + char *buf = iov->iov_base; + + for (total_read = 0; total_read < to_read; total_read += length) { + length = kernel_recvmsg(server->ssocket, smb_msg, iov, 1, + to_read - total_read, 0); + if (server->tcpStatus == CifsExiting) { + /* then will exit */ + rc = 2; + break; + } else if (server->tcpStatus == CifsNeedReconnect) { + cifs_reconnect(server); + /* Reconnect wakes up rspns q */ + /* Now we will reread sock */ + rc = 1; + break; + } else if (length == -ERESTARTSYS || + length == -EAGAIN || + length == -EINTR) { + /* + * Minimum sleep to prevent looping, allowing socket + * to clear and app threads to set tcpStatus + * CifsNeedReconnect if server hung. + */ + usleep_range(1000, 2000); + length = 0; + if (!is_header_read) + continue; + /* Special handling for header read */ + if (total_read) { + iov->iov_base = (to_read - total_read) + + buf; + iov->iov_len = to_read - total_read; + smb_msg->msg_control = NULL; + smb_msg->msg_controllen = 0; + rc = 3; + } else + rc = 1; + break; + } else if (length <= 0) { + cERROR(1, "Received no data, expecting %d", + to_read - total_read); + cifs_reconnect(server); + rc = 1; + break; + } + } + + *ptotal_read = total_read; + return rc; +} + +static bool +check_rfc1002_header(struct TCP_Server_Info *server, char *buf) +{ + char temp = *buf; + unsigned int pdu_length = be32_to_cpu( + ((struct smb_hdr *)buf)->smb_buf_length); + + /* + * The first byte big endian of the length field, + * is actually not part of the length but the type + * with the most common, zero, as regular data. + */ + if (temp == (char) RFC1002_SESSION_KEEP_ALIVE) { + return false; + } else if (temp == (char)RFC1002_POSITIVE_SESSION_RESPONSE) { + cFYI(1, "Good RFC 1002 session rsp"); + return false; + } else if (temp == (char)RFC1002_NEGATIVE_SESSION_RESPONSE) { + /* + * We get this from Windows 98 instead of an error on + * SMB negprot response. + */ + cFYI(1, "Negative RFC1002 Session Response Error 0x%x)", + pdu_length); + /* give server a second to clean up */ + msleep(1000); + /* + * Always try 445 first on reconnect since we get NACK + * on some if we ever connected to port 139 (the NACK + * is since we do not begin with RFC1001 session + * initialize frame). + */ + cifs_set_port((struct sockaddr *) + &server->dstaddr, CIFS_PORT); + cifs_reconnect(server); + wake_up(&server->response_q); + return false; + } else if (temp != (char) 0) { + cERROR(1, "Unknown RFC 1002 frame"); + cifs_dump_mem(" Received Data: ", buf, 4); + cifs_reconnect(server); + return false; + } + + /* else we have an SMB response */ + if ((pdu_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) || + (pdu_length < sizeof(struct smb_hdr) - 1 - 4)) { + cERROR(1, "Invalid size SMB length %d pdu_length %d", + 4, pdu_length+4); + cifs_reconnect(server); + wake_up(&server->response_q); + return false; + } + + return true; +} + +static struct mid_q_entry * +find_cifs_mid(struct TCP_Server_Info *server, struct smb_hdr *buf, + int *length, bool is_large_buf, bool *is_multi_rsp, char **bigbuf) +{ + struct mid_q_entry *mid = NULL, *tmp_mid, *ret = NULL; + + spin_lock(&GlobalMid_Lock); + list_for_each_entry_safe(mid, tmp_mid, &server->pending_mid_q, qhead) { + if (mid->mid != buf->Mid || + mid->midState != MID_REQUEST_SUBMITTED || + mid->command != buf->Command) + continue; + + if (*length == 0 && check2ndT2(buf, server->maxBuf) > 0) { + /* We have a multipart transact2 resp */ + *is_multi_rsp = true; + if (mid->resp_buf) { + /* merge response - fix up 1st*/ + *length = coalesce_t2(buf, mid->resp_buf); + if (*length > 0) { + *length = 0; + mid->multiRsp = true; + break; + } + /* All parts received or packet is malformed. */ + mid->multiEnd = true; + goto multi_t2_fnd; + } + if (!is_large_buf) { + /*FIXME: switch to already allocated largebuf?*/ + cERROR(1, "1st trans2 resp needs bigbuf"); + } else { + /* Have first buffer */ + mid->resp_buf = buf; + mid->largeBuf = true; + *bigbuf = NULL; + } + break; + } + mid->resp_buf = buf; + mid->largeBuf = is_large_buf; +multi_t2_fnd: + if (*length == 0) + mid->midState = MID_RESPONSE_RECEIVED; + else + mid->midState = MID_RESPONSE_MALFORMED; +#ifdef CONFIG_CIFS_STATS2 + mid->when_received = jiffies; +#endif + list_del_init(&mid->qhead); + ret = mid; + break; + } + spin_unlock(&GlobalMid_Lock); + + return ret; +} + +static void clean_demultiplex_info(struct TCP_Server_Info *server) +{ + int length; + + /* take it off the list, if it's not already */ + spin_lock(&cifs_tcp_ses_lock); + list_del_init(&server->tcp_ses_list); + spin_unlock(&cifs_tcp_ses_lock); + + spin_lock(&GlobalMid_Lock); + server->tcpStatus = CifsExiting; + spin_unlock(&GlobalMid_Lock); + wake_up_all(&server->response_q); + + /* + * Check if we have blocked requests that need to free. Note that + * cifs_max_pending is normally 50, but can be set at module install + * time to as little as two. + */ + spin_lock(&GlobalMid_Lock); + if (atomic_read(&server->inFlight) >= cifs_max_pending) + atomic_set(&server->inFlight, cifs_max_pending - 1); + /* + * We do not want to set the max_pending too low or we could end up + * with the counter going negative. + */ + spin_unlock(&GlobalMid_Lock); + /* + * Although there should not be any requests blocked on this queue it + * can not hurt to be paranoid and try to wake up requests that may + * haven been blocked when more than 50 at time were on the wire to the + * same server - they now will see the session is in exit state and get + * out of SendReceive. + */ + wake_up_all(&server->request_q); + /* give those requests time to exit */ + msleep(125); + + if (server->ssocket) { + sock_release(server->ssocket); + server->ssocket = NULL; + } + + if (!list_empty(&server->pending_mid_q)) { + struct list_head dispose_list; + struct mid_q_entry *mid_entry; + struct list_head *tmp, *tmp2; + + INIT_LIST_HEAD(&dispose_list); + spin_lock(&GlobalMid_Lock); + list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { + mid_entry = list_entry(tmp, struct mid_q_entry, qhead); + cFYI(1, "Clearing mid 0x%x", mid_entry->mid); + mid_entry->midState = MID_SHUTDOWN; + list_move(&mid_entry->qhead, &dispose_list); + } + spin_unlock(&GlobalMid_Lock); + + /* now walk dispose list and issue callbacks */ + list_for_each_safe(tmp, tmp2, &dispose_list) { + mid_entry = list_entry(tmp, struct mid_q_entry, qhead); + cFYI(1, "Callback mid 0x%x", mid_entry->mid); + list_del_init(&mid_entry->qhead); + mid_entry->callback(mid_entry); + } + /* 1/8th of sec is more than enough time for them to exit */ + msleep(125); + } + + if (!list_empty(&server->pending_mid_q)) { + /* + * mpx threads have not exited yet give them at least the smb + * send timeout time for long ops. + * + * Due to delays on oplock break requests, we need to wait at + * least 45 seconds before giving up on a request getting a + * response and going ahead and killing cifsd. + */ + cFYI(1, "Wait for exit from demultiplex thread"); + msleep(46000); + /* + * If threads still have not exited they are probably never + * coming home not much else we can do but free the memory. + */ + } + + kfree(server->hostname); + kfree(server); + + length = atomic_dec_return(&tcpSesAllocCount); + if (length > 0) + mempool_resize(cifs_req_poolp, length + cifs_min_rcv, + GFP_KERNEL); +} + static int cifs_demultiplex_thread(void *p) { int length; struct TCP_Server_Info *server = p; unsigned int pdu_length, total_read; + char *buf = NULL, *bigbuf = NULL, *smallbuf = NULL; struct smb_hdr *smb_buffer = NULL; - struct smb_hdr *bigbuf = NULL; - struct smb_hdr *smallbuf = NULL; struct msghdr smb_msg; struct kvec iov; - struct socket *csocket = server->ssocket; - struct list_head *tmp, *tmp2; struct task_struct *task_to_wake = NULL; struct mid_q_entry *mid_entry; - char temp; bool isLargeBuf = false; - bool isMultiRsp; - int reconnect; + bool isMultiRsp = false; + int rc; current->flags |= PF_MEMALLOC; cFYI(1, "Demultiplex PID: %d", task_pid_nr(current)); @@ -351,35 +654,16 @@ cifs_demultiplex_thread(void *p) while (server->tcpStatus != CifsExiting) { if (try_to_freeze()) continue; - if (bigbuf == NULL) { - bigbuf = cifs_buf_get(); - if (!bigbuf) { - cERROR(1, "No memory for large SMB response"); - msleep(3000); - /* retry will check if exiting */ - continue; - } - } else if (isLargeBuf) { - /* we are reusing a dirty large buf, clear its start */ - memset(bigbuf, 0, sizeof(struct smb_hdr)); - } - if (smallbuf == NULL) { - smallbuf = cifs_small_buf_get(); - if (!smallbuf) { - cERROR(1, "No memory for SMB response"); - msleep(1000); - /* retry will check if exiting */ - continue; - } - /* beginning of smb buffer is cleared in our buf_get */ - } else /* if existing small buf clear beginning */ - memset(smallbuf, 0, sizeof(struct smb_hdr)); + if (!allocate_buffers(&bigbuf, &smallbuf, + sizeof(struct smb_hdr), isLargeBuf)) + continue; isLargeBuf = false; isMultiRsp = false; - smb_buffer = smallbuf; - iov.iov_base = smb_buffer; + smb_buffer = (struct smb_hdr *)smallbuf; + buf = smallbuf; + iov.iov_base = buf; iov.iov_len = 4; smb_msg.msg_control = NULL; smb_msg.msg_controllen = 0; @@ -393,158 +677,50 @@ incomplete_rcv: "Reconnecting...", server->hostname, (echo_retries * SMB_ECHO_INTERVAL / HZ)); cifs_reconnect(server); - csocket = server->ssocket; wake_up(&server->response_q); continue; } - length = - kernel_recvmsg(csocket, &smb_msg, - &iov, 1, pdu_length, 0 /* BB other flags? */); - - if (server->tcpStatus == CifsExiting) { + rc = read_from_socket(server, &smb_msg, &iov, pdu_length, + &total_read, true /* header read */); + if (rc == 3) + goto incomplete_rcv; + else if (rc == 2) break; - } else if (server->tcpStatus == CifsNeedReconnect) { - cFYI(1, "Reconnect after server stopped responding"); - cifs_reconnect(server); - cFYI(1, "call to reconnect done"); - csocket = server->ssocket; - continue; - } else if (length == -ERESTARTSYS || - length == -EAGAIN || - length == -EINTR) { - msleep(1); /* minimum sleep to prevent looping - allowing socket to clear and app threads to set - tcpStatus CifsNeedReconnect if server hung */ - if (pdu_length < 4) { - iov.iov_base = (4 - pdu_length) + - (char *)smb_buffer; - iov.iov_len = pdu_length; - smb_msg.msg_control = NULL; - smb_msg.msg_controllen = 0; - goto incomplete_rcv; - } else - continue; - } else if (length <= 0) { - cFYI(1, "Reconnect after unexpected peek error %d", - length); - cifs_reconnect(server); - csocket = server->ssocket; - wake_up(&server->response_q); + else if (rc == 1) continue; - } else if (length < pdu_length) { - cFYI(1, "requested %d bytes but only got %d bytes", - pdu_length, length); - pdu_length -= length; - msleep(1); - goto incomplete_rcv; - } - - /* The right amount was read from socket - 4 bytes */ - /* so we can now interpret the length field */ - /* the first byte big endian of the length field, - is actually not part of the length but the type - with the most common, zero, as regular data */ - temp = *((char *) smb_buffer); + /* + * The right amount was read from socket - 4 bytes, + * so we can now interpret the length field. + */ - /* Note that FC 1001 length is big endian on the wire, - but we convert it here so it is always manipulated - as host byte order */ + /* + * Note that RFC 1001 length is big endian on the wire, + * but we convert it here so it is always manipulated + * as host byte order. + */ pdu_length = be32_to_cpu(smb_buffer->smb_buf_length); cFYI(1, "rfc1002 length 0x%x", pdu_length+4); - - if (temp == (char) RFC1002_SESSION_KEEP_ALIVE) { - continue; - } else if (temp == (char)RFC1002_POSITIVE_SESSION_RESPONSE) { - cFYI(1, "Good RFC 1002 session rsp"); - continue; - } else if (temp == (char)RFC1002_NEGATIVE_SESSION_RESPONSE) { - /* we get this from Windows 98 instead of - an error on SMB negprot response */ - cFYI(1, "Negative RFC1002 Session Response Error 0x%x)", - pdu_length); - /* give server a second to clean up */ - msleep(1000); - /* always try 445 first on reconnect since we get NACK - * on some if we ever connected to port 139 (the NACK - * is since we do not begin with RFC1001 session - * initialize frame) - */ - cifs_set_port((struct sockaddr *) - &server->dstaddr, CIFS_PORT); - cifs_reconnect(server); - csocket = server->ssocket; - wake_up(&server->response_q); - continue; - } else if (temp != (char) 0) { - cERROR(1, "Unknown RFC 1002 frame"); - cifs_dump_mem(" Received Data: ", (char *)smb_buffer, - length); - cifs_reconnect(server); - csocket = server->ssocket; + if (!check_rfc1002_header(server, buf)) continue; - } - - /* else we have an SMB response */ - if ((pdu_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) || - (pdu_length < sizeof(struct smb_hdr) - 1 - 4)) { - cERROR(1, "Invalid size SMB length %d pdu_length %d", - length, pdu_length+4); - cifs_reconnect(server); - csocket = server->ssocket; - wake_up(&server->response_q); - continue; - } /* else length ok */ - reconnect = 0; - if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE - 4) { isLargeBuf = true; memcpy(bigbuf, smallbuf, 4); - smb_buffer = bigbuf; + smb_buffer = (struct smb_hdr *)bigbuf; + buf = bigbuf; } - length = 0; - iov.iov_base = 4 + (char *)smb_buffer; + + iov.iov_base = 4 + buf; iov.iov_len = pdu_length; - for (total_read = 0; total_read < pdu_length; - total_read += length) { - length = kernel_recvmsg(csocket, &smb_msg, &iov, 1, - pdu_length - total_read, 0); - if (server->tcpStatus == CifsExiting) { - /* then will exit */ - reconnect = 2; - break; - } else if (server->tcpStatus == CifsNeedReconnect) { - cifs_reconnect(server); - csocket = server->ssocket; - /* Reconnect wakes up rspns q */ - /* Now we will reread sock */ - reconnect = 1; - break; - } else if (length == -ERESTARTSYS || - length == -EAGAIN || - length == -EINTR) { - msleep(1); /* minimum sleep to prevent looping, - allowing socket to clear and app - threads to set tcpStatus - CifsNeedReconnect if server hung*/ - length = 0; - continue; - } else if (length <= 0) { - cERROR(1, "Received no data, expecting %d", - pdu_length - total_read); - cifs_reconnect(server); - csocket = server->ssocket; - reconnect = 1; - break; - } - } - if (reconnect == 2) + rc = read_from_socket(server, &smb_msg, &iov, pdu_length, + &total_read, false); + if (rc == 2) break; - else if (reconnect == 1) + else if (rc == 1) continue; total_read += 4; /* account for rfc1002 hdr */ @@ -562,75 +738,13 @@ incomplete_rcv: */ length = checkSMB(smb_buffer, smb_buffer->Mid, total_read); if (length != 0) - cifs_dump_mem("Bad SMB: ", smb_buffer, - min_t(unsigned int, total_read, 48)); + cifs_dump_mem("Bad SMB: ", buf, + min_t(unsigned int, total_read, 48)); - mid_entry = NULL; server->lstrp = jiffies; - spin_lock(&GlobalMid_Lock); - list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - - if (mid_entry->mid != smb_buffer->Mid || - mid_entry->midState != MID_REQUEST_SUBMITTED || - mid_entry->command != smb_buffer->Command) { - mid_entry = NULL; - continue; - } - - if (length == 0 && - check2ndT2(smb_buffer, server->maxBuf) > 0) { - /* We have a multipart transact2 resp */ - isMultiRsp = true; - if (mid_entry->resp_buf) { - /* merge response - fix up 1st*/ - length = coalesce_t2(smb_buffer, - mid_entry->resp_buf); - if (length > 0) { - length = 0; - mid_entry->multiRsp = true; - break; - } else { - /* all parts received or - * packet is malformed - */ - mid_entry->multiEnd = true; - goto multi_t2_fnd; - } - } else { - if (!isLargeBuf) { - /* - * FIXME: switch to already - * allocated largebuf? - */ - cERROR(1, "1st trans2 resp " - "needs bigbuf"); - } else { - /* Have first buffer */ - mid_entry->resp_buf = - smb_buffer; - mid_entry->largeBuf = true; - bigbuf = NULL; - } - } - break; - } - mid_entry->resp_buf = smb_buffer; - mid_entry->largeBuf = isLargeBuf; -multi_t2_fnd: - if (length == 0) - mid_entry->midState = MID_RESPONSE_RECEIVED; - else - mid_entry->midState = MID_RESPONSE_MALFORMED; -#ifdef CONFIG_CIFS_STATS2 - mid_entry->when_received = jiffies; -#endif - list_del_init(&mid_entry->qhead); - break; - } - spin_unlock(&GlobalMid_Lock); - + mid_entry = find_cifs_mid(server, smb_buffer, &length, + isLargeBuf, &isMultiRsp, &bigbuf); if (mid_entry != NULL) { mid_entry->callback(mid_entry); /* Was previous buf put in mpx struct for multi-rsp? */ @@ -648,7 +762,7 @@ multi_t2_fnd: !isMultiRsp) { cERROR(1, "No task to wake, unknown frame received! " "NumMids %d", atomic_read(&midCount)); - cifs_dump_mem("Received Data is: ", (char *)smb_buffer, + cifs_dump_mem("Received Data is: ", buf, sizeof(struct smb_hdr)); #ifdef CONFIG_CIFS_DEBUG2 cifs_dump_detail(smb_buffer); @@ -658,88 +772,13 @@ multi_t2_fnd: } } /* end while !EXITING */ - /* take it off the list, if it's not already */ - spin_lock(&cifs_tcp_ses_lock); - list_del_init(&server->tcp_ses_list); - spin_unlock(&cifs_tcp_ses_lock); - - spin_lock(&GlobalMid_Lock); - server->tcpStatus = CifsExiting; - spin_unlock(&GlobalMid_Lock); - wake_up_all(&server->response_q); - - /* check if we have blocked requests that need to free */ - /* Note that cifs_max_pending is normally 50, but - can be set at module install time to as little as two */ - spin_lock(&GlobalMid_Lock); - if (atomic_read(&server->inFlight) >= cifs_max_pending) - atomic_set(&server->inFlight, cifs_max_pending - 1); - /* We do not want to set the max_pending too low or we - could end up with the counter going negative */ - spin_unlock(&GlobalMid_Lock); - /* Although there should not be any requests blocked on - this queue it can not hurt to be paranoid and try to wake up requests - that may haven been blocked when more than 50 at time were on the wire - to the same server - they now will see the session is in exit state - and get out of SendReceive. */ - wake_up_all(&server->request_q); - /* give those requests time to exit */ - msleep(125); - - if (server->ssocket) { - sock_release(csocket); - server->ssocket = NULL; - } /* buffer usually freed in free_mid - need to free it here on exit */ cifs_buf_release(bigbuf); if (smallbuf) /* no sense logging a debug message if NULL */ cifs_small_buf_release(smallbuf); - if (!list_empty(&server->pending_mid_q)) { - struct list_head dispose_list; - - INIT_LIST_HEAD(&dispose_list); - spin_lock(&GlobalMid_Lock); - list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - cFYI(1, "Clearing mid 0x%x", mid_entry->mid); - mid_entry->midState = MID_SHUTDOWN; - list_move(&mid_entry->qhead, &dispose_list); - } - spin_unlock(&GlobalMid_Lock); - - /* now walk dispose list and issue callbacks */ - list_for_each_safe(tmp, tmp2, &dispose_list) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - cFYI(1, "Callback mid 0x%x", mid_entry->mid); - list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); - } - /* 1/8th of sec is more than enough time for them to exit */ - msleep(125); - } - - if (!list_empty(&server->pending_mid_q)) { - /* mpx threads have not exited yet give them - at least the smb send timeout time for long ops */ - /* due to delays on oplock break requests, we need - to wait at least 45 seconds before giving up - on a request getting a response and going ahead - and killing cifsd */ - cFYI(1, "Wait for exit from demultiplex thread"); - msleep(46000); - /* if threads still have not exited they are probably never - coming home not much else we can do but free the memory */ - } - - kfree(server->hostname); task_to_wake = xchg(&server->tsk, NULL); - kfree(server); - - length = atomic_dec_return(&tcpSesAllocCount); - if (length > 0) - mempool_resize(cifs_req_poolp, length + cifs_min_rcv, - GFP_KERNEL); + clean_demultiplex_info(server); /* if server->tsk was NULL then wait for a signal before exiting */ if (!task_to_wake) { @@ -3193,15 +3232,9 @@ mount_fail_check: else cifs_put_tcp_session(srvTcp); bdi_destroy(&cifs_sb->bdi); - goto out; } - /* volume_info->password is freed above when existing session found - (in which case it is not needed anymore) but when new sesion is created - the password ptr is put in the new session structure (in which case the - password will be freed at unmount time) */ out: - /* zero out password before freeing */ FreeXid(xid); return rc; } diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 548f062..1d2d91d 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -79,8 +79,8 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) /* Perform the upcall */ rc = dns_query(NULL, hostname, len, NULL, ip_addr, NULL); if (rc < 0) - cERROR(1, "%s: unable to resolve: %*.*s", - __func__, len, len, hostname); + cFYI(1, "%s: unable to resolve: %*.*s", + __func__, len, len, hostname); else cFYI(1, "%s: resolved: %*.*s to %s", __func__, len, len, hostname, *ip_addr); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 378acdaf..9f41a10 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -314,6 +314,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); + cancel_work_sync(&cifs_file->oplock_break); + if (!tcon->need_reconnect && !cifs_file->invalidHandle) { int xid, rc; @@ -2418,31 +2420,6 @@ void cifs_oplock_break(struct work_struct *work) cinode->clientCanCacheRead ? 1 : 0); cFYI(1, "Oplock release rc = %d", rc); } - - /* - * We might have kicked in before is_valid_oplock_break() - * finished grabbing reference for us. Make sure it's done by - * waiting for cifs_file_list_lock. - */ - spin_lock(&cifs_file_list_lock); - spin_unlock(&cifs_file_list_lock); - - cifs_oplock_break_put(cfile); -} - -/* must be called while holding cifs_file_list_lock */ -void cifs_oplock_break_get(struct cifsFileInfo *cfile) -{ - cifs_sb_active(cfile->dentry->d_sb); - cifsFileInfo_get(cfile); -} - -void cifs_oplock_break_put(struct cifsFileInfo *cfile) -{ - struct super_block *sb = cfile->dentry->d_sb; - - cifsFileInfo_put(cfile); - cifs_sb_deactive(sb); } const struct address_space_operations cifs_addr_ops = { diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9b018c8..a7b2dcd 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -764,20 +764,10 @@ char *cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb, if (full_path == NULL) return full_path; - if (dfsplen) { + if (dfsplen) strncpy(full_path, tcon->treeName, dfsplen); - /* switch slash direction in prepath depending on whether - * windows or posix style path names - */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) { - int i; - for (i = 0; i < dfsplen; i++) { - if (full_path[i] == '\\') - full_path[i] = '/'; - } - } - } strncpy(full_path + dfsplen, vol->prepath, pplen); + convert_delimiter(full_path, CIFS_DIR_SEP(cifs_sb)); full_path[dfsplen + pplen] = 0; /* add trailing null */ return full_path; } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 03a1f491..7c16933 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -585,15 +585,8 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) cifs_set_oplock_level(pCifsInode, pSMB->OplockLevel ? OPLOCK_READ : 0); - /* - * cifs_oplock_break_put() can't be called - * from here. Get reference after queueing - * succeeded. cifs_oplock_break() will - * synchronize using cifs_file_list_lock. - */ - if (queue_work(system_nrt_wq, - &netfile->oplock_break)) - cifs_oplock_break_get(netfile); + queue_work(system_nrt_wq, + &netfile->oplock_break); netfile->oplock_break_cancelled = false; spin_unlock(&cifs_file_list_lock); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 147aa22..c1b9c4b 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -362,6 +362,8 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, mid = AllocMidQEntry(hdr, server); if (mid == NULL) { mutex_unlock(&server->srv_mutex); + atomic_dec(&server->inFlight); + wake_up(&server->request_q); return -ENOMEM; } diff --git a/fs/dcache.c b/fs/dcache.c index b05aac3..a88948b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -301,6 +301,27 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) return parent; } +/* + * Unhash a dentry without inserting an RCU walk barrier or checking that + * dentry->d_lock is locked. The caller must take care of that, if + * appropriate. + */ +static void __d_shrink(struct dentry *dentry) +{ + if (!d_unhashed(dentry)) { + struct hlist_bl_head *b; + if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) + b = &dentry->d_sb->s_anon; + else + b = d_hash(dentry->d_parent, dentry->d_name.hash); + + hlist_bl_lock(b); + __hlist_bl_del(&dentry->d_hash); + dentry->d_hash.pprev = NULL; + hlist_bl_unlock(b); + } +} + /** * d_drop - drop a dentry * @dentry: dentry to drop @@ -319,17 +340,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { - struct hlist_bl_head *b; - if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) - b = &dentry->d_sb->s_anon; - else - b = d_hash(dentry->d_parent, dentry->d_name.hash); - - hlist_bl_lock(b); - __hlist_bl_del(&dentry->d_hash); - dentry->d_hash.pprev = NULL; - hlist_bl_unlock(b); - + __d_shrink(dentry); dentry_rcuwalk_barrier(dentry); } } @@ -784,6 +795,7 @@ relock: /** * prune_dcache_sb - shrink the dcache + * @sb: superblock * @nr_to_scan: number of entries to try to free * * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is @@ -828,44 +840,24 @@ EXPORT_SYMBOL(shrink_dcache_sb); static void shrink_dcache_for_umount_subtree(struct dentry *dentry) { struct dentry *parent; - unsigned detached = 0; BUG_ON(!IS_ROOT(dentry)); - /* detach this root from the system */ - spin_lock(&dentry->d_lock); - dentry_lru_del(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - for (;;) { /* descend to the first leaf in the current subtree */ - while (!list_empty(&dentry->d_subdirs)) { - struct dentry *loop; - - /* this is a branch with children - detach all of them - * from the system in one go */ - spin_lock(&dentry->d_lock); - list_for_each_entry(loop, &dentry->d_subdirs, - d_u.d_child) { - spin_lock_nested(&loop->d_lock, - DENTRY_D_LOCK_NESTED); - dentry_lru_del(loop); - __d_drop(loop); - spin_unlock(&loop->d_lock); - } - spin_unlock(&dentry->d_lock); - - /* move to the first child */ + while (!list_empty(&dentry->d_subdirs)) dentry = list_entry(dentry->d_subdirs.next, struct dentry, d_u.d_child); - } /* consume the dentries from this leaf up through its parents * until we find one with children or run out altogether */ do { struct inode *inode; + /* detach from the system */ + dentry_lru_del(dentry); + __d_shrink(dentry); + if (dentry->d_count != 0) { printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%s}" @@ -886,14 +878,10 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) list_del(&dentry->d_u.d_child); } else { parent = dentry->d_parent; - spin_lock(&parent->d_lock); parent->d_count--; list_del(&dentry->d_u.d_child); - spin_unlock(&parent->d_lock); } - detached++; - inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; @@ -938,9 +926,7 @@ void shrink_dcache_for_umount(struct super_block *sb) dentry = sb->s_root; sb->s_root = NULL; - spin_lock(&dentry->d_lock); dentry->d_count--; - spin_unlock(&dentry->d_lock); shrink_dcache_for_umount_subtree(dentry); while (!hlist_bl_empty(&sb->s_anon)) { @@ -1743,7 +1729,7 @@ seqretry: */ if (read_seqcount_retry(&dentry->d_seq, *seq)) goto seqretry; - if (parent->d_flags & DCACHE_OP_COMPARE) { + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { if (parent->d_op->d_compare(parent, *inode, dentry, i, tlen, tname, name)) diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild index 2d0f757..c5a5855 100644 --- a/fs/exofs/Kbuild +++ b/fs/exofs/Kbuild @@ -12,5 +12,8 @@ # Kbuild - Gets included from the Kernels Makefile and build system # -exofs-y := ios.o inode.o file.o symlink.o namei.o dir.o super.o +# ore module library +obj-$(CONFIG_ORE) += ore.o + +exofs-y := inode.o file.o symlink.o namei.o dir.o super.o obj-$(CONFIG_EXOFS_FS) += exofs.o diff --git a/fs/exofs/Kconfig b/fs/exofs/Kconfig index 86194b2..70bae41 100644 --- a/fs/exofs/Kconfig +++ b/fs/exofs/Kconfig @@ -1,6 +1,10 @@ +config ORE + tristate + config EXOFS_FS tristate "exofs: OSD based file system support" depends on SCSI_OSD_ULD + select ORE help EXOFS is a file system that uses an OSD storage device, as its backing storage. diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index c965806..f4e442e 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -36,12 +36,9 @@ #include <linux/fs.h> #include <linux/time.h> #include <linux/backing-dev.h> -#include "common.h" +#include <scsi/osd_ore.h> -/* FIXME: Remove once pnfs hits mainline - * #include <linux/exportfs/pnfs_osd_xdr.h> - */ -#include "pnfs.h" +#include "common.h" #define EXOFS_ERR(fmt, a...) printk(KERN_ERR "exofs: " fmt, ##a) @@ -56,27 +53,11 @@ /* u64 has problems with printk this will cast it to unsigned long long */ #define _LLU(x) (unsigned long long)(x) -struct exofs_layout { - osd_id s_pid; /* partition ID of file system*/ - - /* Our way of looking at the data_map */ - unsigned stripe_unit; - unsigned mirrors_p1; - - unsigned group_width; - u64 group_depth; - unsigned group_count; - - enum exofs_inode_layout_gen_functions lay_func; - - unsigned s_numdevs; /* Num of devices in array */ - struct osd_dev *s_ods[0]; /* Variable length */ -}; - /* * our extension to the in-memory superblock */ struct exofs_sb_info { + struct backing_dev_info bdi; /* register our bdi with VFS */ struct exofs_sb_stats s_ess; /* Written often, pre-allocate*/ int s_timeout; /* timeout for OSD operations */ uint64_t s_nextid; /* highest object ID used */ @@ -84,16 +65,13 @@ struct exofs_sb_info { spinlock_t s_next_gen_lock; /* spinlock for gen # update */ u32 s_next_generation; /* next gen # to use */ atomic_t s_curr_pending; /* number of pending commands */ - uint8_t s_cred[OSD_CAP_LEN]; /* credential for the fscb */ - struct backing_dev_info bdi; /* register our bdi with VFS */ struct pnfs_osd_data_map data_map; /* Default raid to use * FIXME: Needed ? */ -/* struct exofs_layout dir_layout;*/ /* Default dir layout */ - struct exofs_layout layout; /* Default files layout, - * contains the variable osd_dev - * array. Keep last */ + struct ore_layout layout; /* Default files layout */ + struct ore_comp one_comp; /* id & cred of partition id=0*/ + struct ore_components comps; /* comps for the partition */ struct osd_dev *_min_one_dev[1]; /* Place holder for one dev */ }; @@ -107,7 +85,8 @@ struct exofs_i_info { uint32_t i_data[EXOFS_IDATA];/*short symlink names and device #s*/ uint32_t i_dir_start_lookup; /* which page to start lookup */ uint64_t i_commit_size; /* the object's written length */ - uint8_t i_cred[OSD_CAP_LEN];/* all-powerful credential */ + struct ore_comp one_comp; /* same component for all devices */ + struct ore_components comps; /* inode view of the device table */ }; static inline osd_id exofs_oi_objno(struct exofs_i_info *oi) @@ -115,52 +94,6 @@ static inline osd_id exofs_oi_objno(struct exofs_i_info *oi) return oi->vfs_inode.i_ino + EXOFS_OBJ_OFF; } -struct exofs_io_state; -typedef void (*exofs_io_done_fn)(struct exofs_io_state *or, void *private); - -struct exofs_io_state { - struct kref kref; - - void *private; - exofs_io_done_fn done; - - struct exofs_layout *layout; - struct osd_obj_id obj; - u8 *cred; - - /* Global read/write IO*/ - loff_t offset; - unsigned long length; - void *kern_buff; - - struct page **pages; - unsigned nr_pages; - unsigned pgbase; - unsigned pages_consumed; - - /* Attributes */ - unsigned in_attr_len; - struct osd_attr *in_attr; - unsigned out_attr_len; - struct osd_attr *out_attr; - - /* Variable array of size numdevs */ - unsigned numdevs; - struct exofs_per_dev_state { - struct osd_request *or; - struct bio *bio; - loff_t offset; - unsigned length; - unsigned dev; - } per_dev[]; -}; - -static inline unsigned exofs_io_state_size(unsigned numdevs) -{ - return sizeof(struct exofs_io_state) + - sizeof(struct exofs_per_dev_state) * numdevs; -} - /* * our inode flags */ @@ -205,12 +138,6 @@ static inline struct exofs_i_info *exofs_i(struct inode *inode) } /* - * Given a layout, object_number and stripe_index return the associated global - * dev_index - */ -unsigned exofs_layout_od_id(struct exofs_layout *layout, - osd_id obj_no, unsigned layout_index); -/* * Maximum count of links to a file */ #define EXOFS_LINK_MAX 32000 @@ -219,44 +146,8 @@ unsigned exofs_layout_od_id(struct exofs_layout *layout, * function declarations * *************************/ -/* ios.c */ -void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], - const struct osd_obj_id *obj); -int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj, - u64 offset, void *p, unsigned length); - -int exofs_get_io_state(struct exofs_layout *layout, - struct exofs_io_state **ios); -void exofs_put_io_state(struct exofs_io_state *ios); - -int exofs_check_io(struct exofs_io_state *ios, u64 *resid); - -int exofs_sbi_create(struct exofs_io_state *ios); -int exofs_sbi_remove(struct exofs_io_state *ios); -int exofs_sbi_write(struct exofs_io_state *ios); -int exofs_sbi_read(struct exofs_io_state *ios); - -int extract_attr_from_ios(struct exofs_io_state *ios, struct osd_attr *attr); - -int exofs_oi_truncate(struct exofs_i_info *oi, u64 new_len); -static inline int exofs_oi_write(struct exofs_i_info *oi, - struct exofs_io_state *ios) -{ - ios->obj.id = exofs_oi_objno(oi); - ios->cred = oi->i_cred; - return exofs_sbi_write(ios); -} - -static inline int exofs_oi_read(struct exofs_i_info *oi, - struct exofs_io_state *ios) -{ - ios->obj.id = exofs_oi_objno(oi); - ios->cred = oi->i_cred; - return exofs_sbi_read(ios); -} - /* inode.c */ -unsigned exofs_max_io_pages(struct exofs_layout *layout, +unsigned exofs_max_io_pages(struct ore_layout *layout, unsigned expected_pages); int exofs_setattr(struct dentry *, struct iattr *); int exofs_write_begin(struct file *file, struct address_space *mapping, @@ -281,6 +172,8 @@ int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *, struct inode *); /* super.c */ +void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], + const struct osd_obj_id *obj); int exofs_sbi_write_stats(struct exofs_sb_info *sbi); /********************* @@ -295,7 +188,6 @@ extern const struct file_operations exofs_file_operations; /* inode.c */ extern const struct address_space_operations exofs_aops; -extern const struct osd_attr g_attr_logical_length; /* namei.c */ extern const struct inode_operations exofs_dir_inode_operations; @@ -305,4 +197,33 @@ extern const struct inode_operations exofs_special_inode_operations; extern const struct inode_operations exofs_symlink_inode_operations; extern const struct inode_operations exofs_fast_symlink_inode_operations; +/* exofs_init_comps will initialize an ore_components device array + * pointing to a single ore_comp struct, and a round-robin view + * of the device table. + * The first device of each inode is the [inode->ino % num_devices] + * and the rest of the devices sequentially following where the + * first device is after the last device. + * It is assumed that the global device array at @sbi is twice + * bigger and that the device table repeats twice. + * See: exofs_read_lookup_dev_table() + */ +static inline void exofs_init_comps(struct ore_components *comps, + struct ore_comp *one_comp, + struct exofs_sb_info *sbi, osd_id oid) +{ + unsigned dev_mod = (unsigned)oid, first_dev; + + one_comp->obj.partition = sbi->one_comp.obj.partition; + one_comp->obj.id = oid; + exofs_make_credential(one_comp->cred, &one_comp->obj); + + comps->numdevs = sbi->comps.numdevs; + comps->single_comp = EC_SINGLE_COMP; + comps->comps = one_comp; + + /* Round robin device view of the table */ + first_dev = (dev_mod * sbi->layout.mirrors_p1) % sbi->comps.numdevs; + comps->ods = sbi->comps.ods + first_dev; +} + #endif diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 8472c09..f39a38f 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -43,7 +43,7 @@ enum { BIO_MAX_PAGES_KMALLOC = PAGE_SIZE / sizeof(struct page *), }; -unsigned exofs_max_io_pages(struct exofs_layout *layout, +unsigned exofs_max_io_pages(struct ore_layout *layout, unsigned expected_pages) { unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC); @@ -58,7 +58,7 @@ struct page_collect { struct exofs_sb_info *sbi; struct inode *inode; unsigned expected_pages; - struct exofs_io_state *ios; + struct ore_io_state *ios; struct page **pages; unsigned alloc_pages; @@ -110,13 +110,6 @@ static int pcol_try_alloc(struct page_collect *pcol) { unsigned pages; - if (!pcol->ios) { /* First time allocate io_state */ - int ret = exofs_get_io_state(&pcol->sbi->layout, &pcol->ios); - - if (ret) - return ret; - } - /* TODO: easily support bio chaining */ pages = exofs_max_io_pages(&pcol->sbi->layout, pcol->expected_pages); @@ -140,7 +133,7 @@ static void pcol_free(struct page_collect *pcol) pcol->pages = NULL; if (pcol->ios) { - exofs_put_io_state(pcol->ios); + ore_put_io_state(pcol->ios); pcol->ios = NULL; } } @@ -200,7 +193,7 @@ static int __readpages_done(struct page_collect *pcol) u64 resid; u64 good_bytes; u64 length = 0; - int ret = exofs_check_io(pcol->ios, &resid); + int ret = ore_check_io(pcol->ios, &resid); if (likely(!ret)) good_bytes = pcol->length; @@ -241,7 +234,7 @@ static int __readpages_done(struct page_collect *pcol) } /* callback of async reads */ -static void readpages_done(struct exofs_io_state *ios, void *p) +static void readpages_done(struct ore_io_state *ios, void *p) { struct page_collect *pcol = p; @@ -269,20 +262,28 @@ static void _unlock_pcol_pages(struct page_collect *pcol, int ret, int rw) static int read_exec(struct page_collect *pcol) { struct exofs_i_info *oi = exofs_i(pcol->inode); - struct exofs_io_state *ios = pcol->ios; + struct ore_io_state *ios; struct page_collect *pcol_copy = NULL; int ret; if (!pcol->pages) return 0; + if (!pcol->ios) { + int ret = ore_get_rw_state(&pcol->sbi->layout, &oi->comps, true, + pcol->pg_first << PAGE_CACHE_SHIFT, + pcol->length, &pcol->ios); + + if (ret) + return ret; + } + + ios = pcol->ios; ios->pages = pcol->pages; ios->nr_pages = pcol->nr_pages; - ios->length = pcol->length; - ios->offset = pcol->pg_first << PAGE_CACHE_SHIFT; if (pcol->read_4_write) { - exofs_oi_read(oi, pcol->ios); + ore_read(pcol->ios); return __readpages_done(pcol); } @@ -295,14 +296,14 @@ static int read_exec(struct page_collect *pcol) *pcol_copy = *pcol; ios->done = readpages_done; ios->private = pcol_copy; - ret = exofs_oi_read(oi, ios); + ret = ore_read(ios); if (unlikely(ret)) goto err; atomic_inc(&pcol->sbi->s_curr_pending); EXOFS_DBGMSG2("read_exec obj=0x%llx start=0x%llx length=0x%lx\n", - ios->obj.id, _LLU(ios->offset), pcol->length); + oi->one_comp.obj.id, _LLU(ios->offset), pcol->length); /* pages ownership was passed to pcol_copy */ _pcol_reset(pcol); @@ -457,14 +458,14 @@ static int exofs_readpage(struct file *file, struct page *page) } /* Callback for osd_write. All writes are asynchronous */ -static void writepages_done(struct exofs_io_state *ios, void *p) +static void writepages_done(struct ore_io_state *ios, void *p) { struct page_collect *pcol = p; int i; u64 resid; u64 good_bytes; u64 length = 0; - int ret = exofs_check_io(ios, &resid); + int ret = ore_check_io(ios, &resid); atomic_dec(&pcol->sbi->s_curr_pending); @@ -507,13 +508,21 @@ static void writepages_done(struct exofs_io_state *ios, void *p) static int write_exec(struct page_collect *pcol) { struct exofs_i_info *oi = exofs_i(pcol->inode); - struct exofs_io_state *ios = pcol->ios; + struct ore_io_state *ios; struct page_collect *pcol_copy = NULL; int ret; if (!pcol->pages) return 0; + BUG_ON(pcol->ios); + ret = ore_get_rw_state(&pcol->sbi->layout, &oi->comps, false, + pcol->pg_first << PAGE_CACHE_SHIFT, + pcol->length, &pcol->ios); + + if (unlikely(ret)) + goto err; + pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL); if (!pcol_copy) { EXOFS_ERR("write_exec: Failed to kmalloc(pcol)\n"); @@ -523,16 +532,15 @@ static int write_exec(struct page_collect *pcol) *pcol_copy = *pcol; + ios = pcol->ios; ios->pages = pcol_copy->pages; ios->nr_pages = pcol_copy->nr_pages; - ios->offset = pcol_copy->pg_first << PAGE_CACHE_SHIFT; - ios->length = pcol_copy->length; ios->done = writepages_done; ios->private = pcol_copy; - ret = exofs_oi_write(oi, ios); + ret = ore_write(ios); if (unlikely(ret)) { - EXOFS_ERR("write_exec: exofs_oi_write() Failed\n"); + EXOFS_ERR("write_exec: ore_write() Failed\n"); goto err; } @@ -844,17 +852,15 @@ static inline int exofs_inode_is_fast_symlink(struct inode *inode) return S_ISLNK(inode->i_mode) && (oi->i_data[0] != 0); } -const struct osd_attr g_attr_logical_length = ATTR_DEF( - OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8); - static int _do_truncate(struct inode *inode, loff_t newsize) { struct exofs_i_info *oi = exofs_i(inode); + struct exofs_sb_info *sbi = inode->i_sb->s_fs_info; int ret; inode->i_mtime = inode->i_ctime = CURRENT_TIME; - ret = exofs_oi_truncate(oi, (u64)newsize); + ret = ore_truncate(&sbi->layout, &oi->comps, (u64)newsize); if (likely(!ret)) truncate_setsize(inode, newsize); @@ -917,30 +923,26 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi, [1] = g_attr_inode_file_layout, [2] = g_attr_inode_dir_layout, }; - struct exofs_io_state *ios; + struct ore_io_state *ios; struct exofs_on_disk_inode_layout *layout; int ret; - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &oi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__); + EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__); return ret; } - ios->obj.id = exofs_oi_objno(oi); - exofs_make_credential(oi->i_cred, &ios->obj); - ios->cred = oi->i_cred; - - attrs[1].len = exofs_on_disk_inode_layout_size(sbi->layout.s_numdevs); - attrs[2].len = exofs_on_disk_inode_layout_size(sbi->layout.s_numdevs); + attrs[1].len = exofs_on_disk_inode_layout_size(sbi->comps.numdevs); + attrs[2].len = exofs_on_disk_inode_layout_size(sbi->comps.numdevs); ios->in_attr = attrs; ios->in_attr_len = ARRAY_SIZE(attrs); - ret = exofs_sbi_read(ios); + ret = ore_read(ios); if (unlikely(ret)) { EXOFS_ERR("object(0x%llx) corrupted, return empty file=>%d\n", - _LLU(ios->obj.id), ret); + _LLU(oi->one_comp.obj.id), ret); memset(inode, 0, sizeof(*inode)); inode->i_mode = 0040000 | (0777 & ~022); /* If object is lost on target we might as well enable it's @@ -990,7 +992,7 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi, } out: - exofs_put_io_state(ios); + ore_put_io_state(ios); return ret; } @@ -1016,6 +1018,8 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) return inode; oi = exofs_i(inode); __oi_init(oi); + exofs_init_comps(&oi->comps, &oi->one_comp, sb->s_fs_info, + exofs_oi_objno(oi)); /* read the inode from the osd */ ret = exofs_get_inode(sb, oi, &fcb); @@ -1107,21 +1111,22 @@ int __exofs_wait_obj_created(struct exofs_i_info *oi) * set the obj_created flag so that other methods know that the object exists on * the OSD. */ -static void create_done(struct exofs_io_state *ios, void *p) +static void create_done(struct ore_io_state *ios, void *p) { struct inode *inode = p; struct exofs_i_info *oi = exofs_i(inode); struct exofs_sb_info *sbi = inode->i_sb->s_fs_info; int ret; - ret = exofs_check_io(ios, NULL); - exofs_put_io_state(ios); + ret = ore_check_io(ios, NULL); + ore_put_io_state(ios); atomic_dec(&sbi->s_curr_pending); if (unlikely(ret)) { EXOFS_ERR("object=0x%llx creation failed in pid=0x%llx", - _LLU(exofs_oi_objno(oi)), _LLU(sbi->layout.s_pid)); + _LLU(exofs_oi_objno(oi)), + _LLU(oi->one_comp.obj.partition)); /*TODO: When FS is corrupted creation can fail, object already * exist. Get rid of this asynchronous creation, if exist * increment the obj counter and try the next object. Until we @@ -1140,14 +1145,13 @@ static void create_done(struct exofs_io_state *ios, void *p) */ struct inode *exofs_new_inode(struct inode *dir, int mode) { - struct super_block *sb; + struct super_block *sb = dir->i_sb; + struct exofs_sb_info *sbi = sb->s_fs_info; struct inode *inode; struct exofs_i_info *oi; - struct exofs_sb_info *sbi; - struct exofs_io_state *ios; + struct ore_io_state *ios; int ret; - sb = dir->i_sb; inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); @@ -1157,8 +1161,6 @@ struct inode *exofs_new_inode(struct inode *dir, int mode) set_obj_2bcreated(oi); - sbi = sb->s_fs_info; - inode->i_mapping->backing_dev_info = sb->s_bdi; inode_init_owner(inode, dir, mode); inode->i_ino = sbi->s_nextid++; @@ -1170,25 +1172,24 @@ struct inode *exofs_new_inode(struct inode *dir, int mode) spin_unlock(&sbi->s_next_gen_lock); insert_inode_hash(inode); + exofs_init_comps(&oi->comps, &oi->one_comp, sb->s_fs_info, + exofs_oi_objno(oi)); exofs_sbi_write_stats(sbi); /* Make sure new sbi->s_nextid is on disk */ mark_inode_dirty(inode); - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &oi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("exofs_new_inode: exofs_get_io_state failed\n"); + EXOFS_ERR("exofs_new_inode: ore_get_io_state failed\n"); return ERR_PTR(ret); } - ios->obj.id = exofs_oi_objno(oi); - exofs_make_credential(oi->i_cred, &ios->obj); - ios->done = create_done; ios->private = inode; - ios->cred = oi->i_cred; - ret = exofs_sbi_create(ios); + + ret = ore_create(ios); if (ret) { - exofs_put_io_state(ios); + ore_put_io_state(ios); return ERR_PTR(ret); } atomic_inc(&sbi->s_curr_pending); @@ -1207,11 +1208,11 @@ struct updatei_args { /* * Callback function from exofs_update_inode(). */ -static void updatei_done(struct exofs_io_state *ios, void *p) +static void updatei_done(struct ore_io_state *ios, void *p) { struct updatei_args *args = p; - exofs_put_io_state(ios); + ore_put_io_state(ios); atomic_dec(&args->sbi->s_curr_pending); @@ -1227,7 +1228,7 @@ static int exofs_update_inode(struct inode *inode, int do_sync) struct exofs_i_info *oi = exofs_i(inode); struct super_block *sb = inode->i_sb; struct exofs_sb_info *sbi = sb->s_fs_info; - struct exofs_io_state *ios; + struct ore_io_state *ios; struct osd_attr attr; struct exofs_fcb *fcb; struct updatei_args *args; @@ -1266,9 +1267,9 @@ static int exofs_update_inode(struct inode *inode, int do_sync) } else memcpy(fcb->i_data, oi->i_data, sizeof(fcb->i_data)); - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &oi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__); + EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__); goto free_args; } @@ -1285,13 +1286,13 @@ static int exofs_update_inode(struct inode *inode, int do_sync) ios->private = args; } - ret = exofs_oi_write(oi, ios); + ret = ore_write(ios); if (!do_sync && !ret) { atomic_inc(&sbi->s_curr_pending); goto out; /* deallocation in updatei_done */ } - exofs_put_io_state(ios); + ore_put_io_state(ios); free_args: kfree(args); out: @@ -1310,11 +1311,11 @@ int exofs_write_inode(struct inode *inode, struct writeback_control *wbc) * Callback function from exofs_delete_inode() - don't have much cleaning up to * do. */ -static void delete_done(struct exofs_io_state *ios, void *p) +static void delete_done(struct ore_io_state *ios, void *p) { struct exofs_sb_info *sbi = p; - exofs_put_io_state(ios); + ore_put_io_state(ios); atomic_dec(&sbi->s_curr_pending); } @@ -1329,7 +1330,7 @@ void exofs_evict_inode(struct inode *inode) struct exofs_i_info *oi = exofs_i(inode); struct super_block *sb = inode->i_sb; struct exofs_sb_info *sbi = sb->s_fs_info; - struct exofs_io_state *ios; + struct ore_io_state *ios; int ret; truncate_inode_pages(&inode->i_data, 0); @@ -1349,20 +1350,19 @@ void exofs_evict_inode(struct inode *inode) /* ignore the error, attempt a remove anyway */ /* Now Remove the OSD objects */ - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &oi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_get_io_state failed\n", __func__); + EXOFS_ERR("%s: ore_get_io_state failed\n", __func__); return; } - ios->obj.id = exofs_oi_objno(oi); ios->done = delete_done; ios->private = sbi; - ios->cred = oi->i_cred; - ret = exofs_sbi_remove(ios); + + ret = ore_remove(ios); if (ret) { - EXOFS_ERR("%s: exofs_sbi_remove failed\n", __func__); - exofs_put_io_state(ios); + EXOFS_ERR("%s: ore_remove failed\n", __func__); + ore_put_io_state(ios); return; } atomic_inc(&sbi->s_curr_pending); diff --git a/fs/exofs/ios.c b/fs/exofs/ore.c index f74a2ec..25305af 100644 --- a/fs/exofs/ios.c +++ b/fs/exofs/ore.c @@ -23,81 +23,87 @@ */ #include <linux/slab.h> -#include <scsi/scsi_device.h> #include <asm/div64.h> -#include "exofs.h" +#include <scsi/osd_ore.h> -#define EXOFS_DBGMSG2(M...) do {} while (0) -/* #define EXOFS_DBGMSG2 EXOFS_DBGMSG */ +#define ORE_ERR(fmt, a...) printk(KERN_ERR "ore: " fmt, ##a) -void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj) -{ - osd_sec_init_nosec_doall_caps(cred_a, obj, false, true); -} +#ifdef CONFIG_EXOFS_DEBUG +#define ORE_DBGMSG(fmt, a...) \ + printk(KERN_NOTICE "ore @%s:%d: " fmt, __func__, __LINE__, ##a) +#else +#define ORE_DBGMSG(fmt, a...) \ + do { if (0) printk(fmt, ##a); } while (0) +#endif -int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj, - u64 offset, void *p, unsigned length) -{ - struct osd_request *or = osd_start_request(od, GFP_KERNEL); -/* struct osd_sense_info osi = {.key = 0};*/ - int ret; +/* u64 has problems with printk this will cast it to unsigned long long */ +#define _LLU(x) (unsigned long long)(x) - if (unlikely(!or)) { - EXOFS_DBGMSG("%s: osd_start_request failed.\n", __func__); - return -ENOMEM; - } - ret = osd_req_read_kern(or, obj, offset, p, length); - if (unlikely(ret)) { - EXOFS_DBGMSG("%s: osd_req_read_kern failed.\n", __func__); - goto out; - } +#define ORE_DBGMSG2(M...) do {} while (0) +/* #define ORE_DBGMSG2 ORE_DBGMSG */ - ret = osd_finalize_request(or, 0, cred, NULL); - if (unlikely(ret)) { - EXOFS_DBGMSG("Failed to osd_finalize_request() => %d\n", ret); - goto out; - } +MODULE_AUTHOR("Boaz Harrosh <bharrosh@panasas.com>"); +MODULE_DESCRIPTION("Objects Raid Engine ore.ko"); +MODULE_LICENSE("GPL"); - ret = osd_execute_request(or); - if (unlikely(ret)) - EXOFS_DBGMSG("osd_execute_request() => %d\n", ret); - /* osd_req_decode_sense(or, ret); */ +static u8 *_ios_cred(struct ore_io_state *ios, unsigned index) +{ + return ios->comps->comps[index & ios->comps->single_comp].cred; +} -out: - osd_end_request(or); - return ret; +static struct osd_obj_id *_ios_obj(struct ore_io_state *ios, unsigned index) +{ + return &ios->comps->comps[index & ios->comps->single_comp].obj; } -int exofs_get_io_state(struct exofs_layout *layout, - struct exofs_io_state **pios) +static struct osd_dev *_ios_od(struct ore_io_state *ios, unsigned index) { - struct exofs_io_state *ios; + return ios->comps->ods[index]; +} + +int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps, + bool is_reading, u64 offset, u64 length, + struct ore_io_state **pios) +{ + struct ore_io_state *ios; /*TODO: Maybe use kmem_cach per sbi of size * exofs_io_state_size(layout->s_numdevs) */ - ios = kzalloc(exofs_io_state_size(layout->s_numdevs), GFP_KERNEL); + ios = kzalloc(ore_io_state_size(comps->numdevs), GFP_KERNEL); if (unlikely(!ios)) { - EXOFS_DBGMSG("Failed kzalloc bytes=%d\n", - exofs_io_state_size(layout->s_numdevs)); + ORE_DBGMSG("Failed kzalloc bytes=%d\n", + ore_io_state_size(comps->numdevs)); *pios = NULL; return -ENOMEM; } ios->layout = layout; - ios->obj.partition = layout->s_pid; + ios->comps = comps; + ios->offset = offset; + ios->length = length; + ios->reading = is_reading; + *pios = ios; return 0; } +EXPORT_SYMBOL(ore_get_rw_state); + +int ore_get_io_state(struct ore_layout *layout, struct ore_components *comps, + struct ore_io_state **ios) +{ + return ore_get_rw_state(layout, comps, true, 0, 0, ios); +} +EXPORT_SYMBOL(ore_get_io_state); -void exofs_put_io_state(struct exofs_io_state *ios) +void ore_put_io_state(struct ore_io_state *ios) { if (ios) { unsigned i; for (i = 0; i < ios->numdevs; i++) { - struct exofs_per_dev_state *per_dev = &ios->per_dev[i]; + struct ore_per_dev_state *per_dev = &ios->per_dev[i]; if (per_dev->or) osd_end_request(per_dev->or); @@ -108,31 +114,9 @@ void exofs_put_io_state(struct exofs_io_state *ios) kfree(ios); } } +EXPORT_SYMBOL(ore_put_io_state); -unsigned exofs_layout_od_id(struct exofs_layout *layout, - osd_id obj_no, unsigned layout_index) -{ -/* switch (layout->lay_func) { - case LAYOUT_MOVING_WINDOW: - {*/ - unsigned dev_mod = obj_no; - - return (layout_index + dev_mod * layout->mirrors_p1) % - layout->s_numdevs; -/* } - case LAYOUT_FUNC_IMPLICT: - return layout->devs[layout_index]; - }*/ -} - -static inline struct osd_dev *exofs_ios_od(struct exofs_io_state *ios, - unsigned layout_index) -{ - return ios->layout->s_ods[ - exofs_layout_od_id(ios->layout, ios->obj.id, layout_index)]; -} - -static void _sync_done(struct exofs_io_state *ios, void *p) +static void _sync_done(struct ore_io_state *ios, void *p) { struct completion *waiting = p; @@ -141,20 +125,20 @@ static void _sync_done(struct exofs_io_state *ios, void *p) static void _last_io(struct kref *kref) { - struct exofs_io_state *ios = container_of( - kref, struct exofs_io_state, kref); + struct ore_io_state *ios = container_of( + kref, struct ore_io_state, kref); ios->done(ios, ios->private); } static void _done_io(struct osd_request *or, void *p) { - struct exofs_io_state *ios = p; + struct ore_io_state *ios = p; kref_put(&ios->kref, _last_io); } -static int exofs_io_execute(struct exofs_io_state *ios) +static int ore_io_execute(struct ore_io_state *ios) { DECLARE_COMPLETION_ONSTACK(wait); bool sync = (ios->done == NULL); @@ -170,9 +154,9 @@ static int exofs_io_execute(struct exofs_io_state *ios) if (unlikely(!or)) continue; - ret = osd_finalize_request(or, 0, ios->cred, NULL); + ret = osd_finalize_request(or, 0, _ios_cred(ios, i), NULL); if (unlikely(ret)) { - EXOFS_DBGMSG("Failed to osd_finalize_request() => %d\n", + ORE_DBGMSG("Failed to osd_finalize_request() => %d\n", ret); return ret; } @@ -194,7 +178,7 @@ static int exofs_io_execute(struct exofs_io_state *ios) if (sync) { wait_for_completion(&wait); - ret = exofs_check_io(ios, NULL); + ret = ore_check_io(ios, NULL); } return ret; } @@ -214,7 +198,7 @@ static void _clear_bio(struct bio *bio) } } -int exofs_check_io(struct exofs_io_state *ios, u64 *resid) +int ore_check_io(struct ore_io_state *ios, u64 *resid) { enum osd_err_priority acumulated_osd_err = 0; int acumulated_lin_err = 0; @@ -235,7 +219,7 @@ int exofs_check_io(struct exofs_io_state *ios, u64 *resid) if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) { /* start read offset passed endof file */ _clear_bio(ios->per_dev[i].bio); - EXOFS_DBGMSG("start read offset passed end of file " + ORE_DBGMSG("start read offset passed end of file " "offset=0x%llx, length=0x%llx\n", _LLU(ios->per_dev[i].offset), _LLU(ios->per_dev[i].length)); @@ -259,6 +243,7 @@ int exofs_check_io(struct exofs_io_state *ios, u64 *resid) return acumulated_lin_err; } +EXPORT_SYMBOL(ore_check_io); /* * L - logical offset into the file @@ -305,20 +290,21 @@ int exofs_check_io(struct exofs_io_state *ios, u64 *resid) struct _striping_info { u64 obj_offset; u64 group_length; + u64 M; /* for truncate */ unsigned dev; unsigned unit_off; }; -static void _calc_stripe_info(struct exofs_io_state *ios, u64 file_offset, +static void _calc_stripe_info(struct ore_layout *layout, u64 file_offset, struct _striping_info *si) { - u32 stripe_unit = ios->layout->stripe_unit; - u32 group_width = ios->layout->group_width; - u64 group_depth = ios->layout->group_depth; + u32 stripe_unit = layout->stripe_unit; + u32 group_width = layout->group_width; + u64 group_depth = layout->group_depth; u32 U = stripe_unit * group_width; u64 T = U * group_depth; - u64 S = T * ios->layout->group_count; + u64 S = T * layout->group_count; u64 M = div64_u64(file_offset, S); /* @@ -333,7 +319,7 @@ static void _calc_stripe_info(struct exofs_io_state *ios, u64 file_offset, /* "H - (N * U)" is just "H % U" so it's bound to u32 */ si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width; - si->dev *= ios->layout->mirrors_p1; + si->dev *= layout->mirrors_p1; div_u64_rem(file_offset, stripe_unit, &si->unit_off); @@ -341,15 +327,16 @@ static void _calc_stripe_info(struct exofs_io_state *ios, u64 file_offset, (M * group_depth * stripe_unit); si->group_length = T - H; + si->M = M; } -static int _add_stripe_unit(struct exofs_io_state *ios, unsigned *cur_pg, - unsigned pgbase, struct exofs_per_dev_state *per_dev, +static int _add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg, + unsigned pgbase, struct ore_per_dev_state *per_dev, int cur_len) { unsigned pg = *cur_pg; struct request_queue *q = - osd_request_queue(exofs_ios_od(ios, per_dev->dev)); + osd_request_queue(_ios_od(ios, per_dev->dev)); per_dev->length += cur_len; @@ -361,7 +348,7 @@ static int _add_stripe_unit(struct exofs_io_state *ios, unsigned *cur_pg, per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size); if (unlikely(!per_dev->bio)) { - EXOFS_DBGMSG("Failed to allocate BIO size=%u\n", + ORE_DBGMSG("Failed to allocate BIO size=%u\n", bio_size); return -ENOMEM; } @@ -387,7 +374,7 @@ static int _add_stripe_unit(struct exofs_io_state *ios, unsigned *cur_pg, return 0; } -static int _prepare_one_group(struct exofs_io_state *ios, u64 length, +static int _prepare_one_group(struct ore_io_state *ios, u64 length, struct _striping_info *si) { unsigned stripe_unit = ios->layout->stripe_unit; @@ -400,7 +387,7 @@ static int _prepare_one_group(struct exofs_io_state *ios, u64 length, int ret = 0; while (length) { - struct exofs_per_dev_state *per_dev = &ios->per_dev[dev]; + struct ore_per_dev_state *per_dev = &ios->per_dev[dev]; unsigned cur_len, page_off = 0; if (!per_dev->length) { @@ -443,7 +430,7 @@ out: return ret; } -static int _prepare_for_striping(struct exofs_io_state *ios) +static int _prepare_for_striping(struct ore_io_state *ios) { u64 length = ios->length; u64 offset = ios->offset; @@ -452,9 +439,9 @@ static int _prepare_for_striping(struct exofs_io_state *ios) if (!ios->pages) { if (ios->kern_buff) { - struct exofs_per_dev_state *per_dev = &ios->per_dev[0]; + struct ore_per_dev_state *per_dev = &ios->per_dev[0]; - _calc_stripe_info(ios, ios->offset, &si); + _calc_stripe_info(ios->layout, ios->offset, &si); per_dev->offset = si.obj_offset; per_dev->dev = si.dev; @@ -468,7 +455,7 @@ static int _prepare_for_striping(struct exofs_io_state *ios) } while (length) { - _calc_stripe_info(ios, offset, &si); + _calc_stripe_info(ios->layout, offset, &si); if (length < si.group_length) si.group_length = length; @@ -485,57 +472,59 @@ out: return ret; } -int exofs_sbi_create(struct exofs_io_state *ios) +int ore_create(struct ore_io_state *ios) { int i, ret; - for (i = 0; i < ios->layout->s_numdevs; i++) { + for (i = 0; i < ios->comps->numdevs; i++) { struct osd_request *or; - or = osd_start_request(exofs_ios_od(ios, i), GFP_KERNEL); + or = osd_start_request(_ios_od(ios, i), GFP_KERNEL); if (unlikely(!or)) { - EXOFS_ERR("%s: osd_start_request failed\n", __func__); + ORE_ERR("%s: osd_start_request failed\n", __func__); ret = -ENOMEM; goto out; } ios->per_dev[i].or = or; ios->numdevs++; - osd_req_create_object(or, &ios->obj); + osd_req_create_object(or, _ios_obj(ios, i)); } - ret = exofs_io_execute(ios); + ret = ore_io_execute(ios); out: return ret; } +EXPORT_SYMBOL(ore_create); -int exofs_sbi_remove(struct exofs_io_state *ios) +int ore_remove(struct ore_io_state *ios) { int i, ret; - for (i = 0; i < ios->layout->s_numdevs; i++) { + for (i = 0; i < ios->comps->numdevs; i++) { struct osd_request *or; - or = osd_start_request(exofs_ios_od(ios, i), GFP_KERNEL); + or = osd_start_request(_ios_od(ios, i), GFP_KERNEL); if (unlikely(!or)) { - EXOFS_ERR("%s: osd_start_request failed\n", __func__); + ORE_ERR("%s: osd_start_request failed\n", __func__); ret = -ENOMEM; goto out; } ios->per_dev[i].or = or; ios->numdevs++; - osd_req_remove_object(or, &ios->obj); + osd_req_remove_object(or, _ios_obj(ios, i)); } - ret = exofs_io_execute(ios); + ret = ore_io_execute(ios); out: return ret; } +EXPORT_SYMBOL(ore_remove); -static int _sbi_write_mirror(struct exofs_io_state *ios, int cur_comp) +static int _write_mirror(struct ore_io_state *ios, int cur_comp) { - struct exofs_per_dev_state *master_dev = &ios->per_dev[cur_comp]; + struct ore_per_dev_state *master_dev = &ios->per_dev[cur_comp]; unsigned dev = ios->per_dev[cur_comp].dev; unsigned last_comp = cur_comp + ios->layout->mirrors_p1; int ret = 0; @@ -544,12 +533,12 @@ static int _sbi_write_mirror(struct exofs_io_state *ios, int cur_comp) return 0; /* Just an empty slot */ for (; cur_comp < last_comp; ++cur_comp, ++dev) { - struct exofs_per_dev_state *per_dev = &ios->per_dev[cur_comp]; + struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp]; struct osd_request *or; - or = osd_start_request(exofs_ios_od(ios, dev), GFP_KERNEL); + or = osd_start_request(_ios_od(ios, dev), GFP_KERNEL); if (unlikely(!or)) { - EXOFS_ERR("%s: osd_start_request failed\n", __func__); + ORE_ERR("%s: osd_start_request failed\n", __func__); ret = -ENOMEM; goto out; } @@ -563,7 +552,7 @@ static int _sbi_write_mirror(struct exofs_io_state *ios, int cur_comp) bio = bio_kmalloc(GFP_KERNEL, master_dev->bio->bi_max_vecs); if (unlikely(!bio)) { - EXOFS_DBGMSG( + ORE_DBGMSG( "Failed to allocate BIO size=%u\n", master_dev->bio->bi_max_vecs); ret = -ENOMEM; @@ -582,25 +571,29 @@ static int _sbi_write_mirror(struct exofs_io_state *ios, int cur_comp) bio->bi_rw |= REQ_WRITE; } - osd_req_write(or, &ios->obj, per_dev->offset, bio, - per_dev->length); - EXOFS_DBGMSG("write(0x%llx) offset=0x%llx " + osd_req_write(or, _ios_obj(ios, dev), per_dev->offset, + bio, per_dev->length); + ORE_DBGMSG("write(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(ios->obj.id), _LLU(per_dev->offset), + _LLU(_ios_obj(ios, dev)->id), + _LLU(per_dev->offset), _LLU(per_dev->length), dev); } else if (ios->kern_buff) { - ret = osd_req_write_kern(or, &ios->obj, per_dev->offset, - ios->kern_buff, ios->length); + ret = osd_req_write_kern(or, _ios_obj(ios, dev), + per_dev->offset, + ios->kern_buff, ios->length); if (unlikely(ret)) goto out; - EXOFS_DBGMSG2("write_kern(0x%llx) offset=0x%llx " + ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(ios->obj.id), _LLU(per_dev->offset), + _LLU(_ios_obj(ios, dev)->id), + _LLU(per_dev->offset), _LLU(ios->length), dev); } else { - osd_req_set_attributes(or, &ios->obj); - EXOFS_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n", - _LLU(ios->obj.id), ios->out_attr_len, dev); + osd_req_set_attributes(or, _ios_obj(ios, dev)); + ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n", + _LLU(_ios_obj(ios, dev)->id), + ios->out_attr_len, dev); } if (ios->out_attr) @@ -616,7 +609,7 @@ out: return ret; } -int exofs_sbi_write(struct exofs_io_state *ios) +int ore_write(struct ore_io_state *ios) { int i; int ret; @@ -626,52 +619,55 @@ int exofs_sbi_write(struct exofs_io_state *ios) return ret; for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) { - ret = _sbi_write_mirror(ios, i); + ret = _write_mirror(ios, i); if (unlikely(ret)) return ret; } - ret = exofs_io_execute(ios); + ret = ore_io_execute(ios); return ret; } +EXPORT_SYMBOL(ore_write); -static int _sbi_read_mirror(struct exofs_io_state *ios, unsigned cur_comp) +static int _read_mirror(struct ore_io_state *ios, unsigned cur_comp) { struct osd_request *or; - struct exofs_per_dev_state *per_dev = &ios->per_dev[cur_comp]; - unsigned first_dev = (unsigned)ios->obj.id; + struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp]; + struct osd_obj_id *obj = _ios_obj(ios, cur_comp); + unsigned first_dev = (unsigned)obj->id; if (ios->pages && !per_dev->length) return 0; /* Just an empty slot */ first_dev = per_dev->dev + first_dev % ios->layout->mirrors_p1; - or = osd_start_request(exofs_ios_od(ios, first_dev), GFP_KERNEL); + or = osd_start_request(_ios_od(ios, first_dev), GFP_KERNEL); if (unlikely(!or)) { - EXOFS_ERR("%s: osd_start_request failed\n", __func__); + ORE_ERR("%s: osd_start_request failed\n", __func__); return -ENOMEM; } per_dev->or = or; if (ios->pages) { - osd_req_read(or, &ios->obj, per_dev->offset, + osd_req_read(or, obj, per_dev->offset, per_dev->bio, per_dev->length); - EXOFS_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx" - " dev=%d\n", _LLU(ios->obj.id), + ORE_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx" + " dev=%d\n", _LLU(obj->id), _LLU(per_dev->offset), _LLU(per_dev->length), first_dev); } else if (ios->kern_buff) { - int ret = osd_req_read_kern(or, &ios->obj, per_dev->offset, + int ret = osd_req_read_kern(or, obj, per_dev->offset, ios->kern_buff, ios->length); - EXOFS_DBGMSG2("read_kern(0x%llx) offset=0x%llx " + ORE_DBGMSG2("read_kern(0x%llx) offset=0x%llx " "length=0x%llx dev=%d ret=>%d\n", - _LLU(ios->obj.id), _LLU(per_dev->offset), + _LLU(obj->id), _LLU(per_dev->offset), _LLU(ios->length), first_dev, ret); if (unlikely(ret)) return ret; } else { - osd_req_get_attributes(or, &ios->obj); - EXOFS_DBGMSG2("obj(0x%llx) get_attributes=%d dev=%d\n", - _LLU(ios->obj.id), ios->in_attr_len, first_dev); + osd_req_get_attributes(or, obj); + ORE_DBGMSG2("obj(0x%llx) get_attributes=%d dev=%d\n", + _LLU(obj->id), + ios->in_attr_len, first_dev); } if (ios->out_attr) osd_req_add_set_attr_list(or, ios->out_attr, ios->out_attr_len); @@ -682,7 +678,7 @@ static int _sbi_read_mirror(struct exofs_io_state *ios, unsigned cur_comp) return 0; } -int exofs_sbi_read(struct exofs_io_state *ios) +int ore_read(struct ore_io_state *ios) { int i; int ret; @@ -692,16 +688,17 @@ int exofs_sbi_read(struct exofs_io_state *ios) return ret; for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) { - ret = _sbi_read_mirror(ios, i); + ret = _read_mirror(ios, i); if (unlikely(ret)) return ret; } - ret = exofs_io_execute(ios); + ret = ore_io_execute(ios); return ret; } +EXPORT_SYMBOL(ore_read); -int extract_attr_from_ios(struct exofs_io_state *ios, struct osd_attr *attr) +int extract_attr_from_ios(struct ore_io_state *ios, struct osd_attr *attr) { struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */ void *iter = NULL; @@ -721,83 +718,118 @@ int extract_attr_from_ios(struct exofs_io_state *ios, struct osd_attr *attr) return -EIO; } +EXPORT_SYMBOL(extract_attr_from_ios); -static int _truncate_mirrors(struct exofs_io_state *ios, unsigned cur_comp, +static int _truncate_mirrors(struct ore_io_state *ios, unsigned cur_comp, struct osd_attr *attr) { int last_comp = cur_comp + ios->layout->mirrors_p1; for (; cur_comp < last_comp; ++cur_comp) { - struct exofs_per_dev_state *per_dev = &ios->per_dev[cur_comp]; + struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp]; struct osd_request *or; - or = osd_start_request(exofs_ios_od(ios, cur_comp), GFP_KERNEL); + or = osd_start_request(_ios_od(ios, cur_comp), GFP_KERNEL); if (unlikely(!or)) { - EXOFS_ERR("%s: osd_start_request failed\n", __func__); + ORE_ERR("%s: osd_start_request failed\n", __func__); return -ENOMEM; } per_dev->or = or; - osd_req_set_attributes(or, &ios->obj); + osd_req_set_attributes(or, _ios_obj(ios, cur_comp)); osd_req_add_set_attr_list(or, attr, 1); } return 0; } -int exofs_oi_truncate(struct exofs_i_info *oi, u64 size) +struct _trunc_info { + struct _striping_info si; + u64 prev_group_obj_off; + u64 next_group_obj_off; + + unsigned first_group_dev; + unsigned nex_group_dev; + unsigned max_devs; +}; + +void _calc_trunk_info(struct ore_layout *layout, u64 file_offset, + struct _trunc_info *ti) +{ + unsigned stripe_unit = layout->stripe_unit; + + _calc_stripe_info(layout, file_offset, &ti->si); + + ti->prev_group_obj_off = ti->si.M * stripe_unit; + ti->next_group_obj_off = ti->si.M ? (ti->si.M - 1) * stripe_unit : 0; + + ti->first_group_dev = ti->si.dev - (ti->si.dev % layout->group_width); + ti->nex_group_dev = ti->first_group_dev + layout->group_width; + ti->max_devs = layout->group_width * layout->group_count; +} + +int ore_truncate(struct ore_layout *layout, struct ore_components *comps, + u64 size) { - struct exofs_sb_info *sbi = oi->vfs_inode.i_sb->s_fs_info; - struct exofs_io_state *ios; + struct ore_io_state *ios; struct exofs_trunc_attr { struct osd_attr attr; __be64 newsize; } *size_attrs; - struct _striping_info si; + struct _trunc_info ti; int i, ret; - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(layout, comps, &ios); if (unlikely(ret)) return ret; - size_attrs = kcalloc(ios->layout->group_width, sizeof(*size_attrs), + _calc_trunk_info(ios->layout, size, &ti); + + size_attrs = kcalloc(ti.max_devs, sizeof(*size_attrs), GFP_KERNEL); if (unlikely(!size_attrs)) { ret = -ENOMEM; goto out; } - ios->obj.id = exofs_oi_objno(oi); - ios->cred = oi->i_cred; + ios->numdevs = ios->comps->numdevs; - ios->numdevs = ios->layout->s_numdevs; - _calc_stripe_info(ios, size, &si); - - for (i = 0; i < ios->layout->group_width; ++i) { + for (i = 0; i < ti.max_devs; ++i) { struct exofs_trunc_attr *size_attr = &size_attrs[i]; u64 obj_size; - if (i < si.dev) - obj_size = si.obj_offset + - ios->layout->stripe_unit - si.unit_off; - else if (i == si.dev) - obj_size = si.obj_offset; - else /* i > si.dev */ - obj_size = si.obj_offset - si.unit_off; + if (i < ti.first_group_dev) + obj_size = ti.prev_group_obj_off; + else if (i >= ti.nex_group_dev) + obj_size = ti.next_group_obj_off; + else if (i < ti.si.dev) /* dev within this group */ + obj_size = ti.si.obj_offset + + ios->layout->stripe_unit - ti.si.unit_off; + else if (i == ti.si.dev) + obj_size = ti.si.obj_offset; + else /* i > ti.dev */ + obj_size = ti.si.obj_offset - ti.si.unit_off; size_attr->newsize = cpu_to_be64(obj_size); size_attr->attr = g_attr_logical_length; size_attr->attr.val_ptr = &size_attr->newsize; + ORE_DBGMSG("trunc(0x%llx) obj_offset=0x%llx dev=%d\n", + _LLU(comps->comps->obj.id), _LLU(obj_size), i); ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1, &size_attr->attr); if (unlikely(ret)) goto out; } - ret = exofs_io_execute(ios); + ret = ore_io_execute(ios); out: kfree(size_attrs); - exofs_put_io_state(ios); + ore_put_io_state(ios); return ret; } +EXPORT_SYMBOL(ore_truncate); + +const struct osd_attr g_attr_logical_length = ATTR_DEF( + OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8); +EXPORT_SYMBOL(g_attr_logical_length); diff --git a/fs/exofs/pnfs.h b/fs/exofs/pnfs.h deleted file mode 100644 index c52e988..0000000 --- a/fs/exofs/pnfs.h +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Copyright (C) 2008, 2009 - * Boaz Harrosh <bharrosh@panasas.com> - * - * This file is part of exofs. - * - * exofs is free software; you can redistribute it and/or modify it under the - * terms of the GNU General Public License version 2 as published by the Free - * Software Foundation. - * - */ - -/* FIXME: Remove this file once pnfs hits mainline */ - -#ifndef __EXOFS_PNFS_H__ -#define __EXOFS_PNFS_H__ - -#if ! defined(__PNFS_OSD_XDR_H__) - -enum pnfs_iomode { - IOMODE_READ = 1, - IOMODE_RW = 2, - IOMODE_ANY = 3, -}; - -/* Layout Structure */ -enum pnfs_osd_raid_algorithm4 { - PNFS_OSD_RAID_0 = 1, - PNFS_OSD_RAID_4 = 2, - PNFS_OSD_RAID_5 = 3, - PNFS_OSD_RAID_PQ = 4 /* Reed-Solomon P+Q */ -}; - -struct pnfs_osd_data_map { - u32 odm_num_comps; - u64 odm_stripe_unit; - u32 odm_group_width; - u32 odm_group_depth; - u32 odm_mirror_cnt; - u32 odm_raid_algorithm; -}; - -#endif /* ! defined(__PNFS_OSD_XDR_H__) */ - -#endif /* __EXOFS_PNFS_H__ */ diff --git a/fs/exofs/super.c b/fs/exofs/super.c index c57bedd..2748940 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -40,6 +40,8 @@ #include "exofs.h" +#define EXOFS_DBGMSG2(M...) do {} while (0) + /****************************************************************************** * MOUNT OPTIONS *****************************************************************************/ @@ -208,10 +210,48 @@ static void destroy_inodecache(void) } /****************************************************************************** - * SUPERBLOCK FUNCTIONS + * Some osd helpers *****************************************************************************/ -static const struct super_operations exofs_sops; -static const struct export_operations exofs_export_ops; +void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj) +{ + osd_sec_init_nosec_doall_caps(cred_a, obj, false, true); +} + +static int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj, + u64 offset, void *p, unsigned length) +{ + struct osd_request *or = osd_start_request(od, GFP_KERNEL); +/* struct osd_sense_info osi = {.key = 0};*/ + int ret; + + if (unlikely(!or)) { + EXOFS_DBGMSG("%s: osd_start_request failed.\n", __func__); + return -ENOMEM; + } + ret = osd_req_read_kern(or, obj, offset, p, length); + if (unlikely(ret)) { + EXOFS_DBGMSG("%s: osd_req_read_kern failed.\n", __func__); + goto out; + } + + ret = osd_finalize_request(or, 0, cred, NULL); + if (unlikely(ret)) { + EXOFS_DBGMSG("Failed to osd_finalize_request() => %d\n", ret); + goto out; + } + + ret = osd_execute_request(or); + if (unlikely(ret)) + EXOFS_DBGMSG("osd_execute_request() => %d\n", ret); + /* osd_req_decode_sense(or, ret); */ + +out: + osd_end_request(or); + EXOFS_DBGMSG2("read_kern(0x%llx) offset=0x%llx " + "length=0x%llx dev=%p ret=>%d\n", + _LLU(obj->id), _LLU(offset), _LLU(length), od, ret); + return ret; +} static const struct osd_attr g_attr_sb_stats = ATTR_DEF( EXOFS_APAGE_SB_DATA, @@ -223,21 +263,19 @@ static int __sbi_read_stats(struct exofs_sb_info *sbi) struct osd_attr attrs[] = { [0] = g_attr_sb_stats, }; - struct exofs_io_state *ios; + struct ore_io_state *ios; int ret; - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &sbi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__); + EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__); return ret; } - ios->cred = sbi->s_cred; - ios->in_attr = attrs; ios->in_attr_len = ARRAY_SIZE(attrs); - ret = exofs_sbi_read(ios); + ret = ore_read(ios); if (unlikely(ret)) { EXOFS_ERR("Error reading super_block stats => %d\n", ret); goto out; @@ -264,13 +302,13 @@ static int __sbi_read_stats(struct exofs_sb_info *sbi) } out: - exofs_put_io_state(ios); + ore_put_io_state(ios); return ret; } -static void stats_done(struct exofs_io_state *ios, void *p) +static void stats_done(struct ore_io_state *ios, void *p) { - exofs_put_io_state(ios); + ore_put_io_state(ios); /* Good thanks nothing to do anymore */ } @@ -280,12 +318,12 @@ int exofs_sbi_write_stats(struct exofs_sb_info *sbi) struct osd_attr attrs[] = { [0] = g_attr_sb_stats, }; - struct exofs_io_state *ios; + struct ore_io_state *ios; int ret; - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &sbi->comps, &ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__); + EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__); return ret; } @@ -293,21 +331,27 @@ int exofs_sbi_write_stats(struct exofs_sb_info *sbi) sbi->s_ess.s_numfiles = cpu_to_le64(sbi->s_numfiles); attrs[0].val_ptr = &sbi->s_ess; - ios->cred = sbi->s_cred; + ios->done = stats_done; ios->private = sbi; ios->out_attr = attrs; ios->out_attr_len = ARRAY_SIZE(attrs); - ret = exofs_sbi_write(ios); + ret = ore_write(ios); if (unlikely(ret)) { - EXOFS_ERR("%s: exofs_sbi_write failed.\n", __func__); - exofs_put_io_state(ios); + EXOFS_ERR("%s: ore_write failed.\n", __func__); + ore_put_io_state(ios); } return ret; } +/****************************************************************************** + * SUPERBLOCK FUNCTIONS + *****************************************************************************/ +static const struct super_operations exofs_sops; +static const struct export_operations exofs_export_ops; + /* * Write the superblock to the OSD */ @@ -315,7 +359,9 @@ int exofs_sync_fs(struct super_block *sb, int wait) { struct exofs_sb_info *sbi; struct exofs_fscb *fscb; - struct exofs_io_state *ios; + struct ore_comp one_comp; + struct ore_components comps; + struct ore_io_state *ios; int ret = -ENOMEM; fscb = kmalloc(sizeof(*fscb), GFP_KERNEL); @@ -331,7 +377,10 @@ int exofs_sync_fs(struct super_block *sb, int wait) * version). Otherwise the exofs_fscb is read-only from mkfs time. All * the writeable info is set in exofs_sbi_write_stats() above. */ - ret = exofs_get_io_state(&sbi->layout, &ios); + + exofs_init_comps(&comps, &one_comp, sbi, EXOFS_SUPER_ID); + + ret = ore_get_io_state(&sbi->layout, &comps, &ios); if (unlikely(ret)) goto out; @@ -345,14 +394,12 @@ int exofs_sync_fs(struct super_block *sb, int wait) fscb->s_newfs = 0; fscb->s_version = EXOFS_FSCB_VER; - ios->obj.id = EXOFS_SUPER_ID; ios->offset = 0; ios->kern_buff = fscb; - ios->cred = sbi->s_cred; - ret = exofs_sbi_write(ios); + ret = ore_write(ios); if (unlikely(ret)) - EXOFS_ERR("%s: exofs_sbi_write failed.\n", __func__); + EXOFS_ERR("%s: ore_write failed.\n", __func__); else sb->s_dirt = 0; @@ -360,7 +407,7 @@ int exofs_sync_fs(struct super_block *sb, int wait) unlock_super(sb); out: EXOFS_DBGMSG("s_nextid=0x%llx ret=%d\n", _LLU(sbi->s_nextid), ret); - exofs_put_io_state(ios); + ore_put_io_state(ios); kfree(fscb); return ret; } @@ -384,15 +431,17 @@ static void _exofs_print_device(const char *msg, const char *dev_path, void exofs_free_sbi(struct exofs_sb_info *sbi) { - while (sbi->layout.s_numdevs) { - int i = --sbi->layout.s_numdevs; - struct osd_dev *od = sbi->layout.s_ods[i]; + while (sbi->comps.numdevs) { + int i = --sbi->comps.numdevs; + struct osd_dev *od = sbi->comps.ods[i]; if (od) { - sbi->layout.s_ods[i] = NULL; + sbi->comps.ods[i] = NULL; osduld_put_device(od); } } + if (sbi->comps.ods != sbi->_min_one_dev) + kfree(sbi->comps.ods); kfree(sbi); } @@ -419,8 +468,8 @@ static void exofs_put_super(struct super_block *sb) msecs_to_jiffies(100)); } - _exofs_print_device("Unmounting", NULL, sbi->layout.s_ods[0], - sbi->layout.s_pid); + _exofs_print_device("Unmounting", NULL, sbi->comps.ods[0], + sbi->one_comp.obj.partition); bdi_destroy(&sbi->bdi); exofs_free_sbi(sbi); @@ -501,10 +550,19 @@ static int _read_and_match_data_map(struct exofs_sb_info *sbi, unsigned numdevs, return -EINVAL; } + EXOFS_DBGMSG("exofs: layout: " + "num_comps=%u stripe_unit=0x%x group_width=%u " + "group_depth=0x%llx mirrors_p1=%u raid_algorithm=%u\n", + numdevs, + sbi->layout.stripe_unit, + sbi->layout.group_width, + _LLU(sbi->layout.group_depth), + sbi->layout.mirrors_p1, + sbi->data_map.odm_raid_algorithm); return 0; } -static unsigned __ra_pages(struct exofs_layout *layout) +static unsigned __ra_pages(struct ore_layout *layout) { const unsigned _MIN_RA = 32; /* min 128K read-ahead */ unsigned ra_pages = layout->group_width * layout->stripe_unit / @@ -547,13 +605,11 @@ static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev, return !(odi->systemid_len || odi->osdname_len); } -static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, +static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi, + struct osd_dev *fscb_od, unsigned table_count) { - struct exofs_sb_info *sbi = *psbi; - struct osd_dev *fscb_od; - struct osd_obj_id obj = {.partition = sbi->layout.s_pid, - .id = EXOFS_DEVTABLE_ID}; + struct ore_comp comp; struct exofs_device_table *dt; unsigned table_bytes = table_count * sizeof(dt->dt_dev_table[0]) + sizeof(*dt); @@ -567,10 +623,14 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, return -ENOMEM; } - fscb_od = sbi->layout.s_ods[0]; - sbi->layout.s_ods[0] = NULL; - sbi->layout.s_numdevs = 0; - ret = exofs_read_kern(fscb_od, sbi->s_cred, &obj, 0, dt, table_bytes); + sbi->comps.numdevs = 0; + + comp.obj.partition = sbi->one_comp.obj.partition; + comp.obj.id = EXOFS_DEVTABLE_ID; + exofs_make_credential(comp.cred, &comp.obj); + + ret = exofs_read_kern(fscb_od, comp.cred, &comp.obj, 0, dt, + table_bytes); if (unlikely(ret)) { EXOFS_ERR("ERROR: reading device table\n"); goto out; @@ -588,16 +648,18 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, goto out; if (likely(numdevs > 1)) { - unsigned size = numdevs * sizeof(sbi->layout.s_ods[0]); + unsigned size = numdevs * sizeof(sbi->comps.ods[0]); - sbi = krealloc(sbi, sizeof(*sbi) + size, GFP_KERNEL); - if (unlikely(!sbi)) { + /* Twice bigger table: See exofs_init_comps() and below + * comment + */ + sbi->comps.ods = kzalloc(size + size - 1, GFP_KERNEL); + if (unlikely(!sbi->comps.ods)) { + EXOFS_ERR("ERROR: faild allocating Device array[%d]\n", + numdevs); ret = -ENOMEM; goto out; } - memset(&sbi->layout.s_ods[1], 0, - size - sizeof(sbi->layout.s_ods[0])); - *psbi = sbi; } for (i = 0; i < numdevs; i++) { @@ -619,8 +681,8 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, * line. We always keep them in device-table order. */ if (fscb_od && osduld_device_same(fscb_od, &odi)) { - sbi->layout.s_ods[i] = fscb_od; - ++sbi->layout.s_numdevs; + sbi->comps.ods[i] = fscb_od; + ++sbi->comps.numdevs; fscb_od = NULL; continue; } @@ -633,13 +695,13 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, goto out; } - sbi->layout.s_ods[i] = od; - ++sbi->layout.s_numdevs; + sbi->comps.ods[i] = od; + ++sbi->comps.numdevs; /* Read the fscb of the other devices to make sure the FS * partition is there. */ - ret = exofs_read_kern(od, sbi->s_cred, &obj, 0, &fscb, + ret = exofs_read_kern(od, comp.cred, &comp.obj, 0, &fscb, sizeof(fscb)); if (unlikely(ret)) { EXOFS_ERR("ERROR: Malformed participating device " @@ -656,13 +718,22 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi, out: kfree(dt); - if (unlikely(!ret && fscb_od)) { - EXOFS_ERR( - "ERROR: Bad device-table container device not present\n"); - osduld_put_device(fscb_od); - ret = -EINVAL; - } + if (likely(!ret)) { + unsigned numdevs = sbi->comps.numdevs; + if (unlikely(fscb_od)) { + EXOFS_ERR("ERROR: Bad device-table container device not present\n"); + osduld_put_device(fscb_od); + return -EINVAL; + } + /* exofs round-robins the device table view according to inode + * number. We hold a: twice bigger table hence inodes can point + * to any device and have a sequential view of the table + * starting at this device. See exofs_init_comps() + */ + for (i = 0; i < numdevs - 1; ++i) + sbi->comps.ods[i + numdevs] = sbi->comps.ods[i]; + } return ret; } @@ -676,7 +747,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) struct exofs_sb_info *sbi; /*extended info */ struct osd_dev *od; /* Master device */ struct exofs_fscb fscb; /*on-disk superblock info */ - struct osd_obj_id obj; + struct ore_comp comp; unsigned table_count; int ret; @@ -684,10 +755,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) return -ENOMEM; - ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY); - if (ret) - goto free_bdi; - /* use mount options to fill superblock */ if (opts->is_osdname) { struct osd_dev_info odi = {.systemid_len = 0}; @@ -695,6 +762,8 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) odi.osdname_len = strlen(opts->dev_name); odi.osdname = (u8 *)opts->dev_name; od = osduld_info_lookup(&odi); + kfree(opts->dev_name); + opts->dev_name = NULL; } else { od = osduld_path_lookup(opts->dev_name); } @@ -709,11 +778,16 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) sbi->layout.group_width = 1; sbi->layout.group_depth = -1; sbi->layout.group_count = 1; - sbi->layout.s_ods[0] = od; - sbi->layout.s_numdevs = 1; - sbi->layout.s_pid = opts->pid; sbi->s_timeout = opts->timeout; + sbi->one_comp.obj.partition = opts->pid; + sbi->one_comp.obj.id = 0; + exofs_make_credential(sbi->one_comp.cred, &sbi->one_comp.obj); + sbi->comps.numdevs = 1; + sbi->comps.single_comp = EC_SINGLE_COMP; + sbi->comps.comps = &sbi->one_comp; + sbi->comps.ods = sbi->_min_one_dev; + /* fill in some other data by hand */ memset(sb->s_id, 0, sizeof(sb->s_id)); strcpy(sb->s_id, "exofs"); @@ -724,11 +798,11 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) sb->s_bdev = NULL; sb->s_dev = 0; - obj.partition = sbi->layout.s_pid; - obj.id = EXOFS_SUPER_ID; - exofs_make_credential(sbi->s_cred, &obj); + comp.obj.partition = sbi->one_comp.obj.partition; + comp.obj.id = EXOFS_SUPER_ID; + exofs_make_credential(comp.cred, &comp.obj); - ret = exofs_read_kern(od, sbi->s_cred, &obj, 0, &fscb, sizeof(fscb)); + ret = exofs_read_kern(od, comp.cred, &comp.obj, 0, &fscb, sizeof(fscb)); if (unlikely(ret)) goto free_sbi; @@ -757,9 +831,11 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) table_count = le64_to_cpu(fscb.s_dev_table_count); if (table_count) { - ret = exofs_read_lookup_dev_table(&sbi, table_count); + ret = exofs_read_lookup_dev_table(sbi, od, table_count); if (unlikely(ret)) goto free_sbi; + } else { + sbi->comps.ods[0] = od; } __sbi_read_stats(sbi); @@ -793,20 +869,20 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) goto free_sbi; } - _exofs_print_device("Mounting", opts->dev_name, sbi->layout.s_ods[0], - sbi->layout.s_pid); - if (opts->is_osdname) - kfree(opts->dev_name); + ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY); + if (ret) { + EXOFS_DBGMSG("Failed to bdi_setup_and_register\n"); + goto free_sbi; + } + + _exofs_print_device("Mounting", opts->dev_name, sbi->comps.ods[0], + sbi->one_comp.obj.partition); return 0; free_sbi: - bdi_destroy(&sbi->bdi); -free_bdi: EXOFS_ERR("Unable to mount exofs on %s pid=0x%llx err=%d\n", - opts->dev_name, sbi->layout.s_pid, ret); + opts->dev_name, sbi->one_comp.obj.partition, ret); exofs_free_sbi(sbi); - if (opts->is_osdname) - kfree(opts->dev_name); return ret; } @@ -837,7 +913,7 @@ static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct exofs_sb_info *sbi = sb->s_fs_info; - struct exofs_io_state *ios; + struct ore_io_state *ios; struct osd_attr attrs[] = { ATTR_DEF(OSD_APAGE_PARTITION_QUOTAS, OSD_ATTR_PQ_CAPACITY_QUOTA, sizeof(__be64)), @@ -846,21 +922,18 @@ static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf) }; uint64_t capacity = ULLONG_MAX; uint64_t used = ULLONG_MAX; - uint8_t cred_a[OSD_CAP_LEN]; int ret; - ret = exofs_get_io_state(&sbi->layout, &ios); + ret = ore_get_io_state(&sbi->layout, &sbi->comps, &ios); if (ret) { - EXOFS_DBGMSG("exofs_get_io_state failed.\n"); + EXOFS_DBGMSG("ore_get_io_state failed.\n"); return ret; } - exofs_make_credential(cred_a, &ios->obj); - ios->cred = sbi->s_cred; ios->in_attr = attrs; ios->in_attr_len = ARRAY_SIZE(attrs); - ret = exofs_sbi_read(ios); + ret = ore_read(ios); if (unlikely(ret)) goto out; @@ -889,7 +962,7 @@ static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = EXOFS_NAME_LEN; out: - exofs_put_io_state(ios); + ore_put_io_state(ios); return ret; } diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 52c0537..35d6a3c 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -194,12 +194,10 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl) case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); if (error == 0) @@ -253,16 +251,14 @@ ext2_init_acl(struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; if (S_ISDIR(inode->i_mode)) { error = ext2_set_acl(inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_KERNEL, &mode); + error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext2_set_acl(inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 6c29bf0..3091f62 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -199,12 +199,10 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME_SEC; ext3_mark_inode_dirty(handle, inode); if (error == 0) @@ -261,19 +259,16 @@ ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { error = ext3_set_acl(handle, inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_NOFS, &mode); + error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext3_set_acl(handle, inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 04109460..56fd8f86 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ - mmp.o + mmp.o indirect.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index dca2d1d..a5c29bb 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -198,12 +198,10 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); if (error == 0) @@ -259,19 +257,16 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { error = ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_NOFS, &mode); + error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 264f694..f8224ad 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -620,3 +620,51 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) } +/** + * ext4_inode_to_goal_block - return a hint for block allocation + * @inode: inode for block allocation + * + * Return the ideal location to start allocating blocks for a + * newly created inode. + */ +ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_group_t block_group; + ext4_grpblk_t colour; + int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb)); + ext4_fsblk_t bg_start; + ext4_fsblk_t last_block; + + block_group = ei->i_block_group; + if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) { + /* + * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME + * block groups per flexgroup, reserve the first block + * group for directories and special files. Regular + * files will start at the second block group. This + * tends to speed up directory access and improves + * fsck times. + */ + block_group &= ~(flex_size-1); + if (S_ISREG(inode->i_mode)) + block_group++; + } + bg_start = ext4_group_first_block_no(inode->i_sb, block_group); + last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; + + /* + * If we are doing delayed allocation, we don't need take + * colour into account. + */ + if (test_opt(inode->i_sb, DELALLOC)) + return bg_start; + + if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) + colour = (current->pid % 16) * + (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + else + colour = (current->pid % 16) * ((last_block - bg_start) / 16); + return bg_start + colour; +} + diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index fac90f3..8efb2f0 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -246,3 +246,24 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, return 1; } +int ext4_check_blockref(const char *function, unsigned int line, + struct inode *inode, __le32 *p, unsigned int max) +{ + struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + __le32 *bref = p; + unsigned int blk; + + while (bref < p+max) { + blk = le32_to_cpu(*bref++); + if (blk && + unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), + blk, 1))) { + es->s_last_error_block = cpu_to_le64(blk); + ext4_error_inode(inode, function, line, blk, + "invalid block"); + return -EIO; + } + } + return 0; +} + diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index fa44df8..e717dfd 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -526,6 +526,7 @@ struct ext4_new_group_data { #define EXT4_FREE_BLOCKS_METADATA 0x0001 #define EXT4_FREE_BLOCKS_FORGET 0x0002 #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 +#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 /* * ioctl commands @@ -939,6 +940,8 @@ struct ext4_inode_info { #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le +extern void ext4_set_bits(void *bm, int cur, int len); + /* * Maximal mount counts between two filesystem checks */ @@ -1126,7 +1129,8 @@ struct ext4_sb_info { struct journal_s *s_journal; struct list_head s_orphan; struct mutex s_orphan_lock; - struct mutex s_resize_lock; + unsigned long s_resize_flags; /* Flags indicating if there + is a resizer */ unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; @@ -1214,6 +1218,9 @@ struct ext4_sb_info { /* Kernel thread for multiple mount protection */ struct task_struct *s_mmp_tsk; + + /* record the last minlen when FITRIM is called. */ + atomic_t s_last_trim_minblks; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1743,6 +1750,7 @@ extern unsigned ext4_init_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc); #define ext4_free_blocks_after_init(sb, group, desc) \ ext4_init_block_bitmap(sb, NULL, group, desc) +ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, @@ -1793,7 +1801,7 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode, unsigned long count, int flags); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); -extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, +extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); @@ -1834,6 +1842,17 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); + +/* indirect.c */ +extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, int flags); +extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs); +extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); +extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk); +extern void ext4_ind_truncate(struct inode *inode); + /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); @@ -1855,6 +1874,9 @@ extern int ext4_group_extend(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern void *ext4_kvmalloc(size_t size, gfp_t flags); +extern void *ext4_kvzalloc(size_t size, gfp_t flags); +extern void ext4_kvfree(void *ptr); extern void __ext4_error(struct super_block *, const char *, unsigned int, const char *, ...) __attribute__ ((format (printf, 4, 5))); @@ -2067,11 +2089,19 @@ struct ext4_group_info { * 5 free 8-block regions. */ }; -#define EXT4_GROUP_INFO_NEED_INIT_BIT 0 +#define EXT4_GROUP_INFO_NEED_INIT_BIT 0 +#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_WAS_TRIMMED(grp) \ + (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_SET_TRIMMED(grp) \ + (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ + (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) + #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 @@ -2123,6 +2153,19 @@ static inline void ext4_mark_super_dirty(struct super_block *sb) } /* + * Block validity checking + */ +#define ext4_check_indirect_blockref(inode, bh) \ + ext4_check_blockref(__func__, __LINE__, inode, \ + (__le32 *)(bh)->b_data, \ + EXT4_ADDR_PER_BLOCK((inode)->i_sb)) + +#define ext4_ind_check_inode(inode) \ + ext4_check_blockref(__func__, __LINE__, inode, \ + EXT4_I(inode)->i_data, \ + EXT4_NDIR_BLOCKS) + +/* * Inodes and files operations */ @@ -2151,6 +2194,8 @@ extern void ext4_exit_system_zone(void); extern int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, unsigned int count); +extern int ext4_check_blockref(const char *, unsigned int, + struct inode *, __le32 *, unsigned int); /* extents.c */ extern int ext4_ext_tree_init(handle_t *handle, struct inode *); @@ -2230,6 +2275,10 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; +#define EXT4_RESIZING 0 +extern int ext4_resize_begin(struct super_block *sb); +extern void ext4_resize_end(struct super_block *sb); + #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index f815cc8..57cf568 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -114,12 +114,6 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { - struct ext4_inode_info *ei = EXT4_I(inode); - ext4_fsblk_t bg_start; - ext4_fsblk_t last_block; - ext4_grpblk_t colour; - ext4_group_t block_group; - int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb)); int depth; if (path) { @@ -161,36 +155,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, } /* OK. use inode's group */ - block_group = ei->i_block_group; - if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) { - /* - * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME - * block groups per flexgroup, reserve the first block - * group for directories and special files. Regular - * files will start at the second block group. This - * tends to speed up directory access and improves - * fsck times. - */ - block_group &= ~(flex_size-1); - if (S_ISREG(inode->i_mode)) - block_group++; - } - bg_start = ext4_group_first_block_no(inode->i_sb, block_group); - last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; - - /* - * If we are doing delayed allocation, we don't need take - * colour into account. - */ - if (test_opt(inode->i_sb, DELALLOC)) - return bg_start; - - if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) - colour = (current->pid % 16) * - (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); - else - colour = (current->pid % 16) * ((last_block - bg_start) / 16); - return bg_start + colour + block; + return ext4_inode_to_goal_block(inode); } /* @@ -776,6 +741,16 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, logical, le32_to_cpu(curp->p_idx->ei_block)); return -EIO; } + + if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) + >= le16_to_cpu(curp->p_hdr->eh_max))) { + EXT4_ERROR_INODE(inode, + "eh_entries %d >= eh_max %d!", + le16_to_cpu(curp->p_hdr->eh_entries), + le16_to_cpu(curp->p_hdr->eh_max)); + return -EIO; + } + len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx; if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ @@ -805,13 +780,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); - if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) - > le16_to_cpu(curp->p_hdr->eh_max))) { - EXT4_ERROR_INODE(inode, - "logical %d == ei_block %d!", - logical, le32_to_cpu(curp->p_idx->ei_block)); - return -EIO; - } if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); return -EIO; @@ -1446,8 +1414,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) * ext4_ext_next_leaf_block: * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ -static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, - struct ext4_ext_path *path) +static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path) { int depth; @@ -1757,7 +1724,6 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, goto merge; } -repeat: depth = ext_depth(inode); eh = path[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) @@ -1765,9 +1731,10 @@ repeat: /* probably next leaf has space for us? */ fex = EXT_LAST_EXTENT(eh); - next = ext4_ext_next_leaf_block(inode, path); - if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block) - && next != EXT_MAX_BLOCKS) { + next = EXT_MAX_BLOCKS; + if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) + next = ext4_ext_next_leaf_block(path); + if (next != EXT_MAX_BLOCKS) { ext_debug("next leaf block - %d\n", next); BUG_ON(npath != NULL); npath = ext4_ext_find_extent(inode, next, NULL); @@ -1779,7 +1746,7 @@ repeat: ext_debug("next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); path = npath; - goto repeat; + goto has_space; } ext_debug("next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); @@ -1839,7 +1806,7 @@ has_space: ext4_ext_pblock(newext), ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), - nearex, len, nearex + 1, nearex + 2); + nearex, len, nearex, nearex + 1); memmove(nearex + 1, nearex, len); path[depth].p_ext = nearex; } @@ -2052,7 +2019,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, } /* - * ext4_ext_in_cache() + * ext4_ext_check_cache() * Checks to see if the given block is in the cache. * If it is, the cached extent is stored in the given * cache extent pointer. If the cached extent is a hole, @@ -2134,8 +2101,6 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, /* * ext4_ext_rm_idx: * removes index from the index block. - * It's used in truncate case only, thus all requests are for - * last index in the block only. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) @@ -2153,6 +2118,13 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path); if (err) return err; + + if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) { + int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx; + len *= sizeof(struct ext4_extent_idx); + memmove(path->p_idx, path->p_idx + 1, len); + } + le16_add_cpu(&path->p_hdr->eh_entries, -1); err = ext4_ext_dirty(handle, inode, path); if (err) @@ -2534,8 +2506,7 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path) return 1; } -static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, - ext4_lblk_t end) +static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start) { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); @@ -2575,7 +2546,7 @@ again: if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, - start, end); + start, EXT_MAX_BLOCKS - 1); /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; @@ -3107,12 +3078,10 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, struct ext4_ext_path *path) { struct ext4_extent *ex; - struct ext4_extent_header *eh; int depth; int err = 0; depth = ext_depth(inode); - eh = path[depth].p_hdr; ex = path[depth].p_ext; ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical" @@ -3357,8 +3326,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* check in cache */ - if (ext4_ext_in_cache(inode, map->m_lblk, &newex) && - ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0)) { + if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) && + ext4_ext_in_cache(inode, map->m_lblk, &newex)) { if (!newex.ee_start_lo && !newex.ee_start_hi) { if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* @@ -3497,8 +3466,27 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext4_ext_mark_uninitialized(ex); - err = ext4_ext_remove_space(inode, map->m_lblk, - map->m_lblk + punched_out); + ext4_ext_invalidate_cache(inode); + + err = ext4_ext_rm_leaf(handle, inode, path, + map->m_lblk, map->m_lblk + punched_out); + + if (!err && path->p_hdr->eh_entries == 0) { + /* + * Punch hole freed all of this sub tree, + * so we need to correct eh_depth + */ + err = ext4_ext_get_access(handle, inode, path); + if (err == 0) { + ext_inode_hdr(inode)->eh_depth = 0; + ext_inode_hdr(inode)->eh_max = + cpu_to_le16(ext4_ext_space_root( + inode, 0)); + + err = ext4_ext_dirty( + handle, inode, path); + } + } goto out2; } @@ -3596,17 +3584,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, } err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len); - if (err) - goto out2; - - err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); + if (!err) + err = ext4_ext_insert_extent(handle, inode, path, + &newex, flags); if (err) { + int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? + EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0; /* free data blocks we just allocated */ /* not a good idea to call discard here directly, * but otherwise we'd need to call it every free() */ ext4_discard_preallocations(inode); ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex), - ext4_ext_get_actual_len(&newex), 0); + ext4_ext_get_actual_len(&newex), fb_flags); goto out2; } @@ -3699,7 +3688,7 @@ void ext4_ext_truncate(struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); - err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); + err = ext4_ext_remove_space(inode, last_block); /* In a multi-transaction truncate, we only make the final * transaction synchronous. @@ -3835,7 +3824,7 @@ retry: blkbits) >> blkbits)) new_size = offset + len; else - new_size = (map.m_lblk + ret) << blkbits; + new_size = ((loff_t) map.m_lblk + ret) << blkbits; ext4_falloc_update_inode(inode, mode, new_size, (map.m_flags & EXT4_MAP_NEW)); diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index da3bed3..036f78f 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -129,15 +129,30 @@ static int ext4_sync_parent(struct inode *inode) { struct writeback_control wbc; struct dentry *dentry = NULL; + struct inode *next; int ret = 0; - while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { + if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) + return 0; + inode = igrab(inode); + while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = list_entry(inode->i_dentry.next, - struct dentry, d_alias); - if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode) + dentry = NULL; + spin_lock(&inode->i_lock); + if (!list_empty(&inode->i_dentry)) { + dentry = list_first_entry(&inode->i_dentry, + struct dentry, d_alias); + dget(dentry); + } + spin_unlock(&inode->i_lock); + if (!dentry) break; - inode = dentry->d_parent->d_inode; + next = igrab(dentry->d_parent->d_inode); + dput(dentry); + if (!next) + break; + iput(inode); + inode = next; ret = sync_mapping_buffers(inode->i_mapping); if (ret) break; @@ -148,6 +163,7 @@ static int ext4_sync_parent(struct inode *inode) if (ret) break; } + iput(inode); return ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 21bb2f6..9c63f27 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1287,7 +1287,7 @@ extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, group, used_blks, ext4_itable_unused_count(sb, gdp)); ret = 1; - goto out; + goto err_out; } blk = ext4_inode_table(sb, gdp) + used_blks; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c new file mode 100644 index 0000000..b8602cd --- /dev/null +++ b/fs/ext4/indirect.c @@ -0,0 +1,1482 @@ +/* + * linux/fs/ext4/indirect.c + * + * from + * + * linux/fs/ext4/inode.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Goal-directed block allocation by Stephen Tweedie + * (sct@redhat.com), 1993, 1998 + */ + +#include <linux/module.h> +#include "ext4_jbd2.h" +#include "truncate.h" + +#include <trace/events/ext4.h> + +typedef struct { + __le32 *p; + __le32 key; + struct buffer_head *bh; +} Indirect; + +static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) +{ + p->key = *(p->p = v); + p->bh = bh; +} + +/** + * ext4_block_to_path - parse the block number into array of offsets + * @inode: inode in question (we are only interested in its superblock) + * @i_block: block number to be parsed + * @offsets: array to store the offsets in + * @boundary: set this non-zero if the referred-to block is likely to be + * followed (on disk) by an indirect block. + * + * To store the locations of file's data ext4 uses a data structure common + * for UNIX filesystems - tree of pointers anchored in the inode, with + * data blocks at leaves and indirect blocks in intermediate nodes. + * This function translates the block number into path in that tree - + * return value is the path length and @offsets[n] is the offset of + * pointer to (n+1)th node in the nth one. If @block is out of range + * (negative or too large) warning is printed and zero returned. + * + * Note: function doesn't find node addresses, so no IO is needed. All + * we need to know is the capacity of indirect blocks (taken from the + * inode->i_sb). + */ + +/* + * Portability note: the last comparison (check that we fit into triple + * indirect block) is spelled differently, because otherwise on an + * architecture with 32-bit longs and 8Kb pages we might get into trouble + * if our filesystem had 8Kb blocks. We might use long long, but that would + * kill us on x86. Oh, well, at least the sign propagation does not matter - + * i_block would have to be negative in the very beginning, so we would not + * get there at all. + */ + +static int ext4_block_to_path(struct inode *inode, + ext4_lblk_t i_block, + ext4_lblk_t offsets[4], int *boundary) +{ + int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb); + int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb); + const long direct_blocks = EXT4_NDIR_BLOCKS, + indirect_blocks = ptrs, + double_blocks = (1 << (ptrs_bits * 2)); + int n = 0; + int final = 0; + + if (i_block < direct_blocks) { + offsets[n++] = i_block; + final = direct_blocks; + } else if ((i_block -= direct_blocks) < indirect_blocks) { + offsets[n++] = EXT4_IND_BLOCK; + offsets[n++] = i_block; + final = ptrs; + } else if ((i_block -= indirect_blocks) < double_blocks) { + offsets[n++] = EXT4_DIND_BLOCK; + offsets[n++] = i_block >> ptrs_bits; + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { + offsets[n++] = EXT4_TIND_BLOCK; + offsets[n++] = i_block >> (ptrs_bits * 2); + offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else { + ext4_warning(inode->i_sb, "block %lu > max in inode %lu", + i_block + direct_blocks + + indirect_blocks + double_blocks, inode->i_ino); + } + if (boundary) + *boundary = final - 1 - (i_block & (ptrs - 1)); + return n; +} + +/** + * ext4_get_branch - read the chain of indirect blocks leading to data + * @inode: inode in question + * @depth: depth of the chain (1 - direct pointer, etc.) + * @offsets: offsets of pointers in inode/indirect blocks + * @chain: place to store the result + * @err: here we store the error value + * + * Function fills the array of triples <key, p, bh> and returns %NULL + * if everything went OK or the pointer to the last filled triple + * (incomplete one) otherwise. Upon the return chain[i].key contains + * the number of (i+1)-th block in the chain (as it is stored in memory, + * i.e. little-endian 32-bit), chain[i].p contains the address of that + * number (it points into struct inode for i==0 and into the bh->b_data + * for i>0) and chain[i].bh points to the buffer_head of i-th indirect + * block for i>0 and NULL for i==0. In other words, it holds the block + * numbers of the chain, addresses they were taken from (and where we can + * verify that chain did not change) and buffer_heads hosting these + * numbers. + * + * Function stops when it stumbles upon zero pointer (absent block) + * (pointer to last triple returned, *@err == 0) + * or when it gets an IO error reading an indirect block + * (ditto, *@err == -EIO) + * or when it reads all @depth-1 indirect blocks successfully and finds + * the whole chain, all way to the data (returns %NULL, *err == 0). + * + * Need to be called with + * down_read(&EXT4_I(inode)->i_data_sem) + */ +static Indirect *ext4_get_branch(struct inode *inode, int depth, + ext4_lblk_t *offsets, + Indirect chain[4], int *err) +{ + struct super_block *sb = inode->i_sb; + Indirect *p = chain; + struct buffer_head *bh; + + *err = 0; + /* i_data is not going away, no lock needed */ + add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets); + if (!p->key) + goto no_block; + while (--depth) { + bh = sb_getblk(sb, le32_to_cpu(p->key)); + if (unlikely(!bh)) + goto failure; + + if (!bh_uptodate_or_lock(bh)) { + if (bh_submit_read(bh) < 0) { + put_bh(bh); + goto failure; + } + /* validate block references */ + if (ext4_check_indirect_blockref(inode, bh)) { + put_bh(bh); + goto failure; + } + } + + add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets); + /* Reader: end */ + if (!p->key) + goto no_block; + } + return NULL; + +failure: + *err = -EIO; +no_block: + return p; +} + +/** + * ext4_find_near - find a place for allocation with sufficient locality + * @inode: owner + * @ind: descriptor of indirect block. + * + * This function returns the preferred place for block allocation. + * It is used when heuristic for sequential allocation fails. + * Rules are: + * + if there is a block to the left of our position - allocate near it. + * + if pointer will live in indirect block - allocate near that block. + * + if pointer will live in inode - allocate in the same + * cylinder group. + * + * In the latter case we colour the starting block by the callers PID to + * prevent it from clashing with concurrent allocations for a different inode + * in the same block group. The PID is used here so that functionally related + * files will be close-by on-disk. + * + * Caller must make sure that @ind is valid and will stay that way. + */ +static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; + __le32 *p; + + /* Try to find previous block */ + for (p = ind->p - 1; p >= start; p--) { + if (*p) + return le32_to_cpu(*p); + } + + /* No such thing, so let's try location of indirect block */ + if (ind->bh) + return ind->bh->b_blocknr; + + /* + * It is going to be referred to from the inode itself? OK, just put it + * into the same cylinder group then. + */ + return ext4_inode_to_goal_block(inode); +} + +/** + * ext4_find_goal - find a preferred place for allocation. + * @inode: owner + * @block: block we want + * @partial: pointer to the last triple within a chain + * + * Normally this function find the preferred place for block allocation, + * returns it. + * Because this is only used for non-extent files, we limit the block nr + * to 32 bits. + */ +static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, + Indirect *partial) +{ + ext4_fsblk_t goal; + + /* + * XXX need to get goal block from mballoc's data structures + */ + + goal = ext4_find_near(inode, partial); + goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; + return goal; +} + +/** + * ext4_blks_to_allocate - Look up the block map and count the number + * of direct blocks need to be allocated for the given branch. + * + * @branch: chain of indirect blocks + * @k: number of blocks need for indirect blocks + * @blks: number of data blocks to be mapped. + * @blocks_to_boundary: the offset in the indirect block + * + * return the total number of blocks to be allocate, including the + * direct and indirect blocks. + */ +static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, + int blocks_to_boundary) +{ + unsigned int count = 0; + + /* + * Simple case, [t,d]Indirect block(s) has not allocated yet + * then it's clear blocks on that path have not allocated + */ + if (k > 0) { + /* right now we don't handle cross boundary allocation */ + if (blks < blocks_to_boundary + 1) + count += blks; + else + count += blocks_to_boundary + 1; + return count; + } + + count++; + while (count < blks && count <= blocks_to_boundary && + le32_to_cpu(*(branch[0].p + count)) == 0) { + count++; + } + return count; +} + +/** + * ext4_alloc_blocks: multiple allocate blocks needed for a branch + * @handle: handle for this transaction + * @inode: inode which needs allocated blocks + * @iblock: the logical block to start allocated at + * @goal: preferred physical block of allocation + * @indirect_blks: the number of blocks need to allocate for indirect + * blocks + * @blks: number of desired blocks + * @new_blocks: on return it will store the new block numbers for + * the indirect blocks(if needed) and the first direct block, + * @err: on return it will store the error code + * + * This function will return the number of blocks allocated as + * requested by the passed-in parameters. + */ +static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, + ext4_lblk_t iblock, ext4_fsblk_t goal, + int indirect_blks, int blks, + ext4_fsblk_t new_blocks[4], int *err) +{ + struct ext4_allocation_request ar; + int target, i; + unsigned long count = 0, blk_allocated = 0; + int index = 0; + ext4_fsblk_t current_block = 0; + int ret = 0; + + /* + * Here we try to allocate the requested multiple blocks at once, + * on a best-effort basis. + * To build a branch, we should allocate blocks for + * the indirect blocks(if not allocated yet), and at least + * the first direct block of this branch. That's the + * minimum number of blocks need to allocate(required) + */ + /* first we try to allocate the indirect blocks */ + target = indirect_blks; + while (target > 0) { + count = target; + /* allocating blocks for indirect blocks and direct blocks */ + current_block = ext4_new_meta_blocks(handle, inode, goal, + 0, &count, err); + if (*err) + goto failed_out; + + if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) { + EXT4_ERROR_INODE(inode, + "current_block %llu + count %lu > %d!", + current_block, count, + EXT4_MAX_BLOCK_FILE_PHYS); + *err = -EIO; + goto failed_out; + } + + target -= count; + /* allocate blocks for indirect blocks */ + while (index < indirect_blks && count) { + new_blocks[index++] = current_block++; + count--; + } + if (count > 0) { + /* + * save the new block number + * for the first direct block + */ + new_blocks[index] = current_block; + printk(KERN_INFO "%s returned more blocks than " + "requested\n", __func__); + WARN_ON(1); + break; + } + } + + target = blks - count ; + blk_allocated = count; + if (!target) + goto allocated; + /* Now allocate data blocks */ + memset(&ar, 0, sizeof(ar)); + ar.inode = inode; + ar.goal = goal; + ar.len = target; + ar.logical = iblock; + if (S_ISREG(inode->i_mode)) + /* enable in-core preallocation only for regular files */ + ar.flags = EXT4_MB_HINT_DATA; + + current_block = ext4_mb_new_blocks(handle, &ar, err); + if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) { + EXT4_ERROR_INODE(inode, + "current_block %llu + ar.len %d > %d!", + current_block, ar.len, + EXT4_MAX_BLOCK_FILE_PHYS); + *err = -EIO; + goto failed_out; + } + + if (*err && (target == blks)) { + /* + * if the allocation failed and we didn't allocate + * any blocks before + */ + goto failed_out; + } + if (!*err) { + if (target == blks) { + /* + * save the new block number + * for the first direct block + */ + new_blocks[index] = current_block; + } + blk_allocated += ar.len; + } +allocated: + /* total number of blocks allocated for direct blocks */ + ret = blk_allocated; + *err = 0; + return ret; +failed_out: + for (i = 0; i < index; i++) + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); + return ret; +} + +/** + * ext4_alloc_branch - allocate and set up a chain of blocks. + * @handle: handle for this transaction + * @inode: owner + * @indirect_blks: number of allocated indirect blocks + * @blks: number of allocated direct blocks + * @goal: preferred place for allocation + * @offsets: offsets (in the blocks) to store the pointers to next. + * @branch: place to store the chain in. + * + * This function allocates blocks, zeroes out all but the last one, + * links them into chain and (if we are synchronous) writes them to disk. + * In other words, it prepares a branch that can be spliced onto the + * inode. It stores the information about that chain in the branch[], in + * the same format as ext4_get_branch() would do. We are calling it after + * we had read the existing part of chain and partial points to the last + * triple of that (one with zero ->key). Upon the exit we have the same + * picture as after the successful ext4_get_block(), except that in one + * place chain is disconnected - *branch->p is still zero (we did not + * set the last link), but branch->key contains the number that should + * be placed into *branch->p to fill that gap. + * + * If allocation fails we free all blocks we've allocated (and forget + * their buffer_heads) and return the error value the from failed + * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain + * as described above and return 0. + */ +static int ext4_alloc_branch(handle_t *handle, struct inode *inode, + ext4_lblk_t iblock, int indirect_blks, + int *blks, ext4_fsblk_t goal, + ext4_lblk_t *offsets, Indirect *branch) +{ + int blocksize = inode->i_sb->s_blocksize; + int i, n = 0; + int err = 0; + struct buffer_head *bh; + int num; + ext4_fsblk_t new_blocks[4]; + ext4_fsblk_t current_block; + + num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks, + *blks, new_blocks, &err); + if (err) + return err; + + branch[0].key = cpu_to_le32(new_blocks[0]); + /* + * metadata blocks and data blocks are allocated. + */ + for (n = 1; n <= indirect_blks; n++) { + /* + * Get buffer_head for parent block, zero it out + * and set the pointer to new one, then send + * parent to disk. + */ + bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + if (unlikely(!bh)) { + err = -EIO; + goto failed; + } + + branch[n].bh = bh; + lock_buffer(bh); + BUFFER_TRACE(bh, "call get_create_access"); + err = ext4_journal_get_create_access(handle, bh); + if (err) { + /* Don't brelse(bh) here; it's done in + * ext4_journal_forget() below */ + unlock_buffer(bh); + goto failed; + } + + memset(bh->b_data, 0, blocksize); + branch[n].p = (__le32 *) bh->b_data + offsets[n]; + branch[n].key = cpu_to_le32(new_blocks[n]); + *branch[n].p = branch[n].key; + if (n == indirect_blks) { + current_block = new_blocks[n]; + /* + * End of chain, update the last new metablock of + * the chain to point to the new allocated + * data blocks numbers + */ + for (i = 1; i < num; i++) + *(branch[n].p + i) = cpu_to_le32(++current_block); + } + BUFFER_TRACE(bh, "marking uptodate"); + set_buffer_uptodate(bh); + unlock_buffer(bh); + + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, inode, bh); + if (err) + goto failed; + } + *blks = num; + return err; +failed: + /* Allocation failed, free what we already allocated */ + ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0); + for (i = 1; i <= n ; i++) { + /* + * branch[i].bh is newly allocated, so there is no + * need to revoke the block, which is why we don't + * need to set EXT4_FREE_BLOCKS_METADATA. + */ + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, + EXT4_FREE_BLOCKS_FORGET); + } + for (i = n+1; i < indirect_blks; i++) + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); + + ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); + + return err; +} + +/** + * ext4_splice_branch - splice the allocated branch onto inode. + * @handle: handle for this transaction + * @inode: owner + * @block: (logical) number of block we are adding + * @chain: chain of indirect blocks (with a missing link - see + * ext4_alloc_branch) + * @where: location of missing link + * @num: number of indirect blocks we are adding + * @blks: number of direct blocks we are adding + * + * This function fills the missing link and does all housekeeping needed in + * inode (->i_blocks, etc.). In case of success we end up with the full + * chain to new block and return 0. + */ +static int ext4_splice_branch(handle_t *handle, struct inode *inode, + ext4_lblk_t block, Indirect *where, int num, + int blks) +{ + int i; + int err = 0; + ext4_fsblk_t current_block; + + /* + * If we're splicing into a [td]indirect block (as opposed to the + * inode) then we need to get write access to the [td]indirect block + * before the splice. + */ + if (where->bh) { + BUFFER_TRACE(where->bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, where->bh); + if (err) + goto err_out; + } + /* That's it */ + + *where->p = where->key; + + /* + * Update the host buffer_head or inode to point to more just allocated + * direct blocks blocks + */ + if (num == 0 && blks > 1) { + current_block = le32_to_cpu(where->key) + 1; + for (i = 1; i < blks; i++) + *(where->p + i) = cpu_to_le32(current_block++); + } + + /* We are done with atomic stuff, now do the rest of housekeeping */ + /* had we spliced it onto indirect block? */ + if (where->bh) { + /* + * If we spliced it onto an indirect block, we haven't + * altered the inode. Note however that if it is being spliced + * onto an indirect block at the very end of the file (the + * file is growing) then we *will* alter the inode to reflect + * the new i_size. But that is not done here - it is done in + * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. + */ + jbd_debug(5, "splicing indirect only\n"); + BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, inode, where->bh); + if (err) + goto err_out; + } else { + /* + * OK, we spliced it into the inode itself on a direct block. + */ + ext4_mark_inode_dirty(handle, inode); + jbd_debug(5, "splicing direct\n"); + } + return err; + +err_out: + for (i = 1; i <= num; i++) { + /* + * branch[i].bh is newly allocated, so there is no + * need to revoke the block, which is why we don't + * need to set EXT4_FREE_BLOCKS_METADATA. + */ + ext4_free_blocks(handle, inode, where[i].bh, 0, 1, + EXT4_FREE_BLOCKS_FORGET); + } + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key), + blks, 0); + + return err; +} + +/* + * The ext4_ind_map_blocks() function handles non-extents inodes + * (i.e., using the traditional indirect/double-indirect i_blocks + * scheme) for ext4_map_blocks(). + * + * Allocation strategy is simple: if we have to allocate something, we will + * have to go the whole way to leaf. So let's do it before attaching anything + * to tree, set linkage between the newborn blocks, write them if sync is + * required, recheck the path, free and repeat if check fails, otherwise + * set the last missing link (that will protect us from any truncate-generated + * removals - all blocks on the path are immune now) and possibly force the + * write on the parent block. + * That has a nice additional property: no special recovery from the failed + * allocations is needed - we simply release blocks and do not touch anything + * reachable from inode. + * + * `handle' can be NULL if create == 0. + * + * return > 0, # of blocks mapped or allocated. + * return = 0, if plain lookup failed. + * return < 0, error case. + * + * The ext4_ind_get_blocks() function should be called with + * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem + * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or + * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system + * blocks. + */ +int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + int flags) +{ + int err = -EIO; + ext4_lblk_t offsets[4]; + Indirect chain[4]; + Indirect *partial; + ext4_fsblk_t goal; + int indirect_blks; + int blocks_to_boundary = 0; + int depth; + int count = 0; + ext4_fsblk_t first_block = 0; + + trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); + J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); + J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); + depth = ext4_block_to_path(inode, map->m_lblk, offsets, + &blocks_to_boundary); + + if (depth == 0) + goto out; + + partial = ext4_get_branch(inode, depth, offsets, chain, &err); + + /* Simplest case - block found, no allocation needed */ + if (!partial) { + first_block = le32_to_cpu(chain[depth - 1].key); + count++; + /*map more blocks*/ + while (count < map->m_len && count <= blocks_to_boundary) { + ext4_fsblk_t blk; + + blk = le32_to_cpu(*(chain[depth-1].p + count)); + + if (blk == first_block + count) + count++; + else + break; + } + goto got_it; + } + + /* Next simple case - plain lookup or failed read of indirect block */ + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO) + goto cleanup; + + /* + * Okay, we need to do block allocation. + */ + goal = ext4_find_goal(inode, map->m_lblk, partial); + + /* the number of blocks need to allocate for [d,t]indirect blocks */ + indirect_blks = (chain + depth) - partial - 1; + + /* + * Next look up the indirect map to count the totoal number of + * direct blocks to allocate for this branch. + */ + count = ext4_blks_to_allocate(partial, indirect_blks, + map->m_len, blocks_to_boundary); + /* + * Block out ext4_truncate while we alter the tree + */ + err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks, + &count, goal, + offsets + (partial - chain), partial); + + /* + * The ext4_splice_branch call will free and forget any buffers + * on the new chain if there is a failure, but that risks using + * up transaction credits, especially for bitmaps where the + * credits cannot be returned. Can we handle this somehow? We + * may need to return -EAGAIN upwards in the worst case. --sct + */ + if (!err) + err = ext4_splice_branch(handle, inode, map->m_lblk, + partial, indirect_blks, count); + if (err) + goto cleanup; + + map->m_flags |= EXT4_MAP_NEW; + + ext4_update_inode_fsync_trans(handle, inode, 1); +got_it: + map->m_flags |= EXT4_MAP_MAPPED; + map->m_pblk = le32_to_cpu(chain[depth-1].key); + map->m_len = count; + if (count > blocks_to_boundary) + map->m_flags |= EXT4_MAP_BOUNDARY; + err = count; + /* Clean up and exit */ + partial = chain + depth - 1; /* the whole chain */ +cleanup: + while (partial > chain) { + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + partial--; + } +out: + trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, + map->m_pblk, map->m_len, err); + return err; +} + +/* + * O_DIRECT for ext3 (or indirect map) based files + * + * If the O_DIRECT write will extend the file then add this inode to the + * orphan list. So recovery will truncate it back to the original size + * if the machine crashes during the write. + * + * If the O_DIRECT write is intantiating holes inside i_size and the machine + * crashes then stale disk data _may_ be exposed inside the file. But current + * VFS code falls back into buffered path in that case so we are safe. + */ +ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct ext4_inode_info *ei = EXT4_I(inode); + handle_t *handle; + ssize_t ret; + int orphan = 0; + size_t count = iov_length(iov, nr_segs); + int retries = 0; + + if (rw == WRITE) { + loff_t final_size = offset + count; + + if (final_size > inode->i_size) { + /* Credits for sb + inode write */ + handle = ext4_journal_start(inode, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + ret = ext4_orphan_add(handle, inode); + if (ret) { + ext4_journal_stop(handle); + goto out; + } + orphan = 1; + ei->i_disksize = inode->i_size; + ext4_journal_stop(handle); + } + } + +retry: + if (rw == READ && ext4_should_dioread_nolock(inode)) + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block, NULL, NULL, 0); + else { + ret = blockdev_direct_IO(rw, iocb, inode, iov, + offset, nr_segs, ext4_get_block); + + if (unlikely((rw & WRITE) && ret < 0)) { + loff_t isize = i_size_read(inode); + loff_t end = offset + iov_length(iov, nr_segs); + + if (end > isize) + ext4_truncate_failed_write(inode); + } + } + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + + if (orphan) { + int err; + + /* Credits for sb + inode write */ + handle = ext4_journal_start(inode, 2); + if (IS_ERR(handle)) { + /* This is really bad luck. We've written the data + * but cannot extend i_size. Bail out and pretend + * the write failed... */ + ret = PTR_ERR(handle); + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + + goto out; + } + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + if (ret > 0) { + loff_t end = offset + ret; + if (end > inode->i_size) { + ei->i_disksize = end; + i_size_write(inode, end); + /* + * We're going to return a positive `ret' + * here due to non-zero-length I/O, so there's + * no way of reporting error returns from + * ext4_mark_inode_dirty() to userspace. So + * ignore it. + */ + ext4_mark_inode_dirty(handle, inode); + } + } + err = ext4_journal_stop(handle); + if (ret == 0) + ret = err; + } +out: + return ret; +} + +/* + * Calculate the number of metadata blocks need to reserve + * to allocate a new block at @lblocks for non extent file based file + */ +int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1); + int blk_bits; + + if (lblock < EXT4_NDIR_BLOCKS) + return 0; + + lblock -= EXT4_NDIR_BLOCKS; + + if (ei->i_da_metadata_calc_len && + (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) { + ei->i_da_metadata_calc_len++; + return 0; + } + ei->i_da_metadata_calc_last_lblock = lblock & dind_mask; + ei->i_da_metadata_calc_len = 1; + blk_bits = order_base_2(lblock); + return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1; +} + +int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk) +{ + int indirects; + + /* if nrblocks are contiguous */ + if (chunk) { + /* + * With N contiguous data blocks, we need at most + * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks, + * 2 dindirect blocks, and 1 tindirect block + */ + return DIV_ROUND_UP(nrblocks, + EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; + } + /* + * if nrblocks are not contiguous, worse case, each block touch + * a indirect block, and each indirect block touch a double indirect + * block, plus a triple indirect block + */ + indirects = nrblocks * 2 + 1; + return indirects; +} + +/* + * Truncate transactions can be complex and absolutely huge. So we need to + * be able to restart the transaction at a conventient checkpoint to make + * sure we don't overflow the journal. + * + * start_transaction gets us a new handle for a truncate transaction, + * and extend_transaction tries to extend the existing one a bit. If + * extend fails, we need to propagate the failure up and restart the + * transaction in the top-level truncate loop. --sct + */ +static handle_t *start_transaction(struct inode *inode) +{ + handle_t *result; + + result = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)); + if (!IS_ERR(result)) + return result; + + ext4_std_error(inode->i_sb, PTR_ERR(result)); + return result; +} + +/* + * Try to extend this transaction for the purposes of truncation. + * + * Returns 0 if we managed to create more room. If we can't create more + * room, and the transaction must be restarted we return 1. + */ +static int try_to_extend_transaction(handle_t *handle, struct inode *inode) +{ + if (!ext4_handle_valid(handle)) + return 0; + if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1)) + return 0; + if (!ext4_journal_extend(handle, ext4_blocks_for_truncate(inode))) + return 0; + return 1; +} + +/* + * Probably it should be a library function... search for first non-zero word + * or memcmp with zero_page, whatever is better for particular architecture. + * Linus? + */ +static inline int all_zeroes(__le32 *p, __le32 *q) +{ + while (p < q) + if (*p++) + return 0; + return 1; +} + +/** + * ext4_find_shared - find the indirect blocks for partial truncation. + * @inode: inode in question + * @depth: depth of the affected branch + * @offsets: offsets of pointers in that branch (see ext4_block_to_path) + * @chain: place to store the pointers to partial indirect blocks + * @top: place to the (detached) top of branch + * + * This is a helper function used by ext4_truncate(). + * + * When we do truncate() we may have to clean the ends of several + * indirect blocks but leave the blocks themselves alive. Block is + * partially truncated if some data below the new i_size is referred + * from it (and it is on the path to the first completely truncated + * data block, indeed). We have to free the top of that path along + * with everything to the right of the path. Since no allocation + * past the truncation point is possible until ext4_truncate() + * finishes, we may safely do the latter, but top of branch may + * require special attention - pageout below the truncation point + * might try to populate it. + * + * We atomically detach the top of branch from the tree, store the + * block number of its root in *@top, pointers to buffer_heads of + * partially truncated blocks - in @chain[].bh and pointers to + * their last elements that should not be removed - in + * @chain[].p. Return value is the pointer to last filled element + * of @chain. + * + * The work left to caller to do the actual freeing of subtrees: + * a) free the subtree starting from *@top + * b) free the subtrees whose roots are stored in + * (@chain[i].p+1 .. end of @chain[i].bh->b_data) + * c) free the subtrees growing from the inode past the @chain[0]. + * (no partially truncated stuff there). */ + +static Indirect *ext4_find_shared(struct inode *inode, int depth, + ext4_lblk_t offsets[4], Indirect chain[4], + __le32 *top) +{ + Indirect *partial, *p; + int k, err; + + *top = 0; + /* Make k index the deepest non-null offset + 1 */ + for (k = depth; k > 1 && !offsets[k-1]; k--) + ; + partial = ext4_get_branch(inode, k, offsets, chain, &err); + /* Writer: pointers */ + if (!partial) + partial = chain + k-1; + /* + * If the branch acquired continuation since we've looked at it - + * fine, it should all survive and (new) top doesn't belong to us. + */ + if (!partial->key && *partial->p) + /* Writer: end */ + goto no_top; + for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--) + ; + /* + * OK, we've found the last block that must survive. The rest of our + * branch should be detached before unlocking. However, if that rest + * of branch is all ours and does not grow immediately from the inode + * it's easier to cheat and just decrement partial->p. + */ + if (p == chain + k - 1 && p > chain) { + p->p--; + } else { + *top = *p->p; + /* Nope, don't do this in ext4. Must leave the tree intact */ +#if 0 + *p->p = 0; +#endif + } + /* Writer: end */ + + while (partial > p) { + brelse(partial->bh); + partial--; + } +no_top: + return partial; +} + +/* + * Zero a number of block pointers in either an inode or an indirect block. + * If we restart the transaction we must again get write access to the + * indirect block for further modification. + * + * We release `count' blocks on disk, but (last - first) may be greater + * than `count' because there can be holes in there. + * + * Return 0 on success, 1 on invalid block range + * and < 0 on fatal error. + */ +static int ext4_clear_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, + ext4_fsblk_t block_to_free, + unsigned long count, __le32 *first, + __le32 *last) +{ + __le32 *p; + int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED; + int err; + + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + flags |= EXT4_FREE_BLOCKS_METADATA; + + if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, + count)) { + EXT4_ERROR_INODE(inode, "attempt to clear invalid " + "blocks %llu len %lu", + (unsigned long long) block_to_free, count); + return 1; + } + + if (try_to_extend_transaction(handle, inode)) { + if (bh) { + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, inode, bh); + if (unlikely(err)) + goto out_err; + } + err = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err)) + goto out_err; + err = ext4_truncate_restart_trans(handle, inode, + ext4_blocks_for_truncate(inode)); + if (unlikely(err)) + goto out_err; + if (bh) { + BUFFER_TRACE(bh, "retaking write access"); + err = ext4_journal_get_write_access(handle, bh); + if (unlikely(err)) + goto out_err; + } + } + + for (p = first; p < last; p++) + *p = 0; + + ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); + return 0; +out_err: + ext4_std_error(inode->i_sb, err); + return err; +} + +/** + * ext4_free_data - free a list of data blocks + * @handle: handle for this transaction + * @inode: inode we are dealing with + * @this_bh: indirect buffer_head which contains *@first and *@last + * @first: array of block numbers + * @last: points immediately past the end of array + * + * We are freeing all blocks referred from that array (numbers are stored as + * little-endian 32-bit) and updating @inode->i_blocks appropriately. + * + * We accumulate contiguous runs of blocks to free. Conveniently, if these + * blocks are contiguous then releasing them at one time will only affect one + * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't + * actually use a lot of journal space. + * + * @this_bh will be %NULL if @first and @last point into the inode's direct + * block pointers. + */ +static void ext4_free_data(handle_t *handle, struct inode *inode, + struct buffer_head *this_bh, + __le32 *first, __le32 *last) +{ + ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */ + unsigned long count = 0; /* Number of blocks in the run */ + __le32 *block_to_free_p = NULL; /* Pointer into inode/ind + corresponding to + block_to_free */ + ext4_fsblk_t nr; /* Current block # */ + __le32 *p; /* Pointer into inode/ind + for current block */ + int err = 0; + + if (this_bh) { /* For indirect block */ + BUFFER_TRACE(this_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, this_bh); + /* Important: if we can't update the indirect pointers + * to the blocks, we can't free them. */ + if (err) + return; + } + + for (p = first; p < last; p++) { + nr = le32_to_cpu(*p); + if (nr) { + /* accumulate blocks to free if they're contiguous */ + if (count == 0) { + block_to_free = nr; + block_to_free_p = p; + count = 1; + } else if (nr == block_to_free + count) { + count++; + } else { + err = ext4_clear_blocks(handle, inode, this_bh, + block_to_free, count, + block_to_free_p, p); + if (err) + break; + block_to_free = nr; + block_to_free_p = p; + count = 1; + } + } + } + + if (!err && count > 0) + err = ext4_clear_blocks(handle, inode, this_bh, block_to_free, + count, block_to_free_p, p); + if (err < 0) + /* fatal error */ + return; + + if (this_bh) { + BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata"); + + /* + * The buffer head should have an attached journal head at this + * point. However, if the data is corrupted and an indirect + * block pointed to itself, it would have been detached when + * the block was cleared. Check for this instead of OOPSing. + */ + if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh)) + ext4_handle_dirty_metadata(handle, inode, this_bh); + else + EXT4_ERROR_INODE(inode, + "circular indirect block detected at " + "block %llu", + (unsigned long long) this_bh->b_blocknr); + } +} + +/** + * ext4_free_branches - free an array of branches + * @handle: JBD handle for this transaction + * @inode: inode we are dealing with + * @parent_bh: the buffer_head which contains *@first and *@last + * @first: array of block numbers + * @last: pointer immediately past the end of array + * @depth: depth of the branches to free + * + * We are freeing all blocks referred from these branches (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static void ext4_free_branches(handle_t *handle, struct inode *inode, + struct buffer_head *parent_bh, + __le32 *first, __le32 *last, int depth) +{ + ext4_fsblk_t nr; + __le32 *p; + + if (ext4_handle_is_aborted(handle)) + return; + + if (depth--) { + struct buffer_head *bh; + int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); + p = last; + while (--p >= first) { + nr = le32_to_cpu(*p); + if (!nr) + continue; /* A hole */ + + if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), + nr, 1)) { + EXT4_ERROR_INODE(inode, + "invalid indirect mapped " + "block %lu (level %d)", + (unsigned long) nr, depth); + break; + } + + /* Go read the buffer for the next level down */ + bh = sb_bread(inode->i_sb, nr); + + /* + * A read failure? Report error and clear slot + * (should be rare). + */ + if (!bh) { + EXT4_ERROR_INODE_BLOCK(inode, nr, + "Read failure"); + continue; + } + + /* This zaps the entire block. Bottom up. */ + BUFFER_TRACE(bh, "free child branches"); + ext4_free_branches(handle, inode, bh, + (__le32 *) bh->b_data, + (__le32 *) bh->b_data + addr_per_block, + depth); + brelse(bh); + + /* + * Everything below this this pointer has been + * released. Now let this top-of-subtree go. + * + * We want the freeing of this indirect block to be + * atomic in the journal with the updating of the + * bitmap block which owns it. So make some room in + * the journal. + * + * We zero the parent pointer *after* freeing its + * pointee in the bitmaps, so if extend_transaction() + * for some reason fails to put the bitmap changes and + * the release into the same transaction, recovery + * will merely complain about releasing a free block, + * rather than leaking blocks. + */ + if (ext4_handle_is_aborted(handle)) + return; + if (try_to_extend_transaction(handle, inode)) { + ext4_mark_inode_dirty(handle, inode); + ext4_truncate_restart_trans(handle, inode, + ext4_blocks_for_truncate(inode)); + } + + /* + * The forget flag here is critical because if + * we are journaling (and not doing data + * journaling), we have to make sure a revoke + * record is written to prevent the journal + * replay from overwriting the (former) + * indirect block if it gets reallocated as a + * data block. This must happen in the same + * transaction where the data blocks are + * actually freed. + */ + ext4_free_blocks(handle, inode, NULL, nr, 1, + EXT4_FREE_BLOCKS_METADATA| + EXT4_FREE_BLOCKS_FORGET); + + if (parent_bh) { + /* + * The block which we have just freed is + * pointed to by an indirect block: journal it + */ + BUFFER_TRACE(parent_bh, "get_write_access"); + if (!ext4_journal_get_write_access(handle, + parent_bh)){ + *p = 0; + BUFFER_TRACE(parent_bh, + "call ext4_handle_dirty_metadata"); + ext4_handle_dirty_metadata(handle, + inode, + parent_bh); + } + } + } + } else { + /* We have reached the bottom of the tree. */ + BUFFER_TRACE(parent_bh, "free data blocks"); + ext4_free_data(handle, inode, parent_bh, first, last); + } +} + +void ext4_ind_truncate(struct inode *inode) +{ + handle_t *handle; + struct ext4_inode_info *ei = EXT4_I(inode); + __le32 *i_data = ei->i_data; + int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + ext4_lblk_t offsets[4]; + Indirect chain[4]; + Indirect *partial; + __le32 nr = 0; + int n = 0; + ext4_lblk_t last_block, max_block; + unsigned blocksize = inode->i_sb->s_blocksize; + + handle = start_transaction(inode); + if (IS_ERR(handle)) + return; /* AKPM: return what? */ + + last_block = (inode->i_size + blocksize-1) + >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); + max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) + >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); + + if (inode->i_size & (blocksize - 1)) + if (ext4_block_truncate_page(handle, mapping, inode->i_size)) + goto out_stop; + + if (last_block != max_block) { + n = ext4_block_to_path(inode, last_block, offsets, NULL); + if (n == 0) + goto out_stop; /* error */ + } + + /* + * OK. This truncate is going to happen. We add the inode to the + * orphan list, so that if this truncate spans multiple transactions, + * and we crash, we will resume the truncate when the filesystem + * recovers. It also marks the inode dirty, to catch the new size. + * + * Implication: the file must always be in a sane, consistent + * truncatable state while each transaction commits. + */ + if (ext4_orphan_add(handle, inode)) + goto out_stop; + + /* + * From here we block out all ext4_get_block() callers who want to + * modify the block allocation tree. + */ + down_write(&ei->i_data_sem); + + ext4_discard_preallocations(inode); + + /* + * The orphan list entry will now protect us from any crash which + * occurs before the truncate completes, so it is now safe to propagate + * the new, shorter inode size (held for now in i_size) into the + * on-disk inode. We do this via i_disksize, which is the value which + * ext4 *really* writes onto the disk inode. + */ + ei->i_disksize = inode->i_size; + + if (last_block == max_block) { + /* + * It is unnecessary to free any data blocks if last_block is + * equal to the indirect block limit. + */ + goto out_unlock; + } else if (n == 1) { /* direct blocks */ + ext4_free_data(handle, inode, NULL, i_data+offsets[0], + i_data + EXT4_NDIR_BLOCKS); + goto do_indirects; + } + + partial = ext4_find_shared(inode, n, offsets, chain, &nr); + /* Kill the top of shared branch (not detached) */ + if (nr) { + if (partial == chain) { + /* Shared branch grows from the inode */ + ext4_free_branches(handle, inode, NULL, + &nr, &nr+1, (chain+n-1) - partial); + *partial->p = 0; + /* + * We mark the inode dirty prior to restart, + * and prior to stop. No need for it here. + */ + } else { + /* Shared branch grows from an indirect block */ + BUFFER_TRACE(partial->bh, "get_write_access"); + ext4_free_branches(handle, inode, partial->bh, + partial->p, + partial->p+1, (chain+n-1) - partial); + } + } + /* Clear the ends of indirect blocks on the shared branch */ + while (partial > chain) { + ext4_free_branches(handle, inode, partial->bh, partial->p + 1, + (__le32*)partial->bh->b_data+addr_per_block, + (chain+n-1) - partial); + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + partial--; + } +do_indirects: + /* Kill the remaining (whole) subtrees */ + switch (offsets[0]) { + default: + nr = i_data[EXT4_IND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); + i_data[EXT4_IND_BLOCK] = 0; + } + case EXT4_IND_BLOCK: + nr = i_data[EXT4_DIND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); + i_data[EXT4_DIND_BLOCK] = 0; + } + case EXT4_DIND_BLOCK: + nr = i_data[EXT4_TIND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); + i_data[EXT4_TIND_BLOCK] = 0; + } + case EXT4_TIND_BLOCK: + ; + } + +out_unlock: + up_write(&ei->i_data_sem); + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + + /* + * In a multi-transaction truncate, we only make the final transaction + * synchronous + */ + if (IS_SYNC(inode)) + ext4_handle_sync(handle); +out_stop: + /* + * If this was a simple ftruncate(), and the file will remain alive + * then we need to clear up the orphan record which we created above. + * However, if this was a real unlink then we were called by + * ext4_delete_inode(), and we allow that function to clean up the + * orphan info for us. + */ + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + ext4_journal_stop(handle); + trace_ext4_truncate_exit(inode); +} + diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3e5191f..d47264c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -12,10 +12,6 @@ * * Copyright (C) 1991, 1992 Linus Torvalds * - * Goal-directed block allocation by Stephen Tweedie - * (sct@redhat.com), 1993, 1998 - * Big-endian to little-endian byte-swapping/bitmaps by - * David S. Miller (davem@caip.rutgers.edu), 1995 * 64-bit file support on 64-bit platforms by Jakub Jelinek * (jj@sunsite.ms.mff.cuni.cz) * @@ -47,6 +43,7 @@ #include "xattr.h" #include "acl.h" #include "ext4_extents.h" +#include "truncate.h" #include <trace/events/ext4.h> @@ -89,72 +86,6 @@ static int ext4_inode_is_fast_symlink(struct inode *inode) } /* - * Work out how many blocks we need to proceed with the next chunk of a - * truncate transaction. - */ -static unsigned long blocks_for_truncate(struct inode *inode) -{ - ext4_lblk_t needed; - - needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); - - /* Give ourselves just enough room to cope with inodes in which - * i_blocks is corrupt: we've seen disk corruptions in the past - * which resulted in random data in an inode which looked enough - * like a regular file for ext4 to try to delete it. Things - * will go a bit crazy if that happens, but at least we should - * try not to panic the whole kernel. */ - if (needed < 2) - needed = 2; - - /* But we need to bound the transaction so we don't overflow the - * journal. */ - if (needed > EXT4_MAX_TRANS_DATA) - needed = EXT4_MAX_TRANS_DATA; - - return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; -} - -/* - * Truncate transactions can be complex and absolutely huge. So we need to - * be able to restart the transaction at a conventient checkpoint to make - * sure we don't overflow the journal. - * - * start_transaction gets us a new handle for a truncate transaction, - * and extend_transaction tries to extend the existing one a bit. If - * extend fails, we need to propagate the failure up and restart the - * transaction in the top-level truncate loop. --sct - */ -static handle_t *start_transaction(struct inode *inode) -{ - handle_t *result; - - result = ext4_journal_start(inode, blocks_for_truncate(inode)); - if (!IS_ERR(result)) - return result; - - ext4_std_error(inode->i_sb, PTR_ERR(result)); - return result; -} - -/* - * Try to extend this transaction for the purposes of truncation. - * - * Returns 0 if we managed to create more room. If we can't create more - * room, and the transaction must be restarted we return 1. - */ -static int try_to_extend_transaction(handle_t *handle, struct inode *inode) -{ - if (!ext4_handle_valid(handle)) - return 0; - if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1)) - return 0; - if (!ext4_journal_extend(handle, blocks_for_truncate(inode))) - return 0; - return 1; -} - -/* * Restart the transaction associated with *handle. This does a commit, * so before we call here everything must be consistently dirtied against * this transaction. @@ -190,6 +121,33 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); if (inode->i_nlink) { + /* + * When journalling data dirty buffers are tracked only in the + * journal. So although mm thinks everything is clean and + * ready for reaping the inode might still have some pages to + * write in the running transaction or waiting to be + * checkpointed. Thus calling jbd2_journal_invalidatepage() + * (via truncate_inode_pages()) to discard these buffers can + * cause data loss. Also even if we did not discard these + * buffers, we would have no way to find them after the inode + * is reaped and thus user could see stale data if he tries to + * read them before the transaction is checkpointed. So be + * careful and force everything to disk here... We use + * ei->i_datasync_tid to store the newest transaction + * containing inode's data. + * + * Note that directories do not have this problem because they + * don't use page cache. + */ + if (ext4_should_journal_data(inode) && + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; + + jbd2_log_start_commit(journal, commit_tid); + jbd2_log_wait_commit(journal, commit_tid); + filemap_write_and_wait(&inode->i_data); + } truncate_inode_pages(&inode->i_data, 0); goto no_delete; } @@ -204,7 +162,7 @@ void ext4_evict_inode(struct inode *inode) if (is_bad_inode(inode)) goto no_delete; - handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3); + handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -277,793 +235,6 @@ no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } -typedef struct { - __le32 *p; - __le32 key; - struct buffer_head *bh; -} Indirect; - -static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) -{ - p->key = *(p->p = v); - p->bh = bh; -} - -/** - * ext4_block_to_path - parse the block number into array of offsets - * @inode: inode in question (we are only interested in its superblock) - * @i_block: block number to be parsed - * @offsets: array to store the offsets in - * @boundary: set this non-zero if the referred-to block is likely to be - * followed (on disk) by an indirect block. - * - * To store the locations of file's data ext4 uses a data structure common - * for UNIX filesystems - tree of pointers anchored in the inode, with - * data blocks at leaves and indirect blocks in intermediate nodes. - * This function translates the block number into path in that tree - - * return value is the path length and @offsets[n] is the offset of - * pointer to (n+1)th node in the nth one. If @block is out of range - * (negative or too large) warning is printed and zero returned. - * - * Note: function doesn't find node addresses, so no IO is needed. All - * we need to know is the capacity of indirect blocks (taken from the - * inode->i_sb). - */ - -/* - * Portability note: the last comparison (check that we fit into triple - * indirect block) is spelled differently, because otherwise on an - * architecture with 32-bit longs and 8Kb pages we might get into trouble - * if our filesystem had 8Kb blocks. We might use long long, but that would - * kill us on x86. Oh, well, at least the sign propagation does not matter - - * i_block would have to be negative in the very beginning, so we would not - * get there at all. - */ - -static int ext4_block_to_path(struct inode *inode, - ext4_lblk_t i_block, - ext4_lblk_t offsets[4], int *boundary) -{ - int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb); - int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb); - const long direct_blocks = EXT4_NDIR_BLOCKS, - indirect_blocks = ptrs, - double_blocks = (1 << (ptrs_bits * 2)); - int n = 0; - int final = 0; - - if (i_block < direct_blocks) { - offsets[n++] = i_block; - final = direct_blocks; - } else if ((i_block -= direct_blocks) < indirect_blocks) { - offsets[n++] = EXT4_IND_BLOCK; - offsets[n++] = i_block; - final = ptrs; - } else if ((i_block -= indirect_blocks) < double_blocks) { - offsets[n++] = EXT4_DIND_BLOCK; - offsets[n++] = i_block >> ptrs_bits; - offsets[n++] = i_block & (ptrs - 1); - final = ptrs; - } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { - offsets[n++] = EXT4_TIND_BLOCK; - offsets[n++] = i_block >> (ptrs_bits * 2); - offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); - offsets[n++] = i_block & (ptrs - 1); - final = ptrs; - } else { - ext4_warning(inode->i_sb, "block %lu > max in inode %lu", - i_block + direct_blocks + - indirect_blocks + double_blocks, inode->i_ino); - } - if (boundary) - *boundary = final - 1 - (i_block & (ptrs - 1)); - return n; -} - -static int __ext4_check_blockref(const char *function, unsigned int line, - struct inode *inode, - __le32 *p, unsigned int max) -{ - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - __le32 *bref = p; - unsigned int blk; - - while (bref < p+max) { - blk = le32_to_cpu(*bref++); - if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { - es->s_last_error_block = cpu_to_le64(blk); - ext4_error_inode(inode, function, line, blk, - "invalid block"); - return -EIO; - } - } - return 0; -} - - -#define ext4_check_indirect_blockref(inode, bh) \ - __ext4_check_blockref(__func__, __LINE__, inode, \ - (__le32 *)(bh)->b_data, \ - EXT4_ADDR_PER_BLOCK((inode)->i_sb)) - -#define ext4_check_inode_blockref(inode) \ - __ext4_check_blockref(__func__, __LINE__, inode, \ - EXT4_I(inode)->i_data, \ - EXT4_NDIR_BLOCKS) - -/** - * ext4_get_branch - read the chain of indirect blocks leading to data - * @inode: inode in question - * @depth: depth of the chain (1 - direct pointer, etc.) - * @offsets: offsets of pointers in inode/indirect blocks - * @chain: place to store the result - * @err: here we store the error value - * - * Function fills the array of triples <key, p, bh> and returns %NULL - * if everything went OK or the pointer to the last filled triple - * (incomplete one) otherwise. Upon the return chain[i].key contains - * the number of (i+1)-th block in the chain (as it is stored in memory, - * i.e. little-endian 32-bit), chain[i].p contains the address of that - * number (it points into struct inode for i==0 and into the bh->b_data - * for i>0) and chain[i].bh points to the buffer_head of i-th indirect - * block for i>0 and NULL for i==0. In other words, it holds the block - * numbers of the chain, addresses they were taken from (and where we can - * verify that chain did not change) and buffer_heads hosting these - * numbers. - * - * Function stops when it stumbles upon zero pointer (absent block) - * (pointer to last triple returned, *@err == 0) - * or when it gets an IO error reading an indirect block - * (ditto, *@err == -EIO) - * or when it reads all @depth-1 indirect blocks successfully and finds - * the whole chain, all way to the data (returns %NULL, *err == 0). - * - * Need to be called with - * down_read(&EXT4_I(inode)->i_data_sem) - */ -static Indirect *ext4_get_branch(struct inode *inode, int depth, - ext4_lblk_t *offsets, - Indirect chain[4], int *err) -{ - struct super_block *sb = inode->i_sb; - Indirect *p = chain; - struct buffer_head *bh; - - *err = 0; - /* i_data is not going away, no lock needed */ - add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets); - if (!p->key) - goto no_block; - while (--depth) { - bh = sb_getblk(sb, le32_to_cpu(p->key)); - if (unlikely(!bh)) - goto failure; - - if (!bh_uptodate_or_lock(bh)) { - if (bh_submit_read(bh) < 0) { - put_bh(bh); - goto failure; - } - /* validate block references */ - if (ext4_check_indirect_blockref(inode, bh)) { - put_bh(bh); - goto failure; - } - } - - add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets); - /* Reader: end */ - if (!p->key) - goto no_block; - } - return NULL; - -failure: - *err = -EIO; -no_block: - return p; -} - -/** - * ext4_find_near - find a place for allocation with sufficient locality - * @inode: owner - * @ind: descriptor of indirect block. - * - * This function returns the preferred place for block allocation. - * It is used when heuristic for sequential allocation fails. - * Rules are: - * + if there is a block to the left of our position - allocate near it. - * + if pointer will live in indirect block - allocate near that block. - * + if pointer will live in inode - allocate in the same - * cylinder group. - * - * In the latter case we colour the starting block by the callers PID to - * prevent it from clashing with concurrent allocations for a different inode - * in the same block group. The PID is used here so that functionally related - * files will be close-by on-disk. - * - * Caller must make sure that @ind is valid and will stay that way. - */ -static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; - __le32 *p; - ext4_fsblk_t bg_start; - ext4_fsblk_t last_block; - ext4_grpblk_t colour; - ext4_group_t block_group; - int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb)); - - /* Try to find previous block */ - for (p = ind->p - 1; p >= start; p--) { - if (*p) - return le32_to_cpu(*p); - } - - /* No such thing, so let's try location of indirect block */ - if (ind->bh) - return ind->bh->b_blocknr; - - /* - * It is going to be referred to from the inode itself? OK, just put it - * into the same cylinder group then. - */ - block_group = ei->i_block_group; - if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) { - block_group &= ~(flex_size-1); - if (S_ISREG(inode->i_mode)) - block_group++; - } - bg_start = ext4_group_first_block_no(inode->i_sb, block_group); - last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; - - /* - * If we are doing delayed allocation, we don't need take - * colour into account. - */ - if (test_opt(inode->i_sb, DELALLOC)) - return bg_start; - - if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) - colour = (current->pid % 16) * - (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); - else - colour = (current->pid % 16) * ((last_block - bg_start) / 16); - return bg_start + colour; -} - -/** - * ext4_find_goal - find a preferred place for allocation. - * @inode: owner - * @block: block we want - * @partial: pointer to the last triple within a chain - * - * Normally this function find the preferred place for block allocation, - * returns it. - * Because this is only used for non-extent files, we limit the block nr - * to 32 bits. - */ -static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, - Indirect *partial) -{ - ext4_fsblk_t goal; - - /* - * XXX need to get goal block from mballoc's data structures - */ - - goal = ext4_find_near(inode, partial); - goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; - return goal; -} - -/** - * ext4_blks_to_allocate - Look up the block map and count the number - * of direct blocks need to be allocated for the given branch. - * - * @branch: chain of indirect blocks - * @k: number of blocks need for indirect blocks - * @blks: number of data blocks to be mapped. - * @blocks_to_boundary: the offset in the indirect block - * - * return the total number of blocks to be allocate, including the - * direct and indirect blocks. - */ -static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, - int blocks_to_boundary) -{ - unsigned int count = 0; - - /* - * Simple case, [t,d]Indirect block(s) has not allocated yet - * then it's clear blocks on that path have not allocated - */ - if (k > 0) { - /* right now we don't handle cross boundary allocation */ - if (blks < blocks_to_boundary + 1) - count += blks; - else - count += blocks_to_boundary + 1; - return count; - } - - count++; - while (count < blks && count <= blocks_to_boundary && - le32_to_cpu(*(branch[0].p + count)) == 0) { - count++; - } - return count; -} - -/** - * ext4_alloc_blocks: multiple allocate blocks needed for a branch - * @handle: handle for this transaction - * @inode: inode which needs allocated blocks - * @iblock: the logical block to start allocated at - * @goal: preferred physical block of allocation - * @indirect_blks: the number of blocks need to allocate for indirect - * blocks - * @blks: number of desired blocks - * @new_blocks: on return it will store the new block numbers for - * the indirect blocks(if needed) and the first direct block, - * @err: on return it will store the error code - * - * This function will return the number of blocks allocated as - * requested by the passed-in parameters. - */ -static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, ext4_fsblk_t goal, - int indirect_blks, int blks, - ext4_fsblk_t new_blocks[4], int *err) -{ - struct ext4_allocation_request ar; - int target, i; - unsigned long count = 0, blk_allocated = 0; - int index = 0; - ext4_fsblk_t current_block = 0; - int ret = 0; - - /* - * Here we try to allocate the requested multiple blocks at once, - * on a best-effort basis. - * To build a branch, we should allocate blocks for - * the indirect blocks(if not allocated yet), and at least - * the first direct block of this branch. That's the - * minimum number of blocks need to allocate(required) - */ - /* first we try to allocate the indirect blocks */ - target = indirect_blks; - while (target > 0) { - count = target; - /* allocating blocks for indirect blocks and direct blocks */ - current_block = ext4_new_meta_blocks(handle, inode, goal, - 0, &count, err); - if (*err) - goto failed_out; - - if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + count %lu > %d!", - current_block, count, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - target -= count; - /* allocate blocks for indirect blocks */ - while (index < indirect_blks && count) { - new_blocks[index++] = current_block++; - count--; - } - if (count > 0) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - printk(KERN_INFO "%s returned more blocks than " - "requested\n", __func__); - WARN_ON(1); - break; - } - } - - target = blks - count ; - blk_allocated = count; - if (!target) - goto allocated; - /* Now allocate data blocks */ - memset(&ar, 0, sizeof(ar)); - ar.inode = inode; - ar.goal = goal; - ar.len = target; - ar.logical = iblock; - if (S_ISREG(inode->i_mode)) - /* enable in-core preallocation only for regular files */ - ar.flags = EXT4_MB_HINT_DATA; - - current_block = ext4_mb_new_blocks(handle, &ar, err); - if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + ar.len %d > %d!", - current_block, ar.len, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - if (*err && (target == blks)) { - /* - * if the allocation failed and we didn't allocate - * any blocks before - */ - goto failed_out; - } - if (!*err) { - if (target == blks) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - } - blk_allocated += ar.len; - } -allocated: - /* total number of blocks allocated for direct blocks */ - ret = blk_allocated; - *err = 0; - return ret; -failed_out: - for (i = 0; i < index; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - return ret; -} - -/** - * ext4_alloc_branch - allocate and set up a chain of blocks. - * @handle: handle for this transaction - * @inode: owner - * @indirect_blks: number of allocated indirect blocks - * @blks: number of allocated direct blocks - * @goal: preferred place for allocation - * @offsets: offsets (in the blocks) to store the pointers to next. - * @branch: place to store the chain in. - * - * This function allocates blocks, zeroes out all but the last one, - * links them into chain and (if we are synchronous) writes them to disk. - * In other words, it prepares a branch that can be spliced onto the - * inode. It stores the information about that chain in the branch[], in - * the same format as ext4_get_branch() would do. We are calling it after - * we had read the existing part of chain and partial points to the last - * triple of that (one with zero ->key). Upon the exit we have the same - * picture as after the successful ext4_get_block(), except that in one - * place chain is disconnected - *branch->p is still zero (we did not - * set the last link), but branch->key contains the number that should - * be placed into *branch->p to fill that gap. - * - * If allocation fails we free all blocks we've allocated (and forget - * their buffer_heads) and return the error value the from failed - * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain - * as described above and return 0. - */ -static int ext4_alloc_branch(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, int indirect_blks, - int *blks, ext4_fsblk_t goal, - ext4_lblk_t *offsets, Indirect *branch) -{ - int blocksize = inode->i_sb->s_blocksize; - int i, n = 0; - int err = 0; - struct buffer_head *bh; - int num; - ext4_fsblk_t new_blocks[4]; - ext4_fsblk_t current_block; - - num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks, - *blks, new_blocks, &err); - if (err) - return err; - - branch[0].key = cpu_to_le32(new_blocks[0]); - /* - * metadata blocks and data blocks are allocated. - */ - for (n = 1; n <= indirect_blks; n++) { - /* - * Get buffer_head for parent block, zero it out - * and set the pointer to new one, then send - * parent to disk. - */ - bh = sb_getblk(inode->i_sb, new_blocks[n-1]); - if (unlikely(!bh)) { - err = -EIO; - goto failed; - } - - branch[n].bh = bh; - lock_buffer(bh); - BUFFER_TRACE(bh, "call get_create_access"); - err = ext4_journal_get_create_access(handle, bh); - if (err) { - /* Don't brelse(bh) here; it's done in - * ext4_journal_forget() below */ - unlock_buffer(bh); - goto failed; - } - - memset(bh->b_data, 0, blocksize); - branch[n].p = (__le32 *) bh->b_data + offsets[n]; - branch[n].key = cpu_to_le32(new_blocks[n]); - *branch[n].p = branch[n].key; - if (n == indirect_blks) { - current_block = new_blocks[n]; - /* - * End of chain, update the last new metablock of - * the chain to point to the new allocated - * data blocks numbers - */ - for (i = 1; i < num; i++) - *(branch[n].p + i) = cpu_to_le32(++current_block); - } - BUFFER_TRACE(bh, "marking uptodate"); - set_buffer_uptodate(bh); - unlock_buffer(bh); - - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, inode, bh); - if (err) - goto failed; - } - *blks = num; - return err; -failed: - /* Allocation failed, free what we already allocated */ - ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0); - for (i = 1; i <= n ; i++) { - /* - * branch[i].bh is newly allocated, so there is no - * need to revoke the block, which is why we don't - * need to set EXT4_FREE_BLOCKS_METADATA. - */ - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, - EXT4_FREE_BLOCKS_FORGET); - } - for (i = n+1; i < indirect_blks; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - - ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); - - return err; -} - -/** - * ext4_splice_branch - splice the allocated branch onto inode. - * @handle: handle for this transaction - * @inode: owner - * @block: (logical) number of block we are adding - * @chain: chain of indirect blocks (with a missing link - see - * ext4_alloc_branch) - * @where: location of missing link - * @num: number of indirect blocks we are adding - * @blks: number of direct blocks we are adding - * - * This function fills the missing link and does all housekeeping needed in - * inode (->i_blocks, etc.). In case of success we end up with the full - * chain to new block and return 0. - */ -static int ext4_splice_branch(handle_t *handle, struct inode *inode, - ext4_lblk_t block, Indirect *where, int num, - int blks) -{ - int i; - int err = 0; - ext4_fsblk_t current_block; - - /* - * If we're splicing into a [td]indirect block (as opposed to the - * inode) then we need to get write access to the [td]indirect block - * before the splice. - */ - if (where->bh) { - BUFFER_TRACE(where->bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, where->bh); - if (err) - goto err_out; - } - /* That's it */ - - *where->p = where->key; - - /* - * Update the host buffer_head or inode to point to more just allocated - * direct blocks blocks - */ - if (num == 0 && blks > 1) { - current_block = le32_to_cpu(where->key) + 1; - for (i = 1; i < blks; i++) - *(where->p + i) = cpu_to_le32(current_block++); - } - - /* We are done with atomic stuff, now do the rest of housekeeping */ - /* had we spliced it onto indirect block? */ - if (where->bh) { - /* - * If we spliced it onto an indirect block, we haven't - * altered the inode. Note however that if it is being spliced - * onto an indirect block at the very end of the file (the - * file is growing) then we *will* alter the inode to reflect - * the new i_size. But that is not done here - it is done in - * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. - */ - jbd_debug(5, "splicing indirect only\n"); - BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, inode, where->bh); - if (err) - goto err_out; - } else { - /* - * OK, we spliced it into the inode itself on a direct block. - */ - ext4_mark_inode_dirty(handle, inode); - jbd_debug(5, "splicing direct\n"); - } - return err; - -err_out: - for (i = 1; i <= num; i++) { - /* - * branch[i].bh is newly allocated, so there is no - * need to revoke the block, which is why we don't - * need to set EXT4_FREE_BLOCKS_METADATA. - */ - ext4_free_blocks(handle, inode, where[i].bh, 0, 1, - EXT4_FREE_BLOCKS_FORGET); - } - ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key), - blks, 0); - - return err; -} - -/* - * The ext4_ind_map_blocks() function handles non-extents inodes - * (i.e., using the traditional indirect/double-indirect i_blocks - * scheme) for ext4_map_blocks(). - * - * Allocation strategy is simple: if we have to allocate something, we will - * have to go the whole way to leaf. So let's do it before attaching anything - * to tree, set linkage between the newborn blocks, write them if sync is - * required, recheck the path, free and repeat if check fails, otherwise - * set the last missing link (that will protect us from any truncate-generated - * removals - all blocks on the path are immune now) and possibly force the - * write on the parent block. - * That has a nice additional property: no special recovery from the failed - * allocations is needed - we simply release blocks and do not touch anything - * reachable from inode. - * - * `handle' can be NULL if create == 0. - * - * return > 0, # of blocks mapped or allocated. - * return = 0, if plain lookup failed. - * return < 0, error case. - * - * The ext4_ind_get_blocks() function should be called with - * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem - * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or - * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system - * blocks. - */ -static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, - struct ext4_map_blocks *map, - int flags) -{ - int err = -EIO; - ext4_lblk_t offsets[4]; - Indirect chain[4]; - Indirect *partial; - ext4_fsblk_t goal; - int indirect_blks; - int blocks_to_boundary = 0; - int depth; - int count = 0; - ext4_fsblk_t first_block = 0; - - trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); - J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); - J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); - depth = ext4_block_to_path(inode, map->m_lblk, offsets, - &blocks_to_boundary); - - if (depth == 0) - goto out; - - partial = ext4_get_branch(inode, depth, offsets, chain, &err); - - /* Simplest case - block found, no allocation needed */ - if (!partial) { - first_block = le32_to_cpu(chain[depth - 1].key); - count++; - /*map more blocks*/ - while (count < map->m_len && count <= blocks_to_boundary) { - ext4_fsblk_t blk; - - blk = le32_to_cpu(*(chain[depth-1].p + count)); - - if (blk == first_block + count) - count++; - else - break; - } - goto got_it; - } - - /* Next simple case - plain lookup or failed read of indirect block */ - if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO) - goto cleanup; - - /* - * Okay, we need to do block allocation. - */ - goal = ext4_find_goal(inode, map->m_lblk, partial); - - /* the number of blocks need to allocate for [d,t]indirect blocks */ - indirect_blks = (chain + depth) - partial - 1; - - /* - * Next look up the indirect map to count the totoal number of - * direct blocks to allocate for this branch. - */ - count = ext4_blks_to_allocate(partial, indirect_blks, - map->m_len, blocks_to_boundary); - /* - * Block out ext4_truncate while we alter the tree - */ - err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks, - &count, goal, - offsets + (partial - chain), partial); - - /* - * The ext4_splice_branch call will free and forget any buffers - * on the new chain if there is a failure, but that risks using - * up transaction credits, especially for bitmaps where the - * credits cannot be returned. Can we handle this somehow? We - * may need to return -EAGAIN upwards in the worst case. --sct - */ - if (!err) - err = ext4_splice_branch(handle, inode, map->m_lblk, - partial, indirect_blks, count); - if (err) - goto cleanup; - - map->m_flags |= EXT4_MAP_NEW; - - ext4_update_inode_fsync_trans(handle, inode, 1); -got_it: - map->m_flags |= EXT4_MAP_MAPPED; - map->m_pblk = le32_to_cpu(chain[depth-1].key); - map->m_len = count; - if (count > blocks_to_boundary) - map->m_flags |= EXT4_MAP_BOUNDARY; - err = count; - /* Clean up and exit */ - partial = chain + depth - 1; /* the whole chain */ -cleanup: - while (partial > chain) { - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - partial--; - } -out: - trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, - map->m_pblk, map->m_len, err); - return err; -} - #ifdef CONFIG_QUOTA qsize_t *ext4_get_reserved_space(struct inode *inode) { @@ -1073,33 +244,6 @@ qsize_t *ext4_get_reserved_space(struct inode *inode) /* * Calculate the number of metadata blocks need to reserve - * to allocate a new block at @lblocks for non extent file based file - */ -static int ext4_indirect_calc_metadata_amount(struct inode *inode, - sector_t lblock) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1); - int blk_bits; - - if (lblock < EXT4_NDIR_BLOCKS) - return 0; - - lblock -= EXT4_NDIR_BLOCKS; - - if (ei->i_da_metadata_calc_len && - (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) { - ei->i_da_metadata_calc_len++; - return 0; - } - ei->i_da_metadata_calc_last_lblock = lblock & dind_mask; - ei->i_da_metadata_calc_len = 1; - blk_bits = order_base_2(lblock); - return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1; -} - -/* - * Calculate the number of metadata blocks need to reserve * to allocate a block located at @lblock */ static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) @@ -1107,7 +251,7 @@ static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return ext4_ext_calc_metadata_amount(inode, lblock); - return ext4_indirect_calc_metadata_amount(inode, lblock); + return ext4_ind_calc_metadata_amount(inode, lblock); } /* @@ -1589,16 +733,6 @@ static int do_journal_get_write_access(handle_t *handle, return ret; } -/* - * Truncate blocks that were not used by write. We have to truncate the - * pagecache as well so that corresponding buffers get properly unmapped. - */ -static void ext4_truncate_failed_write(struct inode *inode) -{ - truncate_inode_pages(inode->i_mapping, inode->i_size); - ext4_truncate(inode); -} - static int ext4_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); static int ext4_write_begin(struct file *file, struct address_space *mapping, @@ -1863,6 +997,7 @@ static int ext4_journalled_write_end(struct file *file, if (new_i_size > inode->i_size) i_size_write(inode, pos+copied); ext4_set_inode_state(inode, EXT4_STATE_JDATA); + EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; if (new_i_size > EXT4_I(inode)->i_disksize) { ext4_update_i_disksize(inode, new_i_size); ret2 = ext4_mark_inode_dirty(handle, inode); @@ -2571,6 +1706,7 @@ static int __ext4_journalled_writepage(struct page *page, write_end_fn); if (ret == 0) ret = err; + EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -3450,112 +2586,6 @@ static int ext4_releasepage(struct page *page, gfp_t wait) } /* - * O_DIRECT for ext3 (or indirect map) based files - * - * If the O_DIRECT write will extend the file then add this inode to the - * orphan list. So recovery will truncate it back to the original size - * if the machine crashes during the write. - * - * If the O_DIRECT write is intantiating holes inside i_size and the machine - * crashes then stale disk data _may_ be exposed inside the file. But current - * VFS code falls back into buffered path in that case so we are safe. - */ -static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - struct ext4_inode_info *ei = EXT4_I(inode); - handle_t *handle; - ssize_t ret; - int orphan = 0; - size_t count = iov_length(iov, nr_segs); - int retries = 0; - - if (rw == WRITE) { - loff_t final_size = offset + count; - - if (final_size > inode->i_size) { - /* Credits for sb + inode write */ - handle = ext4_journal_start(inode, 2); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - ret = ext4_orphan_add(handle, inode); - if (ret) { - ext4_journal_stop(handle); - goto out; - } - orphan = 1; - ei->i_disksize = inode->i_size; - ext4_journal_stop(handle); - } - } - -retry: - if (rw == READ && ext4_should_dioread_nolock(inode)) - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block, NULL, NULL, 0); - else { - ret = blockdev_direct_IO(rw, iocb, inode, iov, - offset, nr_segs, ext4_get_block); - - if (unlikely((rw & WRITE) && ret < 0)) { - loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); - - if (end > isize) - ext4_truncate_failed_write(inode); - } - } - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry; - - if (orphan) { - int err; - - /* Credits for sb + inode write */ - handle = ext4_journal_start(inode, 2); - if (IS_ERR(handle)) { - /* This is really bad luck. We've written the data - * but cannot extend i_size. Bail out and pretend - * the write failed... */ - ret = PTR_ERR(handle); - if (inode->i_nlink) - ext4_orphan_del(NULL, inode); - - goto out; - } - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - if (ret > 0) { - loff_t end = offset + ret; - if (end > inode->i_size) { - ei->i_disksize = end; - i_size_write(inode, end); - /* - * We're going to return a positive `ret' - * here due to non-zero-length I/O, so there's - * no way of reporting error returns from - * ext4_mark_inode_dirty() to userspace. So - * ignore it. - */ - ext4_mark_inode_dirty(handle, inode); - } - } - err = ext4_journal_stop(handle); - if (ret == 0) - ret = err; - } -out: - return ret; -} - -/* * ext4_get_block used when preparing for a DIO write or buffer write. * We allocate an uinitialized extent if blocks haven't been allocated. * The extent will be converted to initialized after the IO is complete. @@ -4033,383 +3063,6 @@ unlock: return err; } -/* - * Probably it should be a library function... search for first non-zero word - * or memcmp with zero_page, whatever is better for particular architecture. - * Linus? - */ -static inline int all_zeroes(__le32 *p, __le32 *q) -{ - while (p < q) - if (*p++) - return 0; - return 1; -} - -/** - * ext4_find_shared - find the indirect blocks for partial truncation. - * @inode: inode in question - * @depth: depth of the affected branch - * @offsets: offsets of pointers in that branch (see ext4_block_to_path) - * @chain: place to store the pointers to partial indirect blocks - * @top: place to the (detached) top of branch - * - * This is a helper function used by ext4_truncate(). - * - * When we do truncate() we may have to clean the ends of several - * indirect blocks but leave the blocks themselves alive. Block is - * partially truncated if some data below the new i_size is referred - * from it (and it is on the path to the first completely truncated - * data block, indeed). We have to free the top of that path along - * with everything to the right of the path. Since no allocation - * past the truncation point is possible until ext4_truncate() - * finishes, we may safely do the latter, but top of branch may - * require special attention - pageout below the truncation point - * might try to populate it. - * - * We atomically detach the top of branch from the tree, store the - * block number of its root in *@top, pointers to buffer_heads of - * partially truncated blocks - in @chain[].bh and pointers to - * their last elements that should not be removed - in - * @chain[].p. Return value is the pointer to last filled element - * of @chain. - * - * The work left to caller to do the actual freeing of subtrees: - * a) free the subtree starting from *@top - * b) free the subtrees whose roots are stored in - * (@chain[i].p+1 .. end of @chain[i].bh->b_data) - * c) free the subtrees growing from the inode past the @chain[0]. - * (no partially truncated stuff there). */ - -static Indirect *ext4_find_shared(struct inode *inode, int depth, - ext4_lblk_t offsets[4], Indirect chain[4], - __le32 *top) -{ - Indirect *partial, *p; - int k, err; - - *top = 0; - /* Make k index the deepest non-null offset + 1 */ - for (k = depth; k > 1 && !offsets[k-1]; k--) - ; - partial = ext4_get_branch(inode, k, offsets, chain, &err); - /* Writer: pointers */ - if (!partial) - partial = chain + k-1; - /* - * If the branch acquired continuation since we've looked at it - - * fine, it should all survive and (new) top doesn't belong to us. - */ - if (!partial->key && *partial->p) - /* Writer: end */ - goto no_top; - for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--) - ; - /* - * OK, we've found the last block that must survive. The rest of our - * branch should be detached before unlocking. However, if that rest - * of branch is all ours and does not grow immediately from the inode - * it's easier to cheat and just decrement partial->p. - */ - if (p == chain + k - 1 && p > chain) { - p->p--; - } else { - *top = *p->p; - /* Nope, don't do this in ext4. Must leave the tree intact */ -#if 0 - *p->p = 0; -#endif - } - /* Writer: end */ - - while (partial > p) { - brelse(partial->bh); - partial--; - } -no_top: - return partial; -} - -/* - * Zero a number of block pointers in either an inode or an indirect block. - * If we restart the transaction we must again get write access to the - * indirect block for further modification. - * - * We release `count' blocks on disk, but (last - first) may be greater - * than `count' because there can be holes in there. - * - * Return 0 on success, 1 on invalid block range - * and < 0 on fatal error. - */ -static int ext4_clear_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, - ext4_fsblk_t block_to_free, - unsigned long count, __le32 *first, - __le32 *last) -{ - __le32 *p; - int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED; - int err; - - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - flags |= EXT4_FREE_BLOCKS_METADATA; - - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { - EXT4_ERROR_INODE(inode, "attempt to clear invalid " - "blocks %llu len %lu", - (unsigned long long) block_to_free, count); - return 1; - } - - if (try_to_extend_transaction(handle, inode)) { - if (bh) { - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, inode, bh); - if (unlikely(err)) - goto out_err; - } - err = ext4_mark_inode_dirty(handle, inode); - if (unlikely(err)) - goto out_err; - err = ext4_truncate_restart_trans(handle, inode, - blocks_for_truncate(inode)); - if (unlikely(err)) - goto out_err; - if (bh) { - BUFFER_TRACE(bh, "retaking write access"); - err = ext4_journal_get_write_access(handle, bh); - if (unlikely(err)) - goto out_err; - } - } - - for (p = first; p < last; p++) - *p = 0; - - ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); - return 0; -out_err: - ext4_std_error(inode->i_sb, err); - return err; -} - -/** - * ext4_free_data - free a list of data blocks - * @handle: handle for this transaction - * @inode: inode we are dealing with - * @this_bh: indirect buffer_head which contains *@first and *@last - * @first: array of block numbers - * @last: points immediately past the end of array - * - * We are freeing all blocks referred from that array (numbers are stored as - * little-endian 32-bit) and updating @inode->i_blocks appropriately. - * - * We accumulate contiguous runs of blocks to free. Conveniently, if these - * blocks are contiguous then releasing them at one time will only affect one - * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't - * actually use a lot of journal space. - * - * @this_bh will be %NULL if @first and @last point into the inode's direct - * block pointers. - */ -static void ext4_free_data(handle_t *handle, struct inode *inode, - struct buffer_head *this_bh, - __le32 *first, __le32 *last) -{ - ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */ - unsigned long count = 0; /* Number of blocks in the run */ - __le32 *block_to_free_p = NULL; /* Pointer into inode/ind - corresponding to - block_to_free */ - ext4_fsblk_t nr; /* Current block # */ - __le32 *p; /* Pointer into inode/ind - for current block */ - int err = 0; - - if (this_bh) { /* For indirect block */ - BUFFER_TRACE(this_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, this_bh); - /* Important: if we can't update the indirect pointers - * to the blocks, we can't free them. */ - if (err) - return; - } - - for (p = first; p < last; p++) { - nr = le32_to_cpu(*p); - if (nr) { - /* accumulate blocks to free if they're contiguous */ - if (count == 0) { - block_to_free = nr; - block_to_free_p = p; - count = 1; - } else if (nr == block_to_free + count) { - count++; - } else { - err = ext4_clear_blocks(handle, inode, this_bh, - block_to_free, count, - block_to_free_p, p); - if (err) - break; - block_to_free = nr; - block_to_free_p = p; - count = 1; - } - } - } - - if (!err && count > 0) - err = ext4_clear_blocks(handle, inode, this_bh, block_to_free, - count, block_to_free_p, p); - if (err < 0) - /* fatal error */ - return; - - if (this_bh) { - BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata"); - - /* - * The buffer head should have an attached journal head at this - * point. However, if the data is corrupted and an indirect - * block pointed to itself, it would have been detached when - * the block was cleared. Check for this instead of OOPSing. - */ - if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh)) - ext4_handle_dirty_metadata(handle, inode, this_bh); - else - EXT4_ERROR_INODE(inode, - "circular indirect block detected at " - "block %llu", - (unsigned long long) this_bh->b_blocknr); - } -} - -/** - * ext4_free_branches - free an array of branches - * @handle: JBD handle for this transaction - * @inode: inode we are dealing with - * @parent_bh: the buffer_head which contains *@first and *@last - * @first: array of block numbers - * @last: pointer immediately past the end of array - * @depth: depth of the branches to free - * - * We are freeing all blocks referred from these branches (numbers are - * stored as little-endian 32-bit) and updating @inode->i_blocks - * appropriately. - */ -static void ext4_free_branches(handle_t *handle, struct inode *inode, - struct buffer_head *parent_bh, - __le32 *first, __le32 *last, int depth) -{ - ext4_fsblk_t nr; - __le32 *p; - - if (ext4_handle_is_aborted(handle)) - return; - - if (depth--) { - struct buffer_head *bh; - int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); - p = last; - while (--p >= first) { - nr = le32_to_cpu(*p); - if (!nr) - continue; /* A hole */ - - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { - EXT4_ERROR_INODE(inode, - "invalid indirect mapped " - "block %lu (level %d)", - (unsigned long) nr, depth); - break; - } - - /* Go read the buffer for the next level down */ - bh = sb_bread(inode->i_sb, nr); - - /* - * A read failure? Report error and clear slot - * (should be rare). - */ - if (!bh) { - EXT4_ERROR_INODE_BLOCK(inode, nr, - "Read failure"); - continue; - } - - /* This zaps the entire block. Bottom up. */ - BUFFER_TRACE(bh, "free child branches"); - ext4_free_branches(handle, inode, bh, - (__le32 *) bh->b_data, - (__le32 *) bh->b_data + addr_per_block, - depth); - brelse(bh); - - /* - * Everything below this this pointer has been - * released. Now let this top-of-subtree go. - * - * We want the freeing of this indirect block to be - * atomic in the journal with the updating of the - * bitmap block which owns it. So make some room in - * the journal. - * - * We zero the parent pointer *after* freeing its - * pointee in the bitmaps, so if extend_transaction() - * for some reason fails to put the bitmap changes and - * the release into the same transaction, recovery - * will merely complain about releasing a free block, - * rather than leaking blocks. - */ - if (ext4_handle_is_aborted(handle)) - return; - if (try_to_extend_transaction(handle, inode)) { - ext4_mark_inode_dirty(handle, inode); - ext4_truncate_restart_trans(handle, inode, - blocks_for_truncate(inode)); - } - - /* - * The forget flag here is critical because if - * we are journaling (and not doing data - * journaling), we have to make sure a revoke - * record is written to prevent the journal - * replay from overwriting the (former) - * indirect block if it gets reallocated as a - * data block. This must happen in the same - * transaction where the data blocks are - * actually freed. - */ - ext4_free_blocks(handle, inode, NULL, nr, 1, - EXT4_FREE_BLOCKS_METADATA| - EXT4_FREE_BLOCKS_FORGET); - - if (parent_bh) { - /* - * The block which we have just freed is - * pointed to by an indirect block: journal it - */ - BUFFER_TRACE(parent_bh, "get_write_access"); - if (!ext4_journal_get_write_access(handle, - parent_bh)){ - *p = 0; - BUFFER_TRACE(parent_bh, - "call ext4_handle_dirty_metadata"); - ext4_handle_dirty_metadata(handle, - inode, - parent_bh); - } - } - } - } else { - /* We have reached the bottom of the tree. */ - BUFFER_TRACE(parent_bh, "free data blocks"); - ext4_free_data(handle, inode, parent_bh, first, last); - } -} - int ext4_can_truncate(struct inode *inode) { if (S_ISREG(inode->i_mode)) @@ -4476,19 +3129,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) */ void ext4_truncate(struct inode *inode) { - handle_t *handle; - struct ext4_inode_info *ei = EXT4_I(inode); - __le32 *i_data = ei->i_data; - int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); - struct address_space *mapping = inode->i_mapping; - ext4_lblk_t offsets[4]; - Indirect chain[4]; - Indirect *partial; - __le32 nr = 0; - int n = 0; - ext4_lblk_t last_block, max_block; - unsigned blocksize = inode->i_sb->s_blocksize; - trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) @@ -4499,149 +3139,11 @@ void ext4_truncate(struct inode *inode) if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_ext_truncate(inode); - trace_ext4_truncate_exit(inode); - return; - } - - handle = start_transaction(inode); - if (IS_ERR(handle)) - return; /* AKPM: return what? */ - - last_block = (inode->i_size + blocksize-1) - >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); - max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) - >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); - - if (inode->i_size & (blocksize - 1)) - if (ext4_block_truncate_page(handle, mapping, inode->i_size)) - goto out_stop; - - if (last_block != max_block) { - n = ext4_block_to_path(inode, last_block, offsets, NULL); - if (n == 0) - goto out_stop; /* error */ - } - - /* - * OK. This truncate is going to happen. We add the inode to the - * orphan list, so that if this truncate spans multiple transactions, - * and we crash, we will resume the truncate when the filesystem - * recovers. It also marks the inode dirty, to catch the new size. - * - * Implication: the file must always be in a sane, consistent - * truncatable state while each transaction commits. - */ - if (ext4_orphan_add(handle, inode)) - goto out_stop; - - /* - * From here we block out all ext4_get_block() callers who want to - * modify the block allocation tree. - */ - down_write(&ei->i_data_sem); - - ext4_discard_preallocations(inode); - - /* - * The orphan list entry will now protect us from any crash which - * occurs before the truncate completes, so it is now safe to propagate - * the new, shorter inode size (held for now in i_size) into the - * on-disk inode. We do this via i_disksize, which is the value which - * ext4 *really* writes onto the disk inode. - */ - ei->i_disksize = inode->i_size; - - if (last_block == max_block) { - /* - * It is unnecessary to free any data blocks if last_block is - * equal to the indirect block limit. - */ - goto out_unlock; - } else if (n == 1) { /* direct blocks */ - ext4_free_data(handle, inode, NULL, i_data+offsets[0], - i_data + EXT4_NDIR_BLOCKS); - goto do_indirects; - } - - partial = ext4_find_shared(inode, n, offsets, chain, &nr); - /* Kill the top of shared branch (not detached) */ - if (nr) { - if (partial == chain) { - /* Shared branch grows from the inode */ - ext4_free_branches(handle, inode, NULL, - &nr, &nr+1, (chain+n-1) - partial); - *partial->p = 0; - /* - * We mark the inode dirty prior to restart, - * and prior to stop. No need for it here. - */ - } else { - /* Shared branch grows from an indirect block */ - BUFFER_TRACE(partial->bh, "get_write_access"); - ext4_free_branches(handle, inode, partial->bh, - partial->p, - partial->p+1, (chain+n-1) - partial); - } - } - /* Clear the ends of indirect blocks on the shared branch */ - while (partial > chain) { - ext4_free_branches(handle, inode, partial->bh, partial->p + 1, - (__le32*)partial->bh->b_data+addr_per_block, - (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - partial--; - } -do_indirects: - /* Kill the remaining (whole) subtrees */ - switch (offsets[0]) { - default: - nr = i_data[EXT4_IND_BLOCK]; - if (nr) { - ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); - i_data[EXT4_IND_BLOCK] = 0; - } - case EXT4_IND_BLOCK: - nr = i_data[EXT4_DIND_BLOCK]; - if (nr) { - ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); - i_data[EXT4_DIND_BLOCK] = 0; - } - case EXT4_DIND_BLOCK: - nr = i_data[EXT4_TIND_BLOCK]; - if (nr) { - ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); - i_data[EXT4_TIND_BLOCK] = 0; - } - case EXT4_TIND_BLOCK: - ; - } - -out_unlock: - up_write(&ei->i_data_sem); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - - /* - * In a multi-transaction truncate, we only make the final transaction - * synchronous - */ - if (IS_SYNC(inode)) - ext4_handle_sync(handle); -out_stop: - /* - * If this was a simple ftruncate(), and the file will remain alive - * then we need to clear up the orphan record which we created above. - * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the - * orphan info for us. - */ - if (inode->i_nlink) - ext4_orphan_del(handle, inode); + else + ext4_ind_truncate(inode); - ext4_journal_stop(handle); trace_ext4_truncate_exit(inode); } @@ -5012,7 +3514,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) (S_ISLNK(inode->i_mode) && !ext4_inode_is_fast_symlink(inode))) { /* Validate block references which are part of inode */ - ret = ext4_check_inode_blockref(inode); + ret = ext4_ind_check_inode(inode); } if (ret) goto bad_inode; @@ -5459,34 +3961,10 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, return 0; } -static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks, - int chunk) -{ - int indirects; - - /* if nrblocks are contiguous */ - if (chunk) { - /* - * With N contiguous data blocks, we need at most - * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks, - * 2 dindirect blocks, and 1 tindirect block - */ - return DIV_ROUND_UP(nrblocks, - EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; - } - /* - * if nrblocks are not contiguous, worse case, each block touch - * a indirect block, and each indirect block touch a double indirect - * block, plus a triple indirect block - */ - indirects = nrblocks * 2 + 1; - return indirects; -} - static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) { if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - return ext4_indirect_trans_blocks(inode, nrblocks, chunk); + return ext4_ind_trans_blocks(inode, nrblocks, chunk); return ext4_ext_index_trans_blocks(inode, nrblocks, chunk); } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 808c554..f18bfe3 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -202,8 +202,9 @@ setversion_out: struct super_block *sb = inode->i_sb; int err, err2=0; - if (!capable(CAP_SYS_RESOURCE)) - return -EPERM; + err = ext4_resize_begin(sb); + if (err) + return err; if (get_user(n_blocks_count, (__u32 __user *)arg)) return -EFAULT; @@ -221,6 +222,7 @@ setversion_out: if (err == 0) err = err2; mnt_drop_write(filp->f_path.mnt); + ext4_resize_end(sb); return err; } @@ -271,8 +273,9 @@ mext_out: struct super_block *sb = inode->i_sb; int err, err2=0; - if (!capable(CAP_SYS_RESOURCE)) - return -EPERM; + err = ext4_resize_begin(sb); + if (err) + return err; if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, sizeof(input))) @@ -291,6 +294,7 @@ mext_out: if (err == 0) err = err2; mnt_drop_write(filp->f_path.mnt); + ext4_resize_end(sb); return err; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 6ed859d..17a5a57 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -75,8 +75,8 @@ * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc - * space we will consume the particular prealloc space. This make sure that - * that the we have contiguous physical blocks representing the file blocks + * space we will consume the particular prealloc space. This makes sure that + * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except @@ -84,7 +84,7 @@ * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group - * prealloc space. These are per CPU prealloc list repreasented as + * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * @@ -128,12 +128,13 @@ * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is * 512 blocks. This can be tuned via - * /sys/fs/ext4/<partition/mb_group_prealloc. The value is represented in + * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the - * stripe value (sbi->s_stripe) + * the smallest multiple of the stripe value (sbi->s_stripe) which is + * greater than the default mb_group_prealloc. * - * The regular allocator(using the buddy cache) supports few tunables. + * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan @@ -152,7 +153,7 @@ * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it - * can used for allocation. ext4_mb_good_group explains how the groups are + * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * Both the prealloc space are getting populated as above. So for the first @@ -492,10 +493,11 @@ static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { - printk(KERN_ERR "corruption in group %u " - "at byte %u(%u): %x in copy != %x " - "on disk/prealloc\n", - e4b->bd_group, i, i * 8, b1[i], b2[i]); + ext4_msg(e4b->bd_sb, KERN_ERR, + "corruption in group %u " + "at byte %u(%u): %x in copy != %x " + "on disk/prealloc", + e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } @@ -1125,7 +1127,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, grp = ext4_get_group_info(sb, group); e4b->bd_blkbits = sb->s_blocksize_bits; - e4b->bd_info = ext4_get_group_info(sb, group); + e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_page = NULL; @@ -1281,7 +1283,7 @@ static void mb_clear_bits(void *bm, int cur, int len) } } -static void mb_set_bits(void *bm, int cur, int len) +void ext4_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1510,7 +1512,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); - mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0); + ext4_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0); mb_check_buddy(e4b); return ret; @@ -2223,8 +2225,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_KERNEL); if (meta_group_info == NULL) { - printk(KERN_ERR "EXT4-fs: can't allocate mem for a " - "buddy group\n"); + ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate mem " + "for a buddy group"); goto exit_meta_group_info; } sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = @@ -2237,7 +2239,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL); if (meta_group_info[i] == NULL) { - printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n"); + ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate buddy mem"); goto exit_group_info; } memset(meta_group_info[i], 0, kmem_cache_size(cachep)); @@ -2279,8 +2281,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, exit_group_info: /* If a meta_group_info table has been allocated, release it now */ - if (group % EXT4_DESC_PER_BLOCK(sb) == 0) + if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]); + sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL; + } exit_meta_group_info: return -ENOMEM; } /* ext4_mb_add_groupinfo */ @@ -2328,23 +2332,26 @@ static int ext4_mb_init_backend(struct super_block *sb) /* An 8TB filesystem with 64-bit pointers requires a 4096 byte * kmalloc. A 128kb malloc should suffice for a 256TB filesystem. * So a two level scheme suffices for now. */ - sbi->s_group_info = kzalloc(array_size, GFP_KERNEL); + sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL); if (sbi->s_group_info == NULL) { - printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n"); + ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { - printk(KERN_ERR "EXT4-fs: can't get new inode\n"); + ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } - sbi->s_buddy_cache->i_ino = get_next_ino(); + /* To avoid potentially colliding with an valid on-disk inode number, + * use EXT4_BAD_INO for the buddy cache inode number. This inode is + * not in the inode hash, so it should never be found by iget(), but + * this will avoid confusion if it ever shows up during debugging. */ + sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { - printk(KERN_ERR - "EXT4-fs: can't read descriptor %u\n", i); + ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) @@ -2362,7 +2369,7 @@ err_freebuddy: kfree(sbi->s_group_info[i]); iput(sbi->s_buddy_cache); err_freesgi: - kfree(sbi->s_group_info); + ext4_kvfree(sbi->s_group_info); return -ENOMEM; } @@ -2404,14 +2411,15 @@ static int ext4_groupinfo_create_slab(size_t size) slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); + ext4_groupinfo_caches[cache_index] = cachep; + mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { - printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n"); + printk(KERN_EMERG + "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } - ext4_groupinfo_caches[cache_index] = cachep; - return 0; } @@ -2457,12 +2465,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) i++; } while (i <= sb->s_blocksize_bits + 1); - /* init file for buddy data */ - ret = ext4_mb_init_backend(sb); - if (ret != 0) { - goto out; - } - spin_lock_init(&sbi->s_md_lock); spin_lock_init(&sbi->s_bal_lock); @@ -2472,6 +2474,18 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC; + /* + * If there is a s_stripe > 1, then we set the s_mb_group_prealloc + * to the lowest multiple of s_stripe which is bigger than + * the s_mb_group_prealloc as determined above. We want + * the preallocation size to be an exact multiple of the + * RAID stripe size so that preallocations don't fragment + * the stripes. + */ + if (sbi->s_stripe > 1) { + sbi->s_mb_group_prealloc = roundup( + sbi->s_mb_group_prealloc, sbi->s_stripe); + } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { @@ -2487,6 +2501,12 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) spin_lock_init(&lg->lg_prealloc_lock); } + /* init file for buddy data */ + ret = ext4_mb_init_backend(sb); + if (ret != 0) { + goto out; + } + if (sbi->s_proc) proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, &ext4_mb_seq_groups_fops, sb); @@ -2544,32 +2564,32 @@ int ext4_mb_release(struct super_block *sb) EXT4_DESC_PER_BLOCK_BITS(sb); for (i = 0; i < num_meta_group_infos; i++) kfree(sbi->s_group_info[i]); - kfree(sbi->s_group_info); + ext4_kvfree(sbi->s_group_info); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); if (sbi->s_buddy_cache) iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { - printk(KERN_INFO - "EXT4-fs: mballoc: %u blocks %u reqs (%u success)\n", + ext4_msg(sb, KERN_INFO, + "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); - printk(KERN_INFO - "EXT4-fs: mballoc: %u extents scanned, %u goal hits, " - "%u 2^N hits, %u breaks, %u lost\n", + ext4_msg(sb, KERN_INFO, + "mballoc: %u extents scanned, %u goal hits, " + "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); - printk(KERN_INFO - "EXT4-fs: mballoc: %lu generated and it took %Lu\n", - sbi->s_mb_buddies_generated++, + ext4_msg(sb, KERN_INFO, + "mballoc: %lu generated and it took %Lu", + sbi->s_mb_buddies_generated, sbi->s_mb_generation_time); - printk(KERN_INFO - "EXT4-fs: mballoc: %u preallocated, %u discarded\n", + ext4_msg(sb, KERN_INFO, + "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } @@ -2628,6 +2648,15 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) rb_erase(&entry->node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count); + /* + * Clear the trimmed flag for the group so that the next + * ext4_trim_fs can trim it. + * If the volume is mounted with -o discard, online discard + * is supported and the free blocks will be trimmed online. + */ + if (!test_opt(sb, DISCARD)) + EXT4_MB_GRP_CLEAR_TRIMMED(db); + if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() @@ -2771,8 +2800,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); + ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) @@ -2790,7 +2819,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } } #endif - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len); + ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_blks_set(sb, gdp, @@ -2830,8 +2860,9 @@ out_err: /* * here we normalize request for locality group - * Group request are normalized to s_strip size if we set the same via mount - * option. If not we set it to s_mb_group_prealloc which can be configured via + * Group request are normalized to s_mb_group_prealloc, which goes to + * s_strip if we set the same via mount option. + * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? @@ -2842,10 +2873,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); - if (EXT4_SB(sb)->s_stripe) - ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe; - else - ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; + ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(1, "#%u: goal %u blocks for locality group\n", current->pid, ac->ac_g_ex.fe_len); } @@ -3001,9 +3029,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, if (start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical) { - printk(KERN_ERR "start %lu, size %lu, fe_logical %lu\n", - (unsigned long) start, (unsigned long) size, - (unsigned long) ac->ac_o_ex.fe_logical); + ext4_msg(ac->ac_sb, KERN_ERR, + "start %lu, size %lu, fe_logical %lu", + (unsigned long) start, (unsigned long) size, + (unsigned long) ac->ac_o_ex.fe_logical); } BUG_ON(start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical); @@ -3262,7 +3291,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, node); - mb_set_bits(bitmap, entry->start_blk, entry->count); + ext4_set_bits(bitmap, entry->start_blk, entry->count); n = rb_next(n); } return; @@ -3304,7 +3333,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); - mb_set_bits(bitmap, start, len); + ext4_set_bits(bitmap, start, len); preallocated += len; count++; } @@ -3584,10 +3613,11 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, bit = next + 1; } if (free != pa->pa_free) { - printk(KERN_CRIT "pa %p: logic %lu, phys. %lu, len %lu\n", - pa, (unsigned long) pa->pa_lstart, - (unsigned long) pa->pa_pstart, - (unsigned long) pa->pa_len); + ext4_msg(e4b->bd_sb, KERN_CRIT, + "pa %p: logic %lu, phys. %lu, len %lu", + pa, (unsigned long) pa->pa_lstart, + (unsigned long) pa->pa_pstart, + (unsigned long) pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* @@ -3775,7 +3805,8 @@ repeat: * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); spin_unlock(&ei->i_prealloc_lock); - printk(KERN_ERR "uh-oh! used pa while discarding\n"); + ext4_msg(sb, KERN_ERR, + "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; @@ -3852,12 +3883,13 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) return; - printk(KERN_ERR "EXT4-fs: Can't allocate:" - " Allocation context details:\n"); - printk(KERN_ERR "EXT4-fs: status %d flags %d\n", + ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: Can't allocate:" + " Allocation context details:"); + ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: status %d flags %d", ac->ac_status, ac->ac_flags); - printk(KERN_ERR "EXT4-fs: orig %lu/%lu/%lu@%lu, goal %lu/%lu/%lu@%lu, " - "best %lu/%lu/%lu@%lu cr %d\n", + ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: orig %lu/%lu/%lu@%lu, " + "goal %lu/%lu/%lu@%lu, " + "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, @@ -3871,9 +3903,9 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); - printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned, - ac->ac_found); - printk(KERN_ERR "EXT4-fs: groups: \n"); + ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: %lu scanned, %d found", + ac->ac_ex_scanned, ac->ac_found); + ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: groups: "); ngroups = ext4_get_groups_count(sb); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); @@ -4637,7 +4669,7 @@ do_more: } ext4_mark_super_dirty(sb); error_return: - if (freed) + if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, freed); brelse(bitmap_bh); ext4_std_error(sb, err); @@ -4645,7 +4677,7 @@ error_return: } /** - * ext4_add_groupblocks() -- Add given blocks to an existing group + * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physcial block to add to the block group @@ -4653,7 +4685,7 @@ error_return: * * This marks the blocks as free in the bitmap and buddy. */ -void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, +int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh = NULL; @@ -4666,25 +4698,35 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, struct ext4_buddy e4b; int err = 0, ret, blk_free_count; ext4_grpblk_t blocks_freed; - struct ext4_group_info *grp; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); + if (count == 0) + return 0; + ext4_get_group_no_and_offset(sb, block, &block_group, &bit); - grp = ext4_get_group_info(sb, block_group); /* * Check to see if we are freeing blocks across a group * boundary. */ - if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) + if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) { + ext4_warning(sb, "too much blocks added to group %u\n", + block_group); + err = -EINVAL; goto error_return; + } bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (!bitmap_bh) + if (!bitmap_bh) { + err = -EIO; goto error_return; + } + desc = ext4_get_group_desc(sb, block_group, &gd_bh); - if (!desc) + if (!desc) { + err = -EIO; goto error_return; + } if (in_range(ext4_block_bitmap(sb, desc), block, count) || in_range(ext4_inode_bitmap(sb, desc), block, count) || @@ -4694,6 +4736,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); + err = -EINVAL; goto error_return; } @@ -4762,7 +4805,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, error_return: brelse(bitmap_bh); ext4_std_error(sb, err); - return; + return err; } /** @@ -4782,6 +4825,8 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count, { struct ext4_free_extent ex; + trace_ext4_trim_extent(sb, group, start, count); + assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; @@ -4802,7 +4847,7 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count, /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system - * @e4b: ext4 buddy + * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count @@ -4823,10 +4868,12 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t minblocks) { void *bitmap; - ext4_grpblk_t next, count = 0; + ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; int ret; + trace_ext4_trim_all_free(sb, group, start, max); + ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_error(sb, "Error in loading buddy " @@ -4836,6 +4883,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); + if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && + minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) + goto out; + start = (e4b.bd_info->bb_first_free > start) ? e4b.bd_info->bb_first_free : start; @@ -4850,6 +4901,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, next - start, group, &e4b); count += next - start; } + free_count += next - start; start = next + 1; if (fatal_signal_pending(current)) { @@ -4863,9 +4915,13 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); } - if ((e4b.bd_info->bb_free - count) < minblocks) + if ((e4b.bd_info->bb_free - free_count) < minblocks) break; } + + if (!ret) + EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); +out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -4904,6 +4960,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb))) return -EINVAL; + if (start + len <= first_data_blk) + goto out; if (start < first_data_blk) { len -= first_data_blk - start; start = first_data_blk; @@ -4952,5 +5010,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } range->len = trimmed * sb->s_blocksize; + if (!ret) + atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + +out: return ret; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 20b5e7b..9d4a636 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -187,7 +187,6 @@ struct ext4_allocation_context { __u16 ac_flags; /* allocation hints */ __u8 ac_status; __u8 ac_criteria; - __u8 ac_repeats; __u8 ac_2order; /* if request is to allocate 2^N blocks and * N > 0, the field stores N, otherwise 0 */ __u8 ac_op; /* operation, for history only */ diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 8c9baba..565a154 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -289,7 +289,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent while (len--) printk("%c", *name++); ext4fs_dirhash(de->name, de->name_len, &h); printk(":%x.%u ", h.hash, - ((char *) de - base)); + (unsigned) ((char *) de - base)); } space += EXT4_DIR_REC_LEN(de->name_len); names++; @@ -1013,7 +1013,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q *err = -ENOENT; errout: - dxtrace(printk(KERN_DEBUG "%s not found\n", name)); + dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name)); dx_release (frames); return NULL; } @@ -1985,18 +1985,11 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) if (!list_empty(&EXT4_I(inode)->i_orphan)) goto out_unlock; - /* Orphan handling is only valid for files with data blocks - * being truncated, or files being unlinked. */ - - /* @@@ FIXME: Observation from aviro: - * I think I can trigger J_ASSERT in ext4_orphan_add(). We block - * here (on s_orphan_lock), so race with ext4_link() which might bump - * ->i_nlink. For, say it, character device. Not a regular file, - * not a directory, not a symlink and ->i_nlink > 0. - * - * tytso, 4/25/2009: I'm not sure how that could happen; - * shouldn't the fs core protect us from these sort of - * unlink()/link() races? + /* + * Orphan handling is only valid for files with data blocks + * being truncated, or files being unlinked. Note that we either + * hold i_mutex, or the inode can not be referenced from outside, + * so i_nlink should not be bumped due to race */ J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 7bb8f76..430c401 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -285,11 +285,7 @@ static int io_submit_init(struct ext4_io_submit *io, io_end = ext4_init_io_end(inode, GFP_NOFS); if (!io_end) return -ENOMEM; - do { - bio = bio_alloc(GFP_NOIO, nvecs); - nvecs >>= 1; - } while (bio == NULL); - + bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES)); bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; bio->bi_private = io->io_end = io_end; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 80bbc9c..707d3f1 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -16,6 +16,35 @@ #include "ext4_jbd2.h" +int ext4_resize_begin(struct super_block *sb) +{ + int ret = 0; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + /* + * We are not allowed to do online-resizing on a filesystem mounted + * with error, because it can destroy the filesystem easily. + */ + if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + ext4_warning(sb, "There are errors in the filesystem, " + "so online resizing is not allowed\n"); + return -EPERM; + } + + if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags)) + ret = -EBUSY; + + return ret; +} + +void ext4_resize_end(struct super_block *sb) +{ + clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags); + smp_mb__after_clear_bit(); +} + #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) @@ -118,10 +147,8 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, brelse(bh); bh = ERR_PTR(err); } else { - lock_buffer(bh); memset(bh->b_data, 0, sb->s_blocksize); set_buffer_uptodate(bh); - unlock_buffer(bh); } return bh; @@ -132,8 +159,7 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, * If that fails, restart the transaction & regain write access for the * buffer head which is used for block_bitmap modifications. */ -static int extend_or_restart_transaction(handle_t *handle, int thresh, - struct buffer_head *bh) +static int extend_or_restart_transaction(handle_t *handle, int thresh) { int err; @@ -144,9 +170,8 @@ static int extend_or_restart_transaction(handle_t *handle, int thresh, if (err < 0) return err; if (err) { - if ((err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) - return err; - if ((err = ext4_journal_get_write_access(handle, bh))) + err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA); + if (err) return err; } @@ -181,21 +206,7 @@ static int setup_new_group_blocks(struct super_block *sb, if (IS_ERR(handle)) return PTR_ERR(handle); - mutex_lock(&sbi->s_resize_lock); - if (input->group != sbi->s_groups_count) { - err = -EBUSY; - goto exit_journal; - } - - if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) { - err = PTR_ERR(bh); - goto exit_journal; - } - - if (ext4_bg_has_super(sb, input->group)) { - ext4_debug("mark backup superblock %#04llx (+0)\n", start); - ext4_set_bit(0, bh->b_data); - } + BUG_ON(input->group != sbi->s_groups_count); /* Copy all of the GDT blocks into the backup in this group */ for (i = 0, bit = 1, block = start + 1; @@ -203,29 +214,26 @@ static int setup_new_group_blocks(struct super_block *sb, struct buffer_head *gdb; ext4_debug("update backup group %#04llx (+%d)\n", block, bit); - - if ((err = extend_or_restart_transaction(handle, 1, bh))) - goto exit_bh; + err = extend_or_restart_transaction(handle, 1); + if (err) + goto exit_journal; gdb = sb_getblk(sb, block); if (!gdb) { err = -EIO; - goto exit_bh; + goto exit_journal; } if ((err = ext4_journal_get_write_access(handle, gdb))) { brelse(gdb); - goto exit_bh; + goto exit_journal; } - lock_buffer(gdb); memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size); set_buffer_uptodate(gdb); - unlock_buffer(gdb); err = ext4_handle_dirty_metadata(handle, NULL, gdb); if (unlikely(err)) { brelse(gdb); - goto exit_bh; + goto exit_journal; } - ext4_set_bit(bit, bh->b_data); brelse(gdb); } @@ -235,9 +243,22 @@ static int setup_new_group_blocks(struct super_block *sb, err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb, GFP_NOFS); if (err) - goto exit_bh; - for (i = 0, bit = gdblocks + 1; i < reserved_gdb; i++, bit++) - ext4_set_bit(bit, bh->b_data); + goto exit_journal; + + err = extend_or_restart_transaction(handle, 2); + if (err) + goto exit_journal; + + bh = bclean(handle, sb, input->block_bitmap); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + goto exit_journal; + } + + if (ext4_bg_has_super(sb, input->group)) { + ext4_debug("mark backup group tables %#04llx (+0)\n", start); + ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb + 1); + } ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap, input->block_bitmap - start); @@ -253,12 +274,9 @@ static int setup_new_group_blocks(struct super_block *sb, err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS); if (err) goto exit_bh; - for (i = 0, bit = input->inode_table - start; - i < sbi->s_itb_per_group; i++, bit++) - ext4_set_bit(bit, bh->b_data); + ext4_set_bits(bh->b_data, input->inode_table - start, + sbi->s_itb_per_group); - if ((err = extend_or_restart_transaction(handle, 2, bh))) - goto exit_bh; ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data); @@ -285,7 +303,6 @@ exit_bh: brelse(bh); exit_journal: - mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; @@ -377,15 +394,15 @@ static int verify_reserved_gdb(struct super_block *sb, * fail once we start modifying the data on disk, because JBD has no rollback. */ static int add_new_gdb(handle_t *handle, struct inode *inode, - struct ext4_new_group_data *input, - struct buffer_head **primary) + ext4_group_t group) { struct super_block *sb = inode->i_sb; struct ext4_super_block *es = EXT4_SB(sb)->s_es; - unsigned long gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb); + unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num; struct buffer_head **o_group_desc, **n_group_desc; struct buffer_head *dind; + struct buffer_head *gdb_bh; int gdbackups; struct ext4_iloc iloc; __le32 *data; @@ -408,11 +425,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, return -EPERM; } - *primary = sb_bread(sb, gdblock); - if (!*primary) + gdb_bh = sb_bread(sb, gdblock); + if (!gdb_bh) return -EIO; - if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) { + gdbackups = verify_reserved_gdb(sb, gdb_bh); + if (gdbackups < 0) { err = gdbackups; goto exit_bh; } @@ -427,7 +445,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, data = (__le32 *)dind->b_data; if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) { ext4_warning(sb, "new group %u GDT block %llu not reserved", - input->group, gdblock); + group, gdblock); err = -EINVAL; goto exit_dind; } @@ -436,7 +454,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, if (unlikely(err)) goto exit_dind; - err = ext4_journal_get_write_access(handle, *primary); + err = ext4_journal_get_write_access(handle, gdb_bh); if (unlikely(err)) goto exit_sbh; @@ -449,12 +467,13 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, if (unlikely(err)) goto exit_dindj; - n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *), - GFP_NOFS); + n_group_desc = ext4_kvmalloc((gdb_num + 1) * + sizeof(struct buffer_head *), + GFP_NOFS); if (!n_group_desc) { err = -ENOMEM; - ext4_warning(sb, - "not enough memory for %lu groups", gdb_num + 1); + ext4_warning(sb, "not enough memory for %lu groups", + gdb_num + 1); goto exit_inode; } @@ -475,8 +494,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, } inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9; ext4_mark_iloc_dirty(handle, inode, &iloc); - memset((*primary)->b_data, 0, sb->s_blocksize); - err = ext4_handle_dirty_metadata(handle, NULL, *primary); + memset(gdb_bh->b_data, 0, sb->s_blocksize); + err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); goto exit_inode; @@ -486,10 +505,10 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, o_group_desc = EXT4_SB(sb)->s_group_desc; memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); - n_group_desc[gdb_num] = *primary; + n_group_desc[gdb_num] = gdb_bh; EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; - kfree(o_group_desc); + ext4_kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); @@ -499,6 +518,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, return err; exit_inode: + ext4_kvfree(n_group_desc); /* ext4_handle_release_buffer(handle, iloc.bh); */ brelse(iloc.bh); exit_dindj: @@ -508,7 +528,7 @@ exit_sbh: exit_dind: brelse(dind); exit_bh: - brelse(*primary); + brelse(gdb_bh); ext4_debug("leaving with error %d\n", err); return err; @@ -528,7 +548,7 @@ exit_bh: * backup GDT blocks are stored in their reserved primary GDT block. */ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, - struct ext4_new_group_data *input) + ext4_group_t group) { struct super_block *sb = inode->i_sb; int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); @@ -599,7 +619,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, * Finally we can add each of the reserved backup GDT blocks from * the new group to its reserved primary GDT block. */ - blk = input->group * EXT4_BLOCKS_PER_GROUP(sb); + blk = group * EXT4_BLOCKS_PER_GROUP(sb); for (i = 0; i < reserved_gdb; i++) { int err2; data = (__le32 *)primary[i]->b_data; @@ -799,13 +819,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) goto exit_put; } - mutex_lock(&sbi->s_resize_lock); - if (input->group != sbi->s_groups_count) { - ext4_warning(sb, "multiple resizers run on filesystem!"); - err = -EBUSY; - goto exit_journal; - } - if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh))) goto exit_journal; @@ -820,16 +833,25 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) if ((err = ext4_journal_get_write_access(handle, primary))) goto exit_journal; - if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) && - (err = reserve_backup_gdb(handle, inode, input))) + if (reserved_gdb && ext4_bg_num_gdb(sb, input->group)) { + err = reserve_backup_gdb(handle, inode, input->group); + if (err) + goto exit_journal; + } + } else { + /* + * Note that we can access new group descriptor block safely + * only if add_new_gdb() succeeds. + */ + err = add_new_gdb(handle, inode, input->group); + if (err) goto exit_journal; - } else if ((err = add_new_gdb(handle, inode, input, &primary))) - goto exit_journal; + primary = sbi->s_group_desc[gdb_num]; + } /* * OK, now we've set up the new group. Time to make it active. * - * We do not lock all allocations via s_resize_lock * so we have to be safe wrt. concurrent accesses the group * data. So we need to be careful to set all of the relevant * group descriptor data etc. *before* we enable the group. @@ -886,13 +908,9 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * * The precise rules we use are: * - * * Writers of s_groups_count *must* hold s_resize_lock - * AND * * Writers must perform a smp_wmb() after updating all dependent * data and before modifying the groups count * - * * Readers must hold s_resize_lock over the access - * OR * * Readers must perform an smp_rmb() after reading the groups count * and before reading any dependent data. * @@ -937,10 +955,9 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) ext4_handle_dirty_super(handle, sb); exit_journal: - mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; - if (!err) { + if (!err && primary) { update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, sizeof(struct ext4_super_block)); update_backups(sb, primary->b_blocknr, primary->b_data, @@ -969,16 +986,13 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_grpblk_t add; struct buffer_head *bh; handle_t *handle; - int err; + int err, err2; ext4_group_t group; - /* We don't need to worry about locking wrt other resizers just - * yet: we're going to revalidate es->s_blocks_count after - * taking the s_resize_lock below. */ o_blocks_count = ext4_blocks_count(es); if (test_opt(sb, DEBUG)) - printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n", + printk(KERN_DEBUG "EXT4-fs: extending last group from %llu to %llu blocks\n", o_blocks_count, n_blocks_count); if (n_blocks_count == 0 || n_blocks_count == o_blocks_count) @@ -995,7 +1009,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, if (n_blocks_count < o_blocks_count) { ext4_warning(sb, "can't shrink FS - resize aborted"); - return -EBUSY; + return -EINVAL; } /* Handle the remaining blocks in the last group only. */ @@ -1038,32 +1052,25 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, goto exit_put; } - mutex_lock(&EXT4_SB(sb)->s_resize_lock); - if (o_blocks_count != ext4_blocks_count(es)) { - ext4_warning(sb, "multiple resizers run on filesystem!"); - mutex_unlock(&EXT4_SB(sb)->s_resize_lock); - ext4_journal_stop(handle); - err = -EBUSY; - goto exit_put; - } - if ((err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh))) { ext4_warning(sb, "error %d on journal write access", err); - mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_journal_stop(handle); goto exit_put; } ext4_blocks_count_set(es, o_blocks_count + add); - mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ - ext4_add_groupblocks(handle, sb, o_blocks_count, add); + err = ext4_group_add_blocks(handle, sb, o_blocks_count, add); ext4_handle_dirty_super(handle, sb); ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); - if ((err = ext4_journal_stop(handle))) + err2 = ext4_journal_stop(handle); + if (!err && err2) + err = err2; + + if (err) goto exit_put; if (test_opt(sb, DEBUG)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9ea71aa..4687fea 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -110,6 +110,35 @@ static struct file_system_type ext3_fs_type = { #define IS_EXT3_SB(sb) (0) #endif +void *ext4_kvmalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kmalloc(size, flags); + if (!ret) + ret = __vmalloc(size, flags, PAGE_KERNEL); + return ret; +} + +void *ext4_kvzalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kzalloc(size, flags); + if (!ret) + ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); + return ret; +} + +void ext4_kvfree(void *ptr) +{ + if (is_vmalloc_addr(ptr)) + vfree(ptr); + else + kfree(ptr); + +} + ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { @@ -269,6 +298,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) journal_t *journal; handle_t *handle; + trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); @@ -789,11 +819,8 @@ static void ext4_put_super(struct super_block *sb) for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); - kfree(sbi->s_group_desc); - if (is_vmalloc_addr(sbi->s_flex_groups)) - vfree(sbi->s_flex_groups); - else - kfree(sbi->s_flex_groups); + ext4_kvfree(sbi->s_group_desc); + ext4_kvfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1976,15 +2003,11 @@ static int ext4_fill_flex_info(struct super_block *sb) ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex; size = flex_group_count * sizeof(struct flex_groups); - sbi->s_flex_groups = kzalloc(size, GFP_KERNEL); + sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL); if (sbi->s_flex_groups == NULL) { - sbi->s_flex_groups = vzalloc(size); - if (sbi->s_flex_groups == NULL) { - ext4_msg(sb, KERN_ERR, - "not enough memory for %u flex groups", - flex_group_count); - goto failed; - } + ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups", + flex_group_count); + goto failed; } for (i = 0; i < sbi->s_groups_count; i++) { @@ -2383,17 +2406,25 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); unsigned long stripe_width = le32_to_cpu(sbi->s_es->s_raid_stripe_width); + int ret; if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) - return sbi->s_stripe; - - if (stripe_width <= sbi->s_blocks_per_group) - return stripe_width; + ret = sbi->s_stripe; + else if (stripe_width <= sbi->s_blocks_per_group) + ret = stripe_width; + else if (stride <= sbi->s_blocks_per_group) + ret = stride; + else + ret = 0; - if (stride <= sbi->s_blocks_per_group) - return stride; + /* + * If the stripe width is 1, this makes no sense and + * we set it to 0 to turn off stripe handling code. + */ + if (ret <= 1) + ret = 0; - return 0; + return ret; } /* sysfs supprt */ @@ -3408,8 +3439,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); - sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), - GFP_KERNEL); + sbi->s_group_desc = ext4_kvmalloc(db_count * + sizeof(struct buffer_head *), + GFP_KERNEL); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); goto failed_mount; @@ -3491,7 +3523,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); - mutex_init(&sbi->s_resize_lock); + sbi->s_resize_flags = 0; sb->s_root = NULL; @@ -3741,12 +3773,8 @@ failed_mount_wq: } failed_mount3: del_timer(&sbi->s_err_report); - if (sbi->s_flex_groups) { - if (is_vmalloc_addr(sbi->s_flex_groups)) - vfree(sbi->s_flex_groups); - else - kfree(sbi->s_flex_groups); - } + if (sbi->s_flex_groups) + ext4_kvfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -3756,7 +3784,7 @@ failed_mount3: failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); - kfree(sbi->s_group_desc); + ext4_kvfree(sbi->s_group_desc); failed_mount: if (sbi->s_proc) { remove_proc_entry(sb->s_id, ext4_proc_root); diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h new file mode 100644 index 0000000..011ba66 --- /dev/null +++ b/fs/ext4/truncate.h @@ -0,0 +1,43 @@ +/* + * linux/fs/ext4/truncate.h + * + * Common inline functions needed for truncate support + */ + +/* + * Truncate blocks that were not used by write. We have to truncate the + * pagecache as well so that corresponding buffers get properly unmapped. + */ +static inline void ext4_truncate_failed_write(struct inode *inode) +{ + truncate_inode_pages(inode->i_mapping, inode->i_size); + ext4_truncate(inode); +} + +/* + * Work out how many blocks we need to proceed with the next chunk of a + * truncate transaction. + */ +static inline unsigned long ext4_blocks_for_truncate(struct inode *inode) +{ + ext4_lblk_t needed; + + needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); + + /* Give ourselves just enough room to cope with inodes in which + * i_blocks is corrupt: we've seen disk corruptions in the past + * which resulted in random data in an inode which looked enough + * like a regular file for ext4 to try to delete it. Things + * will go a bit crazy if that happens, but at least we should + * try not to panic the whole kernel. */ + if (needed < 2) + needed = 2; + + /* But we need to bound the transaction so we don't overflow the + * journal. */ + if (needed > EXT4_MAX_TRANS_DATA) + needed = EXT4_MAX_TRANS_DATA; + + return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; +} + diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1599aa9..04cf3b9 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -618,7 +618,12 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, struct super_block *sb = inode->i_sb; if (!grab_super_passive(sb)) { - requeue_io(inode, wb); + /* + * grab_super_passive() may fail consistently due to + * s_umount being grabbed by someone else. Don't use + * requeue_io() to avoid busy retrying the inode/sb. + */ + redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); diff --git a/fs/generic_acl.c b/fs/generic_acl.c index d5e33a0..d0dddac 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -82,18 +82,14 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value, return PTR_ERR(acl); } if (acl) { - mode_t mode; - error = posix_acl_valid(acl); if (error) goto failed; switch (type) { case ACL_TYPE_ACCESS: - mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) goto failed; - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME; if (error == 0) { posix_acl_release(acl); @@ -125,21 +121,20 @@ int generic_acl_init(struct inode *inode, struct inode *dir) { struct posix_acl *acl = NULL; - mode_t mode = inode->i_mode; int error; - inode->i_mode = mode & ~current_umask(); if (!S_ISLNK(inode->i_mode)) acl = get_cached_acl(dir, ACL_TYPE_DEFAULT); if (acl) { if (S_ISDIR(inode->i_mode)) set_cached_acl(inode, ACL_TYPE_DEFAULT, acl); - error = posix_acl_create(&acl, GFP_KERNEL, &mode); + error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) set_cached_acl(inode, ACL_TYPE_ACCESS, acl); + } else { + inode->i_mode &= ~current_umask(); } error = 0; diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 884c9af..34501b6 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -72,7 +72,7 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type) return gfs2_acl_get(GFS2_I(inode), type); } -static int gfs2_set_mode(struct inode *inode, mode_t mode) +static int gfs2_set_mode(struct inode *inode, umode_t mode) { int error = 0; @@ -117,7 +117,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct posix_acl *acl; - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; int error = 0; if (!sdp->sd_args.ar_posix_acl) @@ -276,7 +276,7 @@ static int gfs2_xattr_system_set(struct dentry *dentry, const char *name, goto out_release; if (type == ACL_TYPE_ACCESS) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; error = posix_acl_equiv_mode(acl, &mode); if (error <= 0) { diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 8635be5..970ea98 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -16,6 +16,7 @@ #include <linux/statfs.h> #include <linux/types.h> #include <linux/pid_namespace.h> +#include <linux/namei.h> #include <asm/uaccess.h> #include "os.h" @@ -143,6 +143,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_op = &empty_iops; inode->i_fop = &empty_fops; inode->i_nlink = 1; + inode->i_opflags = 0; inode->i_uid = 0; inode->i_gid = 0; atomic_set(&inode->i_writecount, 0); @@ -399,12 +400,12 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) EXPORT_SYMBOL(__insert_inode_hash); /** - * remove_inode_hash - remove an inode from the hash + * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ -void remove_inode_hash(struct inode *inode) +void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); @@ -412,7 +413,7 @@ void remove_inode_hash(struct inode *inode) spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } -EXPORT_SYMBOL(remove_inode_hash); +EXPORT_SYMBOL(__remove_inode_hash); void end_writeback(struct inode *inode) { @@ -454,7 +455,9 @@ static void evict(struct inode *inode) BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); - inode_wb_list_del(inode); + if (!list_empty(&inode->i_wb_list)) + inode_wb_list_del(inode); + inode_sb_list_del(inode); if (op->evict_inode) { @@ -1328,7 +1331,8 @@ static void iput_final(struct inode *inode) } inode->i_state |= I_FREEING; - inode_lru_list_del(inode); + if (!list_empty(&inode->i_lru)) + inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 2c62c5a..16a698b 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -257,9 +257,12 @@ static void __flush_batch(journal_t *journal, int *batch_count) { int i; + struct blk_plug plug; + blk_start_plug(&plug); for (i = 0; i < *batch_count; i++) - write_dirty_buffer(journal->j_chkpt_bhs[i], WRITE); + write_dirty_buffer(journal->j_chkpt_bhs[i], WRITE_SYNC); + blk_finish_plug(&plug); for (i = 0; i < *batch_count; i++) { struct buffer_head *bh = journal->j_chkpt_bhs[i]; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0dfa5b59..f24df13 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2390,73 +2390,6 @@ static void __exit journal_exit(void) jbd2_journal_destroy_caches(); } -/* - * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 - * tracing infrastructure to map a dev_t to a device name. - * - * The caller should use rcu_read_lock() in order to make sure the - * device name stays valid until its done with it. We use - * rcu_read_lock() as well to make sure we're safe in case the caller - * gets sloppy, and because rcu_read_lock() is cheap and can be safely - * nested. - */ -struct devname_cache { - struct rcu_head rcu; - dev_t device; - char devname[BDEVNAME_SIZE]; -}; -#define CACHE_SIZE_BITS 6 -static struct devname_cache *devcache[1 << CACHE_SIZE_BITS]; -static DEFINE_SPINLOCK(devname_cache_lock); - -static void free_devcache(struct rcu_head *rcu) -{ - kfree(rcu); -} - -const char *jbd2_dev_to_name(dev_t device) -{ - int i = hash_32(device, CACHE_SIZE_BITS); - char *ret; - struct block_device *bd; - static struct devname_cache *new_dev; - - rcu_read_lock(); - if (devcache[i] && devcache[i]->device == device) { - ret = devcache[i]->devname; - rcu_read_unlock(); - return ret; - } - rcu_read_unlock(); - - new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); - if (!new_dev) - return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ - bd = bdget(device); - spin_lock(&devname_cache_lock); - if (devcache[i]) { - if (devcache[i]->device == device) { - kfree(new_dev); - bdput(bd); - ret = devcache[i]->devname; - spin_unlock(&devname_cache_lock); - return ret; - } - call_rcu(&devcache[i]->rcu, free_devcache); - } - devcache[i] = new_dev; - devcache[i]->device = device; - if (bd) { - bdevname(bd, devcache[i]->devname); - bdput(bd); - } else - __bdevname(device, devcache[i]->devname); - ret = devcache[i]->devname; - spin_unlock(&devname_cache_lock); - return ret; -} -EXPORT_SYMBOL(jbd2_dev_to_name); - MODULE_LICENSE("GPL"); module_init(journal_init); module_exit(journal_exit); diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 27c511a..926d020 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -227,7 +227,7 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; rc = posix_acl_equiv_mode(acl, &mode); if (rc < 0) return rc; @@ -259,7 +259,7 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) return rc; } -int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, mode_t *i_mode) +int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, umode_t *i_mode) { struct posix_acl *acl; int rc; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index b3421c7..9b47724 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -28,7 +28,7 @@ struct jffs2_acl_header { struct posix_acl *jffs2_get_acl(struct inode *inode, int type); extern int jffs2_acl_chmod(struct inode *); -extern int jffs2_init_acl_pre(struct inode *, struct inode *, mode_t *); +extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *); extern int jffs2_init_acl_post(struct inode *); extern const struct xattr_handler jffs2_acl_access_xattr_handler; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index b81b35d..bbcb975 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -406,7 +406,7 @@ int jffs2_remount_fs (struct super_block *sb, int *flags, char *data) /* jffs2_new_inode: allocate a new inode and inocache, add it to the hash, fill in the raw_inode while you're at it. */ -struct inode *jffs2_new_inode (struct inode *dir_i, mode_t mode, struct jffs2_raw_inode *ri) +struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_raw_inode *ri) { struct inode *inode; struct super_block *sb = dir_i->i_sb; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 526979c..6c1755c 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -173,7 +173,7 @@ int jffs2_do_setattr (struct inode *, struct iattr *); struct inode *jffs2_iget(struct super_block *, unsigned long); void jffs2_evict_inode (struct inode *); void jffs2_dirty_inode(struct inode *inode, int flags); -struct inode *jffs2_new_inode (struct inode *dir_i, mode_t mode, +struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_raw_inode *ri); int jffs2_statfs (struct dentry *, struct kstatfs *); int jffs2_remount_fs (struct super_block *, int *, char *); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index b3a32ca..45559dc 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -127,16 +127,14 @@ int jfs_init_acl(tid_t tid, struct inode *inode, struct inode *dir) return PTR_ERR(acl); if (acl) { - mode_t mode = inode->i_mode; if (S_ISDIR(inode->i_mode)) { rc = jfs_set_acl(tid, inode, ACL_TYPE_DEFAULT, acl); if (rc) goto cleanup; } - rc = posix_acl_create(&acl, GFP_KERNEL, &mode); + rc = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (rc < 0) goto cleanup; /* posix_acl_release(NULL) is no-op */ - inode->i_mode = mode; if (rc > 0) rc = jfs_set_acl(tid, inode, ACL_TYPE_ACCESS, acl); cleanup: diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 24838f1..e87fede 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -693,8 +693,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, return rc; } if (acl) { - mode_t mode = inode->i_mode; - rc = posix_acl_equiv_mode(acl, &mode); + rc = posix_acl_equiv_mode(acl, &inode->i_mode); posix_acl_release(acl); if (rc < 0) { printk(KERN_ERR @@ -702,7 +701,6 @@ static int can_set_system_xattr(struct inode *inode, const char *name, rc); return rc; } - inode->i_mode = mode; mark_inode_dirty(inode); } /* @@ -179,19 +179,14 @@ static int check_acl(struct inode *inode, int mask) #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; - /* - * Under RCU walk, we cannot even do a "get_cached_acl()", - * because that involves locking and getting a refcount on - * a cached ACL. - * - * So the only case we handle during RCU walking is the - * case of a cached "no ACL at all", which needs no locks - * or refcounts. - */ if (mask & MAY_NOT_BLOCK) { - if (negative_cached_acl(inode, ACL_TYPE_ACCESS)) + acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); + if (!acl) return -EAGAIN; - return -ECHILD; + /* no ->get_acl() calls in RCU mode... */ + if (acl == ACL_NOT_CACHED) + return -ECHILD; + return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK); } acl = get_cached_acl(inode, ACL_TYPE_ACCESS); @@ -313,6 +308,26 @@ int generic_permission(struct inode *inode, int mask) return -EACCES; } +/* + * We _really_ want to just do "generic_permission()" without + * even looking at the inode->i_op values. So we keep a cache + * flag in inode->i_opflags, that says "this has not special + * permission function, use the fast case". + */ +static inline int do_inode_permission(struct inode *inode, int mask) +{ + if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { + if (likely(inode->i_op->permission)) + return inode->i_op->permission(inode, mask); + + /* This gets set once for the inode lifetime */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_FASTPERM; + spin_unlock(&inode->i_lock); + } + return generic_permission(inode, mask); +} + /** * inode_permission - check for access rights to a given inode * @inode: inode to check permission on @@ -327,7 +342,7 @@ int inode_permission(struct inode *inode, int mask) { int retval; - if (mask & MAY_WRITE) { + if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* @@ -344,11 +359,7 @@ int inode_permission(struct inode *inode, int mask) return -EACCES; } - if (inode->i_op->permission) - retval = inode->i_op->permission(inode, mask); - else - retval = generic_permission(inode, mask); - + retval = do_inode_permission(inode, mask); if (retval) return retval; @@ -716,19 +727,25 @@ static int follow_automount(struct path *path, unsigned flags, if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT)) return -EISDIR; /* we actually want to stop here */ - /* We want to mount if someone is trying to open/create a file of any - * type under the mountpoint, wants to traverse through the mountpoint - * or wants to open the mounted directory. - * + /* * We don't want to mount if someone's just doing a stat and they've * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and * appended a '/' to the name. */ - if (!(flags & LOOKUP_FOLLOW) && - !(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | - LOOKUP_OPEN | LOOKUP_CREATE))) - return -EISDIR; - + if (!(flags & LOOKUP_FOLLOW)) { + /* We do, however, want to mount if someone wants to open or + * create a file of any type under the mountpoint, wants to + * traverse through the mountpoint or wants to open the mounted + * directory. + * Also, autofs may mark negative dentries as being automount + * points. These will need the attentions of the daemon to + * instantiate them before they can be used. + */ + if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | + LOOKUP_OPEN | LOOKUP_CREATE)) && + path->dentry->d_inode) + return -EISDIR; + } current->total_link_count++; if (current->total_link_count >= 40) return -ELOOP; @@ -1244,6 +1261,26 @@ static void terminate_walk(struct nameidata *nd) } } +/* + * Do we need to follow links? We _really_ want to be able + * to do this check without having to look at inode->i_op, + * so we keep a cache of "no, this doesn't need follow_link" + * for the common case. + */ +static inline int should_follow_link(struct inode *inode, int follow) +{ + if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { + if (likely(inode->i_op->follow_link)) + return follow; + + /* This gets set once for the inode lifetime */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_NOFOLLOW; + spin_unlock(&inode->i_lock); + } + return 0; +} + static inline int walk_component(struct nameidata *nd, struct path *path, struct qstr *name, int type, int follow) { @@ -1266,7 +1303,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path, terminate_walk(nd); return -ENOENT; } - if (unlikely(inode->i_op->follow_link) && follow) { + if (should_follow_link(inode, follow)) { if (nd->flags & LOOKUP_RCU) { if (unlikely(unlazy_walk(nd, path->dentry))) { terminate_walk(nd); @@ -1319,6 +1356,26 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) } /* + * We really don't want to look at inode->i_op->lookup + * when we don't have to. So we keep a cache bit in + * the inode ->i_opflags field that says "yes, we can + * do lookup on this inode". + */ +static inline int can_lookup(struct inode *inode) +{ + if (likely(inode->i_opflags & IOP_LOOKUP)) + return 1; + if (likely(!inode->i_op->lookup)) + return 0; + + /* We do this once for the lifetime of the inode */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_LOOKUP; + spin_unlock(&inode->i_lock); + return 1; +} + +/* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. @@ -1397,10 +1454,10 @@ static int link_path_walk(const char *name, struct nameidata *nd) if (err) return err; } + if (can_lookup(nd->inode)) + continue; err = -ENOTDIR; - if (!nd->inode->i_op->lookup) - break; - continue; + break; /* here ends the main loop */ last_component: diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 2cde5d9..be02077 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -79,15 +79,21 @@ config NFS_V4_1 depends on NFS_FS && NFS_V4 && EXPERIMENTAL select SUNRPC_BACKCHANNEL select PNFS_FILE_LAYOUT + select PNFS_BLOCK + select MD + select BLK_DEV_DM help This option enables support for minor version 1 of the NFSv4 protocol - (RFC 5661) in the kernel's NFS client. + (RFC 5661 and RFC 5663) in the kernel's NFS client. If unsure, say N. config PNFS_FILE_LAYOUT tristate +config PNFS_BLOCK + tristate + config PNFS_OBJLAYOUT tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)" depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 6a34f7d..b58613d 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/ +obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile new file mode 100644 index 0000000..d581550 --- /dev/null +++ b/fs/nfs/blocklayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS block layout driver kernel module +# +obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o +blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o blocklayoutdm.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c new file mode 100644 index 0000000..e56564d --- /dev/null +++ b/fs/nfs/blocklayout/blocklayout.c @@ -0,0 +1,1019 @@ +/* + * linux/fs/nfs/blocklayout/blocklayout.c + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/bio.h> /* struct bio */ +#include <linux/buffer_head.h> /* various write calls */ + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>"); +MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver"); + +struct dentry *bl_device_pipe; +wait_queue_head_t bl_wq; + +static void print_page(struct page *page) +{ + dprintk("PRINTPAGE page %p\n", page); + dprintk(" PagePrivate %d\n", PagePrivate(page)); + dprintk(" PageUptodate %d\n", PageUptodate(page)); + dprintk(" PageError %d\n", PageError(page)); + dprintk(" PageDirty %d\n", PageDirty(page)); + dprintk(" PageReferenced %d\n", PageReferenced(page)); + dprintk(" PageLocked %d\n", PageLocked(page)); + dprintk(" PageWriteback %d\n", PageWriteback(page)); + dprintk(" PageMappedToDisk %d\n", PageMappedToDisk(page)); + dprintk("\n"); +} + +/* Given the be associated with isect, determine if page data needs to be + * initialized. + */ +static int is_hole(struct pnfs_block_extent *be, sector_t isect) +{ + if (be->be_state == PNFS_BLOCK_NONE_DATA) + return 1; + else if (be->be_state != PNFS_BLOCK_INVALID_DATA) + return 0; + else + return !bl_is_sector_init(be->be_inval, isect); +} + +/* Given the be associated with isect, determine if page data can be + * written to disk. + */ +static int is_writable(struct pnfs_block_extent *be, sector_t isect) +{ + return (be->be_state == PNFS_BLOCK_READWRITE_DATA || + be->be_state == PNFS_BLOCK_INVALID_DATA); +} + +/* The data we are handed might be spread across several bios. We need + * to track when the last one is finished. + */ +struct parallel_io { + struct kref refcnt; + struct rpc_call_ops call_ops; + void (*pnfs_callback) (void *data); + void *data; +}; + +static inline struct parallel_io *alloc_parallel(void *data) +{ + struct parallel_io *rv; + + rv = kmalloc(sizeof(*rv), GFP_NOFS); + if (rv) { + rv->data = data; + kref_init(&rv->refcnt); + } + return rv; +} + +static inline void get_parallel(struct parallel_io *p) +{ + kref_get(&p->refcnt); +} + +static void destroy_parallel(struct kref *kref) +{ + struct parallel_io *p = container_of(kref, struct parallel_io, refcnt); + + dprintk("%s enter\n", __func__); + p->pnfs_callback(p->data); + kfree(p); +} + +static inline void put_parallel(struct parallel_io *p) +{ + kref_put(&p->refcnt, destroy_parallel); +} + +static struct bio * +bl_submit_bio(int rw, struct bio *bio) +{ + if (bio) { + get_parallel(bio->bi_private); + dprintk("%s submitting %s bio %u@%llu\n", __func__, + rw == READ ? "read" : "write", + bio->bi_size, (unsigned long long)bio->bi_sector); + submit_bio(rw, bio); + } + return NULL; +} + +static struct bio *bl_alloc_init_bio(int npg, sector_t isect, + struct pnfs_block_extent *be, + void (*end_io)(struct bio *, int err), + struct parallel_io *par) +{ + struct bio *bio; + + bio = bio_alloc(GFP_NOIO, npg); + if (!bio) + return NULL; + + bio->bi_sector = isect - be->be_f_offset + be->be_v_offset; + bio->bi_bdev = be->be_mdev; + bio->bi_end_io = end_io; + bio->bi_private = par; + return bio; +} + +static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw, + sector_t isect, struct page *page, + struct pnfs_block_extent *be, + void (*end_io)(struct bio *, int err), + struct parallel_io *par) +{ +retry: + if (!bio) { + bio = bl_alloc_init_bio(npg, isect, be, end_io, par); + if (!bio) + return ERR_PTR(-ENOMEM); + } + if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + bio = bl_submit_bio(rw, bio); + goto retry; + } + return bio; +} + +static void bl_set_lo_fail(struct pnfs_layout_segment *lseg) +{ + if (lseg->pls_range.iomode == IOMODE_RW) { + dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__); + set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); + } else { + dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__); + set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); + } +} + +/* This is basically copied from mpage_end_io_read */ +static void bl_end_io_read(struct bio *bio, int err) +{ + struct parallel_io *par = bio->bi_private; + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + struct nfs_read_data *rdata = (struct nfs_read_data *)par->data; + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + if (uptodate) + SetPageUptodate(page); + } while (bvec >= bio->bi_io_vec); + if (!uptodate) { + if (!rdata->pnfs_error) + rdata->pnfs_error = -EIO; + bl_set_lo_fail(rdata->lseg); + } + bio_put(bio); + put_parallel(par); +} + +static void bl_read_cleanup(struct work_struct *work) +{ + struct rpc_task *task; + struct nfs_read_data *rdata; + dprintk("%s enter\n", __func__); + task = container_of(work, struct rpc_task, u.tk_work); + rdata = container_of(task, struct nfs_read_data, task); + pnfs_ld_read_done(rdata); +} + +static void +bl_end_par_io_read(void *data) +{ + struct nfs_read_data *rdata = data; + + INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); + schedule_work(&rdata->task.u.tk_work); +} + +/* We don't want normal .rpc_call_done callback used, so we replace it + * with this stub. + */ +static void bl_rpc_do_nothing(struct rpc_task *task, void *calldata) +{ + return; +} + +static enum pnfs_try_status +bl_read_pagelist(struct nfs_read_data *rdata) +{ + int i, hole; + struct bio *bio = NULL; + struct pnfs_block_extent *be = NULL, *cow_read = NULL; + sector_t isect, extent_length = 0; + struct parallel_io *par; + loff_t f_offset = rdata->args.offset; + size_t count = rdata->args.count; + struct page **pages = rdata->args.pages; + int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT; + + dprintk("%s enter nr_pages %u offset %lld count %Zd\n", __func__, + rdata->npages, f_offset, count); + + par = alloc_parallel(rdata); + if (!par) + goto use_mds; + par->call_ops = *rdata->mds_ops; + par->call_ops.rpc_call_done = bl_rpc_do_nothing; + par->pnfs_callback = bl_end_par_io_read; + /* At this point, we can no longer jump to use_mds */ + + isect = (sector_t) (f_offset >> SECTOR_SHIFT); + /* Code assumes extents are page-aligned */ + for (i = pg_index; i < rdata->npages; i++) { + if (!extent_length) { + /* We've used up the previous extent */ + bl_put_extent(be); + bl_put_extent(cow_read); + bio = bl_submit_bio(READ, bio); + /* Get the next one */ + be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg), + isect, &cow_read); + if (!be) { + rdata->pnfs_error = -EIO; + goto out; + } + extent_length = be->be_length - + (isect - be->be_f_offset); + if (cow_read) { + sector_t cow_length = cow_read->be_length - + (isect - cow_read->be_f_offset); + extent_length = min(extent_length, cow_length); + } + } + hole = is_hole(be, isect); + if (hole && !cow_read) { + bio = bl_submit_bio(READ, bio); + /* Fill hole w/ zeroes w/o accessing device */ + dprintk("%s Zeroing page for hole\n", __func__); + zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); + print_page(pages[i]); + SetPageUptodate(pages[i]); + } else { + struct pnfs_block_extent *be_read; + + be_read = (hole && cow_read) ? cow_read : be; + bio = bl_add_page_to_bio(bio, rdata->npages - i, READ, + isect, pages[i], be_read, + bl_end_io_read, par); + if (IS_ERR(bio)) { + rdata->pnfs_error = PTR_ERR(bio); + goto out; + } + } + isect += PAGE_CACHE_SECTORS; + extent_length -= PAGE_CACHE_SECTORS; + } + if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) { + rdata->res.eof = 1; + rdata->res.count = rdata->inode->i_size - f_offset; + } else { + rdata->res.count = (isect << SECTOR_SHIFT) - f_offset; + } +out: + bl_put_extent(be); + bl_put_extent(cow_read); + bl_submit_bio(READ, bio); + put_parallel(par); + return PNFS_ATTEMPTED; + + use_mds: + dprintk("Giving up and using normal NFS\n"); + return PNFS_NOT_ATTEMPTED; +} + +static void mark_extents_written(struct pnfs_block_layout *bl, + __u64 offset, __u32 count) +{ + sector_t isect, end; + struct pnfs_block_extent *be; + + dprintk("%s(%llu, %u)\n", __func__, offset, count); + if (count == 0) + return; + isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT; + end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK); + end >>= SECTOR_SHIFT; + while (isect < end) { + sector_t len; + be = bl_find_get_extent(bl, isect, NULL); + BUG_ON(!be); /* FIXME */ + len = min(end, be->be_f_offset + be->be_length) - isect; + if (be->be_state == PNFS_BLOCK_INVALID_DATA) + bl_mark_for_commit(be, isect, len); /* What if fails? */ + isect += len; + bl_put_extent(be); + } +} + +static void bl_end_io_write_zero(struct bio *bio, int err) +{ + struct parallel_io *par = bio->bi_private; + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + /* This is the zeroing page we added */ + end_page_writeback(page); + page_cache_release(page); + } while (bvec >= bio->bi_io_vec); + if (!uptodate) { + if (!wdata->pnfs_error) + wdata->pnfs_error = -EIO; + bl_set_lo_fail(wdata->lseg); + } + bio_put(bio); + put_parallel(par); +} + +/* This is basically copied from mpage_end_io_read */ +static void bl_end_io_write(struct bio *bio, int err) +{ + struct parallel_io *par = bio->bi_private; + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; + + if (!uptodate) { + if (!wdata->pnfs_error) + wdata->pnfs_error = -EIO; + bl_set_lo_fail(wdata->lseg); + } + bio_put(bio); + put_parallel(par); +} + +/* Function scheduled for call during bl_end_par_io_write, + * it marks sectors as written and extends the commitlist. + */ +static void bl_write_cleanup(struct work_struct *work) +{ + struct rpc_task *task; + struct nfs_write_data *wdata; + dprintk("%s enter\n", __func__); + task = container_of(work, struct rpc_task, u.tk_work); + wdata = container_of(task, struct nfs_write_data, task); + if (!wdata->pnfs_error) { + /* Marks for LAYOUTCOMMIT */ + mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + wdata->args.offset, wdata->args.count); + } + pnfs_ld_write_done(wdata); +} + +/* Called when last of bios associated with a bl_write_pagelist call finishes */ +static void bl_end_par_io_write(void *data) +{ + struct nfs_write_data *wdata = data; + + wdata->task.tk_status = 0; + wdata->verf.committed = NFS_FILE_SYNC; + INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup); + schedule_work(&wdata->task.u.tk_work); +} + +/* FIXME STUB - mark intersection of layout and page as bad, so is not + * used again. + */ +static void mark_bad_read(void) +{ + return; +} + +/* + * map_block: map a requested I/0 block (isect) into an offset in the LVM + * block_device + */ +static void +map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be) +{ + dprintk("%s enter be=%p\n", __func__, be); + + set_buffer_mapped(bh); + bh->b_bdev = be->be_mdev; + bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >> + (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT); + + dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n", + __func__, (unsigned long long)isect, (long)bh->b_blocknr, + bh->b_size); + return; +} + +/* Given an unmapped page, zero it or read in page for COW, page is locked + * by caller. + */ +static int +init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read) +{ + struct buffer_head *bh = NULL; + int ret = 0; + sector_t isect; + + dprintk("%s enter, %p\n", __func__, page); + BUG_ON(PageUptodate(page)); + if (!cow_read) { + zero_user_segment(page, 0, PAGE_SIZE); + SetPageUptodate(page); + goto cleanup; + } + + bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0); + if (!bh) { + ret = -ENOMEM; + goto cleanup; + } + + isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT; + map_block(bh, isect, cow_read); + if (!bh_uptodate_or_lock(bh)) + ret = bh_submit_read(bh); + if (ret) + goto cleanup; + SetPageUptodate(page); + +cleanup: + bl_put_extent(cow_read); + if (bh) + free_buffer_head(bh); + if (ret) { + /* Need to mark layout with bad read...should now + * just use nfs4 for reads and writes. + */ + mark_bad_read(); + } + return ret; +} + +static enum pnfs_try_status +bl_write_pagelist(struct nfs_write_data *wdata, int sync) +{ + int i, ret, npg_zero, pg_index, last = 0; + struct bio *bio = NULL; + struct pnfs_block_extent *be = NULL, *cow_read = NULL; + sector_t isect, last_isect = 0, extent_length = 0; + struct parallel_io *par; + loff_t offset = wdata->args.offset; + size_t count = wdata->args.count; + struct page **pages = wdata->args.pages; + struct page *page; + pgoff_t index; + u64 temp; + int npg_per_block = + NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; + + dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); + /* At this point, wdata->pages is a (sequential) list of nfs_pages. + * We want to write each, and if there is an error set pnfs_error + * to have it redone using nfs. + */ + par = alloc_parallel(wdata); + if (!par) + return PNFS_NOT_ATTEMPTED; + par->call_ops = *wdata->mds_ops; + par->call_ops.rpc_call_done = bl_rpc_do_nothing; + par->pnfs_callback = bl_end_par_io_write; + /* At this point, have to be more careful with error handling */ + + isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); + be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read); + if (!be || !is_writable(be, isect)) { + dprintk("%s no matching extents!\n", __func__); + wdata->pnfs_error = -EINVAL; + goto out; + } + + /* First page inside INVALID extent */ + if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + temp = offset >> PAGE_CACHE_SHIFT; + npg_zero = do_div(temp, npg_per_block); + isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) & + (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); + extent_length = be->be_length - (isect - be->be_f_offset); + +fill_invalid_ext: + dprintk("%s need to zero %d pages\n", __func__, npg_zero); + for (;npg_zero > 0; npg_zero--) { + /* page ref released in bl_end_io_write_zero */ + index = isect >> PAGE_CACHE_SECTOR_SHIFT; + dprintk("%s zero %dth page: index %lu isect %llu\n", + __func__, npg_zero, index, + (unsigned long long)isect); + page = + find_or_create_page(wdata->inode->i_mapping, index, + GFP_NOFS); + if (!page) { + dprintk("%s oom\n", __func__); + wdata->pnfs_error = -ENOMEM; + goto out; + } + + /* PageDirty: Other will write this out + * PageWriteback: Other is writing this out + * PageUptodate: It was read before + * sector_initialized: already written out + */ + if (PageDirty(page) || PageWriteback(page) || + bl_is_sector_init(be->be_inval, isect)) { + print_page(page); + unlock_page(page); + page_cache_release(page); + goto next_page; + } + if (!PageUptodate(page)) { + /* New page, readin or zero it */ + init_page_for_write(page, cow_read); + } + set_page_writeback(page); + unlock_page(page); + + ret = bl_mark_sectors_init(be->be_inval, isect, + PAGE_CACHE_SECTORS, + NULL); + if (unlikely(ret)) { + dprintk("%s bl_mark_sectors_init fail %d\n", + __func__, ret); + end_page_writeback(page); + page_cache_release(page); + wdata->pnfs_error = ret; + goto out; + } + bio = bl_add_page_to_bio(bio, npg_zero, WRITE, + isect, page, be, + bl_end_io_write_zero, par); + if (IS_ERR(bio)) { + wdata->pnfs_error = PTR_ERR(bio); + goto out; + } + /* FIXME: This should be done in bi_end_io */ + mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + page->index << PAGE_CACHE_SHIFT, + PAGE_CACHE_SIZE); +next_page: + isect += PAGE_CACHE_SECTORS; + extent_length -= PAGE_CACHE_SECTORS; + } + if (last) + goto write_done; + } + bio = bl_submit_bio(WRITE, bio); + + /* Middle pages */ + pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT; + for (i = pg_index; i < wdata->npages; i++) { + if (!extent_length) { + /* We've used up the previous extent */ + bl_put_extent(be); + bio = bl_submit_bio(WRITE, bio); + /* Get the next one */ + be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), + isect, NULL); + if (!be || !is_writable(be, isect)) { + wdata->pnfs_error = -EINVAL; + goto out; + } + extent_length = be->be_length - + (isect - be->be_f_offset); + } + if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + ret = bl_mark_sectors_init(be->be_inval, isect, + PAGE_CACHE_SECTORS, + NULL); + if (unlikely(ret)) { + dprintk("%s bl_mark_sectors_init fail %d\n", + __func__, ret); + wdata->pnfs_error = ret; + goto out; + } + } + bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE, + isect, pages[i], be, + bl_end_io_write, par); + if (IS_ERR(bio)) { + wdata->pnfs_error = PTR_ERR(bio); + goto out; + } + isect += PAGE_CACHE_SECTORS; + last_isect = isect; + extent_length -= PAGE_CACHE_SECTORS; + } + + /* Last page inside INVALID extent */ + if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + bio = bl_submit_bio(WRITE, bio); + temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT; + npg_zero = npg_per_block - do_div(temp, npg_per_block); + if (npg_zero < npg_per_block) { + last = 1; + goto fill_invalid_ext; + } + } + +write_done: + wdata->res.count = (last_isect << SECTOR_SHIFT) - (offset); + if (count < wdata->res.count) { + wdata->res.count = count; + } +out: + bl_put_extent(be); + bl_submit_bio(WRITE, bio); + put_parallel(par); + return PNFS_ATTEMPTED; +} + +/* FIXME - range ignored */ +static void +release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range) +{ + int i; + struct pnfs_block_extent *be; + + spin_lock(&bl->bl_ext_lock); + for (i = 0; i < EXTENT_LISTS; i++) { + while (!list_empty(&bl->bl_extents[i])) { + be = list_first_entry(&bl->bl_extents[i], + struct pnfs_block_extent, + be_node); + list_del(&be->be_node); + bl_put_extent(be); + } + } + spin_unlock(&bl->bl_ext_lock); +} + +static void +release_inval_marks(struct pnfs_inval_markings *marks) +{ + struct pnfs_inval_tracking *pos, *temp; + + list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) { + list_del(&pos->it_link); + kfree(pos); + } + return; +} + +static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + + dprintk("%s enter\n", __func__); + release_extents(bl, NULL); + release_inval_marks(&bl->bl_inval); + kfree(bl); +} + +static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode, + gfp_t gfp_flags) +{ + struct pnfs_block_layout *bl; + + dprintk("%s enter\n", __func__); + bl = kzalloc(sizeof(*bl), gfp_flags); + if (!bl) + return NULL; + spin_lock_init(&bl->bl_ext_lock); + INIT_LIST_HEAD(&bl->bl_extents[0]); + INIT_LIST_HEAD(&bl->bl_extents[1]); + INIT_LIST_HEAD(&bl->bl_commit); + INIT_LIST_HEAD(&bl->bl_committing); + bl->bl_count = 0; + bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT; + BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize); + return &bl->bl_layout; +} + +static void bl_free_lseg(struct pnfs_layout_segment *lseg) +{ + dprintk("%s enter\n", __func__); + kfree(lseg); +} + +/* We pretty much ignore lseg, and store all data layout wide, so we + * can correctly merge. + */ +static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + struct pnfs_layout_segment *lseg; + int status; + + dprintk("%s enter\n", __func__); + lseg = kzalloc(sizeof(*lseg), gfp_flags); + if (!lseg) + return ERR_PTR(-ENOMEM); + status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags); + if (status) { + /* We don't want to call the full-blown bl_free_lseg, + * since on error extents were not touched. + */ + kfree(lseg); + return ERR_PTR(status); + } + return lseg; +} + +static void +bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *arg) +{ + dprintk("%s enter\n", __func__); + encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg); +} + +static void +bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) +{ + struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout; + + dprintk("%s enter\n", __func__); + clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status); +} + +static void free_blk_mountid(struct block_mount_id *mid) +{ + if (mid) { + struct pnfs_block_dev *dev; + spin_lock(&mid->bm_lock); + while (!list_empty(&mid->bm_devlist)) { + dev = list_first_entry(&mid->bm_devlist, + struct pnfs_block_dev, + bm_node); + list_del(&dev->bm_node); + bl_free_block_dev(dev); + } + spin_unlock(&mid->bm_lock); + kfree(mid); + } +} + +/* This is mostly copied from the filelayout's get_device_info function. + * It seems much of this should be at the generic pnfs level. + */ +static struct pnfs_block_dev * +nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, + struct nfs4_deviceid *d_id) +{ + struct pnfs_device *dev; + struct pnfs_block_dev *rv = NULL; + u32 max_resp_sz; + int max_pages; + struct page **pages = NULL; + int i, rc; + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = max_resp_sz >> PAGE_SHIFT; + dprintk("%s max_resp_sz %u max_pages %d\n", + __func__, max_resp_sz, max_pages); + + dev = kmalloc(sizeof(*dev), GFP_NOFS); + if (!dev) { + dprintk("%s kmalloc failed\n", __func__); + return NULL; + } + + pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS); + if (pages == NULL) { + kfree(dev); + return NULL; + } + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(GFP_NOFS); + if (!pages[i]) + goto out_free; + } + + memcpy(&dev->dev_id, d_id, sizeof(*d_id)); + dev->layout_type = LAYOUT_BLOCK_VOLUME; + dev->pages = pages; + dev->pgbase = 0; + dev->pglen = PAGE_SIZE * max_pages; + dev->mincount = 0; + + dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data); + rc = nfs4_proc_getdeviceinfo(server, dev); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free; + + rv = nfs4_blk_decode_device(server, dev); + out_free: + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); + kfree(dev); + return rv; +} + +static int +bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) +{ + struct block_mount_id *b_mt_id = NULL; + struct pnfs_devicelist *dlist = NULL; + struct pnfs_block_dev *bdev; + LIST_HEAD(block_disklist); + int status = 0, i; + + dprintk("%s enter\n", __func__); + + if (server->pnfs_blksize == 0) { + dprintk("%s Server did not return blksize\n", __func__); + return -EINVAL; + } + b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS); + if (!b_mt_id) { + status = -ENOMEM; + goto out_error; + } + /* Initialize nfs4 block layout mount id */ + spin_lock_init(&b_mt_id->bm_lock); + INIT_LIST_HEAD(&b_mt_id->bm_devlist); + + dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS); + if (!dlist) { + status = -ENOMEM; + goto out_error; + } + dlist->eof = 0; + while (!dlist->eof) { + status = nfs4_proc_getdevicelist(server, fh, dlist); + if (status) + goto out_error; + dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n", + __func__, dlist->num_devs, dlist->eof); + for (i = 0; i < dlist->num_devs; i++) { + bdev = nfs4_blk_get_deviceinfo(server, fh, + &dlist->dev_id[i]); + if (!bdev) { + status = -ENODEV; + goto out_error; + } + spin_lock(&b_mt_id->bm_lock); + list_add(&bdev->bm_node, &b_mt_id->bm_devlist); + spin_unlock(&b_mt_id->bm_lock); + } + } + dprintk("%s SUCCESS\n", __func__); + server->pnfs_ld_data = b_mt_id; + + out_return: + kfree(dlist); + return status; + + out_error: + free_blk_mountid(b_mt_id); + goto out_return; +} + +static int +bl_clear_layoutdriver(struct nfs_server *server) +{ + struct block_mount_id *b_mt_id = server->pnfs_ld_data; + + dprintk("%s enter\n", __func__); + free_blk_mountid(b_mt_id); + dprintk("%s RETURNS\n", __func__); + return 0; +} + +static const struct nfs_pageio_ops bl_pg_read_ops = { + .pg_init = pnfs_generic_pg_init_read, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_readpages, +}; + +static const struct nfs_pageio_ops bl_pg_write_ops = { + .pg_init = pnfs_generic_pg_init_write, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_writepages, +}; + +static struct pnfs_layoutdriver_type blocklayout_type = { + .id = LAYOUT_BLOCK_VOLUME, + .name = "LAYOUT_BLOCK_VOLUME", + .read_pagelist = bl_read_pagelist, + .write_pagelist = bl_write_pagelist, + .alloc_layout_hdr = bl_alloc_layout_hdr, + .free_layout_hdr = bl_free_layout_hdr, + .alloc_lseg = bl_alloc_lseg, + .free_lseg = bl_free_lseg, + .encode_layoutcommit = bl_encode_layoutcommit, + .cleanup_layoutcommit = bl_cleanup_layoutcommit, + .set_layoutdriver = bl_set_layoutdriver, + .clear_layoutdriver = bl_clear_layoutdriver, + .pg_read_ops = &bl_pg_read_ops, + .pg_write_ops = &bl_pg_write_ops, +}; + +static const struct rpc_pipe_ops bl_upcall_ops = { + .upcall = bl_pipe_upcall, + .downcall = bl_pipe_downcall, + .destroy_msg = bl_pipe_destroy_msg, +}; + +static int __init nfs4blocklayout_init(void) +{ + struct vfsmount *mnt; + struct path path; + int ret; + + dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__); + + ret = pnfs_register_layoutdriver(&blocklayout_type); + if (ret) + goto out; + + init_waitqueue_head(&bl_wq); + + mnt = rpc_get_mount(); + if (IS_ERR(mnt)) { + ret = PTR_ERR(mnt); + goto out_remove; + } + + ret = vfs_path_lookup(mnt->mnt_root, + mnt, + NFS_PIPE_DIRNAME, 0, &path); + if (ret) + goto out_remove; + + bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL, + &bl_upcall_ops, 0); + if (IS_ERR(bl_device_pipe)) { + ret = PTR_ERR(bl_device_pipe); + goto out_remove; + } +out: + return ret; + +out_remove: + pnfs_unregister_layoutdriver(&blocklayout_type); + return ret; +} + +static void __exit nfs4blocklayout_exit(void) +{ + dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n", + __func__); + + pnfs_unregister_layoutdriver(&blocklayout_type); + rpc_unlink(bl_device_pipe); +} + +MODULE_ALIAS("nfs-layouttype4-3"); + +module_init(nfs4blocklayout_init); +module_exit(nfs4blocklayout_exit); diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h new file mode 100644 index 0000000..f27d827 --- /dev/null +++ b/fs/nfs/blocklayout/blocklayout.h @@ -0,0 +1,207 @@ +/* + * linux/fs/nfs/blocklayout/blocklayout.h + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ +#ifndef FS_NFS_NFS4BLOCKLAYOUT_H +#define FS_NFS_NFS4BLOCKLAYOUT_H + +#include <linux/device-mapper.h> +#include <linux/nfs_fs.h> +#include <linux/sunrpc/rpc_pipe_fs.h> + +#include "../pnfs.h" + +#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT) +#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT) + +struct block_mount_id { + spinlock_t bm_lock; /* protects list */ + struct list_head bm_devlist; /* holds pnfs_block_dev */ +}; + +struct pnfs_block_dev { + struct list_head bm_node; + struct nfs4_deviceid bm_mdevid; /* associated devid */ + struct block_device *bm_mdev; /* meta device itself */ +}; + +enum exstate4 { + PNFS_BLOCK_READWRITE_DATA = 0, + PNFS_BLOCK_READ_DATA = 1, + PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */ + PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */ +}; + +#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */ + +struct my_tree { + sector_t mtt_step_size; /* Internal sector alignment */ + struct list_head mtt_stub; /* Should be a radix tree */ +}; + +struct pnfs_inval_markings { + spinlock_t im_lock; + struct my_tree im_tree; /* Sectors that need LAYOUTCOMMIT */ + sector_t im_block_size; /* Server blocksize in sectors */ +}; + +struct pnfs_inval_tracking { + struct list_head it_link; + int it_sector; + int it_tags; +}; + +/* sector_t fields are all in 512-byte sectors */ +struct pnfs_block_extent { + struct kref be_refcnt; + struct list_head be_node; /* link into lseg list */ + struct nfs4_deviceid be_devid; /* FIXME: could use device cache instead */ + struct block_device *be_mdev; + sector_t be_f_offset; /* the starting offset in the file */ + sector_t be_length; /* the size of the extent */ + sector_t be_v_offset; /* the starting offset in the volume */ + enum exstate4 be_state; /* the state of this extent */ + struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */ +}; + +/* Shortened extent used by LAYOUTCOMMIT */ +struct pnfs_block_short_extent { + struct list_head bse_node; + struct nfs4_deviceid bse_devid; + struct block_device *bse_mdev; + sector_t bse_f_offset; /* the starting offset in the file */ + sector_t bse_length; /* the size of the extent */ +}; + +static inline void +BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize) +{ + spin_lock_init(&marks->im_lock); + INIT_LIST_HEAD(&marks->im_tree.mtt_stub); + marks->im_block_size = blocksize; + marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS, + blocksize); +} + +enum extentclass4 { + RW_EXTENT = 0, /* READWRTE and INVAL */ + RO_EXTENT = 1, /* READ and NONE */ + EXTENT_LISTS = 2, +}; + +static inline int bl_choose_list(enum exstate4 state) +{ + if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA) + return RO_EXTENT; + else + return RW_EXTENT; +} + +struct pnfs_block_layout { + struct pnfs_layout_hdr bl_layout; + struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */ + spinlock_t bl_ext_lock; /* Protects list manipulation */ + struct list_head bl_extents[EXTENT_LISTS]; /* R and RW extents */ + struct list_head bl_commit; /* Needs layout commit */ + struct list_head bl_committing; /* Layout committing */ + unsigned int bl_count; /* entries in bl_commit */ + sector_t bl_blocksize; /* Server blocksize in sectors */ +}; + +#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data)) + +static inline struct pnfs_block_layout * +BLK_LO2EXT(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct pnfs_block_layout, bl_layout); +} + +static inline struct pnfs_block_layout * +BLK_LSEG2EXT(struct pnfs_layout_segment *lseg) +{ + return BLK_LO2EXT(lseg->pls_layout); +} + +struct bl_dev_msg { + int status; + uint32_t major, minor; +}; + +struct bl_msg_hdr { + u8 type; + u16 totallen; /* length of entire message, including hdr itself */ +}; + +extern struct dentry *bl_device_pipe; +extern wait_queue_head_t bl_wq; + +#define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */ +#define BL_DEVICE_MOUNT 0x1 /* Mount--create devices*/ +#define BL_DEVICE_REQUEST_INIT 0x0 /* Start request */ +#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */ +#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */ + +/* blocklayoutdev.c */ +ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *, + char __user *, size_t); +ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t); +void bl_pipe_destroy_msg(struct rpc_pipe_msg *); +struct block_device *nfs4_blkdev_get(dev_t dev); +int nfs4_blkdev_put(struct block_device *bdev); +struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server, + struct pnfs_device *dev); +int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, + struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); + +/* blocklayoutdm.c */ +void bl_free_block_dev(struct pnfs_block_dev *bdev); + +/* extents.c */ +struct pnfs_block_extent * +bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent **cow_read); +int bl_mark_sectors_init(struct pnfs_inval_markings *marks, + sector_t offset, sector_t length, + sector_t **pages); +void bl_put_extent(struct pnfs_block_extent *be); +struct pnfs_block_extent *bl_alloc_extent(void); +int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect); +int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, + struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *arg); +void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, + const struct nfs4_layoutcommit_args *arg, + int status); +int bl_add_merge_extent(struct pnfs_block_layout *bl, + struct pnfs_block_extent *new); +int bl_mark_for_commit(struct pnfs_block_extent *be, + sector_t offset, sector_t length); + +#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */ diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c new file mode 100644 index 0000000..a83b393 --- /dev/null +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -0,0 +1,410 @@ +/* + * linux/fs/nfs/blocklayout/blocklayoutdev.c + * + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ +#include <linux/module.h> +#include <linux/buffer_head.h> /* __bread */ + +#include <linux/genhd.h> +#include <linux/blkdev.h> +#include <linux/hash.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static int decode_sector_number(__be32 **rp, sector_t *sp) +{ + uint64_t s; + + *rp = xdr_decode_hyper(*rp, &s); + if (s & 0x1ff) { + printk(KERN_WARNING "%s: sector not aligned\n", __func__); + return -1; + } + *sp = s >> SECTOR_SHIFT; + return 0; +} + +/* Open a block_device by device number. */ +struct block_device *nfs4_blkdev_get(dev_t dev) +{ + struct block_device *bd; + + dprintk("%s enter\n", __func__); + bd = blkdev_get_by_dev(dev, FMODE_READ, NULL); + if (IS_ERR(bd)) + goto fail; + return bd; +fail: + dprintk("%s failed to open device : %ld\n", + __func__, PTR_ERR(bd)); + return NULL; +} + +/* + * Release the block device + */ +int nfs4_blkdev_put(struct block_device *bdev) +{ + dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev), + MINOR(bdev->bd_dev)); + return blkdev_put(bdev, FMODE_READ); +} + +/* + * Shouldn't there be a rpc_generic_upcall() to do this for us? + */ +ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg, + char __user *dst, size_t buflen) +{ + char *data = (char *)msg->data + msg->copied; + size_t mlen = min(msg->len - msg->copied, buflen); + unsigned long left; + + left = copy_to_user(dst, data, mlen); + if (left == mlen) { + msg->errno = -EFAULT; + return -EFAULT; + } + + mlen -= left; + msg->copied += mlen; + msg->errno = 0; + return mlen; +} + +static struct bl_dev_msg bl_mount_reply; + +ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, + size_t mlen) +{ + if (mlen != sizeof (struct bl_dev_msg)) + return -EINVAL; + + if (copy_from_user(&bl_mount_reply, src, mlen) != 0) + return -EFAULT; + + wake_up(&bl_wq); + + return mlen; +} + +void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) +{ + if (msg->errno >= 0) + return; + wake_up(&bl_wq); +} + +/* + * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf. + */ +struct pnfs_block_dev * +nfs4_blk_decode_device(struct nfs_server *server, + struct pnfs_device *dev) +{ + struct pnfs_block_dev *rv = NULL; + struct block_device *bd = NULL; + struct rpc_pipe_msg msg; + struct bl_msg_hdr bl_msg = { + .type = BL_DEVICE_MOUNT, + .totallen = dev->mincount, + }; + uint8_t *dataptr; + DECLARE_WAITQUEUE(wq, current); + struct bl_dev_msg *reply = &bl_mount_reply; + int offset, len, i; + + dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); + dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data, + dev->mincount); + + memset(&msg, 0, sizeof(msg)); + msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS); + if (!msg.data) { + rv = ERR_PTR(-ENOMEM); + goto out; + } + + memcpy(msg.data, &bl_msg, sizeof(bl_msg)); + dataptr = (uint8_t *) msg.data; + len = dev->mincount; + offset = sizeof(bl_msg); + for (i = 0; len > 0; i++) { + memcpy(&dataptr[offset], page_address(dev->pages[i]), + len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE); + len -= PAGE_CACHE_SIZE; + offset += PAGE_CACHE_SIZE; + } + msg.len = sizeof(bl_msg) + dev->mincount; + + dprintk("%s CALLING USERSPACE DAEMON\n", __func__); + add_wait_queue(&bl_wq, &wq); + if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) { + remove_wait_queue(&bl_wq, &wq); + goto out; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&bl_wq, &wq); + + if (reply->status != BL_DEVICE_REQUEST_PROC) { + dprintk("%s failed to open device: %d\n", + __func__, reply->status); + rv = ERR_PTR(-EINVAL); + goto out; + } + + bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor)); + if (IS_ERR(bd)) { + dprintk("%s failed to open device : %ld\n", + __func__, PTR_ERR(bd)); + goto out; + } + + rv = kzalloc(sizeof(*rv), GFP_NOFS); + if (!rv) { + rv = ERR_PTR(-ENOMEM); + goto out; + } + + rv->bm_mdev = bd; + memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid)); + dprintk("%s Created device %s with bd_block_size %u\n", + __func__, + bd->bd_disk->disk_name, + bd->bd_block_size); + +out: + kfree(msg.data); + return rv; +} + +/* Map deviceid returned by the server to constructed block_device */ +static struct block_device *translate_devid(struct pnfs_layout_hdr *lo, + struct nfs4_deviceid *id) +{ + struct block_device *rv = NULL; + struct block_mount_id *mid; + struct pnfs_block_dev *dev; + + dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id); + mid = BLK_ID(lo); + spin_lock(&mid->bm_lock); + list_for_each_entry(dev, &mid->bm_devlist, bm_node) { + if (memcmp(id->data, dev->bm_mdevid.data, + NFS4_DEVICEID4_SIZE) == 0) { + rv = dev->bm_mdev; + goto out; + } + } + out: + spin_unlock(&mid->bm_lock); + dprintk("%s returning %p\n", __func__, rv); + return rv; +} + +/* Tracks info needed to ensure extents in layout obey constraints of spec */ +struct layout_verification { + u32 mode; /* R or RW */ + u64 start; /* Expected start of next non-COW extent */ + u64 inval; /* Start of INVAL coverage */ + u64 cowread; /* End of COW read coverage */ +}; + +/* Verify the extent meets the layout requirements of the pnfs-block draft, + * section 2.3.1. + */ +static int verify_extent(struct pnfs_block_extent *be, + struct layout_verification *lv) +{ + if (lv->mode == IOMODE_READ) { + if (be->be_state == PNFS_BLOCK_READWRITE_DATA || + be->be_state == PNFS_BLOCK_INVALID_DATA) + return -EIO; + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } + /* lv->mode == IOMODE_RW */ + if (be->be_state == PNFS_BLOCK_READWRITE_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + if (lv->cowread > lv->start) + return -EIO; + lv->start += be->be_length; + lv->inval = lv->start; + return 0; + } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } else if (be->be_state == PNFS_BLOCK_READ_DATA) { + if (be->be_f_offset > lv->start) + return -EIO; + if (be->be_f_offset < lv->inval) + return -EIO; + if (be->be_f_offset < lv->cowread) + return -EIO; + /* It looks like you might want to min this with lv->start, + * but you really don't. + */ + lv->inval = lv->inval + be->be_length; + lv->cowread = be->be_f_offset + be->be_length; + return 0; + } else + return -EIO; +} + +/* XDR decode pnfs_block_layout4 structure */ +int +nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, + struct nfs4_layoutget_res *lgr, gfp_t gfp_flags) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + int i, status = -EIO; + uint32_t count; + struct pnfs_block_extent *be = NULL, *save; + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + __be32 *p; + struct layout_verification lv = { + .mode = lgr->range.iomode, + .start = lgr->range.offset >> SECTOR_SHIFT, + .inval = lgr->range.offset >> SECTOR_SHIFT, + .cowread = lgr->range.offset >> SECTOR_SHIFT, + }; + LIST_HEAD(extents); + + dprintk("---> %s\n", __func__); + + scratch = alloc_page(gfp_flags); + if (!scratch) + return -ENOMEM; + + xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err; + + count = be32_to_cpup(p++); + + dprintk("%s enter, number of extents %i\n", __func__, count); + p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count); + if (unlikely(!p)) + goto out_err; + + /* Decode individual extents, putting them in temporary + * staging area until whole layout is decoded to make error + * recovery easier. + */ + for (i = 0; i < count; i++) { + be = bl_alloc_extent(); + if (!be) { + status = -ENOMEM; + goto out_err; + } + memcpy(&be->be_devid, p, NFS4_DEVICEID4_SIZE); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + be->be_mdev = translate_devid(lo, &be->be_devid); + if (!be->be_mdev) + goto out_err; + + /* The next three values are read in as bytes, + * but stored as 512-byte sector lengths + */ + if (decode_sector_number(&p, &be->be_f_offset) < 0) + goto out_err; + if (decode_sector_number(&p, &be->be_length) < 0) + goto out_err; + if (decode_sector_number(&p, &be->be_v_offset) < 0) + goto out_err; + be->be_state = be32_to_cpup(p++); + if (be->be_state == PNFS_BLOCK_INVALID_DATA) + be->be_inval = &bl->bl_inval; + if (verify_extent(be, &lv)) { + dprintk("%s verify failed\n", __func__); + goto out_err; + } + list_add_tail(&be->be_node, &extents); + } + if (lgr->range.offset + lgr->range.length != + lv.start << SECTOR_SHIFT) { + dprintk("%s Final length mismatch\n", __func__); + be = NULL; + goto out_err; + } + if (lv.start < lv.cowread) { + dprintk("%s Final uncovered COW extent\n", __func__); + be = NULL; + goto out_err; + } + /* Extents decoded properly, now try to merge them in to + * existing layout extents. + */ + spin_lock(&bl->bl_ext_lock); + list_for_each_entry_safe(be, save, &extents, be_node) { + list_del(&be->be_node); + status = bl_add_merge_extent(bl, be); + if (status) { + spin_unlock(&bl->bl_ext_lock); + /* This is a fairly catastrophic error, as the + * entire layout extent lists are now corrupted. + * We should have some way to distinguish this. + */ + be = NULL; + goto out_err; + } + } + spin_unlock(&bl->bl_ext_lock); + status = 0; + out: + __free_page(scratch); + dprintk("%s returns %i\n", __func__, status); + return status; + + out_err: + bl_put_extent(be); + while (!list_empty(&extents)) { + be = list_first_entry(&extents, struct pnfs_block_extent, + be_node); + list_del(&be->be_node); + bl_put_extent(be); + } + goto out; +} diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c new file mode 100644 index 0000000..d055c75 --- /dev/null +++ b/fs/nfs/blocklayout/blocklayoutdm.c @@ -0,0 +1,111 @@ +/* + * linux/fs/nfs/blocklayout/blocklayoutdm.c + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2007 The Regents of the University of Michigan. + * All rights reserved. + * + * Fred Isaman <iisaman@umich.edu> + * Andy Adamson <andros@citi.umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include <linux/genhd.h> /* gendisk - used in a dprintk*/ +#include <linux/sched.h> +#include <linux/hash.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static void dev_remove(dev_t dev) +{ + struct rpc_pipe_msg msg; + struct bl_dev_msg bl_umount_request; + struct bl_msg_hdr bl_msg = { + .type = BL_DEVICE_UMOUNT, + .totallen = sizeof(bl_umount_request), + }; + uint8_t *dataptr; + DECLARE_WAITQUEUE(wq, current); + + dprintk("Entering %s\n", __func__); + + memset(&msg, 0, sizeof(msg)); + msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS); + if (!msg.data) + goto out; + + memset(&bl_umount_request, 0, sizeof(bl_umount_request)); + bl_umount_request.major = MAJOR(dev); + bl_umount_request.minor = MINOR(dev); + + memcpy(msg.data, &bl_msg, sizeof(bl_msg)); + dataptr = (uint8_t *) msg.data; + memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request)); + msg.len = sizeof(bl_msg) + bl_msg.totallen; + + add_wait_queue(&bl_wq, &wq); + if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) { + remove_wait_queue(&bl_wq, &wq); + goto out; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&bl_wq, &wq); + +out: + kfree(msg.data); +} + +/* + * Release meta device + */ +static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev) +{ + int rv; + + dprintk("%s Releasing\n", __func__); + rv = nfs4_blkdev_put(bdev->bm_mdev); + if (rv) + printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n", + __func__, rv); + + dev_remove(bdev->bm_mdev->bd_dev); +} + +void bl_free_block_dev(struct pnfs_block_dev *bdev) +{ + if (bdev) { + if (bdev->bm_mdev) { + dprintk("%s Removing DM device: %d:%d\n", + __func__, + MAJOR(bdev->bm_mdev->bd_dev), + MINOR(bdev->bm_mdev->bd_dev)); + nfs4_blk_metadev_release(bdev); + } + kfree(bdev); + } +} diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c new file mode 100644 index 0000000..19fa7b0 --- /dev/null +++ b/fs/nfs/blocklayout/extents.c @@ -0,0 +1,935 @@ +/* + * linux/fs/nfs/blocklayout/blocklayout.h + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include "blocklayout.h" +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +/* Bit numbers */ +#define EXTENT_INITIALIZED 0 +#define EXTENT_WRITTEN 1 +#define EXTENT_IN_COMMIT 2 +#define INTERNAL_EXISTS MY_MAX_TAGS +#define INTERNAL_MASK ((1 << INTERNAL_EXISTS) - 1) + +/* Returns largest t<=s s.t. t%base==0 */ +static inline sector_t normalize(sector_t s, int base) +{ + sector_t tmp = s; /* Since do_div modifies its argument */ + return s - do_div(tmp, base); +} + +static inline sector_t normalize_up(sector_t s, int base) +{ + return normalize(s + base - 1, base); +} + +/* Complete stub using list while determine API wanted */ + +/* Returns tags, or negative */ +static int32_t _find_entry(struct my_tree *tree, u64 s) +{ + struct pnfs_inval_tracking *pos; + + dprintk("%s(%llu) enter\n", __func__, s); + list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { + if (pos->it_sector > s) + continue; + else if (pos->it_sector == s) + return pos->it_tags & INTERNAL_MASK; + else + break; + } + return -ENOENT; +} + +static inline +int _has_tag(struct my_tree *tree, u64 s, int32_t tag) +{ + int32_t tags; + + dprintk("%s(%llu, %i) enter\n", __func__, s, tag); + s = normalize(s, tree->mtt_step_size); + tags = _find_entry(tree, s); + if ((tags < 0) || !(tags & (1 << tag))) + return 0; + else + return 1; +} + +/* Creates entry with tag, or if entry already exists, unions tag to it. + * If storage is not NULL, newly created entry will use it. + * Returns number of entries added, or negative on error. + */ +static int _add_entry(struct my_tree *tree, u64 s, int32_t tag, + struct pnfs_inval_tracking *storage) +{ + int found = 0; + struct pnfs_inval_tracking *pos; + + dprintk("%s(%llu, %i, %p) enter\n", __func__, s, tag, storage); + list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { + if (pos->it_sector > s) + continue; + else if (pos->it_sector == s) { + found = 1; + break; + } else + break; + } + if (found) { + pos->it_tags |= (1 << tag); + return 0; + } else { + struct pnfs_inval_tracking *new; + if (storage) + new = storage; + else { + new = kmalloc(sizeof(*new), GFP_NOFS); + if (!new) + return -ENOMEM; + } + new->it_sector = s; + new->it_tags = (1 << tag); + list_add(&new->it_link, &pos->it_link); + return 1; + } +} + +/* XXXX Really want option to not create */ +/* Over range, unions tag with existing entries, else creates entry with tag */ +static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length) +{ + u64 i; + + dprintk("%s(%i, %llu, %llu) enter\n", __func__, tag, s, length); + for (i = normalize(s, tree->mtt_step_size); i < s + length; + i += tree->mtt_step_size) + if (_add_entry(tree, i, tag, NULL)) + return -ENOMEM; + return 0; +} + +/* Ensure that future operations on given range of tree will not malloc */ +static int _preload_range(struct my_tree *tree, u64 offset, u64 length) +{ + u64 start, end, s; + int count, i, used = 0, status = -ENOMEM; + struct pnfs_inval_tracking **storage; + + dprintk("%s(%llu, %llu) enter\n", __func__, offset, length); + start = normalize(offset, tree->mtt_step_size); + end = normalize_up(offset + length, tree->mtt_step_size); + count = (int)(end - start) / (int)tree->mtt_step_size; + + /* Pre-malloc what memory we might need */ + storage = kmalloc(sizeof(*storage) * count, GFP_NOFS); + if (!storage) + return -ENOMEM; + for (i = 0; i < count; i++) { + storage[i] = kmalloc(sizeof(struct pnfs_inval_tracking), + GFP_NOFS); + if (!storage[i]) + goto out_cleanup; + } + + /* Now need lock - HOW??? */ + + for (s = start; s < end; s += tree->mtt_step_size) + used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]); + + /* Unlock - HOW??? */ + status = 0; + + out_cleanup: + for (i = used; i < count; i++) { + if (!storage[i]) + break; + kfree(storage[i]); + } + kfree(storage); + return status; +} + +static void set_needs_init(sector_t *array, sector_t offset) +{ + sector_t *p = array; + + dprintk("%s enter\n", __func__); + if (!p) + return; + while (*p < offset) + p++; + if (*p == offset) + return; + else if (*p == ~0) { + *p++ = offset; + *p = ~0; + return; + } else { + sector_t *save = p; + dprintk("%s Adding %llu\n", __func__, (u64)offset); + while (*p != ~0) + p++; + p++; + memmove(save + 1, save, (char *)p - (char *)save); + *save = offset; + return; + } +} + +/* We are relying on page lock to serialize this */ +int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect) +{ + int rv; + + spin_lock(&marks->im_lock); + rv = _has_tag(&marks->im_tree, isect, EXTENT_INITIALIZED); + spin_unlock(&marks->im_lock); + return rv; +} + +/* Assume start, end already sector aligned */ +static int +_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag) +{ + struct pnfs_inval_tracking *pos; + u64 expect = 0; + + dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag); + list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) { + if (pos->it_sector >= end) + continue; + if (!expect) { + if ((pos->it_sector == end - tree->mtt_step_size) && + (pos->it_tags & (1 << tag))) { + expect = pos->it_sector - tree->mtt_step_size; + if (pos->it_sector < tree->mtt_step_size || expect < start) + return 1; + continue; + } else { + return 0; + } + } + if (pos->it_sector != expect || !(pos->it_tags & (1 << tag))) + return 0; + expect -= tree->mtt_step_size; + if (expect < start) + return 1; + } + return 0; +} + +static int is_range_written(struct pnfs_inval_markings *marks, + sector_t start, sector_t end) +{ + int rv; + + spin_lock(&marks->im_lock); + rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN); + spin_unlock(&marks->im_lock); + return rv; +} + +/* Marks sectors in [offest, offset_length) as having been initialized. + * All lengths are step-aligned, where step is min(pagesize, blocksize). + * Notes where partial block is initialized, and helps prepare it for + * complete initialization later. + */ +/* Currently assumes offset is page-aligned */ +int bl_mark_sectors_init(struct pnfs_inval_markings *marks, + sector_t offset, sector_t length, + sector_t **pages) +{ + sector_t s, start, end; + sector_t *array = NULL; /* Pages to mark */ + + dprintk("%s(offset=%llu,len=%llu) enter\n", + __func__, (u64)offset, (u64)length); + s = max((sector_t) 3, + 2 * (marks->im_block_size / (PAGE_CACHE_SECTORS))); + dprintk("%s set max=%llu\n", __func__, (u64)s); + if (pages) { + array = kmalloc(s * sizeof(sector_t), GFP_NOFS); + if (!array) + goto outerr; + array[0] = ~0; + } + + start = normalize(offset, marks->im_block_size); + end = normalize_up(offset + length, marks->im_block_size); + if (_preload_range(&marks->im_tree, start, end - start)) + goto outerr; + + spin_lock(&marks->im_lock); + + for (s = normalize_up(start, PAGE_CACHE_SECTORS); + s < offset; s += PAGE_CACHE_SECTORS) { + dprintk("%s pre-area pages\n", __func__); + /* Portion of used block is not initialized */ + if (!_has_tag(&marks->im_tree, s, EXTENT_INITIALIZED)) + set_needs_init(array, s); + } + if (_set_range(&marks->im_tree, EXTENT_INITIALIZED, offset, length)) + goto out_unlock; + for (s = normalize_up(offset + length, PAGE_CACHE_SECTORS); + s < end; s += PAGE_CACHE_SECTORS) { + dprintk("%s post-area pages\n", __func__); + if (!_has_tag(&marks->im_tree, s, EXTENT_INITIALIZED)) + set_needs_init(array, s); + } + + spin_unlock(&marks->im_lock); + + if (pages) { + if (array[0] == ~0) { + kfree(array); + *pages = NULL; + } else + *pages = array; + } + return 0; + + out_unlock: + spin_unlock(&marks->im_lock); + outerr: + if (pages) { + kfree(array); + *pages = NULL; + } + return -ENOMEM; +} + +/* Marks sectors in [offest, offset+length) as having been written to disk. + * All lengths should be block aligned. + */ +static int mark_written_sectors(struct pnfs_inval_markings *marks, + sector_t offset, sector_t length) +{ + int status; + + dprintk("%s(offset=%llu,len=%llu) enter\n", __func__, + (u64)offset, (u64)length); + spin_lock(&marks->im_lock); + status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length); + spin_unlock(&marks->im_lock); + return status; +} + +static void print_short_extent(struct pnfs_block_short_extent *be) +{ + dprintk("PRINT SHORT EXTENT extent %p\n", be); + if (be) { + dprintk(" be_f_offset %llu\n", (u64)be->bse_f_offset); + dprintk(" be_length %llu\n", (u64)be->bse_length); + } +} + +static void print_clist(struct list_head *list, unsigned int count) +{ + struct pnfs_block_short_extent *be; + unsigned int i = 0; + + ifdebug(FACILITY) { + printk(KERN_DEBUG "****************\n"); + printk(KERN_DEBUG "Extent list looks like:\n"); + list_for_each_entry(be, list, bse_node) { + i++; + print_short_extent(be); + } + if (i != count) + printk(KERN_DEBUG "\n\nExpected %u entries\n\n\n", count); + printk(KERN_DEBUG "****************\n"); + } +} + +/* Note: In theory, we should do more checking that devid's match between + * old and new, but if they don't, the lists are too corrupt to salvage anyway. + */ +/* Note this is very similar to bl_add_merge_extent */ +static void add_to_commitlist(struct pnfs_block_layout *bl, + struct pnfs_block_short_extent *new) +{ + struct list_head *clist = &bl->bl_commit; + struct pnfs_block_short_extent *old, *save; + sector_t end = new->bse_f_offset + new->bse_length; + + dprintk("%s enter\n", __func__); + print_short_extent(new); + print_clist(clist, bl->bl_count); + bl->bl_count++; + /* Scan for proper place to insert, extending new to the left + * as much as possible. + */ + list_for_each_entry_safe(old, save, clist, bse_node) { + if (new->bse_f_offset < old->bse_f_offset) + break; + if (end <= old->bse_f_offset + old->bse_length) { + /* Range is already in list */ + bl->bl_count--; + kfree(new); + return; + } else if (new->bse_f_offset <= + old->bse_f_offset + old->bse_length) { + /* new overlaps or abuts existing be */ + if (new->bse_mdev == old->bse_mdev) { + /* extend new to fully replace old */ + new->bse_length += new->bse_f_offset - + old->bse_f_offset; + new->bse_f_offset = old->bse_f_offset; + list_del(&old->bse_node); + bl->bl_count--; + kfree(old); + } + } + } + /* Note that if we never hit the above break, old will not point to a + * valid extent. However, in that case &old->bse_node==list. + */ + list_add_tail(&new->bse_node, &old->bse_node); + /* Scan forward for overlaps. If we find any, extend new and + * remove the overlapped extent. + */ + old = list_prepare_entry(new, clist, bse_node); + list_for_each_entry_safe_continue(old, save, clist, bse_node) { + if (end < old->bse_f_offset) + break; + /* new overlaps or abuts old */ + if (new->bse_mdev == old->bse_mdev) { + if (end < old->bse_f_offset + old->bse_length) { + /* extend new to fully cover old */ + end = old->bse_f_offset + old->bse_length; + new->bse_length = end - new->bse_f_offset; + } + list_del(&old->bse_node); + bl->bl_count--; + kfree(old); + } + } + dprintk("%s: after merging\n", __func__); + print_clist(clist, bl->bl_count); +} + +/* Note the range described by offset, length is guaranteed to be contained + * within be. + */ +int bl_mark_for_commit(struct pnfs_block_extent *be, + sector_t offset, sector_t length) +{ + sector_t new_end, end = offset + length; + struct pnfs_block_short_extent *new; + struct pnfs_block_layout *bl = container_of(be->be_inval, + struct pnfs_block_layout, + bl_inval); + + new = kmalloc(sizeof(*new), GFP_NOFS); + if (!new) + return -ENOMEM; + + mark_written_sectors(be->be_inval, offset, length); + /* We want to add the range to commit list, but it must be + * block-normalized, and verified that the normalized range has + * been entirely written to disk. + */ + new->bse_f_offset = offset; + offset = normalize(offset, bl->bl_blocksize); + if (offset < new->bse_f_offset) { + if (is_range_written(be->be_inval, offset, new->bse_f_offset)) + new->bse_f_offset = offset; + else + new->bse_f_offset = offset + bl->bl_blocksize; + } + new_end = normalize_up(end, bl->bl_blocksize); + if (end < new_end) { + if (is_range_written(be->be_inval, end, new_end)) + end = new_end; + else + end = new_end - bl->bl_blocksize; + } + if (end <= new->bse_f_offset) { + kfree(new); + return 0; + } + new->bse_length = end - new->bse_f_offset; + new->bse_devid = be->be_devid; + new->bse_mdev = be->be_mdev; + + spin_lock(&bl->bl_ext_lock); + /* new will be freed, either by add_to_commitlist if it decides not + * to use it, or after LAYOUTCOMMIT uses it in the commitlist. + */ + add_to_commitlist(bl, new); + spin_unlock(&bl->bl_ext_lock); + return 0; +} + +static void print_bl_extent(struct pnfs_block_extent *be) +{ + dprintk("PRINT EXTENT extent %p\n", be); + if (be) { + dprintk(" be_f_offset %llu\n", (u64)be->be_f_offset); + dprintk(" be_length %llu\n", (u64)be->be_length); + dprintk(" be_v_offset %llu\n", (u64)be->be_v_offset); + dprintk(" be_state %d\n", be->be_state); + } +} + +static void +destroy_extent(struct kref *kref) +{ + struct pnfs_block_extent *be; + + be = container_of(kref, struct pnfs_block_extent, be_refcnt); + dprintk("%s be=%p\n", __func__, be); + kfree(be); +} + +void +bl_put_extent(struct pnfs_block_extent *be) +{ + if (be) { + dprintk("%s enter %p (%i)\n", __func__, be, + atomic_read(&be->be_refcnt.refcount)); + kref_put(&be->be_refcnt, destroy_extent); + } +} + +struct pnfs_block_extent *bl_alloc_extent(void) +{ + struct pnfs_block_extent *be; + + be = kmalloc(sizeof(struct pnfs_block_extent), GFP_NOFS); + if (!be) + return NULL; + INIT_LIST_HEAD(&be->be_node); + kref_init(&be->be_refcnt); + be->be_inval = NULL; + return be; +} + +static void print_elist(struct list_head *list) +{ + struct pnfs_block_extent *be; + dprintk("****************\n"); + dprintk("Extent list looks like:\n"); + list_for_each_entry(be, list, be_node) { + print_bl_extent(be); + } + dprintk("****************\n"); +} + +static inline int +extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new) +{ + /* Note this assumes new->be_f_offset >= old->be_f_offset */ + return (new->be_state == old->be_state) && + ((new->be_state == PNFS_BLOCK_NONE_DATA) || + ((new->be_v_offset - old->be_v_offset == + new->be_f_offset - old->be_f_offset) && + new->be_mdev == old->be_mdev)); +} + +/* Adds new to appropriate list in bl, modifying new and removing existing + * extents as appropriate to deal with overlaps. + * + * See bl_find_get_extent for list constraints. + * + * Refcount on new is already set. If end up not using it, or error out, + * need to put the reference. + * + * bl->bl_ext_lock is held by caller. + */ +int +bl_add_merge_extent(struct pnfs_block_layout *bl, + struct pnfs_block_extent *new) +{ + struct pnfs_block_extent *be, *tmp; + sector_t end = new->be_f_offset + new->be_length; + struct list_head *list; + + dprintk("%s enter with be=%p\n", __func__, new); + print_bl_extent(new); + list = &bl->bl_extents[bl_choose_list(new->be_state)]; + print_elist(list); + + /* Scan for proper place to insert, extending new to the left + * as much as possible. + */ + list_for_each_entry_safe_reverse(be, tmp, list, be_node) { + if (new->be_f_offset >= be->be_f_offset + be->be_length) + break; + if (new->be_f_offset >= be->be_f_offset) { + if (end <= be->be_f_offset + be->be_length) { + /* new is a subset of existing be*/ + if (extents_consistent(be, new)) { + dprintk("%s: new is subset, ignoring\n", + __func__); + bl_put_extent(new); + return 0; + } else { + goto out_err; + } + } else { + /* |<-- be -->| + * |<-- new -->| */ + if (extents_consistent(be, new)) { + /* extend new to fully replace be */ + new->be_length += new->be_f_offset - + be->be_f_offset; + new->be_f_offset = be->be_f_offset; + new->be_v_offset = be->be_v_offset; + dprintk("%s: removing %p\n", __func__, be); + list_del(&be->be_node); + bl_put_extent(be); + } else { + goto out_err; + } + } + } else if (end >= be->be_f_offset + be->be_length) { + /* new extent overlap existing be */ + if (extents_consistent(be, new)) { + /* extend new to fully replace be */ + dprintk("%s: removing %p\n", __func__, be); + list_del(&be->be_node); + bl_put_extent(be); + } else { + goto out_err; + } + } else if (end > be->be_f_offset) { + /* |<-- be -->| + *|<-- new -->| */ + if (extents_consistent(new, be)) { + /* extend new to fully replace be */ + new->be_length += be->be_f_offset + be->be_length - + new->be_f_offset - new->be_length; + dprintk("%s: removing %p\n", __func__, be); + list_del(&be->be_node); + bl_put_extent(be); + } else { + goto out_err; + } + } + } + /* Note that if we never hit the above break, be will not point to a + * valid extent. However, in that case &be->be_node==list. + */ + list_add(&new->be_node, &be->be_node); + dprintk("%s: inserting new\n", __func__); + print_elist(list); + /* FIXME - The per-list consistency checks have all been done, + * should now check cross-list consistency. + */ + return 0; + + out_err: + bl_put_extent(new); + return -EIO; +} + +/* Returns extent, or NULL. If a second READ extent exists, it is returned + * in cow_read, if given. + * + * The extents are kept in two seperate ordered lists, one for READ and NONE, + * one for READWRITE and INVALID. Within each list, we assume: + * 1. Extents are ordered by file offset. + * 2. For any given isect, there is at most one extents that matches. + */ +struct pnfs_block_extent * +bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent **cow_read) +{ + struct pnfs_block_extent *be, *cow, *ret; + int i; + + dprintk("%s enter with isect %llu\n", __func__, (u64)isect); + cow = ret = NULL; + spin_lock(&bl->bl_ext_lock); + for (i = 0; i < EXTENT_LISTS; i++) { + list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) { + if (isect >= be->be_f_offset + be->be_length) + break; + if (isect >= be->be_f_offset) { + /* We have found an extent */ + dprintk("%s Get %p (%i)\n", __func__, be, + atomic_read(&be->be_refcnt.refcount)); + kref_get(&be->be_refcnt); + if (!ret) + ret = be; + else if (be->be_state != PNFS_BLOCK_READ_DATA) + bl_put_extent(be); + else + cow = be; + break; + } + } + if (ret && + (!cow_read || ret->be_state != PNFS_BLOCK_INVALID_DATA)) + break; + } + spin_unlock(&bl->bl_ext_lock); + if (cow_read) + *cow_read = cow; + print_bl_extent(ret); + return ret; +} + +/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */ +static struct pnfs_block_extent * +bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect) +{ + struct pnfs_block_extent *be, *ret = NULL; + int i; + + dprintk("%s enter with isect %llu\n", __func__, (u64)isect); + for (i = 0; i < EXTENT_LISTS; i++) { + if (ret) + break; + list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) { + if (isect >= be->be_f_offset + be->be_length) + break; + if (isect >= be->be_f_offset) { + /* We have found an extent */ + dprintk("%s Get %p (%i)\n", __func__, be, + atomic_read(&be->be_refcnt.refcount)); + kref_get(&be->be_refcnt); + ret = be; + break; + } + } + } + print_bl_extent(ret); + return ret; +} + +int +encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, + struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *arg) +{ + struct pnfs_block_short_extent *lce, *save; + unsigned int count = 0; + __be32 *p, *xdr_start; + + dprintk("%s enter\n", __func__); + /* BUG - creation of bl_commit is buggy - need to wait for + * entire block to be marked WRITTEN before it can be added. + */ + spin_lock(&bl->bl_ext_lock); + /* Want to adjust for possible truncate */ + /* We now want to adjust argument range */ + + /* XDR encode the ranges found */ + xdr_start = xdr_reserve_space(xdr, 8); + if (!xdr_start) + goto out; + list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) { + p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data)); + if (!p) + break; + p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE); + p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT); + p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT); + p = xdr_encode_hyper(p, 0LL); + *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA); + list_del(&lce->bse_node); + list_add_tail(&lce->bse_node, &bl->bl_committing); + bl->bl_count--; + count++; + } + xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4); + xdr_start[1] = cpu_to_be32(count); +out: + spin_unlock(&bl->bl_ext_lock); + dprintk("%s found %i ranges\n", __func__, count); + return 0; +} + +/* Helper function to set_to_rw that initialize a new extent */ +static void +_prep_new_extent(struct pnfs_block_extent *new, + struct pnfs_block_extent *orig, + sector_t offset, sector_t length, int state) +{ + kref_init(&new->be_refcnt); + /* don't need to INIT_LIST_HEAD(&new->be_node) */ + memcpy(&new->be_devid, &orig->be_devid, sizeof(struct nfs4_deviceid)); + new->be_mdev = orig->be_mdev; + new->be_f_offset = offset; + new->be_length = length; + new->be_v_offset = orig->be_v_offset - orig->be_f_offset + offset; + new->be_state = state; + new->be_inval = orig->be_inval; +} + +/* Tries to merge be with extent in front of it in list. + * Frees storage if not used. + */ +static struct pnfs_block_extent * +_front_merge(struct pnfs_block_extent *be, struct list_head *head, + struct pnfs_block_extent *storage) +{ + struct pnfs_block_extent *prev; + + if (!storage) + goto no_merge; + if (&be->be_node == head || be->be_node.prev == head) + goto no_merge; + prev = list_entry(be->be_node.prev, struct pnfs_block_extent, be_node); + if ((prev->be_f_offset + prev->be_length != be->be_f_offset) || + !extents_consistent(prev, be)) + goto no_merge; + _prep_new_extent(storage, prev, prev->be_f_offset, + prev->be_length + be->be_length, prev->be_state); + list_replace(&prev->be_node, &storage->be_node); + bl_put_extent(prev); + list_del(&be->be_node); + bl_put_extent(be); + return storage; + + no_merge: + kfree(storage); + return be; +} + +static u64 +set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length) +{ + u64 rv = offset + length; + struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old; + struct pnfs_block_extent *children[3]; + struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL; + int i = 0, j; + + dprintk("%s(%llu, %llu)\n", __func__, offset, length); + /* Create storage for up to three new extents e1, e2, e3 */ + e1 = kmalloc(sizeof(*e1), GFP_ATOMIC); + e2 = kmalloc(sizeof(*e2), GFP_ATOMIC); + e3 = kmalloc(sizeof(*e3), GFP_ATOMIC); + /* BUG - we are ignoring any failure */ + if (!e1 || !e2 || !e3) + goto out_nosplit; + + spin_lock(&bl->bl_ext_lock); + be = bl_find_get_extent_locked(bl, offset); + rv = be->be_f_offset + be->be_length; + if (be->be_state != PNFS_BLOCK_INVALID_DATA) { + spin_unlock(&bl->bl_ext_lock); + goto out_nosplit; + } + /* Add e* to children, bumping e*'s krefs */ + if (be->be_f_offset != offset) { + _prep_new_extent(e1, be, be->be_f_offset, + offset - be->be_f_offset, + PNFS_BLOCK_INVALID_DATA); + children[i++] = e1; + print_bl_extent(e1); + } else + merge1 = e1; + _prep_new_extent(e2, be, offset, + min(length, be->be_f_offset + be->be_length - offset), + PNFS_BLOCK_READWRITE_DATA); + children[i++] = e2; + print_bl_extent(e2); + if (offset + length < be->be_f_offset + be->be_length) { + _prep_new_extent(e3, be, e2->be_f_offset + e2->be_length, + be->be_f_offset + be->be_length - + offset - length, + PNFS_BLOCK_INVALID_DATA); + children[i++] = e3; + print_bl_extent(e3); + } else + merge2 = e3; + + /* Remove be from list, and insert the e* */ + /* We don't get refs on e*, since this list is the base reference + * set when init'ed. + */ + if (i < 3) + children[i] = NULL; + new = children[0]; + list_replace(&be->be_node, &new->be_node); + bl_put_extent(be); + new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1); + for (j = 1; j < i; j++) { + old = new; + new = children[j]; + list_add(&new->be_node, &old->be_node); + } + if (merge2) { + /* This is a HACK, should just create a _back_merge function */ + new = list_entry(new->be_node.next, + struct pnfs_block_extent, be_node); + new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2); + } + spin_unlock(&bl->bl_ext_lock); + + /* Since we removed the base reference above, be is now scheduled for + * destruction. + */ + bl_put_extent(be); + dprintk("%s returns %llu after split\n", __func__, rv); + return rv; + + out_nosplit: + kfree(e1); + kfree(e2); + kfree(e3); + dprintk("%s returns %llu without splitting\n", __func__, rv); + return rv; +} + +void +clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl, + const struct nfs4_layoutcommit_args *arg, + int status) +{ + struct pnfs_block_short_extent *lce, *save; + + dprintk("%s status %d\n", __func__, status); + list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) { + if (likely(!status)) { + u64 offset = lce->bse_f_offset; + u64 end = offset + lce->bse_length; + + do { + offset = set_to_rw(bl, offset, end - offset); + } while (offset < end); + list_del(&lce->bse_node); + + kfree(lce); + } else { + list_del(&lce->bse_node); + spin_lock(&bl->bl_ext_lock); + add_to_commitlist(bl, lce); + spin_unlock(&bl->bl_ext_lock); + } + } +} diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 19ea7d9..5833fbb 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -105,7 +105,7 @@ struct rpc_program nfs_program = { .nrvers = ARRAY_SIZE(nfs_version), .version = nfs_version, .stats = &nfs_rpcstat, - .pipe_dir_name = "/nfs", + .pipe_dir_name = NFS_PIPE_DIRNAME, }; struct rpc_stat nfs_rpcstat = { @@ -904,7 +904,9 @@ error: /* * Load up the server record from information gained in an fsinfo record */ -static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo) +static void nfs_server_set_fsinfo(struct nfs_server *server, + struct nfs_fh *mntfh, + struct nfs_fsinfo *fsinfo) { unsigned long max_rpc_payload; @@ -934,7 +936,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo * if (server->wsize > NFS_MAX_FILE_IO_SIZE) server->wsize = NFS_MAX_FILE_IO_SIZE; server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - set_pnfs_layoutdriver(server, fsinfo->layouttype); + server->pnfs_blksize = fsinfo->blksize; + set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype); server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); @@ -980,7 +983,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str if (error < 0) goto out_error; - nfs_server_set_fsinfo(server, &fsinfo); + nfs_server_set_fsinfo(server, mntfh, &fsinfo); /* Get some general file system info */ if (server->namelen == 0) { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 57f578e..b238d95 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -134,18 +134,19 @@ const struct inode_operations nfs4_dir_inode_operations = { #endif /* CONFIG_NFS_V4 */ -static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct rpc_cred *cred) +static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) { struct nfs_open_dir_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (ctx != NULL) { ctx->duped = 0; + ctx->attr_gencount = NFS_I(dir)->attr_gencount; ctx->dir_cookie = 0; ctx->dup_cookie = 0; ctx->cred = get_rpccred(cred); - } else - ctx = ERR_PTR(-ENOMEM); - return ctx; + return ctx; + } + return ERR_PTR(-ENOMEM); } static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx) @@ -173,7 +174,7 @@ nfs_opendir(struct inode *inode, struct file *filp) cred = rpc_lookup_cred(); if (IS_ERR(cred)) return PTR_ERR(cred); - ctx = alloc_nfs_open_dir_context(cred); + ctx = alloc_nfs_open_dir_context(inode, cred); if (IS_ERR(ctx)) { res = PTR_ERR(ctx); goto out; @@ -323,7 +324,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri { loff_t diff = desc->file->f_pos - desc->current_index; unsigned int index; - struct nfs_open_dir_context *ctx = desc->file->private_data; if (diff < 0) goto out_eof; @@ -336,7 +336,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri index = (unsigned int)diff; *desc->dir_cookie = array->array[index].cookie; desc->cache_entry_index = index; - ctx->duped = 0; return 0; out_eof: desc->eof = 1; @@ -349,14 +348,34 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des int i; loff_t new_pos; int status = -EAGAIN; - struct nfs_open_dir_context *ctx = desc->file->private_data; for (i = 0; i < array->size; i++) { if (array->array[i].cookie == *desc->dir_cookie) { + struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode); + struct nfs_open_dir_context *ctx = desc->file->private_data; + new_pos = desc->current_index + i; - if (new_pos < desc->file->f_pos) { + if (ctx->attr_gencount != nfsi->attr_gencount + || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) { + ctx->duped = 0; + ctx->attr_gencount = nfsi->attr_gencount; + } else if (new_pos < desc->file->f_pos) { + if (ctx->duped > 0 + && ctx->dup_cookie == *desc->dir_cookie) { + if (printk_ratelimit()) { + pr_notice("NFS: directory %s/%s contains a readdir loop." + "Please contact your server vendor. " + "The file: %s has duplicate cookie %llu\n", + desc->file->f_dentry->d_parent->d_name.name, + desc->file->f_dentry->d_name.name, + array->array[i].string.name, + *desc->dir_cookie); + } + status = -ELOOP; + goto out; + } ctx->dup_cookie = *desc->dir_cookie; - ctx->duped = 1; + ctx->duped = -1; } desc->file->f_pos = new_pos; desc->cache_entry_index = i; @@ -368,6 +387,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des if (*desc->dir_cookie == array->last_cookie) desc->eof = 1; } +out: return status; } @@ -740,19 +760,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, struct nfs_cache_array *array = NULL; struct nfs_open_dir_context *ctx = file->private_data; - if (ctx->duped != 0 && ctx->dup_cookie == *desc->dir_cookie) { - if (printk_ratelimit()) { - pr_notice("NFS: directory %s/%s contains a readdir loop. " - "Please contact your server vendor. " - "Offending cookie: %llu\n", - file->f_dentry->d_parent->d_name.name, - file->f_dentry->d_name.name, - *desc->dir_cookie); - } - res = -ELOOP; - goto out; - } - array = nfs_readdir_get_array(desc->page); if (IS_ERR(array)) { res = PTR_ERR(array); @@ -774,6 +781,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, *desc->dir_cookie = array->array[i+1].cookie; else *desc->dir_cookie = array->last_cookie; + if (ctx->duped != 0) + ctx->duped = 1; } if (array->eof_index >= 0) desc->eof = 1; @@ -805,6 +814,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, struct page *page = NULL; int status; struct inode *inode = desc->file->f_path.dentry->d_inode; + struct nfs_open_dir_context *ctx = desc->file->private_data; dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", (unsigned long long)*desc->dir_cookie); @@ -818,6 +828,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, desc->page_index = 0; desc->last_cookie = *desc->dir_cookie; desc->page = page; + ctx->duped = 0; status = nfs_readdir_xdr_to_array(desc, page, inode); if (status < 0) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index e49e731..7ef2397 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -415,7 +415,7 @@ fail: } int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode) + umode_t mode) { struct posix_acl *dfacl, *acl; int error = 0; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 38053d8..85f1690 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -316,7 +316,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, int flags, struct nfs_open_context *ctx) { struct nfs3_createdata *data; - mode_t mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call create %s\n", dentry->d_name.name); @@ -562,7 +562,7 @@ static int nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct nfs3_createdata *data; - int mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call mkdir %s\n", dentry->d_name.name); @@ -681,7 +681,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, dev_t rdev) { struct nfs3_createdata *data; - mode_t mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call mknod %s %u:%u\n", dentry->d_name.name, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 1909ee8..1ec1a85 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; extern const u32 nfs4_fattr_bitmap[2]; extern const u32 nfs4_statfs_bitmap[2]; extern const u32 nfs4_pathconf_bitmap[2]; -extern const u32 nfs4_fsinfo_bitmap[2]; +extern const u32 nfs4_fsinfo_bitmap[3]; extern const u32 nfs4_fs_locations_bitmap[2]; /* nfs4renewd.c */ diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index be93a62..e8915d4 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -170,7 +170,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata) pnfs_set_layoutcommit(wdata); dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino, - (unsigned long) wdata->lseg->pls_end_pos); + (unsigned long) NFS_I(wdata->inode)->layout->plh_lwb); } /* diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 079614d..8c77039 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = { 0 }; -const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE +const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_LEASE_TIME, FATTR4_WORD1_TIME_DELTA - | FATTR4_WORD1_FS_LAYOUT_TYPES + | FATTR4_WORD1_FS_LAYOUT_TYPES, + FATTR4_WORD2_LAYOUT_BLKSIZE }; const u32 nfs4_fs_locations_bitmap[2] = { @@ -5834,6 +5835,54 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) return status; } +/* + * Retrieve the list of Data Server devices from the MDS. + */ +static int _nfs4_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist) +{ + struct nfs4_getdevicelist_args args = { + .fh = fh, + .layoutclass = server->pnfs_curr_ld->id, + }; + struct nfs4_getdevicelist_res res = { + .devlist = devlist, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + return status; +} + +int nfs4_proc_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_getdevicelist(server, fh, devlist), + &exception); + } while (exception.retry); + + dprintk("%s: err=%d, num_devs=%u\n", __func__, + err, devlist->num_devs); + + return err; +} +EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist); + static int _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) { @@ -5912,9 +5961,16 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) static void nfs4_layoutcommit_release(void *calldata) { struct nfs4_layoutcommit_data *data = calldata; + struct pnfs_layout_segment *lseg, *tmp; + pnfs_cleanup_layoutcommit(data); /* Matched by references in pnfs_set_layoutcommit */ - put_lseg(data->lseg); + list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) { + list_del_init(&lseg->pls_lc_list); + if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, + &lseg->pls_flags)) + put_lseg(lseg); + } put_rpccred(data->cred); kfree(data); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c191a9b..1dce12f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int); #define encode_restorefh_maxsz (op_encode_hdr_maxsz) #define decode_restorefh_maxsz (op_decode_hdr_maxsz) #define encode_fsinfo_maxsz (encode_getattr_maxsz) -#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + 15) +/* The 5 accounts for the PNFS attributes, and assumes that at most three + * layout types will be returned. + */ +#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz + 4 + 8 + 5) #define encode_renew_maxsz (op_encode_hdr_maxsz + 3) #define decode_renew_maxsz (op_decode_hdr_maxsz) #define encode_setclientid_maxsz \ @@ -314,6 +318,17 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) +#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \ + encode_verifier_maxsz) +#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \ + 2 /* nfs_cookie4 gdlr_cookie */ + \ + decode_verifier_maxsz \ + /* verifier4 gdlr_verifier */ + \ + 1 /* gdlr_deviceid_list count */ + \ + XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \ + NFS4_DEVICEID4_SIZE) \ + /* gdlr_deviceid_list */ + \ + 1 /* bool gdlr_eof */) #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ @@ -748,6 +763,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_reclaim_complete_maxsz) +#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getdevicelist_maxsz) +#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getdevicelist_maxsz) #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz +\ encode_getdeviceinfo_maxsz) @@ -1104,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm hdr->replen += decode_getattr_maxsz; } +static void +encode_getattr_three(struct xdr_stream *xdr, + uint32_t bm0, uint32_t bm1, uint32_t bm2, + struct compound_hdr *hdr) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_GETATTR); + if (bm2) { + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bm0); + *p++ = cpu_to_be32(bm1); + *p = cpu_to_be32(bm2); + } else if (bm1) { + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p = cpu_to_be32(bm1); + } else { + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(bm0); + } + hdr->nops++; + hdr->replen += decode_getattr_maxsz; +} + static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0], @@ -1112,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { - encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0], - bitmask[1] & nfs4_fsinfo_bitmap[1], hdr); + encode_getattr_three(xdr, + bitmask[0] & nfs4_fsinfo_bitmap[0], + bitmask[1] & nfs4_fsinfo_bitmap[1], + bitmask[2] & nfs4_fsinfo_bitmap[2], + hdr); } static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) @@ -1855,6 +1910,26 @@ static void encode_sequence(struct xdr_stream *xdr, #ifdef CONFIG_NFS_V4_1 static void +encode_getdevicelist(struct xdr_stream *xdr, + const struct nfs4_getdevicelist_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + nfs4_verifier dummy = { + .data = "dummmmmy", + }; + + p = reserve_space(xdr, 20); + *p++ = cpu_to_be32(OP_GETDEVICELIST); + *p++ = cpu_to_be32(args->layoutclass); + *p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM); + xdr_encode_hyper(p, 0ULL); /* cookie */ + encode_nfs4_verifier(xdr, &dummy); + hdr->nops++; + hdr->replen += decode_getdevicelist_maxsz; +} + +static void encode_getdeviceinfo(struct xdr_stream *xdr, const struct nfs4_getdeviceinfo_args *args, struct compound_hdr *hdr) @@ -1916,7 +1991,7 @@ encode_layoutcommit(struct xdr_stream *xdr, *p++ = cpu_to_be32(OP_LAYOUTCOMMIT); /* Only whole file layouts */ p = xdr_encode_hyper(p, 0); /* offset */ - p = xdr_encode_hyper(p, NFS4_MAX_UINT64); /* length */ + p = xdr_encode_hyper(p, args->lastbytewritten + 1); /* length */ *p++ = cpu_to_be32(0); /* reclaim */ p = xdr_encode_opaque_fixed(p, args->stateid.data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(1); /* newoffset = TRUE */ @@ -2604,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct compound_hdr hdr = { .nops = 0, }; - const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 }; + const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; encode_compound_hdr(xdr, req, &hdr); encode_setclientid_confirm(xdr, arg, &hdr); @@ -2748,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), }; - const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 }; + const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->la_seq_args, &hdr); @@ -2775,6 +2850,24 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, } /* + * Encode GETDEVICELIST request + */ +static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_getdevicelist_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getdevicelist(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* * Encode GETDEVICEINFO request */ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, @@ -3011,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) goto out_overflow; bmlen = be32_to_cpup(p); - bitmap[0] = bitmap[1] = 0; + bitmap[0] = bitmap[1] = bitmap[2] = 0; p = xdr_inline_decode(xdr, (bmlen << 2)); if (unlikely(!p)) goto out_overflow; if (bmlen > 0) { bitmap[0] = be32_to_cpup(p++); - if (bmlen > 1) - bitmap[1] = be32_to_cpup(p); + if (bmlen > 1) { + bitmap[1] = be32_to_cpup(p++); + if (bmlen > 2) + bitmap[2] = be32_to_cpup(p); + } } return 0; out_overflow: @@ -3050,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3 return ret; bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS; } else - bitmask[0] = bitmask[1] = 0; - dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]); + bitmask[0] = bitmask[1] = bitmask[2] = 0; + dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__, + bitmask[0], bitmask[1], bitmask[2]); return 0; } @@ -4105,7 +4202,7 @@ out_overflow: static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4131,7 +4228,7 @@ xdr_error: static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4163,7 +4260,7 @@ xdr_error: static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4303,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat { __be32 *savep; uint32_t attrlen, - bitmap[2] = {0}; + bitmap[3] = {0}; int status; status = decode_op_hdr(xdr, OP_GETATTR); @@ -4389,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap, return status; } +/* + * The prefered block size for layout directed io + */ +static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[2]); + *res = 0; + if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE; + } + return 0; +} + static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { __be32 *savep; - uint32_t attrlen, bitmap[2]; + uint32_t attrlen, bitmap[3]; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4420,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); if (status != 0) goto xdr_error; + status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize); + if (status) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -4839,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, { __be32 *savep; uint32_t attrlen, - bitmap[2] = {0}; + bitmap[3] = {0}; struct kvec *iov = req->rq_rcv_buf.head; int status; @@ -5268,6 +5390,53 @@ out_overflow: } #if defined(CONFIG_NFS_V4_1) +/* + * TODO: Need to handle case when EOF != true; + */ +static int decode_getdevicelist(struct xdr_stream *xdr, + struct pnfs_devicelist *res) +{ + __be32 *p; + int status, i; + struct nfs_writeverf verftemp; + + status = decode_op_hdr(xdr, OP_GETDEVICELIST); + if (status) + return status; + + p = xdr_inline_decode(xdr, 8 + 8 + 4); + if (unlikely(!p)) + goto out_overflow; + + /* TODO: Skip cookie for now */ + p += 2; + + /* Read verifier */ + p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8); + + res->num_devs = be32_to_cpup(p); + + dprintk("%s: num_dev %d\n", __func__, res->num_devs); + + if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) { + printk(KERN_ERR "%s too many result dev_num %u\n", + __func__, res->num_devs); + return -EIO; + } + + p = xdr_inline_decode(xdr, + res->num_devs * NFS4_DEVICEID4_SIZE + 4); + if (unlikely(!p)) + goto out_overflow; + for (i = 0; i < res->num_devs; i++) + p = xdr_decode_opaque_fixed(p, res->dev_id[i].data, + NFS4_DEVICEID4_SIZE); + res->eof = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} static int decode_getdeviceinfo(struct xdr_stream *xdr, struct pnfs_device *pdev) @@ -5430,6 +5599,7 @@ static int decode_layoutcommit(struct xdr_stream *xdr, int status; status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT); + res->status = status; if (status) return status; @@ -6542,6 +6712,32 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, } /* + * Decode GETDEVICELIST response + */ +static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_getdevicelist_res *res) +{ + struct compound_hdr hdr; + int status; + + dprintk("encoding getdevicelist!\n"); + + status = decode_compound_hdr(xdr, &hdr); + if (status != 0) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status != 0) + goto out; + status = decode_putfh(xdr); + if (status != 0) + goto out; + status = decode_getdevicelist(xdr, res->devlist); +out: + return status; +} + +/* * Decode GETDEVINFO response */ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, @@ -6722,7 +6918,7 @@ out: int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, int plus) { - uint32_t bitmap[2] = {0}; + uint32_t bitmap[3] = {0}; uint32_t len; __be32 *p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) @@ -6908,6 +7104,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name), PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), + PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 38e5508..e550e88 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -76,8 +76,11 @@ find_pnfs_driver(u32 id) void unset_pnfs_layoutdriver(struct nfs_server *nfss) { - if (nfss->pnfs_curr_ld) + if (nfss->pnfs_curr_ld) { + if (nfss->pnfs_curr_ld->clear_layoutdriver) + nfss->pnfs_curr_ld->clear_layoutdriver(nfss); module_put(nfss->pnfs_curr_ld->owner); + } nfss->pnfs_curr_ld = NULL; } @@ -88,7 +91,8 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss) * @id layout type. Zero (illegal layout type) indicates pNFS not in use. */ void -set_pnfs_layoutdriver(struct nfs_server *server, u32 id) +set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, + u32 id) { struct pnfs_layoutdriver_type *ld_type = NULL; @@ -115,6 +119,13 @@ set_pnfs_layoutdriver(struct nfs_server *server, u32 id) goto out_no_driver; } server->pnfs_curr_ld = ld_type; + if (ld_type->set_layoutdriver + && ld_type->set_layoutdriver(server, mntfh)) { + printk(KERN_ERR "%s: Error initializing pNFS layout driver %u.\n", + __func__, id); + module_put(ld_type->owner); + goto out_no_driver; + } dprintk("%s: pNFS module for %u set\n", __func__, id); return; @@ -190,6 +201,7 @@ static void pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld; + put_rpccred(lo->plh_lc_cred); return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo); } @@ -224,6 +236,7 @@ static void init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg) { INIT_LIST_HEAD(&lseg->pls_list); + INIT_LIST_HEAD(&lseg->pls_lc_list); atomic_set(&lseg->pls_refcount, 1); smp_mb(); set_bit(NFS_LSEG_VALID, &lseg->pls_flags); @@ -816,7 +829,9 @@ out: } static struct pnfs_layout_hdr * -alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags) +alloc_init_layout_hdr(struct inode *ino, + struct nfs_open_context *ctx, + gfp_t gfp_flags) { struct pnfs_layout_hdr *lo; @@ -828,11 +843,14 @@ alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags) INIT_LIST_HEAD(&lo->plh_segs); INIT_LIST_HEAD(&lo->plh_bulk_recall); lo->plh_inode = ino; + lo->plh_lc_cred = get_rpccred(ctx->state->owner->so_cred); return lo; } static struct pnfs_layout_hdr * -pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags) +pnfs_find_alloc_layout(struct inode *ino, + struct nfs_open_context *ctx, + gfp_t gfp_flags) { struct nfs_inode *nfsi = NFS_I(ino); struct pnfs_layout_hdr *new = NULL; @@ -847,7 +865,7 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags) return nfsi->layout; } spin_unlock(&ino->i_lock); - new = alloc_init_layout_hdr(ino, gfp_flags); + new = alloc_init_layout_hdr(ino, ctx, gfp_flags); spin_lock(&ino->i_lock); if (likely(nfsi->layout == NULL)) /* Won the race? */ @@ -940,7 +958,7 @@ pnfs_update_layout(struct inode *ino, if (!pnfs_enabled_sb(NFS_SERVER(ino))) return NULL; spin_lock(&ino->i_lock); - lo = pnfs_find_alloc_layout(ino, gfp_flags); + lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__); goto out_unlock; @@ -1350,16 +1368,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); /* - * Currently there is only one (whole file) write lseg. + * There can be multiple RW segments. */ -static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode) +static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp) { - struct pnfs_layout_segment *lseg, *rv = NULL; + struct pnfs_layout_segment *lseg; - list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) - if (lseg->pls_range.iomode == IOMODE_RW) - rv = lseg; - return rv; + list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) { + if (lseg->pls_range.iomode == IOMODE_RW && + test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) + list_add(&lseg->pls_lc_list, listp); + } } void @@ -1371,17 +1390,19 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata) spin_lock(&nfsi->vfs_inode.i_lock); if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { - /* references matched in nfs4_layoutcommit_release */ - get_lseg(wdata->lseg); - wdata->lseg->pls_lc_cred = - get_rpccred(wdata->args.context->state->owner->so_cred); mark_as_dirty = true; dprintk("%s: Set layoutcommit for inode %lu ", __func__, wdata->inode->i_ino); } - if (end_pos > wdata->lseg->pls_end_pos) - wdata->lseg->pls_end_pos = end_pos; + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) { + /* references matched in nfs4_layoutcommit_release */ + get_lseg(wdata->lseg); + } + if (end_pos > nfsi->layout->plh_lwb) + nfsi->layout->plh_lwb = end_pos; spin_unlock(&nfsi->vfs_inode.i_lock); + dprintk("%s: lseg %p end_pos %llu\n", + __func__, wdata->lseg, nfsi->layout->plh_lwb); /* if pnfs_layoutcommit_inode() runs between inode locks, the next one * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */ @@ -1390,6 +1411,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata) } EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data) +{ + struct nfs_server *nfss = NFS_SERVER(data->args.inode); + + if (nfss->pnfs_curr_ld->cleanup_layoutcommit) + nfss->pnfs_curr_ld->cleanup_layoutcommit(data); +} + /* * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough @@ -1403,8 +1432,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) { struct nfs4_layoutcommit_data *data; struct nfs_inode *nfsi = NFS_I(inode); - struct pnfs_layout_segment *lseg; - struct rpc_cred *cred; loff_t end_pos; int status = 0; @@ -1421,30 +1448,25 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) goto out; } + INIT_LIST_HEAD(&data->lseg_list); spin_lock(&inode->i_lock); if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { spin_unlock(&inode->i_lock); kfree(data); goto out; } - /* - * Currently only one (whole file) write lseg which is referenced - * in pnfs_set_layoutcommit and will be found. - */ - lseg = pnfs_list_write_lseg(inode); - end_pos = lseg->pls_end_pos; - cred = lseg->pls_lc_cred; - lseg->pls_end_pos = 0; - lseg->pls_lc_cred = NULL; + pnfs_list_write_lseg(inode, &data->lseg_list); + + end_pos = nfsi->layout->plh_lwb; + nfsi->layout->plh_lwb = 0; memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data, sizeof(nfsi->layout->plh_stateid.data)); spin_unlock(&inode->i_lock); data->args.inode = inode; - data->lseg = lseg; - data->cred = cred; + data->cred = get_rpccred(nfsi->layout->plh_lc_cred); nfs_fattr_init(&data->fattr); data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; data->res.fattr = &data->fattr; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 078670d..01cbfd5 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -36,16 +36,16 @@ enum { NFS_LSEG_VALID = 0, /* cleared when lseg is recalled/returned */ NFS_LSEG_ROC, /* roc bit received from server */ + NFS_LSEG_LAYOUTCOMMIT, /* layoutcommit bit set for layoutcommit */ }; struct pnfs_layout_segment { struct list_head pls_list; + struct list_head pls_lc_list; struct pnfs_layout_range pls_range; atomic_t pls_refcount; unsigned long pls_flags; struct pnfs_layout_hdr *pls_layout; - struct rpc_cred *pls_lc_cred; /* LAYOUTCOMMIT credential */ - loff_t pls_end_pos; /* LAYOUTCOMMIT write end */ }; enum pnfs_try_status { @@ -80,6 +80,9 @@ struct pnfs_layoutdriver_type { struct module *owner; unsigned flags; + int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *); + int (*clear_layoutdriver) (struct nfs_server *); + struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags); void (*free_layout_hdr) (struct pnfs_layout_hdr *); @@ -110,6 +113,8 @@ struct pnfs_layoutdriver_type { struct xdr_stream *xdr, const struct nfs4_layoutreturn_args *args); + void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data); + void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid, struct xdr_stream *xdr, const struct nfs4_layoutcommit_args *args); @@ -125,6 +130,8 @@ struct pnfs_layout_hdr { unsigned long plh_block_lgets; /* block LAYOUTGET if >0 */ u32 plh_barrier; /* ignore lower seqids */ unsigned long plh_flags; + loff_t plh_lwb; /* last write byte for layoutcommit */ + struct rpc_cred *plh_lc_cred; /* layoutcommit cred */ struct inode *plh_inode; }; @@ -137,10 +144,21 @@ struct pnfs_device { unsigned int pglen; }; +#define NFS4_PNFS_GETDEVLIST_MAXNUM 16 + +struct pnfs_devicelist { + unsigned int eof; + unsigned int num_devs; + struct nfs4_deviceid dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM]; +}; + extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); /* nfs4proc.c */ +extern int nfs4_proc_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); @@ -153,7 +171,7 @@ void put_lseg(struct pnfs_layout_segment *lseg); bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *); bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int); -void set_pnfs_layoutdriver(struct nfs_server *, u32 id); +void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); void unset_pnfs_layoutdriver(struct nfs_server *); void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); @@ -179,6 +197,7 @@ void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); bool pnfs_roc_drain(struct inode *ino, u32 *barrier); void pnfs_set_layoutcommit(struct nfs_write_data *wdata); +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); int _pnfs_return_layout(struct inode *); int pnfs_ld_write_done(struct nfs_write_data *); @@ -360,7 +379,8 @@ pnfs_roc_drain(struct inode *ino, u32 *barrier) return false; } -static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id) +static inline void set_pnfs_layoutdriver(struct nfs_server *s, + const struct nfs_fh *mntfh, u32 id) { } diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 783c58d..a721907 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -247,7 +247,7 @@ static int ocfs2_set_acl(handle_t *handle, case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; ret = posix_acl_equiv_mode(acl, &mode); if (ret < 0) return ret; @@ -351,7 +351,7 @@ int ocfs2_init_acl(handle_t *handle, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct posix_acl *acl = NULL; int ret = 0, ret2; - mode_t mode; + umode_t mode; if (!S_ISLNK(inode->i_mode)) { if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { diff --git a/fs/posix_acl.c b/fs/posix_acl.c index d43729a7..10027b4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -149,10 +149,10 @@ posix_acl_valid(const struct posix_acl *acl) * file mode permission bits, or else 1. Returns -E... on error. */ int -posix_acl_equiv_mode(const struct posix_acl *acl, mode_t *mode_p) +posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; - mode_t mode = 0; + umode_t mode = 0; int not_equiv = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { @@ -188,7 +188,7 @@ posix_acl_equiv_mode(const struct posix_acl *acl, mode_t *mode_p) * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * -posix_acl_from_mode(mode_t mode, gfp_t flags) +posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) @@ -279,11 +279,11 @@ check_perm: * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ -static int posix_acl_create_masq(struct posix_acl *acl, mode_t *mode_p) +static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; - mode_t mode = *mode_p; + umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ @@ -336,7 +336,7 @@ static int posix_acl_create_masq(struct posix_acl *acl, mode_t *mode_p) /* * Modify the ACL for the chmod syscall. */ -static int posix_acl_chmod_masq(struct posix_acl *acl, mode_t mode) +static int posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; @@ -382,7 +382,7 @@ static int posix_acl_chmod_masq(struct posix_acl *acl, mode_t mode) } int -posix_acl_create(struct posix_acl **acl, gfp_t gfp, mode_t *mode_p) +posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; @@ -400,7 +400,7 @@ posix_acl_create(struct posix_acl **acl, gfp_t gfp, mode_t *mode_p) EXPORT_SYMBOL(posix_acl_create); int -posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, mode_t mode) +posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; diff --git a/fs/proc/base.c b/fs/proc/base.c index 08e3ecc..5eb0206 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1118,7 +1118,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, * Warn that /proc/pid/oom_adj is deprecated, see * Documentation/feature-removal-schedule.txt. */ - WARN_ONCE(1, "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); task->signal->oom_adj = oom_adjust; @@ -1919,6 +1919,14 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info) spin_lock(&files->file_lock); file = fcheck_files(files, fd); if (file) { + unsigned int f_flags; + struct fdtable *fdt; + + fdt = files_fdtable(files); + f_flags = file->f_flags & ~O_CLOEXEC; + if (FD_ISSET(fd, fdt->close_on_exec)) + f_flags |= O_CLOEXEC; + if (path) { *path = file->f_path; path_get(&file->f_path); @@ -1928,7 +1936,7 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info) "pos:\t%lli\n" "flags:\t0%o\n", (long long) file->f_pos, - file->f_flags); + f_flags); spin_unlock(&files->file_lock); put_files_struct(files); return 0; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 977ed27..893b961 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -39,8 +39,9 @@ #define PSTORE_NAMELEN 64 struct pstore_private { + struct pstore_info *psi; + enum pstore_type_id type; u64 id; - int (*erase)(u64); ssize_t size; char data[]; }; @@ -73,7 +74,7 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = dentry->d_inode->i_private; - p->erase(p->id); + p->psi->erase(p->type, p->id, p->psi); return simple_unlink(dir, dentry); } @@ -175,8 +176,8 @@ int pstore_is_mounted(void) * Set the mtime & ctime to the date that this record was originally stored. */ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, - char *data, size_t size, - struct timespec time, int (*erase)(u64)) + char *data, size_t size, struct timespec time, + struct pstore_info *psi) { struct dentry *root = pstore_sb->s_root; struct dentry *dentry; @@ -192,8 +193,9 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, private = kmalloc(sizeof *private + size, GFP_KERNEL); if (!private) goto fail_alloc; + private->type = type; private->id = id; - private->erase = erase; + private->psi = psi; switch (type) { case PSTORE_TYPE_DMESG: diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 8c9f23e..611c1b3 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -2,5 +2,5 @@ extern void pstore_set_kmsg_bytes(int); extern void pstore_get_records(void); extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, char *data, size_t size, - struct timespec time, int (*erase)(u64)); + struct timespec time, struct pstore_info *psi); extern int pstore_is_mounted(void); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index f2c3ff2..c5300ec 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -37,6 +37,8 @@ static DEFINE_SPINLOCK(pstore_lock); static struct pstore_info *psinfo; +static char *backend; + /* How much of the console log to snapshot */ static unsigned long kmsg_bytes = 10240; @@ -67,7 +69,8 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned long size, total = 0; char *dst, *why; u64 id; - int hsize, part = 1; + int hsize; + unsigned int part = 1; if (reason < ARRAY_SIZE(reason_str)) why = reason_str[reason]; @@ -78,7 +81,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, oopscount++; while (total < kmsg_bytes) { dst = psinfo->buf; - hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part++); + hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; @@ -94,14 +97,16 @@ static void pstore_dump(struct kmsg_dumper *dumper, memcpy(dst, s1 + s1_start, l1_cpy); memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy); + id = psinfo->write(PSTORE_TYPE_DMESG, part, + hsize + l1_cpy + l2_cpy, psinfo); if (reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, hsize + l1_cpy + l2_cpy, - CURRENT_TIME, psinfo->erase); + CURRENT_TIME, psinfo); l1 -= l1_cpy; l2 -= l2_cpy; total += l1_cpy + l2_cpy; + part++; } mutex_unlock(&psinfo->buf_mutex); } @@ -128,6 +133,12 @@ int pstore_register(struct pstore_info *psi) spin_unlock(&pstore_lock); return -EBUSY; } + + if (backend && strcmp(backend, psi->name)) { + spin_unlock(&pstore_lock); + return -EINVAL; + } + psinfo = psi; spin_unlock(&pstore_lock); @@ -166,9 +177,9 @@ void pstore_get_records(void) if (rc) goto out; - while ((size = psi->read(&id, &type, &time)) > 0) { + while ((size = psi->read(&id, &type, &time, psi)) > 0) { if (pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size, - time, psi->erase)) + time, psi)) failed++; } psi->close(psi); @@ -196,12 +207,15 @@ int pstore_write(enum pstore_type_id type, char *buf, size_t size) mutex_lock(&psinfo->buf_mutex); memcpy(psinfo->buf, buf, size); - id = psinfo->write(type, size); + id = psinfo->write(type, 0, size, psinfo); if (pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, - size, CURRENT_TIME, psinfo->erase); + size, CURRENT_TIME, psinfo); mutex_unlock(&psinfo->buf_mutex); return 0; } EXPORT_SYMBOL_GPL(pstore_write); + +module_param(backend, charp, 0444); +MODULE_PARM_DESC(backend, "Pstore backend to use"); diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 7362cf4..6da0396e 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -272,12 +272,10 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; if (error == 0) acl = NULL; } @@ -354,8 +352,6 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, return PTR_ERR(acl); if (acl) { - mode_t mode = inode->i_mode; - /* Copy the default ACL to the default ACL of a new directory */ if (S_ISDIR(inode->i_mode)) { err = reiserfs_set_acl(th, inode, ACL_TYPE_DEFAULT, @@ -366,12 +362,10 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, /* Now we reconcile the new ACL and the mode, potentially modifying both */ - err = posix_acl_create(&acl, GFP_NOFS, &mode); + err = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (err < 0) return err; - inode->i_mode = mode; - /* If we need an ACL.. */ if (err > 0) err = reiserfs_set_acl(th, inode, ACL_TYPE_ACCESS, acl); @@ -29,10 +29,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src) * * We don't actually know what locking is used at the lower level; * but if it's a filesystem that supports quotas, it will be using - * i_lock as in inode_add_bytes(). tmpfs uses other locking, and - * its 32-bit is (just) able to exceed 2TB i_size with the aid of - * holes; but its i_blocks cannot carry into the upper long without - * almost 2TB swap - let's ignore that case. + * i_lock as in inode_add_bytes(). */ if (sizeof(i_blocks) > sizeof(long)) spin_lock(&src->i_lock); @@ -27,12 +27,12 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->uid = inode->i_uid; stat->gid = inode->i_gid; stat->rdev = inode->i_rdev; + stat->size = i_size_read(inode); stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; - stat->size = i_size_read(inode); - stat->blocks = inode->i_blocks; stat->blksize = (1 << inode->i_blkbits); + stat->blocks = inode->i_blocks; } EXPORT_SYMBOL(generic_fillattr); diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 44ce516..b6c4b37 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -221,7 +221,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) } static int -xfs_set_mode(struct inode *inode, mode_t mode) +xfs_set_mode(struct inode *inode, umode_t mode) { int error = 0; @@ -267,7 +267,7 @@ posix_acl_default_exists(struct inode *inode) int xfs_inherit_acl(struct inode *inode, struct posix_acl *acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; int error = 0, inherit = 0; if (S_ISDIR(inode->i_mode)) { @@ -381,7 +381,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name, goto out_release; if (type == ACL_TYPE_ACCESS) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; error = posix_acl_equiv_mode(acl, &mode); if (error <= 0) { |
