diff options
Diffstat (limited to 'fs')
110 files changed, 2251 insertions, 2745 deletions
@@ -443,7 +443,7 @@ static struct kiocb *__aio_get_req(struct kioctx *ctx) req->private = NULL; req->ki_iovec = NULL; INIT_LIST_HEAD(&req->ki_run_list); - req->ki_eventfd = ERR_PTR(-EINVAL); + req->ki_eventfd = NULL; /* Check if the completion queue has enough free space to * accept an event from this io. @@ -485,8 +485,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) { assert_spin_locked(&ctx->ctx_lock); - if (!IS_ERR(req->ki_eventfd)) - fput(req->ki_eventfd); if (req->ki_dtor) req->ki_dtor(req); if (req->ki_iovec != &req->ki_inline_vec) @@ -508,8 +506,11 @@ static void aio_fput_routine(struct work_struct *data) list_del(&req->ki_list); spin_unlock_irq(&fput_lock); - /* Complete the fput */ - __fput(req->ki_filp); + /* Complete the fput(s) */ + if (req->ki_filp != NULL) + __fput(req->ki_filp); + if (req->ki_eventfd != NULL) + __fput(req->ki_eventfd); /* Link the iocb into the context's free list */ spin_lock_irq(&ctx->ctx_lock); @@ -527,12 +528,14 @@ static void aio_fput_routine(struct work_struct *data) */ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) { + int schedule_putreq = 0; + dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", req, atomic_long_read(&req->ki_filp->f_count)); assert_spin_locked(&ctx->ctx_lock); - req->ki_users --; + req->ki_users--; BUG_ON(req->ki_users < 0); if (likely(req->ki_users)) return 0; @@ -540,10 +543,23 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) req->ki_cancel = NULL; req->ki_retry = NULL; - /* Must be done under the lock to serialise against cancellation. - * Call this aio_fput as it duplicates fput via the fput_work. + /* + * Try to optimize the aio and eventfd file* puts, by avoiding to + * schedule work in case it is not __fput() time. In normal cases, + * we would not be holding the last reference to the file*, so + * this function will be executed w/out any aio kthread wakeup. */ - if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) { + if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) + schedule_putreq++; + else + req->ki_filp = NULL; + if (req->ki_eventfd != NULL) { + if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count))) + schedule_putreq++; + else + req->ki_eventfd = NULL; + } + if (unlikely(schedule_putreq)) { get_ioctx(ctx); spin_lock(&fput_lock); list_add(&req->ki_list, &fput_head); @@ -571,7 +587,7 @@ int aio_put_req(struct kiocb *req) static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct mm_struct *mm = current->mm; - struct kioctx *ctx = NULL; + struct kioctx *ctx, *ret = NULL; struct hlist_node *n; rcu_read_lock(); @@ -579,12 +595,13 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) { if (ctx->user_id == ctx_id && !ctx->dead) { get_ioctx(ctx); + ret = ctx; break; } } rcu_read_unlock(); - return ctx; + return ret; } /* @@ -1009,7 +1026,7 @@ int aio_complete(struct kiocb *iocb, long res, long res2) * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (!IS_ERR(iocb->ki_eventfd)) + if (iocb->ki_eventfd != NULL) eventfd_signal(iocb->ki_eventfd, 1); put_rq: @@ -1608,6 +1625,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd); if (IS_ERR(req->ki_eventfd)) { ret = PTR_ERR(req->ki_eventfd); + req->ki_eventfd = NULL; goto out_put_req; } } diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 549b0144da1..fe2b1aa2464 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -685,19 +685,20 @@ EXPORT_SYMBOL(bio_integrity_split); * bio_integrity_clone - Callback for cloning bios with integrity metadata * @bio: New bio * @bio_src: Original bio + * @gfp_mask: Memory allocation mask * @bs: bio_set to allocate bip from * * Description: Called to allocate a bip when cloning a bio */ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, - struct bio_set *bs) + gfp_t gfp_mask, struct bio_set *bs) { struct bio_integrity_payload *bip_src = bio_src->bi_integrity; struct bio_integrity_payload *bip; BUG_ON(bip_src == NULL); - bip = bio_integrity_alloc_bioset(bio, GFP_NOIO, bip_src->bip_vcnt, bs); + bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs); if (bip == NULL) return -EIO; @@ -463,10 +463,12 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) if (bio_integrity(bio)) { int ret; - ret = bio_integrity_clone(b, bio, fs_bio_set); + ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set); - if (ret < 0) + if (ret < 0) { + bio_put(b); return NULL; + } } return b; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 42491d728e9..37f31b5529a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -277,7 +277,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (*cow_ret == buf) unlock_orig = 1; - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); if (parent) parent_start = parent->start; @@ -2365,7 +2365,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (slot >= btrfs_header_nritems(upper) - 1) return 1; - WARN_ON(!btrfs_tree_locked(path->nodes[1])); + btrfs_assert_tree_locked(path->nodes[1]); right = read_node_slot(root, upper, slot + 1); btrfs_tree_lock(right); @@ -2562,7 +2562,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root if (right_nritems == 0) return 1; - WARN_ON(!btrfs_tree_locked(path->nodes[1])); + btrfs_assert_tree_locked(path->nodes[1]); left = read_node_slot(root, path->nodes[1], slot - 1); btrfs_tree_lock(left); @@ -4101,7 +4101,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) next = read_node_slot(root, c, slot); if (!path->skip_locking) { - WARN_ON(!btrfs_tree_locked(c)); + btrfs_assert_tree_locked(c); btrfs_tree_lock(next); btrfs_set_lock_blocking(next); } @@ -4126,7 +4126,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) reada_for_search(root, path, level, slot, 0); next = read_node_slot(root, next, 0); if (!path->skip_locking) { - WARN_ON(!btrfs_tree_locked(path->nodes[level])); + btrfs_assert_tree_locked(path->nodes[level]); btrfs_tree_lock(next); btrfs_set_lock_blocking(next); } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 82491ba8fa4..5e1d4e30e9d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -784,7 +784,14 @@ struct btrfs_fs_info { struct list_head dirty_cowonly_roots; struct btrfs_fs_devices *fs_devices; + + /* + * the space_info list is almost entirely read only. It only changes + * when we add a new raid type to the FS, and that happens + * very rarely. RCU is used to protect it. + */ struct list_head space_info; + spinlock_t delalloc_lock; spinlock_t new_trans_lock; u64 delalloc_bytes; @@ -1797,6 +1804,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root); int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags); void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde); +void btrfs_clear_space_info_full(struct btrfs_fs_info *info); + int btrfs_check_metadata_free_space(struct btrfs_root *root); int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode, u64 bytes); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index adda739a021..3e18175248e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -857,7 +857,7 @@ int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *btree_inode = root->fs_info->btree_inode; if (btrfs_header_generation(buf) == root->fs_info->running_transaction->transid) { - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); /* ugh, clear_extent_buffer_dirty can be expensive */ btrfs_set_lock_blocking(buf); @@ -2361,7 +2361,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) btrfs_set_lock_blocking(buf); - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); if (transid != root->fs_info->generation) { printk(KERN_CRIT "btrfs transid mismatch buffer %llu, " "found %llu running %llu\n", diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6b5966aacf4..fefe83ad205 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -20,6 +20,7 @@ #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/sort.h> +#include <linux/rcupdate.h> #include "compat.h" #include "hash.h" #include "crc32c.h" @@ -330,13 +331,33 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, { struct list_head *head = &info->space_info; struct btrfs_space_info *found; - list_for_each_entry(found, head, list) { - if (found->flags == flags) + + rcu_read_lock(); + list_for_each_entry_rcu(found, head, list) { + if (found->flags == flags) { + rcu_read_unlock(); return found; + } } + rcu_read_unlock(); return NULL; } +/* + * after adding space to the filesystem, we need to clear the full flags + * on all the space infos. + */ +void btrfs_clear_space_info_full(struct btrfs_fs_info *info) +{ + struct list_head *head = &info->space_info; + struct btrfs_space_info *found; + + rcu_read_lock(); + list_for_each_entry_rcu(found, head, list) + found->full = 0; + rcu_read_unlock(); +} + static u64 div_factor(u64 num, int factor) { if (factor == 10) @@ -1903,7 +1924,6 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, if (!found) return -ENOMEM; - list_add(&found->list, &info->space_info); INIT_LIST_HEAD(&found->block_groups); init_rwsem(&found->groups_sem); spin_lock_init(&found->lock); @@ -1917,6 +1937,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->full = 0; found->force_alloc = 0; *space_info = found; + list_add_rcu(&found->list, &info->space_info); return 0; } @@ -4418,13 +4439,13 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); BUG_ON(!path); - BUG_ON(!btrfs_tree_locked(parent)); + btrfs_assert_tree_locked(parent); parent_level = btrfs_header_level(parent); extent_buffer_get(parent); path->nodes[parent_level] = parent; path->slots[parent_level] = btrfs_header_nritems(parent); - BUG_ON(!btrfs_tree_locked(node)); + btrfs_assert_tree_locked(node); level = btrfs_header_level(node); extent_buffer_get(node); path->nodes[level] = node; @@ -6320,6 +6341,7 @@ out: int btrfs_free_block_groups(struct btrfs_fs_info *info) { struct btrfs_block_group_cache *block_group; + struct btrfs_space_info *space_info; struct rb_node *n; spin_lock(&info->block_group_cache_lock); @@ -6341,6 +6363,23 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) spin_lock(&info->block_group_cache_lock); } spin_unlock(&info->block_group_cache_lock); + + /* now that all the block groups are freed, go through and + * free all the space_info structs. This is only called during + * the final stages of unmount, and so we know nobody is + * using them. We call synchronize_rcu() once before we start, + * just to be on the safe side. + */ + synchronize_rcu(); + + while(!list_empty(&info->space_info)) { + space_info = list_entry(info->space_info.next, + struct btrfs_space_info, + list); + + list_del(&space_info->list); + kfree(space_info); + } return 0; } diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 85506c4a3af..47b0a88c12a 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -220,8 +220,8 @@ int btrfs_tree_unlock(struct extent_buffer *eb) return 0; } -int btrfs_tree_locked(struct extent_buffer *eb) +void btrfs_assert_tree_locked(struct extent_buffer *eb) { - return test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags) || - spin_is_locked(&eb->lock); + if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) + assert_spin_locked(&eb->lock); } diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 6bb0afbff92..6c4ce457168 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -21,11 +21,11 @@ int btrfs_tree_lock(struct extent_buffer *eb); int btrfs_tree_unlock(struct extent_buffer *eb); -int btrfs_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_lock(struct extent_buffer *eb); int btrfs_try_spin_lock(struct extent_buffer *eb); void btrfs_set_lock_blocking(struct extent_buffer *eb); void btrfs_clear_lock_blocking(struct extent_buffer *eb); +void btrfs_assert_tree_locked(struct extent_buffer *eb); #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1316139bf9e..dd06e18e5aa 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1374,6 +1374,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_add_device(trans, root, device); } + /* + * we've got more storage, clear any full flags on the space + * infos + */ + btrfs_clear_space_info_full(root->fs_info); + unlock_chunks(root); btrfs_commit_transaction(trans, root); @@ -1459,6 +1465,8 @@ static int __btrfs_grow_device(struct btrfs_trans_handle *trans, device->fs_devices->total_rw_bytes += diff; device->total_bytes = new_size; + btrfs_clear_space_info_full(device->dev_root->fs_info); + return btrfs_update_device(trans, device); } diff --git a/fs/buffer.c b/fs/buffer.c index 9f697419ed8..891e1c78e4f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -760,15 +760,9 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * If warn is true, then emit a warning if the page is not uptodate and has * not been truncated. */ -static int __set_page_dirty(struct page *page, +static void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { - if (unlikely(!mapping)) - return !TestSetPageDirty(page); - - if (TestSetPageDirty(page)) - return 0; - spin_lock_irq(&mapping->tree_lock); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); @@ -785,8 +779,6 @@ static int __set_page_dirty(struct page *page, } spin_unlock_irq(&mapping->tree_lock); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - - return 1; } /* @@ -816,6 +808,7 @@ static int __set_page_dirty(struct page *page, */ int __set_page_dirty_buffers(struct page *page) { + int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) @@ -831,9 +824,12 @@ int __set_page_dirty_buffers(struct page *page) bh = bh->b_this_page; } while (bh != head); } + newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); - return __set_page_dirty(page, mapping, 1); + if (newly_dirty) + __set_page_dirty(page, mapping, 1); + return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -1262,8 +1258,11 @@ void mark_buffer_dirty(struct buffer_head *bh) return; } - if (!test_set_buffer_dirty(bh)) - __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0); + if (!test_set_buffer_dirty(bh)) { + struct page *page = bh->b_page; + if (!TestSetPageDirty(page)) + __set_page_dirty(page, page_mapping(page), 0); + } } /* diff --git a/fs/compat.c b/fs/compat.c index d0145ca2757..0949b43794a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1402,6 +1402,7 @@ int compat_do_execve(char * filename, retval = mutex_lock_interruptible(¤t->cred_exec_mutex); if (retval < 0) goto out_free; + current->in_execve = 1; retval = -ENOMEM; bprm->cred = prepare_exec_creds(); @@ -1454,6 +1455,7 @@ int compat_do_execve(char * filename, goto out; /* execve succeeded */ + current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); acct_update_integrals(current); free_bprm(bprm); @@ -1470,6 +1472,7 @@ out_file: } out_unlock: + current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); out_free: diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 5f3231b9633..bff4052b05e 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -198,9 +198,6 @@ static int mknod_ptmx(struct super_block *sb) fsi->ptmx_dentry = dentry; rc = 0; - - printk(KERN_DEBUG "Created ptmx node in devpts ino %lu\n", - inode->i_ino); out: mutex_unlock(&root->d_inode->i_mutex); return rc; @@ -369,8 +366,6 @@ static int new_pts_mount(struct file_system_type *fs_type, int flags, struct pts_fs_info *fsi; struct pts_mount_opts *opts; - printk(KERN_NOTICE "devpts: newinstance mount\n"); - err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt); if (err) return err; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index f6caeb1d110..8b65f289ee0 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -946,6 +946,8 @@ static int ecryptfs_copy_mount_wide_sigs_to_inode_sigs( list_for_each_entry(global_auth_tok, &mount_crypt_stat->global_auth_tok_list, mount_crypt_stat_list) { + if (global_auth_tok->flags & ECRYPTFS_AUTH_TOK_FNEK) + continue; rc = ecryptfs_add_keysig(crypt_stat, global_auth_tok->sig); if (rc) { printk(KERN_ERR "Error adding keysig; rc = [%d]\n", rc); @@ -1322,14 +1324,13 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max, } static int -ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat, - struct dentry *ecryptfs_dentry, - char *virt) +ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry, + char *virt, size_t virt_len) { int rc; rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt, - 0, crypt_stat->num_header_bytes_at_front); + 0, virt_len); if (rc) printk(KERN_ERR "%s: Error attempting to write header " "information to lower file; rc = [%d]\n", __func__, @@ -1339,7 +1340,6 @@ ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat, static int ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, - struct ecryptfs_crypt_stat *crypt_stat, char *page_virt, size_t size) { int rc; @@ -1349,6 +1349,17 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, return rc; } +static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask, + unsigned int order) +{ + struct page *page; + + page = alloc_pages(gfp_mask | __GFP_ZERO, order); + if (page) + return (unsigned long) page_address(page); + return 0; +} + /** * ecryptfs_write_metadata * @ecryptfs_dentry: The eCryptfs dentry @@ -1365,7 +1376,9 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat; + unsigned int order; char *virt; + size_t virt_len; size_t size = 0; int rc = 0; @@ -1381,33 +1394,35 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) rc = -EINVAL; goto out; } + virt_len = crypt_stat->num_header_bytes_at_front; + order = get_order(virt_len); /* Released in this function */ - virt = (char *)get_zeroed_page(GFP_KERNEL); + virt = (char *)ecryptfs_get_zeroed_pages(GFP_KERNEL, order); if (!virt) { printk(KERN_ERR "%s: Out of memory\n", __func__); rc = -ENOMEM; goto out; } - rc = ecryptfs_write_headers_virt(virt, PAGE_CACHE_SIZE, &size, - crypt_stat, ecryptfs_dentry); + rc = ecryptfs_write_headers_virt(virt, virt_len, &size, crypt_stat, + ecryptfs_dentry); if (unlikely(rc)) { printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n", __func__, rc); goto out_free; } if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) - rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, - crypt_stat, virt, size); + rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt, + size); else - rc = ecryptfs_write_metadata_to_contents(crypt_stat, - ecryptfs_dentry, virt); + rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt, + virt_len); if (rc) { printk(KERN_ERR "%s: Error writing metadata out to lower file; " "rc = [%d]\n", __func__, rc); goto out_free; } out_free: - free_page((unsigned long)virt); + free_pages((unsigned long)virt, order); out: return rc; } @@ -2206,17 +2221,19 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name, struct dentry *ecryptfs_dir_dentry, const char *name, size_t name_size) { + struct ecryptfs_mount_crypt_stat *mount_crypt_stat = + &ecryptfs_superblock_to_private( + ecryptfs_dir_dentry->d_sb)->mount_crypt_stat; char *decoded_name; size_t decoded_name_size; size_t packet_size; int rc = 0; - if ((name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) + if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) + && !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + && (name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) && (strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) == 0)) { - struct ecryptfs_mount_crypt_stat *mount_crypt_stat = - &ecryptfs_superblock_to_private( - ecryptfs_dir_dentry->d_sb)->mount_crypt_stat; const char *orig_name = name; size_t orig_name_size = name_size; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index c11fc95714a..ac749d4d644 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -328,6 +328,7 @@ struct ecryptfs_dentry_info { */ struct ecryptfs_global_auth_tok { #define ECRYPTFS_AUTH_TOK_INVALID 0x00000001 +#define ECRYPTFS_AUTH_TOK_FNEK 0x00000002 u32 flags; struct list_head mount_crypt_stat_list; struct key *global_auth_tok_key; @@ -619,7 +620,6 @@ int ecryptfs_interpose(struct dentry *hidden_dentry, u32 flags); int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, struct dentry *lower_dentry, - struct ecryptfs_crypt_stat *crypt_stat, struct inode *ecryptfs_dir_inode, struct nameidata *ecryptfs_nd); int ecryptfs_decode_and_decrypt_filename(char **decrypted_name, @@ -696,7 +696,7 @@ ecryptfs_write_header_metadata(char *virt, int ecryptfs_add_keysig(struct ecryptfs_crypt_stat *crypt_stat, char *sig); int ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat, - char *sig); + char *sig, u32 global_auth_tok_flags); int ecryptfs_get_global_auth_tok_for_sig( struct ecryptfs_global_auth_tok **global_auth_tok, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, char *sig); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5697899a168..55b3145b807 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -246,7 +246,6 @@ out: */ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, struct dentry *lower_dentry, - struct ecryptfs_crypt_stat *crypt_stat, struct inode *ecryptfs_dir_inode, struct nameidata *ecryptfs_nd) { @@ -254,6 +253,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, struct vfsmount *lower_mnt; struct inode *lower_inode; struct ecryptfs_mount_crypt_stat *mount_crypt_stat; + struct ecryptfs_crypt_stat *crypt_stat; char *page_virt = NULL; u64 file_size; int rc = 0; @@ -314,6 +314,11 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, goto out_free_kmem; } } + crypt_stat = &ecryptfs_inode_to_private( + ecryptfs_dentry->d_inode)->crypt_stat; + /* TODO: lock for crypt_stat comparison */ + if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) + ecryptfs_set_default_sizes(crypt_stat); rc = ecryptfs_read_and_validate_header_region(page_virt, ecryptfs_dentry->d_inode); if (rc) { @@ -362,9 +367,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, { char *encrypted_and_encoded_name = NULL; size_t encrypted_and_encoded_name_size; - struct ecryptfs_crypt_stat *crypt_stat = NULL; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL; - struct ecryptfs_inode_info *inode_info; struct dentry *lower_dir_dentry, *lower_dentry; int rc = 0; @@ -388,26 +391,15 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, } if (lower_dentry->d_inode) goto lookup_and_interpose; - inode_info = ecryptfs_inode_to_private(ecryptfs_dentry->d_inode); - if (inode_info) { - crypt_stat = &inode_info->crypt_stat; - /* TODO: lock for crypt_stat comparison */ - if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) - ecryptfs_set_default_sizes(crypt_stat); - } - if (crypt_stat) - mount_crypt_stat = crypt_stat->mount_crypt_stat; - else - mount_crypt_stat = &ecryptfs_superblock_to_private( - ecryptfs_dentry->d_sb)->mount_crypt_stat; - if (!(crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES)) - && !(mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) + mount_crypt_stat = &ecryptfs_superblock_to_private( + ecryptfs_dentry->d_sb)->mount_crypt_stat; + if (!(mount_crypt_stat + && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) goto lookup_and_interpose; dput(lower_dentry); rc = ecryptfs_encrypt_and_encode_filename( &encrypted_and_encoded_name, &encrypted_and_encoded_name_size, - crypt_stat, mount_crypt_stat, ecryptfs_dentry->d_name.name, + NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name, ecryptfs_dentry->d_name.len); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt and encode " @@ -426,7 +418,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, } lookup_and_interpose: rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry, - crypt_stat, ecryptfs_dir_inode, + ecryptfs_dir_inode, ecryptfs_nd); goto out; out_d_drop: diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index ff539420cc6..e4a6223c314 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -2375,7 +2375,7 @@ struct kmem_cache *ecryptfs_global_auth_tok_cache; int ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat, - char *sig) + char *sig, u32 global_auth_tok_flags) { struct ecryptfs_global_auth_tok *new_auth_tok; int rc = 0; @@ -2389,6 +2389,7 @@ ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat, goto out; } memcpy(new_auth_tok->sig, sig, ECRYPTFS_SIG_SIZE_HEX); + new_auth_tok->flags = global_auth_tok_flags; new_auth_tok->sig[ECRYPTFS_SIG_SIZE_HEX] = '\0'; mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex); list_add(&new_auth_tok->mount_crypt_stat_list, diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 789cf2e1be1..aed56c25539 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -319,7 +319,7 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) case ecryptfs_opt_ecryptfs_sig: sig_src = args[0].from; rc = ecryptfs_add_global_auth_tok(mount_crypt_stat, - sig_src); + sig_src, 0); if (rc) { printk(KERN_ERR "Error attempting to register " "global sig; rc = [%d]\n", rc); @@ -370,7 +370,8 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) ECRYPTFS_SIG_SIZE_HEX] = '\0'; rc = ecryptfs_add_global_auth_tok( mount_crypt_stat, - mount_crypt_stat->global_default_fnek_sig); + mount_crypt_stat->global_default_fnek_sig, + ECRYPTFS_AUTH_TOK_FNEK); if (rc) { printk(KERN_ERR "Error attempting to register " "global fnek sig [%s]; rc = [%d]\n", diff --git a/fs/exec.c b/fs/exec.c index 929b58004b7..b9f1c144b7a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/mount.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> @@ -127,6 +128,9 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) MAY_READ | MAY_EXEC | MAY_OPEN); if (error) goto exit; + error = ima_path_check(&nd.path, MAY_READ | MAY_EXEC | MAY_OPEN); + if (error) + goto exit; file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE); error = PTR_ERR(file); @@ -674,6 +678,9 @@ struct file *open_exec(const char *name) err = inode_permission(nd.path.dentry->d_inode, MAY_EXEC | MAY_OPEN); if (err) goto out_path_put; + err = ima_path_check(&nd.path, MAY_EXEC | MAY_OPEN); + if (err) + goto out_path_put; file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE); if (IS_ERR(file)) @@ -1184,6 +1191,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) retval = security_bprm_check(bprm); if (retval) return retval; + retval = ima_bprm_check(bprm); + if (retval) + return retval; /* kernel module loader fixup */ /* so we don't try to load run modprobe in kernel space. */ @@ -1284,6 +1294,7 @@ int do_execve(char * filename, retval = mutex_lock_interruptible(¤t->cred_exec_mutex); if (retval < 0) goto out_free; + current->in_execve = 1; retval = -ENOMEM; bprm->cred = prepare_exec_creds(); @@ -1337,6 +1348,7 @@ int do_execve(char * filename, goto out; /* execve succeeded */ + current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); acct_update_integrals(current); free_bprm(bprm); @@ -1355,6 +1367,7 @@ out_file: } out_unlock: + current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); out_free: diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e2eab196875..e0aa4fe4f59 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1122,7 +1122,8 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent_idx *ix; struct ext4_extent *ex; ext4_fsblk_t block; - int depth, ee_len; + int depth; /* Note, NOT eh_depth; depth from top of tree */ + int ee_len; BUG_ON(path == NULL); depth = path->p_depth; @@ -1179,7 +1180,8 @@ got_index: if (bh == NULL) return -EIO; eh = ext_block_hdr(bh); - if (ext4_ext_check_header(inode, eh, depth)) { + /* subtract from p_depth to get proper eh_depth */ + if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) { put_bh(bh); return -EIO; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f18a919be70..2d2b3585ee9 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -188,7 +188,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) struct ext4_group_desc *gdp; struct ext4_super_block *es; struct ext4_sb_info *sbi; - int fatal = 0, err, count; + int fatal = 0, err, count, cleared; ext4_group_t flex_group; if (atomic_read(&inode->i_count) > 1) { @@ -248,8 +248,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ - if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), - bit, bitmap_bh->b_data)) + spin_lock(sb_bgl_lock(sbi, block_group)); + cleared = ext4_clear_bit(bit, bitmap_bh->b_data); + spin_unlock(sb_bgl_lock(sbi, block_group)); + if (!cleared) ext4_error(sb, "ext4_free_inode", "bit already cleared for inode %lu", ino); else { @@ -696,6 +698,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) struct inode *ret; ext4_group_t i; int free = 0; + static int once = 1; ext4_group_t flex_group; /* Cannot create files in a deleted directory */ @@ -717,7 +720,8 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) ret2 = find_group_flex(sb, dir, &group); if (ret2 == -1) { ret2 = find_group_other(sb, dir, &group); - if (ret2 == 0 && printk_ratelimit()) + if (ret2 == 0 && once) + once = 0; printk(KERN_NOTICE "ext4: find_group_flex " "failed, fallback succeeded dir %lu\n", dir->i_ino); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4415beeb0b6..9f61e62f435 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1447,7 +1447,7 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); - BUG_ON(ex->fe_len >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); + BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); @@ -3292,7 +3292,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, } BUG_ON(start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical); - BUG_ON(size <= 0 || size >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); + BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ @@ -3589,6 +3589,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; + ext4_fsblk_t grp_blk; if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) return; @@ -3603,8 +3604,12 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, pa->pa_deleted = 1; spin_unlock(&pa->pa_lock); - /* -1 is to protect from crossing allocation group */ - ext4_get_group_no_and_offset(sb, pa->pa_pstart - 1, &grp, NULL); + grp_blk = pa->pa_pstart; + /* If linear, pa_pstart may be in the next group when pa is used up */ + if (pa->pa_linear) + grp_blk--; + + ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL); /* * possible race: diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 6b74d09adbe..de0004fe6e0 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -202,9 +202,9 @@ static sector_t _fat_bmap(struct address_space *mapping, sector_t block) sector_t blocknr; /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ - mutex_lock(&mapping->host->i_mutex); + down_read(&mapping->host->i_alloc_sem); blocknr = generic_block_bmap(mapping, block, fat_get_block); - mutex_unlock(&mapping->host->i_mutex); + up_read(&mapping->host->i_alloc_sem); return blocknr; } diff --git a/fs/file_table.c b/fs/file_table.c index bbeeac6efa1..da806aceae3 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> @@ -279,6 +280,7 @@ void __fput(struct file *file) if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); + ima_file_free(file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e5eaa62fd17..e3fe9918faa 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -274,6 +274,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) int ret; BUG_ON(inode->i_state & I_SYNC); + WARN_ON(inode->i_state & I_NEW); /* Set I_SYNC, reset I_DIRTY */ dirty = inode->i_state & I_DIRTY; @@ -298,6 +299,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) } spin_lock(&inode_lock); + WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_SYNC; if (!(inode->i_state & I_FREEING)) { if (!(inode->i_state & I_DIRTY) && @@ -470,6 +472,11 @@ void generic_sync_sb_inodes(struct super_block *sb, break; } + if (inode->i_state & I_NEW) { + requeue_io(inode); + continue; + } + if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; if (!sb_is_blkdev_sb(sb)) @@ -531,7 +538,7 @@ void generic_sync_sb_inodes(struct super_block *sb, list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct address_space *mapping; - if (inode->i_state & (I_FREEING|I_WILL_FREE)) + if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) continue; mapping = inode->i_mapping; if (mapping->nrpages == 0) diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index e563a644981..3a981b7f64c 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -1,6 +1,10 @@ config GFS2_FS tristate "GFS2 file system support" depends on EXPERIMENTAL && (64BIT || LBD) + select DLM if GFS2_FS_LOCKING_DLM + select CONFIGFS_FS if GFS2_FS_LOCKING_DLM + select SYSFS if GFS2_FS_LOCKING_DLM + select IP_SCTP if DLM_SCTP select FS_POSIX_ACL select CRC32 help @@ -18,17 +22,16 @@ config GFS2_FS the locking module below. Documentation and utilities for GFS2 can be found here: http://sources.redhat.com/cluster - The "nolock" lock module is now built in to GFS2 by default. + The "nolock" lock module is now built in to GFS2 by default. If + you want to use the DLM, be sure to enable HOTPLUG and IPv4/6 + networking. config GFS2_FS_LOCKING_DLM - tristate "GFS2 DLM locking module" - depends on GFS2_FS && SYSFS && NET && INET && (IPV6 || IPV6=n) - select IP_SCTP if DLM_SCTP - select CONFIGFS_FS - select DLM + bool "GFS2 DLM locking" + depends on (GFS2_FS!=n) && NET && INET && (IPV6 || IPV6=n) && HOTPLUG help Multiple node locking module for GFS2 - Most users of GFS2 will require this module. It provides the locking + Most users of GFS2 will require this. It provides the locking interface between GFS2 and the DLM, which is required to use GFS2 in a cluster environment. diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile index c1b4ec6a965..a851ea4bdf7 100644 --- a/fs/gfs2/Makefile +++ b/fs/gfs2/Makefile @@ -1,9 +1,9 @@ obj-$(CONFIG_GFS2_FS) += gfs2.o gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \ - glops.o inode.o log.o lops.o locking.o main.o meta_io.o \ + glops.o inode.o log.o lops.o main.o meta_io.o \ mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \ ops_fstype.o ops_inode.o ops_super.o quota.o \ recovery.o rgrp.o super.o sys.o trans.o util.o -obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += locking/dlm/ +gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index e335dceb6a4..43764f4fa76 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -15,7 +15,6 @@ #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 11ffc56f1f8..3a5d3f883e1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -13,7 +13,6 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index b7c8e5c7079..aef4d0c0674 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -60,7 +60,6 @@ #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> #include <linux/vmalloc.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c index f114ba2b355..dee9b03e5b3 100644 --- a/fs/gfs2/eaops.c +++ b/fs/gfs2/eaops.c @@ -14,7 +14,6 @@ #include <linux/capability.h> #include <linux/xattr.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <asm/uaccess.h> #include "gfs2.h" diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index 0d1c76d906a..899763aed21 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -13,7 +13,6 @@ #include <linux/buffer_head.h> #include <linux/xattr.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <asm/uaccess.h> #include "gfs2.h" diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6b983aef785..3984e47d1d3 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -10,7 +10,6 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/delay.h> #include <linux/sort.h> @@ -18,7 +17,6 @@ #include <linux/kallsyms.h> #include <linux/gfs2_ondisk.h> #include <linux/list.h> -#include <linux/lm_interface.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/rwsem.h> @@ -155,13 +153,10 @@ static void glock_free(struct gfs2_glock *gl) struct gfs2_sbd *sdp = gl->gl_sbd; struct inode *aspace = gl->gl_aspace; - if (sdp->sd_lockstruct.ls_ops->lm_put_lock) - sdp->sd_lockstruct.ls_ops->lm_put_lock(gl->gl_lock); - if (aspace) gfs2_aspace_put(aspace); - kmem_cache_free(gfs2_glock_cachep, gl); + sdp->sd_lockstruct.ls_ops->lm_put_lock(gfs2_glock_cachep, gl); } /** @@ -172,6 +167,7 @@ static void glock_free(struct gfs2_glock *gl) static void gfs2_glock_hold(struct gfs2_glock *gl) { + GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0); atomic_inc(&gl->gl_ref); } @@ -211,17 +207,15 @@ int gfs2_glock_put(struct gfs2_glock *gl) atomic_dec(&lru_count); } spin_unlock(&lru_lock); - GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_UNLOCKED); - GLOCK_BUG_ON(gl, !list_empty(&gl->gl_lru)); GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders)); glock_free(gl); rv = 1; goto out; } - write_unlock(gl_lock_addr(gl->gl_hash)); /* 1 for being hashed, 1 for having state != LM_ST_UNLOCKED */ if (atomic_read(&gl->gl_ref) == 2) gfs2_glock_schedule_for_reclaim(gl); + write_unlock(gl_lock_addr(gl->gl_hash)); out: return rv; } @@ -256,27 +250,6 @@ static struct gfs2_glock *search_bucket(unsigned int hash, } /** - * gfs2_glock_find() - Find glock by lock number - * @sdp: The GFS2 superblock - * @name: The lock name - * - * Returns: NULL, or the struct gfs2_glock with the requested number - */ - -static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp, - const struct lm_lockname *name) -{ - unsigned int hash = gl_hash(sdp, name); - struct gfs2_glock *gl; - - read_lock(gl_lock_addr(hash)); - gl = search_bucket(hash, sdp, name); - read_unlock(gl_lock_addr(hash)); - - return gl; -} - -/** * may_grant - check if its ok to grant a new lock * @gl: The glock * @gh: The lock request which we wish to grant @@ -523,7 +496,7 @@ out_locked: } static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock, - unsigned int cur_state, unsigned int req_state, + unsigned int req_state, unsigned int flags) { int ret = LM_OUT_ERROR; @@ -532,7 +505,7 @@ static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock, return req_state == LM_ST_UNLOCKED ? 0 : req_state; if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state, + ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, req_state, flags); return ret; } @@ -575,7 +548,7 @@ __acquires(&gl->gl_spin) gl->gl_state == LM_ST_DEFERRED) && !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) lck_flags |= LM_FLAG_TRY_1CB; - ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, target, lck_flags); + ret = gfs2_lm_lock(sdp, gl, target, lck_flags); if (!(ret & LM_OUT_ASYNC)) { finish_xmote(gl, ret); @@ -624,10 +597,11 @@ __acquires(&gl->gl_spin) GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)); + down_read(&gfs2_umount_flush_sem); if (test_bit(GLF_DEMOTE, &gl->gl_flags) && gl->gl_demote_state != gl->gl_state) { if (find_first_holder(gl)) - goto out; + goto out_unlock; if (nonblock) goto out_sched; set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); @@ -638,23 +612,26 @@ __acquires(&gl->gl_spin) gfs2_demote_wake(gl); ret = do_promote(gl); if (ret == 0) - goto out; + goto out_unlock; if (ret == 2) - return; + goto out_sem; gh = find_first_waiter(gl); gl->gl_target = gh->gh_state; if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) do_error(gl, 0); /* Fail queued try locks */ } do_xmote(gl, gh, gl->gl_target); +out_sem: + up_read(&gfs2_umount_flush_sem); return; out_sched: gfs2_glock_hold(gl); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); -out: +out_unlock: clear_bit(GLF_LOCK, &gl->gl_flags); + goto out_sem; } static void glock_work_func(struct work_struct *work) @@ -681,18 +658,6 @@ static void glock_work_func(struct work_struct *work) gfs2_glock_put(gl); } -static int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name, - void **lockp) -{ - int error = -EIO; - if (!sdp->sd_lockstruct.ls_ops->lm_get_lock) - return 0; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = sdp->sd_lockstruct.ls_ops->lm_get_lock( - sdp->sd_lockstruct.ls_lockspace, name, lockp); - return error; -} - /** * gfs2_glock_get() - Get a glock, or create one if one doesn't exist * @sdp: The GFS2 superblock @@ -719,10 +684,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl = search_bucket(hash, sdp, &name); read_unlock(gl_lock_addr(hash)); - if (gl || !create) { - *glp = gl; + *glp = gl; + if (gl) return 0; - } + if (!create) + return -ENOENT; gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_KERNEL); if (!gl) @@ -736,7 +702,9 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_demote_state = LM_ST_EXCLUSIVE; gl->gl_hash = hash; gl->gl_ops = glops; - gl->gl_stamp = jiffies; + snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number); + memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb)); + gl->gl_lksb.sb_lvbptr = gl->gl_lvb; gl->gl_tchange = jiffies; gl->gl_object = NULL; gl->gl_sbd = sdp; @@ -753,10 +721,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, } } - error = gfs2_lm_get_lock(sdp, &name, &gl->gl_lock); - if (error) - goto fail_aspace; - write_lock(gl_lock_addr(hash)); tmp = search_bucket(hash, sdp, &name); if (tmp) { @@ -772,9 +736,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, return 0; -fail_aspace: - if (gl->gl_aspace) - gfs2_aspace_put(gl->gl_aspace); fail: kmem_cache_free(gfs2_glock_cachep, gl); return error; @@ -966,7 +927,7 @@ do_cancel: if (!(gh->gh_flags & LM_FLAG_PRIORITY)) { spin_unlock(&gl->gl_spin); if (sdp->sd_lockstruct.ls_ops->lm_cancel) - sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock); + sdp->sd_lockstruct.ls_ops->lm_cancel(gl); spin_lock(&gl->gl_spin); } return; @@ -1051,7 +1012,6 @@ void gfs2_glock_dq(struct gfs2_holder *gh) spin_lock(&gl->gl_spin); clear_bit(GLF_LOCK, &gl->gl_flags); } - gl->gl_stamp = jiffies; if (list_empty(&gl->gl_holders) && !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && !test_bit(GLF_DEMOTE, &gl->gl_flags)) @@ -1240,70 +1200,13 @@ void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs) gfs2_glock_dq_uninit(&ghs[x]); } -static int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp) -{ - int error = -EIO; - if (!sdp->sd_lockstruct.ls_ops->lm_hold_lvb) - return 0; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = sdp->sd_lockstruct.ls_ops->lm_hold_lvb(lock, lvbp); - return error; -} - -/** - * gfs2_lvb_hold - attach a LVB from a glock - * @gl: The glock in question - * - */ - -int gfs2_lvb_hold(struct gfs2_glock *gl) -{ - int error; - - if (!atomic_read(&gl->gl_lvb_count)) { - error = gfs2_lm_hold_lvb(gl->gl_sbd, gl->gl_lock, &gl->gl_lvb); - if (error) - return error; - gfs2_glock_hold(gl); - } - atomic_inc(&gl->gl_lvb_count); - - return 0; -} - -/** - * gfs2_lvb_unhold - detach a LVB from a glock - * @gl: The glock in question - * - */ - -void gfs2_lvb_unhold(struct gfs2_glock *gl) -{ - struct gfs2_sbd *sdp = gl->gl_sbd; - - gfs2_glock_hold(gl); - gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count) > 0); - if (atomic_dec_and_test(&gl->gl_lvb_count)) { - if (sdp->sd_lockstruct.ls_ops->lm_unhold_lvb) - sdp->sd_lockstruct.ls_ops->lm_unhold_lvb(gl->gl_lock, gl->gl_lvb); - gl->gl_lvb = NULL; - gfs2_glock_put(gl); - } - gfs2_glock_put(gl); -} - -static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name, - unsigned int state) +void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) { - struct gfs2_glock *gl; unsigned long delay = 0; unsigned long holdtime; unsigned long now = jiffies; - gl = gfs2_glock_find(sdp, name); - if (!gl) - return; - + gfs2_glock_hold(gl); holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time; if (time_before(now, holdtime)) delay = holdtime - now; @@ -1317,74 +1220,33 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name, gfs2_glock_put(gl); } -static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid) -{ - struct gfs2_jdesc *jd; - - spin_lock(&sdp->sd_jindex_spin); - list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { - if (jd->jd_jid != jid) - continue; - jd->jd_dirty = 1; - break; - } - spin_unlock(&sdp->sd_jindex_spin); -} - /** - * gfs2_glock_cb - Callback used by locking module - * @sdp: Pointer to the superblock - * @type: Type of callback - * @data: Type dependent data pointer + * gfs2_glock_complete - Callback used by locking + * @gl: Pointer to the glock + * @ret: The return value from the dlm * - * Called by the locking module when it wants to tell us something. - * Either we need to drop a lock, one of our ASYNC requests completed, or - * a journal from another client needs to be recovered. */ -void gfs2_glock_cb(void *cb_data, unsigned int type, void *data) +void gfs2_glock_complete(struct gfs2_glock *gl, int ret) { - struct gfs2_sbd *sdp = cb_data; - - switch (type) { - case LM_CB_NEED_E: - blocking_cb(sdp, data, LM_ST_UNLOCKED); - return; - - case LM_CB_NEED_D: - blocking_cb(sdp, data, LM_ST_DEFERRED); - return; - - case LM_CB_NEED_S: - blocking_cb(sdp, data, LM_ST_SHARED); - return; - - case LM_CB_ASYNC: { - struct lm_async_cb *async = data; - struct gfs2_glock *gl; - - down_read(&gfs2_umount_flush_sem); - gl = gfs2_glock_find(sdp, &async->lc_name); - if (gfs2_assert_warn(sdp, gl)) + struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct; + gl->gl_reply = ret; + if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) { + struct gfs2_holder *gh; + spin_lock(&gl->gl_spin); + gh = find_first_waiter(gl); + if ((!(gh && (gh->gh_flags & LM_FLAG_NOEXP)) && + (gl->gl_target != LM_ST_UNLOCKED)) || + ((ret & ~LM_OUT_ST_MASK) != 0)) + set_bit(GLF_FROZEN, &gl->gl_flags); + spin_unlock(&gl->gl_spin); + if (test_bit(GLF_FROZEN, &gl->gl_flags)) return; - gl->gl_reply = async->lc_ret; - set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); - up_read(&gfs2_umount_flush_sem); - return; - } - - case LM_CB_NEED_RECOVERY: - gfs2_jdesc_make_dirty(sdp, *(unsigned int *)data); - if (sdp->sd_recoverd_process) - wake_up_process(sdp->sd_recoverd_process); - return; - - default: - gfs2_assert_warn(sdp, 0); - return; } + set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + gfs2_glock_hold(gl); + if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) + gfs2_glock_put(gl); } /** @@ -1515,6 +1377,25 @@ out: return has_entries; } + +/** + * thaw_glock - thaw out a glock which has an unprocessed reply waiting + * @gl: The glock to thaw + * + * N.B. When we freeze a glock, we leave a ref to the glock outstanding, + * so this has to result in the ref count being dropped by one. + */ + +static void thaw_glock(struct gfs2_glock *gl) +{ + if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) + return; + set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + gfs2_glock_hold(gl); + if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) + gfs2_glock_put(gl); +} + /** * clear_glock - look at a glock and see if we can free it from glock cache * @gl: the glock to look at @@ -1540,6 +1421,20 @@ static void clear_glock(struct gfs2_glock *gl) } /** + * gfs2_glock_thaw - Thaw any frozen glocks + * @sdp: The super block + * + */ + +void gfs2_glock_thaw(struct gfs2_sbd *sdp) +{ + unsigned x; + + for (x = 0; x < GFS2_GL_HASH_SIZE; x++) + examine_bucket(thaw_glock, sdp, x); +} + +/** * gfs2_gl_hash_clear - Empty out the glock hash table * @sdp: the filesystem * @wait: wait until it's all gone @@ -1619,7 +1514,7 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags) if (flags & LM_FLAG_NOEXP) *p++ = 'e'; if (flags & LM_FLAG_ANY) - *p++ = 'a'; + *p++ = 'A'; if (flags & LM_FLAG_PRIORITY) *p++ = 'p'; if (flags & GL_ASYNC) @@ -1683,6 +1578,10 @@ static const char *gflags2str(char *buf, const unsigned long *gflags) *p++ = 'i'; if (test_bit(GLF_REPLY_PENDING, gflags)) *p++ = 'r'; + if (test_bit(GLF_INITIAL, gflags)) + *p++ = 'I'; + if (test_bit(GLF_FROZEN, gflags)) + *p++ = 'F'; *p = 0; return buf; } @@ -1717,14 +1616,13 @@ static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) dtime *= 1000000/HZ; /* demote time in uSec */ if (!test_bit(GLF_DEMOTE, &gl->gl_flags)) dtime = 0; - gfs2_print_dbg(seq, "G: s:%s n:%u/%llu f:%s t:%s d:%s/%llu l:%d a:%d r:%d\n", + gfs2_print_dbg(seq, "G: s:%s n:%u/%llu f:%s t:%s d:%s/%llu a:%d r:%d\n", state2str(gl->gl_state), gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, gflags2str(gflags_buf, &gl->gl_flags), state2str(gl->gl_target), state2str(gl->gl_demote_state), dtime, - atomic_read(&gl->gl_lvb_count), atomic_read(&gl->gl_ail_count), atomic_read(&gl->gl_ref)); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 543ec7ecfbd..a602a28f6f0 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -11,15 +11,130 @@ #define __GLOCK_DOT_H__ #include <linux/sched.h> +#include <linux/parser.h> #include "incore.h" -/* Flags for lock requests; used in gfs2_holder gh_flag field. - From lm_interface.h: +/* Options for hostdata parser */ + +enum { + Opt_jid, + Opt_id, + Opt_first, + Opt_nodir, + Opt_err, +}; + +/* + * lm_lockname types + */ + +#define LM_TYPE_RESERVED 0x00 +#define LM_TYPE_NONDISK 0x01 +#define LM_TYPE_INODE 0x02 +#define LM_TYPE_RGRP 0x03 +#define LM_TYPE_META 0x04 +#define LM_TYPE_IOPEN 0x05 +#define LM_TYPE_FLOCK 0x06 +#define LM_TYPE_PLOCK 0x07 +#define LM_TYPE_QUOTA 0x08 +#define LM_TYPE_JOURNAL 0x09 + +/* + * lm_lock() states + * + * SHARED is compatible with SHARED, not with DEFERRED or EX. + * DEFERRED is compatible with DEFERRED, not with SHARED or EX. + */ + +#define LM_ST_UNLOCKED 0 +#define LM_ST_EXCLUSIVE 1 +#define LM_ST_DEFERRED 2 +#define LM_ST_SHARED 3 + +/* + * lm_lock() flags + * + * LM_FLAG_TRY + * Don't wait to acquire the lock if it can't be granted immediately. + * + * LM_FLAG_TRY_1CB + * Send one blocking callback if TRY is set and the lock is not granted. + * + * LM_FLAG_NOEXP + * GFS sets this flag on lock requests it makes while doing journal recovery. + * These special requests should not be blocked due to the recovery like + * ordinary locks would be. + * + * LM_FLAG_ANY + * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may + * also be granted in SHARED. The preferred state is whichever is compatible + * with other granted locks, or the specified state if no other locks exist. + * + * LM_FLAG_PRIORITY + * Override fairness considerations. Suppose a lock is held in a shared state + * and there is a pending request for the deferred state. A shared lock + * request with the priority flag would be allowed to bypass the deferred + * request and directly join the other shared lock. A shared lock request + * without the priority flag might be forced to wait until the deferred + * requested had acquired and released the lock. + */ + #define LM_FLAG_TRY 0x00000001 #define LM_FLAG_TRY_1CB 0x00000002 #define LM_FLAG_NOEXP 0x00000004 #define LM_FLAG_ANY 0x00000008 -#define LM_FLAG_PRIORITY 0x00000010 */ +#define LM_FLAG_PRIORITY 0x00000010 +#define GL_ASYNC 0x00000040 +#define GL_EXACT 0x00000080 +#define GL_SKIP 0x00000100 +#define GL_ATIME 0x00000200 +#define GL_NOCACHE 0x00000400 + +/* + * lm_lock() and lm_async_cb return flags + * + * LM_OUT_ST_MASK + * Masks the lower two bits of lock state in the returned value. + * + * LM_OUT_CANCELED + * The lock request was canceled. + * + * LM_OUT_ASYNC + * The result of the request will be returned in an LM_CB_ASYNC callback. + * + */ + +#define LM_OUT_ST_MASK 0x00000003 +#define LM_OUT_CANCELED 0x00000008 +#define LM_OUT_ASYNC 0x00000080 +#define LM_OUT_ERROR 0x00000100 + +/* + * lm_recovery_done() messages + */ + +#define LM_RD_GAVEUP 308 +#define LM_RD_SUCCESS 309 + +#define GLR_TRYFAILED 13 + +struct lm_lockops { + const char *lm_proto_name; + int (*lm_mount) (struct gfs2_sbd *sdp, const char *fsname); + void (*lm_unmount) (struct gfs2_sbd *sdp); + void (*lm_withdraw) (struct gfs2_sbd *sdp); + void (*lm_put_lock) (struct kmem_cache *cachep, void *gl); + unsigned int (*lm_lock) (struct gfs2_glock *gl, + unsigned int req_state, unsigned int flags); + void (*lm_cancel) (struct gfs2_glock *gl); + const match_table_t *lm_tokens; +}; + +#define LM_FLAG_TRY 0x00000001 +#define LM_FLAG_TRY_1CB 0x00000002 +#define LM_FLAG_NOEXP 0x00000004 +#define LM_FLAG_ANY 0x00000008 +#define LM_FLAG_PRIORITY 0x00000010 #define GL_ASYNC 0x00000040 #define GL_EXACT 0x00000080 @@ -128,10 +243,12 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl, int gfs2_lvb_hold(struct gfs2_glock *gl); void gfs2_lvb_unhold(struct gfs2_glock *gl); -void gfs2_glock_cb(void *cb_data, unsigned int type, void *data); +void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state); +void gfs2_glock_complete(struct gfs2_glock *gl, int ret); void gfs2_reclaim_glock(struct gfs2_sbd *sdp); void gfs2_gl_hash_clear(struct gfs2_sbd *sdp); void gfs2_glock_finish_truncate(struct gfs2_inode *ip); +void gfs2_glock_thaw(struct gfs2_sbd *sdp); int __init gfs2_glock_init(void); void gfs2_glock_exit(void); @@ -141,4 +258,6 @@ void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp); int gfs2_register_debugfs(void); void gfs2_unregister_debugfs(void); +extern const struct lm_lockops gfs2_dlm_ops; + #endif /* __GLOCK_DOT_H__ */ diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 8522d3aa64f..bf23a62aa92 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -12,7 +12,6 @@ #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <linux/bio.h> #include "gfs2.h" @@ -38,20 +37,25 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_sbd; - unsigned int blocks; struct list_head *head = &gl->gl_ail_list; struct gfs2_bufdata *bd; struct buffer_head *bh; - int error; + struct gfs2_trans tr; - blocks = atomic_read(&gl->gl_ail_count); - if (!blocks) - return; + memset(&tr, 0, sizeof(tr)); + tr.tr_revokes = atomic_read(&gl->gl_ail_count); - error = gfs2_trans_begin(sdp, 0, blocks); - if (gfs2_assert_withdraw(sdp, !error)) + if (!tr.tr_revokes) return; + /* A shortened, inline version of gfs2_trans_begin() */ + tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64)); + tr.tr_ip = (unsigned long)__builtin_return_address(0); + INIT_LIST_HEAD(&tr.tr_list_buf); + gfs2_log_reserve(sdp, tr.tr_reserved); + BUG_ON(current->journal_info); + current->journal_info = &tr; + gfs2_log_lock(sdp); while (!list_empty(head)) { bd = list_entry(head->next, struct gfs2_bufdata, @@ -72,29 +76,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) } /** - * gfs2_pte_inval - Sync and invalidate all PTEs associated with a glock - * @gl: the glock - * - */ - -static void gfs2_pte_inval(struct gfs2_glock *gl) -{ - struct gfs2_inode *ip; - struct inode *inode; - - ip = gl->gl_object; - inode = &ip->i_inode; - if (!ip || !S_ISREG(inode->i_mode)) - return; - - unmap_shared_mapping_range(inode->i_mapping, 0, 0); - if (test_bit(GIF_SW_PAGED, &ip->i_flags)) - set_bit(GLF_DIRTY, &gl->gl_flags); - -} - -/** - * meta_go_sync - sync out the metadata for this glock + * rgrp_go_sync - sync out the metadata for this glock * @gl: the glock * * Called when demoting or unlocking an EX glock. We must flush @@ -102,36 +84,42 @@ static void gfs2_pte_inval(struct gfs2_glock *gl) * not return to caller to demote/unlock the glock until I/O is complete. */ -static void meta_go_sync(struct gfs2_glock *gl) +static void rgrp_go_sync(struct gfs2_glock *gl) { - if (gl->gl_state != LM_ST_EXCLUSIVE) + struct address_space *metamapping = gl->gl_aspace->i_mapping; + int error; + + if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return; + BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE); - if (test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) { - gfs2_log_flush(gl->gl_sbd, gl); - gfs2_meta_sync(gl); - gfs2_ail_empty_gl(gl); - } + gfs2_log_flush(gl->gl_sbd, gl); + filemap_fdatawrite(metamapping); + error = filemap_fdatawait(metamapping); + mapping_set_error(metamapping, error); + gfs2_ail_empty_gl(gl); } /** - * meta_go_inval - invalidate the metadata for this glock + * rgrp_go_inval - invalidate the metadata for this glock * @gl: the glock * @flags: * + * We never used LM_ST_DEFERRED with resource groups, so that we + * should always see the metadata flag set here. + * */ -static void meta_go_inval(struct gfs2_glock *gl, int flags) +static void rgrp_go_inval(struct gfs2_glock *gl, int flags) { - if (!(flags & DIO_METADATA)) - return; + struct address_space *mapping = gl->gl_aspace->i_mapping; - gfs2_meta_inval(gl); - if (gl->gl_object == GFS2_I(gl->gl_sbd->sd_rindex)) - gl->gl_sbd->sd_rindex_uptodate = 0; - else if (gl->gl_ops == &gfs2_rgrp_glops && gl->gl_object) { - struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object; + BUG_ON(!(flags & DIO_METADATA)); + gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count)); + truncate_inode_pages(mapping, 0); + if (gl->gl_object) { + struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object; rgd->rd_flags &= ~GFS2_RDF_UPTODATE; } } @@ -148,48 +136,54 @@ static void inode_go_sync(struct gfs2_glock *gl) struct address_space *metamapping = gl->gl_aspace->i_mapping; int error; - if (gl->gl_state != LM_ST_UNLOCKED) - gfs2_pte_inval(gl); - if (gl->gl_state != LM_ST_EXCLUSIVE) - return; - if (ip && !S_ISREG(ip->i_inode.i_mode)) ip = NULL; + if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) + unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); + if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) + return; - if (test_bit(GLF_DIRTY, &gl->gl_flags)) { - gfs2_log_flush(gl->gl_sbd, gl); - filemap_fdatawrite(metamapping); - if (ip) { - struct address_space *mapping = ip->i_inode.i_mapping; - filemap_fdatawrite(mapping); - error = filemap_fdatawait(mapping); - mapping_set_error(mapping, error); - } - error = filemap_fdatawait(metamapping); - mapping_set_error(metamapping, error); - clear_bit(GLF_DIRTY, &gl->gl_flags); - gfs2_ail_empty_gl(gl); + BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE); + + gfs2_log_flush(gl->gl_sbd, gl); + filemap_fdatawrite(metamapping); + if (ip) { + struct address_space *mapping = ip->i_inode.i_mapping; + filemap_fdatawrite(mapping); + error = filemap_fdatawait(mapping); + mapping_set_error(mapping, error); } + error = filemap_fdatawait(metamapping); + mapping_set_error(metamapping, error); + gfs2_ail_empty_gl(gl); } /** * inode_go_inval - prepare a inode glock to be released * @gl: the glock * @flags: + * + * Normally we invlidate everything, but if we are moving into + * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we + * can keep hold of the metadata, since it won't have changed. * */ static void inode_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_inode *ip = gl->gl_object; - int meta = (flags & DIO_METADATA); - if (meta) { - gfs2_meta_inval(gl); + gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count)); + + if (flags & DIO_METADATA) { + struct address_space *mapping = gl->gl_aspace->i_mapping; + truncate_inode_pages(mapping, 0); if (ip) set_bit(GIF_INVALID, &ip->i_flags); } + if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) + gl->gl_sbd->sd_rindex_uptodate = 0; if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); } @@ -390,20 +384,7 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl) return 0; } -/** - * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock - * @gl: the glock - * - * Returns: 1 if it's ok - */ - -static int quota_go_demote_ok(const struct gfs2_glock *gl) -{ - return !atomic_read(&gl->gl_lvb_count); -} - const struct gfs2_glock_operations gfs2_meta_glops = { - .go_xmote_th = meta_go_sync, .go_type = LM_TYPE_META, }; @@ -418,8 +399,8 @@ const struct gfs2_glock_operations gfs2_inode_glops = { }; const struct gfs2_glock_operations gfs2_rgrp_glops = { - .go_xmote_th = meta_go_sync, - .go_inval = meta_go_inval, + .go_xmote_th = rgrp_go_sync, + .go_inval = rgrp_go_inval, .go_demote_ok = rgrp_go_demote_ok, .go_lock = rgrp_go_lock, .go_unlock = rgrp_go_unlock, @@ -448,7 +429,6 @@ const struct gfs2_glock_operations gfs2_nondisk_glops = { }; const struct gfs2_glock_operations gfs2_quota_glops = { - .go_demote_ok = quota_go_demote_ok, .go_type = LM_TYPE_QUOTA, }; @@ -456,3 +436,15 @@ const struct gfs2_glock_operations gfs2_journal_glops = { .go_type = LM_TYPE_JOURNAL, }; +const struct gfs2_glock_operations *gfs2_glops_list[] = { + [LM_TYPE_META] = &gfs2_meta_glops, + [LM_TYPE_INODE] = &gfs2_inode_glops, + [LM_TYPE_RGRP] = &gfs2_rgrp_glops, + [LM_TYPE_NONDISK] = &gfs2_trans_glops, + [LM_TYPE_IOPEN] = &gfs2_iopen_glops, + [LM_TYPE_FLOCK] = &gfs2_flock_glops, + [LM_TYPE_NONDISK] = &gfs2_nondisk_glops, + [LM_TYPE_QUOTA] = &gfs2_quota_glops, + [LM_TYPE_JOURNAL] = &gfs2_journal_glops, +}; + diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h index a1d9b5b024e..b3aa2e3210f 100644 --- a/fs/gfs2/glops.h +++ b/fs/gfs2/glops.h @@ -21,5 +21,6 @@ extern const struct gfs2_glock_operations gfs2_flock_glops; extern const struct gfs2_glock_operations gfs2_nondisk_glops; extern const struct gfs2_glock_operations gfs2_quota_glops; extern const struct gfs2_glock_operations gfs2_journal_glops; +extern const struct gfs2_glock_operations *gfs2_glops_list[]; #endif /* __GLOPS_DOT_H__ */ diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 608849d0002..399d1b97804 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -12,6 +12,8 @@ #include <linux/fs.h> #include <linux/workqueue.h> +#include <linux/dlm.h> +#include <linux/buffer_head.h> #define DIO_WAIT 0x00000010 #define DIO_METADATA 0x00000020 @@ -26,6 +28,7 @@ struct gfs2_trans; struct gfs2_ail; struct gfs2_jdesc; struct gfs2_sbd; +struct lm_lockops; typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret); @@ -121,6 +124,28 @@ struct gfs2_bufdata { struct list_head bd_ail_gl_list; }; +/* + * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a + * prefix of lock_dlm_ gets awkward. + */ + +#define GDLM_STRNAME_BYTES 25 +#define GDLM_LVB_SIZE 32 + +enum { + DFL_BLOCK_LOCKS = 0, +}; + +struct lm_lockname { + u64 ln_number; + unsigned int ln_type; +}; + +#define lm_name_equal(name1, name2) \ + (((name1)->ln_number == (name2)->ln_number) && \ + ((name1)->ln_type == (name2)->ln_type)) + + struct gfs2_glock_operations { void (*go_xmote_th) (struct gfs2_glock *gl); int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh); @@ -162,6 +187,8 @@ enum { GLF_LFLUSH = 7, GLF_INVALIDATE_IN_PROGRESS = 8, GLF_REPLY_PENDING = 9, + GLF_INITIAL = 10, + GLF_FROZEN = 11, }; struct gfs2_glock { @@ -176,16 +203,15 @@ struct gfs2_glock { unsigned int gl_target; unsigned int gl_reply; unsigned int gl_hash; + unsigned int gl_req; unsigned int gl_demote_state; /* state requested by remote node */ unsigned long gl_demote_time; /* time of first demote request */ struct list_head gl_holders; const struct gfs2_glock_operations *gl_ops; - void *gl_lock; - char *gl_lvb; - atomic_t gl_lvb_count; - - unsigned long gl_stamp; + char gl_strname[GDLM_STRNAME_BYTES]; + struct dlm_lksb gl_lksb; + char gl_lvb[32]; unsigned long gl_tchange; void *gl_object; @@ -283,7 +309,9 @@ enum { struct gfs2_quota_data { struct list_head qd_list; - unsigned int qd_count; + struct list_head qd_reclaim; + + atomic_t qd_count; u32 qd_id; unsigned long qd_flags; /* QDF_... */ @@ -303,7 +331,6 @@ struct gfs2_quota_data { u64 qd_sync_gen; unsigned long qd_last_warn; - unsigned long qd_last_touched; }; struct gfs2_trans { @@ -390,7 +417,7 @@ struct gfs2_args { unsigned int ar_suiddir:1; /* suiddir support */ unsigned int ar_data:2; /* ordered/writeback */ unsigned int ar_meta:1; /* mount metafs */ - unsigned int ar_num_glockd; /* Number of glockd threads */ + unsigned int ar_discard:1; /* discard requests */ }; struct gfs2_tune { @@ -406,7 +433,6 @@ struct gfs2_tune { unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */ unsigned int gt_quota_scale_num; /* Numerator */ unsigned int gt_quota_scale_den; /* Denominator */ - unsigned int gt_quota_cache_secs; unsigned int gt_quota_quantum; /* Secs between syncs to quota file */ unsigned int gt_new_files_jdata; unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */ @@ -445,6 +471,31 @@ struct gfs2_sb_host { char sb_lockproto[GFS2_LOCKNAME_LEN]; char sb_locktable[GFS2_LOCKNAME_LEN]; + u8 sb_uuid[16]; +}; + +/* + * lm_mount() return values + * + * ls_jid - the journal ID this node should use + * ls_first - this node is the first to mount the file system + * ls_lockspace - lock module's context for this file system + * ls_ops - lock module's functions + */ + +struct lm_lockstruct { + u32 ls_id; + unsigned int ls_jid; + unsigned int ls_first; + unsigned int ls_first_done; + unsigned int ls_nodir; + const struct lm_lockops *ls_ops; + unsigned long ls_flags; + dlm_lockspace_t *ls_dlm; + + int ls_recover_jid; + int ls_recover_jid_done; + int ls_recover_jid_status; }; struct gfs2_sbd { @@ -520,7 +571,6 @@ struct gfs2_sbd { spinlock_t sd_jindex_spin; struct mutex sd_jindex_mutex; unsigned int sd_journals; - unsigned long sd_jindex_refresh_time; struct gfs2_jdesc *sd_jdesc; struct gfs2_holder sd_journal_gh; @@ -540,7 +590,6 @@ struct gfs2_sbd { struct list_head sd_quota_list; atomic_t sd_quota_count; - spinlock_t sd_quota_spin; struct mutex sd_quota_mutex; wait_queue_head_t sd_quota_wait; struct list_head sd_trunc_list; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 3b87c188da4..7b277d44915 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -16,7 +16,6 @@ #include <linux/sort.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/security.h> #include <linux/time.h> @@ -137,16 +136,16 @@ void gfs2_set_iop(struct inode *inode) if (S_ISREG(mode)) { inode->i_op = &gfs2_file_iops; - if (sdp->sd_args.ar_localflocks) - inode->i_fop = &gfs2_file_fops_nolock; + if (gfs2_localflocks(sdp)) + inode->i_fop = gfs2_file_fops_nolock; else - inode->i_fop = &gfs2_file_fops; + inode->i_fop = gfs2_file_fops; } else if (S_ISDIR(mode)) { inode->i_op = &gfs2_dir_iops; - if (sdp->sd_args.ar_localflocks) - inode->i_fop = &gfs2_dir_fops_nolock; + if (gfs2_localflocks(sdp)) + inode->i_fop = gfs2_dir_fops_nolock; else - inode->i_fop = &gfs2_dir_fops; + inode->i_fop = gfs2_dir_fops; } else if (S_ISLNK(mode)) { inode->i_op = &gfs2_symlink_iops; } else { diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index d5329364cdf..dca4fee3078 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -101,12 +101,26 @@ void gfs2_dinode_print(const struct gfs2_inode *ip); extern const struct inode_operations gfs2_file_iops; extern const struct inode_operations gfs2_dir_iops; extern const struct inode_operations gfs2_symlink_iops; -extern const struct file_operations gfs2_file_fops; -extern const struct file_operations gfs2_dir_fops; -extern const struct file_operations gfs2_file_fops_nolock; -extern const struct file_operations gfs2_dir_fops_nolock; +extern const struct file_operations *gfs2_file_fops_nolock; +extern const struct file_operations *gfs2_dir_fops_nolock; extern void gfs2_set_inode_flags(struct inode *inode); + +#ifdef CONFIG_GFS2_FS_LOCKING_DLM +extern const struct file_operations *gfs2_file_fops; +extern const struct file_operations *gfs2_dir_fops; +static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) +{ + return sdp->sd_args.ar_localflocks; +} +#else /* Single node only */ +#define gfs2_file_fops NULL +#define gfs2_dir_fops NULL +static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) +{ + return 1; +} +#endif /* CONFIG_GFS2_FS_LOCKING_DLM */ #endif /* __INODE_DOT_H__ */ diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c new file mode 100644 index 00000000000..46df988323b --- /dev/null +++ b/fs/gfs2/lock_dlm.c @@ -0,0 +1,241 @@ +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License version 2. + */ + +#include <linux/fs.h> +#include <linux/dlm.h> +#include <linux/types.h> +#include <linux/gfs2_ondisk.h> + +#include "incore.h" +#include "glock.h" +#include "util.h" + + +static void gdlm_ast(void *arg) +{ + struct gfs2_glock *gl = arg; + unsigned ret = gl->gl_state; + + BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED); + + if (gl->gl_lksb.sb_flags & DLM_SBF_VALNOTVALID) + memset(gl->gl_lvb, 0, GDLM_LVB_SIZE); + + switch (gl->gl_lksb.sb_status) { + case -DLM_EUNLOCK: /* Unlocked, so glock can be freed */ + kmem_cache_free(gfs2_glock_cachep, gl); + return; + case -DLM_ECANCEL: /* Cancel while getting lock */ + ret |= LM_OUT_CANCELED; + goto out; + case -EAGAIN: /* Try lock fails */ + goto out; + case -EINVAL: /* Invalid */ + case -ENOMEM: /* Out of memory */ + ret |= LM_OUT_ERROR; + goto out; + case 0: /* Success */ + break; + default: /* Something unexpected */ + BUG(); + } + + ret = gl->gl_req; + if (gl->gl_lksb.sb_flags & DLM_SBF_ALTMODE) { + if (gl->gl_req == LM_ST_SHARED) + ret = LM_ST_DEFERRED; + else if (gl->gl_req == LM_ST_DEFERRED) + ret = LM_ST_SHARED; + else + BUG(); + } + + set_bit(GLF_INITIAL, &gl->gl_flags); + gfs2_glock_complete(gl, ret); + return; +out: + if (!test_bit(GLF_INITIAL, &gl->gl_flags)) + gl->gl_lksb.sb_lkid = 0; + gfs2_glock_complete(gl, ret); +} + +static void gdlm_bast(void *arg, int mode) +{ + struct gfs2_glock *gl = arg; + + switch (mode) { + case DLM_LOCK_EX: + gfs2_glock_cb(gl, LM_ST_UNLOCKED); + break; + case DLM_LOCK_CW: + gfs2_glock_cb(gl, LM_ST_DEFERRED); + break; + case DLM_LOCK_PR: + gfs2_glock_cb(gl, LM_ST_SHARED); + break; + default: + printk(KERN_ERR "unknown bast mode %d", mode); + BUG(); + } +} + +/* convert gfs lock-state to dlm lock-mode */ + +static int make_mode(const unsigned int lmstate) +{ + switch (lmstate) { + case LM_ST_UNLOCKED: + return DLM_LOCK_NL; + case LM_ST_EXCLUSIVE: + return DLM_LOCK_EX; + case LM_ST_DEFERRED: + return DLM_LOCK_CW; + case LM_ST_SHARED: + return DLM_LOCK_PR; + } + printk(KERN_ERR "unknown LM state %d", lmstate); + BUG(); + return -1; +} + +static u32 make_flags(const u32 lkid, const unsigned int gfs_flags, + const int req) +{ + u32 lkf = 0; + + if (gfs_flags & LM_FLAG_TRY) + lkf |= DLM_LKF_NOQUEUE; + + if (gfs_flags & LM_FLAG_TRY_1CB) { + lkf |= DLM_LKF_NOQUEUE; + lkf |= DLM_LKF_NOQUEUEBAST; + } + + if (gfs_flags & LM_FLAG_PRIORITY) { + lkf |= DLM_LKF_NOORDER; + lkf |= DLM_LKF_HEADQUE; + } + + if (gfs_flags & LM_FLAG_ANY) { + if (req == DLM_LOCK_PR) + lkf |= DLM_LKF_ALTCW; + else if (req == DLM_LOCK_CW) + lkf |= DLM_LKF_ALTPR; + else + BUG(); + } + + if (lkid != 0) + lkf |= DLM_LKF_CONVERT; + + lkf |= DLM_LKF_VALBLK; + + return lkf; +} + +static unsigned int gdlm_lock(struct gfs2_glock *gl, + unsigned int req_state, unsigned int flags) +{ + struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct; + int error; + int req; + u32 lkf; + + gl->gl_req = req_state; + req = make_mode(req_state); + lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req); + + /* + * Submit the actual lock request. + */ + + error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname, + GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast); + if (error == -EAGAIN) + return 0; + if (error) + return LM_OUT_ERROR; + return LM_OUT_ASYNC; +} + +static void gdlm_put_lock(struct kmem_cache *cachep, void *ptr) +{ + struct gfs2_glock *gl = ptr; + struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct; + int error; + + if (gl->gl_lksb.sb_lkid == 0) { + kmem_cache_free(cachep, gl); + return; + } + + error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, + NULL, gl); + if (error) { + printk(KERN_ERR "gdlm_unlock %x,%llx err=%d\n", + gl->gl_name.ln_type, + (unsigned long long)gl->gl_name.ln_number, error); + return; + } +} + +static void gdlm_cancel(struct gfs2_glock *gl) +{ + struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct; + dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_CANCEL, NULL, gl); +} + +static int gdlm_mount(struct gfs2_sbd *sdp, const char *fsname) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + int error; + + if (fsname == NULL) { + fs_info(sdp, "no fsname found\n"); + return -EINVAL; + } + + error = dlm_new_lockspace(fsname, strlen(fsname), &ls->ls_dlm, + DLM_LSFL_FS | DLM_LSFL_NEWEXCL | + (ls->ls_nodir ? DLM_LSFL_NODIR : 0), + GDLM_LVB_SIZE); + if (error) + printk(KERN_ERR "dlm_new_lockspace error %d", error); + + return error; +} + +static void gdlm_unmount(struct gfs2_sbd *sdp) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + + if (ls->ls_dlm) { + dlm_release_lockspace(ls->ls_dlm, 2); + ls->ls_dlm = NULL; + } +} + +static const match_table_t dlm_tokens = { + { Opt_jid, "jid=%d"}, + { Opt_id, "id=%d"}, + { Opt_first, "first=%d"}, + { Opt_nodir, "nodir=%d"}, + { Opt_err, NULL }, +}; + +const struct lm_lockops gfs2_dlm_ops = { + .lm_proto_name = "lock_dlm", + .lm_mount = gdlm_mount, + .lm_unmount = gdlm_unmount, + .lm_put_lock = gdlm_put_lock, + .lm_lock = gdlm_lock, + .lm_cancel = gdlm_cancel, + .lm_tokens = &dlm_tokens, +}; + diff --git a/fs/gfs2/locking.c b/fs/gfs2/locking.c deleted file mode 100644 index 523243a13a2..00000000000 --- a/fs/gfs2/locking.c +++ /dev/null @@ -1,232 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/string.h> -#include <linux/slab.h> -#include <linux/wait.h> -#include <linux/sched.h> -#include <linux/kmod.h> -#include <linux/fs.h> -#include <linux/delay.h> -#include <linux/lm_interface.h> - -struct lmh_wrapper { - struct list_head lw_list; - const struct lm_lockops *lw_ops; -}; - -static int nolock_mount(char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj); - -/* List of registered low-level locking protocols. A file system selects one - of them by name at mount time, e.g. lock_nolock, lock_dlm. */ - -static const struct lm_lockops nolock_ops = { - .lm_proto_name = "lock_nolock", - .lm_mount = nolock_mount, -}; - -static struct lmh_wrapper nolock_proto = { - .lw_list = LIST_HEAD_INIT(nolock_proto.lw_list), - .lw_ops = &nolock_ops, -}; - -static LIST_HEAD(lmh_list); -static DEFINE_MUTEX(lmh_lock); - -static int nolock_mount(char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj) -{ - char *c; - unsigned int jid; - - c = strstr(host_data, "jid="); - if (!c) - jid = 0; - else { - c += 4; - sscanf(c, "%u", &jid); - } - - lockstruct->ls_jid = jid; - lockstruct->ls_first = 1; - lockstruct->ls_lvb_size = min_lvb_size; - lockstruct->ls_ops = &nolock_ops; - lockstruct->ls_flags = LM_LSFLAG_LOCAL; - - return 0; -} - -/** - * gfs2_register_lockproto - Register a low-level locking protocol - * @proto: the protocol definition - * - * Returns: 0 on success, -EXXX on failure - */ - -int gfs2_register_lockproto(const struct lm_lockops *proto) -{ - struct lmh_wrapper *lw; - - mutex_lock(&lmh_lock); - - list_for_each_entry(lw, &lmh_list, lw_list) { - if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) { - mutex_unlock(&lmh_lock); - printk(KERN_INFO "GFS2: protocol %s already exists\n", - proto->lm_proto_name); - return -EEXIST; - } - } - - lw = kzalloc(sizeof(struct lmh_wrapper), GFP_KERNEL); - if (!lw) { - mutex_unlock(&lmh_lock); - return -ENOMEM; - } - - lw->lw_ops = proto; - list_add(&lw->lw_list, &lmh_list); - - mutex_unlock(&lmh_lock); - - return 0; -} - -/** - * gfs2_unregister_lockproto - Unregister a low-level locking protocol - * @proto: the protocol definition - * - */ - -void gfs2_unregister_lockproto(const struct lm_lockops *proto) -{ - struct lmh_wrapper *lw; - - mutex_lock(&lmh_lock); - - list_for_each_entry(lw, &lmh_list, lw_list) { - if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) { - list_del(&lw->lw_list); - mutex_unlock(&lmh_lock); - kfree(lw); - return; - } - } - - mutex_unlock(&lmh_lock); - - printk(KERN_WARNING "GFS2: can't unregister lock protocol %s\n", - proto->lm_proto_name); -} - -/** - * gfs2_mount_lockproto - Mount a lock protocol - * @proto_name - the name of the protocol - * @table_name - the name of the lock space - * @host_data - data specific to this host - * @cb - the callback to the code using the lock module - * @sdp - The GFS2 superblock - * @min_lvb_size - the mininum LVB size that the caller can deal with - * @flags - LM_MFLAG_* - * @lockstruct - a structure returned describing the mount - * - * Returns: 0 on success, -EXXX on failure - */ - -int gfs2_mount_lockproto(char *proto_name, char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj) -{ - struct lmh_wrapper *lw = NULL; - int try = 0; - int error, found; - - -retry: - mutex_lock(&lmh_lock); - - if (list_empty(&nolock_proto.lw_list)) - list_add(&nolock_proto.lw_list, &lmh_list); - - found = 0; - list_for_each_entry(lw, &lmh_list, lw_list) { - if (!strcmp(lw->lw_ops->lm_proto_name, proto_name)) { - found = 1; - break; - } - } - - if (!found) { - if (!try && capable(CAP_SYS_MODULE)) { - try = 1; - mutex_unlock(&lmh_lock); - request_module(proto_name); - goto retry; - } - printk(KERN_INFO "GFS2: can't find protocol %s\n", proto_name); - error = -ENOENT; - goto out; - } - - if (lw->lw_ops->lm_owner && - !try_module_get(lw->lw_ops->lm_owner)) { - try = 0; - mutex_unlock(&lmh_lock); - msleep(1000); - goto retry; - } - - error = lw->lw_ops->lm_mount(table_name, host_data, cb, cb_data, - min_lvb_size, flags, lockstruct, fskobj); - if (error) - module_put(lw->lw_ops->lm_owner); -out: - mutex_unlock(&lmh_lock); - return error; -} - -void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct) -{ - mutex_lock(&lmh_lock); - if (lockstruct->ls_ops->lm_unmount) - lockstruct->ls_ops->lm_unmount(lockstruct->ls_lockspace); - if (lockstruct->ls_ops->lm_owner) - module_put(lockstruct->ls_ops->lm_owner); - mutex_unlock(&lmh_lock); -} - -/** - * gfs2_withdraw_lockproto - abnormally unmount a lock module - * @lockstruct: the lockstruct passed into mount - * - */ - -void gfs2_withdraw_lockproto(struct lm_lockstruct *lockstruct) -{ - mutex_lock(&lmh_lock); - lockstruct->ls_ops->lm_withdraw(lockstruct->ls_lockspace); - if (lockstruct->ls_ops->lm_owner) - module_put(lockstruct->ls_ops->lm_owner); - mutex_unlock(&lmh_lock); -} - -EXPORT_SYMBOL_GPL(gfs2_register_lockproto); -EXPORT_SYMBOL_GPL(gfs2_unregister_lockproto); - diff --git a/fs/gfs2/locking/dlm/Makefile b/fs/gfs2/locking/dlm/Makefile deleted file mode 100644 index 2609bb6cd01..00000000000 --- a/fs/gfs2/locking/dlm/Makefile +++ /dev/null @@ -1,3 +0,0 @@ -obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o -lock_dlm-y := lock.o main.o mount.o sysfs.o thread.o - diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c deleted file mode 100644 index 2482c904750..00000000000 --- a/fs/gfs2/locking/dlm/lock.c +++ /dev/null @@ -1,708 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include "lock_dlm.h" - -static char junk_lvb[GDLM_LVB_SIZE]; - - -/* convert dlm lock-mode to gfs lock-state */ - -static s16 gdlm_make_lmstate(s16 dlmmode) -{ - switch (dlmmode) { - case DLM_LOCK_IV: - case DLM_LOCK_NL: - return LM_ST_UNLOCKED; - case DLM_LOCK_EX: - return LM_ST_EXCLUSIVE; - case DLM_LOCK_CW: - return LM_ST_DEFERRED; - case DLM_LOCK_PR: - return LM_ST_SHARED; - } - gdlm_assert(0, "unknown DLM mode %d", dlmmode); - return -1; -} - -/* A lock placed on this queue is re-submitted to DLM as soon as the lock_dlm - thread gets to it. */ - -static void queue_submit(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - - spin_lock(&ls->async_lock); - list_add_tail(&lp->delay_list, &ls->submit); - spin_unlock(&ls->async_lock); - wake_up(&ls->thread_wait); -} - -static void wake_up_ast(struct gdlm_lock *lp) -{ - clear_bit(LFL_AST_WAIT, &lp->flags); - smp_mb__after_clear_bit(); - wake_up_bit(&lp->flags, LFL_AST_WAIT); -} - -static void gdlm_delete_lp(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - - spin_lock(&ls->async_lock); - if (!list_empty(&lp->delay_list)) - list_del_init(&lp->delay_list); - ls->all_locks_count--; - spin_unlock(&ls->async_lock); - - kfree(lp); -} - -static void gdlm_queue_delayed(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - - spin_lock(&ls->async_lock); - list_add_tail(&lp->delay_list, &ls->delayed); - spin_unlock(&ls->async_lock); -} - -static void process_complete(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - struct lm_async_cb acb; - - memset(&acb, 0, sizeof(acb)); - - if (lp->lksb.sb_status == -DLM_ECANCEL) { - log_info("complete dlm cancel %x,%llx flags %lx", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, - lp->flags); - - lp->req = lp->cur; - acb.lc_ret |= LM_OUT_CANCELED; - if (lp->cur == DLM_LOCK_IV) - lp->lksb.sb_lkid = 0; - goto out; - } - - if (test_and_clear_bit(LFL_DLM_UNLOCK, &lp->flags)) { - if (lp->lksb.sb_status != -DLM_EUNLOCK) { - log_info("unlock sb_status %d %x,%llx flags %lx", - lp->lksb.sb_status, lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, - lp->flags); - return; - } - - lp->cur = DLM_LOCK_IV; - lp->req = DLM_LOCK_IV; - lp->lksb.sb_lkid = 0; - - if (test_and_clear_bit(LFL_UNLOCK_DELETE, &lp->flags)) { - gdlm_delete_lp(lp); - return; - } - goto out; - } - - if (lp->lksb.sb_flags & DLM_SBF_VALNOTVALID) - memset(lp->lksb.sb_lvbptr, 0, GDLM_LVB_SIZE); - - if (lp->lksb.sb_flags & DLM_SBF_ALTMODE) { - if (lp->req == DLM_LOCK_PR) - lp->req = DLM_LOCK_CW; - else if (lp->req == DLM_LOCK_CW) - lp->req = DLM_LOCK_PR; - } - - /* - * A canceled lock request. The lock was just taken off the delayed - * list and was never even submitted to dlm. - */ - - if (test_and_clear_bit(LFL_CANCEL, &lp->flags)) { - log_info("complete internal cancel %x,%llx", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number); - lp->req = lp->cur; - acb.lc_ret |= LM_OUT_CANCELED; - goto out; - } - - /* - * An error occured. - */ - - if (lp->lksb.sb_status) { - /* a "normal" error */ - if ((lp->lksb.sb_status == -EAGAIN) && - (lp->lkf & DLM_LKF_NOQUEUE)) { - lp->req = lp->cur; - if (lp->cur == DLM_LOCK_IV) - lp->lksb.sb_lkid = 0; - goto out; - } - - /* this could only happen with cancels I think */ - log_info("ast sb_status %d %x,%llx flags %lx", - lp->lksb.sb_status, lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, - lp->flags); - return; - } - - /* - * This is an AST for an EX->EX conversion for sync_lvb from GFS. - */ - - if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) { - wake_up_ast(lp); - return; - } - - /* - * A lock has been demoted to NL because it initially completed during - * BLOCK_LOCKS. Now it must be requested in the originally requested - * mode. - */ - - if (test_and_clear_bit(LFL_REREQUEST, &lp->flags)) { - gdlm_assert(lp->req == DLM_LOCK_NL, "%x,%llx", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number); - gdlm_assert(lp->prev_req > DLM_LOCK_NL, "%x,%llx", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number); - - lp->cur = DLM_LOCK_NL; - lp->req = lp->prev_req; - lp->prev_req = DLM_LOCK_IV; - lp->lkf &= ~DLM_LKF_CONVDEADLK; - - set_bit(LFL_NOCACHE, &lp->flags); - - if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) && - !test_bit(LFL_NOBLOCK, &lp->flags)) - gdlm_queue_delayed(lp); - else - queue_submit(lp); - return; - } - - /* - * A request is granted during dlm recovery. It may be granted - * because the locks of a failed node were cleared. In that case, - * there may be inconsistent data beneath this lock and we must wait - * for recovery to complete to use it. When gfs recovery is done this - * granted lock will be converted to NL and then reacquired in this - * granted state. - */ - - if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) && - !test_bit(LFL_NOBLOCK, &lp->flags) && - lp->req != DLM_LOCK_NL) { - - lp->cur = lp->req; - lp->prev_req = lp->req; - lp->req = DLM_LOCK_NL; - lp->lkf |= DLM_LKF_CONVERT; - lp->lkf &= ~DLM_LKF_CONVDEADLK; - - log_debug("rereq %x,%llx id %x %d,%d", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, - lp->lksb.sb_lkid, lp->cur, lp->req); - - set_bit(LFL_REREQUEST, &lp->flags); - queue_submit(lp); - return; - } - - /* - * DLM demoted the lock to NL before it was granted so GFS must be - * told it cannot cache data for this lock. - */ - - if (lp->lksb.sb_flags & DLM_SBF_DEMOTED) - set_bit(LFL_NOCACHE, &lp->flags); - -out: - /* - * This is an internal lock_dlm lock - */ - - if (test_bit(LFL_INLOCK, &lp->flags)) { - clear_bit(LFL_NOBLOCK, &lp->flags); - lp->cur = lp->req; - wake_up_ast(lp); - return; - } - - /* - * Normal completion of a lock request. Tell GFS it now has the lock. - */ - - clear_bit(LFL_NOBLOCK, &lp->flags); - lp->cur = lp->req; - - acb.lc_name = lp->lockname; - acb.lc_ret |= gdlm_make_lmstate(lp->cur); - - ls->fscb(ls->sdp, LM_CB_ASYNC, &acb); -} - -static void gdlm_ast(void *astarg) -{ - struct gdlm_lock *lp = astarg; - clear_bit(LFL_ACTIVE, &lp->flags); - process_complete(lp); -} - -static void process_blocking(struct gdlm_lock *lp, int bast_mode) -{ - struct gdlm_ls *ls = lp->ls; - unsigned int cb = 0; - - switch (gdlm_make_lmstate(bast_mode)) { - case LM_ST_EXCLUSIVE: - cb = LM_CB_NEED_E; - break; - case LM_ST_DEFERRED: - cb = LM_CB_NEED_D; - break; - case LM_ST_SHARED: - cb = LM_CB_NEED_S; - break; - default: - gdlm_assert(0, "unknown bast mode %u", bast_mode); - } - - ls->fscb(ls->sdp, cb, &lp->lockname); -} - - -static void gdlm_bast(void *astarg, int mode) -{ - struct gdlm_lock *lp = astarg; - - if (!mode) { - printk(KERN_INFO "lock_dlm: bast mode zero %x,%llx\n", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number); - return; - } - - process_blocking(lp, mode); -} - -/* convert gfs lock-state to dlm lock-mode */ - -static s16 make_mode(s16 lmstate) -{ - switch (lmstate) { - case LM_ST_UNLOCKED: - return DLM_LOCK_NL; - case LM_ST_EXCLUSIVE: - return DLM_LOCK_EX; - case LM_ST_DEFERRED: - return DLM_LOCK_CW; - case LM_ST_SHARED: - return DLM_LOCK_PR; - } - gdlm_assert(0, "unknown LM state %d", lmstate); - return -1; -} - - -/* verify agreement with GFS on the current lock state, NB: DLM_LOCK_NL and - DLM_LOCK_IV are both considered LM_ST_UNLOCKED by GFS. */ - -static void check_cur_state(struct gdlm_lock *lp, unsigned int cur_state) -{ - s16 cur = make_mode(cur_state); - if (lp->cur != DLM_LOCK_IV) - gdlm_assert(lp->cur == cur, "%d, %d", lp->cur, cur); -} - -static inline unsigned int make_flags(struct gdlm_lock *lp, - unsigned int gfs_flags, - s16 cur, s16 req) -{ - unsigned int lkf = 0; - - if (gfs_flags & LM_FLAG_TRY) - lkf |= DLM_LKF_NOQUEUE; - - if (gfs_flags & LM_FLAG_TRY_1CB) { - lkf |= DLM_LKF_NOQUEUE; - lkf |= DLM_LKF_NOQUEUEBAST; - } - - if (gfs_flags & LM_FLAG_PRIORITY) { - lkf |= DLM_LKF_NOORDER; - lkf |= DLM_LKF_HEADQUE; - } - - if (gfs_flags & LM_FLAG_ANY) { - if (req == DLM_LOCK_PR) - lkf |= DLM_LKF_ALTCW; - else if (req == DLM_LOCK_CW) - lkf |= DLM_LKF_ALTPR; - } - - if (lp->lksb.sb_lkid != 0) { - lkf |= DLM_LKF_CONVERT; - } - - if (lp->lvb) - lkf |= DLM_LKF_VALBLK; - - return lkf; -} - -/* make_strname - convert GFS lock numbers to a string */ - -static inline void make_strname(const struct lm_lockname *lockname, - struct gdlm_strname *str) -{ - sprintf(str->name, "%8x%16llx", lockname->ln_type, - (unsigned long long)lockname->ln_number); - str->namelen = GDLM_STRNAME_BYTES; -} - -static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name, - struct gdlm_lock **lpp) -{ - struct gdlm_lock *lp; - - lp = kzalloc(sizeof(struct gdlm_lock), GFP_NOFS); - if (!lp) - return -ENOMEM; - - lp->lockname = *name; - make_strname(name, &lp->strname); - lp->ls = ls; - lp->cur = DLM_LOCK_IV; - INIT_LIST_HEAD(&lp->delay_list); - - spin_lock(&ls->async_lock); - ls->all_locks_count++; - spin_unlock(&ls->async_lock); - - *lpp = lp; - return 0; -} - -int gdlm_get_lock(void *lockspace, struct lm_lockname *name, - void **lockp) -{ - struct gdlm_lock *lp; - int error; - - error = gdlm_create_lp(lockspace, name, &lp); - - *lockp = lp; - return error; -} - -void gdlm_put_lock(void *lock) -{ - gdlm_delete_lp(lock); -} - -unsigned int gdlm_do_lock(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - int error, bast = 1; - - /* - * When recovery is in progress, delay lock requests for submission - * once recovery is done. Requests for recovery (NOEXP) and unlocks - * can pass. - */ - - if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) && - !test_bit(LFL_NOBLOCK, &lp->flags) && lp->req != DLM_LOCK_NL) { - gdlm_queue_delayed(lp); - return LM_OUT_ASYNC; - } - - /* - * Submit the actual lock request. - */ - - if (test_bit(LFL_NOBAST, &lp->flags)) - bast = 0; - - set_bit(LFL_ACTIVE, &lp->flags); - - log_debug("lk %x,%llx id %x %d,%d %x", lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, lp->lksb.sb_lkid, - lp->cur, lp->req, lp->lkf); - - error = dlm_lock(ls->dlm_lockspace, lp->req, &lp->lksb, lp->lkf, - lp->strname.name, lp->strname.namelen, 0, gdlm_ast, - lp, bast ? gdlm_bast : NULL); - - if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) { - lp->lksb.sb_status = -EAGAIN; - gdlm_ast(lp); - error = 0; - } - - if (error) { - log_error("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x " - "flags=%lx", ls->fsname, lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, error, - lp->cur, lp->req, lp->lkf, lp->flags); - return LM_OUT_ERROR; - } - return LM_OUT_ASYNC; -} - -static unsigned int gdlm_do_unlock(struct gdlm_lock *lp) -{ - struct gdlm_ls *ls = lp->ls; - unsigned int lkf = 0; - int error; - - set_bit(LFL_DLM_UNLOCK, &lp->flags); - set_bit(LFL_ACTIVE, &lp->flags); - - if (lp->lvb) - lkf = DLM_LKF_VALBLK; - - log_debug("un %x,%llx %x %d %x", lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, - lp->lksb.sb_lkid, lp->cur, lkf); - - error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, lkf, NULL, lp); - - if (error) { - log_error("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x " - "flags=%lx", ls->fsname, lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, error, - lp->cur, lp->req, lp->lkf, lp->flags); - return LM_OUT_ERROR; - } - return LM_OUT_ASYNC; -} - -unsigned int gdlm_lock(void *lock, unsigned int cur_state, - unsigned int req_state, unsigned int flags) -{ - struct gdlm_lock *lp = lock; - - if (req_state == LM_ST_UNLOCKED) - return gdlm_unlock(lock, cur_state); - - if (req_state == LM_ST_UNLOCKED) - return gdlm_unlock(lock, cur_state); - - clear_bit(LFL_DLM_CANCEL, &lp->flags); - if (flags & LM_FLAG_NOEXP) - set_bit(LFL_NOBLOCK, &lp->flags); - - check_cur_state(lp, cur_state); - lp->req = make_mode(req_state); - lp->lkf = make_flags(lp, flags, lp->cur, lp->req); - - return gdlm_do_lock(lp); -} - -unsigned int gdlm_unlock(void *lock, unsigned int cur_state) -{ - struct gdlm_lock *lp = lock; - - clear_bit(LFL_DLM_CANCEL, &lp->flags); - if (lp->cur == DLM_LOCK_IV) - return 0; - return gdlm_do_unlock(lp); -} - -void gdlm_cancel(void *lock) -{ - struct gdlm_lock *lp = lock; - struct gdlm_ls *ls = lp->ls; - int error, delay_list = 0; - - if (test_bit(LFL_DLM_CANCEL, &lp->flags)) - return; - - log_info("gdlm_cancel %x,%llx flags %lx", lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, lp->flags); - - spin_lock(&ls->async_lock); - if (!list_empty(&lp->delay_list)) { - list_del_init(&lp->delay_list); - delay_list = 1; - } - spin_unlock(&ls->async_lock); - - if (delay_list) { - set_bit(LFL_CANCEL, &lp->flags); - set_bit(LFL_ACTIVE, &lp->flags); - gdlm_ast(lp); - return; - } - - if (!test_bit(LFL_ACTIVE, &lp->flags) || - test_bit(LFL_DLM_UNLOCK, &lp->flags)) { - log_info("gdlm_cancel skip %x,%llx flags %lx", - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, lp->flags); - return; - } - - /* the lock is blocked in the dlm */ - - set_bit(LFL_DLM_CANCEL, &lp->flags); - set_bit(LFL_ACTIVE, &lp->flags); - - error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, DLM_LKF_CANCEL, - NULL, lp); - - log_info("gdlm_cancel rv %d %x,%llx flags %lx", error, - lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number, lp->flags); - - if (error == -EBUSY) - clear_bit(LFL_DLM_CANCEL, &lp->flags); -} - -static int gdlm_add_lvb(struct gdlm_lock *lp) -{ - char *lvb; - - lvb = kzalloc(GDLM_LVB_SIZE, GFP_NOFS); - if (!lvb) - return -ENOMEM; - - lp->lksb.sb_lvbptr = lvb; - lp->lvb = lvb; - return 0; -} - -static void gdlm_del_lvb(struct gdlm_lock *lp) -{ - kfree(lp->lvb); - lp->lvb = NULL; - lp->lksb.sb_lvbptr = NULL; -} - -static int gdlm_ast_wait(void *word) -{ - schedule(); - return 0; -} - -/* This can do a synchronous dlm request (requiring a lock_dlm thread to get - the completion) because gfs won't call hold_lvb() during a callback (from - the context of a lock_dlm thread). */ - -static int hold_null_lock(struct gdlm_lock *lp) -{ - struct gdlm_lock *lpn = NULL; - int error; - - if (lp->hold_null) { - printk(KERN_INFO "lock_dlm: lvb already held\n"); - return 0; - } - - error = gdlm_create_lp(lp->ls, &lp->lockname, &lpn); - if (error) - goto out; - - lpn->lksb.sb_lvbptr = junk_lvb; - lpn->lvb = junk_lvb; - - lpn->req = DLM_LOCK_NL; - lpn->lkf = DLM_LKF_VALBLK | DLM_LKF_EXPEDITE; - set_bit(LFL_NOBAST, &lpn->flags); - set_bit(LFL_INLOCK, &lpn->flags); - set_bit(LFL_AST_WAIT, &lpn->flags); - - gdlm_do_lock(lpn); - wait_on_bit(&lpn->flags, LFL_AST_WAIT, gdlm_ast_wait, TASK_UNINTERRUPTIBLE); - error = lpn->lksb.sb_status; - if (error) { - printk(KERN_INFO "lock_dlm: hold_null_lock dlm error %d\n", - error); - gdlm_delete_lp(lpn); - lpn = NULL; - } -out: - lp->hold_null = lpn; - return error; -} - -/* This cannot do a synchronous dlm request (requiring a lock_dlm thread to get - the completion) because gfs may call unhold_lvb() during a callback (from - the context of a lock_dlm thread) which could cause a deadlock since the - other lock_dlm thread could be engaged in recovery. */ - -static void unhold_null_lock(struct gdlm_lock *lp) -{ - struct gdlm_lock *lpn = lp->hold_null; - - gdlm_assert(lpn, "%x,%llx", lp->lockname.ln_type, - (unsigned long long)lp->lockname.ln_number); - lpn->lksb.sb_lvbptr = NULL; - lpn->lvb = NULL; - set_bit(LFL_UNLOCK_DELETE, &lpn->flags); - gdlm_do_unlock(lpn); - lp->hold_null = NULL; -} - -/* Acquire a NL lock because gfs requires the value block to remain - intact on the resource while the lvb is "held" even if it's holding no locks - on the resource. */ - -int gdlm_hold_lvb(void *lock, char **lvbp) -{ - struct gdlm_lock *lp = lock; - int error; - - error = gdlm_add_lvb(lp); - if (error) - return error; - - *lvbp = lp->lvb; - - error = hold_null_lock(lp); - if (error) - gdlm_del_lvb(lp); - - return error; -} - -void gdlm_unhold_lvb(void *lock, char *lvb) -{ - struct gdlm_lock *lp = lock; - - unhold_null_lock(lp); - gdlm_del_lvb(lp); -} - -void gdlm_submit_delayed(struct gdlm_ls *ls) -{ - struct gdlm_lock *lp, *safe; - - spin_lock(&ls->async_lock); - list_for_each_entry_safe(lp, safe, &ls->delayed, delay_list) { - list_del_init(&lp->delay_list); - list_add_tail(&lp->delay_list, &ls->submit); - } - spin_unlock(&ls->async_lock); - wake_up(&ls->thread_wait); -} - diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h deleted file mode 100644 index 3c98e7c6f93..00000000000 --- a/fs/gfs2/locking/dlm/lock_dlm.h +++ /dev/null @@ -1,166 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef LOCK_DLM_DOT_H -#define LOCK_DLM_DOT_H - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/list.h> -#include <linux/socket.h> -#include <linux/delay.h> -#include <linux/kthread.h> -#include <linux/kobject.h> -#include <linux/fcntl.h> -#include <linux/wait.h> -#include <net/sock.h> - -#include <linux/dlm.h> -#include <linux/dlm_plock.h> -#include <linux/lm_interface.h> - -/* - * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a - * prefix of lock_dlm_ gets awkward. Externally, GFS refers to this module - * as "lock_dlm". - */ - -#define GDLM_STRNAME_BYTES 24 -#define GDLM_LVB_SIZE 32 -#define GDLM_DROP_COUNT 0 -#define GDLM_DROP_PERIOD 60 -#define GDLM_NAME_LEN 128 - -/* GFS uses 12 bytes to identify a resource (32 bit type + 64 bit number). - We sprintf these numbers into a 24 byte string of hex values to make them - human-readable (to make debugging simpler.) */ - -struct gdlm_strname { - unsigned char name[GDLM_STRNAME_BYTES]; - unsigned short namelen; -}; - -enum { - DFL_BLOCK_LOCKS = 0, - DFL_SPECTATOR = 1, - DFL_WITHDRAW = 2, -}; - -struct gdlm_ls { - u32 id; - int jid; - int first; - int first_done; - unsigned long flags; - struct kobject kobj; - char clustername[GDLM_NAME_LEN]; - char fsname[GDLM_NAME_LEN]; - int fsflags; - dlm_lockspace_t *dlm_lockspace; - lm_callback_t fscb; - struct gfs2_sbd *sdp; - int recover_jid; - int recover_jid_done; - int recover_jid_status; - spinlock_t async_lock; - struct list_head delayed; - struct list_head submit; - u32 all_locks_count; - wait_queue_head_t wait_control; - struct task_struct *thread; - wait_queue_head_t thread_wait; -}; - -enum { - LFL_NOBLOCK = 0, - LFL_NOCACHE = 1, - LFL_DLM_UNLOCK = 2, - LFL_DLM_CANCEL = 3, - LFL_SYNC_LVB = 4, - LFL_FORCE_PROMOTE = 5, - LFL_REREQUEST = 6, - LFL_ACTIVE = 7, - LFL_INLOCK = 8, - LFL_CANCEL = 9, - LFL_NOBAST = 10, - LFL_HEADQUE = 11, - LFL_UNLOCK_DELETE = 12, - LFL_AST_WAIT = 13, -}; - -struct gdlm_lock { - struct gdlm_ls *ls; - struct lm_lockname lockname; - struct gdlm_strname strname; - char *lvb; - struct dlm_lksb lksb; - - s16 cur; - s16 req; - s16 prev_req; - u32 lkf; /* dlm flags DLM_LKF_ */ - unsigned long flags; /* lock_dlm flags LFL_ */ - - struct list_head delay_list; /* delayed */ - struct gdlm_lock *hold_null; /* NL lock for hold_lvb */ -}; - -#define gdlm_assert(assertion, fmt, args...) \ -do { \ - if (unlikely(!(assertion))) { \ - printk(KERN_EMERG "lock_dlm: fatal assertion failed \"%s\"\n" \ - "lock_dlm: " fmt "\n", \ - #assertion, ##args); \ - BUG(); \ - } \ -} while (0) - -#define log_print(lev, fmt, arg...) printk(lev "lock_dlm: " fmt "\n" , ## arg) -#define log_info(fmt, arg...) log_print(KERN_INFO , fmt , ## arg) -#define log_error(fmt, arg...) log_print(KERN_ERR , fmt , ## arg) -#ifdef LOCK_DLM_LOG_DEBUG -#define log_debug(fmt, arg...) log_print(KERN_DEBUG , fmt , ## arg) -#else -#define log_debug(fmt, arg...) -#endif - -/* sysfs.c */ - -int gdlm_sysfs_init(void); -void gdlm_sysfs_exit(void); -int gdlm_kobject_setup(struct gdlm_ls *, struct kobject *); -void gdlm_kobject_release(struct gdlm_ls *); - -/* thread.c */ - -int gdlm_init_threads(struct gdlm_ls *); -void gdlm_release_threads(struct gdlm_ls *); - -/* lock.c */ - -void gdlm_submit_delayed(struct gdlm_ls *); -unsigned int gdlm_do_lock(struct gdlm_lock *); - -int gdlm_get_lock(void *, struct lm_lockname *, void **); -void gdlm_put_lock(void *); -unsigned int gdlm_lock(void *, unsigned int, unsigned int, unsigned int); -unsigned int gdlm_unlock(void *, unsigned int); -void gdlm_cancel(void *); -int gdlm_hold_lvb(void *, char **); -void gdlm_unhold_lvb(void *, char *); - -/* mount.c */ - -extern const struct lm_lockops gdlm_ops; - -#endif - diff --git a/fs/gfs2/locking/dlm/main.c b/fs/gfs2/locking/dlm/main.c deleted file mode 100644 index b9a03a7ff80..00000000000 --- a/fs/gfs2/locking/dlm/main.c +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/init.h> - -#include "lock_dlm.h" - -static int __init init_lock_dlm(void) -{ - int error; - - error = gfs2_register_lockproto(&gdlm_ops); - if (error) { - printk(KERN_WARNING "lock_dlm: can't register protocol: %d\n", - error); - return error; - } - - error = gdlm_sysfs_init(); - if (error) { - gfs2_unregister_lockproto(&gdlm_ops); - return error; - } - - printk(KERN_INFO - "Lock_DLM (built %s %s) installed\n", __DATE__, __TIME__); - return 0; -} - -static void __exit exit_lock_dlm(void) -{ - gdlm_sysfs_exit(); - gfs2_unregister_lockproto(&gdlm_ops); -} - -module_init(init_lock_dlm); -module_exit(exit_lock_dlm); - -MODULE_DESCRIPTION("GFS DLM Locking Module"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c deleted file mode 100644 index 1aa7eb6a022..00000000000 --- a/fs/gfs2/locking/dlm/mount.c +++ /dev/null @@ -1,276 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include "lock_dlm.h" - -const struct lm_lockops gdlm_ops; - - -static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp, - int flags, char *table_name) -{ - struct gdlm_ls *ls; - char buf[256], *p; - - ls = kzalloc(sizeof(struct gdlm_ls), GFP_KERNEL); - if (!ls) - return NULL; - - ls->fscb = cb; - ls->sdp = sdp; - ls->fsflags = flags; - spin_lock_init(&ls->async_lock); - INIT_LIST_HEAD(&ls->delayed); - INIT_LIST_HEAD(&ls->submit); - init_waitqueue_head(&ls->thread_wait); - init_waitqueue_head(&ls->wait_control); - ls->jid = -1; - - strncpy(buf, table_name, 256); - buf[255] = '\0'; - - p = strchr(buf, ':'); - if (!p) { - log_info("invalid table_name \"%s\"", table_name); - kfree(ls); - return NULL; - } - *p = '\0'; - p++; - - strncpy(ls->clustername, buf, GDLM_NAME_LEN); - strncpy(ls->fsname, p, GDLM_NAME_LEN); - - return ls; -} - -static int make_args(struct gdlm_ls *ls, char *data_arg, int *nodir) -{ - char data[256]; - char *options, *x, *y; - int error = 0; - - memset(data, 0, 256); - strncpy(data, data_arg, 255); - - if (!strlen(data)) { - log_error("no mount options, (u)mount helpers not installed"); - return -EINVAL; - } - - for (options = data; (x = strsep(&options, ":")); ) { - if (!*x) - continue; - - y = strchr(x, '='); - if (y) - *y++ = 0; - - if (!strcmp(x, "jid")) { - if (!y) { - log_error("need argument to jid"); - error = -EINVAL; - break; - } - sscanf(y, "%u", &ls->jid); - - } else if (!strcmp(x, "first")) { - if (!y) { - log_error("need argument to first"); - error = -EINVAL; - break; - } - sscanf(y, "%u", &ls->first); - - } else if (!strcmp(x, "id")) { - if (!y) { - log_error("need argument to id"); - error = -EINVAL; - break; - } - sscanf(y, "%u", &ls->id); - - } else if (!strcmp(x, "nodir")) { - if (!y) { - log_error("need argument to nodir"); - error = -EINVAL; - break; - } - sscanf(y, "%u", nodir); - - } else { - log_error("unkonwn option: %s", x); - error = -EINVAL; - break; - } - } - - return error; -} - -static int gdlm_mount(char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj) -{ - struct gdlm_ls *ls; - int error = -ENOMEM, nodir = 0; - - if (min_lvb_size > GDLM_LVB_SIZE) - goto out; - - ls = init_gdlm(cb, cb_data, flags, table_name); - if (!ls) - goto out; - - error = make_args(ls, host_data, &nodir); - if (error) - goto out; - - error = gdlm_init_threads(ls); - if (error) - goto out_free; - - error = gdlm_kobject_setup(ls, fskobj); - if (error) - goto out_thread; - - error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname), - &ls->dlm_lockspace, - DLM_LSFL_FS | DLM_LSFL_NEWEXCL | - (nodir ? DLM_LSFL_NODIR : 0), - GDLM_LVB_SIZE); - if (error) { - log_error("dlm_new_lockspace error %d", error); - goto out_kobj; - } - - lockstruct->ls_jid = ls->jid; - lockstruct->ls_first = ls->first; - lockstruct->ls_lockspace = ls; - lockstruct->ls_ops = &gdlm_ops; - lockstruct->ls_flags = 0; - lockstruct->ls_lvb_size = GDLM_LVB_SIZE; - return 0; - -out_kobj: - gdlm_kobject_release(ls); -out_thread: - gdlm_release_threads(ls); -out_free: - kfree(ls); -out: - return error; -} - -static void gdlm_unmount(void *lockspace) -{ - struct gdlm_ls *ls = lockspace; - - log_debug("unmount flags %lx", ls->flags); - - /* FIXME: serialize unmount and withdraw in case they - happen at once. Also, if unmount follows withdraw, - wait for withdraw to finish. */ - - if (test_bit(DFL_WITHDRAW, &ls->flags)) - goto out; - - gdlm_kobject_release(ls); - dlm_release_lockspace(ls->dlm_lockspace, 2); - gdlm_release_threads(ls); - BUG_ON(ls->all_locks_count); -out: - kfree(ls); -} - -static void gdlm_recovery_done(void *lockspace, unsigned int jid, - unsigned int message) -{ - char env_jid[20]; - char env_status[20]; - char *envp[] = { env_jid, env_status, NULL }; - struct gdlm_ls *ls = lockspace; - ls->recover_jid_done = jid; - ls->recover_jid_status = message; - sprintf(env_jid, "JID=%d", jid); - sprintf(env_status, "RECOVERY=%s", - message == LM_RD_SUCCESS ? "Done" : "Failed"); - kobject_uevent_env(&ls->kobj, KOBJ_CHANGE, envp); -} - -static void gdlm_others_may_mount(void *lockspace) -{ - char *message = "FIRSTMOUNT=Done"; - char *envp[] = { message, NULL }; - struct gdlm_ls *ls = lockspace; - ls->first_done = 1; - kobject_uevent_env(&ls->kobj, KOBJ_CHANGE, envp); -} - -/* Userspace gets the offline uevent, blocks new gfs locks on - other mounters, and lets us know (sets WITHDRAW flag). Then, - userspace leaves the mount group while we leave the lockspace. */ - -static void gdlm_withdraw(void *lockspace) -{ - struct gdlm_ls *ls = lockspace; - - kobject_uevent(&ls->kobj, KOBJ_OFFLINE); - - wait_event_interruptible(ls->wait_control, - test_bit(DFL_WITHDRAW, &ls->flags)); - - dlm_release_lockspace(ls->dlm_lockspace, 2); - gdlm_release_threads(ls); - gdlm_kobject_release(ls); -} - -static int gdlm_plock(void *lockspace, struct lm_lockname *name, - struct file *file, int cmd, struct file_lock *fl) -{ - struct gdlm_ls *ls = lockspace; - return dlm_posix_lock(ls->dlm_lockspace, name->ln_number, file, cmd, fl); -} - -static int gdlm_punlock(void *lockspace, struct lm_lockname *name, - struct file *file, struct file_lock *fl) -{ - struct gdlm_ls *ls = lockspace; - return dlm_posix_unlock(ls->dlm_lockspace, name->ln_number, file, fl); -} - -static int gdlm_plock_get(void *lockspace, struct lm_lockname *name, - struct file *file, struct file_lock *fl) -{ - struct gdlm_ls *ls = lockspace; - return dlm_posix_get(ls->dlm_lockspace, name->ln_number, file, fl); -} - -const struct lm_lockops gdlm_ops = { - .lm_proto_name = "lock_dlm", - .lm_mount = gdlm_mount, - .lm_others_may_mount = gdlm_others_may_mount, - .lm_unmount = gdlm_unmount, - .lm_withdraw = gdlm_withdraw, - .lm_get_lock = gdlm_get_lock, - .lm_put_lock = gdlm_put_lock, - .lm_lock = gdlm_lock, - .lm_unlock = gdlm_unlock, - .lm_plock = gdlm_plock, - .lm_punlock = gdlm_punlock, - .lm_plock_get = gdlm_plock_get, - .lm_cancel = gdlm_cancel, - .lm_hold_lvb = gdlm_hold_lvb, - .lm_unhold_lvb = gdlm_unhold_lvb, - .lm_recovery_done = gdlm_recovery_done, - .lm_owner = THIS_MODULE, -}; - diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c deleted file mode 100644 index 9b7edcf7bd4..00000000000 --- a/fs/gfs2/locking/dlm/sysfs.c +++ /dev/null @@ -1,226 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/ctype.h> -#include <linux/stat.h> - -#include "lock_dlm.h" - -static ssize_t proto_name_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%s\n", gdlm_ops.lm_proto_name); -} - -static ssize_t block_show(struct gdlm_ls *ls, char *buf) -{ - ssize_t ret; - int val = 0; - - if (test_bit(DFL_BLOCK_LOCKS, &ls->flags)) - val = 1; - ret = sprintf(buf, "%d\n", val); - return ret; -} - -static ssize_t block_store(struct gdlm_ls *ls, const char *buf, size_t len) -{ - ssize_t ret = len; - int val; - - val = simple_strtol(buf, NULL, 0); - - if (val == 1) - set_bit(DFL_BLOCK_LOCKS, &ls->flags); - else if (val == 0) { - clear_bit(DFL_BLOCK_LOCKS, &ls->flags); - gdlm_submit_delayed(ls); - } else { - ret = -EINVAL; - } - return ret; -} - -static ssize_t withdraw_show(struct gdlm_ls *ls, char *buf) -{ - ssize_t ret; - int val = 0; - - if (test_bit(DFL_WITHDRAW, &ls->flags)) - val = 1; - ret = sprintf(buf, "%d\n", val); - return ret; -} - -static ssize_t withdraw_store(struct gdlm_ls *ls, const char *buf, size_t len) -{ - ssize_t ret = len; - int val; - - val = simple_strtol(buf, NULL, 0); - - if (val == 1) - set_bit(DFL_WITHDRAW, &ls->flags); - else - ret = -EINVAL; - wake_up(&ls->wait_control); - return ret; -} - -static ssize_t id_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%u\n", ls->id); -} - -static ssize_t jid_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->jid); -} - -static ssize_t first_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->first); -} - -static ssize_t first_done_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->first_done); -} - -static ssize_t recover_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->recover_jid); -} - -static ssize_t recover_store(struct gdlm_ls *ls, const char *buf, size_t len) -{ - ls->recover_jid = simple_strtol(buf, NULL, 0); - ls->fscb(ls->sdp, LM_CB_NEED_RECOVERY, &ls->recover_jid); - return len; -} - -static ssize_t recover_done_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->recover_jid_done); -} - -static ssize_t recover_status_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->recover_jid_status); -} - -struct gdlm_attr { - struct attribute attr; - ssize_t (*show)(struct gdlm_ls *, char *); - ssize_t (*store)(struct gdlm_ls *, const char *, size_t); -}; - -#define GDLM_ATTR(_name,_mode,_show,_store) \ -static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) - -GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); -GDLM_ATTR(block, 0644, block_show, block_store); -GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); -GDLM_ATTR(id, 0444, id_show, NULL); -GDLM_ATTR(jid, 0444, jid_show, NULL); -GDLM_ATTR(first, 0444, first_show, NULL); -GDLM_ATTR(first_done, 0444, first_done_show, NULL); -GDLM_ATTR(recover, 0644, recover_show, recover_store); -GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); -GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); - -static struct attribute *gdlm_attrs[] = { - &gdlm_attr_proto_name.attr, - &gdlm_attr_block.attr, - &gdlm_attr_withdraw.attr, - &gdlm_attr_id.attr, - &gdlm_attr_jid.attr, - &gdlm_attr_first.attr, - &gdlm_attr_first_done.attr, - &gdlm_attr_recover.attr, - &gdlm_attr_recover_done.attr, - &gdlm_attr_recover_status.attr, - NULL, -}; - -static ssize_t gdlm_attr_show(struct kobject *kobj, struct attribute *attr, - char *buf) -{ - struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj); - struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr); - return a->show ? a->show(ls, buf) : 0; -} - -static ssize_t gdlm_attr_store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t len) -{ - struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj); - struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr); - return a->store ? a->store(ls, buf, len) : len; -} - -static struct sysfs_ops gdlm_attr_ops = { - .show = gdlm_attr_show, - .store = gdlm_attr_store, -}; - -static struct kobj_type gdlm_ktype = { - .default_attrs = gdlm_attrs, - .sysfs_ops = &gdlm_attr_ops, -}; - -static struct kset *gdlm_kset; - -int gdlm_kobject_setup(struct gdlm_ls *ls, struct kobject *fskobj) -{ - int error; - - ls->kobj.kset = gdlm_kset; - error = kobject_init_and_add(&ls->kobj, &gdlm_ktype, fskobj, - "lock_module"); - if (error) - log_error("can't register kobj %d", error); - kobject_uevent(&ls->kobj, KOBJ_ADD); - - return error; -} - -void gdlm_kobject_release(struct gdlm_ls *ls) -{ - kobject_put(&ls->kobj); -} - -static int gdlm_uevent(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env) -{ - struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj); - add_uevent_var(env, "LOCKTABLE=%s:%s", ls->clustername, ls->fsname); - add_uevent_var(env, "LOCKPROTO=lock_dlm"); - return 0; -} - -static struct kset_uevent_ops gdlm_uevent_ops = { - .uevent = gdlm_uevent, -}; - - -int gdlm_sysfs_init(void) -{ - gdlm_kset = kset_create_and_add("lock_dlm", &gdlm_uevent_ops, kernel_kobj); - if (!gdlm_kset) { - printk(KERN_WARNING "%s: can not create kset\n", __func__); - return -ENOMEM; - } - return 0; -} - -void gdlm_sysfs_exit(void) -{ - kset_unregister(gdlm_kset); -} - diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c deleted file mode 100644 index 38823efd698..00000000000 --- a/fs/gfs2/locking/dlm/thread.c +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include "lock_dlm.h" - -static inline int no_work(struct gdlm_ls *ls) -{ - int ret; - - spin_lock(&ls->async_lock); - ret = list_empty(&ls->submit); - spin_unlock(&ls->async_lock); - - return ret; -} - -static int gdlm_thread(void *data) -{ - struct gdlm_ls *ls = (struct gdlm_ls *) data; - struct gdlm_lock *lp = NULL; - - while (!kthread_should_stop()) { - wait_event_interruptible(ls->thread_wait, - !no_work(ls) || kthread_should_stop()); - - spin_lock(&ls->async_lock); - - if (!list_empty(&ls->submit)) { - lp = list_entry(ls->submit.next, struct gdlm_lock, - delay_list); - list_del_init(&lp->delay_list); - spin_unlock(&ls->async_lock); - gdlm_do_lock(lp); - spin_lock(&ls->async_lock); - } - spin_unlock(&ls->async_lock); - } - - return 0; -} - -int gdlm_init_threads(struct gdlm_ls *ls) -{ - struct task_struct *p; - int error; - - p = kthread_run(gdlm_thread, ls, "lock_dlm"); - error = IS_ERR(p); - if (error) { - log_error("can't start lock_dlm thread %d", error); - return error; - } - ls->thread = p; - - return 0; -} - -void gdlm_release_threads(struct gdlm_ls *ls) -{ - kthread_stop(ls->thread); -} - diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index ad305854bdc..98918a75641 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -14,7 +14,6 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 4390f6f4047..80e4f5f898b 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -13,7 +13,6 @@ #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 7cacfde3219..a6892ed0840 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <asm/atomic.h> #include "gfs2.h" @@ -23,6 +22,12 @@ #include "sys.h" #include "util.h" #include "glock.h" +#include "quota.h" + +static struct shrinker qd_shrinker = { + .shrink = gfs2_shrink_qd_memory, + .seeks = DEFAULT_SEEKS, +}; static void gfs2_init_inode_once(void *foo) { @@ -41,8 +46,6 @@ static void gfs2_init_glock_once(void *foo) INIT_HLIST_NODE(&gl->gl_list); spin_lock_init(&gl->gl_spin); INIT_LIST_HEAD(&gl->gl_holders); - gl->gl_lvb = NULL; - atomic_set(&gl->gl_lvb_count, 0); INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); atomic_set(&gl->gl_ail_count, 0); @@ -100,6 +103,8 @@ static int __init init_gfs2_fs(void) if (!gfs2_quotad_cachep) goto fail; + register_shrinker(&qd_shrinker); + error = register_filesystem(&gfs2_fs_type); if (error) goto fail; @@ -117,6 +122,7 @@ static int __init init_gfs2_fs(void) fail_unregister: unregister_filesystem(&gfs2_fs_type); fail: + unregister_shrinker(&qd_shrinker); gfs2_glock_exit(); if (gfs2_quotad_cachep) @@ -145,6 +151,7 @@ fail: static void __exit exit_gfs2_fs(void) { + unregister_shrinker(&qd_shrinker); gfs2_glock_exit(); gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 09853620c95..8d6f13256b2 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -19,7 +19,6 @@ #include <linux/delay.h> #include <linux/bio.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" @@ -90,27 +89,6 @@ void gfs2_aspace_put(struct inode *aspace) } /** - * gfs2_meta_inval - Invalidate all buffers associated with a glock - * @gl: the glock - * - */ - -void gfs2_meta_inval(struct gfs2_glock *gl) -{ - struct gfs2_sbd *sdp = gl->gl_sbd; - struct inode *aspace = gl->gl_aspace; - struct address_space *mapping = gl->gl_aspace->i_mapping; - - gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); - - atomic_inc(&aspace->i_writecount); - truncate_inode_pages(mapping, 0); - atomic_dec(&aspace->i_writecount); - - gfs2_assert_withdraw(sdp, !mapping->nrpages); -} - -/** * gfs2_meta_sync - Sync all buffers associated with a glock * @gl: The glock * diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index b1a5f3674d4..de270c2f9b6 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -40,7 +40,6 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp); void gfs2_aspace_put(struct inode *aspace); -void gfs2_meta_inval(struct gfs2_glock *gl); void gfs2_meta_sync(struct gfs2_glock *gl); struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c index 3cb0a44ba02..f7e8527a21e 100644 --- a/fs/gfs2/mount.c +++ b/fs/gfs2/mount.c @@ -12,12 +12,11 @@ #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <linux/parser.h> #include "gfs2.h" #include "incore.h" -#include "mount.h" +#include "super.h" #include "sys.h" #include "util.h" @@ -37,11 +36,15 @@ enum { Opt_quota_off, Opt_quota_account, Opt_quota_on, + Opt_quota, + Opt_noquota, Opt_suiddir, Opt_nosuiddir, Opt_data_writeback, Opt_data_ordered, Opt_meta, + Opt_discard, + Opt_nodiscard, Opt_err, }; @@ -61,11 +64,15 @@ static const match_table_t tokens = { {Opt_quota_off, "quota=off"}, {Opt_quota_account, "quota=account"}, {Opt_quota_on, "quota=on"}, + {Opt_quota, "quota"}, + {Opt_noquota, "noquota"}, {Opt_suiddir, "suiddir"}, {Opt_nosuiddir, "nosuiddir"}, {Opt_data_writeback, "data=writeback"}, {Opt_data_ordered, "data=ordered"}, {Opt_meta, "meta"}, + {Opt_discard, "discard"}, + {Opt_nodiscard, "nodiscard"}, {Opt_err, NULL} }; @@ -77,101 +84,46 @@ static const match_table_t tokens = { * Return: errno */ -int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount) +int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) { - struct gfs2_args *args = &sdp->sd_args; - char *data = data_arg; - char *options, *o, *v; - int error = 0; - - if (!remount) { - /* Set some defaults */ - args->ar_quota = GFS2_QUOTA_DEFAULT; - args->ar_data = GFS2_DATA_DEFAULT; - } + char *o; + int token; + substring_t tmp[MAX_OPT_ARGS]; /* Split the options into tokens with the "," character and process them */ - for (options = data; (o = strsep(&options, ",")); ) { - int token; - substring_t tmp[MAX_OPT_ARGS]; - - if (!*o) + while (1) { + o = strsep(&options, ","); + if (o == NULL) + break; + if (*o == '\0') continue; token = match_token(o, tokens, tmp); switch (token) { case Opt_lockproto: - v = match_strdup(&tmp[0]); - if (!v) { - fs_info(sdp, "no memory for lockproto\n"); - error = -ENOMEM; - goto out_error; - } - - if (remount && strcmp(v, args->ar_lockproto)) { - kfree(v); - goto cant_remount; - } - - strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN); - args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0; - kfree(v); + match_strlcpy(args->ar_lockproto, &tmp[0], + GFS2_LOCKNAME_LEN); break; case Opt_locktable: - v = match_strdup(&tmp[0]); - if (!v) { - fs_info(sdp, "no memory for locktable\n"); - error = -ENOMEM; - goto out_error; - } - - if (remount && strcmp(v, args->ar_locktable)) { - kfree(v); - goto cant_remount; - } - - strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN); - args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0; - kfree(v); + match_strlcpy(args->ar_locktable, &tmp[0], + GFS2_LOCKNAME_LEN); break; case Opt_hostdata: - v = match_strdup(&tmp[0]); - if (!v) { - fs_info(sdp, "no memory for hostdata\n"); - error = -ENOMEM; - goto out_error; - } - - if (remount && strcmp(v, args->ar_hostdata)) { - kfree(v); - goto cant_remount; - } - - strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN); - args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0; - kfree(v); + match_strlcpy(args->ar_hostdata, &tmp[0], + GFS2_LOCKNAME_LEN); break; case Opt_spectator: - if (remount && !args->ar_spectator) - goto cant_remount; args->ar_spectator = 1; - sdp->sd_vfs->s_flags |= MS_RDONLY; break; case Opt_ignore_local_fs: - if (remount && !args->ar_ignore_local_fs) - goto cant_remount; args->ar_ignore_local_fs = 1; break; case Opt_localflocks: - if (remount && !args->ar_localflocks) - goto cant_remount; args->ar_localflocks = 1; break; case Opt_localcaching: - if (remount && !args->ar_localcaching) - goto cant_remount; args->ar_localcaching = 1; break; case Opt_debug: @@ -181,25 +133,23 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount) args->ar_debug = 0; break; case Opt_upgrade: - if (remount && !args->ar_upgrade) - goto cant_remount; args->ar_upgrade = 1; break; case Opt_acl: args->ar_posix_acl = 1; - sdp->sd_vfs->s_flags |= MS_POSIXACL; break; case Opt_noacl: args->ar_posix_acl = 0; - sdp->sd_vfs->s_flags &= ~MS_POSIXACL; break; case Opt_quota_off: + case Opt_noquota: args->ar_quota = GFS2_QUOTA_OFF; break; case Opt_quota_account: args->ar_quota = GFS2_QUOTA_ACCOUNT; break; case Opt_quota_on: + case Opt_quota: args->ar_quota = GFS2_QUOTA_ON; break; case Opt_suiddir: @@ -215,29 +165,21 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount) args->ar_data = GFS2_DATA_ORDERED; break; case Opt_meta: - if (remount && args->ar_meta != 1) - goto cant_remount; args->ar_meta = 1; break; + case Opt_discard: + args->ar_discard = 1; + break; + case Opt_nodiscard: + args->ar_discard = 0; + break; case Opt_err: default: - fs_info(sdp, "unknown option: %s\n", o); - error = -EINVAL; - goto out_error; + fs_info(sdp, "invalid mount option: %s\n", o); + return -EINVAL; } } -out_error: - if (error) - fs_info(sdp, "invalid mount option(s)\n"); - - if (data != data_arg) - kfree(data); - - return error; - -cant_remount: - fs_info(sdp, "can't remount with option %s\n", o); - return -EINVAL; + return 0; } diff --git a/fs/gfs2/mount.h b/fs/gfs2/mount.h deleted file mode 100644 index 401288acfdf..00000000000 --- a/fs/gfs2/mount.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __MOUNT_DOT_H__ -#define __MOUNT_DOT_H__ - -struct gfs2_sbd; - -int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount); - -#endif /* __MOUNT_DOT_H__ */ diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 4ddab67867e..a6dde1751e1 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -19,7 +19,6 @@ #include <linux/writeback.h> #include <linux/swap.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <linux/backing-dev.h> #include "gfs2.h" @@ -442,6 +441,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) */ if (unlikely(page->index)) { zero_user(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); return 0; } @@ -1096,6 +1096,7 @@ static const struct address_space_operations gfs2_writeback_aops = { .releasepage = gfs2_releasepage, .direct_IO = gfs2_direct_IO, .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations gfs2_ordered_aops = { @@ -1111,6 +1112,7 @@ static const struct address_space_operations gfs2_ordered_aops = { .releasepage = gfs2_releasepage, .direct_IO = gfs2_direct_IO, .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations gfs2_jdata_aops = { @@ -1125,6 +1127,7 @@ static const struct address_space_operations gfs2_jdata_aops = { .bmap = gfs2_bmap, .invalidatepage = gfs2_invalidatepage, .releasepage = gfs2_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, }; void gfs2_set_aops(struct inode *inode) diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/ops_dentry.c index c2ad36330ca..5eb57b04438 100644 --- a/fs/gfs2/ops_dentry.c +++ b/fs/gfs2/ops_dentry.c @@ -13,7 +13,6 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index 7fdeb14ddd1..9200ef22171 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -14,7 +14,6 @@ #include <linux/exportfs.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c index 93fe41b67f9..3b9e8de3500 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/ops_file.c @@ -20,9 +20,10 @@ #include <linux/gfs2_ondisk.h> #include <linux/ext2_fs.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/writeback.h> #include <asm/uaccess.h> +#include <linux/dlm.h> +#include <linux/dlm_plock.h> #include "gfs2.h" #include "incore.h" @@ -354,7 +355,9 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page) if (ret) goto out; + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); set_bit(GIF_SW_PAGED, &ip->i_flags); + ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required); if (ret || !alloc_required) goto out_unlock; @@ -560,57 +563,24 @@ static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync) return ret; } +#ifdef CONFIG_GFS2_FS_LOCKING_DLM + /** * gfs2_setlease - acquire/release a file lease * @file: the file pointer * @arg: lease type * @fl: file lock * + * We don't currently have a way to enforce a lease across the whole + * cluster; until we do, disable leases (by just returning -EINVAL), + * unless the administrator has requested purely local locking. + * * Returns: errno */ static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl) { - struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host); - - /* - * We don't currently have a way to enforce a lease across the whole - * cluster; until we do, disable leases (by just returning -EINVAL), - * unless the administrator has requested purely local locking. - */ - if (!sdp->sd_args.ar_localflocks) - return -EINVAL; - return generic_setlease(file, arg, fl); -} - -static int gfs2_lm_plock_get(struct gfs2_sbd *sdp, struct lm_lockname *name, - struct file *file, struct file_lock *fl) -{ - int error = -EIO; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = sdp->sd_lockstruct.ls_ops->lm_plock_get( - sdp->sd_lockstruct.ls_lockspace, name, file, fl); - return error; -} - -static int gfs2_lm_plock(struct gfs2_sbd *sdp, struct lm_lockname *name, - struct file *file, int cmd, struct file_lock *fl) -{ - int error = -EIO; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = sdp->sd_lockstruct.ls_ops->lm_plock( - sdp->sd_lockstruct.ls_lockspace, name, file, cmd, fl); - return error; -} - -static int gfs2_lm_punlock(struct gfs2_sbd *sdp, struct lm_lockname *name, - struct file *file, struct file_lock *fl) -{ - int error = -EIO; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = sdp->sd_lockstruct.ls_ops->lm_punlock( - sdp->sd_lockstruct.ls_lockspace, name, file, fl); - return error; + return -EINVAL; } /** @@ -626,9 +596,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) { struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host); - struct lm_lockname name = - { .ln_number = ip->i_no_addr, - .ln_type = LM_TYPE_PLOCK }; + struct lm_lockstruct *ls = &sdp->sd_lockstruct; if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; @@ -640,12 +608,14 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) cmd = F_SETLK; fl->fl_type = F_UNLCK; } + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + return -EIO; if (IS_GETLK(cmd)) - return gfs2_lm_plock_get(sdp, &name, file, fl); + return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl); else if (fl->fl_type == F_UNLCK) - return gfs2_lm_punlock(sdp, &name, file, fl); + return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl); else - return gfs2_lm_plock(sdp, &name, file, cmd, fl); + return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl); } static int do_flock(struct file *file, int cmd, struct file_lock *fl) @@ -732,7 +702,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) } } -const struct file_operations gfs2_file_fops = { +const struct file_operations *gfs2_file_fops = &(const struct file_operations){ .llseek = gfs2_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, @@ -750,7 +720,7 @@ const struct file_operations gfs2_file_fops = { .setlease = gfs2_setlease, }; -const struct file_operations gfs2_dir_fops = { +const struct file_operations *gfs2_dir_fops = &(const struct file_operations){ .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, @@ -760,7 +730,9 @@ const struct file_operations gfs2_dir_fops = { .flock = gfs2_flock, }; -const struct file_operations gfs2_file_fops_nolock = { +#endif /* CONFIG_GFS2_FS_LOCKING_DLM */ + +const struct file_operations *gfs2_file_fops_nolock = &(const struct file_operations){ .llseek = gfs2_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, @@ -773,10 +745,10 @@ const struct file_operations gfs2_file_fops_nolock = { .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, - .setlease = gfs2_setlease, + .setlease = generic_setlease, }; -const struct file_operations gfs2_dir_fops_nolock = { +const struct file_operations *gfs2_dir_fops_nolock = &(const struct file_operations){ .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index f91eebdde58..51883b3ad89 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -17,7 +17,6 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" @@ -25,7 +24,6 @@ #include "glock.h" #include "glops.h" #include "inode.h" -#include "mount.h" #include "recovery.h" #include "rgrp.h" #include "super.h" @@ -64,7 +62,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_quota_warn_period = 10; gt->gt_quota_scale_num = 1; gt->gt_quota_scale_den = 1; - gt->gt_quota_cache_secs = 300; gt->gt_quota_quantum = 60; gt->gt_new_files_jdata = 0; gt->gt_max_readahead = 1 << 18; @@ -100,7 +97,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mutex_init(&sdp->sd_jindex_mutex); INIT_LIST_HEAD(&sdp->sd_quota_list); - spin_lock_init(&sdp->sd_quota_spin); mutex_init(&sdp->sd_quota_mutex); init_waitqueue_head(&sdp->sd_quota_wait); INIT_LIST_HEAD(&sdp->sd_trunc_list); @@ -238,6 +234,7 @@ static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf) memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN); memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN); + memcpy(sb->sb_uuid, str->sb_uuid, 16); } /** @@ -299,15 +296,15 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector) __free_page(page); return 0; } + /** * gfs2_read_sb - Read super block * @sdp: The GFS2 superblock - * @gl: the glock for the superblock (assumed to be held) * @silent: Don't print message if mount fails * */ -static int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent) +static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent) { u32 hash_blocks, ind_blocks, leaf_blocks; u32 tmp_blocks; @@ -527,7 +524,7 @@ static int init_sb(struct gfs2_sbd *sdp, int silent) return ret; } - ret = gfs2_read_sb(sdp, sb_gh.gh_gl, silent); + ret = gfs2_read_sb(sdp, silent); if (ret) { fs_err(sdp, "can't read superblock: %d\n", ret); goto out; @@ -630,13 +627,13 @@ static int map_journal_extents(struct gfs2_sbd *sdp) return rc; } -static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp) +static void gfs2_others_may_mount(struct gfs2_sbd *sdp) { - if (!sdp->sd_lockstruct.ls_ops->lm_others_may_mount) - return; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - sdp->sd_lockstruct.ls_ops->lm_others_may_mount( - sdp->sd_lockstruct.ls_lockspace); + char *message = "FIRSTMOUNT=Done"; + char *envp[] = { message, NULL }; + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + ls->ls_first_done = 1; + kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); } /** @@ -796,7 +793,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) } } - gfs2_lm_others_may_mount(sdp); + gfs2_others_may_mount(sdp); } else if (!sdp->sd_args.ar_spectator) { error = gfs2_recover_journal(sdp->sd_jdesc); if (error) { @@ -1005,7 +1002,6 @@ static int init_threads(struct gfs2_sbd *sdp, int undo) goto fail_quotad; sdp->sd_log_flush_time = jiffies; - sdp->sd_jindex_refresh_time = jiffies; p = kthread_run(gfs2_logd, sdp, "gfs2_logd"); error = IS_ERR(p); @@ -1033,6 +1029,17 @@ fail: return error; } +static const match_table_t nolock_tokens = { + { Opt_jid, "jid=%d\n", }, + { Opt_err, NULL }, +}; + +static const struct lm_lockops nolock_ops = { + .lm_proto_name = "lock_nolock", + .lm_put_lock = kmem_cache_free, + .lm_tokens = &nolock_tokens, +}; + /** * gfs2_lm_mount - mount a locking protocol * @sdp: the filesystem @@ -1044,31 +1051,73 @@ fail: static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent) { - char *proto = sdp->sd_proto_name; - char *table = sdp->sd_table_name; - int flags = LM_MFLAG_CONV_NODROP; - int error; + const struct lm_lockops *lm; + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + struct gfs2_args *args = &sdp->sd_args; + const char *proto = sdp->sd_proto_name; + const char *table = sdp->sd_table_name; + const char *fsname; + char *o, *options; + int ret; - if (sdp->sd_args.ar_spectator) - flags |= LM_MFLAG_SPECTATOR; + if (!strcmp("lock_nolock", proto)) { + lm = &nolock_ops; + sdp->sd_args.ar_localflocks = 1; + sdp->sd_args.ar_localcaching = 1; +#ifdef CONFIG_GFS2_FS_LOCKING_DLM + } else if (!strcmp("lock_dlm", proto)) { + lm = &gfs2_dlm_ops; +#endif + } else { + printk(KERN_INFO "GFS2: can't find protocol %s\n", proto); + return -ENOENT; + } fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table); - error = gfs2_mount_lockproto(proto, table, sdp->sd_args.ar_hostdata, - gfs2_glock_cb, sdp, - GFS2_MIN_LVB_SIZE, flags, - &sdp->sd_lockstruct, &sdp->sd_kobj); - if (error) { - fs_info(sdp, "can't mount proto=%s, table=%s, hostdata=%s\n", - proto, table, sdp->sd_args.ar_hostdata); - goto out; - } + ls->ls_ops = lm; + ls->ls_first = 1; + ls->ls_id = 0; - if (gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_ops) || - gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lvb_size >= - GFS2_MIN_LVB_SIZE)) { - gfs2_unmount_lockproto(&sdp->sd_lockstruct); - goto out; + for (options = args->ar_hostdata; (o = strsep(&options, ":")); ) { + substring_t tmp[MAX_OPT_ARGS]; + int token, option; + + if (!o || !*o) + continue; + + token = match_token(o, *lm->lm_tokens, tmp); + switch (token) { + case Opt_jid: + ret = match_int(&tmp[0], &option); + if (ret || option < 0) + goto hostdata_error; + ls->ls_jid = option; + break; + case Opt_id: + ret = match_int(&tmp[0], &option); + if (ret) + goto hostdata_error; + ls->ls_id = option; + break; + case Opt_first: + ret = match_int(&tmp[0], &option); + if (ret || (option != 0 && option != 1)) + goto hostdata_error; + ls->ls_first = option; + break; + case Opt_nodir: + ret = match_int(&tmp[0], &option); + if (ret || (option != 0 && option != 1)) + goto hostdata_error; + ls->ls_nodir = option; + break; + case Opt_err: + default: +hostdata_error: + fs_info(sdp, "unknown hostdata (%s)\n", o); + return -EINVAL; + } } if (sdp->sd_args.ar_spectator) @@ -1077,22 +1126,25 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent) snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table, sdp->sd_lockstruct.ls_jid); - fs_info(sdp, "Joined cluster. Now mounting FS...\n"); - - if ((sdp->sd_lockstruct.ls_flags & LM_LSFLAG_LOCAL) && - !sdp->sd_args.ar_ignore_local_fs) { - sdp->sd_args.ar_localflocks = 1; - sdp->sd_args.ar_localcaching = 1; + fsname = strchr(table, ':'); + if (fsname) + fsname++; + if (lm->lm_mount == NULL) { + fs_info(sdp, "Now mounting FS...\n"); + return 0; } - -out: - return error; + ret = lm->lm_mount(sdp, fsname); + if (ret == 0) + fs_info(sdp, "Joined cluster. Now mounting FS...\n"); + return ret; } void gfs2_lm_unmount(struct gfs2_sbd *sdp) { - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - gfs2_unmount_lockproto(&sdp->sd_lockstruct); + const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops; + if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) && + lm->lm_unmount) + lm->lm_unmount(sdp); } /** @@ -1116,12 +1168,20 @@ static int fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; } - error = gfs2_mount_args(sdp, (char *)data, 0); + sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT; + sdp->sd_args.ar_data = GFS2_DATA_DEFAULT; + + error = gfs2_mount_args(sdp, &sdp->sd_args, data); if (error) { printk(KERN_WARNING "GFS2: can't parse mount arguments\n"); goto fail; } + if (sdp->sd_args.ar_spectator) + sb->s_flags |= MS_RDONLY; + if (sdp->sd_args.ar_posix_acl) + sb->s_flags |= MS_POSIXACL; + sb->s_magic = GFS2_MAGIC; sb->s_op = &gfs2_super_ops; sb->s_export_op = &gfs2_export_ops; @@ -1199,6 +1259,8 @@ fail_sb: dput(sdp->sd_root_dir); if (sdp->sd_master_dir) dput(sdp->sd_master_dir); + if (sb->s_root) + dput(sb->s_root); sb->s_root = NULL; fail_locking: init_locking(sdp, &mount_gh, UNDO); diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 49877546beb..abd5429ae28 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -18,7 +18,6 @@ #include <linux/posix_acl.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/fiemap.h> #include <asm/uaccess.h> diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 320323d0347..458019569dc 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -19,7 +19,6 @@ #include <linux/delay.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/time.h> #include "gfs2.h" @@ -27,7 +26,6 @@ #include "glock.h" #include "inode.h" #include "log.h" -#include "mount.h" #include "quota.h" #include "recovery.h" #include "rgrp.h" @@ -40,6 +38,8 @@ #include "bmap.h" #include "meta_io.h" +#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) + /** * gfs2_write_inode - Make sure the inode is stable on the disk * @inode: The inode @@ -435,25 +435,45 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) { struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_args args = sdp->sd_args; /* Default to current settings */ int error; - error = gfs2_mount_args(sdp, data, 1); + error = gfs2_mount_args(sdp, &args, data); if (error) return error; + /* Not allowed to change locking details */ + if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) || + strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) || + strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata)) + return -EINVAL; + + /* Some flags must not be changed */ + if (args_neq(&args, &sdp->sd_args, spectator) || + args_neq(&args, &sdp->sd_args, ignore_local_fs) || + args_neq(&args, &sdp->sd_args, localflocks) || + args_neq(&args, &sdp->sd_args, localcaching) || + args_neq(&args, &sdp->sd_args, meta)) + return -EINVAL; + if (sdp->sd_args.ar_spectator) *flags |= MS_RDONLY; - else { - if (*flags & MS_RDONLY) { - if (!(sb->s_flags & MS_RDONLY)) - error = gfs2_make_fs_ro(sdp); - } else if (!(*flags & MS_RDONLY) && - (sb->s_flags & MS_RDONLY)) { + + if ((sb->s_flags ^ *flags) & MS_RDONLY) { + if (*flags & MS_RDONLY) + error = gfs2_make_fs_ro(sdp); + else error = gfs2_make_fs_rw(sdp); - } + if (error) + return error; } - return error; + sdp->sd_args = args; + if (sdp->sd_args.ar_posix_acl) + sb->s_flags |= MS_POSIXACL; + else + sb->s_flags &= ~MS_POSIXACL; + return 0; } /** @@ -588,6 +608,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) } seq_printf(s, ",data=%s", state); } + if (args->ar_discard) + seq_printf(s, ",discard"); return 0; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index b08d09696b3..8d53f66b5bc 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -45,7 +45,6 @@ #include <linux/fs.h> #include <linux/bio.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -80,6 +79,51 @@ struct gfs2_quota_change_host { u32 qc_id; }; +static LIST_HEAD(qd_lru_list); +static atomic_t qd_lru_count = ATOMIC_INIT(0); +static spinlock_t qd_lru_lock = SPIN_LOCK_UNLOCKED; + +int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask) +{ + struct gfs2_quota_data *qd; + struct gfs2_sbd *sdp; + + if (nr == 0) + goto out; + + if (!(gfp_mask & __GFP_FS)) + return -1; + + spin_lock(&qd_lru_lock); + while (nr && !list_empty(&qd_lru_list)) { + qd = list_entry(qd_lru_list.next, + struct gfs2_quota_data, qd_reclaim); + sdp = qd->qd_gl->gl_sbd; + + /* Free from the filesystem-specific list */ + list_del(&qd->qd_list); + + gfs2_assert_warn(sdp, !qd->qd_change); + gfs2_assert_warn(sdp, !qd->qd_slot_count); + gfs2_assert_warn(sdp, !qd->qd_bh_count); + + gfs2_glock_put(qd->qd_gl); + atomic_dec(&sdp->sd_quota_count); + + /* Delete it from the common reclaim list */ + list_del_init(&qd->qd_reclaim); + atomic_dec(&qd_lru_count); + spin_unlock(&qd_lru_lock); + kmem_cache_free(gfs2_quotad_cachep, qd); + spin_lock(&qd_lru_lock); + nr--; + } + spin_unlock(&qd_lru_lock); + +out: + return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100; +} + static u64 qd2offset(struct gfs2_quota_data *qd) { u64 offset; @@ -100,22 +144,18 @@ static int qd_alloc(struct gfs2_sbd *sdp, int user, u32 id, if (!qd) return -ENOMEM; - qd->qd_count = 1; + atomic_set(&qd->qd_count, 1); qd->qd_id = id; if (user) set_bit(QDF_USER, &qd->qd_flags); qd->qd_slot = -1; + INIT_LIST_HEAD(&qd->qd_reclaim); error = gfs2_glock_get(sdp, 2 * (u64)id + !user, &gfs2_quota_glops, CREATE, &qd->qd_gl); if (error) goto fail; - error = gfs2_lvb_hold(qd->qd_gl); - gfs2_glock_put(qd->qd_gl); - if (error) - goto fail; - *qdp = qd; return 0; @@ -135,11 +175,17 @@ static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create, for (;;) { found = 0; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { if (qd->qd_id == id && !test_bit(QDF_USER, &qd->qd_flags) == !user) { - qd->qd_count++; + if (!atomic_read(&qd->qd_count) && + !list_empty(&qd->qd_reclaim)) { + /* Remove it from reclaim list */ + list_del_init(&qd->qd_reclaim); + atomic_dec(&qd_lru_count); + } + atomic_inc(&qd->qd_count); found = 1; break; } @@ -155,11 +201,11 @@ static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create, new_qd = NULL; } - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); if (qd || !create) { if (new_qd) { - gfs2_lvb_unhold(new_qd->qd_gl); + gfs2_glock_put(new_qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, new_qd); } *qdp = qd; @@ -175,21 +221,18 @@ static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create, static void qd_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - - spin_lock(&sdp->sd_quota_spin); - gfs2_assert(sdp, qd->qd_count); - qd->qd_count++; - spin_unlock(&sdp->sd_quota_spin); + gfs2_assert(sdp, atomic_read(&qd->qd_count)); + atomic_inc(&qd->qd_count); } static void qd_put(struct gfs2_quota_data *qd) { - struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - spin_lock(&sdp->sd_quota_spin); - gfs2_assert(sdp, qd->qd_count); - if (!--qd->qd_count) - qd->qd_last_touched = jiffies; - spin_unlock(&sdp->sd_quota_spin); + if (atomic_dec_and_lock(&qd->qd_count, &qd_lru_lock)) { + /* Add to the reclaim list */ + list_add_tail(&qd->qd_reclaim, &qd_lru_list); + atomic_inc(&qd_lru_count); + spin_unlock(&qd_lru_lock); + } } static int slot_get(struct gfs2_quota_data *qd) @@ -198,10 +241,10 @@ static int slot_get(struct gfs2_quota_data *qd) unsigned int c, o = 0, b; unsigned char byte = 0; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); if (qd->qd_slot_count++) { - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); return 0; } @@ -225,13 +268,13 @@ found: sdp->sd_quota_bitmap[c][o] |= 1 << b; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); return 0; fail: qd->qd_slot_count--; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); return -ENOSPC; } @@ -239,23 +282,23 @@ static void slot_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); gfs2_assert(sdp, qd->qd_slot_count); qd->qd_slot_count++; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); } static void slot_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); gfs2_assert(sdp, qd->qd_slot_count); if (!--qd->qd_slot_count) { gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, qd->qd_slot, 0); qd->qd_slot = -1; } - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); } static int bh_get(struct gfs2_quota_data *qd) @@ -330,7 +373,7 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) if (sdp->sd_vfs->s_flags & MS_RDONLY) return 0; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { if (test_bit(QDF_LOCKED, &qd->qd_flags) || @@ -341,8 +384,8 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) list_move_tail(&qd->qd_list, &sdp->sd_quota_list); set_bit(QDF_LOCKED, &qd->qd_flags); - gfs2_assert_warn(sdp, qd->qd_count); - qd->qd_count++; + gfs2_assert_warn(sdp, atomic_read(&qd->qd_count)); + atomic_inc(&qd->qd_count); qd->qd_change_sync = qd->qd_change; gfs2_assert_warn(sdp, qd->qd_slot_count); qd->qd_slot_count++; @@ -354,7 +397,7 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) if (!found) qd = NULL; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); if (qd) { gfs2_assert_warn(sdp, qd->qd_change_sync); @@ -379,24 +422,24 @@ static int qd_trylock(struct gfs2_quota_data *qd) if (sdp->sd_vfs->s_flags & MS_RDONLY) return 0; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); if (test_bit(QDF_LOCKED, &qd->qd_flags) || !test_bit(QDF_CHANGE, &qd->qd_flags)) { - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); return 0; } list_move_tail(&qd->qd_list, &sdp->sd_quota_list); set_bit(QDF_LOCKED, &qd->qd_flags); - gfs2_assert_warn(sdp, qd->qd_count); - qd->qd_count++; + gfs2_assert_warn(sdp, atomic_read(&qd->qd_count)); + atomic_inc(&qd->qd_count); qd->qd_change_sync = qd->qd_change; gfs2_assert_warn(sdp, qd->qd_slot_count); qd->qd_slot_count++; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); gfs2_assert_warn(sdp, qd->qd_change_sync); if (bh_get(qd)) { @@ -556,9 +599,9 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) x = be64_to_cpu(qc->qc_change) + change; qc->qc_change = cpu_to_be64(x); - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); qd->qd_change = x; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); if (!x) { gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags)); @@ -802,8 +845,8 @@ restart: loff_t pos; gfs2_glock_dq_uninit(q_gh); error = gfs2_glock_nq_init(qd->qd_gl, - LM_ST_EXCLUSIVE, GL_NOCACHE, - q_gh); + LM_ST_EXCLUSIVE, GL_NOCACHE, + q_gh); if (error) return error; @@ -820,7 +863,6 @@ restart: gfs2_glock_dq_uninit(&i_gh); - gfs2_quota_in(&q, buf); qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb; qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC); @@ -890,9 +932,9 @@ static int need_sync(struct gfs2_quota_data *qd) if (!qd->qd_qb.qb_limit) return 0; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); value = qd->qd_change; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); spin_lock(>->gt_spin); num = gt->gt_quota_scale_num; @@ -985,9 +1027,9 @@ int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid) continue; value = (s64)be64_to_cpu(qd->qd_qb.qb_value); - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); value += qd->qd_change; - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) { print_message(qd, "exceeded"); @@ -1171,13 +1213,12 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) qd->qd_change = qc.qc_change; qd->qd_slot = slot; qd->qd_slot_count = 1; - qd->qd_last_touched = jiffies; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, slot, 1); list_add(&qd->qd_list, &sdp->sd_quota_list); atomic_inc(&sdp->sd_quota_count); - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); found++; } @@ -1197,73 +1238,48 @@ fail: return error; } -static void gfs2_quota_scan(struct gfs2_sbd *sdp) -{ - struct gfs2_quota_data *qd, *safe; - LIST_HEAD(dead); - - spin_lock(&sdp->sd_quota_spin); - list_for_each_entry_safe(qd, safe, &sdp->sd_quota_list, qd_list) { - if (!qd->qd_count && - time_after_eq(jiffies, qd->qd_last_touched + - gfs2_tune_get(sdp, gt_quota_cache_secs) * HZ)) { - list_move(&qd->qd_list, &dead); - gfs2_assert_warn(sdp, - atomic_read(&sdp->sd_quota_count) > 0); - atomic_dec(&sdp->sd_quota_count); - } - } - spin_unlock(&sdp->sd_quota_spin); - - while (!list_empty(&dead)) { - qd = list_entry(dead.next, struct gfs2_quota_data, qd_list); - list_del(&qd->qd_list); - - gfs2_assert_warn(sdp, !qd->qd_change); - gfs2_assert_warn(sdp, !qd->qd_slot_count); - gfs2_assert_warn(sdp, !qd->qd_bh_count); - - gfs2_lvb_unhold(qd->qd_gl); - kmem_cache_free(gfs2_quotad_cachep, qd); - } -} - void gfs2_quota_cleanup(struct gfs2_sbd *sdp) { struct list_head *head = &sdp->sd_quota_list; struct gfs2_quota_data *qd; unsigned int x; - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); while (!list_empty(head)) { qd = list_entry(head->prev, struct gfs2_quota_data, qd_list); - if (qd->qd_count > 1 || - (qd->qd_count && !test_bit(QDF_CHANGE, &qd->qd_flags))) { + if (atomic_read(&qd->qd_count) > 1 || + (atomic_read(&qd->qd_count) && + !test_bit(QDF_CHANGE, &qd->qd_flags))) { list_move(&qd->qd_list, head); - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); schedule(); - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); continue; } list_del(&qd->qd_list); + /* Also remove if this qd exists in the reclaim list */ + if (!list_empty(&qd->qd_reclaim)) { + list_del_init(&qd->qd_reclaim); + atomic_dec(&qd_lru_count); + } atomic_dec(&sdp->sd_quota_count); - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); - if (!qd->qd_count) { + if (!atomic_read(&qd->qd_count)) { gfs2_assert_warn(sdp, !qd->qd_change); gfs2_assert_warn(sdp, !qd->qd_slot_count); } else gfs2_assert_warn(sdp, qd->qd_slot_count == 1); gfs2_assert_warn(sdp, !qd->qd_bh_count); - gfs2_lvb_unhold(qd->qd_gl); + gfs2_glock_put(qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, qd); - spin_lock(&sdp->sd_quota_spin); + spin_lock(&qd_lru_lock); } - spin_unlock(&sdp->sd_quota_spin); + spin_unlock(&qd_lru_lock); gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count)); @@ -1341,9 +1357,6 @@ int gfs2_quotad(void *data) quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t, "ad_timeo, &tune->gt_quota_quantum); - /* FIXME: This should be turned into a shrinker */ - gfs2_quota_scan(sdp); - /* Check for & recover partially truncated inodes */ quotad_check_trunc_list(sdp); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index cec9032be97..0fa5fa63d0e 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -49,4 +49,6 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; } +extern int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask); + #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index efd09c3d2b2..247e8f7d6b3 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -13,7 +13,6 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/lm_interface.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -427,20 +426,23 @@ static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *hea } -static void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, - unsigned int message) +static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, + unsigned int message) { - if (!sdp->sd_lockstruct.ls_ops->lm_recovery_done) - return; - - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - sdp->sd_lockstruct.ls_ops->lm_recovery_done( - sdp->sd_lockstruct.ls_lockspace, jid, message); + char env_jid[20]; + char env_status[20]; + char *envp[] = { env_jid, env_status, NULL }; + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + ls->ls_recover_jid_done = jid; + ls->ls_recover_jid_status = message; + sprintf(env_jid, "JID=%d", jid); + sprintf(env_status, "RECOVERY=%s", + message == LM_RD_SUCCESS ? "Done" : "Failed"); + kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); } - /** - * gfs2_recover_journal - recovery a given journal + * gfs2_recover_journal - recover a given journal * @jd: the struct gfs2_jdesc describing the journal * * Acquire the journal's lock, check to see if the journal is clean, and @@ -561,7 +563,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) gfs2_glock_dq_uninit(&ji_gh); - gfs2_lm_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS); + gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS); if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) gfs2_glock_dq_uninit(&j_gh); @@ -581,7 +583,7 @@ fail_gunlock_j: fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done"); fail: - gfs2_lm_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP); + gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP); return error; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 8b01c635d92..f03d024038e 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -13,8 +13,8 @@ #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <linux/prefetch.h> +#include <linux/blkdev.h> #include "gfs2.h" #include "incore.h" @@ -132,81 +132,90 @@ static inline unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, } /** + * gfs2_bit_search + * @ptr: Pointer to bitmap data + * @mask: Mask to use (normally 0x55555.... but adjusted for search start) + * @state: The state we are searching for + * + * We xor the bitmap data with a patter which is the bitwise opposite + * of what we are looking for, this gives rise to a pattern of ones + * wherever there is a match. Since we have two bits per entry, we + * take this pattern, shift it down by one place and then and it with + * the original. All the even bit positions (0,2,4, etc) then represent + * successful matches, so we mask with 0x55555..... to remove the unwanted + * odd bit positions. + * + * This allows searching of a whole u64 at once (32 blocks) with a + * single test (on 64 bit arches). + */ + +static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state) +{ + u64 tmp; + static const u64 search[] = { + [0] = 0xffffffffffffffffULL, + [1] = 0xaaaaaaaaaaaaaaaaULL, + [2] = 0x5555555555555555ULL, + [3] = 0x0000000000000000ULL, + }; + tmp = le64_to_cpu(*ptr) ^ search[state]; + tmp &= (tmp >> 1); + tmp &= mask; + return tmp; +} + +/** * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing * a block in a given allocation state. * @buffer: the buffer that holds the bitmaps - * @buflen: the length (in bytes) of the buffer + * @len: the length (in bytes) of the buffer * @goal: start search at this block's bit-pair (within @buffer) - * @old_state: GFS2_BLKST_XXX the state of the block we're looking for. + * @state: GFS2_BLKST_XXX the state of the block we're looking for. * * Scope of @goal and returned block number is only within this bitmap buffer, * not entire rgrp or filesystem. @buffer will be offset from the actual - * beginning of a bitmap block buffer, skipping any header structures. + * beginning of a bitmap block buffer, skipping any header structures, but + * headers are always a multiple of 64 bits long so that the buffer is + * always aligned to a 64 bit boundary. + * + * The size of the buffer is in bytes, but is it assumed that it is + * always ok to to read a complete multiple of 64 bits at the end + * of the block in case the end is no aligned to a natural boundary. * * Return: the block number (bitmap buffer scope) that was found */ -static u32 gfs2_bitfit(const u8 *buffer, unsigned int buflen, u32 goal, - u8 old_state) +static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, + u32 goal, u8 state) { - const u8 *byte, *start, *end; - int bit, startbit; - u32 g1, g2, misaligned; - unsigned long *plong; - unsigned long lskipval; - - lskipval = (old_state & GFS2_BLKST_USED) ? LBITSKIP00 : LBITSKIP55; - g1 = (goal / GFS2_NBBY); - start = buffer + g1; - byte = start; - end = buffer + buflen; - g2 = ALIGN(g1, sizeof(unsigned long)); - plong = (unsigned long *)(buffer + g2); - startbit = bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE; - misaligned = g2 - g1; - if (!misaligned) - goto ulong_aligned; -/* parse the bitmap a byte at a time */ -misaligned: - while (byte < end) { - if (((*byte >> bit) & GFS2_BIT_MASK) == old_state) { - return goal + - (((byte - start) * GFS2_NBBY) + - ((bit - startbit) >> 1)); - } - bit += GFS2_BIT_SIZE; - if (bit >= GFS2_NBBY * GFS2_BIT_SIZE) { - bit = 0; - byte++; - misaligned--; - if (!misaligned) { - plong = (unsigned long *)byte; - goto ulong_aligned; - } - } - } - return BFITNOENT; - -/* parse the bitmap a unsigned long at a time */ -ulong_aligned: - /* Stop at "end - 1" or else prefetch can go past the end and segfault. - We could "if" it but we'd lose some of the performance gained. - This way will only slow down searching the very last 4/8 bytes - depending on architecture. I've experimented with several ways - of writing this section such as using an else before the goto - but this one seems to be the fastest. */ - while ((unsigned char *)plong < end - sizeof(unsigned long)) { - prefetch(plong + 1); - if (((*plong) & LBITMASK) != lskipval) - break; - plong++; - } - if ((unsigned char *)plong < end) { - byte = (const u8 *)plong; - misaligned += sizeof(unsigned long) - 1; - goto misaligned; + u32 spoint = (goal << 1) & ((8*sizeof(u64)) - 1); + const __le64 *ptr = ((__le64 *)buf) + (goal >> 5); + const __le64 *end = (__le64 *)(buf + ALIGN(len, sizeof(u64))); + u64 tmp; + u64 mask = 0x5555555555555555ULL; + u32 bit; + + BUG_ON(state > 3); + + /* Mask off bits we don't care about at the start of the search */ + mask <<= spoint; + tmp = gfs2_bit_search(ptr, mask, state); + ptr++; + while(tmp == 0 && ptr < end) { + tmp = gfs2_bit_search(ptr, 0x5555555555555555ULL, state); + ptr++; } - return BFITNOENT; + /* Mask off any bits which are more than len bytes from the start */ + if (ptr == end && (len & (sizeof(u64) - 1))) + tmp &= (((u64)~0) >> (64 - 8*(len & (sizeof(u64) - 1)))); + /* Didn't find anything, so return */ + if (tmp == 0) + return BFITNOENT; + ptr--; + bit = fls64(tmp); + bit--; /* fls64 always adds one to the bit count */ + bit /= 2; /* two bits per entry in the bitmap */ + return (((const unsigned char *)ptr - buf) * GFS2_NBBY) + bit; } /** @@ -831,6 +840,58 @@ void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd) spin_unlock(&sdp->sd_rindex_spin); } +static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, + const struct gfs2_bitmap *bi) +{ + struct super_block *sb = sdp->sd_vfs; + struct block_device *bdev = sb->s_bdev; + const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize / + bdev_hardsect_size(sb->s_bdev); + u64 blk; + sector_t start = 0; + sector_t nr_sects = 0; + int rv; + unsigned int x; + + for (x = 0; x < bi->bi_len; x++) { + const u8 *orig = bi->bi_bh->b_data + bi->bi_offset + x; + const u8 *clone = bi->bi_clone + bi->bi_offset + x; + u8 diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1)); + diff &= 0x55; + if (diff == 0) + continue; + blk = offset + ((bi->bi_start + x) * GFS2_NBBY); + blk *= sects_per_blk; /* convert to sectors */ + while(diff) { + if (diff & 1) { + if (nr_sects == 0) + goto start_new_extent; + if ((start + nr_sects) != blk) { + rv = blkdev_issue_discard(bdev, start, + nr_sects, GFP_NOFS); + if (rv) + goto fail; + nr_sects = 0; +start_new_extent: + start = blk; + } + nr_sects += sects_per_blk; + } + diff >>= 2; + blk += sects_per_blk; + } + } + if (nr_sects) { + rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS); + if (rv) + goto fail; + } + return; +fail: + fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem", rv); + sdp->sd_args.ar_discard = 0; +} + void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; @@ -841,6 +902,8 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) struct gfs2_bitmap *bi = rgd->rd_bits + x; if (!bi->bi_clone) continue; + if (sdp->sd_args.ar_discard) + gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi); memcpy(bi->bi_clone + bi->bi_offset, bi->bi_bh->b_data + bi->bi_offset, bi->bi_len); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 141b781f2fc..601913e0a48 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -15,7 +15,6 @@ #include <linux/crc32.h> #include <linux/gfs2_ondisk.h> #include <linux/bio.h> -#include <linux/lm_interface.h> #include "gfs2.h" #include "incore.h" @@ -339,7 +338,6 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp, struct gfs2_holder *t_gh) { struct gfs2_inode *ip; - struct gfs2_holder ji_gh; struct gfs2_jdesc *jd; struct lfcc *lfcc; LIST_HEAD(list); @@ -387,7 +385,6 @@ out: gfs2_glock_dq_uninit(&lfcc->gh); kfree(lfcc); } - gfs2_glock_dq_uninit(&ji_gh); return error; } diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index f6b8b00ad88..91abdbedcc8 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -14,7 +14,7 @@ #include <linux/dcache.h> #include "incore.h" -void gfs2_lm_unmount(struct gfs2_sbd *sdp); +extern void gfs2_lm_unmount(struct gfs2_sbd *sdp); static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp) { @@ -27,21 +27,23 @@ static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp) void gfs2_jindex_free(struct gfs2_sbd *sdp); -struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid); -int gfs2_jdesc_check(struct gfs2_jdesc *jd); +extern int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *data); -int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename, - struct gfs2_inode **ipp); +extern struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid); +extern int gfs2_jdesc_check(struct gfs2_jdesc *jd); -int gfs2_make_fs_rw(struct gfs2_sbd *sdp); +extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename, + struct gfs2_inode **ipp); -int gfs2_statfs_init(struct gfs2_sbd *sdp); -void gfs2_statfs_change(struct gfs2_sbd *sdp, - s64 total, s64 free, s64 dinodes); -int gfs2_statfs_sync(struct gfs2_sbd *sdp); +extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp); -int gfs2_freeze_fs(struct gfs2_sbd *sdp); -void gfs2_unfreeze_fs(struct gfs2_sbd *sdp); +extern int gfs2_statfs_init(struct gfs2_sbd *sdp); +extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free, + s64 dinodes); +extern int gfs2_statfs_sync(struct gfs2_sbd *sdp); + +extern int gfs2_freeze_fs(struct gfs2_sbd *sdp); +extern void gfs2_unfreeze_fs(struct gfs2_sbd *sdp); extern struct file_system_type gfs2_fs_type; extern struct file_system_type gfs2meta_fs_type; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 26c1fa777a9..7655f5025fe 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -14,9 +14,8 @@ #include <linux/buffer_head.h> #include <linux/module.h> #include <linux/kobject.h> -#include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <asm/uaccess.h> +#include <linux/gfs2_ondisk.h> #include "gfs2.h" #include "incore.h" @@ -25,6 +24,7 @@ #include "glock.h" #include "quota.h" #include "util.h" +#include "glops.h" static ssize_t id_show(struct gfs2_sbd *sdp, char *buf) { @@ -37,6 +37,30 @@ static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf) return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname); } +static int gfs2_uuid_valid(const u8 *uuid) +{ + int i; + + for (i = 0; i < 16; i++) { + if (uuid[i]) + return 1; + } + return 0; +} + +static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf) +{ + const u8 *uuid = sdp->sd_sb.sb_uuid; + buf[0] = '\0'; + if (!gfs2_uuid_valid(uuid)) + return 0; + return snprintf(buf, PAGE_SIZE, "%02X%02X%02X%02X-%02X%02X-" + "%02X%02X-%02X%02X-%02X%02X%02X%02X%02X%02X\n", + uuid[0], uuid[1], uuid[2], uuid[3], uuid[4], uuid[5], + uuid[6], uuid[7], uuid[8], uuid[9], uuid[10], uuid[11], + uuid[12], uuid[13], uuid[14], uuid[15]); +} + static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf) { unsigned int count; @@ -148,6 +172,46 @@ static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf, return len; } +static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len) +{ + struct gfs2_glock *gl; + const struct gfs2_glock_operations *glops; + unsigned int glmode; + unsigned int gltype; + unsigned long long glnum; + char mode[16]; + int rv; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum, + mode); + if (rv != 3) + return -EINVAL; + + if (strcmp(mode, "EX") == 0) + glmode = LM_ST_UNLOCKED; + else if ((strcmp(mode, "CW") == 0) || (strcmp(mode, "DF") == 0)) + glmode = LM_ST_DEFERRED; + else if ((strcmp(mode, "PR") == 0) || (strcmp(mode, "SH") == 0)) + glmode = LM_ST_SHARED; + else + return -EINVAL; + + if (gltype > LM_TYPE_JOURNAL) + return -EINVAL; + glops = gfs2_glops_list[gltype]; + if (glops == NULL) + return -EINVAL; + rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl); + if (rv) + return rv; + gfs2_glock_cb(gl, glmode); + gfs2_glock_put(gl); + return len; +} + struct gfs2_attr { struct attribute attr; ssize_t (*show)(struct gfs2_sbd *, char *); @@ -159,22 +223,26 @@ static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store) GFS2_ATTR(id, 0444, id_show, NULL); GFS2_ATTR(fsname, 0444, fsname_show, NULL); +GFS2_ATTR(uuid, 0444, uuid_show, NULL); GFS2_ATTR(freeze, 0644, freeze_show, freeze_store); GFS2_ATTR(withdraw, 0644, withdraw_show, withdraw_store); GFS2_ATTR(statfs_sync, 0200, NULL, statfs_sync_store); GFS2_ATTR(quota_sync, 0200, NULL, quota_sync_store); GFS2_ATTR(quota_refresh_user, 0200, NULL, quota_refresh_user_store); GFS2_ATTR(quota_refresh_group, 0200, NULL, quota_refresh_group_store); +GFS2_ATTR(demote_rq, 0200, NULL, demote_rq_store); static struct attribute *gfs2_attrs[] = { &gfs2_attr_id.attr, &gfs2_attr_fsname.attr, + &gfs2_attr_uuid.attr, &gfs2_attr_freeze.attr, &gfs2_attr_withdraw.attr, &gfs2_attr_statfs_sync.attr, &gfs2_attr_quota_sync.attr, &gfs2_attr_quota_refresh_user.attr, &gfs2_attr_quota_refresh_group.attr, + &gfs2_attr_demote_rq.attr, NULL, }; @@ -224,14 +292,145 @@ static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name) LOCKSTRUCT_ATTR(jid, "%u\n"); LOCKSTRUCT_ATTR(first, "%u\n"); -LOCKSTRUCT_ATTR(lvb_size, "%u\n"); -LOCKSTRUCT_ATTR(flags, "%d\n"); static struct attribute *lockstruct_attrs[] = { &lockstruct_attr_jid.attr, &lockstruct_attr_first.attr, - &lockstruct_attr_lvb_size.attr, - &lockstruct_attr_flags.attr, + NULL, +}; + +/* + * lock_module. Originally from lock_dlm + */ + +static ssize_t proto_name_show(struct gfs2_sbd *sdp, char *buf) +{ + const struct lm_lockops *ops = sdp->sd_lockstruct.ls_ops; + return sprintf(buf, "%s\n", ops->lm_proto_name); +} + +static ssize_t block_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + ssize_t ret; + int val = 0; + + if (test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags)) + val = 1; + ret = sprintf(buf, "%d\n", val); + return ret; +} + +static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + ssize_t ret = len; + int val; + + val = simple_strtol(buf, NULL, 0); + + if (val == 1) + set_bit(DFL_BLOCK_LOCKS, &ls->ls_flags); + else if (val == 0) { + clear_bit(DFL_BLOCK_LOCKS, &ls->ls_flags); + smp_mb__after_clear_bit(); + gfs2_glock_thaw(sdp); + } else { + ret = -EINVAL; + } + return ret; +} + +static ssize_t lkid_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%u\n", ls->ls_id); +} + +static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%d\n", ls->ls_first); +} + +static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%d\n", ls->ls_first_done); +} + +static ssize_t recover_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%d\n", ls->ls_recover_jid); +} + +static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid) +{ + struct gfs2_jdesc *jd; + + spin_lock(&sdp->sd_jindex_spin); + list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { + if (jd->jd_jid != jid) + continue; + jd->jd_dirty = 1; + break; + } + spin_unlock(&sdp->sd_jindex_spin); +} + +static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + ls->ls_recover_jid = simple_strtol(buf, NULL, 0); + gfs2_jdesc_make_dirty(sdp, ls->ls_recover_jid); + if (sdp->sd_recoverd_process) + wake_up_process(sdp->sd_recoverd_process); + return len; +} + +static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%d\n", ls->ls_recover_jid_done); +} + +static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf) +{ + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + return sprintf(buf, "%d\n", ls->ls_recover_jid_status); +} + +struct gdlm_attr { + struct attribute attr; + ssize_t (*show)(struct gfs2_sbd *sdp, char *); + ssize_t (*store)(struct gfs2_sbd *sdp, const char *, size_t); +}; + +#define GDLM_ATTR(_name,_mode,_show,_store) \ +static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) + +GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); +GDLM_ATTR(block, 0644, block_show, block_store); +GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); +GDLM_ATTR(id, 0444, lkid_show, NULL); +GDLM_ATTR(first, 0444, lkfirst_show, NULL); +GDLM_ATTR(first_done, 0444, first_done_show, NULL); +GDLM_ATTR(recover, 0644, recover_show, recover_store); +GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); +GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); + +static struct attribute *lock_module_attrs[] = { + &gdlm_attr_proto_name.attr, + &gdlm_attr_block.attr, + &gdlm_attr_withdraw.attr, + &gdlm_attr_id.attr, + &lockstruct_attr_jid.attr, + &gdlm_attr_first.attr, + &gdlm_attr_first_done.attr, + &gdlm_attr_recover.attr, + &gdlm_attr_recover_done.attr, + &gdlm_attr_recover_status.attr, NULL, }; @@ -373,7 +572,6 @@ TUNE_ATTR(complain_secs, 0); TUNE_ATTR(statfs_slow, 0); TUNE_ATTR(new_files_jdata, 0); TUNE_ATTR(quota_simul_sync, 1); -TUNE_ATTR(quota_cache_secs, 1); TUNE_ATTR(stall_secs, 1); TUNE_ATTR(statfs_quantum, 1); TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process); @@ -389,7 +587,6 @@ static struct attribute *tune_attrs[] = { &tune_attr_complain_secs.attr, &tune_attr_statfs_slow.attr, &tune_attr_quota_simul_sync.attr, - &tune_attr_quota_cache_secs.attr, &tune_attr_stall_secs.attr, &tune_attr_statfs_quantum.attr, &tune_attr_recoverd_secs.attr, @@ -414,6 +611,11 @@ static struct attribute_group tune_group = { .attrs = tune_attrs, }; +static struct attribute_group lock_module_group = { + .name = "lock_module", + .attrs = lock_module_attrs, +}; + int gfs2_sys_fs_add(struct gfs2_sbd *sdp) { int error; @@ -436,9 +638,15 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail_args; + error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group); + if (error) + goto fail_tune; + kobject_uevent(&sdp->sd_kobj, KOBJ_ADD); return 0; +fail_tune: + sysfs_remove_group(&sdp->sd_kobj, &tune_group); fail_args: sysfs_remove_group(&sdp->sd_kobj, &args_group); fail_lockstruct: @@ -455,15 +663,27 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) sysfs_remove_group(&sdp->sd_kobj, &tune_group); sysfs_remove_group(&sdp->sd_kobj, &args_group); sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); + sysfs_remove_group(&sdp->sd_kobj, &lock_module_group); kobject_put(&sdp->sd_kobj); } + static int gfs2_uevent(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env) { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + const u8 *uuid = sdp->sd_sb.sb_uuid; + add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name); add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name); + if (gfs2_uuid_valid(uuid)) { + add_uevent_var(env, "UUID=%02X%02X%02X%02X-%02X%02X-%02X%02X-" + "%02X%02X-%02X%02X%02X%02X%02X%02X", + uuid[0], uuid[1], uuid[2], uuid[3], uuid[4], + uuid[5], uuid[6], uuid[7], uuid[8], uuid[9], + uuid[10], uuid[11], uuid[12], uuid[13], + uuid[14], uuid[15]); + } return 0; } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index f677b8a83f0..053752d4b27 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -12,9 +12,8 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> -#include <linux/gfs2_ondisk.h> #include <linux/kallsyms.h> -#include <linux/lm_interface.h> +#include <linux/gfs2_ondisk.h> #include "gfs2.h" #include "incore.h" @@ -88,9 +87,11 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) if (!tr->tr_touched) { gfs2_log_release(sdp, tr->tr_reserved); - gfs2_glock_dq(&tr->tr_t_gh); - gfs2_holder_uninit(&tr->tr_t_gh); - kfree(tr); + if (tr->tr_t_gh.gh_gl) { + gfs2_glock_dq(&tr->tr_t_gh); + gfs2_holder_uninit(&tr->tr_t_gh); + kfree(tr); + } return; } @@ -106,9 +107,11 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) } gfs2_log_commit(sdp, tr); - gfs2_glock_dq(&tr->tr_t_gh); - gfs2_holder_uninit(&tr->tr_t_gh); - kfree(tr); + if (tr->tr_t_gh.gh_gl) { + gfs2_glock_dq(&tr->tr_t_gh); + gfs2_holder_uninit(&tr->tr_t_gh); + kfree(tr); + } if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) gfs2_log_flush(sdp, NULL); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 374f50e9549..9d12b1118ba 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -13,7 +13,6 @@ #include <linux/buffer_head.h> #include <linux/crc32.h> #include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> #include <asm/uaccess.h> #include "gfs2.h" @@ -35,6 +34,8 @@ void gfs2_assert_i(struct gfs2_sbd *sdp) int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...) { + struct lm_lockstruct *ls = &sdp->sd_lockstruct; + const struct lm_lockops *lm = ls->ls_ops; va_list args; if (test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags)) @@ -47,8 +48,12 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...) fs_err(sdp, "about to withdraw this file system\n"); BUG_ON(sdp->sd_args.ar_debug); - fs_err(sdp, "telling LM to withdraw\n"); - gfs2_withdraw_lockproto(&sdp->sd_lockstruct); + kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE); + + if (lm->lm_unmount) { + fs_err(sdp, "telling LM to unmount\n"); + lm->lm_unmount(sdp); + } fs_err(sdp, "withdrawn\n"); dump_stack(); diff --git a/fs/inode.c b/fs/inode.c index 913ab2d9a5d..643ac43e5a5 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -17,6 +17,7 @@ #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/pagemap.h> #include <linux/cdev.h> #include <linux/bootmem.h> @@ -147,13 +148,13 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->i_cdev = NULL; inode->i_rdev = 0; inode->dirtied_when = 0; - if (security_inode_alloc(inode)) { - if (inode->i_sb->s_op->destroy_inode) - inode->i_sb->s_op->destroy_inode(inode); - else - kmem_cache_free(inode_cachep, (inode)); - return NULL; - } + + if (security_inode_alloc(inode)) + goto out_free_inode; + + /* allocate and initialize an i_integrity */ + if (ima_inode_alloc(inode)) + goto out_free_security; spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); @@ -189,6 +190,15 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->i_mapping = mapping; return inode; + +out_free_security: + security_inode_free(inode); +out_free_inode: + if (inode->i_sb->s_op->destroy_inode) + inode->i_sb->s_op->destroy_inode(inode); + else + kmem_cache_free(inode_cachep, (inode)); + return NULL; } EXPORT_SYMBOL(inode_init_always); @@ -359,6 +369,7 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose) invalidate_inode_buffers(inode); if (!atomic_read(&inode->i_count)) { list_move(&inode->i_list, dispose); + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; count++; continue; @@ -460,6 +471,7 @@ static void prune_icache(int nr_to_scan) continue; } list_move(&inode->i_list, &freeable); + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; nr_pruned++; } @@ -656,6 +668,7 @@ void unlock_new_inode(struct inode *inode) * just created it (so there can be no old holders * that haven't tested I_LOCK). */ + WARN_ON((inode->i_state & (I_LOCK|I_NEW)) != (I_LOCK|I_NEW)); inode->i_state &= ~(I_LOCK|I_NEW); wake_up_inode(inode); } @@ -1145,6 +1158,7 @@ void generic_delete_inode(struct inode *inode) list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; inodes_stat.nr_inodes--; spin_unlock(&inode_lock); @@ -1186,16 +1200,19 @@ static void generic_forget_inode(struct inode *inode) spin_unlock(&inode_lock); return; } + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); write_inode_now(inode, 1); spin_lock(&inode_lock); + WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; inodes_stat.nr_unused--; hlist_del_init(&inode->i_hash); } list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; inodes_stat.nr_inodes--; spin_unlock(&inode_lock); @@ -1283,6 +1300,40 @@ sector_t bmap(struct inode * inode, sector_t block) } EXPORT_SYMBOL(bmap); +/* + * With relative atime, only update atime if the previous atime is + * earlier than either the ctime or mtime or if at least a day has + * passed since the last atime update. + */ +static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, + struct timespec now) +{ + + if (!(mnt->mnt_flags & MNT_RELATIME)) + return 1; + /* + * Is mtime younger than atime? If yes, update atime: + */ + if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0) + return 1; + /* + * Is ctime younger than atime? If yes, update atime: + */ + if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0) + return 1; + + /* + * Is the previous atime value older than a day? If yes, + * update atime: + */ + if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) + return 1; + /* + * Good, we can skip the atime update: + */ + return 0; +} + /** * touch_atime - update the access time * @mnt: mount the inode is accessed on @@ -1310,17 +1361,12 @@ void touch_atime(struct vfsmount *mnt, struct dentry *dentry) goto out; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) goto out; - if (mnt->mnt_flags & MNT_RELATIME) { - /* - * With relative atime, only update atime if the previous - * atime is earlier than either the ctime or mtime. - */ - if (timespec_compare(&inode->i_mtime, &inode->i_atime) < 0 && - timespec_compare(&inode->i_ctime, &inode->i_atime) < 0) - goto out; - } now = current_fs_time(inode->i_sb); + + if (!relatime_need_update(mnt, inode, now)) + goto out; + if (timespec_equal(&inode->i_atime, &now)) goto out; diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 1f3b0fc0d35..aedc47a264c 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -139,6 +139,55 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) return 0; } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static const struct in6_addr *nlmclnt_map_v4addr(const struct sockaddr *sap, + struct in6_addr *addr_mapped) +{ + const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; + + switch (sap->sa_family) { + case AF_INET6: + return &((const struct sockaddr_in6 *)sap)->sin6_addr; + case AF_INET: + ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, addr_mapped); + return addr_mapped; + } + + return NULL; +} + +/* + * If lockd is using a PF_INET6 listener, all incoming requests appear + * to come from AF_INET6 remotes. The address of AF_INET remotes are + * mapped to AF_INET6 automatically by the network layer. In case the + * user passed an AF_INET server address at mount time, ensure both + * addresses are AF_INET6 before comparing them. + */ +static int nlmclnt_cmp_addr(const struct nlm_host *host, + const struct sockaddr *sap) +{ + const struct in6_addr *addr1; + const struct in6_addr *addr2; + struct in6_addr addr1_mapped; + struct in6_addr addr2_mapped; + + addr1 = nlmclnt_map_v4addr(nlm_addr(host), &addr1_mapped); + if (likely(addr1 != NULL)) { + addr2 = nlmclnt_map_v4addr(sap, &addr2_mapped); + if (likely(addr2 != NULL)) + return ipv6_addr_equal(addr1, addr2); + } + + return 0; +} +#else /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */ +static int nlmclnt_cmp_addr(const struct nlm_host *host, + const struct sockaddr *sap) +{ + return nlm_cmp_addr(nlm_addr(host), sap); +} +#endif /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */ + /* * The server lockd has called us back to tell us the lock was granted */ @@ -166,7 +215,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock) */ if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid) continue; - if (!nlm_cmp_addr(nlm_addr(block->b_host), addr)) + if (!nlmclnt_cmp_addr(block->b_host, addr)) continue; if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0) continue; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index d1d1eb84679..618865b3128 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -3,7 +3,7 @@ * * Copyright (C) 1991, 1992 Linus Torvalds * - * Copyright (C) 1996 Gertjan van Wingerde (gertjan@cs.vu.nl) + * Copyright (C) 1996 Gertjan van Wingerde * Minix V2 fs support. * * Modified for 680x0 by Andreas Schwab diff --git a/fs/namei.c b/fs/namei.c index bbc15c23755..199317642ad 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -24,6 +24,7 @@ #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> @@ -850,6 +851,8 @@ static int __link_path_walk(const char *name, struct nameidata *nd) if (err == -EAGAIN) err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC); + if (!err) + err = ima_path_check(&nd->path, MAY_EXEC); if (err) break; @@ -1509,6 +1512,11 @@ int may_open(struct path *path, int acc_mode, int flag) error = inode_permission(inode, acc_mode); if (error) return error; + + error = ima_path_check(path, + acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC)); + if (error) + return error; /* * An append-only file must be opened in append mode for writing. */ diff --git a/fs/namespace.c b/fs/namespace.c index 06f8e63f6cb..f0e75309735 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -780,6 +780,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) { MNT_NOATIME, ",noatime" }, { MNT_NODIRATIME, ",nodiratime" }, { MNT_RELATIME, ",relatime" }, + { MNT_STRICTATIME, ",strictatime" }, { 0, NULL } }; const struct proc_fs_info *fs_infop; @@ -1919,6 +1920,9 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; + /* Default to relatime */ + mnt_flags |= MNT_RELATIME; + /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; @@ -1930,13 +1934,14 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; - if (flags & MS_RELATIME) - mnt_flags |= MNT_RELATIME; + if (flags & MS_STRICTATIME) + mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | - MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT); + MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | + MS_STRICTATIME); /* ... and get the mountpoint */ retval = kern_path(dir_name, LOOKUP_FOLLOW, &path); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9b728f3565a..574158ae239 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -255,6 +255,32 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, } return 0; } + +/* + * Test if two ip6 socket addresses refer to the same socket by + * comparing relevant fields. The padding bytes specifically, are not + * compared. sin6_flowinfo is not compared because it only affects QoS + * and sin6_scope_id is only compared if the address is "link local" + * because "link local" addresses need only be unique to a specific + * link. Conversely, ordinary unicast addresses might have different + * sin6_scope_id. + * + * The caller should ensure both socket addresses are AF_INET6. + */ +static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1; + const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2; + + if (!ipv6_addr_equal(&saddr1->sin6_addr, + &saddr1->sin6_addr)) + return 0; + if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL && + saddr1->sin6_scope_id != saddr2->sin6_scope_id) + return 0; + return saddr1->sin6_port == saddr2->sin6_port; +} #else static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1, const struct sockaddr_in *sa2) @@ -270,9 +296,52 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1, (const struct sockaddr_in *)sa2); } + +static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1, + const struct sockaddr * sa2) +{ + return 0; +} #endif /* + * Test if two ip4 socket addresses refer to the same socket, by + * comparing relevant fields. The padding bytes specifically, are + * not compared. + * + * The caller should ensure both socket addresses are AF_INET. + */ +static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1; + const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2; + + if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr) + return 0; + return saddr1->sin_port == saddr2->sin_port; +} + +/* + * Test if two socket addresses represent the same actual socket, + * by comparing (only) relevant fields. + */ +static int nfs_sockaddr_cmp(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + if (sa1->sa_family != sa2->sa_family) + return 0; + + switch (sa1->sa_family) { + case AF_INET: + return nfs_sockaddr_cmp_ip4(sa1, sa2); + case AF_INET6: + return nfs_sockaddr_cmp_ip6(sa1, sa2); + } + return 0; +} + +/* * Find a client by IP address and protocol version * - returns NULL if no such client */ @@ -344,8 +413,10 @@ struct nfs_client *nfs_find_client_next(struct nfs_client *clp) static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data) { struct nfs_client *clp; + const struct sockaddr *sap = data->addr; list_for_each_entry(clp, &nfs_client_list, cl_share_link) { + const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; /* Don't match clients that failed to initialise properly */ if (clp->cl_cons_state < 0) continue; @@ -358,7 +429,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat continue; /* Match the full socket address */ - if (memcmp(&clp->cl_addr, data->addr, sizeof(clp->cl_addr)) != 0) + if (!nfs_sockaddr_cmp(sap, clap)) continue; atomic_inc(&clp->cl_count); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e35c8199f82..672368f865c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1892,8 +1892,14 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) cache.cred = cred; cache.jiffies = jiffies; status = NFS_PROTO(inode)->access(inode, &cache); - if (status != 0) + if (status != 0) { + if (status == -ESTALE) { + nfs_zap_caches(inode); + if (!S_ISDIR(inode->i_mode)) + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + } return status; + } nfs_access_add_cache(inode, &cache); out: if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index cef62557c87..6bbf0e6daad 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -292,7 +292,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, { struct nfs_server *server = NFS_SERVER(inode); struct nfs_fattr fattr; - struct page *pages[NFSACL_MAXPAGES] = { }; + struct page *pages[NFSACL_MAXPAGES]; struct nfs3_setaclargs args = { .inode = inode, .mask = NFS_ACL, @@ -303,7 +303,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, .rpc_argp = &args, .rpc_resp = &fattr, }; - int status, count; + int status; status = -EOPNOTSUPP; if (!nfs_server_capable(inode, NFS_CAP_ACLS)) @@ -319,6 +319,20 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, if (S_ISDIR(inode->i_mode)) { args.mask |= NFS_DFACL; args.acl_default = dfacl; + args.len = nfsacl_size(acl, dfacl); + } else + args.len = nfsacl_size(acl, NULL); + + if (args.len > NFS_ACL_INLINE_BUFSIZE) { + unsigned int npages = 1 + ((args.len - 1) >> PAGE_SHIFT); + + status = -ENOMEM; + do { + args.pages[args.npages] = alloc_page(GFP_KERNEL); + if (args.pages[args.npages] == NULL) + goto out_freepages; + args.npages++; + } while (args.npages < npages); } dprintk("NFS call setacl\n"); @@ -329,10 +343,6 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, nfs_zap_acl_cache(inode); dprintk("NFS reply setacl: %d\n", status); - /* pages may have been allocated at the xdr layer. */ - for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++) - __free_page(args.pages[count]); - switch (status) { case 0: status = nfs_refresh_inode(inode, &fattr); @@ -346,6 +356,11 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, case -ENOTSUPP: status = -EOPNOTSUPP; } +out_freepages: + while (args.npages != 0) { + args.npages--; + __free_page(args.pages[args.npages]); + } out: return status; } diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 11cdddec143..6cdeacffde4 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -82,8 +82,10 @@ #define NFS3_commitres_sz (1+NFS3_wcc_data_sz+2) #define ACL3_getaclargs_sz (NFS3_fh_sz+1) -#define ACL3_setaclargs_sz (NFS3_fh_sz+1+2*(2+5*3)) -#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+2*(2+5*3)) +#define ACL3_setaclargs_sz (NFS3_fh_sz+1+ \ + XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) +#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+ \ + XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) #define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) /* @@ -703,28 +705,18 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p, struct nfs3_setaclargs *args) { struct xdr_buf *buf = &req->rq_snd_buf; - unsigned int base, len_in_head, len = nfsacl_size( - (args->mask & NFS_ACL) ? args->acl_access : NULL, - (args->mask & NFS_DFACL) ? args->acl_default : NULL); - int count, err; + unsigned int base; + int err; p = xdr_encode_fhandle(p, NFS_FH(args->inode)); *p++ = htonl(args->mask); - base = (char *)p - (char *)buf->head->iov_base; - /* put as much of the acls into head as possible. */ - len_in_head = min_t(unsigned int, buf->head->iov_len - base, len); - len -= len_in_head; - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p + (len_in_head >> 2)); - - for (count = 0; (count << PAGE_SHIFT) < len; count++) { - args->pages[count] = alloc_page(GFP_KERNEL); - if (!args->pages[count]) { - while (count) - __free_page(args->pages[--count]); - return -ENOMEM; - } - } - xdr_encode_pages(buf, args->pages, 0, len); + req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); + base = req->rq_slen; + + if (args->npages != 0) + xdr_encode_pages(buf, args->pages, 0, args->len); + else + req->rq_slen += args->len; err = nfsacl_encode(buf, base, args->inode, (args->mask & NFS_ACL) ? diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 30befc39b3c..2a2a0a7143a 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -21,7 +21,9 @@ #define NFSDBG_FACILITY NFSDBG_VFS /* - * Check if fs_root is valid + * Convert the NFSv4 pathname components into a standard posix path. + * + * Note that the resulting string will be placed at the end of the buffer */ static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname, char *buffer, ssize_t buflen) @@ -99,21 +101,20 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, { struct vfsmount *mnt = ERR_PTR(-ENOENT); char *mnt_path; - int page2len; + unsigned int maxbuflen; unsigned int s; mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE); if (IS_ERR(mnt_path)) return mnt; mountdata->mnt_path = mnt_path; - page2 += strlen(mnt_path) + 1; - page2len = PAGE_SIZE - strlen(mnt_path) - 1; + maxbuflen = mnt_path - 1 - page2; for (s = 0; s < location->nservers; s++) { const struct nfs4_string *buf = &location->servers[s]; struct sockaddr_storage addr; - if (buf->len <= 0 || buf->len >= PAGE_SIZE) + if (buf->len <= 0 || buf->len >= maxbuflen) continue; mountdata->addr = (struct sockaddr *)&addr; @@ -126,8 +127,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, continue; nfs_set_port(mountdata->addr, NFS_PORT); - strncpy(page2, buf->data, page2len); - page2[page2len] = '\0'; + memcpy(page2, buf->data, buf->len); + page2[buf->len] = '\0'; mountdata->hostname = page2; snprintf(page, PAGE_SIZE, "%s:%s", diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index f65953be39c..9250067943d 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2596,6 +2596,7 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, + [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 3a9e5deed74..19e3a96aa02 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -176,7 +176,8 @@ static int ocfs2_dinode_insert_check(struct inode *inode, BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL); mlog_bug_on_msg(!ocfs2_sparse_alloc(osb) && - (OCFS2_I(inode)->ip_clusters != rec->e_cpos), + (OCFS2_I(inode)->ip_clusters != + le32_to_cpu(rec->e_cpos)), "Device %s, asking for sparse allocation: inode %llu, " "cpos %u, clusters %u\n", osb->dev_str, diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index a067a6cffb0..8e1709a679b 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -227,7 +227,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page, size = i_size_read(inode); if (size > PAGE_CACHE_SIZE || - size > ocfs2_max_inline_data(inode->i_sb)) { + size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) { ocfs2_error(inode->i_sb, "Inode %llu has with inline data has bad size: %Lu", (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -1555,6 +1555,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping, int ret, written = 0; loff_t end = pos + len; struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_dinode *di = NULL; mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n", (unsigned long long)oi->ip_blkno, len, (unsigned long long)pos, @@ -1587,7 +1588,9 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping, /* * Check whether the write can fit. */ - if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb)) + di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; + if (mmap_page || + end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) return 0; do_inline_write: diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 084aba86c3b..4b11762f249 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -532,7 +532,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL); - fe->id2.i_data.id_count = cpu_to_le16(ocfs2_max_inline_data(osb->sb)); + fe->id2.i_data.id_count = cpu_to_le16( + ocfs2_max_inline_data_with_xattr(osb->sb, fe)); } else { fel = &fe->id2.i_list; fel->l_tree_depth = 0; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index c7ae45aaa36..2332ef740f4 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -1070,12 +1070,6 @@ static inline int ocfs2_fast_symlink_chars(struct super_block *sb) offsetof(struct ocfs2_dinode, id2.i_symlink); } -static inline int ocfs2_max_inline_data(struct super_block *sb) -{ - return sb->s_blocksize - - offsetof(struct ocfs2_dinode, id2.i_data.id_data); -} - static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb, struct ocfs2_dinode *di) { diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 4ddd788add6..2563df89fc2 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -547,8 +547,12 @@ int ocfs2_calc_xattr_init(struct inode *dir, * when blocksize = 512, may reserve one more cluser for * xattr bucket, otherwise reserve one metadata block * for them is ok. + * If this is a new directory with inline data, + * we choose to reserve the entire inline area for + * directory contents and force an external xattr block. */ if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE || + (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) || (s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) { ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac); if (ret) { @@ -4791,19 +4795,33 @@ static int ocfs2_xattr_bucket_set_value_outside(struct inode *inode, char *val, int value_len) { - int offset; + int ret, offset, block_off; struct ocfs2_xattr_value_root *xv; struct ocfs2_xattr_entry *xe = xs->here; + struct ocfs2_xattr_header *xh = bucket_xh(xs->bucket); + void *base; BUG_ON(!xs->base || !xe || ocfs2_xattr_is_local(xe)); - offset = le16_to_cpu(xe->xe_name_offset) + - OCFS2_XATTR_SIZE(xe->xe_name_len); + ret = ocfs2_xattr_bucket_get_name_value(inode, xh, + xe - xh->xh_entries, + &block_off, + &offset); + if (ret) { + mlog_errno(ret); + goto out; + } - xv = (struct ocfs2_xattr_value_root *)(xs->base + offset); + base = bucket_block(xs->bucket, block_off); + xv = (struct ocfs2_xattr_value_root *)(base + offset + + OCFS2_XATTR_SIZE(xe->xe_name_len)); - return __ocfs2_xattr_set_value_outside(inode, handle, - xv, val, value_len); + ret = __ocfs2_xattr_set_value_outside(inode, handle, + xv, val, value_len); + if (ret) + mlog_errno(ret); +out: + return ret; } static int ocfs2_rm_xattr_cluster(struct inode *inode, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 6d720243f5f..38e337d51ce 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -400,7 +400,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ - pdev->uevent_suppress = 1; + dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; @@ -410,7 +410,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, if (!p->holder_dir) goto out_del; - pdev->uevent_suppress = 0; + dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) @@ -422,7 +422,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk supresses it */ - if (!ddev->uevent_suppress) + if (!dev_get_uevent_suppress(pdev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return p; @@ -455,7 +455,7 @@ void register_disk(struct gendisk *disk) dev_set_name(ddev, disk->disk_name); /* delay uevents, until we scanned partition table */ - ddev->uevent_suppress = 1; + dev_set_uevent_suppress(ddev, 1); if (device_add(ddev)) return; @@ -490,7 +490,7 @@ void register_disk(struct gendisk *disk) exit: /* announce disk after possible partitions are created */ - ddev->uevent_suppress = 0; + dev_set_uevent_suppress(ddev, 0); kobject_uevent(&ddev->kobj, KOBJ_ADD); /* announce possible partitions */ diff --git a/fs/pipe.c b/fs/pipe.c index 3a48ba5179d..14f502b89cf 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -699,12 +699,12 @@ pipe_rdwr_fasync(int fd, struct file *filp, int on) int retval; mutex_lock(&inode->i_mutex); - retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); - - if (retval >= 0) + if (retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); - + if (retval < 0) /* this can happen only if on == T */ + fasync_helper(-1, filp, 0, &pipe->fasync_readers); + } mutex_unlock(&inode->i_mutex); if (retval < 0) diff --git a/fs/proc/base.c b/fs/proc/base.c index 0c9de19a163..beaa0ce3b82 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3066,7 +3066,6 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi int retval = -ENOENT; ino_t ino; int tid; - unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ struct pid_namespace *ns; task = get_proc_task(inode); @@ -3083,18 +3082,18 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi goto out_no_task; retval = 0; - switch (pos) { + switch ((unsigned long)filp->f_pos) { case 0: ino = inode->i_ino; - if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0) + if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) < 0) goto out; - pos++; + filp->f_pos++; /* fall through */ case 1: ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0) + if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) < 0) goto out; - pos++; + filp->f_pos++; /* fall through */ } @@ -3104,9 +3103,9 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi ns = filp->f_dentry->d_sb->s_fs_info; tid = (int)filp->f_version; filp->f_version = 0; - for (task = first_tid(leader, tid, pos - 2, ns); + for (task = first_tid(leader, tid, filp->f_pos - 2, ns); task; - task = next_tid(task), pos++) { + task = next_tid(task), filp->f_pos++) { tid = task_pid_nr_ns(task, ns); if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) { /* returning this tgid failed, save it as the first @@ -3117,7 +3116,6 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi } } out: - filp->f_pos = pos; put_task_struct(leader); out_no_task: return retval; diff --git a/fs/proc/page.c b/fs/proc/page.c index 2d1345112a4..e9983837d08 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -80,7 +80,7 @@ static const struct file_operations proc_kpagecount_operations = { #define KPF_RECLAIM 9 #define KPF_BUDDY 10 -#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos) +#define kpf_copy_bit(flags, dstpos, srcpos) (((flags >> srcpos) & 1) << dstpos) static ssize_t kpageflags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index b9b567a2837..5d7c7ececa6 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -114,6 +114,9 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) if (!pagevec_add(&lru_pvec, page)) __pagevec_lru_add_file(&lru_pvec); + /* prevent the page from being discarded on memory pressure */ + SetPageDirty(page); + unlock_page(page); } @@ -126,6 +129,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) return -EFBIG; add_error: + pagevec_lru_add_file(&lru_pvec); page_cache_release(pages + loop); for (loop++; loop < npages; loop++) __free_page(pages + loop); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index c837dfc2b3c..2a796031034 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -80,7 +80,7 @@ static struct buffer_head *get_block_length(struct super_block *sb, * generated a larger block - this does occasionally happen with zlib). */ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, - int length, u64 *next_index, int srclength) + int length, u64 *next_index, int srclength, int pages) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct buffer_head **bh; @@ -184,7 +184,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, offset = 0; } - if (msblk->stream.avail_out == 0) { + if (msblk->stream.avail_out == 0 && page < pages) { msblk->stream.next_out = buffer[page++]; msblk->stream.avail_out = PAGE_CACHE_SIZE; } @@ -201,25 +201,20 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, zlib_init = 1; } - zlib_err = zlib_inflate(&msblk->stream, Z_NO_FLUSH); + zlib_err = zlib_inflate(&msblk->stream, Z_SYNC_FLUSH); if (msblk->stream.avail_in == 0 && k < b) put_bh(bh[k++]); } while (zlib_err == Z_OK); if (zlib_err != Z_STREAM_END) { - ERROR("zlib_inflate returned unexpected result" - " 0x%x, srclength %d, avail_in %d," - " avail_out %d\n", zlib_err, srclength, - msblk->stream.avail_in, - msblk->stream.avail_out); + ERROR("zlib_inflate error, data probably corrupt\n"); goto release_mutex; } zlib_err = zlib_inflateEnd(&msblk->stream); if (zlib_err != Z_OK) { - ERROR("zlib_inflateEnd returned unexpected result 0x%x," - " srclength %d\n", zlib_err, srclength); + ERROR("zlib_inflate error, data probably corrupt\n"); goto release_mutex; } length = msblk->stream.total_out; @@ -268,7 +263,8 @@ block_release: put_bh(bh[k]); read_failure: - ERROR("sb_bread failed reading block 0x%llx\n", cur_index); + ERROR("squashfs_read_data failed to read block 0x%llx\n", + (unsigned long long) index); kfree(bh); return -EIO; } diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index f29eda16d25..1c4739e33af 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -119,7 +119,7 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, entry->length = squashfs_read_data(sb, entry->data, block, length, &entry->next_index, - cache->block_size); + cache->block_size, cache->pages); spin_lock(&cache->lock); @@ -406,7 +406,7 @@ int squashfs_read_table(struct super_block *sb, void *buffer, u64 block, for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) data[i] = buffer; res = squashfs_read_data(sb, data, block, length | - SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length); + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages); kfree(data); return res; } diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 7a63398bb85..9101dbde39e 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -133,7 +133,8 @@ int squashfs_read_inode(struct inode *inode, long long ino) type = le16_to_cpu(sqshb_ino->inode_type); switch (type) { case SQUASHFS_REG_TYPE: { - unsigned int frag_offset, frag_size, frag; + unsigned int frag_offset, frag; + int frag_size; u64 frag_blk; struct squashfs_reg_inode *sqsh_ino = &squashfs_ino.reg; @@ -175,7 +176,8 @@ int squashfs_read_inode(struct inode *inode, long long ino) break; } case SQUASHFS_LREG_TYPE: { - unsigned int frag_offset, frag_size, frag; + unsigned int frag_offset, frag; + int frag_size; u64 frag_blk; struct squashfs_lreg_inode *sqsh_ino = &squashfs_ino.lreg; diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 6b2515d027d..0e9feb6adf7 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -34,7 +34,7 @@ static inline struct squashfs_inode_info *squashfs_i(struct inode *inode) /* block.c */ extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *, - int); + int, int); /* cache.c */ extern struct squashfs_cache *squashfs_cache_init(char *, int, int); diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 071df5b5b49..681ec0d8379 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -389,7 +389,7 @@ static int __init init_squashfs_fs(void) return err; } - printk(KERN_INFO "squashfs: version 4.0 (2009/01/03) " + printk(KERN_INFO "squashfs: version 4.0 (2009/01/31) " "Phillip Lougher\n"); return 0; diff --git a/fs/super.c b/fs/super.c index 8349ed6b141..6ce501447ad 100644 --- a/fs/super.c +++ b/fs/super.c @@ -371,8 +371,10 @@ retry: continue; if (!grab_super(old)) goto retry; - if (s) + if (s) { + up_write(&s->s_umount); destroy_super(s); + } return old; } } @@ -387,6 +389,7 @@ retry: err = set(s, data); if (err) { spin_unlock(&sb_lock); + up_write(&s->s_umount); destroy_super(s); return ERR_PTR(err); } diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index f2c478c3424..07703d3ff4a 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -21,15 +21,28 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include "sysfs.h" +/* + * There's one bin_buffer for each open file. + * + * filp->private_data points to bin_buffer and + * sysfs_dirent->s_bin_attr.buffers points to a the bin_buffer s + * sysfs_dirent->s_bin_attr.buffers is protected by sysfs_bin_lock + */ +static DEFINE_MUTEX(sysfs_bin_lock); + struct bin_buffer { - struct mutex mutex; - void *buffer; - int mmapped; + struct mutex mutex; + void *buffer; + int mmapped; + struct vm_operations_struct *vm_ops; + struct file *file; + struct hlist_node list; }; static int @@ -168,6 +181,175 @@ out_free: return count; } +static void bin_vma_open(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + + if (!bb->vm_ops || !bb->vm_ops->open) + return; + + if (!sysfs_get_active_two(attr_sd)) + return; + + bb->vm_ops->open(vma); + + sysfs_put_active_two(attr_sd); +} + +static void bin_vma_close(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + + if (!bb->vm_ops || !bb->vm_ops->close) + return; + + if (!sysfs_get_active_two(attr_sd)) + return; + + bb->vm_ops->close(vma); + + sysfs_put_active_two(attr_sd); +} + +static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + int ret; + + if (!bb->vm_ops || !bb->vm_ops->fault) + return VM_FAULT_SIGBUS; + + if (!sysfs_get_active_two(attr_sd)) + return VM_FAULT_SIGBUS; + + ret = bb->vm_ops->fault(vma, vmf); + + sysfs_put_active_two(attr_sd); + return ret; +} + +static int bin_page_mkwrite(struct vm_area_struct *vma, struct page *page) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + int ret; + + if (!bb->vm_ops) + return -EINVAL; + + if (!bb->vm_ops->page_mkwrite) + return 0; + + if (!sysfs_get_active_two(attr_sd)) + return -EINVAL; + + ret = bb->vm_ops->page_mkwrite(vma, page); + + sysfs_put_active_two(attr_sd); + return ret; +} + +static int bin_access(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + int ret; + + if (!bb->vm_ops || !bb->vm_ops->access) + return -EINVAL; + + if (!sysfs_get_active_two(attr_sd)) + return -EINVAL; + + ret = bb->vm_ops->access(vma, addr, buf, len, write); + + sysfs_put_active_two(attr_sd); + return ret; +} + +#ifdef CONFIG_NUMA +static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + int ret; + + if (!bb->vm_ops || !bb->vm_ops->set_policy) + return 0; + + if (!sysfs_get_active_two(attr_sd)) + return -EINVAL; + + ret = bb->vm_ops->set_policy(vma, new); + + sysfs_put_active_two(attr_sd); + return ret; +} + +static struct mempolicy *bin_get_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + struct mempolicy *pol; + + if (!bb->vm_ops || !bb->vm_ops->get_policy) + return vma->vm_policy; + + if (!sysfs_get_active_two(attr_sd)) + return vma->vm_policy; + + pol = bb->vm_ops->get_policy(vma, addr); + + sysfs_put_active_two(attr_sd); + return pol; +} + +static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, + const nodemask_t *to, unsigned long flags) +{ + struct file *file = vma->vm_file; + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + int ret; + + if (!bb->vm_ops || !bb->vm_ops->migrate) + return 0; + + if (!sysfs_get_active_two(attr_sd)) + return 0; + + ret = bb->vm_ops->migrate(vma, from, to, flags); + + sysfs_put_active_two(attr_sd); + return ret; +} +#endif + +static struct vm_operations_struct bin_vm_ops = { + .open = bin_vma_open, + .close = bin_vma_close, + .fault = bin_fault, + .page_mkwrite = bin_page_mkwrite, + .access = bin_access, +#ifdef CONFIG_NUMA + .set_policy = bin_set_policy, + .get_policy = bin_get_policy, + .migrate = bin_migrate, +#endif +}; + static int mmap(struct file *file, struct vm_area_struct *vma) { struct bin_buffer *bb = file->private_data; @@ -179,18 +361,37 @@ static int mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&bb->mutex); /* need attr_sd for attr, its parent for kobj */ + rc = -ENODEV; if (!sysfs_get_active_two(attr_sd)) - return -ENODEV; + goto out_unlock; rc = -EINVAL; - if (attr->mmap) - rc = attr->mmap(kobj, attr, vma); + if (!attr->mmap) + goto out_put; + + rc = attr->mmap(kobj, attr, vma); + if (rc) + goto out_put; - if (rc == 0 && !bb->mmapped) - bb->mmapped = 1; - else - sysfs_put_active_two(attr_sd); + /* + * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() + * to satisfy versions of X which crash if the mmap fails: that + * substitutes a new vm_file, and we don't then want bin_vm_ops. + */ + if (vma->vm_file != file) + goto out_put; + rc = -EINVAL; + if (bb->mmapped && bb->vm_ops != vma->vm_ops) + goto out_put; + + rc = 0; + bb->mmapped = 1; + bb->vm_ops = vma->vm_ops; + vma->vm_ops = &bin_vm_ops; +out_put: + sysfs_put_active_two(attr_sd); +out_unlock: mutex_unlock(&bb->mutex); return rc; @@ -223,8 +424,13 @@ static int open(struct inode * inode, struct file * file) goto err_out; mutex_init(&bb->mutex); + bb->file = file; file->private_data = bb; + mutex_lock(&sysfs_bin_lock); + hlist_add_head(&bb->list, &attr_sd->s_bin_attr.buffers); + mutex_unlock(&sysfs_bin_lock); + /* open succeeded, put active references */ sysfs_put_active_two(attr_sd); return 0; @@ -237,11 +443,12 @@ static int open(struct inode * inode, struct file * file) static int release(struct inode * inode, struct file * file) { - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct bin_buffer *bb = file->private_data; - if (bb->mmapped) - sysfs_put_active_two(attr_sd); + mutex_lock(&sysfs_bin_lock); + hlist_del(&bb->list); + mutex_unlock(&sysfs_bin_lock); + kfree(bb->buffer); kfree(bb); return 0; @@ -256,6 +463,26 @@ const struct file_operations bin_fops = { .release = release, }; + +void unmap_bin_file(struct sysfs_dirent *attr_sd) +{ + struct bin_buffer *bb; + struct hlist_node *tmp; + + if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR) + return; + + mutex_lock(&sysfs_bin_lock); + + hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) { + struct inode *inode = bb->file->f_path.dentry->d_inode; + + unmap_mapping_range(inode->i_mapping, 0, 0, 1); + } + + mutex_unlock(&sysfs_bin_lock); +} + /** * sysfs_create_bin_file - create binary file for object. * @kobj: object. diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 82d3b79d0e0..66aeb4fff0c 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -434,6 +434,26 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) } /** + * sysfs_pathname - return full path to sysfs dirent + * @sd: sysfs_dirent whose path we want + * @path: caller allocated buffer + * + * Gives the name "/" to the sysfs_root entry; any path returned + * is relative to wherever sysfs is mounted. + * + * XXX: does no error checking on @path size + */ +static char *sysfs_pathname(struct sysfs_dirent *sd, char *path) +{ + if (sd->s_parent) { + sysfs_pathname(sd->s_parent, path); + strcat(path, "/"); + } + strcat(path, sd->s_name); + return path; +} + +/** * sysfs_add_one - add sysfs_dirent to parent * @acxt: addrm context to use * @sd: sysfs_dirent to be added @@ -458,8 +478,16 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) int ret; ret = __sysfs_add_one(acxt, sd); - WARN(ret == -EEXIST, KERN_WARNING "sysfs: duplicate filename '%s' " - "can not be created\n", sd->s_name); + if (ret == -EEXIST) { + char *path = kzalloc(PATH_MAX, GFP_KERNEL); + WARN(1, KERN_WARNING + "sysfs: cannot create duplicate filename '%s'\n", + (path == NULL) ? sd->s_name : + strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"), + sd->s_name)); + kfree(path); + } + return ret; } @@ -581,6 +609,7 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt) sysfs_drop_dentry(sd); sysfs_deactivate(sd); + unmap_bin_file(sd); sysfs_put(sd); } } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 1f4a3f87726..289c43a4726 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -659,13 +659,16 @@ void sysfs_remove_file_from_group(struct kobject *kobj, EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); struct sysfs_schedule_callback_struct { - struct kobject *kobj; + struct list_head workq_list; + struct kobject *kobj; void (*func)(void *); void *data; struct module *owner; struct work_struct work; }; +static DEFINE_MUTEX(sysfs_workq_mutex); +static LIST_HEAD(sysfs_workq); static void sysfs_schedule_callback_work(struct work_struct *work) { struct sysfs_schedule_callback_struct *ss = container_of(work, @@ -674,6 +677,9 @@ static void sysfs_schedule_callback_work(struct work_struct *work) (ss->func)(ss->data); kobject_put(ss->kobj); module_put(ss->owner); + mutex_lock(&sysfs_workq_mutex); + list_del(&ss->workq_list); + mutex_unlock(&sysfs_workq_mutex); kfree(ss); } @@ -695,15 +701,25 @@ static void sysfs_schedule_callback_work(struct work_struct *work) * until @func returns. * * Returns 0 if the request was submitted, -ENOMEM if storage could not - * be allocated, -ENODEV if a reference to @owner isn't available. + * be allocated, -ENODEV if a reference to @owner isn't available, + * -EAGAIN if a callback has already been scheduled for @kobj. */ int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), void *data, struct module *owner) { - struct sysfs_schedule_callback_struct *ss; + struct sysfs_schedule_callback_struct *ss, *tmp; if (!try_module_get(owner)) return -ENODEV; + + mutex_lock(&sysfs_workq_mutex); + list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list) + if (ss->kobj == kobj) { + mutex_unlock(&sysfs_workq_mutex); + return -EAGAIN; + } + mutex_unlock(&sysfs_workq_mutex); + ss = kmalloc(sizeof(*ss), GFP_KERNEL); if (!ss) { module_put(owner); @@ -715,6 +731,10 @@ int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), ss->data = data; ss->owner = owner; INIT_WORK(&ss->work, sysfs_schedule_callback_work); + INIT_LIST_HEAD(&ss->workq_list); + mutex_lock(&sysfs_workq_mutex); + list_add_tail(&ss->workq_list, &sysfs_workq); + mutex_unlock(&sysfs_workq_mutex); schedule_work(&ss->work); return 0; } diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index dfa3d94cfc7..555f0ff988d 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -147,6 +147,7 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) { struct bin_attribute *bin_attr; + inode->i_private = sysfs_get(sd); inode->i_mapping->a_ops = &sysfs_aops; inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; inode->i_op = &sysfs_inode_operations; @@ -214,6 +215,22 @@ struct inode * sysfs_get_inode(struct sysfs_dirent *sd) return inode; } +/* + * The sysfs_dirent serves as both an inode and a directory entry for sysfs. + * To prevent the sysfs inode numbers from being freed prematurely we take a + * reference to sysfs_dirent from the sysfs inode. A + * super_operations.delete_inode() implementation is needed to drop that + * reference upon inode destruction. + */ +void sysfs_delete_inode(struct inode *inode) +{ + struct sysfs_dirent *sd = inode->i_private; + + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + sysfs_put(sd); +} + int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name) { struct sysfs_addrm_cxt acxt; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index ab343e371d6..49749955cca 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -17,11 +17,10 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/module.h> +#include <linux/magic.h> #include "sysfs.h" -/* Random magic number */ -#define SYSFS_MAGIC 0x62656572 static struct vfsmount *sysfs_mount; struct super_block * sysfs_sb = NULL; @@ -30,6 +29,7 @@ struct kmem_cache *sysfs_dir_cachep; static const struct super_operations sysfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, + .delete_inode = sysfs_delete_inode, }; struct sysfs_dirent sysfs_root = { @@ -53,7 +53,9 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) sysfs_sb = sb; /* get root inode, initialize and unlock it */ + mutex_lock(&sysfs_mutex); inode = sysfs_get_inode(&sysfs_root); + mutex_unlock(&sysfs_mutex); if (!inode) { pr_debug("sysfs: could not get root inode\n"); return -ENOMEM; diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 93c6d6b27c4..3fa0d98481e 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -28,6 +28,7 @@ struct sysfs_elem_attr { struct sysfs_elem_bin_attr { struct bin_attribute *bin_attr; + struct hlist_head buffers; }; /* @@ -145,6 +146,7 @@ static inline void __sysfs_put(struct sysfs_dirent *sd) * inode.c */ struct inode *sysfs_get_inode(struct sysfs_dirent *sd); +void sysfs_delete_inode(struct inode *inode); int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name); int sysfs_inode_init(void); @@ -163,6 +165,7 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd, * bin.c */ extern const struct file_operations bin_fops; +void unmap_bin_file(struct sysfs_dirent *attr_sd); /* * symlink.c diff --git a/fs/ufs/super.c b/fs/ufs/super.c index e65212dfb60..261a1c2f22d 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -41,7 +41,7 @@ * Stefan Reinauer <stepan@home.culture.mipt.ru> * * Module usage counts added on 96/04/29 by - * Gertjan van Wingerde <gertjan@cs.vu.nl> + * Gertjan van Wingerde <gwingerde@gmail.com> * * Clean swab support on 19970406 by * Francois-Rene Rideau <fare@tunes.org> diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index cb329edc925..aa1016bb913 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -34,6 +34,12 @@ #include <linux/backing-dev.h> #include <linux/freezer.h> +#include "xfs_sb.h" +#include "xfs_inum.h" +#include "xfs_ag.h" +#include "xfs_dmapi.h" +#include "xfs_mount.h" + static kmem_zone_t *xfs_buf_zone; STATIC int xfsbufd(void *); STATIC int xfsbufd_wakeup(int, gfp_t); @@ -1435,10 +1441,12 @@ xfs_unregister_buftarg( void xfs_free_buftarg( - xfs_buftarg_t *btp) + struct xfs_mount *mp, + struct xfs_buftarg *btp) { xfs_flush_buftarg(btp, 1); - xfs_blkdev_issue_flush(btp); + if (mp->m_flags & XFS_MOUNT_BARRIER) + xfs_blkdev_issue_flush(btp); xfs_free_bufhash(btp); iput(btp->bt_mapping->host); diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index 288ae7c4c80..9b4d666ad31 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -413,7 +413,7 @@ static inline int XFS_bwrite(xfs_buf_t *bp) * Handling of buftargs. */ extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int); -extern void xfs_free_buftarg(xfs_buftarg_t *); +extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *); extern void xfs_wait_buftarg(xfs_buftarg_t *); extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int); extern int xfs_flush_buftarg(xfs_buftarg_t *, int); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index c71e226da7f..32ae5028e96 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -734,15 +734,15 @@ xfs_close_devices( { if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { struct block_device *logdev = mp->m_logdev_targp->bt_bdev; - xfs_free_buftarg(mp->m_logdev_targp); + xfs_free_buftarg(mp, mp->m_logdev_targp); xfs_blkdev_put(logdev); } if (mp->m_rtdev_targp) { struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev; - xfs_free_buftarg(mp->m_rtdev_targp); + xfs_free_buftarg(mp, mp->m_rtdev_targp); xfs_blkdev_put(rtdev); } - xfs_free_buftarg(mp->m_ddev_targp); + xfs_free_buftarg(mp, mp->m_ddev_targp); } /* @@ -811,9 +811,9 @@ xfs_open_devices( out_free_rtdev_targ: if (mp->m_rtdev_targp) - xfs_free_buftarg(mp->m_rtdev_targp); + xfs_free_buftarg(mp, mp->m_rtdev_targp); out_free_ddev_targ: - xfs_free_buftarg(mp->m_ddev_targp); + xfs_free_buftarg(mp, mp->m_ddev_targp); out_close_rtdev: if (rtdev) xfs_blkdev_put(rtdev); diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index e2fb6210d4c..478e587087f 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -246,9 +246,6 @@ xfs_iget_cache_miss( goto out_destroy; } - if (lock_flags) - xfs_ilock(ip, lock_flags); - /* * Preload the radix tree so we can insert safely under the * write spinlock. Note that we cannot sleep inside the preload @@ -256,7 +253,16 @@ xfs_iget_cache_miss( */ if (radix_tree_preload(GFP_KERNEL)) { error = EAGAIN; - goto out_unlock; + goto out_destroy; + } + + /* + * Because the inode hasn't been added to the radix-tree yet it can't + * be found by another thread, so we can do the non-sleeping lock here. + */ + if (lock_flags) { + if (!xfs_ilock_nowait(ip, lock_flags)) + BUG(); } mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1); @@ -284,7 +290,6 @@ xfs_iget_cache_miss( out_preload_end: write_unlock(&pag->pag_ici_lock); radix_tree_preload_end(); -out_unlock: if (lock_flags) xfs_iunlock(ip, lock_flags); out_destroy: diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index b1047de2fff..61af610d79b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1455,10 +1455,19 @@ xlog_recover_add_to_trans( item = item->ri_prev; if (item->ri_total == 0) { /* first region to be added */ - item->ri_total = in_f->ilf_size; - ASSERT(item->ri_total <= XLOG_MAX_REGIONS_IN_ITEM); - item->ri_buf = kmem_zalloc((item->ri_total * - sizeof(xfs_log_iovec_t)), KM_SLEEP); + if (in_f->ilf_size == 0 || + in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) { + xlog_warn( + "XFS: bad number of regions (%d) in inode log format", + in_f->ilf_size); + ASSERT(0); + return XFS_ERROR(EIO); + } + + item->ri_total = in_f->ilf_size; + item->ri_buf = + kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t), + KM_SLEEP); } ASSERT(item->ri_total > item->ri_cnt); /* Description region is ri_buf[0] */ |