diff options
Diffstat (limited to 'fs')
174 files changed, 5603 insertions, 1286 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 7385e54be4b9..6b40fd8d719e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -67,6 +67,7 @@ source "fs/quota/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" +source "fs/overlayfs/Kconfig" menu "Caches" diff --git a/fs/Makefile b/fs/Makefile index 47ac07bb4acc..b5954404e02d 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ +obj-$(CONFIG_OVERLAY_FS) += overlayfs/ obj-$(CONFIG_UDF_FS) += udf/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_OMFS_FS) += omfs/ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 529300327f45..5479af6de6ce 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx); static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_release(struct dentry *dentry); -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl); @@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx) * - if afs_dir_iterate_block() spots this function, it'll pass the FID * uniquifier through dtype */ -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, - loff_t fpos, u64 ino, unsigned dtype) +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, + int nlen, loff_t fpos, u64 ino, unsigned dtype) { - struct afs_lookup_cookie *cookie = _cookie; + struct afs_lookup_cookie *cookie = + container_of(ctx, struct afs_lookup_cookie, ctx); _enter("{%s,%u},%s,%u,,%llu,%u", cookie->name.name, cookie->name.len, name, nlen, @@ -141,6 +141,7 @@ struct kioctx { struct { unsigned tail; + unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; @@ -164,6 +165,15 @@ static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; +/* Backing dev info for aio fs. + * -no dirty page accounting or writeback happens + */ +static struct backing_dev_info aio_fs_backing_dev_info = { + .name = "aiofs", + .state = 0, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY, +}; + static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct qstr this = QSTR_INIT("[aio]", 5); @@ -175,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; + inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info; inode->i_size = PAGE_SIZE * nr_pages; path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); @@ -220,6 +231,9 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); + if (bdi_init(&aio_fs_backing_dev_info)) + panic("Failed to init aio fs backing dev info."); + kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); @@ -281,11 +295,6 @@ static const struct file_operations aio_ring_fops = { .mmap = aio_ring_mmap, }; -static int aio_set_page_dirty(struct page *page) -{ - return 0; -} - #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migratepage(struct address_space *mapping, struct page *new, struct page *old, enum migrate_mode mode) @@ -357,7 +366,7 @@ out: #endif static const struct address_space_operations aio_ctx_aops = { - .set_page_dirty = aio_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, #if IS_ENABLED(CONFIG_MIGRATION) .migratepage = aio_migratepage, #endif @@ -412,7 +421,6 @@ static int aio_setup_ring(struct kioctx *ctx) pr_debug("pid(%d) page[%d]->count=%d\n", current->pid, i, page_count(page)); SetPageUptodate(page); - SetPageDirty(page); unlock_page(page); ctx->ring_pages[i] = page; @@ -711,6 +719,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: + atomic_set(&ctx->dead, 1); + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); @@ -796,6 +807,9 @@ void exit_aio(struct mm_struct *mm) unsigned i = 0; while (1) { + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); @@ -823,7 +837,10 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx, NULL); + kill_ioctx(mm, ctx, &requests_done); + + /* Wait until all IO for the context are done. */ + wait_for_completion(&requests_done); } } @@ -880,6 +897,68 @@ out: return ret; } +/* refill_reqs_available + * Updates the reqs_available reference counts used for tracking the + * number of free slots in the completion ring. This can be called + * from aio_complete() (to optimistically update reqs_available) or + * from aio_get_req() (the we're out of events case). It must be + * called holding ctx->completion_lock. + */ +static void refill_reqs_available(struct kioctx *ctx, unsigned head, + unsigned tail) +{ + unsigned events_in_ring, completed; + + /* Clamp head since userland can write to it. */ + head %= ctx->nr_events; + if (head <= tail) + events_in_ring = tail - head; + else + events_in_ring = ctx->nr_events - (head - tail); + + completed = ctx->completed_events; + if (events_in_ring < completed) + completed -= events_in_ring; + else + completed = 0; + + if (!completed) + return; + + ctx->completed_events -= completed; + put_reqs_available(ctx, completed); +} + +/* user_refill_reqs_available + * Called to refill reqs_available when aio_get_req() encounters an + * out of space in the completion ring. + */ +static void user_refill_reqs_available(struct kioctx *ctx) +{ + spin_lock_irq(&ctx->completion_lock); + if (ctx->completed_events) { + struct aio_ring *ring; + unsigned head; + + /* Access of ring->head may race with aio_read_events_ring() + * here, but that's okay since whether we read the old version + * or the new version, and either will be valid. The important + * part is that head cannot pass tail since we prevent + * aio_complete() from updating tail by holding + * ctx->completion_lock. Even if head is invalid, the check + * against ctx->completed_events below will make sure we do the + * safe/right thing. + */ + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + refill_reqs_available(ctx, head, ctx->tail); + } + + spin_unlock_irq(&ctx->completion_lock); +} + /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. @@ -888,8 +967,11 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (!get_reqs_available(ctx)) - return NULL; + if (!get_reqs_available(ctx)) { + user_refill_reqs_available(ctx); + if (!get_reqs_available(ctx)) + return NULL; + } req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); if (unlikely(!req)) @@ -948,8 +1030,8 @@ void aio_complete(struct kiocb *iocb, long res, long res2) struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; + unsigned tail, pos, head; unsigned long flags; - unsigned tail, pos; /* * Special case handling for sync iocbs: @@ -1010,10 +1092,14 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ctx->tail = tail; ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; ring->tail = tail; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); + ctx->completed_events++; + if (ctx->completed_events > 1) + refill_reqs_available(ctx, head, tail); spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); @@ -1028,7 +1114,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* everything turned out well, dispose of the aiocb. */ kiocb_free(iocb); - put_reqs_available(ctx, 1); /* * We have to order our ring_info tail store above and test @@ -1065,6 +1150,12 @@ static long aio_read_events_ring(struct kioctx *ctx, tail = ring->tail; kunmap_atomic(ring); + /* + * Ensure that once we've read the current tail pointer, that + * we also see the events that were stored up to the tail. + */ + smp_rmb(); + pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 3182c0e68b42..e3399dc2453b 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -95,7 +95,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) */ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in) { - struct autofs_dev_ioctl tmp; + struct autofs_dev_ioctl tmp, *res; if (copy_from_user(&tmp, in, sizeof(tmp))) return ERR_PTR(-EFAULT); @@ -103,7 +103,11 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i if (tmp.size < sizeof(tmp)) return ERR_PTR(-EINVAL); - return memdup_user(in, tmp.size); + res = memdup_user(in, tmp.size); + if (!IS_ERR(res)) + res->size = tmp.size; + + return res; } static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 67be2951b98a..f4d7b2fc9ffb 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -549,11 +549,12 @@ out: static unsigned long randomize_stack_top(unsigned long stack_top) { - unsigned int random_variable = 0; + unsigned long random_variable = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = get_random_int() & STACK_RND_MASK; + random_variable = (unsigned long) get_random_int(); + random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c527e3..d43c544d3b68 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cbd3a7d6fa68..93de3ba994e7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2655,32 +2655,23 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key, return 0; } -int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 iobjectid, u64 ioff, u8 key_type, struct btrfs_key *found_key) { int ret; struct btrfs_key key; struct extent_buffer *eb; - struct btrfs_path *path; + + ASSERT(path); key.type = key_type; key.objectid = iobjectid; key.offset = ioff; - if (found_path == NULL) { - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - } else - path = found_path; - ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); - if ((ret < 0) || (found_key == NULL)) { - if (path != found_path) - btrfs_free_path(path); + if ((ret < 0) || (found_key == NULL)) return ret; - } eb = path->nodes[0]; if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 451b00c86f6c..12e35566d2fc 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1854,6 +1854,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode) { struct btrfs_delayed_node *delayed_node; + /* + * we don't do delayed inode updates during log recovery because it + * leads to enospc problems. This means we also can't do + * delayed inode refs + */ + if (BTRFS_I(inode)->root->fs_info->log_root_recovering) + return -EAGAIN; + delayed_node = btrfs_get_or_create_delayed_node(inode); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 370ef7450157..f48d5fc352a9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1560,6 +1560,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, bool check_ref) { struct btrfs_root *root; + struct btrfs_path *path; int ret; if (location->objectid == BTRFS_ROOT_TREE_OBJECTID) @@ -1599,8 +1600,14 @@ again: if (ret) goto fail; - ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID, + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto fail; + } + ret = btrfs_find_item(fs_info->tree_root, path, BTRFS_ORPHAN_OBJECTID, location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL); + btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0) @@ -2411,7 +2418,7 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_ERR "BTRFS: has skinny extents\n"); + printk(KERN_INFO "BTRFS: has skinny extents\n"); /* * flag our filesystem as having big metadata blocks if @@ -3978,12 +3985,6 @@ again: if (ret) break; - /* opt_discard */ - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_error_discard_extent(root, start, - end + 1 - start, - NULL); - clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); cond_resched(); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3ff98e23f651..d2f1c011d73a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5503,7 +5503,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, update_global_block_rsv(fs_info); } -static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) +static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, + const bool return_free_space) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_group_cache *cache = NULL; @@ -5527,7 +5528,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) if (start < cache->last_byte_to_unpin) { len = min(len, cache->last_byte_to_unpin - start); - btrfs_add_free_space(cache, start, len); + if (return_free_space) + btrfs_add_free_space(cache, start, len); } start += len; @@ -5590,7 +5592,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, end + 1 - start, NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); - unpin_extent_range(root, start, end); + unpin_extent_range(root, start, end, true); cond_resched(); } @@ -8886,7 +8888,7 @@ out: int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) { - return unpin_extent_range(root, start, end); + return unpin_extent_range(root, start, end, false); } int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 1a858947006e..fa9f90049099 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4507,7 +4507,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4516,7 +4517,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4530,7 +4532,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4578,7 +4580,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4593,7 +4595,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 996ad56b57db..82845a6c63c2 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -290,8 +290,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, if (!em) goto out; - if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) - list_move(&em->list, &tree->modified_extents); em->generation = gen; clear_bit(EXTENT_FLAG_PINNED, &em->flags); em->mod_start = em->start; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index ca248b0687f4..196b089b0052 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -423,7 +423,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, ret = 0; fail: while (ret < 0 && !list_empty(&tmplist)) { - sums = list_entry(&tmplist, struct btrfs_ordered_sum, list); + sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list); list_del(&sums->list); kfree(sums); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b8672f09..0a841ddd6843 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page - * - * Disable pagefault to avoid recursive lock since - * the pages are already locked */ - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, count); - pagefault_enable(); /* Flush processor's dcache for this page */ flush_dcache_page(page); @@ -475,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } @@ -1778,22 +1774,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, mutex_unlock(&inode->i_mutex); /* - * we want to make sure fsync finds this change - * but we haven't joined a transaction running right now. - * - * Later on, someone is sure to update the inode and get the - * real transid recorded. - * - * We set last_trans now to the fs_info generation + 1, - * this will either be one more than the running transaction - * or the generation used for the next transaction if there isn't - * one running right now. - * * We also have to set last_sub_trans to the current log transid, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occured. */ - BTRFS_I(inode)->last_trans = root->fs_info->generation + 1; BTRFS_I(inode)->last_sub_trans = root->log_transid; if (num_written > 0) { err = generic_write_sync(file, pos, num_written); @@ -1896,25 +1880,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* - * check the transaction that last modified this inode - * and see if its already been committed - */ - if (!BTRFS_I(inode)->last_trans) { - mutex_unlock(&inode->i_mutex); - goto out; - } - - /* - * if the last transaction that changed this file was before - * the current transaction, we can bail out now without any - * syncing + * If the last transaction that changed this file was before the current + * transaction and we have the full sync flag set in our inode, we can + * bail out now without any syncing. + * + * Note that we can't bail out if the full sync flag isn't set. This is + * because when the full sync flag is set we start all ordered extents + * and wait for them to fully complete - when they complete they update + * the inode's last_trans field through: + * + * btrfs_finish_ordered_io() -> + * btrfs_update_inode_fallback() -> + * btrfs_update_inode() -> + * btrfs_set_inode_last_trans() + * + * So we are sure that last_trans is up to date and can do this check to + * bail out safely. For the fast path, when the full sync flag is not + * set in our inode, we can not do it because we start only our ordered + * extents and don't wait for them to complete (that is when + * btrfs_finish_ordered_io runs), so here at this point their last_trans + * value might be less than or equals to fs_info->last_trans_committed, + * and setting a speculative last_trans for an inode when a buffered + * write is made (such as fs_info->generation + 1 for example) would not + * be reliable since after setting the value and before fsync is called + * any number of transactions can start and commit (transaction kthread + * commits the current transaction periodically), and a transaction + * commit does not start nor waits for ordered extents to complete. */ smp_mb(); if (btrfs_inode_in_log(inode, root->fs_info->generation) || - BTRFS_I(inode)->last_trans <= - root->fs_info->last_trans_committed) { - BTRFS_I(inode)->last_trans = 0; - + (full_sync && BTRFS_I(inode)->last_trans <= + root->fs_info->last_trans_committed)) { /* * We'v had everything committed since the last time we were * modified so clear this flag in case it was set for whatever @@ -2510,23 +2506,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; - u64 lockstart = *offset; - u64 lockend = i_size_read(inode); - u64 start = *offset; - u64 len = i_size_read(inode); + u64 lockstart; + u64 lockend; + u64 start; + u64 len; int ret = 0; - lockend = max_t(u64, root->sectorsize, lockend); + if (inode->i_size == 0) + return -ENXIO; + + /* + * *offset can be negative, in this case we start finding DATA/HOLE from + * the very start of the file. + */ + start = max_t(loff_t, 0, *offset); + + lockstart = round_down(start, root->sectorsize); + lockend = round_up(i_size_read(inode), root->sectorsize); if (lockend <= lockstart) lockend = lockstart + root->sectorsize; - lockend--; len = lockend - lockstart + 1; - len = max_t(u64, len, root->sectorsize); - if (inode->i_size == 0) - return -ENXIO; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c69c76351f12..653cdd85e0f2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3596,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * without delay */ if (!btrfs_is_free_space_inode(inode) - && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID + && !root->fs_info->log_root_recovering) { btrfs_update_root_times(trans, root); ret = btrfs_delayed_update_inode(trans, root, inode); @@ -6869,7 +6870,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && em->block_start != EXTENT_MAP_HOLE)) { int type; - int ret; u64 block_start, orig_start, orig_block_len, ram_bytes; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a6d8efa46bfe..96b95e6f9f91 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) goto out_drop; } else { + ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); + if (ret && ret != -ENODATA) + goto out_drop; ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } @@ -679,23 +682,6 @@ out: return ret; } -/* copy of check_sticky in fs/namei.c() -* It's inline, so penalty for filesystems that don't use sticky bit is -* minimal. -*/ -static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode) -{ - kuid_t fsuid = current_fsuid(); - - if (!(dir->i_mode & S_ISVTX)) - return 0; - if (uid_eq(inode->i_uid, fsuid)) - return 0; - if (uid_eq(dir->i_uid, fsuid)) - return 0; - return !capable(CAP_FOWNER); -} - /* copy of may_delete in fs/namei.c() * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. @@ -731,8 +717,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) return error; if (IS_APPEND(dir)) return -EPERM; - if (btrfs_check_sticky(dir, victim->d_inode)|| - IS_APPEND(victim->d_inode)|| + if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) || IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode)) return -EPERM; if (isdir) { @@ -4750,6 +4735,12 @@ long btrfs_ioctl(struct file *file, unsigned int if (ret) return ret; ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + /* + * The transaction thread may want to do more work, + * namely it pokes the cleaner ktread that will start + * processing uncleaned subvols. + */ + wake_up_process(root->fs_info->transaction_kthread); return ret; } case BTRFS_IOC_START_SYNC: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 07b3b36f40ee..01f977e3ce09 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -736,7 +736,8 @@ again: err = ret; goto out; } - BUG_ON(!ret || !path1->slots[0]); + ASSERT(ret); + ASSERT(path1->slots[0]); path1->slots[0]--; @@ -746,10 +747,10 @@ again: * the backref was added previously when processing * backref of type BTRFS_TREE_BLOCK_REF_KEY */ - BUG_ON(!list_is_singular(&cur->upper)); + ASSERT(list_is_singular(&cur->upper)); edge = list_entry(cur->upper.next, struct backref_edge, list[LOWER]); - BUG_ON(!list_empty(&edge->list[UPPER])); + ASSERT(list_empty(&edge->list[UPPER])); exist = edge->node[UPPER]; /* * add the upper level block to pending list if we need @@ -831,7 +832,7 @@ again: cur->cowonly = 1; } #else - BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY); + ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY); if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { #endif if (key.objectid == key.offset) { @@ -840,7 +841,7 @@ again: * backref of this type. */ root = find_reloc_root(rc, cur->bytenr); - BUG_ON(!root); + ASSERT(root); cur->root = root; break; } @@ -868,7 +869,7 @@ again: } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); } list_add_tail(&edge->list[LOWER], &cur->upper); @@ -892,7 +893,7 @@ again: if (btrfs_root_level(&root->root_item) == cur->level) { /* tree root */ - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == cur->bytenr); if (should_ignore_root(root)) list_add(&cur->list, &useless); @@ -927,7 +928,7 @@ again: need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == lower->bytenr); if (should_ignore_root(root)) list_add(&lower->list, &useless); @@ -976,12 +977,15 @@ again: need_check = false; list_add_tail(&edge->list[UPPER], &list); - } else + } else { + if (upper->checked) + need_check = true; INIT_LIST_HEAD(&edge->list[UPPER]); + } } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); if (!upper->owner) upper->owner = btrfs_header_owner(eb); @@ -1025,7 +1029,7 @@ next: * everything goes well, connect backref nodes and insert backref nodes * into the cache. */ - BUG_ON(!node->checked); + ASSERT(node->checked); cowonly = node->cowonly; if (!cowonly) { rb_node = tree_insert(&cache->rb_root, node->bytenr, @@ -1061,8 +1065,21 @@ next: continue; } - BUG_ON(!upper->checked); - BUG_ON(cowonly != upper->cowonly); + if (!upper->checked) { + /* + * Still want to blow up for developers since this is a + * logic bug. + */ + ASSERT(0); + err = -EINVAL; + goto out; + } + if (cowonly != upper->cowonly) { + ASSERT(0); + err = -EINVAL; + goto out; + } + if (!cowonly) { rb_node = tree_insert(&cache->rb_root, upper->bytenr, &upper->rb_node); @@ -1085,7 +1102,7 @@ next: while (!list_empty(&useless)) { upper = list_entry(useless.next, struct backref_node, list); list_del_init(&upper->list); - BUG_ON(!list_empty(&upper->upper)); + ASSERT(list_empty(&upper->upper)); if (upper == node) node = NULL; if (upper->lowest) { @@ -1118,29 +1135,45 @@ out: if (err) { while (!list_empty(&useless)) { lower = list_entry(useless.next, - struct backref_node, upper); - list_del_init(&lower->upper); + struct backref_node, list); + list_del_init(&lower->list); } - upper = node; - INIT_LIST_HEAD(&list); - while (upper) { - if (RB_EMPTY_NODE(&upper->rb_node)) { - list_splice_tail(&upper->upper, &list); - free_backref_node(cache, upper); - } - - if (list_empty(&list)) - break; - - edge = list_entry(list.next, struct backref_edge, - list[LOWER]); + while (!list_empty(&list)) { + edge = list_first_entry(&list, struct backref_edge, + list[UPPER]); + list_del(&edge->list[UPPER]); list_del(&edge->list[LOWER]); + lower = edge->node[LOWER]; upper = edge->node[UPPER]; free_backref_edge(cache, edge); + + /* + * Lower is no longer linked to any upper backref nodes + * and isn't in the cache, we can free it ourselves. + */ + if (list_empty(&lower->upper) && + RB_EMPTY_NODE(&lower->rb_node)) + list_add(&lower->list, &useless); + + if (!RB_EMPTY_NODE(&upper->rb_node)) + continue; + + /* Add this guy's upper edges to the list to proces */ + list_for_each_entry(edge, &upper->upper, list[LOWER]) + list_add_tail(&edge->list[UPPER], &list); + if (list_empty(&upper->upper)) + list_add(&upper->list, &useless); + } + + while (!list_empty(&useless)) { + lower = list_entry(useless.next, + struct backref_node, list); + list_del_init(&lower->list); + free_backref_node(cache, lower); } return ERR_PTR(err); } - BUG_ON(node && node->detached); + ASSERT(!node || !node->detached); return node; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a65ed4cb436b..20d793542096 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4728,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (S_ISREG(sctx->cur_inode_mode)) { if (need_send_hole(sctx)) { - if (sctx->cur_inode_last_extent == (u64)-1) { + if (sctx->cur_inode_last_extent == (u64)-1 || + sctx->cur_inode_last_extent < + sctx->cur_inode_size) { ret = get_last_extent(sctx, (u64)-1); if (ret) goto out; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b05bf58b9395..a0b65a01fed7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) if (transid <= root->fs_info->last_trans_committed) goto out; - ret = -EINVAL; /* find specified transaction */ spin_lock(&root->fs_info->trans_lock); list_for_each_entry(t, &root->fs_info->trans_list, list) { @@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) } } spin_unlock(&root->fs_info->trans_lock); - /* The specified transaction doesn't exist */ - if (!cur_trans) + + /* + * The specified transaction doesn't exist, or we + * raced with btrfs_commit_transaction + */ + if (!cur_trans) { + if (transid > root->fs_info->last_trans_committed) + ret = -EINVAL; goto out; + } } else { /* find newest transaction that is committing | committed */ spin_lock(&root->fs_info->trans_lock); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 39d83da03e03..ec8b6542c8bd 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -979,7 +979,7 @@ again: base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { - extref = (struct btrfs_inode_extref *)base + cur_offset; + extref = (struct btrfs_inode_extref *)(base + cur_offset); victim_name_len = btrfs_inode_extref_name_len(leaf, extref); @@ -1235,13 +1235,14 @@ out: } static int insert_orphan_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 offset) + struct btrfs_root *root, u64 ino) { int ret; - ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID, - offset, BTRFS_ORPHAN_ITEM_KEY, NULL); - if (ret > 0) - ret = btrfs_insert_orphan_item(trans, root, offset); + + ret = btrfs_insert_orphan_item(trans, root, ino); + if (ret == -EEXIST) + ret = 0; + return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 27265a8b43c1..eef21c69f2d7 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1029,7 +1029,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, - index << sizebits, size); + (sector_t)index << sizebits, + size); goto done; } if (!try_to_free_buffers(page)) @@ -1050,7 +1051,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - end_block = init_page_buffers(page, bdev, index << sizebits, size); + end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, + size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; @@ -1366,12 +1368,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); @@ -1483,16 +1486,27 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state, b_state_old; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = bh->b_state; + for (;;) { + b_state_old = cmpxchg(&bh->b_state, b_state, + (b_state & ~BUFFER_FLAGS_DISCARD)); + if (b_state_old == b_state) + break; + b_state = b_state_old; + } unlock_buffer(bh); } @@ -2075,6 +2089,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int i_size_changed = 0; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -2094,6 +2109,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -2311,6 +2328,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, err = 0; balance_dirty_pages_ratelimited(mapping); + + if (unlikely(fatal_signal_pending(current))) { + err = -EINTR; + goto out; + } } /* page covers the boundary, find the boundary offset */ diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index 622f4696e484..5b99bafc31d1 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -124,7 +124,6 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) /* check parameters */ ret = -EOPNOTSUPP; if (!root->d_inode || - !root->d_inode->i_op || !root->d_inode->i_op->lookup || !root->d_inode->i_op->mkdir || !root->d_inode->i_op->setxattr || diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ca65f39dc8dc..c0a681705104 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -391,12 +391,12 @@ try_again: path.dentry = dir; path_to_graveyard.mnt = cache->mnt; path_to_graveyard.dentry = cache->graveyard; - ret = security_path_rename(&path, rep, &path_to_graveyard, grave); + ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0); if (ret < 0) { cachefiles_io_error(cache, "Rename security error %d", ret); } else { ret = vfs_rename(dir->d_inode, rep, - cache->graveyard->d_inode, grave, NULL); + cache->graveyard->d_inode, grave, NULL, 0); if (ret != 0 && ret != -ENOMEM) cachefiles_io_error(cache, "Rename failed with error %d", ret); @@ -779,8 +779,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, } ret = -EPERM; - if (!subdir->d_inode->i_op || - !subdir->d_inode->i_op->setxattr || + if (!subdir->d_inode->i_op->setxattr || !subdir->d_inode->i_op->getxattr || !subdir->d_inode->i_op->lookup || !subdir->d_inode->i_op->mkdir || diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b53278c9fd97..94a85ee5b990 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -676,7 +676,7 @@ static int ceph_writepages_start(struct address_space *mapping, int rc = 0; unsigned wsize = 1 << inode->i_blkbits; struct ceph_osd_request *req = NULL; - int do_sync; + int do_sync = 0; u64 truncate_size, snap_size; u32 truncate_seq; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f4f050a69a48..339c41216d14 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1461,15 +1461,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, dout("discard_cap_releases mds%d\n", session->s_mds); - /* zero out the in-progress message */ - msg = list_first_entry(&session->s_cap_releases, - struct ceph_msg, list_head); - head = msg->front.iov_base; - num = le32_to_cpu(head->num); - dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num); - head->num = cpu_to_le32(0); - msg->front.iov_len = sizeof(*head); - session->s_num_cap_releases += num; + if (!list_empty(&session->s_cap_releases)) { + /* zero out the in-progress message */ + msg = list_first_entry(&session->s_cap_releases, + struct ceph_msg, list_head); + head = msg->front.iov_base; + num = le32_to_cpu(head->num); + dout("discard_cap_releases mds%d %p %u\n", + session->s_mds, msg, num); + head->num = cpu_to_le32(0); + msg->front.iov_len = sizeof(*head); + session->s_num_cap_releases += num; + } /* requeue completed messages */ while (!list_empty(&session->s_cap_releases_done)) { diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f15d4353f30f..5d12d69e2045 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -399,6 +399,8 @@ struct smb_version_operations { const struct cifs_fid *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + /* check if we need to issue closedir */ + bool (*dir_needs_close)(struct cifsFileInfo *); }; struct smb_version_values { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8175b18df819..40ddb6e93912 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* @@ -762,7 +766,7 @@ int cifs_closedir(struct inode *inode, struct file *file) cifs_dbg(FYI, "Freeing private data in close dir\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) @@ -1817,6 +1821,7 @@ refind_writable: cifsFileInfo_put(inv_file); spin_lock(&cifs_file_list_lock); ++refind; + inv_file = NULL; goto refind_writable; } } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 77492301cc2b..dfc95646b88c 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, } src_inode = src_file.file->f_dentry->d_inode; + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants * server could even support copy of range where source = target */ - - /* so we do not deadlock racing two ioctls on same files */ - if (target_inode < src_inode) { - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD); - } + lock_two_nondirectories(target_inode, src_inode); /* determine range to clone */ rc = -EINVAL; @@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ - if (target_inode < src_inode) { - mutex_unlock(&src_inode->i_mutex); - mutex_unlock(&target_inode->i_mutex); - } else { - mutex_unlock(&target_inode->i_mutex); - mutex_unlock(&src_inode->i_mutex); - } + unlock_two_nondirectories(src_inode, target_inode); out_fput: fdput(src_file); out_drop_write: diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 68559fd557fb..a5c2812ead68 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, if (rc) goto out; - rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb, - fromName, buf, &bytes_written); + if (tcon->ses->server->ops->create_mf_symlink) + rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, + cifs_sb, fromName, buf, &bytes_written); + else + rc = -EOPNOTSUPP; + if (rc) goto out; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 2bbf11b09214..b334a89d6a66 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -593,7 +593,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* close and restart search */ cifs_dbg(FYI, "search backing up - close and restart search\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d1fdfa848703..e9ad8d37bb00 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -586,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, tmprc = CIFS_open(xid, &oparms, &oplock, NULL); if (tmprc == -EOPNOTSUPP) *symlink = true; - else + else if (tmprc == 0) CIFSSMBClose(xid, tcon, fid.netfid); } @@ -1009,6 +1009,12 @@ cifs_is_read_op(__u32 oplock) return oplock == OPLOCK_READ; } +static bool +cifs_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1078,6 +1084,7 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, + .dir_needs_close = cifs_dir_needs_close, #ifdef CONFIG_CIFS_XATTR .query_all_EAs = CIFSSMBQAllEAs, .set_EA = CIFSSMBSetEA, diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index e31a9dfdcd39..a491814cb2c0 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"}, {STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"}, {STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"}, - {STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"}, + {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"}, {STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"}, {STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"}, {STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"}, @@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO, "STATUS_DLL_MIGHT_BE_INCOMPATIBLE"}, {STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"}, + {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP, + "STATUS_REPARSE_NOT_HANDLED"}, {STATUS_DEVICE_REQUIRES_CLEANING, -EIO, "STATUS_DEVICE_REQUIRES_CLEANING"}, {STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f8977b2d9187..30f3eb5bc022 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -630,7 +630,8 @@ smb2_clone_range(const unsigned int xid, /* No need to change MaxChunks since already set to 1 */ chunk_sizes_updated = true; - } + } else + goto cchunk_out; } cchunk_out: @@ -1102,6 +1103,12 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch) return le32_to_cpu(lc->lcontext.LeaseState); } +static bool +smb2_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->invalidHandle; +} + struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, @@ -1175,6 +1182,7 @@ struct smb_version_operations smb20_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb21_operations = { @@ -1250,6 +1258,7 @@ struct smb_version_operations smb21_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb30_operations = { @@ -1328,6 +1337,7 @@ struct smb_version_operations smb30_operations = { .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, .validate_negotiate = smb3_validate_negotiate, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 9aab8fe0e508..348792911e1f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2136,6 +2136,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base; if (rc) { + if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) { + srch_inf->endOfSearch = true; + rc = 0; + } cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -2173,11 +2177,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, else cifs_dbg(VFS, "illegal search buffer type\n"); - if (rsp->hdr.Status == STATUS_NO_MORE_FILES) - srch_inf->endOfSearch = 1; - else - srch_inf->endOfSearch = 0; - return rc; qdir_exit: diff --git a/fs/compat.c b/fs/compat.c index 6af20de2c1a3..14da9b327ffa 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -837,10 +837,12 @@ struct compat_readdir_callback { int result; }; -static int compat_fillonedir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int compat_fillonedir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct compat_readdir_callback *buf = __buf; + struct compat_readdir_callback *buf = + container_of(ctx, struct compat_readdir_callback, ctx); struct compat_old_linux_dirent __user *dirent; compat_ulong_t d_ino; @@ -905,11 +907,12 @@ struct compat_getdents_callback { int error; }; -static int compat_filldir(void *__buf, const char *name, int namlen, +static int compat_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct compat_linux_dirent __user * dirent; - struct compat_getdents_callback *buf = __buf; + struct compat_getdents_callback *buf = + container_of(ctx, struct compat_getdents_callback, ctx); compat_ulong_t d_ino; int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + namlen + 2, sizeof(compat_long_t)); @@ -991,11 +994,13 @@ struct compat_getdents_callback64 { int error; }; -static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int compat_filldir64(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct compat_getdents_callback64 *buf = __buf; + struct compat_getdents_callback64 *buf = + container_of(ctx, struct compat_getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); u64 off; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf94d57..a1f801c14fbc 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index 58d57da91d2a..e3c556351810 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2481,12 +2481,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target) dentry->d_name.name = dentry->d_iname; } else { /* - * Both are internal. Just copy target to dentry + * Both are internal. */ - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); - dentry->d_name.len = target->d_name.len; - return; + unsigned int i; + BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); + for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { + swap(((long *) &dentry->d_iname)[i], + ((long *) &target->d_iname)[i]); + } } } swap(dentry->d_name.len, target->d_name.len); @@ -2543,13 +2545,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry, * __d_move - move a dentry * @dentry: entry to move * @target: new dentry + * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ -static void __d_move(struct dentry * dentry, struct dentry * target) +static void __d_move(struct dentry *dentry, struct dentry *target, + bool exchange) { if (!dentry->d_inode) printk(KERN_WARNING "VFS: moving negative dcache entry\n"); @@ -2571,8 +2575,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target) __d_drop(dentry); __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash)); - /* Unhash the target: dput() will then get rid of it */ + /* + * Unhash the target (d_delete() is not usable here). If exchanging + * the two dentries, then rehash onto the other's hash queue. + */ __d_drop(target); + if (exchange) { + __d_rehash(target, + d_hash(dentry->d_parent, dentry->d_name.hash)); + } list_del(&dentry->d_u.d_child); list_del(&target->d_u.d_child); @@ -2599,6 +2610,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target) write_seqcount_end(&dentry->d_seq); dentry_unlock_parents_for_move(dentry, target); + if (exchange) + fsnotify_d_move(target); spin_unlock(&target->d_lock); fsnotify_d_move(dentry); spin_unlock(&dentry->d_lock); @@ -2616,11 +2629,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target) void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); - __d_move(dentry, target); + __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); +/* + * d_exchange - exchange two dentries + * @dentry1: first dentry + * @dentry2: second dentry + */ +void d_exchange(struct dentry *dentry1, struct dentry *dentry2) +{ + write_seqlock(&rename_lock); + + WARN_ON(!dentry1->d_inode); + WARN_ON(!dentry2->d_inode); + WARN_ON(IS_ROOT(dentry1)); + WARN_ON(IS_ROOT(dentry2)); + + __d_move(dentry1, dentry2, true); + + write_sequnlock(&rename_lock); +} + /** * d_ancestor - search for an ancestor * @p1: ancestor dentry @@ -2668,7 +2700,7 @@ static struct dentry *__d_unalias(struct inode *inode, m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: if (likely(!d_mountpoint(alias))) { - __d_move(alias, dentry); + __d_move(alias, dentry, false); ret = alias; } out_err: @@ -2824,6 +2856,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. + * + * Data dependency barrier is needed to make sure that we see that terminating + * NUL. Alpha strikes again, film at 11... */ static int prepend_name(char **buffer, int *buflen, struct qstr *name) { @@ -2831,6 +2866,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; + smp_read_barrier_depends(); + *buflen -= dlen + 1; if (*buflen < 0) return -ENAMETOOLONG; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 15761957cc3f..1ff8fe5dab0d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -245,10 +245,19 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void debugfs_evict_inode(struct inode *inode) +{ + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_private); +} + static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, + .evict_inode = debugfs_evict_inode, }; static int debug_fill_super(struct super_block *sb, void *data, int silent) @@ -465,23 +474,14 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) int ret = 0; if (debugfs_positive(dentry)) { - if (dentry->d_inode) { - dget(dentry); - switch (dentry->d_inode->i_mode & S_IFMT) { - case S_IFDIR: - ret = simple_rmdir(parent->d_inode, dentry); - break; - case S_IFLNK: - kfree(dentry->d_inode->i_private); - /* fall through */ - default: - simple_unlink(parent->d_inode, dentry); - break; - } - if (!ret) - d_delete(dentry); - dput(dentry); - } + dget(dentry); + if (S_ISDIR(dentry->d_inode->i_mode)) + ret = simple_rmdir(parent->d_inode, dentry); + else + simple_unlink(parent->d_inode, dentry); + if (!ret) + d_delete(dentry); + dput(dentry); } return ret; } diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 2f6735dbf1a9..31b148f3e772 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size, break; case 2: dst[dst_byte_offset++] |= (src_byte); - dst[dst_byte_offset] = 0; current_bit_offset = 0; break; } diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b1eaa7a1f82c..121a94876d40 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -76,11 +76,11 @@ struct ecryptfs_getdents_callback { /* Inspired by generic filldir in fs/readdir.c */ static int -ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen, - loff_t offset, u64 ino, unsigned int d_type) +ecryptfs_filldir(struct dir_context *ctx, const char *lower_name, + int lower_namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ecryptfs_getdents_callback *buf = - (struct ecryptfs_getdents_callback *)dirent; + container_of(ctx, struct ecryptfs_getdents_callback, ctx); size_t name_size; char *name; int rc; @@ -191,23 +191,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file) { int rc = 0; struct ecryptfs_crypt_stat *crypt_stat = NULL; - struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct dentry *ecryptfs_dentry = file->f_path.dentry; /* Private value of ecryptfs_dentry allocated in * ecryptfs_lookup() */ struct ecryptfs_file_info *file_info; - mount_crypt_stat = &ecryptfs_superblock_to_private( - ecryptfs_dentry->d_sb)->mount_crypt_stat; - if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) - && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR) - || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC) - || (file->f_flags & O_APPEND))) { - printk(KERN_WARNING "Mount has encrypted view enabled; " - "files may only be read\n"); - rc = -EPERM; - goto out; - } /* Released in ecryptfs_release or end of function if failure */ file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); ecryptfs_set_file_private(file, file_info); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index b167ca48b8ee..57ee4c53b4f8 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, } rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry, lower_new_dir_dentry->d_inode, lower_new_dentry, - NULL); + NULL, 0); if (rc) goto out_lock; if (target_inode) @@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, } rc = vfs_setxattr(lower_dentry, name, value, size, flags); - if (!rc) + if (!rc && dentry->d_inode) fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode); out: return rc; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1b119d3bf924..d9eb84bda559 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags { struct super_block *s; struct ecryptfs_sb_info *sbi; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct ecryptfs_dentry_info *root_info; const char *err = "Getting sb failed"; struct inode *inode; @@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags err = "Error parsing options"; goto out; } + mount_crypt_stat = &sbi->mount_crypt_stat; s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) { @@ -557,15 +559,30 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags /** * Set the POSIX ACL flag based on whether they're enabled in the lower - * mount. Force a read-only eCryptfs mount if the lower mount is ro. - * Allow a ro eCryptfs mount even when the lower mount is rw. + * mount. */ s->s_flags = flags & ~MS_POSIXACL; - s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL); + s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL; + + /** + * Force a read-only eCryptfs mount when: + * 1) The lower mount is ro + * 2) The ecryptfs_encrypted_view mount option is specified + */ + if (path.dentry->d_sb->s_flags & MS_RDONLY || + mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + s->s_flags |= MS_RDONLY; s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; s->s_magic = ECRYPTFS_SUPER_MAGIC; + s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1; + + rc = -EINVAL; + if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("eCryptfs: maximum fs stacking depth exceeded\n"); + goto out_free; + } inode = ecryptfs_get_inode(path.dentry->d_inode, s); rc = PTR_ERR(inode); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ead00467282d..f50d79eb52db 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1852,7 +1852,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - ep_take_care_of_epollwakeup(&epds); + if (ep_op_has_event(op)) + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/fs/exec.c b/fs/exec.c index 31e46b1b358b..ea4449d0536a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,6 +26,7 @@ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> @@ -820,7 +821,7 @@ EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; - struct mm_struct * old_mm, *active_mm; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -846,6 +847,8 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 48a359dd286e..59d339c417c9 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -241,10 +241,11 @@ struct getdents_callback { * A rather strange filldir function to capture * the name matching the specified inode number. */ -static int filldir_one(void * __buf, const char * name, int len, +static int filldir_one(struct dir_context *ctx, const char *name, int len, loff_t pos, u64 ino, unsigned int d_type) { - struct getdents_callback *buf = __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); int result = 0; buf->sequence++; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 37fd31ed16e7..0498390f309e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1354,13 +1354,6 @@ set_qf_format: "not specified."); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext3_msg(sb, KERN_ERR, "error: journaled quota format " - "specified with no journaling " - "enabled."); - return 0; - } } #endif return 1; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index 3285aa5a706a..b610779a958c 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); @@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); @@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); @@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 62f024c051ce..2a6830a7af33 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2110,6 +2110,7 @@ int do_journal_get_write_access(handle_t *handle, #define CONVERT_INLINE_DATA 2 extern struct inode *ext4_iget(struct super_block *, unsigned long); +extern struct inode *ext4_iget_normal(struct super_block *, unsigned long); extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -2340,10 +2341,18 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM | - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); + EXT4_FEATURE_RO_COMPAT_GDT_CSUM) || + (EXT4_SB(sb)->s_chksum_driver != NULL); } +static inline int ext4_has_metadata_csum(struct super_block *sb) +{ + WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + !EXT4_SB(sb)->s_chksum_driver); + + return (EXT4_SB(sb)->s_chksum_driver != NULL); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 47188916dd8d..96a1ce159f51 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -74,8 +74,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); @@ -89,8 +88,7 @@ static void ext4_extent_block_csum_set(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2a8b2e15dcc4..589117e9e9be 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -100,7 +100,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, struct blk_plug plug; int unaligned_aio = 0; ssize_t ret; - int overwrite = 0; + int *overwrite = iocb->private; size_t length = iov_length(iov, nr_segs); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && @@ -118,8 +118,6 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); blk_start_plug(&plug); - iocb->private = &overwrite; - /* check whether we do a DIO overwrite or not */ if (ext4_should_dioread_nolock(inode) && !unaligned_aio && !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { @@ -143,7 +141,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, * So we should check these two conditions. */ if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) - overwrite = 1; + *overwrite = 1; } ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); @@ -170,6 +168,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + int overwrite = 0; /* * If we have encountered a bitmap-format file, the size limit @@ -190,6 +189,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, } } + iocb->private = &overwrite; if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); else diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 64bb32f17903..a8d1a64d8cb0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -864,6 +864,10 @@ got: struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); + if (!block_bitmap_bh) { + err = -EIO; + goto out; + } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { @@ -988,8 +992,7 @@ got: spin_unlock(&sbi->s_next_gen_lock); /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82edf5b93352..8c03b747021b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1128,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b56062dc8b62..3a7e0341447f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); @@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); @@ -2633,6 +2631,20 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } +/* We always reserve for an inode update; the superblock could be there too */ +static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) +{ + if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + return 1; + + if (pos + len <= 0x7fffffffULL) + return 1; + + /* We might need to update the superblock to set LARGE_FILE */ + return 2; +} + static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2683,7 +2695,8 @@ retry_grab: * of file which has an already mapped buffer. */ retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, + ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { page_cache_release(page); return PTR_ERR(handle); @@ -4061,8 +4074,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); @@ -4250,6 +4262,13 @@ bad_inode: return ERR_PTR(ret); } +struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) +{ + if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) + return ERR_PTR(-EIO); + return ext4_iget(sb, ino); +} + static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) @@ -4645,8 +4664,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_orphan_del(NULL, inode); goto err_out; } - } else + } else { + loff_t oldsize = inode->i_size; + i_size_write(inode, attr->ia_size); + pagecache_isize_extended(inode, oldsize, inode->i_size); + } /* * Blocks are going to be removed from the inode. Wait diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a2a837f00407..dfe982dee0b3 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -343,8 +343,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; @@ -544,9 +543,17 @@ group_add_out: } case EXT4_IOC_SWAP_BOOT: + { + int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - return swap_inode_boot_loader(sb, inode); + err = mnt_want_write_file(filp); + if (err) + return err; + err = swap_inode_boot_loader(sb, inode); + mnt_drop_write_file(filp); + return err; + } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 242226a87be7..7620133f78bf 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1172,15 +1172,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1201,9 +1202,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 04434ad3e8e0..1268a1b5afa9 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); @@ -29,8 +28,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d050e043e884..98de4b391e79 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -123,8 +123,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, "directory leaf block found instead of index block"); return ERR_PTR(-EIO); } - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) || + if (!ext4_has_metadata_csum(inode->i_sb) || buffer_verified(bh)) return bh; @@ -339,8 +338,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; t = get_dirent_tail(inode, dirent); @@ -361,8 +359,7 @@ static void ext4_dirent_csum_set(struct inode *inode, { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; t = get_dirent_tail(inode, dirent); @@ -437,8 +434,7 @@ static int ext4_dx_csum_verify(struct inode *inode, struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -467,8 +463,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -556,8 +551,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - EXT4_DIR_REC_LEN(2) - infosize; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -566,8 +560,7 @@ static inline unsigned dx_node_limit(struct inode *dir) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -1429,7 +1422,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi dentry); return ERR_PTR(-EIO); } - inode = ext4_iget(dir->i_sb, ino); + inode = ext4_iget_normal(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", @@ -1460,7 +1453,7 @@ struct dentry *ext4_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); + return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino)); } /* @@ -1534,8 +1527,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, int csum_size = 0; int err = 0, i; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); bh2 = ext4_append(handle, dir, &newblock); @@ -1704,8 +1696,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { @@ -1772,8 +1763,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); blocksize = dir->i_sb->s_blocksize; @@ -1889,8 +1879,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, ext4_lblk_t block, blocks; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; @@ -2152,8 +2141,7 @@ static int ext4_delete_entry(handle_t *handle, return err; } - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); BUFFER_TRACE(bh, "get_write_access"); @@ -2372,8 +2360,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -3204,6 +3191,16 @@ end_rename: return retval; } +static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + if (flags & ~RENAME_NOREPLACE) + return -EINVAL; + + return ext4_rename(old_dir, old_dentry, new_dir, new_dentry); +} + /* * directories can handle most operations... */ @@ -3217,7 +3214,7 @@ const struct inode_operations ext4_dir_inode_operations = { .rmdir = ext4_rmdir, .mknod = ext4_mknod, .tmpfile = ext4_tmpfile, - .rename = ext4_rename, + .rename2 = ext4_rename2, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f3b84cd9de56..2400ad1c3d12 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1071,7 +1071,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data, break; if (meta_bg == 0) - backup_block = group * bpg + blk_off; + backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; else backup_block = (ext4_group_first_block_no(sb, group) + ext4_bg_has_super(sb, group)); @@ -1200,8 +1200,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb, { struct buffer_head *bh; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 0; bh = ext4_get_bitmap(sb, group_data->inode_bitmap); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a46030d6b4af..9fb3e6c0c578 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -140,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb, int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); @@ -151,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); @@ -996,7 +994,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = ext4_iget(sb, ino); + inode = ext4_iget_normal(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { @@ -1706,13 +1704,6 @@ static int parse_options(char *options, struct super_block *sb, "not specified"); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext4_msg(sb, KERN_ERR, "journaled quota format " - "specified with no journaling " - "enabled"); - return 0; - } } #endif if (test_opt(sb, DIOREAD_NOLOCK)) { @@ -2010,8 +2001,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); - if ((sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { + if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __le16 save_csum; __u32 csum32; @@ -2029,6 +2019,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, } /* old crc16 code */ + if (!(sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM))) + return 0; + offset = offsetof(struct ext4_group_desc, bg_checksum); crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); @@ -3167,8 +3161,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; @@ -3475,8 +3468,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Precompute checksum seed for all metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3494,6 +3486,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif + /* don't forget to enable journal_csum when metadata_csum is enabled. */ + if (ext4_has_metadata_csum(sb)) + set_opt(sb, JOURNAL_CHECKSUM); + if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 55e611c1513c..8825154b20b6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -141,8 +141,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + if (ext4_has_metadata_csum(inode->i_sb) && (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) return 0; return 1; @@ -152,8 +151,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); @@ -189,14 +187,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size) } static int -ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) +ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, + void *value_start) { - while (!IS_LAST_ENTRY(entry)) { - struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry); + struct ext4_xattr_entry *e = entry; + + while (!IS_LAST_ENTRY(e)) { + struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) return -EIO; - entry = next; + e = next; } + + while (!IS_LAST_ENTRY(entry)) { + if (entry->e_value_size != 0 && + (value_start + le16_to_cpu(entry->e_value_offs) < + (void *)e + sizeof(__u32) || + value_start + le16_to_cpu(entry->e_value_offs) + + le32_to_cpu(entry->e_value_size) > end)) + return -EIO; + entry = EXT4_XATTR_NEXT(entry); + } + return 0; } @@ -213,7 +225,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) return -EIO; if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EIO; - error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, + bh->b_data); if (!error) set_buffer_verified(bh); return error; @@ -329,7 +342,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(entry, end); + error = ext4_xattr_check_names(entry, end, entry); if (error) goto cleanup; error = ext4_xattr_find_entry(&entry, name_index, name, @@ -457,7 +470,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(IFIRST(header), end); + error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header)); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), @@ -972,7 +985,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { - error = ext4_xattr_check_names(IFIRST(header), is->s.end); + error = ext4_xattr_check_names(IFIRST(header), is->s.end, + IFIRST(header)); if (error) return error; /* Find the named attribute. */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 293d0486a40f..5c6fe278fb63 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -71,7 +71,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b0649b76eb4f..bb6478acb369 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -969,7 +969,6 @@ repeat: } got_it: f2fs_bug_on(nid != nid_of_node(page)); - mark_page_accessed(page); return page; } @@ -1024,7 +1023,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 3963ede84eb0..c5d6bb939d19 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -702,10 +702,11 @@ static int fat_readdir(struct file *file, struct dir_context *ctx) } #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ -static int func(void *__buf, const char *name, int name_len, \ +static int func(struct dir_context *ctx, const char *name, int name_len, \ loff_t offset, u64 ino, unsigned int d_type) \ { \ - struct fat_ioctl_filldir_callback *buf = __buf; \ + struct fat_ioctl_filldir_callback *buf = \ + container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \ struct dirent_type __user *d1 = buf->dirent; \ struct dirent_type __user *d2 = d1 + 1; \ \ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a16315957ef3..23a51f08e3b5 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -476,12 +476,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * write_inode() */ spin_lock(&inode->i_lock); - /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state &= ~I_DIRTY_PAGES; + dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); + inode->i_state &= ~I_DIRTY; + + /* + * Paired with smp_mb() in __mark_inode_dirty(). This allows + * __mark_inode_dirty() to test i_state without grabbing i_lock - + * either they see the I_DIRTY bits cleared or we see the dirtied + * inode. + * + * I_DIRTY_PAGES is always cleared together above even if @mapping + * still has dirty pages. The flag is reinstated after smp_mb() if + * necessary. This guarantees that either __mark_inode_dirty() + * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. + */ + smp_mb(); + + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode->i_state |= I_DIRTY_PAGES; + spin_unlock(&inode->i_lock); + /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { int err = write_inode(inode, wbc); @@ -1145,12 +1161,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) } /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * Paired with smp_mb() in __writeback_single_inode() for the + * following lockless i_state test. See there for details. */ smp_mb(); - /* avoid the locking if we can */ if ((inode->i_state & flags) == flags) return; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 0a648bb455ae..499155ca3e84 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -819,8 +819,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) newpage = buf->page; - if (WARN_ON(!PageUptodate(newpage))) - return -EIO; + if (!PageUptodate(newpage)) + SetPageUptodate(newpage); ClearPageMappedToDisk(newpage); @@ -1614,7 +1614,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - release_pages(req->pages, req->num_pages, 0); + release_pages(req->pages, req->num_pages, false); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, @@ -1726,6 +1726,9 @@ copy_finish: static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { + /* Don't try to move pages (yet) */ + cs->move_pages = 0; + switch (code) { case FUSE_NOTIFY_POLL: return fuse_notify_poll(fc, size, cs); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 342f0239fcbf..33dec83eccfb 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -680,6 +680,14 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, return create_new_entry(fc, req, dir, entry, S_IFLNK); } +static inline void fuse_update_ctime(struct inode *inode) +{ + if (!IS_NOCMTIME(inode)) { + inode->i_ctime = current_fs_time(inode->i_sb); + mark_inode_dirty_sync(inode); + } +} + static int fuse_unlink(struct inode *dir, struct dentry *entry) { int err; @@ -714,6 +722,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); + fuse_update_ctime(inode); } else if (err == -EINTR) fuse_invalidate_entry(entry); return err; @@ -744,23 +753,26 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) return err; } -static int fuse_rename(struct inode *olddir, struct dentry *oldent, - struct inode *newdir, struct dentry *newent) +static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent, + unsigned int flags, int opcode, size_t argsize) { int err; - struct fuse_rename_in inarg; + struct fuse_rename2_in inarg; struct fuse_conn *fc = get_fuse_conn(olddir); - struct fuse_req *req = fuse_get_req_nopages(fc); + struct fuse_req *req; + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) return PTR_ERR(req); - memset(&inarg, 0, sizeof(inarg)); + memset(&inarg, 0, argsize); inarg.newdir = get_node_id(newdir); - req->in.h.opcode = FUSE_RENAME; + inarg.flags = flags; + req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(olddir); req->in.numargs = 3; - req->in.args[0].size = sizeof(inarg); + req->in.args[0].size = argsize; req->in.args[0].value = &inarg; req->in.args[1].size = oldent->d_name.len + 1; req->in.args[1].value = oldent->d_name.name; @@ -772,15 +784,22 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, if (!err) { /* ctime changes */ fuse_invalidate_attr(oldent->d_inode); + fuse_update_ctime(oldent->d_inode); + + if (flags & RENAME_EXCHANGE) { + fuse_invalidate_attr(newent->d_inode); + fuse_update_ctime(newent->d_inode); + } fuse_invalidate_attr(olddir); if (olddir != newdir) fuse_invalidate_attr(newdir); /* newent will end up negative */ - if (newent->d_inode) { + if (!(flags & RENAME_EXCHANGE) && newent->d_inode) { fuse_invalidate_attr(newent->d_inode); fuse_invalidate_entry_cache(newent); + fuse_update_ctime(newent->d_inode); } } else if (err == -EINTR) { /* If request was interrupted, DEITY only knows if the @@ -796,6 +815,36 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, return err; } +static int fuse_rename2(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent, + unsigned int flags) +{ + struct fuse_conn *fc = get_fuse_conn(olddir); + int err; + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags) { + if (fc->no_rename2 || fc->minor < 23) + return -EINVAL; + + err = fuse_rename_common(olddir, oldent, newdir, newent, flags, + FUSE_RENAME2, + sizeof(struct fuse_rename2_in)); + if (err == -ENOSYS) { + fc->no_rename2 = 1; + err = -EINVAL; + } + } else { + err = fuse_rename_common(olddir, oldent, newdir, newent, 0, + FUSE_RENAME, + sizeof(struct fuse_rename_in)); + } + + return err; +} + static int fuse_link(struct dentry *entry, struct inode *newdir, struct dentry *newent) { @@ -830,6 +879,7 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, inc_nlink(inode); spin_unlock(&fc->lock); fuse_invalidate_attr(inode); + fuse_update_ctime(inode); } else if (err == -EINTR) { fuse_invalidate_attr(inode); } @@ -840,6 +890,16 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, struct kstat *stat) { unsigned int blkbits; + struct fuse_conn *fc = get_fuse_conn(inode); + + /* see the comment in fuse_change_attributes() */ + if (fc->writeback_cache && S_ISREG(inode->i_mode)) { + attr->size = i_size_read(inode); + attr->mtime = inode->i_mtime.tv_sec; + attr->mtimensec = inode->i_mtime.tv_nsec; + attr->ctime = inode->i_ctime.tv_sec; + attr->ctimensec = inode->i_ctime.tv_nsec; + } stat->dev = inode->i_sb->s_dev; stat->ino = attr->ino; @@ -1478,12 +1538,16 @@ static long fuse_dir_compat_ioctl(struct file *file, unsigned int cmd, FUSE_IOCTL_COMPAT | FUSE_IOCTL_DIR); } -static bool update_mtime(unsigned ivalid) +static bool update_mtime(unsigned ivalid, bool trust_local_mtime) { /* Always update if mtime is explicitly set */ if (ivalid & ATTR_MTIME_SET) return true; + /* Or if kernel i_mtime is the official one */ + if (trust_local_mtime) + return true; + /* If it's an open(O_TRUNC) or an ftruncate(), don't update */ if ((ivalid & ATTR_SIZE) && (ivalid & (ATTR_OPEN | ATTR_FILE))) return false; @@ -1492,7 +1556,8 @@ static bool update_mtime(unsigned ivalid) return true; } -static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) +static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg, + bool trust_local_mtime) { unsigned ivalid = iattr->ia_valid; @@ -1511,11 +1576,11 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) if (!(ivalid & ATTR_ATIME_SET)) arg->valid |= FATTR_ATIME_NOW; } - if ((ivalid & ATTR_MTIME) && update_mtime(ivalid)) { + if ((ivalid & ATTR_MTIME) && update_mtime(ivalid, trust_local_mtime)) { arg->valid |= FATTR_MTIME; arg->mtime = iattr->ia_mtime.tv_sec; arg->mtimensec = iattr->ia_mtime.tv_nsec; - if (!(ivalid & ATTR_MTIME_SET)) + if (!(ivalid & ATTR_MTIME_SET) && !trust_local_mtime) arg->valid |= FATTR_MTIME_NOW; } } @@ -1564,6 +1629,63 @@ void fuse_release_nowrite(struct inode *inode) spin_unlock(&fc->lock); } +static void fuse_setattr_fill(struct fuse_conn *fc, struct fuse_req *req, + struct inode *inode, + struct fuse_setattr_in *inarg_p, + struct fuse_attr_out *outarg_p) +{ + req->in.h.opcode = FUSE_SETATTR; + req->in.h.nodeid = get_node_id(inode); + req->in.numargs = 1; + req->in.args[0].size = sizeof(*inarg_p); + req->in.args[0].value = inarg_p; + req->out.numargs = 1; + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; + else + req->out.args[0].size = sizeof(*outarg_p); + req->out.args[0].value = outarg_p; +} + +/* + * Flush inode->i_mtime to the server + */ +int fuse_flush_mtime(struct file *file, bool nofail) +{ + struct inode *inode = file->f_mapping->host; + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = NULL; + struct fuse_setattr_in inarg; + struct fuse_attr_out outarg; + int err; + + if (nofail) { + req = fuse_get_req_nofail_nopages(fc, file); + } else { + req = fuse_get_req_nopages(fc); + if (IS_ERR(req)) + return PTR_ERR(req); + } + + memset(&inarg, 0, sizeof(inarg)); + memset(&outarg, 0, sizeof(outarg)); + + inarg.valid |= FATTR_MTIME; + inarg.mtime = inode->i_mtime.tv_sec; + inarg.mtimensec = inode->i_mtime.tv_nsec; + + fuse_setattr_fill(fc, req, inode, &inarg, &outarg); + fuse_request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + + if (!err) + clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); + + return err; +} + /* * Set attributes, and at the same time refresh them. * @@ -1581,8 +1703,10 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct fuse_setattr_in inarg; struct fuse_attr_out outarg; bool is_truncate = false; + bool is_wb = fc->writeback_cache; loff_t oldsize; int err; + bool trust_local_mtime = is_wb && S_ISREG(inode->i_mode); if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) attr->ia_valid |= ATTR_FORCE; @@ -1611,7 +1735,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); - iattr_to_fattr(attr, &inarg); + iattr_to_fattr(attr, &inarg, trust_local_mtime); if (file) { struct fuse_file *ff = file->private_data; inarg.valid |= FATTR_FH; @@ -1622,17 +1746,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, inarg.valid |= FATTR_LOCKOWNER; inarg.lock_owner = fuse_lock_owner_id(fc, current->files); } - req->in.h.opcode = FUSE_SETATTR; - req->in.h.nodeid = get_node_id(inode); - req->in.numargs = 1; - req->in.args[0].size = sizeof(inarg); - req->in.args[0].value = &inarg; - req->out.numargs = 1; - if (fc->minor < 9) - req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; - else - req->out.args[0].size = sizeof(outarg); - req->out.args[0].value = &outarg; + fuse_setattr_fill(fc, req, inode, &inarg, &outarg); fuse_request_send(fc, req); err = req->out.h.error; fuse_put_request(fc, req); @@ -1649,10 +1763,18 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, } spin_lock(&fc->lock); + /* the kernel maintains i_mtime locally */ + if (trust_local_mtime && (attr->ia_valid & ATTR_MTIME)) { + inode->i_mtime = attr->ia_mtime; + clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); + } + fuse_change_attributes_common(inode, &outarg.attr, attr_timeout(&outarg)); oldsize = inode->i_size; - i_size_write(inode, outarg.attr.size); + /* see the comment in fuse_change_attributes() */ + if (!is_wb || is_truncate || !S_ISREG(inode->i_mode)) + i_size_write(inode, outarg.attr.size); if (is_truncate) { /* NOTE: this may release/reacquire fc->lock */ @@ -1664,7 +1786,8 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, * Only call invalidate_inode_pages2() after removing * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock. */ - if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { + if ((is_truncate || !is_wb) && + S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { truncate_pagecache(inode, outarg.attr.size); invalidate_inode_pages2(inode->i_mapping); } @@ -1740,8 +1863,10 @@ static int fuse_setxattr(struct dentry *entry, const char *name, fc->no_setxattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } return err; } @@ -1871,18 +1996,31 @@ static int fuse_removexattr(struct dentry *entry, const char *name) fc->no_removexattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } return err; } +static int fuse_update_time(struct inode *inode, struct timespec *now, + int flags) +{ + if (flags & S_MTIME) { + inode->i_mtime = *now; + set_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state); + BUG_ON(!S_ISREG(inode->i_mode)); + } + return 0; +} + static const struct inode_operations fuse_dir_inode_operations = { .lookup = fuse_lookup, .mkdir = fuse_mkdir, .symlink = fuse_symlink, .unlink = fuse_unlink, .rmdir = fuse_rmdir, - .rename = fuse_rename, + .rename2 = fuse_rename2, .link = fuse_link, .setattr = fuse_setattr, .create = fuse_create, @@ -1915,6 +2053,7 @@ static const struct inode_operations fuse_common_inode_operations = { .getxattr = fuse_getxattr, .listxattr = fuse_listxattr, .removexattr = fuse_removexattr, + .update_time = fuse_update_time, }; static const struct inode_operations fuse_symlink_inode_operations = { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 77bcc303c3ae..5916dc51599b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -188,6 +188,22 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, } EXPORT_SYMBOL_GPL(fuse_do_open); +static void fuse_link_write_file(struct file *file) +{ + struct inode *inode = file_inode(file); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_file *ff = file->private_data; + /* + * file may be written through mmap, so chain it onto the + * inodes's write_file list + */ + spin_lock(&fc->lock); + if (list_empty(&ff->write_entry)) + list_add(&ff->write_entry, &fi->write_files); + spin_unlock(&fc->lock); +} + void fuse_finish_open(struct inode *inode, struct file *file) { struct fuse_file *ff = file->private_data; @@ -292,6 +308,9 @@ static int fuse_open(struct inode *inode, struct file *file) static int fuse_release(struct inode *inode, struct file *file) { + if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) + fuse_flush_mtime(file, true); + fuse_release_common(file, FUSE_RELEASE); /* return value is ignored by VFS */ @@ -459,6 +478,12 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, fuse_sync_writes(inode); + if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) { + int err = fuse_flush_mtime(file, false); + if (err) + goto out; + } + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -655,6 +680,32 @@ static void fuse_read_update_size(struct inode *inode, loff_t size, spin_unlock(&fc->lock); } +static void fuse_short_read(struct fuse_req *req, struct inode *inode, + u64 attr_ver) +{ + size_t num_read = req->out.args[0].size; + struct fuse_conn *fc = get_fuse_conn(inode); + + if (fc->writeback_cache) { + /* + * A hole in a file. Some data after the hole are in page cache, + * but have not reached the client fs yet. So, the hole is not + * present there. + */ + int i; + int start_idx = num_read >> PAGE_CACHE_SHIFT; + size_t off = num_read & (PAGE_CACHE_SIZE - 1); + + for (i = start_idx; i < req->num_pages; i++) { + zero_user_segment(req->pages[i], off, PAGE_CACHE_SIZE); + off = 0; + } + } else { + loff_t pos = page_offset(req->pages[0]) + num_read; + fuse_read_update_size(inode, pos, attr_ver); + } +} + static int fuse_readpage(struct file *file, struct page *page) { struct fuse_io_priv io = { .async = 0, .file = file }; @@ -692,18 +743,18 @@ static int fuse_readpage(struct file *file, struct page *page) req->page_descs[0].length = count; num_read = fuse_send_read(req, &io, pos, count, NULL); err = req->out.h.error; - fuse_put_request(fc, req); if (!err) { /* * Short read means EOF. If file size is larger, truncate it */ if (num_read < count) - fuse_read_update_size(inode, pos + num_read, attr_ver); + fuse_short_read(req, inode, attr_ver); SetPageUptodate(page); } + fuse_put_request(fc, req); fuse_invalidate_atime(inode); out: unlock_page(page); @@ -726,13 +777,9 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) /* * Short read means EOF. If file size is larger, truncate it */ - if (!req->out.h.error && num_read < count) { - loff_t pos; + if (!req->out.h.error && num_read < count) + fuse_short_read(req, inode, req->misc.read.attr_ver); - pos = page_offset(req->pages[0]) + num_read; - fuse_read_update_size(inode, pos, - req->misc.read.attr_ver); - } fuse_invalidate_atime(inode); } @@ -922,16 +969,21 @@ static size_t fuse_send_write(struct fuse_req *req, struct fuse_io_priv *io, return req->misc.write.out.size; } -void fuse_write_update_size(struct inode *inode, loff_t pos) +bool fuse_write_update_size(struct inode *inode, loff_t pos) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); + bool ret = false; spin_lock(&fc->lock); fi->attr_version = ++fc->attr_version; - if (pos > inode->i_size) + if (pos > inode->i_size) { i_size_write(inode, pos); + ret = true; + } spin_unlock(&fc->lock); + + return ret; } static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file, @@ -1003,13 +1055,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); @@ -1946,20 +1994,9 @@ static const struct vm_operations_struct fuse_file_vm_ops = { static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) { - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) { - struct inode *inode = file_inode(file); - struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); - struct fuse_file *ff = file->private_data; - /* - * file may be written through mmap, so chain it onto the - * inodes's write_file list - */ - spin_lock(&fc->lock); - if (list_empty(&ff->write_entry)) - list_add(&ff->write_entry, &fi->write_files); - spin_unlock(&fc->lock); - } + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + fuse_link_write_file(file); + file_accessed(file); vma->vm_ops = &fuse_file_vm_ops; return 0; @@ -2850,8 +2887,16 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; /* we could have extended the file */ - if (!(mode & FALLOC_FL_KEEP_SIZE)) - fuse_write_update_size(inode, offset + length); + if (!(mode & FALLOC_FL_KEEP_SIZE)) { + bool changed = fuse_write_update_size(inode, offset + length); + + if (changed && fc->writeback_cache) { + struct fuse_inode *fi = get_fuse_inode(inode); + + inode->i_mtime = current_fs_time(inode->i_sb); + set_bit(FUSE_I_MTIME_DIRTY, &fi->state); + } + } if (mode & FALLOC_FL_PUNCH_HOLE) truncate_pagecache_range(inode, offset, offset + length - 1); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 2da5db2c8bdb..7cc58c976780 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -119,6 +119,8 @@ enum { FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, + /** i_mtime has been updated locally; a flush to userspace needed */ + FUSE_I_MTIME_DIRTY, }; struct fuse_conn; @@ -480,6 +482,9 @@ struct fuse_conn { /** Set if bdi is valid */ unsigned bdi_initialized:1; + /** write-back cache policy (default is write-through) */ + unsigned writeback_cache:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction @@ -539,6 +544,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Is rename with flags implemented by fs? */ + unsigned no_rename2:1; + /** Use enhanced/automatic page cache invalidation. */ unsigned auto_inval_data:1; @@ -873,7 +881,9 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd, unsigned fuse_file_poll(struct file *file, poll_table *wait); int fuse_dev_release(struct inode *inode, struct file *file); -void fuse_write_update_size(struct inode *inode, loff_t pos); +bool fuse_write_update_size(struct inode *inode, loff_t pos); + +int fuse_flush_mtime(struct file *file, bool nofail); int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct file *file); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 73f6bcb44ea8..8fe0b485908c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -170,10 +170,13 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; - inode->i_mtime.tv_sec = attr->mtime; - inode->i_mtime.tv_nsec = attr->mtimensec; - inode->i_ctime.tv_sec = attr->ctime; - inode->i_ctime.tv_nsec = attr->ctimensec; + /* mtime from server may be stale due to local buffered write */ + if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) { + inode->i_mtime.tv_sec = attr->mtime; + inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; + } if (attr->blksize != 0) inode->i_blkbits = ilog2(attr->blksize); @@ -197,6 +200,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); + bool is_wb = fc->writeback_cache; loff_t oldsize; struct timespec old_mtime; @@ -211,10 +215,16 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; - i_size_write(inode, attr->size); + /* + * In case of writeback_cache enabled, the cached writes beyond EOF + * extend local i_size without keeping userspace server in sync. So, + * attr->size coming from server can be stale. We cannot trust it. + */ + if (!is_wb || !S_ISREG(inode->i_mode)) + i_size_write(inode, attr->size); spin_unlock(&fc->lock); - if (S_ISREG(inode->i_mode)) { + if (!is_wb && S_ISREG(inode->i_mode)) { bool inval = false; if (oldsize != attr->size) { @@ -243,6 +253,10 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; + inode->i_mtime.tv_sec = attr->mtime; + inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); fuse_init_file_inode(inode); @@ -289,7 +303,9 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, return NULL; if ((inode->i_state & I_NEW)) { - inode->i_flags |= S_NOATIME|S_NOCMTIME; + inode->i_flags |= S_NOATIME; + if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) + inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; inode->i_data.backing_dev_info = &fc->bdi; fuse_init_inode(inode, attr); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 49436fa7cd4f..4ccb60d943bb 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -517,7 +517,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 8b9b3775e2e7..c41d255b6a7b 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -69,10 +69,12 @@ struct get_name_filldir { char *name; }; -static int get_name_filldir(void *opaque, const char *name, int length, - loff_t offset, u64 inum, unsigned int type) +static int get_name_filldir(struct dir_context *ctx, const char *name, + int length, loff_t offset, u64 inum, + unsigned int type) { - struct get_name_filldir *gnfd = opaque; + struct get_name_filldir *gnfd = + container_of(ctx, struct get_name_filldir, ctx); if (inum != gnfd->inum.no_addr) return 0; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5c524180c98e..bc643b97423c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -606,8 +606,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); error = PTR_ERR(d); - if (IS_ERR(d)) + if (IS_ERR(d)) { + inode = ERR_CAST(d); goto fail_gunlock; + } error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -823,7 +825,6 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, d = d_splice_alias(inode, dentry); if (IS_ERR(d)) { - iput(inode); gfs2_glock_dq_uninit(&gh); return d; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index c7f24690ed05..e7b149614f5e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = { .releasepage = gfs2_releasepage, }; +const struct address_space_operations gfs2_rgrp_aops = { + .writepage = gfs2_aspace_writepage, + .releasepage = gfs2_releasepage, +}; + /** * gfs2_getbuf - Get a buffer with a given address space * @gl: the glock @@ -131,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -148,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 4823b934208a..ac5d8027d335 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, } extern const struct address_space_operations gfs2_meta_aops; +extern const struct address_space_operations gfs2_rgrp_aops; static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) { struct inode *inode = mapping->host; if (mapping->a_ops == &gfs2_meta_aops) return (((struct gfs2_glock *)mapping) - 1)->gl_sbd; + else if (mapping->a_ops == &gfs2_rgrp_aops) + return container_of(mapping, struct gfs2_sbd, sd_aspace); else return inode->i_sb->s_fs_info; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6872d09561a..f6c9d83aa39b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -104,7 +104,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping = &sdp->sd_aspace; address_space_init_once(mapping); - mapping->a_ops = &gfs2_meta_aops; + mapping->a_ops = &gfs2_rgrp_aops; mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d56094b..754fdf8c6356 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 4338ff32959d..5f2755117ce7 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -548,10 +548,11 @@ struct hppfs_dirent { struct dentry *dentry; }; -static int hppfs_filldir(void *d, const char *name, int size, +static int hppfs_filldir(struct dir_context *ctx, const char *name, int size, loff_t offset, u64 inode, unsigned int type) { - struct hppfs_dirent *dirent = d; + struct hppfs_dirent *dirent = + container_of(ctx, struct hppfs_dirent, ctx); if (file_removed(dirent->dentry, name)) return 0; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d19b30ababf1..a4a8ed56e438 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void) int error; int i; + if (!hugepages_supported()) { + pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + return -ENOTSUPP; + } + error = bdi_init(&hugetlbfs_backing_dev_info); if (error) return error; diff --git a/fs/internal.h b/fs/internal.h index 465742407466..dd41b12c13f1 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -42,7 +42,6 @@ extern void __init chrdev_init(void); /* * namei.c */ -extern int __inode_permission(struct inode *, int); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); @@ -135,12 +134,6 @@ extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern int rw_verify_area(int, struct file *, const loff_t *, size_t); /* - * splice.c - */ -extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, size_t len, unsigned int flags); - -/* * pipe.c */ extern const struct file_operations pipefifo_fops; diff --git a/fs/ioprio.c b/fs/ioprio.c index e50170ca7c33..31666c92b46a 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -157,14 +157,16 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { - unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); - unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); + unsigned short aclass; + unsigned short bclass; - if (aclass == IOPRIO_CLASS_NONE) - aclass = IOPRIO_CLASS_BE; - if (bclass == IOPRIO_CLASS_NONE) - bclass = IOPRIO_CLASS_BE; + if (!ioprio_valid(aprio)) + aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + if (!ioprio_valid(bprio)) + bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aclass = IOPRIO_PRIO_CLASS(aprio); + bclass = IOPRIO_PRIO_CLASS(bprio); if (aclass == bclass) return min(aprio, bprio); if (aclass > bclass) diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index f488bbae541a..735d7522a3a9 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -30,6 +30,7 @@ struct rock_state { int cont_size; int cont_extent; int cont_offset; + int cont_loops; struct inode *inode; }; @@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode) rs->inode = inode; } +/* Maximum number of Rock Ridge continuation entries */ +#define RR_MAX_CE_ENTRIES 32 + /* * Returns 0 if the caller should continue scanning, 1 if the scan must end * and -ve on error. @@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs) goto out; } ret = -EIO; + if (++rs->cont_loops >= RR_MAX_CE_ENTRIES) + goto out; bh = sb_bread(rs->inode->i_sb, rs->cont_extent); if (bh) { memcpy(rs->buffer, bh->b_data + rs->cont_offset, @@ -356,6 +362,9 @@ repeat: rs.cont_size = isonum_733(rr->u.CE.size); break; case SIG('E', 'R'): + /* Invalid length of ER tag id? */ + if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len) + goto out; ISOFS_SB(inode->i_sb)->s_rock = 1; printk(KERN_DEBUG "ISO 9660 Extensions: "); { diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 9b329b55ffe3..bcbef08a4d8f 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -525,6 +525,7 @@ static int do_one_pass(journal_t *journal, !jbd2_descr_block_csum_verify(journal, bh->b_data)) { err = -EIO; + brelse(bh); goto failed; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426435dd..5b234db85854 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 413ef89c2d1b..046fee8b6e9b 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -134,8 +134,6 @@ struct jffs2_sb_info { struct rw_semaphore wbuf_sem; /* Protects the write buffer */ struct delayed_work wbuf_dwork; /* write-buffer write-out work */ - int wbuf_queued; /* non-zero delayed work is queued */ - spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */ unsigned char *oobbuf; int oobavail; /* How many bytes are available for JFFS2 in OOB */ diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 7654e87b0428..9ad5ba4b299b 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -510,6 +510,10 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo sumlen = c->sector_size - je32_to_cpu(sm->offset); sumptr = buf + buf_size - sumlen; + /* sm->offset maybe wrong but MAGIC maybe right */ + if (sumlen > c->sector_size) + goto full_scan; + /* Now, make sure the summary itself is available */ if (sumlen > buf_size) { /* Need to kmalloc for this. */ @@ -544,6 +548,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo } } +full_scan: buf_ofs = jeb->offset; if (!buf_size) { diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index a6597d60d76d..09ed55190ee2 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work) struct jffs2_sb_info *c = work_to_sb(work); struct super_block *sb = OFNI_BS_2SFFJ(c); - spin_lock(&c->wbuf_dwork_lock); - c->wbuf_queued = 0; - spin_unlock(&c->wbuf_dwork_lock); - if (!(sb->s_flags & MS_RDONLY)) { jffs2_dbg(1, "%s()\n", __func__); jffs2_flush_wbuf_gc(c, 0); @@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c) if (sb->s_flags & MS_RDONLY) return; - spin_lock(&c->wbuf_dwork_lock); - if (!c->wbuf_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay)) jffs2_dbg(1, "%s()\n", __func__); - delay = msecs_to_jiffies(dirty_writeback_interval * 10); - queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay); - c->wbuf_queued = 1; - } - spin_unlock(&c->wbuf_dwork_lock); } int jffs2_nand_flash_setup(struct jffs2_sb_info *c) @@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c) /* Initialise write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->erasesize; @@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; @@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) { return 0; init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1812f026960c..6ae664b489af 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + if (status == -ECONNREFUSED) { + dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n", + status); + rpc_force_rebind(clnt); + status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + } if (status < 0) dprintk("lockd: NSM upcall RPC failed, status=%d\n", status); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 6bf06a07f3e0..59a53f664005 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -137,10 +137,6 @@ lockd(void *vrqstp) dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); - if (!nlm_timeout) - nlm_timeout = LOCKD_DFLT_TIMEO; - nlmsvc_timeout = nlm_timeout * HZ; - /* * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. @@ -253,13 +249,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) error = make_socks(serv, net); if (error < 0) - goto err_socks; + goto err_bind; set_grace_period(net); dprintk("lockd_up_net: per-net data created; net=%p\n", net); return 0; -err_socks: - svc_rpcb_cleanup(serv, net); err_bind: ln->nlmsvc_users--; return error; @@ -348,6 +342,10 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); + if (!nlm_timeout) + nlm_timeout = LOCKD_DFLT_TIMEO; + nlmsvc_timeout = nlm_timeout * HZ; + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); diff --git a/fs/locks.c b/fs/locks.c index 4dd39b98a6a3..2c61c4e9368c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2235,16 +2235,28 @@ void locks_remove_flock(struct file *filp) while ((fl = *before) != NULL) { if (fl->fl_file == filp) { - if (IS_FLOCK(fl)) { - locks_delete_lock(before); - continue; - } if (IS_LEASE(fl)) { lease_modify(before, F_UNLCK); continue; } - /* What? */ - BUG(); + + /* + * There's a leftover lock on the list of a type that + * we didn't expect to see. Most likely a classic + * POSIX lock that ended up not getting released + * properly, or that raced onto the list somehow. Log + * some info about it and then just remove it from + * the list. + */ + WARN(!IS_FLOCK(fl), + "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), inode->i_ino, + fl->fl_type, fl->fl_flags, + fl->fl_start, fl->fl_end); + + locks_delete_lock(before); + continue; } before = &fl->fl_next; } diff --git a/fs/namei.c b/fs/namei.c index d5a4faeb39a5..0fbf1504fb63 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -415,6 +415,7 @@ int __inode_permission(struct inode *inode, int mask) return security_inode_permission(inode, mask); } +EXPORT_SYMBOL(__inode_permission); /** * sb_permission - Check superblock-level permissions @@ -642,24 +643,22 @@ static int complete_walk(struct nameidata *nd) static __always_inline void set_root(struct nameidata *nd) { - if (!nd->root.mnt) - get_fs_root(current->fs, &nd->root); + get_fs_root(current->fs, &nd->root); } static int link_path_walk(const char *, struct nameidata *); -static __always_inline void set_root_rcu(struct nameidata *nd) +static __always_inline unsigned set_root_rcu(struct nameidata *nd) { - if (!nd->root.mnt) { - struct fs_struct *fs = current->fs; - unsigned seq; + struct fs_struct *fs = current->fs; + unsigned seq, res; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); - } + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + res = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + return res; } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -859,7 +858,8 @@ follow_link(struct path *link, struct nameidata *nd, void **p) return PTR_ERR(s); } if (*s == '/') { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); path_put(&nd->path); nd->path = nd->root; path_get(&nd->root); @@ -1132,7 +1132,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { - set_root_rcu(nd); + if (!nd->root.mnt) + set_root_rcu(nd); while (1) { if (nd->path.dentry == nd->root.dentry && @@ -1244,7 +1245,8 @@ static void follow_mount(struct path *path) static void follow_dotdot(struct nameidata *nd) { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); while(1) { struct dentry *old = nd->path.dentry; @@ -1842,7 +1844,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); - set_root_rcu(nd); + nd->seq = set_root_rcu(nd); } else { set_root(nd); path_get(&nd->root); @@ -2358,22 +2360,17 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path, } EXPORT_SYMBOL(kern_path_mountpoint); -/* - * It's inline, so penalty for filesystems that don't use sticky bit is - * minimal. - */ -static inline int check_sticky(struct inode *dir, struct inode *inode) +int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (!(dir->i_mode & S_ISVTX)) - return 0; if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } +EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check @@ -2476,7 +2473,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) } mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2); return NULL; } @@ -3036,9 +3033,12 @@ finish_open_created: error = may_open(&nd->path, acc_mode, open_flag); if (error) goto out; - file->f_path.mnt = nd->path.mnt; - error = finish_open(file, nd->path.dentry, NULL, opened); - if (error) { + + BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ + error = vfs_open(&nd->path, file, current_cred()); + if (!error) { + *opened |= FILE_OPENED; + } else { if (error == -EOPENSTALE) goto stale_open; goto out; @@ -3127,7 +3127,8 @@ static int do_tmpfile(int dfd, struct filename *pathname, if (error) goto out2; audit_inode(pathname, nd->path.dentry, 0); - error = may_open(&nd->path, op->acc_mode, op->open_flag); + /* Don't check for other permissions, the inode was just created */ + error = may_open(&nd->path, MAY_OPEN, op->open_flag); if (error) goto out2; file->f_path.mnt = nd->path.mnt; @@ -3975,7 +3976,28 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -/* +/** + * vfs_rename - rename a filesystem object + * @old_dir: parent of source + * @old_dentry: source + * @new_dir: parent of destination + * @new_dentry: destination + * @delegated_inode: returns an inode needing a delegation break + * @flags: rename flags + * + * The caller must hold multiple mutexes--see lock_rename()). + * + * If vfs_rename discovers a delegation in need of breaking at either + * the source or destination, it will return -EWOULDBLOCK and return a + * reference to the inode in delegated_inode. The caller should then + * break the delegation and retry. Because breaking a delegation may + * take a long time, the caller should drop all locks before doing + * so. + * + * Alternatively, a caller may pass NULL for delegated_inode. This may + * be appropriate for callers that expect the underlying filesystem not + * to be NFS exported. + * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: @@ -4003,163 +4025,140 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) +int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + struct inode **delegated_inode, unsigned int flags) { - int error = 0; + int error; + bool is_dir = d_is_dir(old_dentry); + const unsigned char *old_name; + struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; + bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; + if (source == target) + return 0; + + error = may_delete(old_dir, old_dentry, is_dir); + if (error) + return error; + + if (!target) { + error = may_create(new_dir, new_dentry); + } else { + new_is_dir = d_is_dir(new_dentry); + + if (!(flags & RENAME_EXCHANGE)) + error = may_delete(new_dir, new_dentry, is_dir); + else + error = may_delete(new_dir, new_dentry, new_is_dir); + } + if (error) + return error; + + if (!old_dir->i_op->rename && !old_dir->i_op->rename2) + return -EPERM; + + if (flags && !old_dir->i_op->rename2) + return -EINVAL; + /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { - error = inode_permission(old_dentry->d_inode, MAY_WRITE); - if (error) - return error; + if (is_dir) { + error = inode_permission(source, MAY_WRITE); + if (error) + return error; + } + if ((flags & RENAME_EXCHANGE) && new_is_dir) { + error = inode_permission(target, MAY_WRITE); + if (error) + return error; + } } - error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry); + error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, + flags); if (error) return error; + old_name = fsnotify_oldname_init(old_dentry->d_name.name); dget(new_dentry); - if (target) + if (!is_dir || (flags & RENAME_EXCHANGE)) + lock_two_nondirectories(source, target); + else if (target) mutex_lock(&target->i_mutex); error = -EBUSY; if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry)) goto out; - error = -EMLINK; - if (max_links && !target && new_dir != old_dir && - new_dir->i_nlink >= max_links) - goto out; - - if (target) + if (max_links && new_dir != old_dir) { + error = -EMLINK; + if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) + goto out; + if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && + old_dir->i_nlink >= max_links) + goto out; + } + if (is_dir && !(flags & RENAME_EXCHANGE) && target) shrink_dcache_parent(new_dentry); - error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); - if (error) - goto out; - - if (target) { - target->i_flags |= S_DEAD; - dont_mount(new_dentry); + if (!is_dir) { + error = try_break_deleg(source, delegated_inode); + if (error) + goto out; } -out: - if (target) - mutex_unlock(&target->i_mutex); - dput(new_dentry); - if (!error) - if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) - d_move(old_dentry,new_dentry); - return error; -} - -static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode) -{ - struct inode *target = new_dentry->d_inode; - struct inode *source = old_dentry->d_inode; - int error; - - error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry); - if (error) - return error; - - dget(new_dentry); - lock_two_nondirectories(source, target); - - error = -EBUSY; - if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry)) - goto out; - - error = try_break_deleg(source, delegated_inode); - if (error) - goto out; - if (target) { + if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } - error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); + if (!old_dir->i_op->rename2) { + error = old_dir->i_op->rename(old_dir, old_dentry, + new_dir, new_dentry); + } else { + WARN_ON(old_dir->i_op->rename != NULL); + error = old_dir->i_op->rename2(old_dir, old_dentry, + new_dir, new_dentry, flags); + } if (error) goto out; - if (target) + if (!(flags & RENAME_EXCHANGE) && target) { + if (is_dir) + target->i_flags |= S_DEAD; dont_mount(new_dentry); - if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) - d_move(old_dentry, new_dentry); + } + if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { + if (!(flags & RENAME_EXCHANGE)) + d_move(old_dentry, new_dentry); + else + d_exchange(old_dentry, new_dentry); + } out: - unlock_two_nondirectories(source, target); + if (!is_dir || (flags & RENAME_EXCHANGE)) + unlock_two_nondirectories(source, target); + else if (target) + mutex_unlock(&target->i_mutex); dput(new_dentry); - return error; -} - -/** - * vfs_rename - rename a filesystem object - * @old_dir: parent of source - * @old_dentry: source - * @new_dir: parent of destination - * @new_dentry: destination - * @delegated_inode: returns an inode needing a delegation break - * - * The caller must hold multiple mutexes--see lock_rename()). - * - * If vfs_rename discovers a delegation in need of breaking at either - * the source or destination, it will return -EWOULDBLOCK and return a - * reference to the inode in delegated_inode. The caller should then - * break the delegation and retry. Because breaking a delegation may - * take a long time, the caller should drop all locks before doing - * so. - * - * Alternatively, a caller may pass NULL for delegated_inode. This may - * be appropriate for callers that expect the underlying filesystem not - * to be NFS exported. - */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode) -{ - int error; - int is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; - - if (old_dentry->d_inode == new_dentry->d_inode) - return 0; - - error = may_delete(old_dir, old_dentry, is_dir); - if (error) - return error; - - if (!new_dentry->d_inode) - error = may_create(new_dir, new_dentry); - else - error = may_delete(new_dir, new_dentry, is_dir); - if (error) - return error; - - if (!old_dir->i_op->rename) - return -EPERM; - - old_name = fsnotify_oldname_init(old_dentry->d_name.name); - - if (is_dir) - error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry); - else - error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode); - if (!error) + if (!error) { fsnotify_move(old_dir, new_dir, old_name, is_dir, - new_dentry->d_inode, old_dentry); + !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); + if (flags & RENAME_EXCHANGE) { + fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, + new_is_dir, NULL, new_dentry); + } + } fsnotify_oldname_free(old_name); return error; } -SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, - int, newdfd, const char __user *, newname) +SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, unsigned int, flags) { struct dentry *old_dir, *new_dir; struct dentry *old_dentry, *new_dentry; @@ -4171,6 +4170,17 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, unsigned int lookup_flags = 0; bool should_retry = false; int error; + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) + return -EINVAL; + + if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && + (flags & RENAME_EXCHANGE)) + return -EINVAL; + + if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD)) + return -EPERM; + retry: from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags); if (IS_ERR(from)) { @@ -4194,6 +4204,8 @@ retry: goto exit2; new_dir = newnd.path.dentry; + if (flags & RENAME_NOREPLACE) + error = -EEXIST; if (newnd.last_type != LAST_NORM) goto exit2; @@ -4203,7 +4215,8 @@ retry: oldnd.flags &= ~LOOKUP_PARENT; newnd.flags &= ~LOOKUP_PARENT; - newnd.flags |= LOOKUP_RENAME_TARGET; + if (!(flags & RENAME_EXCHANGE)) + newnd.flags |= LOOKUP_RENAME_TARGET; retry_deleg: trap = lock_rename(new_dir, old_dir); @@ -4216,34 +4229,49 @@ retry_deleg: error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; + new_dentry = lookup_hash(&newnd); + error = PTR_ERR(new_dentry); + if (IS_ERR(new_dentry)) + goto exit4; + error = -EEXIST; + if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) + goto exit5; + if (flags & RENAME_EXCHANGE) { + error = -ENOENT; + if (d_is_negative(new_dentry)) + goto exit5; + + if (!d_is_dir(new_dentry)) { + error = -ENOTDIR; + if (newnd.last.name[newnd.last.len]) + goto exit5; + } + } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (oldnd.last.name[oldnd.last.len]) - goto exit4; - if (newnd.last.name[newnd.last.len]) - goto exit4; + goto exit5; + if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len]) + goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) - goto exit4; - new_dentry = lookup_hash(&newnd); - error = PTR_ERR(new_dentry); - if (IS_ERR(new_dentry)) - goto exit4; + goto exit5; /* target should not be an ancestor of source */ - error = -ENOTEMPTY; + if (!(flags & RENAME_EXCHANGE)) + error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&oldnd.path, old_dentry, - &newnd.path, new_dentry); + &newnd.path, new_dentry, flags); if (error) goto exit5; error = vfs_rename(old_dir->d_inode, old_dentry, - new_dir->d_inode, new_dentry, - &delegated_inode); + new_dir->d_inode, new_dentry, + &delegated_inode, flags); exit5: dput(new_dentry); exit4: @@ -4273,16 +4301,34 @@ exit: return error; } +SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname) +{ + return sys_renameat2(olddfd, oldname, newdfd, newname, 0); +} + SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname); + return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link) +int vfs_whiteout(struct inode *dir, struct dentry *dentry) { - int len; + int error = may_create(dir, dentry); + if (error) + return error; - len = PTR_ERR(link); + if (!dir->i_op->mknod) + return -EPERM; + + return dir->i_op->mknod(dir, dentry, + S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); +} +EXPORT_SYMBOL(vfs_whiteout); + +int readlink_copy(char __user *buffer, int buflen, const char *link) +{ + int len = PTR_ERR(link); if (IS_ERR(link)) goto out; @@ -4311,7 +4357,7 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) if (IS_ERR(cookie)) return PTR_ERR(cookie); - res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); + res = readlink_copy(buffer, buflen, nd_get_link(&nd)); if (dentry->d_inode->i_op->put_link) dentry->d_inode->i_op->put_link(dentry, &nd, cookie); return res; @@ -4335,8 +4381,7 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage) int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct page *page = NULL; - char *s = page_getlink(dentry, &page); - int res = vfs_readlink(dentry,buffer,buflen,s); + int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page)); if (page) { kunmap(page); page_cache_release(page); @@ -4432,7 +4477,6 @@ EXPORT_SYMBOL(vfs_link); EXPORT_SYMBOL(vfs_mkdir); EXPORT_SYMBOL(vfs_mknod); EXPORT_SYMBOL(generic_permission); -EXPORT_SYMBOL(vfs_readlink); EXPORT_SYMBOL(vfs_rename); EXPORT_SYMBOL(vfs_rmdir); EXPORT_SYMBOL(vfs_symlink); diff --git a/fs/namespace.c b/fs/namespace.c index 75536db4b69b..c6533ce9cdee 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1295,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how) } if (last) { last->mnt_hash.next = unmounted.first; + if (unmounted.first) + unmounted.first->pprev = &last->mnt_hash.next; unmounted.first = tmp_list.first; unmounted.first->pprev = &unmounted.first; } @@ -1365,6 +1367,8 @@ static int do_umount(struct mount *mnt, int flags) * Special case for "unmounting" root ... * we just try to remount it readonly. */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; down_write(&sb->s_umount); if (!(sb->s_flags & MS_RDONLY)) retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); @@ -1437,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto dput_and_out; + retval = -EPERM; + if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) + goto dput_and_out; retval = do_umount(mnt, flags); dput_and_out: @@ -1579,6 +1586,33 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +/** + * clone_private_mount - create a private clone of a path + * + * This creates a new vfsmount, which will be the clone of @path. The new will + * not be attached anywhere in the namespace and will be private (i.e. changes + * to the originating mount won't be propagated into this). + * + * Release with mntput(). + */ +struct vfsmount *clone_private_mount(struct path *path) +{ + struct mount *old_mnt = real_mount(path->mnt); + struct mount *new_mnt; + + if (IS_MNT_UNBINDABLE(old_mnt)) + return ERR_PTR(-EINVAL); + + down_read(&namespace_sem); + new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) + return ERR_CAST(new_mnt); + + return &new_mnt->mnt; +} +EXPORT_SYMBOL_GPL(clone_private_mount); + int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { @@ -1962,7 +1996,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags, } if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) { - return -EPERM; + /* Was the nodev implicitly added in mount? */ + if ((mnt->mnt_ns->user_ns != &init_user_ns) && + !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) { + mnt_flags |= MNT_NODEV; + } else { + return -EPERM; + } } if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) { @@ -2829,6 +2869,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; + /* make certain new is below the root */ + if (!is_path_reachable(new_mnt, new.dentry, &root)) + goto out4; root_mp->m_count++; /* pin it so it won't go away */ lock_mount_hash(); detach_mnt(new_mnt, &parent_path); diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 60426ccb3b65..2f970de02b16 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg result = -EIO; } } - result = 0; } mutex_unlock(&server->root_setup_lock); diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823ca82e..65d849bdf77a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 073b4cf67ed9..0a2016bd6e58 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp) if (try_to_freeze()) continue; - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, struct rpc_rqst, rq_bc_list); list_del(&req->rq_bc_list); spin_unlock_bh(&serv->sv_cb_lock); + finish_wait(&serv->sv_cb_waitq, &wq); dprintk("Invoking bc_svc_process()\n"); error = bc_svc_process(serv, req, rqstp); dprintk("bc_svc_process() returned w/ error code= %d\n", error); } else { spin_unlock_bh(&serv->sv_cb_lock); - schedule(); + /* schedule_timeout to game the hung task watchdog */ + schedule_timeout(60 * HZ); + finish_wait(&serv->sv_cb_waitq, &wq); } - finish_wait(&serv->sv_cb_waitq, &wq); } return 0; } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index f4ccfe6521ec..02f8d09e119f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -464,8 +464,10 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, for (i = 0; i < args->csa_nrclists; i++) { status = decode_rc_list(xdr, &args->csa_rclists[i]); - if (status) + if (status) { + args->csa_nrclists = i; goto out_free; + } } } status = 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5d8ccecf5f5c..2ea3537b8bde 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -109,6 +109,8 @@ again: continue; if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; get_nfs_open_context(ctx); @@ -159,8 +161,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, &delegation->flags); NFS_I(inode)->delegation_state = delegation->type; spin_unlock(&delegation->lock); - put_rpccred(oldcred); rcu_read_unlock(); + put_rpccred(oldcred); trace_nfs4_reclaim_delegation(inode, res->delegation_type); } else { /* We appear to have raced with a delegation return. */ @@ -177,7 +179,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation * { int res = 0; - res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync); + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); nfs_free_delegation(delegation); return res; } @@ -364,11 +370,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; struct nfs_inode *nfsi = NFS_I(inode); - int err; + int err = 0; if (delegation == NULL) return 0; do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; err = nfs_delegation_claim_opens(inode, &delegation->stateid); if (!issync || err != -EAGAIN) break; @@ -589,10 +597,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; + nfs_revoke_delegation(inode); delegation = nfs_inode_detach_delegation(inode); if (delegation) { nfs_inode_find_state_and_recover(inode, &delegation->stateid); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 9a79c7a99d6d..e02b090ab9da 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -31,6 +31,7 @@ enum { NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831f..7ececa1c6c4f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -123,6 +123,12 @@ static inline int put_dreq(struct nfs_direct_req *dreq) */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp, (long long) pos, nr_segs); @@ -178,6 +184,7 @@ static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); if (dreq->l_ctx != NULL) nfs_put_lock_context(dreq->l_ctx); if (dreq->ctx != NULL) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 15f9d98627a4..6659ce545f15 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -592,7 +592,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; - int err; + int err = 0; trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0e46d3d1b6cc..d3f606255b99 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ if (pos->cl_cons_state > NFS_CS_READY) { @@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (pos->cl_clientid != new->cl_clientid) continue; @@ -564,20 +565,14 @@ static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b) } /* - * Returns true if the server owners match + * Returns true if the server major ids match */ static bool -nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b) +nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b) { struct nfs41_server_owner *o1 = a->cl_serverowner; struct nfs41_server_owner *o2 = b->cl_serverowner; - if (o1->minor_id != o2->minor_id) { - dprintk("NFS: --> %s server owner minor IDs do not match\n", - __func__); - return false; - } - if (o1->major_id_sz != o2->major_id_sz) goto out_major_mismatch; if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0) @@ -615,6 +610,16 @@ int nfs41_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION @@ -628,7 +633,7 @@ int nfs41_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - if (status == 0) { + if (pos->cl_cons_state == NFS_CS_SESSION_INITING) { nfs4_schedule_lease_recovery(pos); status = nfs4_wait_clnt_recover(pos); } @@ -640,19 +645,15 @@ int nfs41_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (!nfs4_match_clientids(pos, new)) continue; - if (!nfs4_match_serverowners(pos, new)) + /* + * Note that session trunking is just a special subcase of + * client id trunking. In either case, we want to fall back + * to using the existing nfs_client. + */ + if (!nfs4_check_clientid_trunking(pos, new)) continue; atomic_inc(&pos->cl_count); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 17f91a72840b..58258ad50d5f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1587,7 +1587,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs_inode_find_state_and_recover(state->inode, stateid); nfs4_schedule_stateid_recovery(server, state); - return 0; + return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: set_bit(NFS_DELEGATED_STATE, &state->flags); @@ -2034,46 +2034,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; } +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + #if defined(CONFIG_NFS_V4_1) -static void nfs41_clear_delegation_stateid(struct nfs4_state *state) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); - nfs4_stateid *stateid = &state->stateid; + nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred = NULL; - int status = -NFS4ERR_BAD_STATEID; - - /* If a state reset has been done, test_stateid is unneeded */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) - return; + struct rpc_cred *cred; + int status; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); - if (delegation != NULL && - nfs4_stateid_match(&delegation->stateid, stateid)) { - cred = get_rpccred(delegation->cred); - rcu_read_unlock(); - status = nfs41_test_stateid(server, stateid, cred); - trace_nfs4_test_delegation_stateid(state, NULL, status); - } else + if (delegation == NULL) { rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ if (status != -NFS4ERR_BAD_STATEID) - nfs41_free_stateid(server, stateid, cred); - nfs_remove_bad_delegation(state->inode); - - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); } - if (cred != NULL) - put_rpccred(cred); + put_rpccred(cred); } /** @@ -2117,7 +2131,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_clear_delegation_stateid(state); + nfs41_check_delegation_stateid(state); status = nfs41_check_open_stateid(state); if (status != NFS_OK) status = nfs4_open_expired(sp, state); @@ -2558,23 +2572,23 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); - /* Calculate the current open share mode */ - calldata->arg.fmode = 0; - if (is_rdonly || is_rdwr) - calldata->arg.fmode |= FMODE_READ; - if (is_wronly || is_rdwr) - calldata->arg.fmode |= FMODE_WRITE; /* Calculate the change in open mode */ + calldata->arg.fmode = 0; if (state->n_rdwr == 0) { - if (state->n_rdonly == 0) { - call_close |= is_rdonly || is_rdwr; - calldata->arg.fmode &= ~FMODE_READ; - } - if (state->n_wronly == 0) { - call_close |= is_wronly || is_rdwr; - calldata->arg.fmode &= ~FMODE_WRITE; - } - } + if (state->n_rdonly == 0) + call_close |= is_rdonly; + else if (is_rdonly) + calldata->arg.fmode |= FMODE_READ; + if (state->n_wronly == 0) + call_close |= is_wronly; + else if (is_wronly) + calldata->arg.fmode |= FMODE_WRITE; + } else if (is_rdwr) + calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; + + if (calldata->arg.fmode == 0) + call_close |= is_rdwr; + if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -7242,7 +7256,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr int ret = 0; if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) - return 0; + return -EAGAIN; task = _nfs41_proc_sequence(clp, cred, false); if (IS_ERR(task)) ret = PTR_ERR(task); @@ -7575,6 +7589,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) dprintk("--> %s\n", __func__); + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); @@ -7587,9 +7604,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.seq_res.sr_slot = NULL; nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); - /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ - pnfs_get_layout_hdr(NFS_I(inode)->layout); - task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return ERR_CAST(task); @@ -8255,7 +8269,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, - .recover_open = nfs4_open_expired, + .recover_open = nfs40_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, }; diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 1720d32ffa54..e1ba58c3d1ad 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work) } nfs_expire_all_delegations(clp); } else { + int ret; + /* Queue an asynchronous RENEW. */ - ops->sched_state_renewal(clp, cred, renew_flags); + ret = ops->sched_state_renewal(clp, cred, renew_flags); put_rpccred(cred); - goto out_exp; + switch (ret) { + default: + goto out_exp; + case -EAGAIN: + case -ENOMEM: + break; + } } } else { dprintk("%s: failed to call renewd. Reason: lease not expired \n", diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 27f5f858502b..b4f177f1d405 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1732,7 +1732,8 @@ restart: if (status < 0) { set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); - return nfs4_recovery_handle_error(clp, status); + status = nfs4_recovery_handle_error(clp, status); + return (status != 0) ? status : -EAGAIN; } nfs4_put_state_owner(sp); @@ -1741,7 +1742,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); - return status; + return 0; } static int nfs4_check_lease(struct nfs_client *clp) @@ -1788,7 +1789,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) break; case -NFS4ERR_STALE_CLIENTID: clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); break; case -NFS4ERR_CLID_INUSE: @@ -2370,6 +2370,7 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; + continue; } if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { @@ -2391,14 +2392,11 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim reboot"; status = nfs4_do_reclaim(clp, clp->cl_mvops->reboot_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) - continue; - nfs4_state_end_reclaim_reboot(clp); - if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; + nfs4_state_end_reclaim_reboot(clp); } /* Now recover expired state... */ @@ -2406,9 +2404,7 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) || - test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2ffebf2081ce..27d7f2742592 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -113,7 +113,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) if (atomic_read(&c->io_count) == 0) break; ret = nfs_wait_bit_killable(&c->flags); - } while (atomic_read(&c->io_count) != 0); + } while (atomic_read(&c->io_count) != 0 && !ret); finish_wait(wq, &q.wait); return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index cc8c5b32043c..f42bbe5fbc0a 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -784,8 +784,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task) { if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); - dprintk("%s slot is busy\n", __func__); - return false; + /* Race breaker */ + if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { + dprintk("%s slot is busy\n", __func__); + return false; + } + rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); } return true; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f23a6ca37504..86f5d3e474bf 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1243,7 +1243,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) */ if (argp->opcnt == resp->opcnt) return false; - + if (next->opnum == OP_ILLEGAL) + return false; nextd = OPDESC(next); /* * Rest of 2.6.3.1.1: certain operations will return WRONGSEC diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 9c271f42604a..674a5d529e09 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -244,10 +244,11 @@ struct nfs4_dir_ctx { }; static int -nfsd4_build_namelist(void *arg, const char *name, int namlen, +nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct nfs4_dir_ctx *ctx = arg; + struct nfs4_dir_ctx *ctx = + container_of(__ctx, struct nfs4_dir_ctx, ctx); struct name_list *entry; if (namlen != HEXDIR_LEN - 1) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 34d2a1f2f400..daa53da1d286 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1209,15 +1209,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) return 0; } -static long long +static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { - long long res; - - res = o1->len - o2->len; - if (res) - return res; - return (long long)memcmp(o1->data, o2->data, o1->len); + if (o1->len < o2->len) + return -1; + if (o1->len > o2->len) + return 1; + return memcmp(o1->data, o2->data, o1->len); } static int same_name(const char *n1, const char *n2) @@ -1401,7 +1400,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { - long long cmp; + int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 86573350350e..dd1afa38f2ae 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1809,6 +1809,9 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components, } else end++; + if (found_esc) + end = next; + str = end; } *pp = p; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index f8f060ffbf4f..6040da8830ff 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -242,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 479eb681c27c..f417fef17118 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -328,12 +328,15 @@ void nfsd_lockd_shutdown(void); (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL) +#define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #else -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0 +#define NFSD4_2_SECURITY_ATTRS 0 #endif +#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ + (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ + NFSD4_2_SECURITY_ATTRS) + static inline u32 nfsd_suppattrs0(u32 minorversion) { return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eea5ad188984..3953a20db16d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1703,7 +1703,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) goto out_dput_new; - host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL); + host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) @@ -1808,10 +1808,12 @@ struct readdir_data { int full; }; -static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct readdir_data *buf = __buf; + struct readdir_data *buf = + container_of(ctx, struct readdir_data, ctx); struct buffered_dirent *de = (void *)(buf->dirent + buf->used); unsigned int reclen; @@ -1831,7 +1833,7 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, return 0; } -static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, +static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, struct readdir_cd *cdp, loff_t *offsetp) { struct buffered_dirent *de; @@ -1915,7 +1917,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, - struct readdir_cd *cdp, filldir_t func) + struct readdir_cd *cdp, nfsd_filldir_t func) { __be32 err; struct file *file; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fbe90bdb2214..ea760b17ecbd 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -36,7 +36,7 @@ /* * Callback function for readdir */ -typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); +typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ int nfsd_racache_init(int); @@ -89,7 +89,7 @@ __be32 nfsd_rename(struct svc_rqst *, __be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, char *name, int len); __be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, - loff_t *, struct readdir_cd *, filldir_t); + loff_t *, struct readdir_cd *, nfsd_filldir_t); __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *, int access); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index b2e3ff347620..ecdbae19a766 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -31,6 +31,8 @@ #include "alloc.h" #include "dat.h" +static void __nilfs_btree_init(struct nilfs_bmap *bmap); + static struct nilfs_btree_path *nilfs_btree_alloc_path(void) { struct nilfs_btree_path *path; @@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, return ret; } +/** + * nilfs_btree_root_broken - verify consistency of btree root node + * @node: btree root node to be examined + * @ino: inode number + * + * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. + */ +static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, + unsigned long ino) +{ + int level, flags, nchildren; + int ret = 0; + + level = nilfs_btree_node_get_level(node); + flags = nilfs_btree_node_get_flags(node); + nchildren = nilfs_btree_node_get_nchildren(node); + + if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || + level > NILFS_BTREE_LEVEL_MAX || + nchildren < 0 || + nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { + pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n", + ino, level, flags, nchildren); + ret = 1; + } + return ret; +} + int nilfs_btree_broken_node_block(struct buffer_head *bh) { int ret; @@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, /* convert and insert */ dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; - nilfs_btree_init(btree); + __nilfs_btree_init(btree); if (nreq != NULL) { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); nilfs_bmap_commit_alloc_ptr(btree, nreq, dat); @@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_gather_data = NULL, }; -int nilfs_btree_init(struct nilfs_bmap *bmap) +static void __nilfs_btree_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); - return 0; +} + +int nilfs_btree_init(struct nilfs_bmap *bmap) +{ + int ret = 0; + + __nilfs_btree_init(bmap); + + if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), + bmap->b_inode->i_ino)) + ret = -EIO; + return ret; } void nilfs_btree_init_gc(struct nilfs_bmap *bmap) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c562e0e..09480c53fd74 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -24,6 +24,7 @@ #include <linux/buffer_head.h> #include <linux/gfp.h> #include <linux/mpage.h> +#include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/aio.h> #include "nilfs.h" @@ -48,6 +49,8 @@ struct nilfs_iget_args { int for_gc; }; +static int nilfs_iget_test(struct inode *inode, void *opaque); + void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; @@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) static int nilfs_set_page_dirty(struct page *page) { + struct inode *inode = page->mapping->host; int ret = __set_page_dirty_nobuffers(page); if (page_has_buffers(page)) { - struct inode *inode = page->mapping->host; unsigned nr_dirty = 0; struct buffer_head *bh, *head; @@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); + } else if (ret) { + unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } @@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +static int nilfs_insert_inode_locked(struct inode *inode, + struct nilfs_root *root, + unsigned long ino) +{ + struct nilfs_iget_args args = { + .ino = ino, .root = root, .cno = 0, .for_gc = 0 + }; + + return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); +} + struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { err = nilfs_bmap_read(ii->i_bmap, NULL); if (err < 0) - goto failed_bmap; + goto failed_after_creation; set_bit(NILFS_I_BMAP, &ii->i_state); /* No lock is needed; iget() ensures it. */ @@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) spin_lock(&nilfs->ns_next_gen_lock); inode->i_generation = nilfs->ns_next_generation++; spin_unlock(&nilfs->ns_next_gen_lock); - insert_inode_hash(inode); + if (nilfs_insert_inode_locked(inode, root, ino) < 0) { + err = -EIO; + goto failed_after_creation; + } err = nilfs_init_acl(inode, dir); if (unlikely(err)) - goto failed_acl; /* never occur. When supporting + goto failed_after_creation; /* never occur. When supporting nilfs_init_acl(), proper cancellation of above jobs should be considered */ return inode; - failed_acl: - failed_bmap: + failed_after_creation: clear_nlink(inode); + unlock_new_inode(inode); iput(inode); /* raw_inode will be deleted through - generic_delete_inode() */ + nilfs_evict_inode() */ goto failed; failed_ifile_create_inode: @@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode, inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); - if (inode->i_nlink == 0 && inode->i_mode == 0) - return -EINVAL; /* this inode is deleted */ + if (inode->i_nlink == 0) + return -ESTALE; /* this inode is deleted */ inode->i_blocks = le64_to_cpu(raw_inode->i_blocks); ii->i_flags = le32_to_cpu(raw_inode->i_flags); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9de78f08989e..0f84b257932c 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) int err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate(dentry, inode); + unlock_new_inode(inode); return 0; } inode_dec_link_count(inode); + unlock_new_inode(inode); iput(inode); return err; } @@ -182,6 +184,7 @@ out: out_fail: drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); goto out; } @@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode_inc_link_count(inode); ihold(inode); - err = nilfs_add_nondir(dentry, inode); - if (!err) + err = nilfs_add_link(dentry, inode); + if (!err) { + d_instantiate(dentry, inode); err = nilfs_transaction_commit(dir->i_sb); - else + } else { + inode_dec_link_count(inode); + iput(inode); nilfs_transaction_abort(dir->i_sb); + } return err; } @@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) nilfs_mark_inode_dirty(inode); d_instantiate(dentry, inode); + unlock_new_inode(inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); @@ -255,6 +263,7 @@ out_fail: drop_nlink(inode); drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); out_dir: drop_nlink(dir); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 9bc72dec3fa6..b02c202223a6 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a1a191634abc..14538a865102 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1899,8 +1905,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1911,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink || during_mount) { + /* + * Defer calling iput() to avoid deadlocks if + * i_nlink == 0 or mount is not yet finished. + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2580,6 +2602,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2606,6 +2630,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2630,6 +2656,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2639,6 +2668,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d0013314..a48d6de1e02c 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/workqueue.h> #include <linux/nilfs2_fs.h> #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 287a22c04149..de6323eb0113 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - client_fd = get_unused_fd(); + client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 238a5930cb3c..9d7e2b9659cb 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) { struct { struct file_handle handle; - u8 pad[64]; + u8 pad[MAX_HANDLE_SZ]; } f; int size, ret, i; @@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f.handle.handle_bytes >> 2; ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0); - if ((ret == 255) || (ret == -ENOSPC)) { + if ((ret == FILEID_INVALID) || (ret < 0)) { WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); return 0; } diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 74825be65b7b..fbb9dfb7b1d2 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -288,20 +288,25 @@ void fsnotify_unmount_inodes(struct list_head *list) spin_unlock(&inode->i_lock); /* In case the dropping of a reference would nuke next_i. */ - if ((&next_i->i_sb_list != list) && - atomic_read(&next_i->i_count)) { + while (&next_i->i_sb_list != list) { spin_lock(&next_i->i_lock); - if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) { + if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) && + atomic_read(&next_i->i_count)) { __iget(next_i); need_iput = next_i; + spin_unlock(&next_i->i_lock); + break; } spin_unlock(&next_i->i_lock); + next_i = list_entry(next_i->i_sb_list.next, + struct inode, i_sb_list); } /* - * We can safely drop inode_sb_list_lock here because we hold - * references on both inode and next_i. Also no new inodes - * will be added since the umount has begun. + * We can safely drop inode_sb_list_lock here because either + * we actually hold references on both inode and next_i or + * end of list. Also no new inodes will be added since the + * umount has begun. */ spin_unlock(&inode_sb_list_lock); diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fecefaf..250ed5b20c8f 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a31725..86ddab916b66 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index aeb44e879c51..bb6ee06118ca 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -899,7 +899,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) } } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) { int i; @@ -920,7 +920,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) page_cache_release(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); +} +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -2045,11 +2049,19 @@ out_write_size: di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); ocfs2_journal_dirty(handle, wc->w_di_bh); + /* unlock pages before dealloc since it needs acquiring j_trans_barrier + * lock, or it will cause a deadlock since journal commit threads holds + * this lock and will ask for the page lock when flushing the data. + * put it here to preserve the unlock order. + */ + ocfs2_unlock_pages(wc); + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); - ocfs2_free_write_ctxt(wc); + brelse(wc->w_di_bh); + kfree(wc); return copied; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 91a7e85ac8fd..478e14d7be54 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2073,10 +2073,12 @@ struct ocfs2_empty_dir_priv { unsigned seen_other; unsigned dx_dir; }; -static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_empty_dir_priv *p = priv; + struct ocfs2_empty_dir_priv *p = + container_of(ctx, struct ocfs2_empty_dir_priv, ctx); /* * Check the positions of "." and ".." records to be sure diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index af3f7aa73e13..1be3398c96f6 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -650,12 +650,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, clear_bit(bit, res->refmap); } - -void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, +static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { - assert_spin_locked(&res->spinlock); - res->inflight_locks++; mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name, @@ -663,6 +660,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, __builtin_return_address(0)); } +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + __dlm_lockres_grab_inflight_ref(dlm, res); +} + void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { @@ -852,10 +856,8 @@ lookup: /* finally add the lockres to its hash bucket */ __dlm_insert_lockres(dlm, res); - /* Grab inflight ref to pin the resource */ - spin_lock(&res->spinlock); - dlm_lockres_grab_inflight_ref(dlm, res); - spin_unlock(&res->spinlock); + /* since this lockres is new it doesn't not require the spinlock */ + __dlm_lockres_grab_inflight_ref(dlm, res); /* get an extra ref on the mle in case this is a BLOCK * if so, the creator of the BLOCK may try to put the last diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 51632c40e896..7fe30f655aa5 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2391,10 +2391,14 @@ out_dio: /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); + if (unlikely(written <= 0)) + goto no_sync; + if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); if (ret < 0) written = ret; @@ -2407,10 +2411,12 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } +no_sync: /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 44fc3e530c3d..a1b7dca075dd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1981,10 +1981,12 @@ struct ocfs2_orphan_filldir_priv { struct ocfs2_super *osb; }; -static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_orphan_filldir_priv *p = priv; + struct ocfs2_orphan_filldir_priv *p = + container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx); struct inode *iter; if (name_len == 1 && !strncmp(".", name, 1)) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index feed025fe064..b2427623dd6c 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, struct inode *inode, const char *symname); +static int ocfs2_double_lock(struct ocfs2_super *osb, + struct buffer_head **bh1, + struct inode *inode1, + struct buffer_head **bh2, + struct inode *inode2, + int rename); + +static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) @@ -656,8 +664,10 @@ static int ocfs2_link(struct dentry *old_dentry, { handle_t *handle; struct inode *inode = old_dentry->d_inode; + struct inode *old_dir = old_dentry->d_parent->d_inode; int err; struct buffer_head *fe_bh = NULL; + struct buffer_head *old_dir_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -674,19 +684,33 @@ static int ocfs2_link(struct dentry *old_dentry, dquot_initialize(dir); - err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT); + err = ocfs2_double_lock(osb, &old_dir_bh, old_dir, + &parent_fe_bh, dir, 0); if (err < 0) { if (err != -ENOENT) mlog_errno(err); return err; } + /* make sure both dirs have bhs + * get an extra ref on old_dir_bh if old==new */ + if (!parent_fe_bh) { + if (old_dir_bh) { + parent_fe_bh = old_dir_bh; + get_bh(parent_fe_bh); + } else { + mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str); + err = -EIO; + goto out; + } + } + if (!dir->i_nlink) { err = -ENOENT; goto out; } - err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (err) { err = -ENOENT; @@ -779,10 +803,11 @@ out_unlock_inode: ocfs2_inode_unlock(inode, 1); out: - ocfs2_inode_unlock(dir, 1); + ocfs2_double_unlock(old_dir, dir); brelse(fe_bh); brelse(parent_fe_bh); + brelse(old_dir_bh); ocfs2_free_dir_lookup_result(&lookup); @@ -991,14 +1016,15 @@ leave: } /* - * The only place this should be used is rename! + * The only place this should be used is rename and link! * if they have the same id, then the 1st one is the only one locked. */ static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, - struct inode *inode2) + struct inode *inode2, + int rename) { int status; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); @@ -1028,7 +1054,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id2 */ status = ocfs2_inode_lock_nested(inode2, bh2, 1, - OI_LS_RENAME1); + rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -1037,7 +1063,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2); + status = ocfs2_inode_lock_nested(inode1, bh1, 1, + rename == 1 ? OI_LS_RENAME2 : OI_LS_PARENT); if (status < 0) { /* * An error return must mean that no cluster locks @@ -1137,7 +1164,7 @@ static int ocfs2_rename(struct inode *old_dir, /* if old and new are the same, this'll just do one lock. */ status = ocfs2_double_lock(osb, &old_dir_bh, old_dir, - &new_dir_bh, new_dir); + &new_dir_bh, new_dir, 1); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/open.c b/fs/open.c index 2ed7325f713e..c92c6ef8bf6d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -822,8 +822,7 @@ struct file *dentry_open(const struct path *path, int flags, f = get_empty_filp(); if (!IS_ERR(f)) { f->f_flags = flags; - f->f_path = *path; - error = do_dentry_open(f, NULL, cred); + error = vfs_open(path, f, cred); if (!error) { /* from now on we need fput() to dispose of f */ error = open_check_o_direct(f); @@ -840,6 +839,26 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +/** + * vfs_open - open the file at the given path + * @path: path to open + * @filp: newly allocated file with f_flag initialized + * @cred: credentials to use + */ +int vfs_open(const struct path *path, struct file *filp, + const struct cred *cred) +{ + struct inode *inode = path->dentry->d_inode; + + if (inode->i_op->dentry_open) + return inode->i_op->dentry_open(path->dentry, filp, cred); + else { + filp->f_path = *path; + return do_dentry_open(filp, NULL, cred); + } +} +EXPORT_SYMBOL(vfs_open); + static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig new file mode 100644 index 000000000000..34355818a2e0 --- /dev/null +++ b/fs/overlayfs/Kconfig @@ -0,0 +1,10 @@ +config OVERLAY_FS + tristate "Overlay filesystem support" + help + An overlay filesystem combines two filesystems - an 'upper' filesystem + and a 'lower' filesystem. When a name exists in both filesystems, the + object in the 'upper' filesystem is visible while the object in the + 'lower' filesystem is either hidden or, in the case of directories, + merged with the 'upper' object. + + For more information see Documentation/filesystems/overlayfs.txt diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile new file mode 100644 index 000000000000..900daed3e91d --- /dev/null +++ b/fs/overlayfs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the overlay filesystem. +# + +obj-$(CONFIG_OVERLAY_FS) += overlay.o + +overlay-objs := super.o inode.o dir.o readdir.o copy_up.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c new file mode 100644 index 000000000000..24f640441bd9 --- /dev/null +++ b/fs/overlayfs/copy_up.c @@ -0,0 +1,413 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/file.h> +#include <linux/splice.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <linux/namei.h> +#include "overlayfs.h" + +#define OVL_COPY_UP_CHUNK_SIZE (1 << 20) + +int ovl_copy_xattr(struct dentry *old, struct dentry *new) +{ + ssize_t list_size, size; + char *buf, *name, *value; + int error; + + if (!old->d_inode->i_op->getxattr || + !new->d_inode->i_op->getxattr) + return 0; + + list_size = vfs_listxattr(old, NULL, 0); + if (list_size <= 0) { + if (list_size == -EOPNOTSUPP) + return 0; + return list_size; + } + + buf = kzalloc(list_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + error = -ENOMEM; + value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); + if (!value) + goto out; + + list_size = vfs_listxattr(old, buf, list_size); + if (list_size <= 0) { + error = list_size; + goto out_free_value; + } + + for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); + if (size <= 0) { + error = size; + goto out_free_value; + } + error = vfs_setxattr(new, name, value, size, 0); + if (error) + goto out_free_value; + } + +out_free_value: + kfree(value); +out: + kfree(buf); + return error; +} + +static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) +{ + struct file *old_file; + struct file *new_file; + loff_t old_pos = 0; + loff_t new_pos = 0; + int error = 0; + + if (len == 0) + return 0; + + old_file = ovl_path_open(old, O_RDONLY); + if (IS_ERR(old_file)) + return PTR_ERR(old_file); + + new_file = ovl_path_open(new, O_WRONLY); + if (IS_ERR(new_file)) { + error = PTR_ERR(new_file); + goto out_fput; + } + + /* FIXME: copy up sparse files efficiently */ + while (len) { + size_t this_len = OVL_COPY_UP_CHUNK_SIZE; + long bytes; + + if (len < this_len) + this_len = len; + + if (signal_pending_state(TASK_KILLABLE, current)) { + error = -EINTR; + break; + } + + bytes = do_splice_direct(old_file, &old_pos, + new_file, &new_pos, + this_len, SPLICE_F_MOVE); + if (bytes <= 0) { + error = bytes; + break; + } + WARN_ON(old_pos != new_pos); + + len -= bytes; + } + + fput(new_file); +out_fput: + fput(old_file); + return error; +} + +static char *ovl_read_symlink(struct dentry *realdentry) +{ + int res; + char *buf; + struct inode *inode = realdentry->d_inode; + mm_segment_t old_fs; + + res = -EINVAL; + if (!inode->i_op->readlink) + goto err; + + res = -ENOMEM; + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + goto err; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = inode->i_op->readlink(realdentry, + (char __user *)buf, PAGE_SIZE - 1); + set_fs(old_fs); + if (res < 0) { + free_page((unsigned long) buf); + goto err; + } + buf[res] = '\0'; + + return buf; + +err: + return ERR_PTR(res); +} + +static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) +{ + struct iattr attr = { + .ia_valid = + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + .ia_atime = stat->atime, + .ia_mtime = stat->mtime, + }; + + return notify_change(upperdentry, &attr, NULL); +} + +int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) +{ + int err = 0; + + if (!S_ISLNK(stat->mode)) { + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = stat->mode, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) { + struct iattr attr = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = stat->uid, + .ia_gid = stat->gid, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) + ovl_set_timestamps(upperdentry, stat); + + return err; +} + +static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, + struct dentry *dentry, struct path *lowerpath, + struct kstat *stat, struct iattr *attr, + const char *link) +{ + struct inode *wdir = workdir->d_inode; + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry = NULL; + struct dentry *upper = NULL; + umode_t mode = stat->mode; + int err; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out1; + + /* Can't properly set mode on creation because of the umask */ + stat->mode &= S_IFMT; + err = ovl_create_real(wdir, newdentry, stat, link, NULL, true); + stat->mode = mode; + if (err) + goto out2; + + if (S_ISREG(stat->mode)) { + struct path upperpath; + ovl_path_upper(dentry, &upperpath); + BUG_ON(upperpath.dentry != NULL); + upperpath.dentry = newdentry; + + err = ovl_copy_up_data(lowerpath, &upperpath, stat->size); + if (err) + goto out_cleanup; + } + + err = ovl_copy_xattr(lowerpath->dentry, newdentry); + if (err) + goto out_cleanup; + + mutex_lock(&newdentry->d_inode->i_mutex); + err = ovl_set_attr(newdentry, stat); + if (!err && attr) + err = notify_change(newdentry, attr, NULL); + mutex_unlock(&newdentry->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + + ovl_dentry_update(dentry, newdentry); + newdentry = NULL; + + /* + * Non-directores become opaque when copied up. + */ + if (!S_ISDIR(stat->mode)) + ovl_dentry_set_opaque(dentry, true); +out2: + dput(upper); +out1: + dput(newdentry); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out; +} + +/* + * Copy up a single dentry + * + * Directory renames only allowed on "pure upper" (already created on + * upper filesystem, never copied up). Directories which are on lower or + * are merged may not be renamed. For these -EXDEV is returned and + * userspace has to deal with it. This means, when copying up a + * directory we can rely on it and ancestors being stable. + * + * Non-directory renames start with copy up of source if necessary. The + * actual rename will only proceed once the copy up was successful. Copy + * up uses upper parent i_mutex for exclusion. Since rename can change + * d_parent it is possible that the copy up will lock the old parent. At + * that point the file will have already been copied up anyway. + */ +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr) +{ + struct dentry *workdir = ovl_workdir(dentry); + int err; + struct kstat pstat; + struct path parentpath; + struct dentry *upperdir; + struct dentry *upperdentry; + const struct cred *old_cred; + struct cred *override_cred; + char *link = NULL; + + ovl_path_upper(parent, &parentpath); + upperdir = parentpath.dentry; + + err = vfs_getattr(&parentpath, &pstat); + if (err) + return err; + + if (S_ISLNK(stat->mode)) { + link = ovl_read_symlink(lowerpath->dentry); + if (IS_ERR(link)) + return PTR_ERR(link); + } + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_free_link; + + override_cred->fsuid = stat->uid; + override_cred->fsgid = stat->gid; + /* + * CAP_SYS_ADMIN for copying up extended attributes + * CAP_DAC_OVERRIDE for create + * CAP_FOWNER for chmod, timestamp update + * CAP_FSETID for chmod + * CAP_CHOWN for chown + * CAP_MKNOD for mknod + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + cap_raise(override_cred->cap_effective, CAP_MKNOD); + old_cred = override_creds(override_cred); + + err = -EIO; + if (lock_rename(workdir, upperdir) != NULL) { + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + goto out_unlock; + } + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + unlock_rename(workdir, upperdir); + err = 0; + /* Raced with another copy-up? Do the setattr here */ + if (attr) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } + goto out_put_cred; + } + + err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, + stat, attr, link); + if (!err) { + /* Restore timestamps on parent (best effort) */ + ovl_set_timestamps(upperdir, &pstat); + } +out_unlock: + unlock_rename(workdir, upperdir); +out_put_cred: + revert_creds(old_cred); + put_cred(override_cred); + +out_free_link: + if (link) + free_page((unsigned long) link); + + return err; +} + +int ovl_copy_up(struct dentry *dentry) +{ + int err; + + err = 0; + while (!err) { + struct dentry *next; + struct dentry *parent; + struct path lowerpath; + struct kstat stat; + enum ovl_path_type type = ovl_path_type(dentry); + + if (OVL_TYPE_UPPER(type)) + break; + + next = dget(dentry); + /* find the topmost dentry not yet copied up */ + for (;;) { + parent = dget_parent(next); + + type = ovl_path_type(parent); + if (OVL_TYPE_UPPER(type)) + break; + + dput(next); + next = parent; + } + + ovl_path_lower(next, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (!err) + err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL); + + dput(parent); + dput(next); + } + + return err; +} diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c new file mode 100644 index 000000000000..0dc4c33a0a1b --- /dev/null +++ b/fs/overlayfs/dir.c @@ -0,0 +1,928 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) +{ + int err; + + dget(wdentry); + if (S_ISDIR(wdentry->d_inode->i_mode)) + err = ovl_do_rmdir(wdir, wdentry); + else + err = ovl_do_unlink(wdir, wdentry); + dput(wdentry); + + if (err) { + pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n", + wdentry, err); + } +} + +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry) +{ + struct dentry *temp; + char name[20]; + + snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry); + + temp = lookup_one_len(name, workdir, strlen(name)); + if (!IS_ERR(temp) && temp->d_inode) { + pr_err("overlayfs: workdir/%s already exists\n", name); + dput(temp); + temp = ERR_PTR(-EIO); + } + + return temp; +} + +/* caller holds i_mutex on workdir */ +static struct dentry *ovl_whiteout(struct dentry *workdir, + struct dentry *dentry) +{ + int err; + struct dentry *whiteout; + struct inode *wdir = workdir->d_inode; + + whiteout = ovl_lookup_temp(workdir, dentry); + if (IS_ERR(whiteout)) + return whiteout; + + err = ovl_do_whiteout(wdir, whiteout); + if (err) { + dput(whiteout); + whiteout = ERR_PTR(err); + } + + return whiteout; +} + +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug) +{ + int err; + + if (newdentry->d_inode) + return -ESTALE; + + if (hardlink) { + err = ovl_do_link(hardlink, dir, newdentry, debug); + } else { + switch (stat->mode & S_IFMT) { + case S_IFREG: + err = ovl_do_create(dir, newdentry, stat->mode, debug); + break; + + case S_IFDIR: + err = ovl_do_mkdir(dir, newdentry, stat->mode, debug); + break; + + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + err = ovl_do_mknod(dir, newdentry, + stat->mode, stat->rdev, debug); + break; + + case S_IFLNK: + err = ovl_do_symlink(dir, newdentry, link, debug); + break; + + default: + err = -EPERM; + } + } + if (!err && WARN_ON(!newdentry->d_inode)) { + /* + * Not quite sure if non-instantiated dentry is legal or not. + * VFS doesn't seem to care so check and warn here. + */ + err = -ENOENT; + } + return err; +} + +static int ovl_set_opaque(struct dentry *upperdentry) +{ + return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0); +} + +static void ovl_remove_opaque(struct dentry *upperdentry) +{ + int err; + + err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE); + if (err) { + pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n", + upperdentry->d_name.name, err); + } +} + +static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + int err; + enum ovl_path_type type; + struct path realpath; + + type = ovl_path_real(dentry, &realpath); + err = vfs_getattr(&realpath, stat); + if (err) + return err; + + stat->dev = dentry->d_sb->s_dev; + stat->ino = dentry->d_inode->i_ino; + + /* + * It's probably not worth it to count subdirs to get the + * correct link count. nlink=1 seems to pacify 'find' and + * other utilities. + */ + if (OVL_TYPE_MERGE(type)) + stat->nlink = 1; + + return 0; +} + +static int ovl_create_upper(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry; + int err; + + mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT); + newdentry = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + err = ovl_create_real(udir, newdentry, stat, link, hardlink, false); + if (err) + goto out_dput; + + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput: + dput(newdentry); +out_unlock: + mutex_unlock(&udir->i_mutex); + return err; +} + +static int ovl_lock_rename_workdir(struct dentry *workdir, + struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} + +static struct dentry *ovl_clear_empty(struct dentry *dentry, + struct list_head *list) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct path upperpath; + struct dentry *upper; + struct dentry *opaquedir; + struct kstat stat; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + ovl_path_upper(dentry, &upperpath); + err = vfs_getattr(&upperpath, &stat); + if (err) + goto out_unlock; + + err = -ESTALE; + if (!S_ISDIR(stat.mode)) + goto out_unlock; + upper = upperpath.dentry; + if (upper->d_parent->d_inode != udir) + goto out_unlock; + + opaquedir = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out_unlock; + + err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true); + if (err) + goto out_dput; + + err = ovl_copy_xattr(upper, opaquedir); + if (err) + goto out_cleanup; + + err = ovl_set_opaque(opaquedir); + if (err) + goto out_cleanup; + + mutex_lock(&opaquedir->d_inode->i_mutex); + err = ovl_set_attr(opaquedir, &stat); + mutex_unlock(&opaquedir->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup_whiteouts(upper, list); + ovl_cleanup(wdir, upper); + unlock_rename(workdir, upperdir); + + /* dentry's upper doesn't match now, get rid of it */ + d_drop(dentry); + + return opaquedir; + +out_cleanup: + ovl_cleanup(wdir, opaquedir); +out_dput: + dput(opaquedir); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return ERR_PTR(err); +} + +static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry) +{ + int err; + struct dentry *ret = NULL; + LIST_HEAD(list); + + err = ovl_check_empty_dir(dentry, &list); + if (err) + ret = ERR_PTR(err); + else { + /* + * If no upperdentry then skip clearing whiteouts. + * + * Can race with copy-up, since we don't hold the upperdir + * mutex. Doesn't matter, since copy-up can't create a + * non-empty directory from an empty one. + */ + if (ovl_dentry_upper(dentry)) + ret = ovl_clear_empty(dentry, &list); + } + + ovl_cache_free(&list); + + return ret; +} + +static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *upper; + struct dentry *newdentry; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out_dput; + + err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true); + if (err) + goto out_dput2; + + if (S_ISDIR(stat->mode)) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, + RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup(wdir, upper); + } else { + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + } + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput2: + dput(upper); +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out_dput2; +} + +static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev, + const char *link, struct dentry *hardlink) +{ + int err; + struct inode *inode; + struct kstat stat = { + .mode = mode, + .rdev = rdev, + }; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata); + if (!inode) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_iput; + + if (!ovl_dentry_is_opaque(dentry)) { + err = ovl_create_upper(dentry, inode, &stat, link, hardlink); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_iput; + + /* + * CAP_SYS_ADMIN for setting opaque xattr + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + old_cred = override_creds(override_cred); + + err = ovl_create_over_whiteout(dentry, inode, &stat, link, + hardlink); + + revert_creds(old_cred); + put_cred(override_cred); + } + + if (!err) + inode = NULL; +out_iput: + iput(inode); +out: + return err; +} + +static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, + const char *link) +{ + int err; + + err = ovl_want_write(dentry); + if (!err) { + err = ovl_create_or_link(dentry, mode, rdev, link, NULL); + ovl_drop_write(dentry); + } + + return err; +} + +static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); +} + +static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); +} + +static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t rdev) +{ + /* Don't allow creation of "whiteout" on overlay */ + if (S_ISCHR(mode) && rdev == WHITEOUT_DEV) + return -EPERM; + + return ovl_create_object(dentry, mode, rdev, NULL); +} + +static int ovl_symlink(struct inode *dir, struct dentry *dentry, + const char *link) +{ + return ovl_create_object(dentry, S_IFLNK, 0, link); +} + +static int ovl_link(struct dentry *old, struct inode *newdir, + struct dentry *new) +{ + int err; + struct dentry *upper; + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + upper = ovl_dentry_upper(old); + err = ovl_create_or_link(new, upper->d_inode->i_mode, 0, NULL, upper); + +out_drop_write: + ovl_drop_write(old); +out: + return err; +} + +static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *whiteout; + struct dentry *upper; + struct dentry *opaquedir = NULL; + int err; + + if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { + opaquedir = ovl_check_empty_and_clear(dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out; + } + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out_dput; + + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto out_unlock; + + upper = ovl_dentry_upper(dentry); + if (!upper) { + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto kill_whiteout; + + err = ovl_do_rename(wdir, whiteout, udir, upper, 0); + dput(upper); + if (err) + goto kill_whiteout; + } else { + int flags = 0; + + if (opaquedir) + upper = opaquedir; + err = -ESTALE; + if (upper->d_parent != upperdir) + goto kill_whiteout; + + if (is_dir) + flags |= RENAME_EXCHANGE; + + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + + if (is_dir) + ovl_cleanup(wdir, upper); + } + ovl_dentry_version_inc(dentry->d_parent); +out_d_drop: + d_drop(dentry); + dput(whiteout); +out_unlock: + unlock_rename(workdir, upperdir); +out_dput: + dput(opaquedir); +out: + return err; + +kill_whiteout: + ovl_cleanup(wdir, whiteout); + goto out_d_drop; +} + +static int ovl_remove_upper(struct dentry *dentry, bool is_dir) +{ + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *dir = upperdir->d_inode; + struct dentry *upper = ovl_dentry_upper(dentry); + int err; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + err = -ESTALE; + if (upper->d_parent == upperdir) { + /* Don't let d_delete() think it can reset d_inode */ + dget(upper); + if (is_dir) + err = vfs_rmdir(dir, upper); + else + err = vfs_unlink(dir, upper, NULL); + dput(upper); + ovl_dentry_version_inc(dentry->d_parent); + } + + /* + * Keeping this dentry hashed would mean having to release + * upperpath/lowerpath, which could only be done if we are the + * sole user of this dentry. Too tricky... Just unhash for + * now. + */ + d_drop(dentry); + mutex_unlock(&dir->i_mutex); + + return err; +} + +static inline int ovl_check_sticky(struct dentry *dentry) +{ + struct inode *dir = ovl_dentry_real(dentry->d_parent)->d_inode; + struct inode *inode = ovl_dentry_real(dentry)->d_inode; + + if (check_sticky(dir, inode)) + return -EPERM; + + return 0; +} + +static int ovl_do_remove(struct dentry *dentry, bool is_dir) +{ + enum ovl_path_type type; + int err; + + err = ovl_check_sticky(dentry); + if (err) + goto out; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_drop_write; + + type = ovl_path_type(dentry); + if (OVL_TYPE_PURE_UPPER(type)) { + err = ovl_remove_upper(dentry, is_dir); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + + err = ovl_remove_and_whiteout(dentry, is_dir); + + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_unlink(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, false); +} + +static int ovl_rmdir(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, true); +} + +static int ovl_rename2(struct inode *olddir, struct dentry *old, + struct inode *newdir, struct dentry *new, + unsigned int flags) +{ + int err; + enum ovl_path_type old_type; + enum ovl_path_type new_type; + struct dentry *old_upperdir; + struct dentry *new_upperdir; + struct dentry *olddentry; + struct dentry *newdentry; + struct dentry *trap; + bool old_opaque; + bool new_opaque; + bool new_create = false; + bool cleanup_whiteout = false; + bool overwrite = !(flags & RENAME_EXCHANGE); + bool is_dir = S_ISDIR(old->d_inode->i_mode); + bool new_is_dir = false; + struct dentry *opaquedir = NULL; + const struct cred *old_cred = NULL; + struct cred *override_cred = NULL; + + err = -EINVAL; + if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) + goto out; + + flags &= ~RENAME_NOREPLACE; + + err = ovl_check_sticky(old); + if (err) + goto out; + + /* Don't copy up directory trees */ + old_type = ovl_path_type(old); + err = -EXDEV; + if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir) + goto out; + + if (new->d_inode) { + err = ovl_check_sticky(new); + if (err) + goto out; + + if (S_ISDIR(new->d_inode->i_mode)) + new_is_dir = true; + + new_type = ovl_path_type(new); + err = -EXDEV; + if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) + goto out; + + err = 0; + if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) { + if (ovl_dentry_lower(old)->d_inode == + ovl_dentry_lower(new)->d_inode) + goto out; + } + if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) { + if (ovl_dentry_upper(old)->d_inode == + ovl_dentry_upper(new)->d_inode) + goto out; + } + } else { + if (ovl_dentry_is_opaque(new)) + new_type = __OVL_PATH_UPPER; + else + new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE; + } + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + err = ovl_copy_up(new->d_parent); + if (err) + goto out_drop_write; + if (!overwrite) { + err = ovl_copy_up(new); + if (err) + goto out_drop_write; + } + + old_opaque = !OVL_TYPE_PURE_UPPER(old_type); + new_opaque = !OVL_TYPE_PURE_UPPER(new_type); + + if (old_opaque || new_opaque) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + } + + if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) { + opaquedir = ovl_check_empty_and_clear(new); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) { + opaquedir = NULL; + goto out_revert_creds; + } + } + + if (overwrite) { + if (old_opaque) { + if (new->d_inode || !new_opaque) { + /* Whiteout source */ + flags |= RENAME_WHITEOUT; + } else { + /* Switch whiteouts */ + flags |= RENAME_EXCHANGE; + } + } else if (is_dir && !new->d_inode && new_opaque) { + flags |= RENAME_EXCHANGE; + cleanup_whiteout = true; + } + } + + old_upperdir = ovl_dentry_upper(old->d_parent); + new_upperdir = ovl_dentry_upper(new->d_parent); + + trap = lock_rename(new_upperdir, old_upperdir); + + olddentry = ovl_dentry_upper(old); + newdentry = ovl_dentry_upper(new); + if (newdentry) { + if (opaquedir) { + newdentry = opaquedir; + opaquedir = NULL; + } else { + dget(newdentry); + } + } else { + new_create = true; + newdentry = lookup_one_len(new->d_name.name, new_upperdir, + new->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + } + + err = -ESTALE; + if (olddentry->d_parent != old_upperdir) + goto out_dput; + if (newdentry->d_parent != new_upperdir) + goto out_dput; + if (olddentry == trap) + goto out_dput; + if (newdentry == trap) + goto out_dput; + + if (is_dir && !old_opaque && new_opaque) { + err = ovl_set_opaque(olddentry); + if (err) + goto out_dput; + } + if (!overwrite && new_is_dir && old_opaque && !new_opaque) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_dput; + } + + if (old_opaque || new_opaque) { + err = ovl_do_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + flags); + } else { + /* No debug for the plain case */ + BUG_ON(flags & ~RENAME_EXCHANGE); + err = vfs_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + NULL, flags); + } + + if (err) { + if (is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(newdentry); + goto out_dput; + } + + if (is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(newdentry); + + if (old_opaque != new_opaque) { + ovl_dentry_set_opaque(old, new_opaque); + if (!overwrite) + ovl_dentry_set_opaque(new, old_opaque); + } + + if (cleanup_whiteout) + ovl_cleanup(old_upperdir->d_inode, newdentry); + + ovl_dentry_version_inc(old->d_parent); + ovl_dentry_version_inc(new->d_parent); + +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(new_upperdir, old_upperdir); +out_revert_creds: + if (old_opaque || new_opaque) { + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(old); +out: + dput(opaquedir); + return err; +} + +const struct inode_operations ovl_dir_inode_operations = { + .lookup = ovl_lookup, + .mkdir = ovl_mkdir, + .symlink = ovl_symlink, + .unlink = ovl_unlink, + .rmdir = ovl_rmdir, + .rename2 = ovl_rename2, + .link = ovl_link, + .setattr = ovl_setattr, + .create = ovl_create, + .mknod = ovl_mknod, + .permission = ovl_permission, + .getattr = ovl_dir_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c new file mode 100644 index 000000000000..04f124884687 --- /dev/null +++ b/fs/overlayfs/inode.c @@ -0,0 +1,436 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/xattr.h> +#include "overlayfs.h" + +static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, + bool no_data) +{ + int err; + struct dentry *parent; + struct kstat stat; + struct path lowerpath; + + parent = dget_parent(dentry); + err = ovl_copy_up(parent); + if (err) + goto out_dput_parent; + + ovl_path_lower(dentry, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (err) + goto out_dput_parent; + + if (no_data) + stat.size = 0; + + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr); + +out_dput_parent: + dput(parent); + return err; +} + +int ovl_setattr(struct dentry *dentry, struct iattr *attr) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } else { + err = ovl_copy_up_last(dentry, attr, false); + } + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct path realpath; + + ovl_path_real(dentry, &realpath); + return vfs_getattr(&realpath, stat); +} + +int ovl_permission(struct inode *inode, int mask) +{ + struct ovl_entry *oe; + struct dentry *alias = NULL; + struct inode *realinode; + struct dentry *realdentry; + bool is_upper; + int err; + + if (S_ISDIR(inode->i_mode)) { + oe = inode->i_private; + } else if (mask & MAY_NOT_BLOCK) { + return -ECHILD; + } else { + /* + * For non-directories find an alias and get the info + * from there. + */ + alias = d_find_any_alias(inode); + if (WARN_ON(!alias)) + return -ENOENT; + + oe = alias->d_fsdata; + } + + realdentry = ovl_entry_real(oe, &is_upper); + + /* Careful in RCU walk mode */ + realinode = ACCESS_ONCE(realdentry->d_inode); + if (!realinode) { + WARN_ON(!(mask & MAY_NOT_BLOCK)); + err = -ENOENT; + goto out_dput; + } + + if (mask & MAY_WRITE) { + umode_t mode = realinode->i_mode; + + /* + * Writes will always be redirected to upper layer, so + * ignore lower layer being read-only. + * + * If the overlay itself is read-only then proceed + * with the permission check, don't return EROFS. + * This will only happen if this is the lower layer of + * another overlayfs. + * + * If upper fs becomes read-only after the overlay was + * constructed return EROFS to prevent modification of + * upper layer. + */ + err = -EROFS; + if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + goto out_dput; + } + + err = __inode_permission(realinode, mask); +out_dput: + dput(alias); + return err; +} + + +struct ovl_link_data { + struct dentry *realdentry; + void *cookie; +}; + +static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + void *ret; + struct dentry *realdentry; + struct inode *realinode; + + realdentry = ovl_dentry_real(dentry); + realinode = realdentry->d_inode; + + if (WARN_ON(!realinode->i_op->follow_link)) + return ERR_PTR(-EPERM); + + ret = realinode->i_op->follow_link(realdentry, nd); + if (IS_ERR(ret)) + return ret; + + if (realinode->i_op->put_link) { + struct ovl_link_data *data; + + data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); + if (!data) { + realinode->i_op->put_link(realdentry, nd, ret); + return ERR_PTR(-ENOMEM); + } + data->realdentry = realdentry; + data->cookie = ret; + + return data; + } else { + return NULL; + } +} + +static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c) +{ + struct inode *realinode; + struct ovl_link_data *data = c; + + if (!data) + return; + + realinode = data->realdentry->d_inode; + realinode->i_op->put_link(data->realdentry, nd, data->cookie); + kfree(data); +} + +static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + struct path realpath; + struct inode *realinode; + + ovl_path_real(dentry, &realpath); + realinode = realpath.dentry->d_inode; + + if (!realinode->i_op->readlink) + return -EINVAL; + + touch_atime(&realpath); + + return realinode->i_op->readlink(realpath.dentry, buf, bufsiz); +} + + +static bool ovl_is_private_xattr(const char *name) +{ + return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0; +} + +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = -EPERM; + if (ovl_is_private_xattr(name)) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + upperdentry = ovl_dentry_upper(dentry); + err = vfs_setxattr(upperdentry, name, value, size, flags); + +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static bool ovl_need_xattr_filter(struct dentry *dentry, + enum ovl_path_type type) +{ + if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER) + return S_ISDIR(dentry->d_inode->i_mode); + else + return false; +} + +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + return -ENODATA; + + return vfs_getxattr(realpath.dentry, name, value, size); +} + +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) +{ + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + ssize_t res; + int off; + + res = vfs_listxattr(realpath.dentry, list, size); + if (res <= 0 || size == 0) + return res; + + if (!ovl_need_xattr_filter(dentry, type)) + return res; + + /* filter out private xattrs */ + for (off = 0; off < res;) { + char *s = list + off; + size_t slen = strlen(s) + 1; + + BUG_ON(off + slen > res); + + if (ovl_is_private_xattr(s)) { + res -= slen; + memmove(s, s + slen, res - off); + } else { + off += slen; + } + } + + return res; +} + +int ovl_removexattr(struct dentry *dentry, const char *name) +{ + int err; + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = -ENODATA; + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + goto out_drop_write; + + if (!OVL_TYPE_UPPER(type)) { + err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (err < 0) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_removexattr(realpath.dentry, name); +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, + struct dentry *realdentry) +{ + if (OVL_TYPE_UPPER(type)) + return false; + + if (special_file(realdentry->d_inode->i_mode)) + return false; + + if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC)) + return false; + + return true; +} + +static int ovl_dentry_open(struct dentry *dentry, struct file *file, + const struct cred *cred) +{ + int err; + struct path realpath; + enum ovl_path_type type; + bool want_write = false; + + type = ovl_path_real(dentry, &realpath); + if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) { + want_write = true; + err = ovl_want_write(dentry); + if (err) + goto out; + + if (file->f_flags & O_TRUNC) + err = ovl_copy_up_last(dentry, NULL, true); + else + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_open(&realpath, file, cred); +out_drop_write: + if (want_write) + ovl_drop_write(dentry); +out: + return err; +} + +static const struct inode_operations ovl_file_inode_operations = { + .setattr = ovl_setattr, + .permission = ovl_permission, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, + .dentry_open = ovl_dentry_open, +}; + +static const struct inode_operations ovl_symlink_inode_operations = { + .setattr = ovl_setattr, + .follow_link = ovl_follow_link, + .put_link = ovl_put_link, + .readlink = ovl_readlink, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe) +{ + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return NULL; + + mode &= S_IFMT; + + inode->i_ino = get_next_ino(); + inode->i_mode = mode; + inode->i_flags |= S_NOATIME | S_NOCMTIME; + + switch (mode) { + case S_IFDIR: + inode->i_private = oe; + inode->i_op = &ovl_dir_inode_operations; + inode->i_fop = &ovl_dir_operations; + break; + + case S_IFLNK: + inode->i_op = &ovl_symlink_inode_operations; + break; + + case S_IFREG: + case S_IFSOCK: + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + inode->i_op = &ovl_file_inode_operations; + break; + + default: + WARN(1, "illegal file type: %i\n", mode); + iput(inode); + inode = NULL; + } + + return inode; +} diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h new file mode 100644 index 000000000000..17ac5afc9ffb --- /dev/null +++ b/fs/overlayfs/overlayfs.h @@ -0,0 +1,199 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/kernel.h> + +struct ovl_entry; + +enum ovl_path_type { + __OVL_PATH_PURE = (1 << 0), + __OVL_PATH_UPPER = (1 << 1), + __OVL_PATH_MERGE = (1 << 2), +}; + +#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER) +#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE) +#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE) +#define OVL_TYPE_MERGE_OR_LOWER(type) \ + (OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type)) + +#define OVL_XATTR_PRE_NAME "trusted.overlay." +#define OVL_XATTR_PRE_LEN 16 +#define OVL_XATTR_OPAQUE OVL_XATTR_PRE_NAME"opaque" + +static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_rmdir(dir, dentry); + pr_debug("rmdir(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_unlink(dir, dentry, NULL); + pr_debug("unlink(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry, bool debug) +{ + int err = vfs_link(old_dentry, dir, new_dentry, NULL); + if (debug) { + pr_debug("link(%pd2, %pd2) = %i\n", + old_dentry, new_dentry, err); + } + return err; +} + +static inline int ovl_do_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_create(dir, dentry, mode, true); + if (debug) + pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_mkdir(dir, dentry, mode); + if (debug) + pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev, bool debug) +{ + int err = vfs_mknod(dir, dentry, mode, dev); + if (debug) { + pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", + dentry, mode, dev, err); + } + return err; +} + +static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry, + const char *oldname, bool debug) +{ + int err = vfs_symlink(dir, dentry, oldname); + if (debug) + pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); + return err; +} + +static inline int ovl_do_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err = vfs_setxattr(dentry, name, value, size, flags); + pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n", + dentry, name, (int) size, (char *) value, flags, err); + return err; +} + +static inline int ovl_do_removexattr(struct dentry *dentry, const char *name) +{ + int err = vfs_removexattr(dentry, name); + pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); + return err; +} + +static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, + struct inode *newdir, struct dentry *newdentry, + unsigned int flags) +{ + int err; + + pr_debug("rename2(%pd2, %pd2, 0x%x)\n", + olddentry, newdentry, flags); + + err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags); + + if (err) { + pr_debug("...rename2(%pd2, %pd2, ...) = %i\n", + olddentry, newdentry, err); + } + return err; +} + +static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_whiteout(dir, dentry); + pr_debug("whiteout(%pd2) = %i\n", dentry, err); + return err; +} + +enum ovl_path_type ovl_path_type(struct dentry *dentry); +u64 ovl_dentry_version_get(struct dentry *dentry); +void ovl_dentry_version_inc(struct dentry *dentry); +void ovl_path_upper(struct dentry *dentry, struct path *path); +void ovl_path_lower(struct dentry *dentry, struct path *path); +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); +int ovl_path_next(int idx, struct dentry *dentry, struct path *path); +struct dentry *ovl_dentry_upper(struct dentry *dentry); +struct dentry *ovl_dentry_lower(struct dentry *dentry); +struct dentry *ovl_dentry_real(struct dentry *dentry); +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper); +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry); +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache); +struct dentry *ovl_workdir(struct dentry *dentry); +int ovl_want_write(struct dentry *dentry); +void ovl_drop_write(struct dentry *dentry); +bool ovl_dentry_is_opaque(struct dentry *dentry); +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque); +bool ovl_is_whiteout(struct dentry *dentry); +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +struct file *ovl_path_open(struct path *path, int flags); + +struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry, + struct kstat *stat, const char *link); + +/* readdir.c */ +extern const struct file_operations ovl_dir_operations; +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list); +void ovl_cache_free(struct list_head *list); + +/* inode.c */ +int ovl_setattr(struct dentry *dentry, struct iattr *attr); +int ovl_permission(struct inode *inode, int mask); +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); +int ovl_removexattr(struct dentry *dentry, const char *name); + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe); +static inline void ovl_copyattr(struct inode *from, struct inode *to) +{ + to->i_uid = from->i_uid; + to->i_gid = from->i_gid; +} + +/* dir.c */ +extern const struct inode_operations ovl_dir_inode_operations; +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry); +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug); +void ovl_cleanup(struct inode *dir, struct dentry *dentry); + +/* copy_up.c */ +int ovl_copy_up(struct dentry *dentry); +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr); +int ovl_copy_xattr(struct dentry *old, struct dentry *new); +int ovl_set_attr(struct dentry *upper, struct kstat *stat); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c new file mode 100644 index 000000000000..907870e81a72 --- /dev/null +++ b/fs/overlayfs/readdir.c @@ -0,0 +1,557 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/file.h> +#include <linux/xattr.h> +#include <linux/rbtree.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +struct ovl_cache_entry { + unsigned int len; + unsigned int type; + u64 ino; + struct list_head l_node; + struct rb_node node; + bool is_whiteout; + char name[]; +}; + +struct ovl_dir_cache { + long refcount; + u64 version; + struct list_head entries; +}; + +struct ovl_readdir_data { + struct dir_context ctx; + bool is_merge; + struct rb_root root; + struct list_head *list; + struct list_head middle; + struct dentry *dir; + int count; + int err; +}; + +struct ovl_dir_file { + bool is_real; + bool is_upper; + struct ovl_dir_cache *cache; + struct list_head *cursor; + struct file *realfile; + struct file *upperfile; +}; + +static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) +{ + return container_of(n, struct ovl_cache_entry, node); +} + +static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, + const char *name, int len) +{ + struct rb_node *node = root->rb_node; + int cmp; + + while (node) { + struct ovl_cache_entry *p = ovl_cache_entry_from_node(node); + + cmp = strncmp(name, p->name, len); + if (cmp > 0) + node = p->node.rb_right; + else if (cmp < 0 || len < p->len) + node = p->node.rb_left; + else + return p; + } + + return NULL; +} + +static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir, + const char *name, int len, + u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + size_t size = offsetof(struct ovl_cache_entry, name[len + 1]); + + p = kmalloc(size, GFP_KERNEL); + if (!p) + return NULL; + + memcpy(p->name, name, len); + p->name[len] = '\0'; + p->len = len; + p->type = d_type; + p->ino = ino; + p->is_whiteout = false; + + if (d_type == DT_CHR) { + struct dentry *dentry; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) { + kfree(p); + return NULL; + } + + /* + * CAP_DAC_OVERRIDE for lookup + */ + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + old_cred = override_creds(override_cred); + + dentry = lookup_one_len(name, dir, len); + if (!IS_ERR(dentry)) { + p->is_whiteout = ovl_is_whiteout(dentry); + dput(dentry); + } + revert_creds(old_cred); + put_cred(override_cred); + } + return p; +} + +static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, + const char *name, int len, u64 ino, + unsigned int d_type) +{ + struct rb_node **newp = &rdd->root.rb_node; + struct rb_node *parent = NULL; + struct ovl_cache_entry *p; + + while (*newp) { + int cmp; + struct ovl_cache_entry *tmp; + + parent = *newp; + tmp = ovl_cache_entry_from_node(*newp); + cmp = strncmp(name, tmp->name, len); + if (cmp > 0) + newp = &tmp->node.rb_right; + else if (cmp < 0 || len < tmp->len) + newp = &tmp->node.rb_left; + else + return 0; + } + + p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type); + if (p == NULL) + return -ENOMEM; + + list_add_tail(&p->l_node, rdd->list); + rb_link_node(&p->node, parent, newp); + rb_insert_color(&p->node, &rdd->root); + + return 0; +} + +static int ovl_fill_lower(struct ovl_readdir_data *rdd, + const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + + p = ovl_cache_entry_find(&rdd->root, name, namelen); + if (p) { + list_move_tail(&p->l_node, &rdd->middle); + } else { + p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type); + if (p == NULL) + rdd->err = -ENOMEM; + else + list_add_tail(&p->l_node, &rdd->middle); + } + + return rdd->err; +} + +void ovl_cache_free(struct list_head *list) +{ + struct ovl_cache_entry *p; + struct ovl_cache_entry *n; + + list_for_each_entry_safe(p, n, list, l_node) + kfree(p); + + INIT_LIST_HEAD(list); +} + +static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) +{ + struct ovl_dir_cache *cache = od->cache; + + WARN_ON(cache->refcount <= 0); + cache->refcount--; + if (!cache->refcount) { + if (ovl_dir_cache(dentry) == cache) + ovl_set_dir_cache(dentry, NULL); + + ovl_cache_free(&cache->entries); + kfree(cache); + } +} + +static int ovl_fill_merge(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct ovl_readdir_data *rdd = + container_of(ctx, struct ovl_readdir_data, ctx); + + rdd->count++; + if (!rdd->is_merge) + return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type); + else + return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type); +} + +static inline int ovl_dir_read(struct path *realpath, + struct ovl_readdir_data *rdd) +{ + struct file *realfile; + int err; + + realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY); + if (IS_ERR(realfile)) + return PTR_ERR(realfile); + + rdd->dir = realpath->dentry; + rdd->ctx.pos = 0; + do { + rdd->count = 0; + rdd->err = 0; + err = iterate_dir(realfile, &rdd->ctx); + if (err >= 0) + err = rdd->err; + } while (!err && rdd->count); + fput(realfile); + + return err; +} + +static void ovl_dir_reset(struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + struct ovl_dir_cache *cache = od->cache; + struct dentry *dentry = file->f_path.dentry; + enum ovl_path_type type = ovl_path_type(dentry); + + if (cache && ovl_dentry_version_get(dentry) != cache->version) { + ovl_cache_put(od, dentry); + od->cache = NULL; + od->cursor = NULL; + } + WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type)); + if (od->is_real && OVL_TYPE_MERGE(type)) + od->is_real = false; +} + +static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) +{ + int err; + struct path realpath; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_merge, + .list = list, + .root = RB_ROOT, + .is_merge = false, + }; + int idx, next; + + for (idx = 0; idx != -1; idx = next) { + next = ovl_path_next(idx, dentry, &realpath); + + if (next != -1) { + err = ovl_dir_read(&realpath, &rdd); + if (err) + break; + } else { + /* + * Insert lowest layer entries before upper ones, this + * allows offsets to be reasonably constant + */ + list_add(&rdd.middle, rdd.list); + rdd.is_merge = true; + err = ovl_dir_read(&realpath, &rdd); + list_del(&rdd.middle); + } + } + return err; +} + +static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) +{ + struct list_head *p; + loff_t off = 0; + + list_for_each(p, &od->cache->entries) { + if (off >= pos) + break; + off++; + } + /* Cursor is safe since the cache is stable */ + od->cursor = p; +} + +static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) +{ + int res; + struct ovl_dir_cache *cache; + + cache = ovl_dir_cache(dentry); + if (cache && ovl_dentry_version_get(dentry) == cache->version) { + cache->refcount++; + return cache; + } + ovl_set_dir_cache(dentry, NULL); + + cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); + if (!cache) + return ERR_PTR(-ENOMEM); + + cache->refcount = 1; + INIT_LIST_HEAD(&cache->entries); + + res = ovl_dir_read_merged(dentry, &cache->entries); + if (res) { + ovl_cache_free(&cache->entries); + kfree(cache); + return ERR_PTR(res); + } + + cache->version = ovl_dentry_version_get(dentry); + ovl_set_dir_cache(dentry, cache); + + return cache; +} + +static int ovl_iterate(struct file *file, struct dir_context *ctx) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct ovl_cache_entry *p; + + if (!ctx->pos) + ovl_dir_reset(file); + + if (od->is_real) + return iterate_dir(od->realfile, ctx); + + if (!od->cache) { + struct ovl_dir_cache *cache; + + cache = ovl_cache_get(dentry); + if (IS_ERR(cache)) + return PTR_ERR(cache); + + od->cache = cache; + ovl_seek_cursor(od, ctx->pos); + } + + while (od->cursor != &od->cache->entries) { + p = list_entry(od->cursor, struct ovl_cache_entry, l_node); + if (!p->is_whiteout) + if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) + break; + od->cursor = p->l_node.next; + ctx->pos++; + } + return 0; +} + +static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t res; + struct ovl_dir_file *od = file->private_data; + + mutex_lock(&file_inode(file)->i_mutex); + if (!file->f_pos) + ovl_dir_reset(file); + + if (od->is_real) { + res = vfs_llseek(od->realfile, offset, origin); + file->f_pos = od->realfile->f_pos; + } else { + res = -EINVAL; + + switch (origin) { + case SEEK_CUR: + offset += file->f_pos; + break; + case SEEK_SET: + break; + default: + goto out_unlock; + } + if (offset < 0) + goto out_unlock; + + if (offset != file->f_pos) { + file->f_pos = offset; + if (od->cache) + ovl_seek_cursor(od, offset); + } + res = offset; + } +out_unlock: + mutex_unlock(&file_inode(file)->i_mutex); + + return res; +} + +static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct file *realfile = od->realfile; + + /* + * Need to check if we started out being a lower dir, but got copied up + */ + if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) { + struct inode *inode = file_inode(file); + + realfile = lockless_dereference(od->upperfile); + if (!realfile) { + struct path upperpath; + + ovl_path_upper(dentry, &upperpath); + realfile = ovl_path_open(&upperpath, O_RDONLY); + smp_mb__before_spinlock(); + mutex_lock(&inode->i_mutex); + if (!od->upperfile) { + if (IS_ERR(realfile)) { + mutex_unlock(&inode->i_mutex); + return PTR_ERR(realfile); + } + od->upperfile = realfile; + } else { + /* somebody has beaten us to it */ + if (!IS_ERR(realfile)) + fput(realfile); + realfile = od->upperfile; + } + mutex_unlock(&inode->i_mutex); + } + } + + return vfs_fsync_range(realfile, start, end, datasync); +} + +static int ovl_dir_release(struct inode *inode, struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + + if (od->cache) { + mutex_lock(&inode->i_mutex); + ovl_cache_put(od, file->f_path.dentry); + mutex_unlock(&inode->i_mutex); + } + fput(od->realfile); + if (od->upperfile) + fput(od->upperfile); + kfree(od); + + return 0; +} + +static int ovl_dir_open(struct inode *inode, struct file *file) +{ + struct path realpath; + struct file *realfile; + struct ovl_dir_file *od; + enum ovl_path_type type; + + od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + if (!od) + return -ENOMEM; + + type = ovl_path_real(file->f_path.dentry, &realpath); + realfile = ovl_path_open(&realpath, file->f_flags); + if (IS_ERR(realfile)) { + kfree(od); + return PTR_ERR(realfile); + } + od->realfile = realfile; + od->is_real = !OVL_TYPE_MERGE(type); + od->is_upper = OVL_TYPE_UPPER(type); + file->private_data = od; + + return 0; +} + +const struct file_operations ovl_dir_operations = { + .read = generic_read_dir, + .open = ovl_dir_open, + .iterate = ovl_iterate, + .llseek = ovl_dir_llseek, + .fsync = ovl_dir_fsync, + .release = ovl_dir_release, +}; + +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) +{ + int err; + struct ovl_cache_entry *p; + + err = ovl_dir_read_merged(dentry, list); + if (err) + return err; + + err = 0; + + list_for_each_entry(p, list, l_node) { + if (p->is_whiteout) + continue; + + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + err = -ENOTEMPTY; + break; + } + + return err; +} + +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) +{ + struct ovl_cache_entry *p; + + mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD); + list_for_each_entry(p, list, l_node) { + struct dentry *dentry; + + if (!p->is_whiteout) + continue; + + dentry = lookup_one_len(p->name, upper, p->len); + if (IS_ERR(dentry)) { + pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n", + upper->d_name.name, p->len, p->name, + (int) PTR_ERR(dentry)); + continue; + } + ovl_cleanup(upper->d_inode, dentry); + dput(dentry); + } + mutex_unlock(&upper->d_inode->i_mutex); +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c new file mode 100644 index 000000000000..5f0d1993e6e3 --- /dev/null +++ b/fs/overlayfs/super.c @@ -0,0 +1,1046 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/mount.h> +#include <linux/slab.h> +#include <linux/parser.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/statfs.h> +#include <linux/seq_file.h> +#include "overlayfs.h" + +MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); +MODULE_DESCRIPTION("Overlay filesystem"); +MODULE_LICENSE("GPL"); + +#define OVERLAYFS_SUPER_MAGIC 0x794c7630 + +struct ovl_config { + char *lowerdir; + char *upperdir; + char *workdir; +}; + +/* private information held for overlayfs's superblock */ +struct ovl_fs { + struct vfsmount *upper_mnt; + unsigned numlower; + struct vfsmount **lower_mnt; + struct dentry *workdir; + long lower_namelen; + /* pathnames of lower and upper dirs, for show_options */ + struct ovl_config config; +}; + +struct ovl_dir_cache; + +/* private information held for every overlayfs dentry */ +struct ovl_entry { + struct dentry *__upperdentry; + struct ovl_dir_cache *cache; + union { + struct { + u64 version; + bool opaque; + }; + struct rcu_head rcu; + }; + unsigned numlower; + struct path lowerstack[]; +}; + +#define OVL_MAX_STACK 500 + +static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe) +{ + return oe->numlower ? oe->lowerstack[0].dentry : NULL; +} + +enum ovl_path_type ovl_path_type(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + enum ovl_path_type type = 0; + + if (oe->__upperdentry) { + type = __OVL_PATH_UPPER; + + if (oe->numlower) { + if (S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + } else if (!oe->opaque) { + type |= __OVL_PATH_PURE; + } + } else { + if (oe->numlower > 1) + type |= __OVL_PATH_MERGE; + } + return type; +} + +static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) +{ + return lockless_dereference(oe->__upperdentry); +} + +void ovl_path_upper(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->upper_mnt; + path->dentry = ovl_upperdentry_dereference(oe); +} + +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) +{ + enum ovl_path_type type = ovl_path_type(dentry); + + if (!OVL_TYPE_UPPER(type)) + ovl_path_lower(dentry, path); + else + ovl_path_upper(dentry, path); + + return type; +} + +struct dentry *ovl_dentry_upper(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return ovl_upperdentry_dereference(oe); +} + +struct dentry *ovl_dentry_lower(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return __ovl_dentry_lower(oe); +} + +struct dentry *ovl_dentry_real(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (!realdentry) + realdentry = __ovl_dentry_lower(oe); + + return realdentry; +} + +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper) +{ + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (realdentry) { + *is_upper = true; + } else { + realdentry = __ovl_dentry_lower(oe); + *is_upper = false; + } + return realdentry; +} + +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->cache; +} + +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + oe->cache = cache; +} + +void ovl_path_lower(struct dentry *dentry, struct path *path) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + *path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL }; +} + +int ovl_want_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return mnt_want_write(ofs->upper_mnt); +} + +void ovl_drop_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + mnt_drop_write(ofs->upper_mnt); +} + +struct dentry *ovl_workdir(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return ofs->workdir; +} + +bool ovl_dentry_is_opaque(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + return oe->opaque; +} + +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque) +{ + struct ovl_entry *oe = dentry->d_fsdata; + oe->opaque = opaque; +} + +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex)); + WARN_ON(oe->__upperdentry); + BUG_ON(!upperdentry->d_inode); + /* + * Make sure upperdentry is consistent before making it visible to + * ovl_upperdentry_dereference(). + */ + smp_wmb(); + oe->__upperdentry = upperdentry; +} + +void ovl_dentry_version_inc(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + oe->version++; +} + +u64 ovl_dentry_version_get(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + return oe->version; +} + +bool ovl_is_whiteout(struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + + return inode && IS_WHITEOUT(inode); +} + +static bool ovl_is_opaquedir(struct dentry *dentry) +{ + int res; + char val; + struct inode *inode = dentry->d_inode; + + if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr) + return false; + + res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +static void ovl_dentry_release(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe) { + unsigned int i; + + dput(oe->__upperdentry); + for (i = 0; i < oe->numlower; i++) + dput(oe->lowerstack[i].dentry); + kfree_rcu(oe, rcu); + } +} + +static const struct dentry_operations ovl_dentry_operations = { + .d_release = ovl_dentry_release, +}; + +static struct ovl_entry *ovl_alloc_entry(unsigned int numlower) +{ + size_t size = offsetof(struct ovl_entry, lowerstack[numlower]); + struct ovl_entry *oe = kzalloc(size, GFP_KERNEL); + + if (oe) + oe->numlower = numlower; + + return oe; +} + +static inline struct dentry *ovl_lookup_real(struct dentry *dir, + struct qstr *name) +{ + struct dentry *dentry; + + mutex_lock(&dir->d_inode->i_mutex); + dentry = lookup_one_len(name->name, dir, name->len); + mutex_unlock(&dir->d_inode->i_mutex); + + if (IS_ERR(dentry)) { + if (PTR_ERR(dentry) == -ENOENT) + dentry = NULL; + } else if (!dentry->d_inode) { + dput(dentry); + dentry = NULL; + } + return dentry; +} + +/* + * Returns next layer in stack starting from top. + * Returns -1 if this is the last layer. + */ +int ovl_path_next(int idx, struct dentry *dentry, struct path *path) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + BUG_ON(idx < 0); + if (idx == 0) { + ovl_path_upper(dentry, path); + if (path->dentry) + return oe->numlower ? 1 : -1; + idx++; + } + BUG_ON(idx > oe->numlower); + *path = oe->lowerstack[idx - 1]; + + return (idx < oe->numlower) ? idx + 1 : -1; +} + +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct ovl_entry *oe; + struct ovl_entry *poe = dentry->d_parent->d_fsdata; + struct path *stack = NULL; + struct dentry *upperdir, *upperdentry = NULL; + unsigned int ctr = 0; + struct inode *inode = NULL; + bool upperopaque = false; + struct dentry *this, *prev = NULL; + unsigned int i; + int err; + + upperdir = ovl_upperdentry_dereference(poe); + if (upperdir) { + this = ovl_lookup_real(upperdir, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) + goto out; + + if (this) { + if (ovl_is_whiteout(this)) { + dput(this); + this = NULL; + upperopaque = true; + } else if (poe->numlower && ovl_is_opaquedir(this)) { + upperopaque = true; + } + } + upperdentry = prev = this; + } + + if (!upperopaque && poe->numlower) { + err = -ENOMEM; + stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_put_upper; + } + + for (i = 0; !upperopaque && i < poe->numlower; i++) { + bool opaque = false; + struct path lowerpath = poe->lowerstack[i]; + + this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) { + /* + * If it's positive, then treat ENAMETOOLONG as ENOENT. + */ + if (err == -ENAMETOOLONG && (upperdentry || ctr)) + continue; + goto out_put; + } + if (!this) + continue; + if (ovl_is_whiteout(this)) { + dput(this); + break; + } + /* + * Only makes sense to check opaque dir if this is not the + * lowermost layer. + */ + if (i < poe->numlower - 1 && ovl_is_opaquedir(this)) + opaque = true; + + if (prev && (!S_ISDIR(prev->d_inode->i_mode) || + !S_ISDIR(this->d_inode->i_mode))) { + /* + * FIXME: check for upper-opaqueness maybe better done + * in remove code. + */ + if (prev == upperdentry) + upperopaque = true; + dput(this); + break; + } + /* + * If this is a non-directory then stop here. + */ + if (!S_ISDIR(this->d_inode->i_mode)) + opaque = true; + + stack[ctr].dentry = this; + stack[ctr].mnt = lowerpath.mnt; + ctr++; + prev = this; + if (opaque) + break; + } + + oe = ovl_alloc_entry(ctr); + err = -ENOMEM; + if (!oe) + goto out_put; + + if (upperdentry || ctr) { + struct dentry *realdentry; + + realdentry = upperdentry ? upperdentry : stack[0].dentry; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode, + oe); + if (!inode) + goto out_free_oe; + ovl_copyattr(realdentry->d_inode, inode); + } + + oe->opaque = upperopaque; + oe->__upperdentry = upperdentry; + memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); + kfree(stack); + dentry->d_fsdata = oe; + d_add(dentry, inode); + + return NULL; + +out_free_oe: + kfree(oe); +out_put: + for (i = 0; i < ctr; i++) + dput(stack[i].dentry); + kfree(stack); +out_put_upper: + dput(upperdentry); +out: + return ERR_PTR(err); +} + +struct file *ovl_path_open(struct path *path, int flags) +{ + return dentry_open(path, flags, current_cred()); +} + +static void ovl_put_super(struct super_block *sb) +{ + struct ovl_fs *ufs = sb->s_fs_info; + unsigned i; + + dput(ufs->workdir); + mntput(ufs->upper_mnt); + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); + + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); + kfree(ufs); +} + +/** + * ovl_statfs + * @sb: The overlayfs super block + * @buf: The struct kstatfs to fill in with stats + * + * Get the filesystem statistics. As writes always target the upper layer + * filesystem pass the statfs to the upper filesystem (if it exists) + */ +static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct dentry *root_dentry = dentry->d_sb->s_root; + struct path path; + int err; + + ovl_path_real(root_dentry, &path); + + err = vfs_statfs(&path, buf); + if (!err) { + buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen); + buf->f_type = OVERLAYFS_SUPER_MAGIC; + } + + return err; +} + +/** + * ovl_show_options + * + * Prints the mount options for a given superblock. + * Returns zero; does not fail. + */ +static int ovl_show_options(struct seq_file *m, struct dentry *dentry) +{ + struct super_block *sb = dentry->d_sb; + struct ovl_fs *ufs = sb->s_fs_info; + + seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir); + if (ufs->config.upperdir) { + seq_printf(m, ",upperdir=%s", ufs->config.upperdir); + seq_printf(m, ",workdir=%s", ufs->config.workdir); + } + return 0; +} + +static int ovl_remount(struct super_block *sb, int *flags, char *data) +{ + struct ovl_fs *ufs = sb->s_fs_info; + + if (!(*flags & MS_RDONLY) && !ufs->upper_mnt) + return -EROFS; + + return 0; +} + +static const struct super_operations ovl_super_operations = { + .put_super = ovl_put_super, + .statfs = ovl_statfs, + .show_options = ovl_show_options, + .remount_fs = ovl_remount, +}; + +enum { + OPT_LOWERDIR, + OPT_UPPERDIR, + OPT_WORKDIR, + OPT_ERR, +}; + +static const match_table_t ovl_tokens = { + {OPT_LOWERDIR, "lowerdir=%s"}, + {OPT_UPPERDIR, "upperdir=%s"}, + {OPT_WORKDIR, "workdir=%s"}, + {OPT_ERR, NULL} +}; + +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + +static int ovl_parse_opt(char *opt, struct ovl_config *config) +{ + char *p; + + while ((p = ovl_next_opt(&opt)) != NULL) { + int token; + substring_t args[MAX_OPT_ARGS]; + + if (!*p) + continue; + + token = match_token(p, ovl_tokens, args); + switch (token) { + case OPT_UPPERDIR: + kfree(config->upperdir); + config->upperdir = match_strdup(&args[0]); + if (!config->upperdir) + return -ENOMEM; + break; + + case OPT_LOWERDIR: + kfree(config->lowerdir); + config->lowerdir = match_strdup(&args[0]); + if (!config->lowerdir) + return -ENOMEM; + break; + + case OPT_WORKDIR: + kfree(config->workdir); + config->workdir = match_strdup(&args[0]); + if (!config->workdir) + return -ENOMEM; + break; + + default: + pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); + return -EINVAL; + } + } + + /* Workdir is useless in non-upper mount */ + if (!config->upperdir && config->workdir) { + pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n", + config->workdir); + kfree(config->workdir); + config->workdir = NULL; + } + + return 0; +} + +#define OVL_WORKDIR_NAME "work" + +static struct dentry *ovl_workdir_create(struct vfsmount *mnt, + struct dentry *dentry) +{ + struct inode *dir = dentry->d_inode; + struct dentry *work; + int err; + bool retried = false; + + err = mnt_want_write(mnt); + if (err) + return ERR_PTR(err); + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); +retry: + work = lookup_one_len(OVL_WORKDIR_NAME, dentry, + strlen(OVL_WORKDIR_NAME)); + + if (!IS_ERR(work)) { + struct kstat stat = { + .mode = S_IFDIR | 0, + }; + + if (work->d_inode) { + err = -EEXIST; + if (retried) + goto out_dput; + + retried = true; + ovl_cleanup(dir, work); + dput(work); + goto retry; + } + + err = ovl_create_real(dir, work, &stat, NULL, NULL, true); + if (err) + goto out_dput; + } +out_unlock: + mutex_unlock(&dir->i_mutex); + mnt_drop_write(mnt); + + return work; + +out_dput: + dput(work); + work = ERR_PTR(err); + goto out_unlock; +} + +static void ovl_unescape(char *s) +{ + char *d = s; + + for (;; s++, d++) { + if (*s == '\\') + s++; + *d = *s; + if (!*s) + break; + } +} + +static bool ovl_is_allowed_fs_type(struct dentry *root) +{ + const struct dentry_operations *dop = root->d_op; + + /* + * We don't support: + * - automount filesystems + * - filesystems with revalidate (FIXME for lower layer) + * - filesystems with case insensitive names + */ + if (dop && + (dop->d_manage || dop->d_automount || + dop->d_revalidate || dop->d_weak_revalidate || + dop->d_compare || dop->d_hash)) { + return false; + } + return true; +} + +static int ovl_mount_dir_noesc(const char *name, struct path *path) +{ + int err = -EINVAL; + + if (!*name) { + pr_err("overlayfs: empty lowerdir\n"); + goto out; + } + err = kern_path(name, LOOKUP_FOLLOW, path); + if (err) { + pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + goto out; + } + err = -EINVAL; + if (!ovl_is_allowed_fs_type(path->dentry)) { + pr_err("overlayfs: filesystem on '%s' not supported\n", name); + goto out_put; + } + if (!S_ISDIR(path->dentry->d_inode->i_mode)) { + pr_err("overlayfs: '%s' not a directory\n", name); + goto out_put; + } + return 0; + +out_put: + path_put(path); +out: + return err; +} + +static int ovl_mount_dir(const char *name, struct path *path) +{ + int err = -ENOMEM; + char *tmp = kstrdup(name, GFP_KERNEL); + + if (tmp) { + ovl_unescape(tmp); + err = ovl_mount_dir_noesc(tmp, path); + kfree(tmp); + } + return err; +} + +static int ovl_lower_dir(const char *name, struct path *path, long *namelen, + int *stack_depth) +{ + int err; + struct kstatfs statfs; + + err = ovl_mount_dir_noesc(name, path); + if (err) + goto out; + + err = vfs_statfs(path, &statfs); + if (err) { + pr_err("overlayfs: statfs failed on '%s'\n", name); + goto out_put; + } + *namelen = max(*namelen, statfs.f_namelen); + *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth); + + return 0; + +out_put: + path_put(path); +out: + return err; +} + +/* Workdir should not be subdir of upperdir and vice versa */ +static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) +{ + bool ok = false; + + if (workdir != upperdir) { + ok = (lock_rename(workdir, upperdir) == NULL); + unlock_rename(workdir, upperdir); + } + return ok; +} + +static unsigned int ovl_split_lowerdirs(char *str) +{ + unsigned int ctr = 1; + char *s, *d; + + for (s = d = str;; s++, d++) { + if (*s == '\\') { + s++; + } else if (*s == ':') { + *d = '\0'; + ctr++; + continue; + } + *d = *s; + if (!*s) + break; + } + return ctr; +} + +static int ovl_fill_super(struct super_block *sb, void *data, int silent) +{ + struct path upperpath = { NULL, NULL }; + struct path workpath = { NULL, NULL }; + struct dentry *root_dentry; + struct ovl_entry *oe; + struct ovl_fs *ufs; + struct path *stack = NULL; + char *lowertmp; + char *lower; + unsigned int numlower; + unsigned int stacklen = 0; + unsigned int i; + int err; + + err = -ENOMEM; + ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ufs) + goto out; + + err = ovl_parse_opt((char *) data, &ufs->config); + if (err) + goto out_free_config; + + err = -EINVAL; + if (!ufs->config.lowerdir) { + pr_err("overlayfs: missing 'lowerdir'\n"); + goto out_free_config; + } + + sb->s_stack_depth = 0; + if (ufs->config.upperdir) { + if (!ufs->config.workdir) { + pr_err("overlayfs: missing 'workdir'\n"); + goto out_free_config; + } + + err = ovl_mount_dir(ufs->config.upperdir, &upperpath); + if (err) + goto out_free_config; + + /* Upper fs should not be r/o */ + if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) { + pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n"); + err = -EINVAL; + goto out_put_upperpath; + } + + err = ovl_mount_dir(ufs->config.workdir, &workpath); + if (err) + goto out_put_upperpath; + + err = -EINVAL; + if (upperpath.mnt != workpath.mnt) { + pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); + goto out_put_workpath; + } + if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) { + pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); + goto out_put_workpath; + } + sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth; + } + err = -ENOMEM; + lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL); + if (!lowertmp) + goto out_put_workpath; + + err = -EINVAL; + stacklen = ovl_split_lowerdirs(lowertmp); + if (stacklen > OVL_MAX_STACK) { + pr_err("overlayfs: too many lower directries, limit is %d\n", + OVL_MAX_STACK); + goto out_free_lowertmp; + } else if (!ufs->config.upperdir && stacklen == 1) { + pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n"); + goto out_free_lowertmp; + } + + stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_free_lowertmp; + + lower = lowertmp; + for (numlower = 0; numlower < stacklen; numlower++) { + err = ovl_lower_dir(lower, &stack[numlower], + &ufs->lower_namelen, &sb->s_stack_depth); + if (err) + goto out_put_lowerpath; + + lower = strchr(lower, '\0') + 1; + } + + err = -EINVAL; + sb->s_stack_depth++; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("overlayfs: maximum fs stacking depth exceeded\n"); + goto out_put_lowerpath; + } + + if (ufs->config.upperdir) { + ufs->upper_mnt = clone_private_mount(&upperpath); + err = PTR_ERR(ufs->upper_mnt); + if (IS_ERR(ufs->upper_mnt)) { + pr_err("overlayfs: failed to clone upperpath\n"); + goto out_put_lowerpath; + } + + ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); + err = PTR_ERR(ufs->workdir); + if (IS_ERR(ufs->workdir)) { + pr_err("overlayfs: failed to create directory %s/%s\n", + ufs->config.workdir, OVL_WORKDIR_NAME); + goto out_put_upper_mnt; + } + } + + err = -ENOMEM; + ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL); + if (ufs->lower_mnt == NULL) + goto out_put_workdir; + for (i = 0; i < numlower; i++) { + struct vfsmount *mnt = clone_private_mount(&stack[i]); + + err = PTR_ERR(mnt); + if (IS_ERR(mnt)) { + pr_err("overlayfs: failed to clone lowerpath\n"); + goto out_put_lower_mnt; + } + /* + * Make lower_mnt R/O. That way fchmod/fchown on lower file + * will fail instead of modifying lower fs. + */ + mnt->mnt_flags |= MNT_READONLY; + + ufs->lower_mnt[ufs->numlower] = mnt; + ufs->numlower++; + } + + /* If the upper fs is nonexistent, we mark overlayfs r/o too */ + if (!ufs->upper_mnt) + sb->s_flags |= MS_RDONLY; + + sb->s_d_op = &ovl_dentry_operations; + + err = -ENOMEM; + oe = ovl_alloc_entry(numlower); + if (!oe) + goto out_put_lower_mnt; + + root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe)); + if (!root_dentry) + goto out_free_oe; + + mntput(upperpath.mnt); + for (i = 0; i < numlower; i++) + mntput(stack[i].mnt); + path_put(&workpath); + kfree(lowertmp); + + oe->__upperdentry = upperpath.dentry; + for (i = 0; i < numlower; i++) { + oe->lowerstack[i].dentry = stack[i].dentry; + oe->lowerstack[i].mnt = ufs->lower_mnt[i]; + } + + root_dentry->d_fsdata = oe; + + sb->s_magic = OVERLAYFS_SUPER_MAGIC; + sb->s_op = &ovl_super_operations; + sb->s_root = root_dentry; + sb->s_fs_info = ufs; + + return 0; + +out_free_oe: + kfree(oe); +out_put_lower_mnt: + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); +out_put_workdir: + dput(ufs->workdir); +out_put_upper_mnt: + mntput(ufs->upper_mnt); +out_put_lowerpath: + for (i = 0; i < numlower; i++) + path_put(&stack[i]); + kfree(stack); +out_free_lowertmp: + kfree(lowertmp); +out_put_workpath: + path_put(&workpath); +out_put_upperpath: + path_put(&upperpath); +out_free_config: + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); + kfree(ufs); +out: + return err; +} + +static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + return mount_nodev(fs_type, flags, raw_data, ovl_fill_super); +} + +static struct file_system_type ovl_fs_type = { + .owner = THIS_MODULE, + .name = "overlay", + .mount = ovl_mount, + .kill_sb = kill_anon_super, +}; +MODULE_ALIAS_FS("overlay"); + +static int __init ovl_init(void) +{ + return register_filesystem(&ovl_fs_type); +} + +static void __exit ovl_exit(void) +{ + unregister_filesystem(&ovl_fs_type); +} + +module_init(ovl_init); +module_exit(ovl_exit); diff --git a/fs/proc/Makefile b/fs/proc/Makefile index ab30716584f5..239493ec718e 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -27,6 +27,5 @@ proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o -proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o diff --git a/fs/proc/base.c b/fs/proc/base.c index b9760628e1fd..489ba8caafc0 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2555,6 +2555,57 @@ static const struct file_operations proc_projid_map_operations = { .llseek = seq_lseek, .release = proc_id_map_release, }; + +static int proc_setgroups_open(struct inode *inode, struct file *file) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + int ret; + + ret = -ESRCH; + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + if (file->f_mode & FMODE_WRITE) { + ret = -EACCES; + if (!ns_capable(ns, CAP_SYS_ADMIN)) + goto err_put_ns; + } + + ret = single_open(file, &proc_setgroups_show, ns); + if (ret) + goto err_put_ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_setgroups_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + int ret = single_release(inode, file); + put_user_ns(ns); + return ret; +} + +static const struct file_operations proc_setgroups_operations = { + .open = proc_setgroups_open, + .write = proc_setgroups_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_setgroups_release, +}; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, @@ -2663,6 +2714,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_CHECKPOINT_RESTORE REG("timers", S_IRUGO, proc_timers_operations), @@ -2998,6 +3050,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index b7f268eb5f45..2e2d9d5d78d9 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -19,7 +19,6 @@ #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> -#include <linux/namei.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/completion.h> @@ -162,17 +161,6 @@ void proc_free_inum(unsigned int inum) spin_unlock_irqrestore(&proc_inum_lock, flags); } -static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - nd_set_link(nd, __PDE_DATA(dentry->d_inode)); - return NULL; -} - -static const struct inode_operations proc_link_inode_operations = { - .readlink = generic_readlink, - .follow_link = proc_follow_link, -}; - /* * Don't create negative dentries here, return -ENOENT by hand * instead. diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43c7090..2f2815f3176e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/mount.h> #include <linux/magic.h> +#include <linux/namei.h> #include <asm/uaccess.h> @@ -401,6 +402,26 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif +static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct proc_dir_entry *pde = PDE(dentry->d_inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + nd_set_link(nd, pde->data); + return pde; +} + +static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p) +{ + unuse_pde(p); +} + +const struct inode_operations proc_link_inode_operations = { + .readlink = generic_readlink, + .follow_link = proc_follow_link, + .put_link = proc_put_link, +}; + struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { struct inode *inode = new_inode_pseudo(sb); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 651d09a11dde..8b24f3640cd9 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -202,6 +202,7 @@ struct pde_opener { int closing; struct completion *c; }; +extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; @@ -211,13 +212,6 @@ extern int proc_fill_super(struct super_block *); extern void proc_entry_rundown(struct proc_dir_entry *); /* - * proc_devtree.c - */ -#ifdef CONFIG_PROC_DEVICETREE -extern void proc_device_tree_init(void); -#endif - -/* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 9ae46b87470d..89026095f2b5 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl struct task_struct *task; void *ns; char name[50]; - int len = -EACCES; + int res = -EACCES; task = get_proc_task(inode); if (!task) @@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; - len = -ENOENT; + res = -ENOENT; ns = ns_ops->get(task); if (!ns) goto out_put_task; snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns)); - len = strlen(name); - - if (len > buflen) - len = buflen; - if (copy_to_user(buffer, name, len)) - len = -EFAULT; - + res = readlink_copy(buffer, buflen, name); ns_ops->put(ns); out_put_task: put_task_struct(task); out: - return len; + return res; } static const struct inode_operations proc_ns_link_inode_operations = { diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c deleted file mode 100644 index c82dd5147845..000000000000 --- a/fs/proc/proc_devtree.c +++ /dev/null @@ -1,241 +0,0 @@ -/* - * proc_devtree.c - handles /proc/device-tree - * - * Copyright 1997 Paul Mackerras - */ -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/time.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/printk.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <linux/of.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <asm/uaccess.h> -#include "internal.h" - -static inline void set_node_proc_entry(struct device_node *np, - struct proc_dir_entry *de) -{ - np->pde = de; -} - -static struct proc_dir_entry *proc_device_tree; - -/* - * Supply data on a read from /proc/device-tree/node/property. - */ -static int property_proc_show(struct seq_file *m, void *v) -{ - struct property *pp = m->private; - - seq_write(m, pp->value, pp->length); - return 0; -} - -static int property_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, property_proc_show, __PDE_DATA(inode)); -} - -static const struct file_operations property_proc_fops = { - .owner = THIS_MODULE, - .open = property_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -/* - * For a node with a name like "gc@10", we make symlinks called "gc" - * and "@10" to it. - */ - -/* - * Add a property to a node - */ -static struct proc_dir_entry * -__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp, - const char *name) -{ - struct proc_dir_entry *ent; - - /* - * Unfortunately proc_register puts each new entry - * at the beginning of the list. So we rearrange them. - */ - ent = proc_create_data(name, - strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR, - de, &property_proc_fops, pp); - if (ent == NULL) - return NULL; - - if (!strncmp(name, "security-", 9)) - proc_set_size(ent, 0); /* don't leak number of password chars */ - else - proc_set_size(ent, pp->length); - - return ent; -} - - -void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop) -{ - __proc_device_tree_add_prop(pde, prop, prop->name); -} - -void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop) -{ - remove_proc_entry(prop->name, pde); -} - -void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop) -{ - struct proc_dir_entry *ent; - - if (!oldprop) { - proc_device_tree_add_prop(pde, newprop); - return; - } - - for (ent = pde->subdir; ent != NULL; ent = ent->next) - if (ent->data == oldprop) - break; - if (ent == NULL) { - pr_warn("device-tree: property \"%s\" does not exist\n", - oldprop->name); - } else { - ent->data = newprop; - ent->size = newprop->length; - } -} - -/* - * Various dodgy firmware might give us nodes and/or properties with - * conflicting names. That's generally ok, except for exporting via /proc, - * so munge names here to ensure they're unique. - */ - -static int duplicate_name(struct proc_dir_entry *de, const char *name) -{ - struct proc_dir_entry *ent; - int found = 0; - - spin_lock(&proc_subdir_lock); - - for (ent = de->subdir; ent != NULL; ent = ent->next) { - if (strcmp(ent->name, name) == 0) { - found = 1; - break; - } - } - - spin_unlock(&proc_subdir_lock); - - return found; -} - -static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de, - const char *name) -{ - char *fixed_name; - int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */ - int i = 1, size; - -realloc: - fixed_name = kmalloc(fixup_len, GFP_KERNEL); - if (fixed_name == NULL) { - pr_err("device-tree: Out of memory trying to fixup " - "name \"%s\"\n", name); - return name; - } - -retry: - size = snprintf(fixed_name, fixup_len, "%s#%d", name, i); - size++; /* account for NULL */ - - if (size > fixup_len) { - /* We ran out of space, free and reallocate. */ - kfree(fixed_name); - fixup_len = size; - goto realloc; - } - - if (duplicate_name(de, fixed_name)) { - /* Multiple duplicates. Retry with a different offset. */ - i++; - goto retry; - } - - pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", - np->full_name, fixed_name); - - return fixed_name; -} - -/* - * Process a node, adding entries for its children and its properties. - */ -void proc_device_tree_add_node(struct device_node *np, - struct proc_dir_entry *de) -{ - struct property *pp; - struct proc_dir_entry *ent; - struct device_node *child; - const char *p; - - set_node_proc_entry(np, de); - for (child = NULL; (child = of_get_next_child(np, child));) { - /* Use everything after the last slash, or the full name */ - p = kbasename(child->full_name); - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = proc_mkdir(p, de); - if (ent == NULL) - break; - proc_device_tree_add_node(child, ent); - } - of_node_put(child); - - for (pp = np->properties; pp != NULL; pp = pp->next) { - p = pp->name; - - if (strchr(p, '/')) - continue; - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = __proc_device_tree_add_prop(de, pp, p); - if (ent == NULL) - break; - } -} - -/* - * Called on initialization to set up the /proc/device-tree subtree - */ -void __init proc_device_tree_init(void) -{ - struct device_node *root; - - proc_device_tree = proc_mkdir("device-tree", NULL); - if (proc_device_tree == NULL) - return; - root = of_find_node_by_path("/"); - if (root == NULL) { - remove_proc_entry("device-tree", NULL); - pr_debug("/proc/device-tree: can't find root\n"); - return; - } - proc_device_tree_add_node(root, proc_device_tree); - of_node_put(root); -} diff --git a/fs/proc/root.c b/fs/proc/root.c index 87dbcbef7fe4..7bbeb5257af1 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -183,9 +183,6 @@ void __init proc_root_init(void) proc_mkdir("openprom", NULL); #endif proc_tty_init(); -#ifdef CONFIG_PROC_DEVICETREE - proc_device_tree_init(); -#endif proc_mkdir("bus", NULL); proc_sys_init(); } diff --git a/fs/proc/self.c b/fs/proc/self.c index ffeb202ec942..4348bb8907c2 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, if (!tgid) return -ENOENT; sprintf(tmp, "%d", tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); + return readlink_copy(buffer, buflen, tmp); } static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6f599c62f0cc..dbd027235440 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -159,7 +159,7 @@ static int show_stat(struct seq_file *p, void *v) /* sum again ? it could be updated? */ for_each_irq_nr(j) - seq_put_decimal_ull(p, ' ', kstat_irqs(j)); + seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j)); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8f788193e3d4..c2546717fc2b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) /* * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at + * vmacache most of the time. We have zero last_addr at * the beginning and also after lseek. We will have -1 last_addr * after the end of the vmas. */ @@ -1226,6 +1227,9 @@ out: static int pagemap_open(struct inode *inode, struct file *file) { + /* do not disclose physical addresses: attack vector */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " "to stop being page-shift some time soon. See the " "linux/Documentation/vm/pagemap.txt for details.\n"); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 12823845d324..14120a3c6195 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -319,10 +319,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s", psname); + sprintf(name, "console-%s-%lld", psname, id); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s", psname); + sprintf(name, "ftrace-%s-%lld", psname, id); break; case PSTORE_TYPE_MCE: sprintf(name, "mce-%s-%lld", psname, id); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index fa8cef2cca3a..fe68d8ac4d3d 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400); MODULE_PARM_DESC(mem_size, "size of reserved RAM used to store oops/panic logs"); +static unsigned int mem_type; +module_param(mem_type, uint, 0600); +MODULE_PARM_DESC(mem_type, + "set to 1 to try to use unbuffered memory (default 0)"); + static int dump_oops = 1; module_param(dump_oops, int, 0600); MODULE_PARM_DESC(dump_oops, @@ -79,6 +84,7 @@ struct ramoops_context { struct persistent_ram_zone *fprz; phys_addr_t phys_addr; unsigned long size; + unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; @@ -86,6 +92,7 @@ struct ramoops_context { struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; unsigned int dump_write_cnt; + /* _read_cnt need clear on ramoops_pstore_open */ unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; @@ -101,6 +108,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; + cxt->ftrace_read_cnt = 0; return 0; } @@ -117,13 +125,15 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return NULL; prz = przs[i]; + if (!prz) + return NULL; - if (update) { - /* Update old/shadowed buffer. */ + /* Update old/shadowed buffer. */ + if (update) persistent_ram_save_old(prz); - if (!persistent_ram_old_size(prz)) - return NULL; - } + + if (!persistent_ram_old_size(prz)) + return NULL; *typep = type; *id = i; @@ -353,7 +363,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, size_t sz = cxt->record_size; cxt->przs[i] = persistent_ram_new(*paddr, sz, 0, - &cxt->ecc_info); + &cxt->ecc_info, + cxt->memtype); if (IS_ERR(cxt->przs[i])) { err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", @@ -383,7 +394,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return -ENOMEM; } - *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info); + *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); @@ -428,9 +439,9 @@ static int ramoops_probe(struct platform_device *pdev) if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); - cxt->dump_read_cnt = 0; cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; + cxt->memtype = pdata->mem_type; cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; @@ -561,6 +572,7 @@ static void ramoops_register_dummy(void) dummy_data->mem_size = mem_size; dummy_data->mem_address = mem_address; + dummy_data->mem_type = 0; dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index de272d426763..bda61a759b68 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz) persistent_ram_update_header_ecc(prz); } -static void *persistent_ram_vmap(phys_addr_t start, size_t size) +static void *persistent_ram_vmap(phys_addr_t start, size_t size, + unsigned int memtype) { struct page **pages; phys_addr_t page_start; @@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) page_start = start - offset_in_page(start); page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE); - prot = pgprot_noncached(PAGE_KERNEL); + if (memtype) + prot = pgprot_noncached(PAGE_KERNEL); + else + prot = pgprot_writecombine(PAGE_KERNEL); pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL); if (!pages) { @@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) return vaddr; } -static void *persistent_ram_iomap(phys_addr_t start, size_t size) +static void *persistent_ram_iomap(phys_addr_t start, size_t size, + unsigned int memtype) { + void *va; + if (!request_mem_region(start, size, "persistent_ram")) { pr_err("request mem region (0x%llx@0x%llx) failed\n", (unsigned long long)size, (unsigned long long)start); @@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size) buffer_start_add = buffer_start_add_locked; buffer_size_add = buffer_size_add_locked; - return ioremap(start, size); + if (memtype) + va = ioremap(start, size); + else + va = ioremap_wc(start, size); + + return va; } static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, - struct persistent_ram_zone *prz) + struct persistent_ram_zone *prz, int memtype) { prz->paddr = start; prz->size = size; if (pfn_valid(start >> PAGE_SHIFT)) - prz->vaddr = persistent_ram_vmap(start, size); + prz->vaddr = persistent_ram_vmap(start, size, memtype); else - prz->vaddr = persistent_ram_iomap(start, size); + prz->vaddr = persistent_ram_iomap(start, size, memtype); if (!prz->vaddr) { pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, @@ -502,7 +514,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) } struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info) + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -513,7 +526,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } - ret = persistent_ram_buffer_map(start, size, prz); + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ce87c9007b0f..89da95700c69 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -637,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); if (!ret && err) - err = ret; + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } diff --git a/fs/readdir.c b/fs/readdir.c index 5b53d995cae6..e21af53ec24e 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -72,10 +72,11 @@ struct readdir_callback { int result; }; -static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int fillonedir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { - struct readdir_callback *buf = (struct readdir_callback *) __buf; + struct readdir_callback *buf = + container_of(ctx, struct readdir_callback, ctx); struct old_linux_dirent __user * dirent; unsigned long d_ino; @@ -146,11 +147,12 @@ struct getdents_callback { int error; }; -static int filldir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent __user * dirent; - struct getdents_callback * buf = (struct getdents_callback *) __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); @@ -230,11 +232,12 @@ struct getdents_callback64 { int error; }; -static int filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir64(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf; + struct getdents_callback64 *buf = + container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 5cdfbd638b5c..d8b7acfd5066 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -177,10 +177,11 @@ struct reiserfs_dentry_buf { }; static int -fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset, - u64 ino, unsigned int d_type) +fill_with_dentries(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) { - struct reiserfs_dentry_buf *dbuf = buf; + struct reiserfs_dentry_buf *dbuf = + container_of(ctx, struct reiserfs_dentry_buf, ctx); struct dentry *dentry; WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex)); @@ -794,10 +795,12 @@ struct listxattr_buf { struct dentry *dentry; }; -static int listxattr_filler(void *buf, const char *name, int namelen, - loff_t offset, u64 ino, unsigned int d_type) +static int listxattr_filler(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) { - struct listxattr_buf *b = (struct listxattr_buf *)buf; + struct listxattr_buf *b = + container_of(ctx, struct listxattr_buf, ctx); size_t size; if (name[0] != '.' || (namelen != 1 && (name[1] != '.' || namelen != 2))) { diff --git a/fs/splice.c b/fs/splice.c index 12028fa41def..ffb92b9d34ba 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1327,6 +1327,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, return ret; } +EXPORT_SYMBOL(do_splice_direct); static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, diff --git a/fs/super.c b/fs/super.c index 7624267b2043..440ef51cd696 100644 --- a/fs/super.c +++ b/fs/super.c @@ -81,6 +81,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); total_objects = dentries + inodes + fs_objects + 1; + if (!total_objects) + total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); @@ -112,9 +114,14 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); - if (!grab_super_passive(sb)) - return 0; - + /* + * Don't call grab_super_passive as it is a potential + * scalability bottleneck. The counts could get updated + * between super_cache_count and super_cache_scan anyway. + * Call to super_cache_count with shrinker_rwsem held + * ensures the safety of call to list_lru_count_node() and + * s_op->nr_cached_objects(). + */ if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc->nid); @@ -125,7 +132,6 @@ static unsigned long super_cache_count(struct shrinker *shrink, sc->nid); total_objects = vfs_pressure_ratio(total_objects); - drop_super(sb); return total_objects; } @@ -276,10 +282,8 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); - fs->kill_sb(s); - - /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + fs->kill_sb(s); put_filesystem(fs); put_super(s); diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index ff8229340cd5..26b69b2d4a45 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c) err = ubifs_orphan_end_commit(c); if (err) goto out; - old_ltail_lnum = c->ltail_lnum; - err = ubifs_log_end_commit(c, new_ltail_lnum); - if (err) - goto out; err = dbg_check_old_index(c, &zroot); if (err) goto out; - mutex_lock(&c->mst_mutex); c->mst_node->cmt_no = cpu_to_le64(c->cmt_no); c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum); c->mst_node->root_lnum = cpu_to_le32(zroot.lnum); @@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c) c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); else c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS); - err = ubifs_write_master(c); - mutex_unlock(&c->mst_mutex); + + old_ltail_lnum = c->ltail_lnum; + err = ubifs_log_end_commit(c, new_ltail_lnum); if (err) goto out; diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index a902c5919e42..8d59de86dc9a 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c) h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs; t = (long long)c->ltail_lnum * c->leb_size; - if (h >= t) + if (h > t) return c->log_bytes - h + t; - else + else if (h != t) return t - h; + else if (c->lhead_lnum != c->ltail_lnum) + return 0; + else + return c->log_bytes; } /** @@ -447,9 +451,9 @@ out: * @ltail_lnum: new log tail LEB number * * This function is called on when the commit operation was finished. It - * moves log tail to new position and unmaps LEBs which contain obsolete data. - * Returns zero in case of success and a negative error code in case of - * failure. + * moves log tail to new position and updates the master node so that it stores + * the new log tail LEB number. Returns zero in case of success and a negative + * error code in case of failure. */ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) { @@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) spin_unlock(&c->buds_lock); err = dbg_check_bud_bytes(c); + if (err) + goto out; + err = ubifs_write_master(c); + +out: mutex_unlock(&c->log_mutex); return err; } diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index ab83ace9910a..1a4bb9e8b3b8 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c) * ubifs_write_master - write master node. * @c: UBIFS file-system description object * - * This function writes the master node. The caller has to take the - * @c->mst_mutex lock before calling this function. Returns zero in case of - * success and a negative error code in case of failure. The master node is - * written twice to enable recovery. + * This function writes the master node. Returns zero in case of success and a + * negative error code in case of failure. The master node is written twice to + * enable recovery. */ int ubifs_write_master(struct ubifs_info *c) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded8490c0c6..94d9a64287b7 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1957,7 +1957,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) mutex_init(&c->lp_mutex); mutex_init(&c->tnc_mutex); mutex_init(&c->log_mutex); - mutex_init(&c->mst_mutex); mutex_init(&c->umount_mutex); mutex_init(&c->bu_mutex); mutex_init(&c->write_reserve_mutex); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index e8c8cfe1435c..7ab9c710c749 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1042,7 +1042,6 @@ struct ubifs_debug_info; * * @mst_node: master node * @mst_offs: offset of valid master node - * @mst_mutex: protects the master node area, @mst_node, and @mst_offs * * @max_bu_buf_len: maximum bulk-read buffer length * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu @@ -1282,7 +1281,6 @@ struct ubifs_info { struct ubifs_mst_node *mst_node; int mst_offs; - struct mutex mst_mutex; int max_bu_buf_len; struct mutex bu_mutex; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05c87ed..287cd5f23421 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1271,13 +1271,22 @@ update_time: return 0; } +/* + * Maximum length of linked list formed by ICB hierarchy. The chosen number is + * arbitrary - just that we hopefully don't limit any real use of rewritten + * inode on write-once media but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_ICB_NESTING 1024 + static void __udf_read_inode(struct inode *inode) { struct buffer_head *bh = NULL; struct fileEntry *fe; uint16_t ident; struct udf_inode_info *iinfo = UDF_I(inode); + unsigned int indirections = 0; +reread: /* * Set defaults, but the inode is still incomplete! * Note: get_new_inode() sets the following on a new inode: @@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode) ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1, &ident); if (ident == TAG_IDENT_IE && ibh) { - struct buffer_head *nbh = NULL; struct kernel_lb_addr loc; struct indirectEntry *ie; ie = (struct indirectEntry *)ibh->b_data; loc = lelb_to_cpu(ie->indirectICB.extLocation); - if (ie->indirectICB.extLength && - (nbh = udf_read_ptagged(inode->i_sb, &loc, 0, - &ident))) { - if (ident == TAG_IDENT_FE || - ident == TAG_IDENT_EFE) { - memcpy(&iinfo->i_location, - &loc, - sizeof(struct kernel_lb_addr)); - brelse(bh); - brelse(ibh); - brelse(nbh); - __udf_read_inode(inode); + if (ie->indirectICB.extLength) { + brelse(bh); + brelse(ibh); + memcpy(&iinfo->i_location, &loc, + sizeof(struct kernel_lb_addr)); + if (++indirections > UDF_MAX_ICB_NESTING) { + udf_err(inode->i_sb, + "too many ICBs in ICB hierarchy" + " (max %d supported)\n", + UDF_MAX_ICB_NESTING); + make_bad_inode(inode); return; } - brelse(nbh); + goto reread; } } brelse(ibh); diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index d7c6dbe4194b..d89f324bc387 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; - int err = -EIO; + int err; unsigned char *p = kmap(page); struct udf_inode_info *iinfo; uint32_t pos; + /* We don't support symlinks longer than one block */ + if (inode->i_size > inode->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto out_unmap; + } + iinfo = UDF_I(inode); pos = udf_block_map(inode, 0); @@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) } else { bh = sb_bread(inode->i_sb, pos); - if (!bh) - goto out; + if (!bh) { + err = -EIO; + goto out_unlock_inode; + } symlink = bh->b_data; } @@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) unlock_page(page); return 0; -out: +out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); +out_unmap: kunmap(page); unlock_page(page); return err; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5d2518b24cea..0461fbe405b7 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -434,10 +434,22 @@ xfs_start_page_writeback( { ASSERT(PageLocked(page)); ASSERT(!PageWriteback(page)); - if (clear_dirty) + + /* + * if the page was not fully cleaned, we need to ensure that the higher + * layers come back to it correctly. That means we need to keep the page + * dirty, and for WB_SYNC_ALL writeback we need to ensure the + * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to + * write this page in this writeback sweep will be made. + */ + if (clear_dirty) { clear_page_dirty_for_io(page); - set_page_writeback(page); + set_page_writeback(page); + } else + set_page_writeback_keepwrite(page); + unlock_page(page); + /* If no buffers on the page are to be written, finish it here */ if (!buffers) end_page_writeback(page); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 33149113e333..645f180f5960 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -319,6 +319,10 @@ xfs_buf_item_format( ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT((bip->bli_flags & XFS_BLI_LOGGED) || (bip->bli_flags & XFS_BLI_STALE)); + ASSERT((bip->bli_flags & XFS_BLI_STALE) || + (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF + && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + /* * If it is an inode buffer, transfer the in-memory state to the diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 3a137e9f9a7d..5d90b8db0ac7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1946,6 +1946,7 @@ xfs_iunlink( agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); return 0; @@ -2037,6 +2038,7 @@ xfs_iunlink_remove( agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); } else { diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 78e62cc471c5..6152cbe353e8 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -271,32 +271,6 @@ xfs_open_by_handle( return error; } -/* - * This is a copy from fs/namei.c:vfs_readlink(), except for removing it's - * unused first argument. - */ -STATIC int -do_readlink( - char __user *buffer, - int buflen, - const char *link) -{ - int len; - - len = PTR_ERR(link); - if (IS_ERR(link)) - goto out; - - len = strlen(link); - if (len > (unsigned) buflen) - len = buflen; - if (copy_to_user(buffer, link, len)) - len = -EFAULT; - out: - return len; -} - - int xfs_readlink_by_handle( struct file *parfilp, @@ -334,7 +308,7 @@ xfs_readlink_by_handle( error = -xfs_readlink(XFS_I(dentry->d_inode), link); if (error) goto out_kfree; - error = do_readlink(hreq->ohandle, olen, link); + error = readlink_copy(hreq->ohandle, olen, link); if (error) goto out_kfree; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index c6ff3cf5a5bb..0eaaa2d296f0 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -321,7 +321,6 @@ reread: * Initialize the mount structure from the superblock. */ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); - xfs_sb_quota_from_disk(sbp); /* * If we haven't validated the superblock, do so now before we try diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6d7d1de13403..1b271f59d518 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1108,6 +1108,11 @@ xfs_qm_reset_dqcounts( */ xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR, "xfs_quotacheck"); + /* + * Reset type in case we are reusing group quota file for + * project quotas or vice versa + */ + ddq->d_flags = type; ddq->d_bcount = 0; ddq->d_icount = 0; ddq->d_rtbcount = 0; diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 1e116794bb66..4afd393846d3 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -397,10 +397,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp) } } -void -xfs_sb_from_disk( +static void +__xfs_sb_from_disk( struct xfs_sb *to, - xfs_dsb_t *from) + xfs_dsb_t *from, + bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); @@ -456,6 +457,17 @@ xfs_sb_from_disk( to->sb_pad = 0; to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); + /* Convert on-disk flags to in-memory flags? */ + if (convert_xquota) + xfs_sb_quota_from_disk(to); +} + +void +xfs_sb_from_disk( + struct xfs_sb *to, + xfs_dsb_t *from) +{ + __xfs_sb_from_disk(to, from, true); } static inline void @@ -571,7 +583,11 @@ xfs_sb_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_sb sb; - xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp)); + /* + * Use call variant which doesn't convert quota flags from disk + * format, because xfs_mount_validate_sb checks the on-disk flags. + */ + __xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false); /* * Only check the in progress field for the primary superblock as diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c812c5c060de..b626f3db67cb 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -474,6 +474,7 @@ xfs_trans_apply_sb_deltas( whole = 1; } + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. |