diff options
Diffstat (limited to 'fs')
73 files changed, 1644 insertions, 712 deletions
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f039b104a98..b03dd23feda 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -43,23 +43,6 @@ #include "fid.h" /** - * v9fs_dentry_delete - called when dentry refcount equals 0 - * @dentry: dentry in question - * - * By returning 1 here we should remove cacheing of unused - * dentry components. - * - */ - -static int v9fs_dentry_delete(const struct dentry *dentry) -{ - p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n", - dentry->d_name.name, dentry); - - return 1; -} - -/** * v9fs_cached_dentry_delete - called when dentry refcount equals 0 * @dentry: dentry in question * @@ -134,6 +117,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = { }; const struct dentry_operations v9fs_dentry_operations = { - .d_delete = v9fs_dentry_delete, + .d_delete = always_delete_dentry, .d_release = v9fs_dentry_release, }; diff --git a/fs/affs/Changes b/fs/affs/Changes index a29409c1ffe..b41c2c9792f 100644 --- a/fs/affs/Changes +++ b/fs/affs/Changes @@ -91,7 +91,7 @@ more 2.4 fixes: [Roman Zippel] Version 3.11 ------------ -- Converted to use 2.3.x page cache [Dave Jones <dave@powertweak.com>] +- Converted to use 2.3.x page cache [Dave Jones] - Corruption in truncate() bugfix [Ken Tyler <kent@werple.net.au>] Version 3.10 @@ -80,6 +80,8 @@ struct kioctx { struct percpu_ref users; atomic_t dead; + struct percpu_ref reqs; + unsigned long user_id; struct __percpu kioctx_cpu *cpu; @@ -107,7 +109,6 @@ struct kioctx { struct page **ring_pages; long nr_pages; - struct rcu_head rcu_head; struct work_struct free_work; struct { @@ -250,8 +251,10 @@ static void aio_free_ring(struct kioctx *ctx) put_aio_ring_file(ctx); - if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) + if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) { kfree(ctx->ring_pages); + ctx->ring_pages = NULL; + } } static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) @@ -463,26 +466,34 @@ static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb) return cancel(kiocb); } -static void free_ioctx_rcu(struct rcu_head *head) +static void free_ioctx(struct work_struct *work) { - struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); + struct kioctx *ctx = container_of(work, struct kioctx, free_work); + pr_debug("freeing %p\n", ctx); + + aio_free_ring(ctx); free_percpu(ctx->cpu); kmem_cache_free(kioctx_cachep, ctx); } +static void free_ioctx_reqs(struct percpu_ref *ref) +{ + struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + + INIT_WORK(&ctx->free_work, free_ioctx); + schedule_work(&ctx->free_work); +} + /* * When this function runs, the kioctx has been removed from the "hash table" * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ -static void free_ioctx(struct work_struct *work) +static void free_ioctx_users(struct percpu_ref *ref) { - struct kioctx *ctx = container_of(work, struct kioctx, free_work); - struct aio_ring *ring; + struct kioctx *ctx = container_of(ref, struct kioctx, users); struct kiocb *req; - unsigned cpu, avail; - DEFINE_WAIT(wait); spin_lock_irq(&ctx->ctx_lock); @@ -496,54 +507,8 @@ static void free_ioctx(struct work_struct *work) spin_unlock_irq(&ctx->ctx_lock); - for_each_possible_cpu(cpu) { - struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu); - - atomic_add(kcpu->reqs_available, &ctx->reqs_available); - kcpu->reqs_available = 0; - } - - while (1) { - prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE); - - ring = kmap_atomic(ctx->ring_pages[0]); - avail = (ring->head <= ring->tail) - ? ring->tail - ring->head - : ctx->nr_events - ring->head + ring->tail; - - atomic_add(avail, &ctx->reqs_available); - ring->head = ring->tail; - kunmap_atomic(ring); - - if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1) - break; - - schedule(); - } - finish_wait(&ctx->wait, &wait); - - WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1); - - aio_free_ring(ctx); - - pr_debug("freeing %p\n", ctx); - - /* - * Here the call_rcu() is between the wait_event() for reqs_active to - * hit 0, and freeing the ioctx. - * - * aio_complete() decrements reqs_active, but it has to touch the ioctx - * after to issue a wakeup so we use rcu. - */ - call_rcu(&ctx->rcu_head, free_ioctx_rcu); -} - -static void free_ioctx_ref(struct percpu_ref *ref) -{ - struct kioctx *ctx = container_of(ref, struct kioctx, users); - - INIT_WORK(&ctx->free_work, free_ioctx); - schedule_work(&ctx->free_work); + percpu_ref_kill(&ctx->reqs); + percpu_ref_put(&ctx->reqs); } static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) @@ -602,6 +567,16 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) } } +static void aio_nr_sub(unsigned nr) +{ + spin_lock(&aio_nr_lock); + if (WARN_ON(aio_nr - nr > aio_nr)) + aio_nr = 0; + else + aio_nr -= nr; + spin_unlock(&aio_nr_lock); +} + /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. */ @@ -639,8 +614,11 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) ctx->max_reqs = nr_events; - if (percpu_ref_init(&ctx->users, free_ioctx_ref)) - goto out_freectx; + if (percpu_ref_init(&ctx->users, free_ioctx_users)) + goto err; + + if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs)) + goto err; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); @@ -651,10 +629,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) - goto out_freeref; + goto err; if (aio_setup_ring(ctx) < 0) - goto out_freepcpu; + goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4); @@ -666,7 +644,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) if (aio_nr + nr_events > (aio_max_nr * 2UL) || aio_nr + nr_events < aio_nr) { spin_unlock(&aio_nr_lock); - goto out_cleanup; + err = -EAGAIN; + goto err; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); @@ -675,23 +654,18 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err = ioctx_add_table(ctx, mm); if (err) - goto out_cleanup_put; + goto err_cleanup; pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; -out_cleanup_put: - percpu_ref_put(&ctx->users); -out_cleanup: - err = -EAGAIN; - aio_free_ring(ctx); -out_freepcpu: +err_cleanup: + aio_nr_sub(ctx->max_reqs); +err: free_percpu(ctx->cpu); -out_freeref: + free_percpu(ctx->reqs.pcpu_count); free_percpu(ctx->users.pcpu_count); -out_freectx: - put_aio_ring_file(ctx); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); @@ -726,10 +700,7 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) * -EAGAIN with no ioctxs actually in use (as far as userspace * could tell). */ - spin_lock(&aio_nr_lock); - BUG_ON(aio_nr - ctx->max_reqs > aio_nr); - aio_nr -= ctx->max_reqs; - spin_unlock(&aio_nr_lock); + aio_nr_sub(ctx->max_reqs); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); @@ -861,6 +832,8 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) if (unlikely(!req)) goto out_put; + percpu_ref_get(&ctx->reqs); + req->ki_ctx = ctx; return req; out_put: @@ -930,12 +903,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) return; } - /* - * Take rcu_read_lock() in case the kioctx is being destroyed, as we - * need to issue a wakeup after incrementing reqs_available. - */ - rcu_read_lock(); - if (iocb->ki_list.next) { unsigned long flags; @@ -1010,7 +977,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - rcu_read_unlock(); + percpu_ref_put(&ctx->reqs); } EXPORT_SYMBOL(aio_complete); @@ -1421,6 +1388,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, return 0; out_put_req: put_reqs_available(ctx, 1); + percpu_ref_put(&ctx->reqs); kiocb_free(req); return ret; } @@ -601,7 +601,7 @@ EXPORT_SYMBOL(bio_get_nr_vecs); static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, - unsigned short max_sectors) + unsigned int max_sectors) { int retried_segments = 0; struct bio_vec *bvec; diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index f9d5094e102..aa976eced2d 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -9,12 +9,17 @@ config BTRFS_FS select XOR_BLOCKS help - Btrfs is a new filesystem with extents, writable snapshotting, - support for multiple devices and many more features. + Btrfs is a general purpose copy-on-write filesystem with extents, + writable snapshotting, support for multiple devices and many more + features focused on fault tolerance, repair and easy administration. - Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET - FINALIZED. You should say N here unless you are interested in - testing Btrfs with non-critical data. + The filesystem disk format is no longer unstable, and it's not + expected to change unless there are strong reasons to do so. If there + is a format change, file systems with a unchanged format will + continue to be mountable and usable by newer kernels. + + For more information, please see the web pages at + http://btrfs.wiki.kernel.org. To compile this file system support as a module, choose M here. The module will be called btrfs. diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 8aec751fa46..c1e0b0caf9c 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -495,6 +495,7 @@ static int __btrfs_start_workers(struct btrfs_workers *workers) spin_lock_irq(&workers->lock); if (workers->stopping) { spin_unlock_irq(&workers->lock); + ret = -EINVAL; goto fail_kthread; } list_add_tail(&worker->worker_list, &workers->idle_list); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index e0aab445697..b50764bef14 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -77,6 +77,15 @@ * the integrity of (super)-block write requests, do not * enable the config option BTRFS_FS_CHECK_INTEGRITY to * include and compile the integrity check tool. + * + * Expect millions of lines of information in the kernel log with an + * enabled check_int_print_mask. Therefore set LOG_BUF_SHIFT in the + * kernel config to at least 26 (which is 64MB). Usually the value is + * limited to 21 (which is 2MB) in init/Kconfig. The file needs to be + * changed like this before LOG_BUF_SHIFT can be set to a high value: + * config LOG_BUF_SHIFT + * int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" + * range 12 30 */ #include <linux/sched.h> @@ -124,6 +133,7 @@ #define BTRFSIC_PRINT_MASK_INITIAL_DATABASE 0x00000400 #define BTRFSIC_PRINT_MASK_NUM_COPIES 0x00000800 #define BTRFSIC_PRINT_MASK_TREE_WITH_ALL_MIRRORS 0x00001000 +#define BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE 0x00002000 struct btrfsic_dev_state; struct btrfsic_state; @@ -3015,6 +3025,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio) (rw & WRITE) && NULL != bio->bi_io_vec) { unsigned int i; u64 dev_bytenr; + u64 cur_bytenr; int bio_is_patched; char **mapped_datav; @@ -3033,6 +3044,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio) GFP_NOFS); if (!mapped_datav) goto leave; + cur_bytenr = dev_bytenr; for (i = 0; i < bio->bi_vcnt; i++) { BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE); mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page); @@ -3044,16 +3056,13 @@ void btrfsic_submit_bio(int rw, struct bio *bio) kfree(mapped_datav); goto leave; } - if ((BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | - BTRFSIC_PRINT_MASK_VERBOSE) == - (dev_state->state->print_mask & - (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | - BTRFSIC_PRINT_MASK_VERBOSE))) + if (dev_state->state->print_mask & + BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE) printk(KERN_INFO - "#%u: page=%p, len=%u, offset=%u\n", - i, bio->bi_io_vec[i].bv_page, - bio->bi_io_vec[i].bv_len, + "#%u: bytenr=%llu, len=%u, offset=%u\n", + i, cur_bytenr, bio->bi_io_vec[i].bv_len, bio->bi_io_vec[i].bv_offset); + cur_bytenr += bio->bi_io_vec[i].bv_len; } btrfsic_process_written_block(dev_state, dev_bytenr, mapped_datav, bio->bi_vcnt, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f9aeb2759a6..54ab86127f7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3613,9 +3613,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum *sums); int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode, struct bio *bio, u64 file_start, int contig); -int btrfs_csum_truncate(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct btrfs_path *path, - u64 isize); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit); /* inode.c */ @@ -3744,9 +3741,6 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, int skip_pinned); -int btrfs_replace_extent_cache(struct inode *inode, struct extent_map *replace, - u64 start, u64 end, int skip_pinned, - int modified); extern const struct file_operations btrfs_file_operations; int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 342f9fd411e..2cfc3dfff64 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -366,7 +366,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, dev_replace->tgtdev = tgt_device; printk_in_rcu(KERN_INFO - "btrfs: dev_replace from %s (devid %llu) to %s) started\n", + "btrfs: dev_replace from %s (devid %llu) to %s started\n", src_device->missing ? "<missing disk>" : rcu_str_deref(src_device->name), src_device->devid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4c4ed0bb3da..8072cfa8a3b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3517,7 +3517,6 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) int btrfs_commit_super(struct btrfs_root *root) { struct btrfs_trans_handle *trans; - int ret; mutex_lock(&root->fs_info->cleaner_mutex); btrfs_run_delayed_iputs(root); @@ -3531,25 +3530,7 @@ int btrfs_commit_super(struct btrfs_root *root) trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - /* run commit again to drop the original snapshot */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - ret = btrfs_write_and_wait_transaction(NULL, root); - if (ret) { - btrfs_error(root->fs_info, ret, - "Failed to sync btree inode to disk."); - return ret; - } - - ret = write_ctree_super(NULL, root, 0); - return ret; + return btrfs_commit_transaction(trans, root); } int close_ctree(struct btrfs_root *root) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 856bc2b2192..8e457fca0a0 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1980,6 +1980,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; int ret; + ASSERT(!(fs_info->sb->s_flags & MS_RDONLY)); BUG_ON(!mirror_num); /* we can't repair anything in raid56 yet */ @@ -2036,6 +2037,9 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb, unsigned long i, num_pages = num_extent_pages(eb->start, eb->len); int ret = 0; + if (root->fs_info->sb->s_flags & MS_RDONLY) + return -EROFS; + for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); ret = repair_io_failure(root->fs_info, start, PAGE_CACHE_SIZE, @@ -2057,12 +2061,12 @@ static int clean_io_failure(u64 start, struct page *page) u64 private; u64 private_failure; struct io_failure_record *failrec; - struct btrfs_fs_info *fs_info; + struct inode *inode = page->mapping->host; + struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct extent_state *state; int num_copies; int did_repair = 0; int ret; - struct inode *inode = page->mapping->host; private = 0; ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private, @@ -2085,6 +2089,8 @@ static int clean_io_failure(u64 start, struct page *page) did_repair = 1; goto out; } + if (fs_info->sb->s_flags & MS_RDONLY) + goto out; spin_lock(&BTRFS_I(inode)->io_tree.lock); state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree, @@ -2094,7 +2100,6 @@ static int clean_io_failure(u64 start, struct page *page) if (state && state->start <= failrec->start && state->end >= failrec->start + failrec->len - 1) { - fs_info = BTRFS_I(inode)->root->fs_info; num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len); if (num_copies > 1) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da8d2f696ac..f1a77449d03 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2129,7 +2129,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path, old->extent_offset, fs_info, path, record_one_backref, old); - BUG_ON(ret < 0 && ret != -ENOENT); + if (ret < 0 && ret != -ENOENT) + return false; /* no backref to be processed for this extent */ if (!old->count) { @@ -6186,8 +6187,7 @@ insert: write_unlock(&em_tree->lock); out: - if (em) - trace_btrfs_get_extent(root, em); + trace_btrfs_get_extent(root, em); if (path) btrfs_free_path(path); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 25a8f3812f1..69582d5b69d 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -638,6 +638,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr) WARN_ON(nr < 0); } } + list_splice_tail(&splice, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); } @@ -803,7 +804,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) btrfs_put_ordered_extent(ordered); break; } - if (ordered->file_offset + ordered->len < start) { + if (ordered->file_offset + ordered->len <= start) { btrfs_put_ordered_extent(ordered); break; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 2544805544f..561e2f16ba3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -938,8 +938,10 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) BTRFS_DEV_STAT_CORRUPTION_ERRS); } - if (sctx->readonly && !sctx->is_dev_replace) - goto did_not_correct_error; + if (sctx->readonly) { + ASSERT(!sctx->is_dev_replace); + goto out; + } if (!is_metadata && !have_csum) { struct scrub_fixup_nodatasum *fixup_nodatasum; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 57c16b46afb..c6a872a8a46 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1480,7 +1480,7 @@ static void do_async_commit(struct work_struct *work) * We've got freeze protection passed with the transaction. * Tell lockdep about it. */ - if (ac->newtrans->type < TRANS_JOIN_NOLOCK) + if (ac->newtrans->type & __TRANS_FREEZABLE) rwsem_acquire_read( &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1], 0, 1, _THIS_IP_); @@ -1521,7 +1521,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, * Tell lockdep we've released the freeze rwsem, since the * async commit thread will be the one to unlock it. */ - if (trans->type < TRANS_JOIN_NOLOCK) + if (ac->newtrans->type & __TRANS_FREEZABLE) rwsem_release( &root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1], 1, _THIS_IP_); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 744553c83fe..9f7fc51ca33 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3697,7 +3697,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, ret = btrfs_truncate_inode_items(trans, log, inode, 0, 0); } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags)) { + &BTRFS_I(inode)->runtime_flags) || + inode_only == LOG_INODE_EXISTS) { if (inode_only == LOG_INODE_ALL) fast_search = true; max_key.type = BTRFS_XATTR_ITEM_KEY; @@ -3801,7 +3802,7 @@ log_extents: err = ret; goto out_unlock; } - } else { + } else if (inode_only == LOG_INODE_ALL) { struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree; struct extent_map *em, *n; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0db63709786..92303f42baa 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5394,7 +5394,7 @@ static int bio_size_ok(struct block_device *bdev, struct bio *bio, { struct bio_vec *prev; struct request_queue *q = bdev_get_queue(bdev); - unsigned short max_sectors = queue_max_sectors(q); + unsigned int max_sectors = queue_max_sectors(q); struct bvec_merge_data bvm = { .bi_bdev = bdev, .bi_sector = sector, diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6df8bd48142..1e561c05953 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -216,7 +216,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) } SetPageUptodate(page); - if (err == 0) + if (err >= 0) ceph_readpage_to_fscache(inode, page); out: diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 7db2e6ca4b8..8c44fdd4e1c 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -324,6 +324,9 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page) { struct ceph_inode_info *ci = ceph_inode(inode); + if (!PageFsCache(page)) + return; + fscache_wait_on_page_write(ci->fscache, page); fscache_uncache_page(ci->fscache, page); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 13976c33332..3c0a4bd7499 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -897,7 +897,7 @@ static int __ceph_is_any_caps(struct ceph_inode_info *ci) * caller should hold i_ceph_lock. * caller will not hold session s_mutex if called from destroy_inode. */ -void __ceph_remove_cap(struct ceph_cap *cap) +void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) { struct ceph_mds_session *session = cap->session; struct ceph_inode_info *ci = cap->ci; @@ -909,6 +909,16 @@ void __ceph_remove_cap(struct ceph_cap *cap) /* remove from session list */ spin_lock(&session->s_cap_lock); + /* + * s_cap_reconnect is protected by s_cap_lock. no one changes + * s_cap_gen while session is in the reconnect state. + */ + if (queue_release && + (!session->s_cap_reconnect || + cap->cap_gen == session->s_cap_gen)) + __queue_cap_release(session, ci->i_vino.ino, cap->cap_id, + cap->mseq, cap->issue_seq); + if (session->s_cap_iterator == cap) { /* not yet, we are iterating over this very cap */ dout("__ceph_remove_cap delaying %p removal from session %p\n", @@ -1023,7 +1033,6 @@ void __queue_cap_release(struct ceph_mds_session *session, struct ceph_mds_cap_release *head; struct ceph_mds_cap_item *item; - spin_lock(&session->s_cap_lock); BUG_ON(!session->s_num_cap_releases); msg = list_first_entry(&session->s_cap_releases, struct ceph_msg, list_head); @@ -1052,7 +1061,6 @@ void __queue_cap_release(struct ceph_mds_session *session, (int)CEPH_CAPS_PER_RELEASE, (int)msg->front.iov_len); } - spin_unlock(&session->s_cap_lock); } /* @@ -1067,12 +1075,8 @@ void ceph_queue_caps_release(struct inode *inode) p = rb_first(&ci->i_caps); while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); - struct ceph_mds_session *session = cap->session; - - __queue_cap_release(session, ceph_ino(inode), cap->cap_id, - cap->mseq, cap->issue_seq); p = rb_next(p); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, true); } } @@ -2791,7 +2795,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, } spin_unlock(&mdsc->cap_dirty_lock); } - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, false); } /* else, we already released it */ @@ -2931,9 +2935,12 @@ void ceph_handle_caps(struct ceph_mds_session *session, if (!inode) { dout(" i don't have ino %llx\n", vino.ino); - if (op == CEPH_CAP_OP_IMPORT) + if (op == CEPH_CAP_OP_IMPORT) { + spin_lock(&session->s_cap_lock); __queue_cap_release(session, vino.ino, cap_id, mseq, seq); + spin_unlock(&session->s_cap_lock); + } goto flush_cap_releases; } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 868b61d56ca..2a0bcaeb189 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -352,8 +352,18 @@ more: } /* note next offset and last dentry name */ + rinfo = &req->r_reply_info; + if (le32_to_cpu(rinfo->dir_dir->frag) != frag) { + frag = le32_to_cpu(rinfo->dir_dir->frag); + if (ceph_frag_is_leftmost(frag)) + fi->next_offset = 2; + else + fi->next_offset = 0; + off = fi->next_offset; + } fi->offset = fi->next_offset; fi->last_readdir = req; + fi->frag = frag; if (req->r_reply_info.dir_end) { kfree(fi->last_name); @@ -363,7 +373,6 @@ more: else fi->next_offset = 0; } else { - rinfo = &req->r_reply_info; err = note_last_dentry(fi, rinfo->dir_dname[rinfo->dir_nr-1], rinfo->dir_dname_len[rinfo->dir_nr-1]); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8549a48115f..9a8e396aed8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,6 +577,8 @@ static int fill_inode(struct inode *inode, int issued = 0, implemented; struct timespec mtime, atime, ctime; u32 nsplits; + struct ceph_inode_frag *frag; + struct rb_node *rb_node; struct ceph_buffer *xattr_blob = NULL; int err = 0; int queue_trunc = 0; @@ -751,15 +753,38 @@ no_change: /* FIXME: move me up, if/when version reflects fragtree changes */ nsplits = le32_to_cpu(info->fragtree.nsplits); mutex_lock(&ci->i_fragtree_mutex); + rb_node = rb_first(&ci->i_fragtree); for (i = 0; i < nsplits; i++) { u32 id = le32_to_cpu(info->fragtree.splits[i].frag); - struct ceph_inode_frag *frag = __get_or_create_frag(ci, id); - - if (IS_ERR(frag)) - continue; + frag = NULL; + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + if (ceph_frag_compare(frag->frag, id) >= 0) { + if (frag->frag != id) + frag = NULL; + else + rb_node = rb_next(rb_node); + break; + } + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + frag = NULL; + } + if (!frag) { + frag = __get_or_create_frag(ci, id); + if (IS_ERR(frag)) + continue; + } frag->split_by = le32_to_cpu(info->fragtree.splits[i].by); dout(" frag %x split by %d\n", frag->frag, frag->split_by); } + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + } mutex_unlock(&ci->i_fragtree_mutex); /* were we issued a capability? */ @@ -1250,8 +1275,20 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, int err = 0, i; struct inode *snapdir = NULL; struct ceph_mds_request_head *rhead = req->r_request->front.iov_base; - u64 frag = le32_to_cpu(rhead->args.readdir.frag); struct ceph_dentry_info *di; + u64 r_readdir_offset = req->r_readdir_offset; + u32 frag = le32_to_cpu(rhead->args.readdir.frag); + + if (rinfo->dir_dir && + le32_to_cpu(rinfo->dir_dir->frag) != frag) { + dout("readdir_prepopulate got new frag %x -> %x\n", + frag, le32_to_cpu(rinfo->dir_dir->frag)); + frag = le32_to_cpu(rinfo->dir_dir->frag); + if (ceph_frag_is_leftmost(frag)) + r_readdir_offset = 2; + else + r_readdir_offset = 0; + } if (req->r_aborted) return readdir_prepopulate_inodes_only(req, session); @@ -1315,7 +1352,7 @@ retry_lookup: } di = dn->d_fsdata; - di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset); + di->offset = ceph_make_fpos(frag, i + r_readdir_offset); /* inode */ if (dn->d_inode) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index b7bda5d9611..d90861f4521 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -43,6 +43,7 @@ */ struct ceph_reconnect_state { + int nr_caps; struct ceph_pagelist *pagelist; bool flock; }; @@ -443,6 +444,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, INIT_LIST_HEAD(&s->s_waiting); INIT_LIST_HEAD(&s->s_unsafe); s->s_num_cap_releases = 0; + s->s_cap_reconnect = 0; s->s_cap_iterator = NULL; INIT_LIST_HEAD(&s->s_cap_releases); INIT_LIST_HEAD(&s->s_cap_releases_done); @@ -642,6 +644,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc, req->r_unsafe_dir = NULL; } + complete_all(&req->r_safe_completion); + ceph_mdsc_put_request(req); } @@ -986,7 +990,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, false); if (!__ceph_is_any_real_caps(ci)) { struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; @@ -1231,9 +1235,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) session->s_trim_caps--; if (oissued) { /* we aren't the only cap.. just remove us */ - __queue_cap_release(session, ceph_ino(inode), cap->cap_id, - cap->mseq, cap->issue_seq); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, true); } else { /* try to drop referring dentries */ spin_unlock(&ci->i_ceph_lock); @@ -1416,7 +1418,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, unsigned num; dout("discard_cap_releases mds%d\n", session->s_mds); - spin_lock(&session->s_cap_lock); /* zero out the in-progress message */ msg = list_first_entry(&session->s_cap_releases, @@ -1443,8 +1444,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, msg->front.iov_len = sizeof(*head); list_add(&msg->list_head, &session->s_cap_releases); } - - spin_unlock(&session->s_cap_lock); } /* @@ -1875,8 +1874,11 @@ static int __do_request(struct ceph_mds_client *mdsc, int mds = -1; int err = -EAGAIN; - if (req->r_err || req->r_got_result) + if (req->r_err || req->r_got_result) { + if (req->r_aborted) + __unregister_request(mdsc, req); goto out; + } if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { @@ -2186,7 +2188,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) if (head->safe) { req->r_got_safe = true; __unregister_request(mdsc, req); - complete_all(&req->r_safe_completion); if (req->r_got_unsafe) { /* @@ -2238,8 +2239,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session); if (err == 0) { if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR || - req->r_op == CEPH_MDS_OP_LSSNAP) && - rinfo->dir_nr) + req->r_op == CEPH_MDS_OP_LSSNAP)) ceph_readdir_prepopulate(req, req->r_session); ceph_unreserve_caps(mdsc, &req->r_caps_reservation); } @@ -2490,6 +2490,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, cap->seq = 0; /* reset cap seq */ cap->issue_seq = 0; /* and issue_seq */ cap->mseq = 0; /* and migrate_seq */ + cap->cap_gen = cap->session->s_cap_gen; if (recon_state->flock) { rec.v2.cap_id = cpu_to_le64(cap->cap_id); @@ -2552,6 +2553,8 @@ encode_again: } else { err = ceph_pagelist_append(pagelist, &rec, reclen); } + + recon_state->nr_caps++; out_free: kfree(path); out_dput: @@ -2579,6 +2582,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, struct rb_node *p; int mds = session->s_mds; int err = -ENOMEM; + int s_nr_caps; struct ceph_pagelist *pagelist; struct ceph_reconnect_state recon_state; @@ -2610,20 +2614,38 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, dout("session %p state %s\n", session, session_state_name(session->s_state)); + spin_lock(&session->s_gen_ttl_lock); + session->s_cap_gen++; + spin_unlock(&session->s_gen_ttl_lock); + + spin_lock(&session->s_cap_lock); + /* + * notify __ceph_remove_cap() that we are composing cap reconnect. + * If a cap get released before being added to the cap reconnect, + * __ceph_remove_cap() should skip queuing cap release. + */ + session->s_cap_reconnect = 1; /* drop old cap expires; we're about to reestablish that state */ discard_cap_releases(mdsc, session); + spin_unlock(&session->s_cap_lock); /* traverse this session's caps */ - err = ceph_pagelist_encode_32(pagelist, session->s_nr_caps); + s_nr_caps = session->s_nr_caps; + err = ceph_pagelist_encode_32(pagelist, s_nr_caps); if (err) goto fail; + recon_state.nr_caps = 0; recon_state.pagelist = pagelist; recon_state.flock = session->s_con.peer_features & CEPH_FEATURE_FLOCK; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; + spin_lock(&session->s_cap_lock); + session->s_cap_reconnect = 0; + spin_unlock(&session->s_cap_lock); + /* * snaprealms. we provide mds with the ino, seq (version), and * parent for all of our realms. If the mds has any newer info, @@ -2646,11 +2668,18 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, if (recon_state.flock) reply->hdr.version = cpu_to_le16(2); - if (pagelist->length) { - /* set up outbound data if we have any */ - reply->hdr.data_len = cpu_to_le32(pagelist->length); - ceph_msg_data_add_pagelist(reply, pagelist); + + /* raced with cap release? */ + if (s_nr_caps != recon_state.nr_caps) { + struct page *page = list_first_entry(&pagelist->head, + struct page, lru); + __le32 *addr = kmap_atomic(page); + *addr = cpu_to_le32(recon_state.nr_caps); + kunmap_atomic(addr); } + + reply->hdr.data_len = cpu_to_le32(pagelist->length); + ceph_msg_data_add_pagelist(reply, pagelist); ceph_con_send(&session->s_con, reply); mutex_unlock(&session->s_mutex); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index c2a19fbbe51..4c053d099ae 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -132,6 +132,7 @@ struct ceph_mds_session { struct list_head s_caps; /* all caps issued by this session */ int s_nr_caps, s_trim_caps; int s_num_cap_releases; + int s_cap_reconnect; struct list_head s_cap_releases; /* waiting cap_release messages */ struct list_head s_cap_releases_done; /* ready to send */ struct ceph_cap *s_cap_iterator; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6014b0a3c40..ef4ac38bb61 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -741,13 +741,7 @@ extern int ceph_add_cap(struct inode *inode, int fmode, unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap_reservation *caps_reservation); -extern void __ceph_remove_cap(struct ceph_cap *cap); -static inline void ceph_remove_cap(struct ceph_cap *cap) -{ - spin_lock(&cap->ci->i_ceph_lock); - __ceph_remove_cap(cap); - spin_unlock(&cap->ci->i_ceph_lock); -} +extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); extern void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 277bd1be21f..e081acbac2e 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -56,29 +56,28 @@ static void configfs_d_iput(struct dentry * dentry, struct configfs_dirent *sd = dentry->d_fsdata; if (sd) { - BUG_ON(sd->s_dentry != dentry); /* Coordinate with configfs_readdir */ spin_lock(&configfs_dirent_lock); - sd->s_dentry = NULL; + /* Coordinate with configfs_attach_attr where will increase + * sd->s_count and update sd->s_dentry to new allocated one. + * Only set sd->dentry to null when this dentry is the only + * sd owner. + * If not do so, configfs_d_iput may run just after + * configfs_attach_attr and set sd->s_dentry to null + * even it's still in use. + */ + if (atomic_read(&sd->s_count) <= 2) + sd->s_dentry = NULL; + spin_unlock(&configfs_dirent_lock); configfs_put(sd); } iput(inode); } -/* - * We _must_ delete our dentries on last dput, as the chain-to-parent - * behavior is required to clear the parents of default_groups. - */ -static int configfs_d_delete(const struct dentry *dentry) -{ - return 1; -} - const struct dentry_operations configfs_dentry_ops = { .d_iput = configfs_d_iput, - /* simple_delete_dentry() isn't exported */ - .d_delete = configfs_d_delete, + .d_delete = always_delete_dentry, }; #ifdef CONFIG_LOCKDEP @@ -426,8 +425,11 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den struct configfs_attribute * attr = sd->s_element; int error; + spin_lock(&configfs_dirent_lock); dentry->d_fsdata = configfs_get(sd); sd->s_dentry = dentry; + spin_unlock(&configfs_dirent_lock); + error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, configfs_init_file); if (error) { diff --git a/fs/coredump.c b/fs/coredump.c index 62406b6959b..bc3fbcd3255 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -695,7 +695,7 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr) while (nr) { if (dump_interrupted()) return 0; - n = vfs_write(file, addr, nr, &pos); + n = __kernel_write(file, addr, nr, &pos); if (n <= 0) return 0; file->f_pos = pos; @@ -733,7 +733,7 @@ int dump_align(struct coredump_params *cprm, int align) { unsigned mod = cprm->written & (align - 1); if (align & (align - 1)) - return -EINVAL; - return mod ? dump_skip(cprm, align - mod) : 0; + return 0; + return mod ? dump_skip(cprm, align - mod) : 1; } EXPORT_SYMBOL(dump_align); diff --git a/fs/dcache.c b/fs/dcache.c index 0a38ef8d7f0..4bdb300b16e 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -88,35 +88,6 @@ EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; -/** - * read_seqbegin_or_lock - begin a sequence number check or locking block - * @lock: sequence lock - * @seq : sequence number to be checked - * - * First try it once optimistically without taking the lock. If that fails, - * take the lock. The sequence number is also used as a marker for deciding - * whether to be a reader (even) or writer (odd). - * N.B. seq must be initialized to an even number to begin with. - */ -static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) -{ - if (!(*seq & 1)) /* Even */ - *seq = read_seqbegin(lock); - else /* Odd */ - read_seqlock_excl(lock); -} - -static inline int need_seqretry(seqlock_t *lock, int seq) -{ - return !(seq & 1) && read_seqretry(lock, seq); -} - -static inline void done_seqretry(seqlock_t *lock, int seq) -{ - if (seq & 1) - read_sequnlock_excl(lock); -} - /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try @@ -125,8 +96,6 @@ static inline void done_seqretry(seqlock_t *lock, int seq) * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. */ -#define D_HASHBITS d_hash_shift -#define D_HASHMASK d_hash_mask static unsigned int d_hash_mask __read_mostly; static unsigned int d_hash_shift __read_mostly; @@ -137,8 +106,8 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; - hash = hash + (hash >> D_HASHBITS); - return dentry_hashtable + (hash & D_HASHMASK); + hash = hash + (hash >> d_hash_shift); + return dentry_hashtable + (hash & d_hash_mask); } /* Statistics gathering. */ @@ -469,7 +438,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) { list_del(&dentry->d_u.d_child); /* - * Inform try_to_ascend() that we are no longer attached to the + * Inform d_walk() that we are no longer attached to the * dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; @@ -1069,34 +1038,6 @@ void shrink_dcache_sb(struct super_block *sb) } EXPORT_SYMBOL(shrink_dcache_sb); -/* - * This tries to ascend one level of parenthood, but - * we can race with renaming, so we need to re-check - * the parenthood after dropping the lock and check - * that the sequence number still matches. - */ -static struct dentry *try_to_ascend(struct dentry *old, unsigned seq) -{ - struct dentry *new = old->d_parent; - - rcu_read_lock(); - spin_unlock(&old->d_lock); - spin_lock(&new->d_lock); - - /* - * might go back up the wrong parent if we have had a rename - * or deletion - */ - if (new != old->d_parent || - (old->d_flags & DCACHE_DENTRY_KILLED) || - need_seqretry(&rename_lock, seq)) { - spin_unlock(&new->d_lock); - new = NULL; - } - rcu_read_unlock(); - return new; -} - /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk @@ -1185,9 +1126,24 @@ resume: */ if (this_parent != parent) { struct dentry *child = this_parent; - this_parent = try_to_ascend(this_parent, seq); - if (!this_parent) + this_parent = child->d_parent; + + rcu_read_lock(); + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* + * might go back up the wrong parent if we have had a rename + * or deletion + */ + if (this_parent != child->d_parent || + (child->d_flags & DCACHE_DENTRY_KILLED) || + need_seqretry(&rename_lock, seq)) { + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); goto rename_retry; + } + rcu_read_unlock(); next = child->d_u.d_child.next; goto resume; } diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 60a327863b1..e7cfbaf8d0e 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -74,14 +74,16 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info) return 0; } -static struct genl_ops dlm_nl_ops = { - .cmd = DLM_CMD_HELLO, - .doit = user_cmd, +static struct genl_ops dlm_nl_ops[] = { + { + .cmd = DLM_CMD_HELLO, + .doit = user_cmd, + }, }; int __init dlm_netlink_init(void) { - return genl_register_family_with_ops(&family, &dlm_nl_ops, 1); + return genl_register_family_with_ops(&family, dlm_nl_ops); } void dlm_netlink_exit(void) diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 2229a74aeee..b1eaa7a1f82 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -313,11 +313,9 @@ static int ecryptfs_fasync(int fd, struct file *file, int flag) static long ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct file *lower_file = NULL; + struct file *lower_file = ecryptfs_file_to_lower(file); long rc = -ENOTTY; - if (ecryptfs_file_to_private(file)) - lower_file = ecryptfs_file_to_lower(file); if (lower_file->f_op->unlocked_ioctl) rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); return rc; @@ -327,11 +325,9 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static long ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct file *lower_file = NULL; + struct file *lower_file = ecryptfs_file_to_lower(file); long rc = -ENOIOCTLCMD; - if (ecryptfs_file_to_private(file)) - lower_file = ecryptfs_file_to_lower(file); if (lower_file->f_op && lower_file->f_op->compat_ioctl) rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); return rc; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index a8766b880c0..becc725a195 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -83,19 +83,10 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) return 0; } -/* - * Retaining negative dentries for an in-memory filesystem just wastes - * memory and lookup time: arrange for them to be deleted immediately. - */ -static int efivarfs_delete_dentry(const struct dentry *dentry) -{ - return 1; -} - static struct dentry_operations efivarfs_d_ops = { .d_compare = efivarfs_d_compare, .d_hash = efivarfs_d_hash, - .d_delete = efivarfs_delete_dentry, + .d_delete = always_delete_dentry, }; static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name) diff --git a/fs/exec.c b/fs/exec.c index 977319fd77f..7ea097f6b34 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1380,10 +1380,6 @@ int search_binary_handler(struct linux_binprm *bprm) if (retval) return retval; - retval = audit_bprm(bprm); - if (retval) - return retval; - retval = -ENOENT; retry: read_lock(&binfmt_lock); @@ -1431,6 +1427,7 @@ static int exec_binprm(struct linux_binprm *bprm) ret = search_binary_handler(bprm); if (ret >= 0) { + audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); current->did_exec = 1; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index e66a8009aff..c8420f7e4db 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1899,7 +1899,8 @@ static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi) gi->nhash = 0; } /* Skip entries for other sb and dead entries */ - } while (gi->sdp != gi->gl->gl_sbd || __lockref_is_dead(&gl->gl_lockref)); + } while (gi->sdp != gi->gl->gl_sbd || + __lockref_is_dead(&gi->gl->gl_lockref)); return 0; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 1615df16cf4..7119504159f 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1171,8 +1171,11 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (d != NULL) dentry = d; if (dentry->d_inode) { - if (!(*opened & FILE_OPENED)) + if (!(*opened & FILE_OPENED)) { + if (d == NULL) + dget(dentry); return finish_no_open(file, dentry); + } dput(d); return 0; } diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index c8423d6de6c..2a6ba06bee6 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -466,19 +466,19 @@ static void gdlm_cancel(struct gfs2_glock *gl) static void control_lvb_read(struct lm_lockstruct *ls, uint32_t *lvb_gen, char *lvb_bits) { - uint32_t gen; + __le32 gen; memcpy(lvb_bits, ls->ls_control_lvb, GDLM_LVB_SIZE); - memcpy(&gen, lvb_bits, sizeof(uint32_t)); + memcpy(&gen, lvb_bits, sizeof(__le32)); *lvb_gen = le32_to_cpu(gen); } static void control_lvb_write(struct lm_lockstruct *ls, uint32_t lvb_gen, char *lvb_bits) { - uint32_t gen; + __le32 gen; memcpy(ls->ls_control_lvb, lvb_bits, GDLM_LVB_SIZE); gen = cpu_to_le32(lvb_gen); - memcpy(ls->ls_control_lvb, &gen, sizeof(uint32_t)); + memcpy(ls->ls_control_lvb, &gen, sizeof(__le32)); } static int all_jid_bits_clear(char *lvb) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 453b50eadde..98236d0df3c 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -667,7 +667,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, struct buffer_head *bh; struct page *page; void *kaddr, *ptr; - struct gfs2_quota q, *qp; + struct gfs2_quota q; int err, nbytes; u64 size; @@ -683,28 +683,25 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, return err; err = -EIO; - qp = &q; - qp->qu_value = be64_to_cpu(qp->qu_value); - qp->qu_value += change; - qp->qu_value = cpu_to_be64(qp->qu_value); - qd->qd_qb.qb_value = qp->qu_value; + be64_add_cpu(&q.qu_value, change); + qd->qd_qb.qb_value = q.qu_value; if (fdq) { if (fdq->d_fieldmask & FS_DQ_BSOFT) { - qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); - qd->qd_qb.qb_warn = qp->qu_warn; + q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); + qd->qd_qb.qb_warn = q.qu_warn; } if (fdq->d_fieldmask & FS_DQ_BHARD) { - qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); - qd->qd_qb.qb_limit = qp->qu_limit; + q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); + qd->qd_qb.qb_limit = q.qu_limit; } if (fdq->d_fieldmask & FS_DQ_BCOUNT) { - qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift); - qd->qd_qb.qb_value = qp->qu_value; + q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift); + qd->qd_qb.qb_value = q.qu_value; } } /* Write the quota into the quota file on disk */ - ptr = qp; + ptr = &q; nbytes = sizeof(struct gfs2_quota); get_a_page: page = find_or_create_page(mapping, index, GFP_NOFS); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 4d83abdd563..c8d6161bd68 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1127,7 +1127,7 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); rgd->rd_free_clone = rgd->rd_free; } - if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) { + if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) { rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd)); gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data); @@ -1161,7 +1161,7 @@ int update_rgrp_lvb(struct gfs2_rgrpd *rgd) if (rgd->rd_flags & GFS2_RDF_UPTODATE) return 0; - if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) + if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) return gfs2_rgrp_bh_get(rgd); rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 25437280a20..db23ce1bd90 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -33,15 +33,6 @@ static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode) #define FILE_HOSTFS_I(file) HOSTFS_I(file_inode(file)) -static int hostfs_d_delete(const struct dentry *dentry) -{ - return 1; -} - -static const struct dentry_operations hostfs_dentry_ops = { - .d_delete = hostfs_d_delete, -}; - /* Changed in hostfs_args before the kernel starts running */ static char *root_ino = ""; static int append = 0; @@ -925,7 +916,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) sb->s_blocksize_bits = 10; sb->s_magic = HOSTFS_SUPER_MAGIC; sb->s_op = &hostfs_sbops; - sb->s_d_op = &hostfs_dentry_ops; + sb->s_d_op = &simple_dentry_operations; sb->s_maxbytes = MAX_LFS_FILESIZE; /* NULL is printed as <NULL> by sprintf: avoid that. */ diff --git a/fs/libfs.c b/fs/libfs.c index 5de06947ba5..a1844244246 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -47,10 +47,16 @@ EXPORT_SYMBOL(simple_statfs); * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ -static int simple_delete_dentry(const struct dentry *dentry) +int always_delete_dentry(const struct dentry *dentry) { return 1; } +EXPORT_SYMBOL(always_delete_dentry); + +const struct dentry_operations simple_dentry_operations = { + .d_delete = always_delete_dentry, +}; +EXPORT_SYMBOL(simple_dentry_operations); /* * Lookup the data. This is trivial - if the dentry didn't already @@ -58,10 +64,6 @@ static int simple_delete_dentry(const struct dentry *dentry) */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - static const struct dentry_operations simple_dentry_operations = { - .d_delete = simple_delete_dentry, - }; - if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_sb->s_d_op) diff --git a/fs/namei.c b/fs/namei.c index e029a4cbff7..8f77a8cea28 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2435,6 +2435,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) */ static inline int may_create(struct inode *dir, struct dentry *child) { + audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 088de1355e9..ee7237f99f5 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -141,8 +141,8 @@ xdr_error: \ static void next_decode_page(struct nfsd4_compoundargs *argp) { - argp->pagelist++; argp->p = page_address(argp->pagelist[0]); + argp->pagelist++; if (argp->pagelen < PAGE_SIZE) { argp->end = argp->p + (argp->pagelen>>2); argp->pagelen = 0; @@ -1229,6 +1229,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) len -= pages * PAGE_SIZE; argp->p = (__be32 *)page_address(argp->pagelist[0]); + argp->pagelist++; argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); } argp->p += XDR_QUADLEN(len); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 94b5f5d2bfe..7eea63cada1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -298,41 +298,12 @@ commit_metadata(struct svc_fh *fhp) } /* - * Set various file attributes. - * N.B. After this call fhp needs an fh_put + * Go over the attributes and take care of the small differences between + * NFS semantics and what Linux expects. */ -__be32 -nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, - int check_guard, time_t guardtime) +static void +nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - struct dentry *dentry; - struct inode *inode; - int accmode = NFSD_MAY_SATTR; - umode_t ftype = 0; - __be32 err; - int host_err; - int size_change = 0; - - if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) - accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; - if (iap->ia_valid & ATTR_SIZE) - ftype = S_IFREG; - - /* Get inode */ - err = fh_verify(rqstp, fhp, ftype, accmode); - if (err) - goto out; - - dentry = fhp->fh_dentry; - inode = dentry->d_inode; - - /* Ignore any mode updates on symlinks */ - if (S_ISLNK(inode->i_mode)) - iap->ia_valid &= ~ATTR_MODE; - - if (!iap->ia_valid) - goto out; - /* * NFSv2 does not differentiate between "set-[ac]time-to-now" * which only requires access, and "set-[ac]time-to-X" which @@ -342,8 +313,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, * convert to "set to now" instead of "set to explicit time" * * We only call inode_change_ok as the last test as technically - * it is not an interface that we should be using. It is only - * valid if the filesystem does not define it's own i_op->setattr. + * it is not an interface that we should be using. */ #define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) #define MAX_TOUCH_TIME_ERROR (30*60) @@ -369,30 +339,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, iap->ia_valid &= ~BOTH_TIME_SET; } } - - /* - * The size case is special. - * It changes the file as well as the attributes. - */ - if (iap->ia_valid & ATTR_SIZE) { - if (iap->ia_size < inode->i_size) { - err = nfsd_permission(rqstp, fhp->fh_export, dentry, - NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE); - if (err) - goto out; - } - - host_err = get_write_access(inode); - if (host_err) - goto out_nfserr; - - size_change = 1; - host_err = locks_verify_truncate(inode, NULL, iap->ia_size); - if (host_err) { - put_write_access(inode); - goto out_nfserr; - } - } /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { @@ -415,32 +361,111 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); } } +} - /* Change the attributes. */ +static __be32 +nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct iattr *iap) +{ + struct inode *inode = fhp->fh_dentry->d_inode; + int host_err; - iap->ia_valid |= ATTR_CTIME; + if (iap->ia_size < inode->i_size) { + __be32 err; - err = nfserr_notsync; - if (!check_guard || guardtime == inode->i_ctime.tv_sec) { - host_err = nfsd_break_lease(inode); - if (host_err) - goto out_nfserr; - fh_lock(fhp); + err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); + if (err) + return err; + } - host_err = notify_change(dentry, iap, NULL); - err = nfserrno(host_err); - fh_unlock(fhp); + host_err = get_write_access(inode); + if (host_err) + goto out_nfserrno; + + host_err = locks_verify_truncate(inode, NULL, iap->ia_size); + if (host_err) + goto out_put_write_access; + return 0; + +out_put_write_access: + put_write_access(inode); +out_nfserrno: + return nfserrno(host_err); +} + +/* + * Set various file attributes. After this call fhp needs an fh_put. + */ +__be32 +nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, + int check_guard, time_t guardtime) +{ + struct dentry *dentry; + struct inode *inode; + int accmode = NFSD_MAY_SATTR; + umode_t ftype = 0; + __be32 err; + int host_err; + int size_change = 0; + + if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) + accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; + if (iap->ia_valid & ATTR_SIZE) + ftype = S_IFREG; + + /* Get inode */ + err = fh_verify(rqstp, fhp, ftype, accmode); + if (err) + goto out; + + dentry = fhp->fh_dentry; + inode = dentry->d_inode; + + /* Ignore any mode updates on symlinks */ + if (S_ISLNK(inode->i_mode)) + iap->ia_valid &= ~ATTR_MODE; + + if (!iap->ia_valid) + goto out; + + nfsd_sanitize_attrs(inode, iap); + + /* + * The size case is special, it changes the file in addition to the + * attributes. + */ + if (iap->ia_valid & ATTR_SIZE) { + err = nfsd_get_write_access(rqstp, fhp, iap); + if (err) + goto out; + size_change = 1; } + + iap->ia_valid |= ATTR_CTIME; + + if (check_guard && guardtime != inode->i_ctime.tv_sec) { + err = nfserr_notsync; + goto out_put_write_access; + } + + host_err = nfsd_break_lease(inode); + if (host_err) + goto out_put_write_access_nfserror; + + fh_lock(fhp); + host_err = notify_change(dentry, iap, NULL); + fh_unlock(fhp); + +out_put_write_access_nfserror: + err = nfserrno(host_err); +out_put_write_access: if (size_change) put_write_access(inode); if (!err) commit_metadata(fhp); out: return err; - -out_nfserr: - err = nfserrno(host_err); - goto out; } #if defined(CONFIG_NFSD_V2_ACL) || \ diff --git a/fs/proc/base.c b/fs/proc/base.c index 1485e38daaa..03c8d747be4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1151,10 +1151,16 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, goto out_free_page; } - kloginuid = make_kuid(file->f_cred->user_ns, loginuid); - if (!uid_valid(kloginuid)) { - length = -EINVAL; - goto out_free_page; + + /* is userspace tring to explicitly UNSET the loginuid? */ + if (loginuid == AUDIT_UID_UNSET) { + kloginuid = INVALID_UID; + } else { + kloginuid = make_kuid(file->f_cred->user_ns, loginuid); + if (!uid_valid(kloginuid)) { + length = -EINVAL; + goto out_free_page; + } } length = audit_set_loginuid(kloginuid); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 737e15615b0..cca93b6fb9a 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -175,22 +175,6 @@ static const struct inode_operations proc_link_inode_operations = { }; /* - * As some entries in /proc are volatile, we want to - * get rid of unused dentries. This could be made - * smarter: we could keep a "volatile" flag in the - * inode to indicate which ones to keep. - */ -static int proc_delete_dentry(const struct dentry * dentry) -{ - return 1; -} - -static const struct dentry_operations proc_dentry_operations = -{ - .d_delete = proc_delete_dentry, -}; - -/* * Don't create negative dentries here, return -ENOENT by hand * instead. */ @@ -209,7 +193,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_dentry_operations); + d_set_d_op(dentry, &simple_dentry_operations); d_add(dentry, inode); return NULL; } diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 49a7fff2e83..9ae46b87470 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -42,12 +42,6 @@ static const struct inode_operations ns_inode_operations = { .setattr = proc_setattr, }; -static int ns_delete_dentry(const struct dentry *dentry) -{ - /* Don't cache namespace inodes when not in use */ - return 1; -} - static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) { struct inode *inode = dentry->d_inode; @@ -59,7 +53,7 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) const struct dentry_operations ns_dentry_operations = { - .d_delete = ns_delete_dentry, + .d_delete = always_delete_dentry, .d_dname = ns_dname, }; diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c index 16e8abb7709..72d29177998 100644 --- a/fs/quota/netlink.c +++ b/fs/quota/netlink.c @@ -9,13 +9,25 @@ #include <net/netlink.h> #include <net/genetlink.h> +static const struct genl_multicast_group quota_mcgrps[] = { + { .name = "events", }, +}; + /* Netlink family structure for quota */ static struct genl_family quota_genl_family = { - .id = GENL_ID_GENERATE, + /* + * Needed due to multicast group ID abuse - old code assumed + * the family ID was also a valid multicast group ID (which + * isn't true) and userspace might thus rely on it. Assign a + * static ID for this group to make dealing with that easier. + */ + .id = GENL_ID_VFS_DQUOT, .hdrsize = 0, .name = "VFS_DQUOT", .version = 1, .maxattr = QUOTA_NL_A_MAX, + .mcgrps = quota_mcgrps, + .n_mcgrps = ARRAY_SIZE(quota_mcgrps), }; /** @@ -78,7 +90,7 @@ void quota_send_warning(struct kqid qid, dev_t dev, goto attr_err_out; genlmsg_end(skb, msg_head); - genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS); + genlmsg_multicast("a_genl_family, skb, 0, 0, GFP_NOFS); return; attr_err_out: printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); diff --git a/fs/seq_file.c b/fs/seq_file.c index 1cd2388ca5b..1d641bb108d 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -136,6 +136,7 @@ static int traverse(struct seq_file *m, loff_t offset) Eoverflow: m->op->stop(m, p); kfree(m->buf); + m->count = 0; m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); return !m->buf ? -ENOMEM : -EAGAIN; } @@ -232,10 +233,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) goto Fill; m->op->stop(m, p); kfree(m->buf); + m->count = 0; m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); if (!m->buf) goto Enomem; - m->count = 0; m->version = 0; pos = m->index; p = m->op->start(m, &pos); diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index c70111ebefd..b6fa8657dcb 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -25,6 +25,78 @@ config SQUASHFS If unsure, say N. +choice + prompt "File decompression options" + depends on SQUASHFS + help + Squashfs now supports two options for decompressing file + data. Traditionally Squashfs has decompressed into an + intermediate buffer and then memcopied it into the page cache. + Squashfs now supports the ability to decompress directly into + the page cache. + + If unsure, select "Decompress file data into an intermediate buffer" + +config SQUASHFS_FILE_CACHE + bool "Decompress file data into an intermediate buffer" + help + Decompress file data into an intermediate buffer and then + memcopy it into the page cache. + +config SQUASHFS_FILE_DIRECT + bool "Decompress files directly into the page cache" + help + Directly decompress file data into the page cache. + Doing so can significantly improve performance because + it eliminates a memcpy and it also removes the lock contention + on the single buffer. + +endchoice + +choice + prompt "Decompressor parallelisation options" + depends on SQUASHFS + help + Squashfs now supports three parallelisation options for + decompression. Each one exhibits various trade-offs between + decompression performance and CPU and memory usage. + + If in doubt, select "Single threaded compression" + +config SQUASHFS_DECOMP_SINGLE + bool "Single threaded compression" + help + Traditionally Squashfs has used single-threaded decompression. + Only one block (data or metadata) can be decompressed at any + one time. This limits CPU and memory usage to a minimum. + +config SQUASHFS_DECOMP_MULTI + bool "Use multiple decompressors for parallel I/O" + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + If you have a parallel I/O workload and your system has enough memory, + using this option may improve overall I/O performance. + + This decompressor implementation uses up to two parallel + decompressors per core. It dynamically allocates decompressors + on a demand basis. + +config SQUASHFS_DECOMP_MULTI_PERCPU + bool "Use percpu multiple decompressors for parallel I/O" + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + This decompressor implementation uses a maximum of one + decompressor per core. It uses percpu variables to ensure + decompression is load-balanced across the cores. + +endchoice + config SQUASHFS_XATTR bool "Squashfs XATTR support" depends on SQUASHFS diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile index 110b0476f3b..4132520b4ff 100644 --- a/fs/squashfs/Makefile +++ b/fs/squashfs/Makefile @@ -5,6 +5,11 @@ obj-$(CONFIG_SQUASHFS) += squashfs.o squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o squashfs-y += namei.o super.o symlink.o decompressor.o +squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o +squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 41d108ecc9b..0cea9b9236d 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -36,6 +36,7 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" /* * Read the metadata block length, this is stored in the first two @@ -86,16 +87,16 @@ static struct buffer_head *get_block_length(struct super_block *sb, * generated a larger block - this does occasionally happen with compression * algorithms). */ -int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, - int length, u64 *next_index, int srclength, int pages) +int squashfs_read_data(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct buffer_head **bh; int offset = index & ((1 << msblk->devblksize_log2) - 1); u64 cur_index = index >> msblk->devblksize_log2; - int bytes, compressed, b = 0, k = 0, page = 0, avail; + int bytes, compressed, b = 0, k = 0, avail, i; - bh = kcalloc(((srclength + msblk->devblksize - 1) + bh = kcalloc(((output->length + msblk->devblksize - 1) >> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL); if (bh == NULL) return -ENOMEM; @@ -111,9 +112,9 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, *next_index = index + length; TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n", - index, compressed ? "" : "un", length, srclength); + index, compressed ? "" : "un", length, output->length); - if (length < 0 || length > srclength || + if (length < 0 || length > output->length || (index + length) > msblk->bytes_used) goto read_failure; @@ -145,7 +146,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, TRACE("Block @ 0x%llx, %scompressed size %d\n", index, compressed ? "" : "un", length); - if (length < 0 || length > srclength || + if (length < 0 || length > output->length || (index + length) > msblk->bytes_used) goto block_release; @@ -158,9 +159,15 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, ll_rw_block(READ, b - 1, bh + 1); } + for (i = 0; i < b; i++) { + wait_on_buffer(bh[i]); + if (!buffer_uptodate(bh[i])) + goto block_release; + } + if (compressed) { - length = squashfs_decompress(msblk, buffer, bh, b, offset, - length, srclength, pages); + length = squashfs_decompress(msblk, bh, b, offset, length, + output); if (length < 0) goto read_failure; } else { @@ -168,22 +175,20 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, * Block is uncompressed. */ int in, pg_offset = 0; + void *data = squashfs_first_page(output); for (bytes = length; k < b; k++) { in = min(bytes, msblk->devblksize - offset); bytes -= in; - wait_on_buffer(bh[k]); - if (!buffer_uptodate(bh[k])) - goto block_release; while (in) { if (pg_offset == PAGE_CACHE_SIZE) { - page++; + data = squashfs_next_page(output); pg_offset = 0; } avail = min_t(int, in, PAGE_CACHE_SIZE - pg_offset); - memcpy(buffer[page] + pg_offset, - bh[k]->b_data + offset, avail); + memcpy(data + pg_offset, bh[k]->b_data + offset, + avail); in -= avail; pg_offset += avail; offset += avail; @@ -191,6 +196,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, offset = 0; put_bh(bh[k]); } + squashfs_finish_page(output); } kfree(bh); diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index af0b7380259..1cb70a0b216 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -56,6 +56,7 @@ #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" +#include "page_actor.h" /* * Look-up block in cache, and increment usage count. If not in cache, read @@ -119,9 +120,8 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, entry->error = 0; spin_unlock(&cache->lock); - entry->length = squashfs_read_data(sb, entry->data, - block, length, &entry->next_index, - cache->block_size, cache->pages); + entry->length = squashfs_read_data(sb, block, length, + &entry->next_index, entry->actor); spin_lock(&cache->lock); @@ -220,6 +220,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache) kfree(cache->entry[i].data[j]); kfree(cache->entry[i].data); } + kfree(cache->entry[i].actor); } kfree(cache->entry); @@ -280,6 +281,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, goto cleanup; } } + + entry->actor = squashfs_page_actor_init(entry->data, + cache->pages, 0); + if (entry->actor == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } } return cache; @@ -410,6 +418,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length) int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; int i, res; void *table, *buffer, **data; + struct squashfs_page_actor *actor; table = buffer = kmalloc(length, GFP_KERNEL); if (table == NULL) @@ -421,19 +430,28 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length) goto failed; } + actor = squashfs_page_actor_init(data, pages, length); + if (actor == NULL) { + res = -ENOMEM; + goto failed2; + } + for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) data[i] = buffer; - res = squashfs_read_data(sb, data, block, length | - SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages); + res = squashfs_read_data(sb, block, length | + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor); kfree(data); + kfree(actor); if (res < 0) goto failed; return table; +failed2: + kfree(data); failed: kfree(table); return ERR_PTR(res); diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index 3f6271d86ab..ac22fe73b0a 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -30,6 +30,7 @@ #include "squashfs_fs_sb.h" #include "decompressor.h" #include "squashfs.h" +#include "page_actor.h" /* * This file (and decompressor.h) implements a decompressor framework for @@ -37,29 +38,29 @@ */ static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = { - NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0 + NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0 }; #ifndef CONFIG_SQUASHFS_LZO static const struct squashfs_decompressor squashfs_lzo_comp_ops = { - NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0 + NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0 }; #endif #ifndef CONFIG_SQUASHFS_XZ static const struct squashfs_decompressor squashfs_xz_comp_ops = { - NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 + NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 }; #endif #ifndef CONFIG_SQUASHFS_ZLIB static const struct squashfs_decompressor squashfs_zlib_comp_ops = { - NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0 + NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0 }; #endif static const struct squashfs_decompressor squashfs_unknown_comp_ops = { - NULL, NULL, NULL, 0, "unknown", 0 + NULL, NULL, NULL, NULL, 0, "unknown", 0 }; static const struct squashfs_decompressor *decompressor[] = { @@ -83,10 +84,11 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id) } -void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags) +static void *get_comp_opts(struct super_block *sb, unsigned short flags) { struct squashfs_sb_info *msblk = sb->s_fs_info; - void *strm, *buffer = NULL; + void *buffer = NULL, *comp_opts; + struct squashfs_page_actor *actor = NULL; int length = 0; /* @@ -94,23 +96,46 @@ void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags) */ if (SQUASHFS_COMP_OPTS(flags)) { buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); - if (buffer == NULL) - return ERR_PTR(-ENOMEM); + if (buffer == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } + + actor = squashfs_page_actor_init(&buffer, 1, 0); + if (actor == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } - length = squashfs_read_data(sb, &buffer, - sizeof(struct squashfs_super_block), 0, NULL, - PAGE_CACHE_SIZE, 1); + length = squashfs_read_data(sb, + sizeof(struct squashfs_super_block), 0, NULL, actor); if (length < 0) { - strm = ERR_PTR(length); - goto finished; + comp_opts = ERR_PTR(length); + goto out; } } - strm = msblk->decompressor->init(msblk, buffer, length); + comp_opts = squashfs_comp_opts(msblk, buffer, length); -finished: +out: + kfree(actor); kfree(buffer); + return comp_opts; +} + + +void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + void *stream, *comp_opts = get_comp_opts(sb, flags); + + if (IS_ERR(comp_opts)) + return comp_opts; + + stream = squashfs_decompressor_create(msblk, comp_opts); + if (IS_ERR(stream)) + kfree(comp_opts); - return strm; + return stream; } diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h index 330073e2902..af098532180 100644 --- a/fs/squashfs/decompressor.h +++ b/fs/squashfs/decompressor.h @@ -24,28 +24,22 @@ */ struct squashfs_decompressor { - void *(*init)(struct squashfs_sb_info *, void *, int); + void *(*init)(struct squashfs_sb_info *, void *); + void *(*comp_opts)(struct squashfs_sb_info *, void *, int); void (*free)(void *); - int (*decompress)(struct squashfs_sb_info *, void **, - struct buffer_head **, int, int, int, int, int); + int (*decompress)(struct squashfs_sb_info *, void *, + struct buffer_head **, int, int, int, + struct squashfs_page_actor *); int id; char *name; int supported; }; -static inline void squashfs_decompressor_free(struct squashfs_sb_info *msblk, - void *s) +static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int length) { - if (msblk->decompressor) - msblk->decompressor->free(s); -} - -static inline int squashfs_decompress(struct squashfs_sb_info *msblk, - void **buffer, struct buffer_head **bh, int b, int offset, int length, - int srclength, int pages) -{ - return msblk->decompressor->decompress(msblk, buffer, bh, b, offset, - length, srclength, pages); + return msblk->decompressor->comp_opts ? + msblk->decompressor->comp_opts(msblk, buff, length) : NULL; } #ifdef CONFIG_SQUASHFS_XZ diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c new file mode 100644 index 00000000000..d6008a63647 --- /dev/null +++ b/fs/squashfs/decompressor_multi.c @@ -0,0 +1,198 @@ +/* + * Copyright (c) 2013 + * Minchan Kim <minchan@kernel.org> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/buffer_head.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/cpumask.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression in the + * decompressor framework + */ + + +/* + * The reason that multiply two is that a CPU can request new I/O + * while it is waiting previous request. + */ +#define MAX_DECOMPRESSOR (num_online_cpus() * 2) + + +int squashfs_max_decompressors(void) +{ + return MAX_DECOMPRESSOR; +} + + +struct squashfs_stream { + void *comp_opts; + struct list_head strm_list; + struct mutex mutex; + int avail_decomp; + wait_queue_head_t wait; +}; + + +struct decomp_stream { + void *stream; + struct list_head list; +}; + + +static void put_decomp_stream(struct decomp_stream *decomp_strm, + struct squashfs_stream *stream) +{ + mutex_lock(&stream->mutex); + list_add(&decomp_strm->list, &stream->strm_list); + mutex_unlock(&stream->mutex); + wake_up(&stream->wait); +} + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct decomp_stream *decomp_strm = NULL; + int err = -ENOMEM; + + stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (!stream) + goto out; + + stream->comp_opts = comp_opts; + mutex_init(&stream->mutex); + INIT_LIST_HEAD(&stream->strm_list); + init_waitqueue_head(&stream->wait); + + /* + * We should have a decompressor at least as default + * so if we fail to allocate new decompressor dynamically, + * we could always fall back to default decompressor and + * file system works. + */ + decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); + if (!decomp_strm) + goto out; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + err = PTR_ERR(decomp_strm->stream); + goto out; + } + + list_add(&decomp_strm->list, &stream->strm_list); + stream->avail_decomp = 1; + return stream; + +out: + kfree(decomp_strm); + kfree(stream); + return ERR_PTR(err); +} + + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + if (stream) { + struct decomp_stream *decomp_strm; + + while (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + msblk->decompressor->free(decomp_strm->stream); + kfree(decomp_strm); + stream->avail_decomp--; + } + WARN_ON(stream->avail_decomp); + kfree(stream->comp_opts); + kfree(stream); + } +} + + +static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk, + struct squashfs_stream *stream) +{ + struct decomp_stream *decomp_strm; + + while (1) { + mutex_lock(&stream->mutex); + + /* There is available decomp_stream */ + if (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + mutex_unlock(&stream->mutex); + break; + } + + /* + * If there is no available decomp and already full, + * let's wait for releasing decomp from other users. + */ + if (stream->avail_decomp >= MAX_DECOMPRESSOR) + goto wait; + + /* Let's allocate new decomp */ + decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); + if (!decomp_strm) + goto wait; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + kfree(decomp_strm); + goto wait; + } + + stream->avail_decomp++; + WARN_ON(stream->avail_decomp > MAX_DECOMPRESSOR); + + mutex_unlock(&stream->mutex); + break; +wait: + /* + * If system memory is tough, let's for other's + * releasing instead of hurting VM because it could + * make page cache thrashing. + */ + mutex_unlock(&stream->mutex); + wait_event(stream->wait, + !list_empty(&stream->strm_list)); + } + + return decomp_strm; +} + + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream); + res = msblk->decompressor->decompress(msblk, decomp_stream->stream, + bh, b, offset, length, output); + put_decomp_stream(decomp_stream, stream); + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + return res; +} diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c new file mode 100644 index 00000000000..23a9c28ad8e --- /dev/null +++ b/fs/squashfs/decompressor_multi_percpu.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/percpu.h> +#include <linux/buffer_head.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression using percpu + * variables, one thread per cpu core. + */ + +struct squashfs_stream { + void *stream; +}; + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct squashfs_stream __percpu *percpu; + int err, cpu; + + percpu = alloc_percpu(struct squashfs_stream); + if (percpu == NULL) + return ERR_PTR(-ENOMEM); + + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + } + + kfree(comp_opts); + return (__force void *) percpu; + +out: + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + if (!IS_ERR_OR_NULL(stream->stream)) + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + return ERR_PTR(err); +} + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; + struct squashfs_stream *stream; + int cpu; + + if (msblk->stream) { + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + } +} + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; + struct squashfs_stream *stream = get_cpu_ptr(percpu); + int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, + offset, length, output); + put_cpu_ptr(stream); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +int squashfs_max_decompressors(void) +{ + return num_possible_cpus(); +} diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c new file mode 100644 index 00000000000..a6c75929a00 --- /dev/null +++ b/fs/squashfs/decompressor_single.c @@ -0,0 +1,85 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/buffer_head.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements single-threaded decompression in the + * decompressor framework + */ + +struct squashfs_stream { + void *stream; + struct mutex mutex; +}; + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + int err = -ENOMEM; + + stream = kmalloc(sizeof(*stream), GFP_KERNEL); + if (stream == NULL) + goto out; + + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + + kfree(comp_opts); + mutex_init(&stream->mutex); + return stream; + +out: + kfree(stream); + return ERR_PTR(err); +} + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + + if (stream) { + msblk->decompressor->free(stream->stream); + kfree(stream); + } +} + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + + mutex_lock(&stream->mutex); + res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, + offset, length, output); + mutex_unlock(&stream->mutex); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +int squashfs_max_decompressors(void) +{ + return 1; +} diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 8ca62c28fe1..e5c9689062b 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -370,77 +370,15 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) return le32_to_cpu(size); } - -static int squashfs_readpage(struct file *file, struct page *page) +/* Copy data into page cache */ +void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, + int bytes, int offset) { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int bytes, i, offset = 0, sparse = 0; - struct squashfs_cache_entry *buffer = NULL; void *pageaddr; - - int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; - int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); - int start_index = page->index & ~mask; - int end_index = start_index | mask; - int file_end = i_size_read(inode) >> msblk->block_log; - - TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", - page->index, squashfs_i(inode)->start); - - if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) - goto out; - - if (index < file_end || squashfs_i(inode)->fragment_block == - SQUASHFS_INVALID_BLK) { - /* - * Reading a datablock from disk. Need to read block list - * to get location and block size. - */ - u64 block = 0; - int bsize = read_blocklist(inode, index, &block); - if (bsize < 0) - goto error_out; - - if (bsize == 0) { /* hole */ - bytes = index == file_end ? - (i_size_read(inode) & (msblk->block_size - 1)) : - msblk->block_size; - sparse = 1; - } else { - /* - * Read and decompress datablock. - */ - buffer = squashfs_get_datablock(inode->i_sb, - block, bsize); - if (buffer->error) { - ERROR("Unable to read page, block %llx, size %x" - "\n", block, bsize); - squashfs_cache_put(buffer); - goto error_out; - } - bytes = buffer->length; - } - } else { - /* - * Datablock is stored inside a fragment (tail-end packed - * block). - */ - buffer = squashfs_get_fragment(inode->i_sb, - squashfs_i(inode)->fragment_block, - squashfs_i(inode)->fragment_size); - - if (buffer->error) { - ERROR("Unable to read page, block %llx, size %x\n", - squashfs_i(inode)->fragment_block, - squashfs_i(inode)->fragment_size); - squashfs_cache_put(buffer); - goto error_out; - } - bytes = i_size_read(inode) & (msblk->block_size - 1); - offset = squashfs_i(inode)->fragment_offset; - } + int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int start_index = page->index & ~mask, end_index = start_index | mask; /* * Loop copying datablock into pages. As the datablock likely covers @@ -451,7 +389,7 @@ static int squashfs_readpage(struct file *file, struct page *page) for (i = start_index; i <= end_index && bytes > 0; i++, bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { struct page *push_page; - int avail = sparse ? 0 : min_t(int, bytes, PAGE_CACHE_SIZE); + int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0; TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail); @@ -475,11 +413,75 @@ skip_page: if (i != page->index) page_cache_release(push_page); } +} + +/* Read datablock stored packed inside a fragment (tail-end packed block) */ +static int squashfs_readpage_fragment(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + else + squashfs_copy_cache(page, buffer, i_size_read(inode) & + (msblk->block_size - 1), + squashfs_i(inode)->fragment_offset); + + squashfs_cache_put(buffer); + return res; +} - if (!sparse) - squashfs_cache_put(buffer); +static int squashfs_readpage_sparse(struct page *page, int index, int file_end) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int bytes = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; + squashfs_copy_cache(page, NULL, bytes, 0); return 0; +} + +static int squashfs_readpage(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); + int file_end = i_size_read(inode) >> msblk->block_log; + int res; + void *pageaddr; + + TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", + page->index, squashfs_i(inode)->start); + + if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT)) + goto out; + + if (index < file_end || squashfs_i(inode)->fragment_block == + SQUASHFS_INVALID_BLK) { + u64 block = 0; + int bsize = read_blocklist(inode, index, &block); + if (bsize < 0) + goto error_out; + + if (bsize == 0) + res = squashfs_readpage_sparse(page, index, file_end); + else + res = squashfs_readpage_block(page, block, bsize); + } else + res = squashfs_readpage_fragment(page); + + if (!res) + return 0; error_out: SetPageError(page); diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c new file mode 100644 index 00000000000..f2310d2a201 --- /dev/null +++ b/fs/squashfs/file_cache.c @@ -0,0 +1,38 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +/* Read separately compressed datablock and memcopy into page cache */ +int squashfs_readpage_block(struct page *page, u64 block, int bsize) +{ + struct inode *i = page->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, + block, bsize); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", block, + bsize); + else + squashfs_copy_cache(page, buffer, buffer->length, 0); + + squashfs_cache_put(buffer); + return res; +} diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c new file mode 100644 index 00000000000..2943b2bfae4 --- /dev/null +++ b/fs/squashfs/file_direct.c @@ -0,0 +1,173 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "page_actor.h" + +static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, + int pages, struct page **page); + +/* Read separately compressed datablock directly into page cache */ +int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) + +{ + struct inode *inode = target_page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + + int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int start_index = target_page->index & ~mask; + int end_index = start_index | mask; + int i, n, pages, missing_pages, bytes, res = -ENOMEM; + struct page **page; + struct squashfs_page_actor *actor; + void *pageaddr; + + if (end_index > file_end) + end_index = file_end; + + pages = end_index - start_index + 1; + + page = kmalloc(sizeof(void *) * pages, GFP_KERNEL); + if (page == NULL) + return res; + + /* + * Create a "page actor" which will kmap and kunmap the + * page cache pages appropriately within the decompressor + */ + actor = squashfs_page_actor_init_special(page, pages, 0); + if (actor == NULL) + goto out; + + /* Try to grab all the pages covered by the Squashfs block */ + for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) { + page[i] = (n == target_page->index) ? target_page : + grab_cache_page_nowait(target_page->mapping, n); + + if (page[i] == NULL) { + missing_pages++; + continue; + } + + if (PageUptodate(page[i])) { + unlock_page(page[i]); + page_cache_release(page[i]); + page[i] = NULL; + missing_pages++; + } + } + + if (missing_pages) { + /* + * Couldn't get one or more pages, this page has either + * been VM reclaimed, but others are still in the page cache + * and uptodate, or we're racing with another thread in + * squashfs_readpage also trying to grab them. Fall back to + * using an intermediate buffer. + */ + res = squashfs_read_cache(target_page, block, bsize, pages, + page); + goto out; + } + + /* Decompress directly into the page cache buffers */ + res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + if (res < 0) + goto mark_errored; + + /* Last page may have trailing bytes not filled */ + bytes = res % PAGE_CACHE_SIZE; + if (bytes) { + pageaddr = kmap_atomic(page[pages - 1]); + memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes); + kunmap_atomic(pageaddr); + } + + /* Mark pages as uptodate, unlock and release */ + for (i = 0; i < pages; i++) { + flush_dcache_page(page[i]); + SetPageUptodate(page[i]); + unlock_page(page[i]); + if (page[i] != target_page) + page_cache_release(page[i]); + } + + kfree(actor); + kfree(page); + + return 0; + +mark_errored: + /* Decompression failed, mark pages as errored. Target_page is + * dealt with by the caller + */ + for (i = 0; i < pages; i++) { + if (page[i] == target_page) + continue; + flush_dcache_page(page[i]); + SetPageError(page[i]); + unlock_page(page[i]); + page_cache_release(page[i]); + } + +out: + kfree(actor); + kfree(page); + return res; +} + + +static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, + int pages, struct page **page) +{ + struct inode *i = target_page->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, + block, bsize); + int bytes = buffer->length, res = buffer->error, n, offset = 0; + void *pageaddr; + + if (res) { + ERROR("Unable to read page, block %llx, size %x\n", block, + bsize); + goto out; + } + + for (n = 0; n < pages && bytes > 0; n++, + bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { + int avail = min_t(int, bytes, PAGE_CACHE_SIZE); + + if (page[n] == NULL) + continue; + + pageaddr = kmap_atomic(page[n]); + squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail); + kunmap_atomic(pageaddr); + flush_dcache_page(page[n]); + SetPageUptodate(page[n]); + unlock_page(page[n]); + if (page[n] != target_page) + page_cache_release(page[n]); + } + +out: + squashfs_cache_put(buffer); + return res; +} diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 00f4dfc5f08..244b9fbfff7 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -31,13 +31,14 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" struct squashfs_lzo { void *input; void *output; }; -static void *lzo_init(struct squashfs_sb_info *msblk, void *buff, int len) +static void *lzo_init(struct squashfs_sb_info *msblk, void *buff) { int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); @@ -74,22 +75,16 @@ static void lzo_free(void *strm) } -static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { - struct squashfs_lzo *stream = msblk->stream; - void *buff = stream->input; + struct squashfs_lzo *stream = strm; + void *buff = stream->input, *data; int avail, i, bytes = length, res; - size_t out_len = srclength; - - mutex_lock(&msblk->read_data_mutex); + size_t out_len = output->length; for (i = 0; i < b; i++) { - wait_on_buffer(bh[i]); - if (!buffer_uptodate(bh[i])) - goto block_release; - avail = min(bytes, msblk->devblksize - offset); memcpy(buff, bh[i]->b_data + offset, avail); buff += avail; @@ -104,24 +99,24 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer, goto failed; res = bytes = (int)out_len; - for (i = 0, buff = stream->output; bytes && i < pages; i++) { - avail = min_t(int, bytes, PAGE_CACHE_SIZE); - memcpy(buffer[i], buff, avail); - buff += avail; - bytes -= avail; + data = squashfs_first_page(output); + buff = stream->output; + while (data) { + if (bytes <= PAGE_CACHE_SIZE) { + memcpy(data, buff, bytes); + break; + } else { + memcpy(data, buff, PAGE_CACHE_SIZE); + buff += PAGE_CACHE_SIZE; + bytes -= PAGE_CACHE_SIZE; + data = squashfs_next_page(output); + } } + squashfs_finish_page(output); - mutex_unlock(&msblk->read_data_mutex); return res; -block_release: - for (; i < b; i++) - put_bh(bh[i]); - failed: - mutex_unlock(&msblk->read_data_mutex); - - ERROR("lzo decompression failed, data probably corrupt\n"); return -EIO; } diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c new file mode 100644 index 00000000000..5a1c11f5644 --- /dev/null +++ b/fs/squashfs/page_actor.c @@ -0,0 +1,100 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include "page_actor.h" + +/* + * This file contains implementations of page_actor for decompressing into + * an intermediate buffer, and for decompressing directly into the + * page cache. + * + * Calling code should avoid sleeping between calls to squashfs_first_page() + * and squashfs_finish_page(). + */ + +/* Implementation of page_actor for decompressing into intermediate buffer */ +static void *cache_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->buffer[0]; +} + +static void *cache_next_page(struct squashfs_page_actor *actor) +{ + if (actor->next_page == actor->pages) + return NULL; + + return actor->buffer[actor->next_page++]; +} + +static void cache_finish_page(struct squashfs_page_actor *actor) +{ + /* empty */ +} + +struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->buffer = buffer; + actor->pages = pages; + actor->next_page = 0; + actor->squashfs_first_page = cache_first_page; + actor->squashfs_next_page = cache_next_page; + actor->squashfs_finish_page = cache_finish_page; + return actor; +} + +/* Implementation of page_actor for decompressing directly into page cache. */ +static void *direct_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->pageaddr = kmap_atomic(actor->page[0]); +} + +static void *direct_next_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) + kunmap_atomic(actor->pageaddr); + + return actor->pageaddr = actor->next_page == actor->pages ? NULL : + kmap_atomic(actor->page[actor->next_page++]); +} + +static void direct_finish_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) + kunmap_atomic(actor->pageaddr); +} + +struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->page = page; + actor->pages = pages; + actor->next_page = 0; + actor->pageaddr = NULL; + actor->squashfs_first_page = direct_first_page; + actor->squashfs_next_page = direct_next_page; + actor->squashfs_finish_page = direct_finish_page; + return actor; +} diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h new file mode 100644 index 00000000000..26dd82008b8 --- /dev/null +++ b/fs/squashfs/page_actor.h @@ -0,0 +1,81 @@ +#ifndef PAGE_ACTOR_H +#define PAGE_ACTOR_H +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#ifndef CONFIG_SQUASHFS_FILE_DIRECT +struct squashfs_page_actor { + void **page; + int pages; + int length; + int next_page; +}; + +static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->page = page; + actor->pages = pages; + actor->next_page = 0; + return actor; +} + +static inline void *squashfs_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->page[0]; +} + +static inline void *squashfs_next_page(struct squashfs_page_actor *actor) +{ + return actor->next_page == actor->pages ? NULL : + actor->page[actor->next_page++]; +} + +static inline void squashfs_finish_page(struct squashfs_page_actor *actor) +{ + /* empty */ +} +#else +struct squashfs_page_actor { + union { + void **buffer; + struct page **page; + }; + void *pageaddr; + void *(*squashfs_first_page)(struct squashfs_page_actor *); + void *(*squashfs_next_page)(struct squashfs_page_actor *); + void (*squashfs_finish_page)(struct squashfs_page_actor *); + int pages; + int length; + int next_page; +}; + +extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int); +extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page + **, int, int); +static inline void *squashfs_first_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_first_page(actor); +} +static inline void *squashfs_next_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_next_page(actor); +} +static inline void squashfs_finish_page(struct squashfs_page_actor *actor) +{ + actor->squashfs_finish_page(actor); +} +#endif +#endif diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index d1266516ed0..9e1bb79f7e6 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -28,8 +28,8 @@ #define WARNING(s, args...) pr_warning("SQUASHFS: "s, ## args) /* block.c */ -extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *, - int, int); +extern int squashfs_read_data(struct super_block *, u64, int, u64 *, + struct squashfs_page_actor *); /* cache.c */ extern struct squashfs_cache *squashfs_cache_init(char *, int, int); @@ -48,7 +48,14 @@ extern void *squashfs_read_table(struct super_block *, u64, int); /* decompressor.c */ extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int); -extern void *squashfs_decompressor_init(struct super_block *, unsigned short); +extern void *squashfs_decompressor_setup(struct super_block *, unsigned short); + +/* decompressor_xxx.c */ +extern void *squashfs_decompressor_create(struct squashfs_sb_info *, void *); +extern void squashfs_decompressor_destroy(struct squashfs_sb_info *); +extern int squashfs_decompress(struct squashfs_sb_info *, struct buffer_head **, + int, int, int, struct squashfs_page_actor *); +extern int squashfs_max_decompressors(void); /* export.c */ extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64, u64, @@ -59,6 +66,13 @@ extern int squashfs_frag_lookup(struct super_block *, unsigned int, u64 *); extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); +/* file.c */ +void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, + int); + +/* file_xxx.c */ +extern int squashfs_readpage_block(struct page *, u64, int); + /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); extern __le64 *squashfs_read_id_index_table(struct super_block *, u64, u64, diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 52934a22f29..1da565cb50c 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -50,6 +50,7 @@ struct squashfs_cache_entry { wait_queue_head_t wait_queue; struct squashfs_cache *cache; void **data; + struct squashfs_page_actor *actor; }; struct squashfs_sb_info { @@ -63,10 +64,9 @@ struct squashfs_sb_info { __le64 *id_table; __le64 *fragment_index; __le64 *xattr_id_table; - struct mutex read_data_mutex; struct mutex meta_index_mutex; struct meta_index *meta_index; - void *stream; + struct squashfs_stream *stream; __le64 *inode_lookup_table; u64 inode_table; u64 directory_table; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 60553a9053c..202df6312d4 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -98,7 +98,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); msblk->devblksize_log2 = ffz(~msblk->devblksize); - mutex_init(&msblk->read_data_mutex); mutex_init(&msblk->meta_index_mutex); /* @@ -206,13 +205,14 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; /* Allocate read_page block */ - msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size); + msblk->read_page = squashfs_cache_init("data", + squashfs_max_decompressors(), msblk->block_size); if (msblk->read_page == NULL) { ERROR("Failed to allocate read_page block\n"); goto failed_mount; } - msblk->stream = squashfs_decompressor_init(sb, flags); + msblk->stream = squashfs_decompressor_setup(sb, flags); if (IS_ERR(msblk->stream)) { err = PTR_ERR(msblk->stream); msblk->stream = NULL; @@ -336,7 +336,7 @@ failed_mount: squashfs_cache_delete(msblk->block_cache); squashfs_cache_delete(msblk->fragment_cache); squashfs_cache_delete(msblk->read_page); - squashfs_decompressor_free(msblk, msblk->stream); + squashfs_decompressor_destroy(msblk); kfree(msblk->inode_lookup_table); kfree(msblk->fragment_index); kfree(msblk->id_table); @@ -383,7 +383,7 @@ static void squashfs_put_super(struct super_block *sb) squashfs_cache_delete(sbi->block_cache); squashfs_cache_delete(sbi->fragment_cache); squashfs_cache_delete(sbi->read_page); - squashfs_decompressor_free(sbi, sbi->stream); + squashfs_decompressor_destroy(sbi); kfree(sbi->id_table); kfree(sbi->fragment_index); kfree(sbi->meta_index); diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index 1760b7d108f..c609624e4b8 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -32,44 +32,70 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" struct squashfs_xz { struct xz_dec *state; struct xz_buf buf; }; -struct comp_opts { +struct disk_comp_opts { __le32 dictionary_size; __le32 flags; }; -static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff, - int len) +struct comp_opts { + int dict_size; +}; + +static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int len) { - struct comp_opts *comp_opts = buff; - struct squashfs_xz *stream; - int dict_size = msblk->block_size; - int err, n; + struct disk_comp_opts *comp_opts = buff; + struct comp_opts *opts; + int err = 0, n; + + opts = kmalloc(sizeof(*opts), GFP_KERNEL); + if (opts == NULL) { + err = -ENOMEM; + goto out2; + } if (comp_opts) { /* check compressor options are the expected length */ if (len < sizeof(*comp_opts)) { err = -EIO; - goto failed; + goto out; } - dict_size = le32_to_cpu(comp_opts->dictionary_size); + opts->dict_size = le32_to_cpu(comp_opts->dictionary_size); /* the dictionary size should be 2^n or 2^n+2^(n+1) */ - n = ffs(dict_size) - 1; - if (dict_size != (1 << n) && dict_size != (1 << n) + + n = ffs(opts->dict_size) - 1; + if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) + (1 << (n + 1))) { err = -EIO; - goto failed; + goto out; } - } + } else + /* use defaults */ + opts->dict_size = max_t(int, msblk->block_size, + SQUASHFS_METADATA_SIZE); + + return opts; + +out: + kfree(opts); +out2: + return ERR_PTR(err); +} + - dict_size = max_t(int, dict_size, SQUASHFS_METADATA_SIZE); +static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff) +{ + struct comp_opts *comp_opts = buff; + struct squashfs_xz *stream; + int err; stream = kmalloc(sizeof(*stream), GFP_KERNEL); if (stream == NULL) { @@ -77,7 +103,7 @@ static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff, goto failed; } - stream->state = xz_dec_init(XZ_PREALLOC, dict_size); + stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size); if (stream->state == NULL) { kfree(stream); err = -ENOMEM; @@ -103,42 +129,37 @@ static void squashfs_xz_free(void *strm) } -static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { enum xz_ret xz_err; - int avail, total = 0, k = 0, page = 0; - struct squashfs_xz *stream = msblk->stream; - - mutex_lock(&msblk->read_data_mutex); + int avail, total = 0, k = 0; + struct squashfs_xz *stream = strm; xz_dec_reset(stream->state); stream->buf.in_pos = 0; stream->buf.in_size = 0; stream->buf.out_pos = 0; stream->buf.out_size = PAGE_CACHE_SIZE; - stream->buf.out = buffer[page++]; + stream->buf.out = squashfs_first_page(output); do { if (stream->buf.in_pos == stream->buf.in_size && k < b) { avail = min(length, msblk->devblksize - offset); length -= avail; - wait_on_buffer(bh[k]); - if (!buffer_uptodate(bh[k])) - goto release_mutex; - stream->buf.in = bh[k]->b_data + offset; stream->buf.in_size = avail; stream->buf.in_pos = 0; offset = 0; } - if (stream->buf.out_pos == stream->buf.out_size - && page < pages) { - stream->buf.out = buffer[page++]; - stream->buf.out_pos = 0; - total += PAGE_CACHE_SIZE; + if (stream->buf.out_pos == stream->buf.out_size) { + stream->buf.out = squashfs_next_page(output); + if (stream->buf.out != NULL) { + stream->buf.out_pos = 0; + total += PAGE_CACHE_SIZE; + } } xz_err = xz_dec_run(stream->state, &stream->buf); @@ -147,23 +168,14 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer, put_bh(bh[k++]); } while (xz_err == XZ_OK); - if (xz_err != XZ_STREAM_END) { - ERROR("xz_dec_run error, data probably corrupt\n"); - goto release_mutex; - } - - if (k < b) { - ERROR("xz_uncompress error, input remaining\n"); - goto release_mutex; - } + squashfs_finish_page(output); - total += stream->buf.out_pos; - mutex_unlock(&msblk->read_data_mutex); - return total; + if (xz_err != XZ_STREAM_END || k < b) + goto out; -release_mutex: - mutex_unlock(&msblk->read_data_mutex); + return total + stream->buf.out_pos; +out: for (; k < b; k++) put_bh(bh[k]); @@ -172,6 +184,7 @@ release_mutex: const struct squashfs_decompressor squashfs_xz_comp_ops = { .init = squashfs_xz_init, + .comp_opts = squashfs_xz_comp_opts, .free = squashfs_xz_free, .decompress = squashfs_xz_uncompress, .id = XZ_COMPRESSION, diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index 55d918fd2d8..8727caba688 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -32,8 +32,9 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" -static void *zlib_init(struct squashfs_sb_info *dummy, void *buff, int len) +static void *zlib_init(struct squashfs_sb_info *dummy, void *buff) { z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL); if (stream == NULL) @@ -61,44 +62,37 @@ static void zlib_free(void *strm) } -static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { - int zlib_err, zlib_init = 0; - int k = 0, page = 0; - z_stream *stream = msblk->stream; - - mutex_lock(&msblk->read_data_mutex); + int zlib_err, zlib_init = 0, k = 0; + z_stream *stream = strm; - stream->avail_out = 0; + stream->avail_out = PAGE_CACHE_SIZE; + stream->next_out = squashfs_first_page(output); stream->avail_in = 0; do { if (stream->avail_in == 0 && k < b) { int avail = min(length, msblk->devblksize - offset); length -= avail; - wait_on_buffer(bh[k]); - if (!buffer_uptodate(bh[k])) - goto release_mutex; - stream->next_in = bh[k]->b_data + offset; stream->avail_in = avail; offset = 0; } - if (stream->avail_out == 0 && page < pages) { - stream->next_out = buffer[page++]; - stream->avail_out = PAGE_CACHE_SIZE; + if (stream->avail_out == 0) { + stream->next_out = squashfs_next_page(output); + if (stream->next_out != NULL) + stream->avail_out = PAGE_CACHE_SIZE; } if (!zlib_init) { zlib_err = zlib_inflateInit(stream); if (zlib_err != Z_OK) { - ERROR("zlib_inflateInit returned unexpected " - "result 0x%x, srclength %d\n", - zlib_err, srclength); - goto release_mutex; + squashfs_finish_page(output); + goto out; } zlib_init = 1; } @@ -109,29 +103,21 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer, put_bh(bh[k++]); } while (zlib_err == Z_OK); - if (zlib_err != Z_STREAM_END) { - ERROR("zlib_inflate error, data probably corrupt\n"); - goto release_mutex; - } + squashfs_finish_page(output); - zlib_err = zlib_inflateEnd(stream); - if (zlib_err != Z_OK) { - ERROR("zlib_inflate error, data probably corrupt\n"); - goto release_mutex; - } + if (zlib_err != Z_STREAM_END) + goto out; - if (k < b) { - ERROR("zlib_uncompress error, data remaining\n"); - goto release_mutex; - } + zlib_err = zlib_inflateEnd(stream); + if (zlib_err != Z_OK) + goto out; - length = stream->total_out; - mutex_unlock(&msblk->read_data_mutex); - return length; + if (k < b) + goto out; -release_mutex: - mutex_unlock(&msblk->read_data_mutex); + return stream->total_out; +out: for (; k < b; k++) put_bh(bh[k]); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 79b5da2acbe..b94f9368509 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -609,7 +609,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; struct sysfs_open_file *of; - bool has_read, has_write; + bool has_read, has_write, has_mmap; int error = -EACCES; /* need attr_sd for attr and ops, its parent for kobj */ @@ -621,6 +621,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) has_read = battr->read || battr->mmap; has_write = battr->write || battr->mmap; + has_mmap = battr->mmap; } else { const struct sysfs_ops *ops = sysfs_file_ops(attr_sd); @@ -632,6 +633,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) has_read = ops->show; has_write = ops->store; + has_mmap = false; } /* check perms and supported operations */ @@ -649,7 +651,23 @@ static int sysfs_open_file(struct inode *inode, struct file *file) if (!of) goto err_out; - mutex_init(&of->mutex); + /* + * The following is done to give a different lockdep key to + * @of->mutex for files which implement mmap. This is a rather + * crude way to avoid false positive lockdep warning around + * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and + * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under + * which mm->mmap_sem nests, while holding @of->mutex. As each + * open file has a separate mutex, it's okay as long as those don't + * happen on the same file. At this point, we can't easily give + * each file a separate locking class. Let's differentiate on + * whether the file has mmap or not for now. + */ + if (has_mmap) + mutex_init(&of->mutex); + else + mutex_init(&of->mutex); + of->sd = attr_sd; of->file = file; diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 1c02da8bb7d..3ef11b22e75 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1137,6 +1137,7 @@ xfs_bmap_add_attrfork( int committed; /* xaction was committed */ int logflags; /* logging flags */ int error; /* error return value */ + int cancel_flags = 0; ASSERT(XFS_IFORK_Q(ip) == 0); @@ -1147,19 +1148,20 @@ xfs_bmap_add_attrfork( if (rsvd) tp->t_flags |= XFS_TRANS_RESERVE; error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0); - if (error) - goto error0; + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + cancel_flags = XFS_TRANS_RELEASE_LOG_RES; xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : XFS_QMOPT_RES_REGBLKS); - if (error) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES); - return error; - } + if (error) + goto trans_cancel; + cancel_flags |= XFS_TRANS_ABORT; if (XFS_IFORK_Q(ip)) - goto error1; + goto trans_cancel; if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) { /* * For inodes coming from pre-6.2 filesystems. @@ -1169,7 +1171,7 @@ xfs_bmap_add_attrfork( } ASSERT(ip->i_d.di_anextents == 0); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); switch (ip->i_d.di_format) { @@ -1191,7 +1193,7 @@ xfs_bmap_add_attrfork( default: ASSERT(0); error = XFS_ERROR(EINVAL); - goto error1; + goto trans_cancel; } ASSERT(ip->i_afp == NULL); @@ -1219,7 +1221,7 @@ xfs_bmap_add_attrfork( if (logflags) xfs_trans_log_inode(tp, ip, logflags); if (error) - goto error2; + goto bmap_cancel; if (!xfs_sb_version_hasattr(&mp->m_sb) || (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { __int64_t sbfields = 0; @@ -1242,14 +1244,16 @@ xfs_bmap_add_attrfork( error = xfs_bmap_finish(&tp, &flist, &committed); if (error) - goto error2; - return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); -error2: + goto bmap_cancel; + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; + +bmap_cancel: xfs_bmap_cancel(&flist); -error1: +trans_cancel: + xfs_trans_cancel(tp, cancel_flags); xfs_iunlock(ip, XFS_ILOCK_EXCL); -error0: - xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index da88f167af7..02df7b408a2 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -41,6 +41,7 @@ #include "xfs_fsops.h" #include "xfs_trace.h" #include "xfs_icache.h" +#include "xfs_dinode.h" #ifdef HAVE_PERCPU_SB @@ -718,8 +719,22 @@ xfs_mountfs( * Set the inode cluster size. * This may still be overridden by the file system * block size if it is larger than the chosen cluster size. + * + * For v5 filesystems, scale the cluster size with the inode size to + * keep a constant ratio of inode per cluster buffer, but only if mkfs + * has set the inode alignment value appropriately for larger cluster + * sizes. */ mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE; + if (xfs_sb_version_hascrc(&mp->m_sb)) { + int new_size = mp->m_inode_cluster_size; + + new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; + if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) + mp->m_inode_cluster_size = new_size; + xfs_info(mp, "Using inode cluster size of %d bytes", + mp->m_inode_cluster_size); + } /* * Set inode alignment fields diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 1d8101a10d8..a466c5e5826 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -112,7 +112,7 @@ typedef struct xfs_mount { __uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ __uint8_t m_agno_log; /* log #ag's */ __uint8_t m_agino_log; /* #bits for agino in inum */ - __uint16_t m_inode_cluster_size;/* min inode buf size */ + uint m_inode_cluster_size;/* min inode buf size */ uint m_blockmask; /* sb_blocksize-1 */ uint m_blockwsize; /* sb_blocksize in words */ uint m_blockwmask; /* blockwsize-1 */ diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 1bba7f60d94..50c3f561428 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -111,12 +111,14 @@ xfs_trans_log_inode( /* * First time we log the inode in a transaction, bump the inode change - * counter if it is configured for this to occur. + * counter if it is configured for this to occur. We don't use + * inode_inc_version() because there is no need for extra locking around + * i_version as we already hold the inode locked exclusively for + * metadata modification. */ if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) && IS_I_VERSION(VFS_I(ip))) { - inode_inc_iversion(VFS_I(ip)); - ip->i_d.di_changecount = VFS_I(ip)->i_version; + ip->i_d.di_changecount = ++VFS_I(ip)->i_version; flags |= XFS_ILOG_CORE; } diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c index d53d9f0627a..2fd59c0dae6 100644 --- a/fs/xfs/xfs_trans_resv.c +++ b/fs/xfs/xfs_trans_resv.c @@ -385,8 +385,7 @@ xfs_calc_ifree_reservation( xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) + - MAX((__uint16_t)XFS_FSB_TO_B(mp, 1), - XFS_INODE_CLUSTER_SIZE(mp)) + + max_t(uint, XFS_FSB_TO_B(mp, 1), XFS_INODE_CLUSTER_SIZE(mp)) + xfs_calc_buf_res(1, 0) + xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) + mp->m_in_maxlevels, 0) + |