From a0acae0e886d44bd5ce6d2f173c1ace0fcf0d9f6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 21 Nov 2011 12:32:22 -0800 Subject: freezer: unexport refrigerator() and update try_to_freeze() slightly There is no reason to export two functions for entering the refrigerator. Calling refrigerator() instead of try_to_freeze() doesn't save anything noticeable or removes any race condition. * Rename refrigerator() to __refrigerator() and make it return bool indicating whether it scheduled out for freezing. * Update try_to_freeze() to return bool and relay the return value of __refrigerator() if freezing(). * Convert all refrigerator() users to try_to_freeze(). * Update documentation accordingly. * While at it, add might_sleep() to try_to_freeze(). Signed-off-by: Tejun Heo Cc: Samuel Ortiz Cc: Chris Mason Cc: "Theodore Ts'o" Cc: Steven Whitehouse Cc: Andrew Morton Cc: Jan Kara Cc: KONISHI Ryusuke Cc: Christoph Hellwig --- fs/btrfs/disk-io.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 62afe5c5694e..622654fe051f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1579,9 +1579,7 @@ static int cleaner_kthread(void *arg) btrfs_run_defrag_inodes(root->fs_info); } - if (freezing(current)) { - refrigerator(); - } else { + if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop()) schedule(); @@ -1635,9 +1633,7 @@ sleep: wake_up_process(root->fs_info->cleaner_kthread); mutex_unlock(&root->fs_info->transaction_kthread_mutex); - if (freezing(current)) { - refrigerator(); - } else { + if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && !btrfs_transaction_blocked(root->fs_info)) -- cgit v1.2.3 From 0dc3b84a73267f47a75468f924f5d58a840e3152 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 18 Nov 2011 14:37:27 -0500 Subject: Btrfs: fix num_workers_starting bug and other bugs in async thread Al pointed out we have some random problems with the way we account for num_workers_starting in the async thread stuff. First of all we need to make sure to decrement num_workers_starting if we fail to start the worker, so make __btrfs_start_workers do this. Also fix __btrfs_start_workers so that it doesn't call btrfs_stop_workers(), there is no point in stopping everybody if we failed to create a worker. Also check_pending_worker_creates needs to call __btrfs_start_work in it's work function since it already increments num_workers_starting. People only start one worker at a time, so get rid of the num_workers argument everywhere, and make btrfs_queue_worker a void since it will always succeed. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/async-thread.c | 115 +++++++++++++++++++++++------------------------- fs/btrfs/async-thread.h | 4 +- fs/btrfs/disk-io.c | 34 ++++++++------ fs/btrfs/scrub.c | 8 +++- 4 files changed, 83 insertions(+), 78 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 7ec14097fef1..af8e117c8978 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -64,6 +64,8 @@ struct btrfs_worker_thread { int idle; }; +static int __btrfs_start_workers(struct btrfs_workers *workers); + /* * btrfs_start_workers uses kthread_run, which can block waiting for memory * for a very long time. It will actually throttle on page writeback, @@ -88,27 +90,10 @@ static void start_new_worker_func(struct btrfs_work *work) { struct worker_start *start; start = container_of(work, struct worker_start, work); - btrfs_start_workers(start->queue, 1); + __btrfs_start_workers(start->queue); kfree(start); } -static int start_new_worker(struct btrfs_workers *queue) -{ - struct worker_start *start; - int ret; - - start = kzalloc(sizeof(*start), GFP_NOFS); - if (!start) - return -ENOMEM; - - start->work.func = start_new_worker_func; - start->queue = queue; - ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work); - if (ret) - kfree(start); - return ret; -} - /* * helper function to move a thread onto the idle list after it * has finished some requests. @@ -153,12 +138,20 @@ static void check_busy_worker(struct btrfs_worker_thread *worker) static void check_pending_worker_creates(struct btrfs_worker_thread *worker) { struct btrfs_workers *workers = worker->workers; + struct worker_start *start; unsigned long flags; rmb(); if (!workers->atomic_start_pending) return; + start = kzalloc(sizeof(*start), GFP_NOFS); + if (!start) + return; + + start->work.func = start_new_worker_func; + start->queue = workers; + spin_lock_irqsave(&workers->lock, flags); if (!workers->atomic_start_pending) goto out; @@ -170,10 +163,11 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker) workers->num_workers_starting += 1; spin_unlock_irqrestore(&workers->lock, flags); - start_new_worker(workers); + btrfs_queue_worker(workers->atomic_worker_start, &start->work); return; out: + kfree(start); spin_unlock_irqrestore(&workers->lock, flags); } @@ -462,56 +456,55 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max, * starts new worker threads. This does not enforce the max worker * count in case you need to temporarily go past it. */ -static int __btrfs_start_workers(struct btrfs_workers *workers, - int num_workers) +static int __btrfs_start_workers(struct btrfs_workers *workers) { struct btrfs_worker_thread *worker; int ret = 0; - int i; - for (i = 0; i < num_workers; i++) { - worker = kzalloc(sizeof(*worker), GFP_NOFS); - if (!worker) { - ret = -ENOMEM; - goto fail; - } + worker = kzalloc(sizeof(*worker), GFP_NOFS); + if (!worker) { + ret = -ENOMEM; + goto fail; + } - INIT_LIST_HEAD(&worker->pending); - INIT_LIST_HEAD(&worker->prio_pending); - INIT_LIST_HEAD(&worker->worker_list); - spin_lock_init(&worker->lock); - - atomic_set(&worker->num_pending, 0); - atomic_set(&worker->refs, 1); - worker->workers = workers; - worker->task = kthread_run(worker_loop, worker, - "btrfs-%s-%d", workers->name, - workers->num_workers + i); - if (IS_ERR(worker->task)) { - ret = PTR_ERR(worker->task); - kfree(worker); - goto fail; - } - spin_lock_irq(&workers->lock); - list_add_tail(&worker->worker_list, &workers->idle_list); - worker->idle = 1; - workers->num_workers++; - workers->num_workers_starting--; - WARN_ON(workers->num_workers_starting < 0); - spin_unlock_irq(&workers->lock); + INIT_LIST_HEAD(&worker->pending); + INIT_LIST_HEAD(&worker->prio_pending); + INIT_LIST_HEAD(&worker->worker_list); + spin_lock_init(&worker->lock); + + atomic_set(&worker->num_pending, 0); + atomic_set(&worker->refs, 1); + worker->workers = workers; + worker->task = kthread_run(worker_loop, worker, + "btrfs-%s-%d", workers->name, + workers->num_workers + 1); + if (IS_ERR(worker->task)) { + ret = PTR_ERR(worker->task); + kfree(worker); + goto fail; } + spin_lock_irq(&workers->lock); + list_add_tail(&worker->worker_list, &workers->idle_list); + worker->idle = 1; + workers->num_workers++; + workers->num_workers_starting--; + WARN_ON(workers->num_workers_starting < 0); + spin_unlock_irq(&workers->lock); + return 0; fail: - btrfs_stop_workers(workers); + spin_lock_irq(&workers->lock); + workers->num_workers_starting--; + spin_unlock_irq(&workers->lock); return ret; } -int btrfs_start_workers(struct btrfs_workers *workers, int num_workers) +int btrfs_start_workers(struct btrfs_workers *workers) { spin_lock_irq(&workers->lock); - workers->num_workers_starting += num_workers; + workers->num_workers_starting++; spin_unlock_irq(&workers->lock); - return __btrfs_start_workers(workers, num_workers); + return __btrfs_start_workers(workers); } /* @@ -568,6 +561,7 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers) struct btrfs_worker_thread *worker; unsigned long flags; struct list_head *fallback; + int ret; again: spin_lock_irqsave(&workers->lock, flags); @@ -584,7 +578,9 @@ again: workers->num_workers_starting++; spin_unlock_irqrestore(&workers->lock, flags); /* we're below the limit, start another worker */ - __btrfs_start_workers(workers, 1); + ret = __btrfs_start_workers(workers); + if (ret) + goto fallback; goto again; } } @@ -665,7 +661,7 @@ void btrfs_set_work_high_prio(struct btrfs_work *work) /* * places a struct btrfs_work into the pending queue of one of the kthreads */ -int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work) +void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work) { struct btrfs_worker_thread *worker; unsigned long flags; @@ -673,7 +669,7 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work) /* don't requeue something already on a list */ if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags)) - goto out; + return; worker = find_worker(workers); if (workers->ordered) { @@ -712,7 +708,4 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work) if (wake) wake_up_process(worker->task); spin_unlock_irqrestore(&worker->lock, flags); - -out: - return 0; } diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 5077746cf85e..f34cc31fa3c9 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -109,8 +109,8 @@ struct btrfs_workers { char *name; }; -int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work); -int btrfs_start_workers(struct btrfs_workers *workers, int num_workers); +void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work); +int btrfs_start_workers(struct btrfs_workers *workers); int btrfs_stop_workers(struct btrfs_workers *workers); void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max, struct btrfs_workers *async_starter); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 94abc25392f6..3f9d5551e582 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2194,19 +2194,27 @@ struct btrfs_root *open_ctree(struct super_block *sb, fs_info->endio_meta_write_workers.idle_thresh = 2; fs_info->readahead_workers.idle_thresh = 2; - btrfs_start_workers(&fs_info->workers, 1); - btrfs_start_workers(&fs_info->generic_worker, 1); - btrfs_start_workers(&fs_info->submit_workers, 1); - btrfs_start_workers(&fs_info->delalloc_workers, 1); - btrfs_start_workers(&fs_info->fixup_workers, 1); - btrfs_start_workers(&fs_info->endio_workers, 1); - btrfs_start_workers(&fs_info->endio_meta_workers, 1); - btrfs_start_workers(&fs_info->endio_meta_write_workers, 1); - btrfs_start_workers(&fs_info->endio_write_workers, 1); - btrfs_start_workers(&fs_info->endio_freespace_worker, 1); - btrfs_start_workers(&fs_info->delayed_workers, 1); - btrfs_start_workers(&fs_info->caching_workers, 1); - btrfs_start_workers(&fs_info->readahead_workers, 1); + /* + * btrfs_start_workers can really only fail because of ENOMEM so just + * return -ENOMEM if any of these fail. + */ + ret = btrfs_start_workers(&fs_info->workers); + ret |= btrfs_start_workers(&fs_info->generic_worker); + ret |= btrfs_start_workers(&fs_info->submit_workers); + ret |= btrfs_start_workers(&fs_info->delalloc_workers); + ret |= btrfs_start_workers(&fs_info->fixup_workers); + ret |= btrfs_start_workers(&fs_info->endio_workers); + ret |= btrfs_start_workers(&fs_info->endio_meta_workers); + ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers); + ret |= btrfs_start_workers(&fs_info->endio_write_workers); + ret |= btrfs_start_workers(&fs_info->endio_freespace_worker); + ret |= btrfs_start_workers(&fs_info->delayed_workers); + ret |= btrfs_start_workers(&fs_info->caching_workers); + ret |= btrfs_start_workers(&fs_info->readahead_workers); + if (ret) { + ret = -ENOMEM; + goto fail_sb_buffer; + } fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index c27bcb67f330..ddf2c90d3fc0 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1535,18 +1535,22 @@ static noinline_for_stack int scrub_supers(struct scrub_dev *sdev) static noinline_for_stack int scrub_workers_get(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; + int ret = 0; mutex_lock(&fs_info->scrub_lock); if (fs_info->scrub_workers_refcnt == 0) { btrfs_init_workers(&fs_info->scrub_workers, "scrub", fs_info->thread_pool_size, &fs_info->generic_worker); fs_info->scrub_workers.idle_thresh = 4; - btrfs_start_workers(&fs_info->scrub_workers, 1); + ret = btrfs_start_workers(&fs_info->scrub_workers); + if (ret) + goto out; } ++fs_info->scrub_workers_refcnt; +out: mutex_unlock(&fs_info->scrub_lock); - return 0; + return ret; } static noinline_for_stack void scrub_workers_put(struct btrfs_root *root) -- cgit v1.2.3 From 21adbd5cbb5344a3fca6bb7ddb2ab6cb03c44546 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Wed, 9 Nov 2011 13:44:05 +0100 Subject: Btrfs: integrate integrity check module into btrfs This is the last part of the patch series. It modifies the btrfs code to use the integrity check module if configured to do so with the define BTRFS_FS_CHECK_INTEGRITY. If this define is not set, the only effective change is that code is added that handles the mount option to activate the integrity check. If the mount option is set and the define BTRFS_FS_CHECK_INTEGRITY is not set, that code complains in the log and the mount fails with EINVAL. Add the mount option to activate the usage of the integrity check code. Add invocation of btrfs integrity check code init and cleanup function on mount and umount, respectively. Add hook to call btrfs integrity check code version of submit_bh/submit_bio. Signed-off-by: Stefan Behrens --- fs/btrfs/ctree.h | 8 +++++++- fs/btrfs/disk-io.c | 26 ++++++++++++++++++++++++-- fs/btrfs/extent_io.c | 5 +++-- fs/btrfs/scrub.c | 5 +++-- fs/btrfs/super.c | 39 ++++++++++++++++++++++++++++++++++++++- fs/btrfs/volumes.c | 7 ++++--- 6 files changed, 79 insertions(+), 11 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67385033323d..39f6188688e6 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -971,7 +971,7 @@ struct btrfs_fs_info { * is required instead of the faster short fsync log commits */ u64 last_trans_log_full_commit; - unsigned long mount_opt:20; + unsigned long mount_opt:21; unsigned long compress_type:4; u64 max_inline; u64 alloc_start; @@ -1155,6 +1155,10 @@ struct btrfs_fs_info { int scrub_workers_refcnt; struct btrfs_workers scrub_workers; +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + u32 check_integrity_print_mask; +#endif + /* filesystem state */ u64 fs_state; @@ -1413,6 +1417,8 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16) #define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17) #define BTRFS_MOUNT_RECOVERY (1 << 18) +#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 19) +#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 20) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3f9d5551e582..f363c6d9c3de 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -43,6 +43,7 @@ #include "tree-log.h" #include "free-space-cache.h" #include "inode-map.h" +#include "check-integrity.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@ -2001,6 +2002,9 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->scrub_pause_wait); init_rwsem(&fs_info->scrub_super_lock); fs_info->scrub_workers_refcnt = 0; +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + fs_info->check_integrity_print_mask = 0; +#endif sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); @@ -2356,6 +2360,19 @@ retry_root_backup: btrfs_set_opt(fs_info->mount_opt, SSD); } +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) { + ret = btrfsic_mount(tree_root, fs_devices, + btrfs_test_opt(tree_root, + CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ? + 1 : 0, + fs_info->check_integrity_print_mask); + if (ret) + printk(KERN_WARNING "btrfs: failed to initialize" + " integrity check module %s\n", sb->s_id); + } +#endif + /* do not make disk changes in broken FS */ if (btrfs_super_log_root(disk_super) != 0 && !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) { @@ -2634,7 +2651,7 @@ static int write_dev_supers(struct btrfs_device *device, * we fua the first super. The others we allow * to go down lazy. */ - ret = submit_bh(WRITE_FUA, bh); + ret = btrfsic_submit_bh(WRITE_FUA, bh); if (ret) errors++; } @@ -2711,7 +2728,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) device->flush_bio = bio; bio_get(bio); - submit_bio(WRITE_FLUSH, bio); + btrfsic_submit_bio(WRITE_FLUSH, bio); return 0; } @@ -3057,6 +3074,11 @@ int close_ctree(struct btrfs_root *root) btrfs_stop_workers(&fs_info->caching_workers); btrfs_stop_workers(&fs_info->readahead_workers); +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(root, CHECK_INTEGRITY)) + btrfsic_unmount(root, fs_info->fs_devices); +#endif + btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 49f3c9dc09f4..246669296e02 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -18,6 +18,7 @@ #include "ctree.h" #include "btrfs_inode.h" #include "volumes.h" +#include "check-integrity.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -1895,7 +1896,7 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start, } bio->bi_bdev = dev->bdev; bio_add_page(bio, page, length, start-page_offset(page)); - submit_bio(WRITE_SYNC, bio); + btrfsic_submit_bio(WRITE_SYNC, bio); wait_for_completion(&compl); if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { @@ -2393,7 +2394,7 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num, ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio, mirror_num, bio_flags, start); else - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ddf2c90d3fc0..567e148caca2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -25,6 +25,7 @@ #include "transaction.h" #include "backref.h" #include "extent_io.h" +#include "check-integrity.h" /* * This is only the first step towards a full-features scrub. It reads all @@ -732,7 +733,7 @@ static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector, bio_add_page(bio, page, PAGE_SIZE, 0); bio->bi_end_io = scrub_fixup_end_io; bio->bi_private = &complete; - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); /* this will also unplug the queue */ wait_for_completion(&complete); @@ -958,7 +959,7 @@ static int scrub_submit(struct scrub_dev *sdev) sdev->curr = -1; atomic_inc(&sdev->in_flight); - submit_bio(READ, sbio->bio); + btrfsic_submit_bio(READ, sbio->bio); return 0; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 34a8b6112ea4..22a2015f1d7b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -165,7 +165,10 @@ enum { Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, - Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_err, + Opt_inode_cache, Opt_no_space_cache, Opt_recovery, + Opt_check_integrity, Opt_check_integrity_including_extent_data, + Opt_check_integrity_print_mask, + Opt_err, }; static match_table_t tokens = { @@ -200,6 +203,9 @@ static match_table_t tokens = { {Opt_inode_cache, "inode_cache"}, {Opt_no_space_cache, "nospace_cache"}, {Opt_recovery, "recovery"}, + {Opt_check_integrity, "check_int"}, + {Opt_check_integrity_including_extent_data, "check_int_data"}, + {Opt_check_integrity_print_mask, "check_int_print_mask=%d"}, {Opt_err, NULL}, }; @@ -398,6 +404,37 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) printk(KERN_INFO "btrfs: enabling auto recovery"); btrfs_set_opt(info->mount_opt, RECOVERY); break; +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + case Opt_check_integrity_including_extent_data: + printk(KERN_INFO "btrfs: enabling check integrity" + " including extent data\n"); + btrfs_set_opt(info->mount_opt, + CHECK_INTEGRITY_INCLUDING_EXTENT_DATA); + btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); + break; + case Opt_check_integrity: + printk(KERN_INFO "btrfs: enabling check integrity\n"); + btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); + break; + case Opt_check_integrity_print_mask: + intarg = 0; + match_int(&args[0], &intarg); + if (intarg) { + info->check_integrity_print_mask = intarg; + printk(KERN_INFO "btrfs:" + " check_integrity_print_mask 0x%x\n", + info->check_integrity_print_mask); + } + break; +#else + case Opt_check_integrity_including_extent_data: + case Opt_check_integrity: + case Opt_check_integrity_print_mask: + printk(KERN_ERR "btrfs: support for check_integrity*" + " not compiled in!\n"); + ret = -EINVAL; + goto out; +#endif case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f4b839fd3c9d..821334f6e3a1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -32,6 +32,7 @@ #include "print-tree.h" #include "volumes.h" #include "async-thread.h" +#include "check-integrity.h" static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -246,7 +247,7 @@ loop_lock: sync_pending = 0; } - submit_bio(cur->bi_rw, cur); + btrfsic_submit_bio(cur->bi_rw, cur); num_run++; batch_run++; if (need_resched()) @@ -3304,7 +3305,7 @@ static noinline int schedule_bio(struct btrfs_root *root, /* don't bother with additional async steps for reads, right now */ if (!(rw & REQ_WRITE)) { bio_get(bio); - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); bio_put(bio); return 0; } @@ -3399,7 +3400,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, if (async_submit) schedule_bio(root, dev, rw, bio); else - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); } else { bio->bi_bdev = root->fs_info->fs_devices->latest_bdev; bio->bi_sector = logical >> 9; -- cgit v1.2.3 From 66d7e7f09f77456fe68683247d77721032a00ee5 Mon Sep 17 00:00:00 2001 From: Arne Jansen Date: Mon, 12 Sep 2011 15:26:38 +0200 Subject: Btrfs: mark delayed refs as for cow Add a for_cow parameter to add_delayed_*_ref and pass the appropriate value from every call site. The for_cow parameter will later on be used to determine if a ref will change anything with respect to qgroups. Delayed refs coming from relocation are always counted as for_cow, as they don't change subvol quota. Also pass in the fs_info for later use. btrfs_find_all_roots() will use this as an optimization, as changes that are for_cow will not change anything with respect to which root points to a certain leaf. Thus, we don't need to add the current sequence number to those delayed refs. Signed-off-by: Arne Jansen Signed-off-by: Jan Schmidt --- fs/btrfs/ctree.c | 42 ++++++++++---------- fs/btrfs/ctree.h | 17 +++++---- fs/btrfs/delayed-ref.c | 50 ++++++++++++++---------- fs/btrfs/delayed-ref.h | 15 +++++--- fs/btrfs/disk-io.c | 3 +- fs/btrfs/extent-tree.c | 101 +++++++++++++++++++++++++++++-------------------- fs/btrfs/file.c | 10 ++--- fs/btrfs/inode.c | 2 +- fs/btrfs/ioctl.c | 5 ++- fs/btrfs/relocation.c | 18 +++++---- fs/btrfs/transaction.c | 4 +- fs/btrfs/tree-log.c | 2 +- 12 files changed, 155 insertions(+), 114 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index dede441bdeee..0639a555e16e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -240,7 +240,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, 0, new_root_objectid, &disk_key, level, - buf->start, 0); + buf->start, 0, 1); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -261,9 +261,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, WARN_ON(btrfs_header_generation(buf) > trans->transid); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); if (ret) return ret; @@ -350,14 +350,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if ((owner == root->root_key.objectid || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { - ret = btrfs_inc_ref(trans, root, buf, 1); + ret = btrfs_inc_ref(trans, root, buf, 1, 1); BUG_ON(ret); if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { - ret = btrfs_dec_ref(trans, root, buf, 0); + ret = btrfs_dec_ref(trans, root, buf, 0, 1); BUG_ON(ret); - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); BUG_ON(ret); } new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; @@ -365,9 +365,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); BUG_ON(ret); } if (new_flags != 0) { @@ -381,11 +381,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) { if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); BUG_ON(ret); - ret = btrfs_dec_ref(trans, root, buf, 1); + ret = btrfs_dec_ref(trans, root, buf, 1, 1); BUG_ON(ret); } clean_tree_block(trans, root, buf); @@ -446,7 +446,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start, root->root_key.objectid, &disk_key, - level, search_start, empty_size); + level, search_start, empty_size, 1); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -484,7 +484,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, rcu_assign_pointer(root->node, cow); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + last_ref, 1); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -500,7 +500,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, trans->transid); btrfs_mark_buffer_dirty(parent); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + last_ref, 1); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -957,7 +957,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, root, mid, 0, 1, 0); /* once for the root ptr */ free_extent_buffer(mid); return 0; @@ -1015,7 +1015,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret) ret = wret; root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1); + btrfs_free_tree_block(trans, root, right, 0, 1, 0); free_extent_buffer(right); right = NULL; } else { @@ -1055,7 +1055,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret) ret = wret; root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, root, mid, 0, 1, 0); free_extent_buffer(mid); mid = NULL; } else { @@ -2089,7 +2089,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, c = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, &lower_key, - level, root->node->start, 0); + level, root->node->start, 0, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -2216,7 +2216,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, split = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + &disk_key, level, c->start, 0, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -2970,7 +2970,7 @@ again: right = btrfs_alloc_free_block(trans, root, root->leafsize, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + &disk_key, 0, l->start, 0, 0); if (IS_ERR(right)) return PTR_ERR(right); @@ -3781,7 +3781,7 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, root, leaf, 0, 1, 0); return 0; } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3e4a07b79817..543f60bddb39 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2277,11 +2277,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size); + u64 hint, u64 empty_size, int for_cow); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref); + u64 parent, int last_ref, int for_cow); struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u32 blocksize, @@ -2301,17 +2301,17 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans, u64 search_end, struct btrfs_key *ins, u64 data); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, int is_data); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, + u64 owner, u64 offset, int for_cow); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len); int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, @@ -2323,7 +2323,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 root_objectid, u64 owner, u64 offset, int for_cow); int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@ -2492,7 +2492,8 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); void btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref); + struct btrfs_block_rsv *block_rsv, int update_ref, + int for_reloc); int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 125cf76fcd08..3a0f0ab804f4 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -390,7 +390,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing, * this does all the dirty work in terms of maintaining the correct * overall modification count. */ -static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans, +static noinline int add_delayed_ref_head(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, int action, int is_data) @@ -468,10 +469,12 @@ static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans, /* * helper to insert a delayed tree ref into the rbtree. */ -static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans, +static noinline int add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, - u64 ref_root, int level, int action) + u64 ref_root, int level, int action, + int for_cow) { struct btrfs_delayed_ref_node *existing; struct btrfs_delayed_tree_ref *full_ref; @@ -522,11 +525,12 @@ static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans, /* * helper to insert a delayed data ref into the rbtree. */ -static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, +static noinline int add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, - int action) + int action, int for_cow) { struct btrfs_delayed_ref_node *existing; struct btrfs_delayed_data_ref *full_ref; @@ -554,6 +558,7 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, full_ref->root = ref_root; ref->type = BTRFS_EXTENT_DATA_REF_KEY; } + full_ref->objectid = owner; full_ref->offset = offset; @@ -580,10 +585,12 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, * to make sure the delayed ref is eventually processed before this * transaction commits. */ -int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int for_cow) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -610,12 +617,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * insert both the head node and the new ref without dropping * the spin lock */ - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes, - action, 0); + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, + num_bytes, action, 0); BUG_ON(ret); - ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes, - parent, ref_root, level, action); + ret = add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr, + num_bytes, parent, ref_root, level, action, + for_cow); BUG_ON(ret); spin_unlock(&delayed_refs->lock); return 0; @@ -624,11 +632,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, /* * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref. */ -int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int for_cow) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -655,18 +665,20 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, * insert both the head node and the new ref without dropping * the spin lock */ - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes, - action, 1); + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, + num_bytes, action, 1); BUG_ON(ret); - ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes, - parent, ref_root, owner, offset, action); + ret = add_delayed_data_ref(fs_info, trans, &ref->node, bytenr, + num_bytes, parent, ref_root, owner, offset, + action, for_cow); BUG_ON(ret); spin_unlock(&delayed_refs->lock); return 0; } -int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op) { @@ -683,7 +695,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, num_bytes, BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data); BUG_ON(ret); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index e287e3b0eab0..8316bff18d30 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -151,16 +151,21 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) } } -int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_extent_op *extent_op, + int for_cow); +int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, + struct btrfs_delayed_extent_op *extent_op, + int for_cow); +int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 94abc25392f6..6f8cd17c9a9f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1243,7 +1243,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->ref_cows = 0; leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, - BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0); + BTRFS_TREE_LOG_OBJECTID, NULL, + 0, 0, 0, 0); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 813c6bb96c9a..dc8b9a834596 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1872,20 +1872,24 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset) + u64 root_objectid, u64 owner, u64 offset, int for_cow) { int ret; + struct btrfs_fs_info *fs_info = root->fs_info; + BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID && root_objectid == BTRFS_TREE_LOG_OBJECTID); if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL); + BTRFS_ADD_DELAYED_REF, NULL, for_cow); } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_REF, NULL); + BTRFS_ADD_DELAYED_REF, NULL, for_cow); } return ret; } @@ -2405,7 +2409,8 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, extent_op->update_key = 0; extent_op->is_data = is_data ? 1 : 0; - ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op); + ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr, + num_bytes, extent_op); if (ret) kfree(extent_op); return ret; @@ -2590,7 +2595,7 @@ out: static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - int full_backref, int inc) + int full_backref, int inc, int for_cow) { u64 bytenr; u64 num_bytes; @@ -2603,7 +2608,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, int level; int ret = 0; int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *, - u64, u64, u64, u64, u64, u64); + u64, u64, u64, u64, u64, u64, int); ref_root = btrfs_header_owner(buf); nritems = btrfs_header_nritems(buf); @@ -2640,14 +2645,15 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, key.offset -= btrfs_file_extent_offset(buf, fi); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, key.objectid, - key.offset); + key.offset, for_cow); if (ret) goto fail; } else { bytenr = btrfs_node_blockptr(buf, i); num_bytes = btrfs_level_size(root, level - 1); ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, level - 1, 0); + parent, ref_root, level - 1, 0, + for_cow); if (ret) goto fail; } @@ -2659,15 +2665,15 @@ fail: } int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref) + struct extent_buffer *buf, int full_backref, int for_cow) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 1); + return __btrfs_mod_ref(trans, root, buf, full_backref, 1, for_cow); } int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref) + struct extent_buffer *buf, int full_backref, int for_cow) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 0); + return __btrfs_mod_ref(trans, root, buf, full_backref, 0, for_cow); } static int write_one_cache_group(struct btrfs_trans_handle *trans, @@ -4937,16 +4943,17 @@ out: void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref) + u64 parent, int last_ref, int for_cow) { struct btrfs_block_group_cache *cache = NULL; int ret; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, buf->start, buf->len, - parent, root->root_key.objectid, - btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL); + ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, + buf->start, buf->len, + parent, root->root_key.objectid, + btrfs_header_level(buf), + BTRFS_DROP_DELAYED_REF, NULL, for_cow); BUG_ON(ret); } @@ -4981,12 +4988,12 @@ out: btrfs_put_block_group(cache); } -int btrfs_free_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset) +int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, + u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, + u64 owner, u64 offset, int for_cow) { int ret; + struct btrfs_fs_info *fs_info = root->fs_info; /* * tree log blocks never actually go into the extent allocation @@ -4998,14 +5005,17 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_pin_extent(root, bytenr, num_bytes, 1); ret = 0; } else if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL); + BTRFS_DROP_DELAYED_REF, NULL, for_cow); BUG_ON(ret); } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes, - parent, root_objectid, owner, - offset, BTRFS_DROP_DELAYED_REF, NULL); + ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, + num_bytes, + parent, root_objectid, owner, + offset, BTRFS_DROP_DELAYED_REF, + NULL, for_cow); BUG_ON(ret); } return ret; @@ -5826,9 +5836,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID); - ret = btrfs_add_delayed_data_ref(trans, ins->objectid, ins->offset, - 0, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_EXTENT, NULL); + ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid, + ins->offset, 0, + root_objectid, owner, offset, + BTRFS_ADD_DELAYED_EXTENT, NULL, 0); return ret; } @@ -5998,7 +6009,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size) + u64 hint, u64 empty_size, int for_cow) { struct btrfs_key ins; struct btrfs_block_rsv *block_rsv; @@ -6042,10 +6053,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, extent_op->update_flags = 1; extent_op->is_data = 0; - ret = btrfs_add_delayed_tree_ref(trans, ins.objectid, + ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, + ins.objectid, ins.offset, parent, root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op); + extent_op, for_cow); BUG_ON(ret); } return buf; @@ -6062,6 +6074,7 @@ struct walk_control { int keep_locks; int reada_slot; int reada_count; + int for_reloc; }; #define DROP_REFERENCE 1 @@ -6200,9 +6213,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, /* wc->stage == UPDATE_BACKREF */ if (!(wc->flags[level] & flag)) { BUG_ON(!path->locks[level]); - ret = btrfs_inc_ref(trans, root, eb, 1); + ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc); BUG_ON(ret); - ret = btrfs_dec_ref(trans, root, eb, 0); + ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc); BUG_ON(ret); ret = btrfs_set_disk_extent_flags(trans, root, eb->start, eb->len, flag, 0); @@ -6346,7 +6359,7 @@ skip: } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, - root->root_key.objectid, level - 1, 0); + root->root_key.objectid, level - 1, 0, 0); BUG_ON(ret); } btrfs_tree_unlock(next); @@ -6420,9 +6433,11 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (wc->refs[level] == 1) { if (level == 0) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) - ret = btrfs_dec_ref(trans, root, eb, 1); + ret = btrfs_dec_ref(trans, root, eb, 1, + wc->for_reloc); else - ret = btrfs_dec_ref(trans, root, eb, 0); + ret = btrfs_dec_ref(trans, root, eb, 0, + wc->for_reloc); BUG_ON(ret); } /* make block locked assertion in clean_tree_block happy */ @@ -6449,7 +6464,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, btrfs_header_owner(path->nodes[level + 1])); } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); + btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1, 0); out: wc->refs[level] = 0; wc->flags[level] = 0; @@ -6533,7 +6548,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, * blocks are properly updated. */ void btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref) + struct btrfs_block_rsv *block_rsv, int update_ref, + int for_reloc) { struct btrfs_path *path; struct btrfs_trans_handle *trans; @@ -6621,6 +6637,7 @@ void btrfs_drop_snapshot(struct btrfs_root *root, wc->stage = DROP_REFERENCE; wc->update_ref = update_ref; wc->keep_locks = 0; + wc->for_reloc = for_reloc; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { @@ -6705,6 +6722,7 @@ out: * drop subtree rooted at tree block 'node'. * * NOTE: this function will unlock and release tree block 'node' + * only used by relocation code */ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -6749,6 +6767,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, wc->stage = DROP_REFERENCE; wc->update_ref = 0; wc->keep_locks = 1; + wc->for_reloc = 1; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f2e928289600..d2b60ed6c33f 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -678,7 +678,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, new_key.objectid, - start - extent_offset); + start - extent_offset, 0); BUG_ON(ret); *hint_byte = disk_bytenr; } @@ -753,7 +753,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, key.objectid, key.offset - - extent_offset); + extent_offset, 0); BUG_ON(ret); inode_sub_bytes(inode, extent_end - key.offset); @@ -962,7 +962,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); if (split == start) { @@ -989,7 +989,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); } other_start = 0; @@ -1006,7 +1006,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); } if (del_nr == 0) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c5ccec23984c..ea819386b864 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3139,7 +3139,7 @@ delete: ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, btrfs_header_owner(leaf), - ino, extent_offset); + ino, extent_offset, 0); BUG_ON(ret); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72d461656f60..c48f2e931ea0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -358,7 +358,7 @@ static noinline int create_subvol(struct btrfs_root *root, return PTR_ERR(trans); leaf = btrfs_alloc_free_block(trans, root, root->leafsize, - 0, objectid, NULL, 0, 0, 0); + 0, objectid, NULL, 0, 0, 0, 0); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); goto fail; @@ -2425,7 +2425,8 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, disko, diskl, 0, root->root_key.objectid, btrfs_ino(inode), - new_key.offset - datao); + new_key.offset - datao, + 0); BUG_ON(ret); } } else if (type == BTRFS_FILE_EXTENT_INLINE) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index dff29d5e151a..8c1aae2c845d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1604,12 +1604,12 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, new_bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset); + key.objectid, key.offset, 1); BUG_ON(ret); ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset); + key.objectid, key.offset, 1); BUG_ON(ret); } if (dirty) @@ -1778,21 +1778,23 @@ again: ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + src->root_key.objectid, level - 1, 0, + 1); BUG_ON(ret); ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0); + 0, 1); BUG_ON(ret); ret = btrfs_free_extent(trans, src, new_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + src->root_key.objectid, level - 1, 0, + 1); BUG_ON(ret); ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0); + 0, 1); BUG_ON(ret); btrfs_unlock_up_safe(path, 0); @@ -2244,7 +2246,7 @@ again: } else { list_del_init(&reloc_root->root_list); } - btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0); + btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1); } if (found) { @@ -2558,7 +2560,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, node->eb->start, blocksize, upper->eb->start, btrfs_header_owner(upper->eb), - node->level, 0); + node->level, 0, 1); BUG_ON(ret); ret = btrfs_drop_subtree(trans, root, eb, upper->eb); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 81376d94cd3c..a2bfedcbcabc 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1393,9 +1393,9 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root) if (btrfs_header_backref_rev(root->node) < BTRFS_MIXED_BACKREF_REV) - btrfs_drop_snapshot(root, NULL, 0); + btrfs_drop_snapshot(root, NULL, 0, 0); else - btrfs_drop_snapshot(root, NULL, 1); + btrfs_drop_snapshot(root, NULL, 1, 0); } return 0; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f4d81c06d48f..fce7b9ec3bfa 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -589,7 +589,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, ins.objectid, ins.offset, 0, root->root_key.objectid, - key->objectid, offset); + key->objectid, offset, 0); BUG_ON(ret); } else { /* -- cgit v1.2.3 From 98c7089c769048f941bd5c5285287f8fc301f8b1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 01:00:31 -0500 Subject: btrfs: preparation to fixing mount/umount race We need fs_info and root to live until the moment when the victim superblock leaves the list, so we need to postpone free_fs_info() until after ->put_super(). The call is buried in close_ctree(), though, so we need to lift it into the callers (including btrfs_put_super()) first. Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 3 +-- fs/btrfs/super.c | 6 +++++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f99a099a7747..dcb5d949b543 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2424,6 +2424,7 @@ retry_root_backup: up_read(&fs_info->cleanup_work_sem); if (err) { close_ctree(tree_root); + free_fs_info(fs_info); return ERR_PTR(err); } } @@ -3059,8 +3060,6 @@ int close_ctree(struct btrfs_root *root) bdi_destroy(&fs_info->bdi); cleanup_srcu_struct(&fs_info->subvol_srcu); - free_fs_info(fs_info); - return 0; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index ae488aa1966a..a3f435e58987 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -151,6 +151,7 @@ static void btrfs_put_super(struct super_block *sb) int ret; ret = close_ctree(root); + free_fs_info(root->fs_info); sb->s_fs_info = NULL; (void)ret; /* FIXME: need to fix VFS to return error? */ @@ -589,6 +590,7 @@ static int btrfs_fill_super(struct super_block *sb, struct inode *inode; struct dentry *root_dentry; struct btrfs_root *tree_root; + struct btrfs_fs_info *fs_info; struct btrfs_key key; int err; @@ -609,12 +611,13 @@ static int btrfs_fill_super(struct super_block *sb, printk("btrfs: open_ctree failed\n"); return PTR_ERR(tree_root); } + fs_info = tree_root->fs_info; sb->s_fs_info = tree_root; key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root, NULL); + inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto fail_close; @@ -635,6 +638,7 @@ static int btrfs_fill_super(struct super_block *sb, fail_close: close_ctree(tree_root); + free_fs_info(fs_info); return err; } -- cgit v1.2.3 From 2eb34cd368b3e5cef960ae9d9971a037cd6fa9d3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 00:32:06 -0500 Subject: btrfs: sanitizing ->fs_info, part 1 take assignment of ->fs_info to callers of __setup_root() Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dcb5d949b543..04eba10af825 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1142,7 +1142,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->orphan_item_inserted = 0; root->orphan_cleanup_state = 0; - root->fs_info = fs_info; root->objectid = objectid; root->last_trans = 0; root->highest_objectid = 0; @@ -1193,6 +1192,7 @@ static int find_and_setup_root(struct btrfs_root *tree_root, u32 blocksize; u64 generation; + root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, objectid); @@ -1227,6 +1227,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, if (!root) return ERR_PTR(-ENOMEM); + root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, BTRFS_TREE_LOG_OBJECTID); @@ -1330,6 +1331,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, goto out; } + root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, location->objectid); @@ -2055,6 +2057,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); + tree_root->fs_info = fs_info; __setup_root(4096, 4096, 4096, 4096, tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); @@ -2247,6 +2250,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_super_chunk_root_level(disk_super)); generation = btrfs_super_chunk_root_generation(disk_super); + chunk_root->fs_info = fs_info; __setup_root(nodesize, leafsize, sectorsize, stripesize, chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID); @@ -2373,6 +2377,7 @@ retry_root_backup: goto fail_trans_kthread; } + log_tree_root->fs_info = fs_info; __setup_root(nodesize, leafsize, sectorsize, stripesize, log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID); -- cgit v1.2.3 From 1233f546ec29ac32424327baf6ae5df81e3d9eae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 00:34:00 -0500 Subject: btrfs: sanitizing ->fs_info, part 2 lift assignment to callers of find_and_setup_root() Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 04eba10af825..b8dae517f80c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1192,7 +1192,6 @@ static int find_and_setup_root(struct btrfs_root *tree_root, u32 blocksize; u64 generation; - root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, objectid); @@ -1322,6 +1321,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, if (!root) return ERR_PTR(-ENOMEM); if (location->offset == (u64)-1) { + root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, location->objectid, root); if (ret) { @@ -2300,18 +2300,21 @@ retry_root_backup: btrfs_set_root_node(&tree_root->root_item, tree_root->node); tree_root->commit_root = btrfs_root_node(tree_root); + extent_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_EXTENT_TREE_OBJECTID, extent_root); if (ret) goto recovery_tree_root; extent_root->track_dirty = 1; + dev_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_DEV_TREE_OBJECTID, dev_root); if (ret) goto recovery_tree_root; dev_root->track_dirty = 1; + csum_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) -- cgit v1.2.3 From 38a77db49ad8f78369dcdfb693b8e5a818a60104 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 00:38:54 -0500 Subject: btrfs: sanitizing ->fs_info, part 3 move assignments to ->fs_info in open_ctree() up, to the place just after the original allocations. Assignment for tree_root becomes a no-op - we'd obtained fs_info from tree_root->fs_info in the first place. Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b8dae517f80c..06480fcf0fb3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1320,8 +1320,8 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, root = kzalloc(sizeof(*root), GFP_NOFS); if (!root) return ERR_PTR(-ENOMEM); + root->fs_info = fs_info; if (location->offset == (u64)-1) { - root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, location->objectid, root); if (ret) { @@ -1331,7 +1331,6 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, goto out; } - root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, location->objectid); @@ -1914,6 +1913,10 @@ struct btrfs_root *open_ctree(struct super_block *sb, err = -ENOMEM; goto fail; } + chunk_root->fs_info = fs_info; + extent_root->fs_info = fs_info; + dev_root->fs_info = fs_info; + csum_root->fs_info = fs_info; ret = init_srcu_struct(&fs_info->subvol_srcu); if (ret) { @@ -2057,7 +2060,6 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); - tree_root->fs_info = fs_info; __setup_root(4096, 4096, 4096, 4096, tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); @@ -2250,7 +2252,6 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_super_chunk_root_level(disk_super)); generation = btrfs_super_chunk_root_generation(disk_super); - chunk_root->fs_info = fs_info; __setup_root(nodesize, leafsize, sectorsize, stripesize, chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID); @@ -2300,21 +2301,18 @@ retry_root_backup: btrfs_set_root_node(&tree_root->root_item, tree_root->node); tree_root->commit_root = btrfs_root_node(tree_root); - extent_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_EXTENT_TREE_OBJECTID, extent_root); if (ret) goto recovery_tree_root; extent_root->track_dirty = 1; - dev_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_DEV_TREE_OBJECTID, dev_root); if (ret) goto recovery_tree_root; dev_root->track_dirty = 1; - csum_root->fs_info = fs_info; ret = find_and_setup_root(tree_root, fs_info, BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) -- cgit v1.2.3 From 6f07e42ee6fcc252a210781d7262f4051e9fd8f6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 00:46:16 -0500 Subject: btrfs: sanitizing ->fs_info, part 4 A new helper: btrfs_alloc_root(fs_info); allocates btrfs_root and sets ->fs_info. All places allocating the suckers converted to it. At that point we *never* reassign ->fs_info of btrfs_root; it's set before anyone sees the address of newly allocated struct btrfs_root and never assigned anywhere else. Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 33 +++++++++++++++------------------ fs/btrfs/disk-io.h | 2 ++ fs/btrfs/super.c | 3 +-- 3 files changed, 18 insertions(+), 20 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 06480fcf0fb3..ee846ce58846 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1215,6 +1215,14 @@ static int find_and_setup_root(struct btrfs_root *tree_root, return 0; } +struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS); + if (root) + root->fs_info = fs_info; + return root; +} + static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { @@ -1222,11 +1230,10 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *tree_root = fs_info->tree_root; struct extent_buffer *leaf; - root = kzalloc(sizeof(*root), GFP_NOFS); + root = btrfs_alloc_root(fs_info); if (!root) return ERR_PTR(-ENOMEM); - root->fs_info = fs_info; __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, BTRFS_TREE_LOG_OBJECTID); @@ -1317,10 +1324,9 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, u32 blocksize; int ret = 0; - root = kzalloc(sizeof(*root), GFP_NOFS); + root = btrfs_alloc_root(fs_info); if (!root) return ERR_PTR(-ENOMEM); - root->fs_info = fs_info; if (location->offset == (u64)-1) { ret = find_and_setup_root(tree_root, fs_info, location->objectid, root); @@ -1900,23 +1906,15 @@ struct btrfs_root *open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; - extent_root = fs_info->extent_root = - kzalloc(sizeof(struct btrfs_root), GFP_NOFS); - csum_root = fs_info->csum_root = - kzalloc(sizeof(struct btrfs_root), GFP_NOFS); - chunk_root = fs_info->chunk_root = - kzalloc(sizeof(struct btrfs_root), GFP_NOFS); - dev_root = fs_info->dev_root = - kzalloc(sizeof(struct btrfs_root), GFP_NOFS); + extent_root = fs_info->extent_root = btrfs_alloc_root(fs_info); + csum_root = fs_info->csum_root = btrfs_alloc_root(fs_info); + chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); + dev_root = fs_info->dev_root = btrfs_alloc_root(fs_info); if (!extent_root || !csum_root || !chunk_root || !dev_root) { err = -ENOMEM; goto fail; } - chunk_root->fs_info = fs_info; - extent_root->fs_info = fs_info; - dev_root->fs_info = fs_info; - csum_root->fs_info = fs_info; ret = init_srcu_struct(&fs_info->subvol_srcu); if (ret) { @@ -2372,13 +2370,12 @@ retry_root_backup: btrfs_level_size(tree_root, btrfs_super_log_root_level(disk_super)); - log_tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); + log_tree_root = btrfs_alloc_root(fs_info); if (!log_tree_root) { err = -ENOMEM; goto fail_trans_kthread; } - log_tree_root->fs_info = fs_info; __setup_root(nodesize, leafsize, sectorsize, stripesize, log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index c99d0a8f13fa..2bb5f59ddf95 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -86,6 +86,8 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root); +struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info); + #ifdef CONFIG_DEBUG_LOCK_ALLOC void btrfs_init_lockdep(void); void btrfs_set_buffer_lockdep_class(u64 objectid, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b9fd62a0fca2..e9f876a1655b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -901,12 +901,11 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (!fs_info) return ERR_PTR(-ENOMEM); - fs_info->tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); + fs_info->tree_root = btrfs_alloc_root(fs_info); if (!fs_info->tree_root) { error = -ENOMEM; goto error_fs_info; } - fs_info->tree_root->fs_info = fs_info; fs_info->fs_devices = fs_devices; fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); -- cgit v1.2.3 From e3029d9fd426c8f582210ba35551ae5506218345 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 00:56:18 -0500 Subject: btrfs: sanitizing ->fs_info, part 5 close_ctree() uses a weird mix of accesses to root->fs_info and its value at the beginning of function stored in local variable. Since ->fs_info *never* changes, let's just use the local variable to avoid confusion. Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ee846ce58846..9308c7f13c17 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2982,7 +2982,7 @@ int close_ctree(struct btrfs_root *root) (atomic_read(&fs_info->defrag_running) == 0)); /* clear out the rbtree of defraggable inodes */ - btrfs_run_defrag_inodes(root->fs_info); + btrfs_run_defrag_inodes(fs_info); /* * Here come 2 situations when btrfs is broken to flip readonly: @@ -3011,8 +3011,8 @@ int close_ctree(struct btrfs_root *root) btrfs_put_block_group_cache(fs_info); - kthread_stop(root->fs_info->transaction_kthread); - kthread_stop(root->fs_info->cleaner_kthread); + kthread_stop(fs_info->transaction_kthread); + kthread_stop(fs_info->cleaner_kthread); fs_info->closing = 2; smp_mb(); @@ -3030,14 +3030,14 @@ int close_ctree(struct btrfs_root *root) free_extent_buffer(fs_info->extent_root->commit_root); free_extent_buffer(fs_info->tree_root->node); free_extent_buffer(fs_info->tree_root->commit_root); - free_extent_buffer(root->fs_info->chunk_root->node); - free_extent_buffer(root->fs_info->chunk_root->commit_root); - free_extent_buffer(root->fs_info->dev_root->node); - free_extent_buffer(root->fs_info->dev_root->commit_root); - free_extent_buffer(root->fs_info->csum_root->node); - free_extent_buffer(root->fs_info->csum_root->commit_root); - - btrfs_free_block_groups(root->fs_info); + free_extent_buffer(fs_info->chunk_root->node); + free_extent_buffer(fs_info->chunk_root->commit_root); + free_extent_buffer(fs_info->dev_root->node); + free_extent_buffer(fs_info->dev_root->commit_root); + free_extent_buffer(fs_info->csum_root->node); + free_extent_buffer(fs_info->csum_root->commit_root); + + btrfs_free_block_groups(fs_info); del_fs_roots(fs_info); -- cgit v1.2.3 From ad2b2c802be2d3e8ed8364fef5ffaddabe448219 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 01:10:02 -0500 Subject: btrfs: make open_ctree() return int It returns either ERR_PTR(-ve) or sb->s_fs_info. The latter can be found by caller just as well, TYVM, no need to return it. Just return -ve or 0... Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 12 ++++++------ fs/btrfs/disk-io.h | 6 +++--- fs/btrfs/super.c | 8 ++++---- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9308c7f13c17..78247522c693 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1880,9 +1880,9 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) } -struct btrfs_root *open_ctree(struct super_block *sb, - struct btrfs_fs_devices *fs_devices, - char *options) +int open_ctree(struct super_block *sb, + struct btrfs_fs_devices *fs_devices, + char *options) { u32 sectorsize; u32 nodesize; @@ -2428,11 +2428,11 @@ retry_root_backup: if (err) { close_ctree(tree_root); free_fs_info(fs_info); - return ERR_PTR(err); + return err; } } - return tree_root; + return 0; fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); @@ -2479,7 +2479,7 @@ fail_srcu: fail: btrfs_close_devices(fs_info->fs_devices); free_fs_info(fs_info); - return ERR_PTR(err); + return err; recovery_tree_root: if (!btrfs_test_opt(tree_root, RECOVERY)) diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 2bb5f59ddf95..6f5f48778b00 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -46,9 +46,9 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize); int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf); -struct btrfs_root *open_ctree(struct super_block *sb, - struct btrfs_fs_devices *fs_devices, - char *options); +int open_ctree(struct super_block *sb, + struct btrfs_fs_devices *fs_devices, + char *options); int close_ctree(struct btrfs_root *root); int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index e9f876a1655b..56e007fd6702 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -604,12 +604,12 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_flags |= MS_POSIXACL; #endif - tree_root = open_ctree(sb, fs_devices, (char *)data); - - if (IS_ERR(tree_root)) { + err = open_ctree(sb, fs_devices, (char *)data); + if (err) { printk("btrfs: open_ctree failed\n"); - return PTR_ERR(tree_root); + return err; } + tree_root = sb->s_fs_info; fs_info = tree_root->fs_info; sb->s_fs_info = tree_root; -- cgit v1.2.3 From be7e0950def403e90b5295ff2192c39967bf2aec Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 01:40:05 -0500 Subject: btrfs: merge free_fs_info() calls on fill_super failures ... all the way up into btrfs_mount(). Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 2 -- fs/btrfs/super.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 78247522c693..b6d11eb4e430 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2427,7 +2427,6 @@ retry_root_backup: up_read(&fs_info->cleanup_work_sem); if (err) { close_ctree(tree_root); - free_fs_info(fs_info); return err; } } @@ -2478,7 +2477,6 @@ fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: btrfs_close_devices(fs_info->fs_devices); - free_fs_info(fs_info); return err; recovery_tree_root: diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a381f9f9b0c2..8901b6c85260 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -634,7 +634,6 @@ static int btrfs_fill_super(struct super_block *sb, fail_close: close_ctree(tree_root); - free_fs_info(fs_info); return err; } @@ -947,6 +946,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); if (error) { + free_fs_info(fs_info); deactivate_locked_super(s); return ERR_PTR(error); } -- cgit v1.2.3 From 815745cf3e46681241ad8025602ffbf2a452d514 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 15:40:49 -0500 Subject: btrfs: let ->s_fs_info point to fs_info, not root... the latter can be obtained from the former (by looking as ->tree_root) just as cheaply as we currently are doing the other way round. Signed-off-by: Al Viro --- fs/btrfs/ctree.h | 2 +- fs/btrfs/disk-io.c | 4 +-- fs/btrfs/export.c | 2 +- fs/btrfs/ioctl.c | 7 +++-- fs/btrfs/super.c | 75 +++++++++++++++++++++++++++--------------------------- 5 files changed, 45 insertions(+), 45 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67385033323d..dbb999a38272 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2196,7 +2196,7 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, return btrfs_item_size(eb, e) - offset; } -static inline struct btrfs_root *btrfs_sb(struct super_block *sb) +static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb) { return sb->s_fs_info; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b6d11eb4e430..f7d8b9ba519b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1894,8 +1894,8 @@ int open_ctree(struct super_block *sb, struct btrfs_key location; struct buffer_head *bh; struct btrfs_super_block *disk_super; - struct btrfs_root *tree_root = btrfs_sb(sb); - struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *extent_root; struct btrfs_root *csum_root; struct btrfs_root *chunk_root; diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1b8dc33778f9..5f77166fd01c 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -67,7 +67,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, u64 root_objectid, u32 generation, int check_generation) { - struct btrfs_fs_info *fs_info = btrfs_sb(sb)->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root; struct inode *inode; struct btrfs_key key; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5441ff1480fd..0c55f8f38091 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -276,14 +276,13 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg) static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) { - struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info; - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(fdentry(file)->d_sb); struct btrfs_device *device; struct request_queue *q; struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; - u64 total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy); + u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); int ret; if (!capable(CAP_SYS_ADMIN)) @@ -312,7 +311,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) range.len = min(range.len, total_bytes - range.start); range.minlen = max(range.minlen, minlen); - ret = btrfs_trim_fs(root, &range); + ret = btrfs_trim_fs(fs_info->tree_root, &range); if (ret < 0) return ret; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 15c8ae571e40..305adf6dc09a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -147,7 +147,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, static void btrfs_put_super(struct super_block *sb) { - (void)close_ctree(btrfs_sb(sb)); + (void)close_ctree(btrfs_sb(sb)->tree_root); /* FIXME: need to fix VFS to return error? */ /* AV: return it _where_? ->put_super() can be triggered by any number * of async events, up to and including delivery of SIGKILL to the @@ -500,7 +500,8 @@ out: static struct dentry *get_default_root(struct super_block *sb, u64 subvol_objectid) { - struct btrfs_root *root = sb->s_fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; struct btrfs_root *new_root; struct btrfs_dir_item *di; struct btrfs_path *path; @@ -530,7 +531,7 @@ static struct dentry *get_default_root(struct super_block *sb, * will mount by default if we haven't been given a specific subvolume * to mount. */ - dir_id = btrfs_super_root_dir(root->fs_info->super_copy); + dir_id = btrfs_super_root_dir(fs_info->super_copy); di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); if (IS_ERR(di)) { btrfs_free_path(path); @@ -544,7 +545,7 @@ static struct dentry *get_default_root(struct super_block *sb, */ btrfs_free_path(path); dir_id = BTRFS_FIRST_FREE_OBJECTID; - new_root = root->fs_info->fs_root; + new_root = fs_info->fs_root; goto setup_root; } @@ -552,7 +553,7 @@ static struct dentry *get_default_root(struct super_block *sb, btrfs_free_path(path); find_root: - new_root = btrfs_read_fs_root_no_name(root->fs_info, &location); + new_root = btrfs_read_fs_root_no_name(fs_info, &location); if (IS_ERR(new_root)) return ERR_CAST(new_root); @@ -588,8 +589,7 @@ static int btrfs_fill_super(struct super_block *sb, { struct inode *inode; struct dentry *root_dentry; - struct btrfs_root *tree_root = sb->s_fs_info; - struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_key key; int err; @@ -634,20 +634,21 @@ static int btrfs_fill_super(struct super_block *sb, return 0; fail_close: - close_ctree(tree_root); + close_ctree(fs_info->tree_root); return err; } int btrfs_sync_fs(struct super_block *sb, int wait) { struct btrfs_trans_handle *trans; - struct btrfs_root *root = btrfs_sb(sb); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; int ret; trace_btrfs_sync_fs(wait); if (!wait) { - filemap_flush(root->fs_info->btree_inode->i_mapping); + filemap_flush(fs_info->btree_inode->i_mapping); return 0; } @@ -663,8 +664,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait) static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { - struct btrfs_root *root = btrfs_sb(dentry->d_sb); - struct btrfs_fs_info *info = root->fs_info; + struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); + struct btrfs_root *root = info->tree_root; char *compress_type; if (btrfs_test_opt(root, DEGRADED)) @@ -727,10 +728,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) static int btrfs_test_super(struct super_block *s, void *data) { - struct btrfs_root *test_root = data; - struct btrfs_root *root = btrfs_sb(s); + struct btrfs_fs_info *p = data; + struct btrfs_fs_info *fs_info = btrfs_sb(s); - return root->fs_info->fs_devices == test_root->fs_info->fs_devices; + return fs_info->fs_devices == p->fs_devices; } static int btrfs_set_super(struct super_block *s, void *data) @@ -922,8 +923,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, - fs_info->tree_root); + s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); goto error_close_devices; @@ -939,7 +939,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, s->s_flags = flags | MS_NOSEC; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); - btrfs_sb(s)->fs_info->bdev_holder = fs_type; + btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); } @@ -959,7 +959,8 @@ error_fs_info: static int btrfs_remount(struct super_block *sb, int *flags, char *data) { - struct btrfs_root *root = btrfs_sb(sb); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; int ret; ret = btrfs_parse_options(root, data); @@ -975,13 +976,13 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) ret = btrfs_commit_super(root); WARN_ON(ret); } else { - if (root->fs_info->fs_devices->rw_devices == 0) + if (fs_info->fs_devices->rw_devices == 0) return -EACCES; - if (btrfs_super_log_root(root->fs_info->super_copy) != 0) + if (btrfs_super_log_root(fs_info->super_copy) != 0) return -EINVAL; - ret = btrfs_cleanup_fs_roots(root->fs_info); + ret = btrfs_cleanup_fs_roots(fs_info); WARN_ON(ret); /* recover relocation */ @@ -1150,18 +1151,18 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct btrfs_root *root = btrfs_sb(dentry->d_sb); - struct btrfs_super_block *disk_super = root->fs_info->super_copy; - struct list_head *head = &root->fs_info->space_info; + struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); + struct btrfs_super_block *disk_super = fs_info->super_copy; + struct list_head *head = &fs_info->space_info; struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; int bits = dentry->d_sb->s_blocksize_bits; - __be32 *fsid = (__be32 *)root->fs_info->fsid; + __be32 *fsid = (__be32 *)fs_info->fsid; int ret; /* holding chunk_muext to avoid allocating new chunks */ - mutex_lock(&root->fs_info->chunk_mutex); + mutex_lock(&fs_info->chunk_mutex); rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { @@ -1180,14 +1181,14 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bavail = total_free_data; - ret = btrfs_calc_avail_data_space(root, &total_free_data); + ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data); if (ret) { - mutex_unlock(&root->fs_info->chunk_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } buf->f_bavail += total_free_data; buf->f_bavail = buf->f_bavail >> bits; - mutex_unlock(&root->fs_info->chunk_mutex); + mutex_unlock(&fs_info->chunk_mutex); /* We treat it as constant endianness (it doesn't matter _which_) because we want the fsid to come out the same whether mounted @@ -1203,7 +1204,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) static void btrfs_kill_super(struct super_block *sb) { - struct btrfs_fs_info *fs_info = btrfs_sb(sb)->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); kill_anon_super(sb); free_fs_info(fs_info); } @@ -1246,17 +1247,17 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, static int btrfs_freeze(struct super_block *sb) { - struct btrfs_root *root = btrfs_sb(sb); - mutex_lock(&root->fs_info->transaction_kthread_mutex); - mutex_lock(&root->fs_info->cleaner_mutex); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + mutex_lock(&fs_info->transaction_kthread_mutex); + mutex_lock(&fs_info->cleaner_mutex); return 0; } static int btrfs_unfreeze(struct super_block *sb) { - struct btrfs_root *root = btrfs_sb(sb); - mutex_unlock(&root->fs_info->cleaner_mutex); - mutex_unlock(&root->fs_info->transaction_kthread_mutex); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + mutex_unlock(&fs_info->cleaner_mutex); + mutex_unlock(&fs_info->transaction_kthread_mutex); return 0; } -- cgit v1.2.3 From f84a8bd60e3ee49eacc9ba824babf149ba3dad7e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 15:57:57 -0500 Subject: btrfs: take allocation of ->tree_root into open_ctree() now that we don't need it for sget() anymore... Signed-off-by: Al Viro --- fs/btrfs/disk-io.c | 8 +++++--- fs/btrfs/disk-io.h | 2 -- fs/btrfs/super.c | 5 ----- 3 files changed, 5 insertions(+), 10 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f7d8b9ba519b..dd71be875939 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1215,7 +1215,7 @@ static int find_and_setup_root(struct btrfs_root *tree_root, return 0; } -struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) +static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) { struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS); if (root) @@ -1895,7 +1895,7 @@ int open_ctree(struct super_block *sb, struct buffer_head *bh; struct btrfs_super_block *disk_super; struct btrfs_fs_info *fs_info = btrfs_sb(sb); - struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *tree_root; struct btrfs_root *extent_root; struct btrfs_root *csum_root; struct btrfs_root *chunk_root; @@ -1906,12 +1906,14 @@ int open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; + tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); extent_root = fs_info->extent_root = btrfs_alloc_root(fs_info); csum_root = fs_info->csum_root = btrfs_alloc_root(fs_info); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); dev_root = fs_info->dev_root = btrfs_alloc_root(fs_info); - if (!extent_root || !csum_root || !chunk_root || !dev_root) { + if (!tree_root || !extent_root || !csum_root || + !chunk_root || !dev_root) { err = -ENOMEM; goto fail; } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 6f5f48778b00..e4bc4741319b 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -86,8 +86,6 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root); -struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info); - #ifdef CONFIG_DEBUG_LOCK_ALLOC void btrfs_init_lockdep(void); void btrfs_set_buffer_lockdep_class(u64 objectid, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 305adf6dc09a..044652ee7ef5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -899,11 +899,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (!fs_info) return ERR_PTR(-ENOMEM); - fs_info->tree_root = btrfs_alloc_root(fs_info); - if (!fs_info->tree_root) { - error = -ENOMEM; - goto error_fs_info; - } fs_info->fs_devices = fs_devices; fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); -- cgit v1.2.3 From b367e47fb3a70f5d24ebd6faf7d42436d485fb2d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Dec 2011 11:38:24 +0800 Subject: Btrfs: fix possible deadlock when opening a seed device The correct lock order is uuid_mutex -> volume_mutex -> chunk_mutex, but when we mount a filesystem which has backing seed devices, we have this lock chain: open_ctree() lock(chunk_mutex); read_chunk_tree(); read_one_dev(); open_seed_devices(); lock(uuid_mutex); and then we hit a lockdep splat. Signed-off-by: Li Zefan --- fs/btrfs/disk-io.c | 2 -- fs/btrfs/volumes.c | 9 +++++++-- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3f9d5551e582..858ab347413e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2270,9 +2270,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE); - mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_chunk_tree(chunk_root); - mutex_unlock(&fs_info->chunk_mutex); if (ret) { printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", sb->s_id); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 563ef650850e..fbb493b28d5a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3506,7 +3506,7 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid) struct btrfs_fs_devices *fs_devices; int ret; - mutex_lock(&uuid_mutex); + BUG_ON(!mutex_is_locked(&uuid_mutex)); fs_devices = root->fs_info->fs_devices->seed; while (fs_devices) { @@ -3544,7 +3544,6 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid) fs_devices->seed = root->fs_info->fs_devices->seed; root->fs_info->fs_devices->seed = fs_devices; out: - mutex_unlock(&uuid_mutex); return ret; } @@ -3687,6 +3686,9 @@ int btrfs_read_chunk_tree(struct btrfs_root *root) if (!path) return -ENOMEM; + mutex_lock(&uuid_mutex); + lock_chunks(root); + /* first we search for all of the device items, and then we * read in all of the chunk items. This way we can create chunk * mappings that reference all of the devices that are afound @@ -3737,6 +3739,9 @@ again: } ret = 0; error: + unlock_chunks(root); + mutex_unlock(&uuid_mutex); + btrfs_free_path(path); return ret; } -- cgit v1.2.3 From b969c4ab9f182a6e1b2a0848be349f99714947b0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Jan 2012 17:19:34 -0800 Subject: mm: compaction: determine if dirty pages can be migrated without blocking within ->migratepage Asynchronous compaction is used when allocating transparent hugepages to avoid blocking for long periods of time. Due to reports of stalling, there was a debate on disabling synchronous compaction but this severely impacted allocation success rates. Part of the reason was that many dirty pages are skipped in asynchronous compaction by the following check; if (PageDirty(page) && !sync && mapping->a_ops->migratepage != migrate_page) rc = -EBUSY; This skips over all mapping aops using buffer_migrate_page() even though it is possible to migrate some of these pages without blocking. This patch updates the ->migratepage callback with a "sync" parameter. It is the responsibility of the callback to fail gracefully if migration would block. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Minchan Kim Cc: Dave Jones Cc: Jan Kara Cc: Andy Isaacson Cc: Nai Xia Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/disk-io.c | 4 +- fs/hugetlbfs/inode.c | 3 +- fs/nfs/internal.h | 2 +- fs/nfs/write.c | 4 +- include/linux/fs.h | 9 ++-- include/linux/migrate.h | 2 +- mm/migrate.c | 129 ++++++++++++++++++++++++++++++++++-------------- 7 files changed, 106 insertions(+), 47 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f99a099a7747..1375494c8cb6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -872,7 +872,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, #ifdef CONFIG_MIGRATION static int btree_migratepage(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, bool sync) { /* * we can't safely write a btree page from here, @@ -887,7 +887,7 @@ static int btree_migratepage(struct address_space *mapping, if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, sync); } #endif diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index e425ad9d0490..06fd4608a990 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -583,7 +583,8 @@ static int hugetlbfs_set_page_dirty(struct page *page) } static int hugetlbfs_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + bool sync) { int rc; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5ee92538b063..114398a15830 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -332,7 +332,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, bool); #else #define nfs_migrate_page NULL #endif diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 0c3885255f97..889e98bc5a21 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1688,7 +1688,7 @@ out_error: #ifdef CONFIG_MIGRATION int nfs_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page) + struct page *page, bool sync) { /* * If PagePrivate is set, then the page is currently associated with @@ -1703,7 +1703,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, nfs_fscache_release_page(page, GFP_KERNEL); - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, sync); } #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index a7409bc157e0..b92b73d0b2b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -609,9 +609,12 @@ struct address_space_operations { loff_t offset, unsigned long nr_segs); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); - /* migrate the contents of a page to the specified target */ + /* + * migrate the contents of a page to the specified target. If sync + * is false, it must not block. + */ int (*migratepage) (struct address_space *, - struct page *, struct page *); + struct page *, struct page *, bool); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); @@ -2537,7 +2540,7 @@ extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, bool); #else #define buffer_migrate_page NULL #endif diff --git a/include/linux/migrate.h b/include/linux/migrate.h index e39aeecfe9a2..14e6d2a88475 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -11,7 +11,7 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **); extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, bool); extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, bool sync); diff --git a/mm/migrate.c b/mm/migrate.c index fc391985899f..4e86f3bacb85 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -216,6 +216,55 @@ out: pte_unmap_unlock(ptep, ptl); } +#ifdef CONFIG_BLOCK +/* Returns true if all buffers are successfully locked */ +static bool buffer_migrate_lock_buffers(struct buffer_head *head, bool sync) +{ + struct buffer_head *bh = head; + + /* Simple case, sync compaction */ + if (sync) { + do { + get_bh(bh); + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return true; + } + + /* async case, we cannot block on lock_buffer so use trylock_buffer */ + do { + get_bh(bh); + if (!trylock_buffer(bh)) { + /* + * We failed to lock the buffer and cannot stall in + * async migration. Release the taken locks + */ + struct buffer_head *failed_bh = bh; + put_bh(failed_bh); + bh = head; + while (bh != failed_bh) { + unlock_buffer(bh); + put_bh(bh); + bh = bh->b_this_page; + } + return false; + } + + bh = bh->b_this_page; + } while (bh != head); + return true; +} +#else +static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, + bool sync) +{ + return true; +} +#endif /* CONFIG_BLOCK */ + /* * Replace the page in the mapping. * @@ -225,7 +274,8 @@ out: * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ static int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + struct buffer_head *head, bool sync) { int expected_count; void **pslot; @@ -254,6 +304,19 @@ static int migrate_page_move_mapping(struct address_space *mapping, return -EAGAIN; } + /* + * In the async migration case of moving a page with buffers, lock the + * buffers using trylock before the mapping is moved. If the mapping + * was moved, we later failed to lock the buffers and could not move + * the mapping back due to an elevated page count, we would have to + * block waiting on other references to be dropped. + */ + if (!sync && head && !buffer_migrate_lock_buffers(head, sync)) { + page_unfreeze_refs(page, expected_count); + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + /* * Now we know that no one else is looking at the page. */ @@ -409,13 +472,13 @@ EXPORT_SYMBOL(fail_migrate_page); * Pages are locked upon entry and exit. */ int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, bool sync) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, sync); if (rc) return rc; @@ -432,28 +495,28 @@ EXPORT_SYMBOL(migrate_page); * exist. */ int buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, bool sync) { struct buffer_head *bh, *head; int rc; if (!page_has_buffers(page)) - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, sync); head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, head, sync); if (rc) return rc; - bh = head; - do { - get_bh(bh); - lock_buffer(bh); - bh = bh->b_this_page; - - } while (bh != head); + /* + * In the async case, migrate_page_move_mapping locked the buffers + * with an IRQ-safe spinlock held. In the sync case, the buffers + * need to be locked now + */ + if (sync) + BUG_ON(!buffer_migrate_lock_buffers(head, sync)); ClearPagePrivate(page); set_page_private(newpage, page_private(page)); @@ -530,10 +593,13 @@ static int writeout(struct address_space *mapping, struct page *page) * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, bool sync) { - if (PageDirty(page)) + if (PageDirty(page)) { + if (!sync) + return -EBUSY; return writeout(mapping, page); + } /* * Buffers may be managed in a filesystem specific way. @@ -543,7 +609,7 @@ static int fallback_migrate_page(struct address_space *mapping, !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, sync); } /* @@ -579,29 +645,18 @@ static int move_to_new_page(struct page *newpage, struct page *page, mapping = page_mapping(page); if (!mapping) - rc = migrate_page(mapping, newpage, page); - else { + rc = migrate_page(mapping, newpage, page, sync); + else if (mapping->a_ops->migratepage) /* - * Do not writeback pages if !sync and migratepage is - * not pointing to migrate_page() which is nonblocking - * (swapcache/tmpfs uses migratepage = migrate_page). + * Most pages have a mapping and most filesystems provide a + * migratepage callback. Anonymous pages are part of swap + * space which also has its own migratepage callback. This + * is the most common path for page migration. */ - if (PageDirty(page) && !sync && - mapping->a_ops->migratepage != migrate_page) - rc = -EBUSY; - else if (mapping->a_ops->migratepage) - /* - * Most pages have a mapping and most filesystems - * should provide a migration function. Anonymous - * pages are part of swap space which also has its - * own migration function. This is the most common - * path for page migration. - */ - rc = mapping->a_ops->migratepage(mapping, - newpage, page); - else - rc = fallback_migrate_page(mapping, newpage, page); - } + rc = mapping->a_ops->migratepage(mapping, + newpage, page, sync); + else + rc = fallback_migrate_page(mapping, newpage, page, sync); if (rc) { newpage->mapping = NULL; -- cgit v1.2.3 From a6bc32b899223a877f595ef9ddc1e89ead5072b8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Jan 2012 17:19:43 -0800 Subject: mm: compaction: introduce sync-light migration for use by compaction This patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT mode that avoids writing back pages to backing storage. Async compaction maps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT. For other migrate_pages users such as memory hotplug, MIGRATE_SYNC is used. This avoids sync compaction stalling for an excessive length of time, particularly when copying files to a USB stick where there might be a large number of dirty pages backed by a filesystem that does not support ->writepages. [aarcange@redhat.com: This patch is heavily based on Andrea's work] [akpm@linux-foundation.org: fix fs/nfs/write.c build] [akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build] Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Minchan Kim Cc: Dave Jones Cc: Jan Kara Cc: Andy Isaacson Cc: Nai Xia Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/disk-io.c | 5 ++-- fs/hugetlbfs/inode.c | 2 +- fs/nfs/internal.h | 2 +- fs/nfs/write.c | 4 +-- include/linux/fs.h | 6 ++-- include/linux/migrate.h | 23 +++++++++++---- mm/compaction.c | 2 +- mm/memory-failure.c | 2 +- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 2 +- mm/migrate.c | 78 +++++++++++++++++++++++++++---------------------- 11 files changed, 76 insertions(+), 52 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1375494c8cb6..d8525662ca7a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -872,7 +872,8 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, #ifdef CONFIG_MIGRATION static int btree_migratepage(struct address_space *mapping, - struct page *newpage, struct page *page, bool sync) + struct page *newpage, struct page *page, + enum migrate_mode mode) { /* * we can't safely write a btree page from here, @@ -887,7 +888,7 @@ static int btree_migratepage(struct address_space *mapping, if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page, sync); + return migrate_page(mapping, newpage, page, mode); } #endif diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 06fd4608a990..1e85a7ac0217 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -584,7 +584,7 @@ static int hugetlbfs_set_page_dirty(struct page *page) static int hugetlbfs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, - bool sync) + enum migrate_mode mode) { int rc; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 114398a15830..8102db9b926c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -332,7 +332,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, - struct page *, struct page *, bool); + struct page *, struct page *, enum migrate_mode); #else #define nfs_migrate_page NULL #endif diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 889e98bc5a21..834f0fe96f89 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1688,7 +1688,7 @@ out_error: #ifdef CONFIG_MIGRATION int nfs_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page, bool sync) + struct page *page, enum migrate_mode mode) { /* * If PagePrivate is set, then the page is currently associated with @@ -1703,7 +1703,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, nfs_fscache_release_page(page, GFP_KERNEL); - return migrate_page(mapping, newpage, page, sync); + return migrate_page(mapping, newpage, page, mode); } #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index b92b73d0b2b9..e694bd4434a4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -525,6 +525,7 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; +enum migrate_mode; struct iov_iter { const struct iovec *iov; @@ -614,7 +615,7 @@ struct address_space_operations { * is false, it must not block. */ int (*migratepage) (struct address_space *, - struct page *, struct page *, bool); + struct page *, struct page *, enum migrate_mode); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); @@ -2540,7 +2541,8 @@ extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *, bool); + struct page *, struct page *, + enum migrate_mode); #else #define buffer_migrate_page NULL #endif diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 14e6d2a88475..eaf867412f7a 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -6,18 +6,31 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **); +/* + * MIGRATE_ASYNC means never block + * MIGRATE_SYNC_LIGHT in the current implementation means to allow blocking + * on most operations but not ->writepage as the potential stall time + * is too significant + * MIGRATE_SYNC will block when migrating pages + */ +enum migrate_mode { + MIGRATE_ASYNC, + MIGRATE_SYNC_LIGHT, + MIGRATE_SYNC, +}; + #ifdef CONFIG_MIGRATION #define PAGE_MIGRATION 1 extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, - struct page *, struct page *, bool); + struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync); + enum migrate_mode mode); extern int migrate_huge_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync); + enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -36,10 +49,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync) { return -ENOSYS; } + enum migrate_mode mode) { return -ENOSYS; } static inline int migrate_huge_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync) { return -ENOSYS; } + enum migrate_mode mode) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/mm/compaction.c b/mm/compaction.c index fb291585e1bf..71a58f67f481 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -557,7 +557,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, (unsigned long)cc, false, - cc->sync); + cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 06d3479513aa..56080ea36140 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1557,7 +1557,7 @@ int soft_offline_page(struct page *page, int flags) page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - 0, true); + 0, MIGRATE_SYNC); if (ret) { putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2168489c0bc9..6629fafd6ce4 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -809,7 +809,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } /* this function returns # of failed pages */ ret = migrate_pages(&source, hotremove_migrate_alloc, 0, - true, true); + true, MIGRATE_SYNC); if (ret) putback_lru_pages(&source); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e3d58f088466..06b145fb64ab 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -942,7 +942,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, - false, true); + false, MIGRATE_SYNC); if (err) putback_lru_pages(&pagelist); } diff --git a/mm/migrate.c b/mm/migrate.c index 4e86f3bacb85..9871a56d82c3 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -218,12 +218,13 @@ out: #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ -static bool buffer_migrate_lock_buffers(struct buffer_head *head, bool sync) +static bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) { struct buffer_head *bh = head; /* Simple case, sync compaction */ - if (sync) { + if (mode != MIGRATE_ASYNC) { do { get_bh(bh); lock_buffer(bh); @@ -259,7 +260,7 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, bool sync) } #else static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, - bool sync) + enum migrate_mode mode) { return true; } @@ -275,7 +276,7 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, */ static int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, - struct buffer_head *head, bool sync) + struct buffer_head *head, enum migrate_mode mode) { int expected_count; void **pslot; @@ -311,7 +312,8 @@ static int migrate_page_move_mapping(struct address_space *mapping, * the mapping back due to an elevated page count, we would have to * block waiting on other references to be dropped. */ - if (!sync && head && !buffer_migrate_lock_buffers(head, sync)) { + if (mode == MIGRATE_ASYNC && head && + !buffer_migrate_lock_buffers(head, mode)) { page_unfreeze_refs(page, expected_count); spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; @@ -472,13 +474,14 @@ EXPORT_SYMBOL(fail_migrate_page); * Pages are locked upon entry and exit. */ int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, bool sync) + struct page *newpage, struct page *page, + enum migrate_mode mode) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page, NULL, sync); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode); if (rc) return rc; @@ -495,17 +498,17 @@ EXPORT_SYMBOL(migrate_page); * exist. */ int buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, bool sync) + struct page *newpage, struct page *page, enum migrate_mode mode) { struct buffer_head *bh, *head; int rc; if (!page_has_buffers(page)) - return migrate_page(mapping, newpage, page, sync); + return migrate_page(mapping, newpage, page, mode); head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page, head, sync); + rc = migrate_page_move_mapping(mapping, newpage, page, head, mode); if (rc) return rc; @@ -515,8 +518,8 @@ int buffer_migrate_page(struct address_space *mapping, * with an IRQ-safe spinlock held. In the sync case, the buffers * need to be locked now */ - if (sync) - BUG_ON(!buffer_migrate_lock_buffers(head, sync)); + if (mode != MIGRATE_ASYNC) + BUG_ON(!buffer_migrate_lock_buffers(head, mode)); ClearPagePrivate(page); set_page_private(newpage, page_private(page)); @@ -593,10 +596,11 @@ static int writeout(struct address_space *mapping, struct page *page) * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, bool sync) + struct page *newpage, struct page *page, enum migrate_mode mode) { if (PageDirty(page)) { - if (!sync) + /* Only writeback pages in full synchronous migration */ + if (mode != MIGRATE_SYNC) return -EBUSY; return writeout(mapping, page); } @@ -609,7 +613,7 @@ static int fallback_migrate_page(struct address_space *mapping, !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page, sync); + return migrate_page(mapping, newpage, page, mode); } /* @@ -624,7 +628,7 @@ static int fallback_migrate_page(struct address_space *mapping, * == 0 - success */ static int move_to_new_page(struct page *newpage, struct page *page, - int remap_swapcache, bool sync) + int remap_swapcache, enum migrate_mode mode) { struct address_space *mapping; int rc; @@ -645,7 +649,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, mapping = page_mapping(page); if (!mapping) - rc = migrate_page(mapping, newpage, page, sync); + rc = migrate_page(mapping, newpage, page, mode); else if (mapping->a_ops->migratepage) /* * Most pages have a mapping and most filesystems provide a @@ -654,9 +658,9 @@ static int move_to_new_page(struct page *newpage, struct page *page, * is the most common path for page migration. */ rc = mapping->a_ops->migratepage(mapping, - newpage, page, sync); + newpage, page, mode); else - rc = fallback_migrate_page(mapping, newpage, page, sync); + rc = fallback_migrate_page(mapping, newpage, page, mode); if (rc) { newpage->mapping = NULL; @@ -671,7 +675,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, } static int __unmap_and_move(struct page *page, struct page *newpage, - int force, bool offlining, bool sync) + int force, bool offlining, enum migrate_mode mode) { int rc = -EAGAIN; int remap_swapcache = 1; @@ -680,7 +684,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, struct anon_vma *anon_vma = NULL; if (!trylock_page(page)) { - if (!force || !sync) + if (!force || mode == MIGRATE_ASYNC) goto out; /* @@ -726,10 +730,12 @@ static int __unmap_and_move(struct page *page, struct page *newpage, if (PageWriteback(page)) { /* - * For !sync, there is no point retrying as the retry loop - * is expected to be too short for PageWriteback to be cleared + * Only in the case of a full syncronous migration is it + * necessary to wait for PageWriteback. In the async case, + * the retry loop is too short and in the sync-light case, + * the overhead of stalling is too much */ - if (!sync) { + if (mode != MIGRATE_SYNC) { rc = -EBUSY; goto uncharge; } @@ -800,7 +806,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, skip_unmap: if (!page_mapped(page)) - rc = move_to_new_page(newpage, page, remap_swapcache, sync); + rc = move_to_new_page(newpage, page, remap_swapcache, mode); if (rc && remap_swapcache) remove_migration_ptes(page, page); @@ -823,7 +829,8 @@ out: * to the newly allocated page in newpage. */ static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, bool sync) + struct page *page, int force, bool offlining, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -843,7 +850,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (unlikely(split_huge_page(page))) goto out; - rc = __unmap_and_move(page, newpage, force, offlining, sync); + rc = __unmap_and_move(page, newpage, force, offlining, mode); out: if (rc != -EAGAIN) { /* @@ -891,7 +898,8 @@ out: */ static int unmap_and_move_huge_page(new_page_t get_new_page, unsigned long private, struct page *hpage, - int force, bool offlining, bool sync) + int force, bool offlining, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -904,7 +912,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, rc = -EAGAIN; if (!trylock_page(hpage)) { - if (!force || !sync) + if (!force || mode != MIGRATE_SYNC) goto out; lock_page(hpage); } @@ -915,7 +923,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); if (!page_mapped(hpage)) - rc = move_to_new_page(new_hpage, hpage, 1, sync); + rc = move_to_new_page(new_hpage, hpage, 1, mode); if (rc) remove_migration_ptes(hpage, hpage); @@ -958,7 +966,7 @@ out: */ int migrate_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, bool offlining, - bool sync) + enum migrate_mode mode) { int retry = 1; int nr_failed = 0; @@ -979,7 +987,7 @@ int migrate_pages(struct list_head *from, rc = unmap_and_move(get_new_page, private, page, pass > 2, offlining, - sync); + mode); switch(rc) { case -ENOMEM: @@ -1009,7 +1017,7 @@ out: int migrate_huge_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, bool offlining, - bool sync) + enum migrate_mode mode) { int retry = 1; int nr_failed = 0; @@ -1026,7 +1034,7 @@ int migrate_huge_pages(struct list_head *from, rc = unmap_and_move_huge_page(get_new_page, private, page, pass > 2, offlining, - sync); + mode); switch(rc) { case -ENOMEM: @@ -1155,7 +1163,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0, true); + (unsigned long)pm, 0, MIGRATE_SYNC); if (err) putback_lru_pages(&pagelist); } -- cgit v1.2.3 From 6fef8df1dcb9b586268caff66df1d71ce8610132 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:47 +0200 Subject: Btrfs: get rid of *_alloc_profile fields {data,metadata,system}_alloc_profile fields have been unused for a long time now. Get rid of them. Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 3 --- fs/btrfs/disk-io.c | 3 --- fs/btrfs/extent-tree.c | 10 ++++------ fs/btrfs/volumes.c | 6 ++---- 4 files changed, 6 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67385033323d..f5434ad49b99 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1135,9 +1135,6 @@ struct btrfs_fs_info { u64 avail_data_alloc_bits; u64 avail_metadata_alloc_bits; u64 avail_system_alloc_bits; - u64 data_alloc_profile; - u64 metadata_alloc_profile; - u64 system_alloc_profile; unsigned data_chunk_allocations; unsigned metadata_ratio; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3f9d5551e582..ce9d0fb3627d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2321,9 +2321,6 @@ retry_root_backup: fs_info->generation = generation; fs_info->last_trans_committed = generation; - fs_info->data_alloc_profile = (u64)-1; - fs_info->metadata_alloc_profile = (u64)-1; - fs_info->system_alloc_profile = fs_info->metadata_alloc_profile; ret = btrfs_init_space_info(fs_info); if (ret) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 8603ee4e3dfd..f0591fd66249 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3067,14 +3067,12 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags) static u64 get_alloc_profile(struct btrfs_root *root, u64 flags) { if (flags & BTRFS_BLOCK_GROUP_DATA) - flags |= root->fs_info->avail_data_alloc_bits & - root->fs_info->data_alloc_profile; + flags |= root->fs_info->avail_data_alloc_bits; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) - flags |= root->fs_info->avail_system_alloc_bits & - root->fs_info->system_alloc_profile; + flags |= root->fs_info->avail_system_alloc_bits; else if (flags & BTRFS_BLOCK_GROUP_METADATA) - flags |= root->fs_info->avail_metadata_alloc_bits & - root->fs_info->metadata_alloc_profile; + flags |= root->fs_info->avail_metadata_alloc_bits; + return btrfs_reduce_alloc_profile(root, flags); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f4b839fd3c9d..89096f6d6fb4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2752,8 +2752,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, return ret; alloc_profile = BTRFS_BLOCK_GROUP_METADATA | - (fs_info->metadata_alloc_profile & - fs_info->avail_metadata_alloc_bits); + fs_info->avail_metadata_alloc_bits; alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile); ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size, @@ -2763,8 +2762,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, sys_chunk_offset = chunk_offset + chunk_size; alloc_profile = BTRFS_BLOCK_GROUP_SYSTEM | - (fs_info->system_alloc_profile & - fs_info->avail_system_alloc_bits); + fs_info->avail_system_alloc_bits; alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile); ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map, -- cgit v1.2.3 From c9e9f97bdfb64d06e9520f8e4f37674ac21cc9bc Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:47 +0200 Subject: Btrfs: add basic restriper infrastructure Add basic restriper infrastructure: extended balancing ioctl and all related ioctl data structures, add data structure for tracking restriper's state to fs_info, etc. The semantics of the old balancing ioctl are fully preserved. Explicitly disallow any volume operations when balance is in progress. Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 6 +++ fs/btrfs/disk-io.c | 4 ++ fs/btrfs/ioctl.c | 135 ++++++++++++++++++++++++++++++++++++++++++++++------- fs/btrfs/ioctl.h | 43 +++++++++++++++++ fs/btrfs/volumes.c | 120 +++++++++++++++++++++++++++++++++++++---------- fs/btrfs/volumes.h | 14 +++++- 6 files changed, 281 insertions(+), 41 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3f8f11e18b53..c4d98c8df5c5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -934,6 +934,7 @@ struct btrfs_block_group_cache { struct reloc_control; struct btrfs_device; struct btrfs_fs_devices; +struct btrfs_balance_control; struct btrfs_delayed_root; struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; @@ -1159,6 +1160,11 @@ struct btrfs_fs_info { u64 avail_metadata_alloc_bits; u64 avail_system_alloc_bits; + /* restriper state */ + spinlock_t balance_lock; + struct mutex balance_mutex; + struct btrfs_balance_control *balance_ctl; + unsigned data_chunk_allocations; unsigned metadata_ratio; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ce9d0fb3627d..190a1b24c902 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2002,6 +2002,10 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_rwsem(&fs_info->scrub_super_lock); fs_info->scrub_workers_refcnt = 0; + spin_lock_init(&fs_info->balance_lock); + mutex_init(&fs_info->balance_mutex); + fs_info->balance_ctl = NULL; + sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); sb->s_bdi = &fs_info->bdi; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c04f02c7d5bb..d838d2cfb947 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1203,13 +1203,21 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - mutex_lock(&root->fs_info->volume_mutex); sizestr = vol_args->name; devstr = strchr(sizestr, ':'); if (devstr) { @@ -1226,7 +1234,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, printk(KERN_INFO "btrfs: resizer unable to find device %llu\n", (unsigned long long)devid); ret = -EINVAL; - goto out_unlock; + goto out_free; } if (!strcmp(sizestr, "max")) new_size = device->bdev->bd_inode->i_size; @@ -1241,7 +1249,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, new_size = memparse(sizestr, NULL); if (new_size == 0) { ret = -EINVAL; - goto out_unlock; + goto out_free; } } @@ -1250,7 +1258,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (mod < 0) { if (new_size > old_size) { ret = -EINVAL; - goto out_unlock; + goto out_free; } new_size = old_size - new_size; } else if (mod > 0) { @@ -1259,11 +1267,11 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (new_size < 256 * 1024 * 1024) { ret = -EINVAL; - goto out_unlock; + goto out_free; } if (new_size > device->bdev->bd_inode->i_size) { ret = -EFBIG; - goto out_unlock; + goto out_free; } do_div(new_size, root->sectorsize); @@ -1276,7 +1284,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - goto out_unlock; + goto out_free; } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); @@ -1284,9 +1292,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, ret = btrfs_shrink_device(device, new_size); } -out_unlock: - mutex_unlock(&root->fs_info->volume_mutex); +out_free: kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -2052,14 +2061,25 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; ret = btrfs_init_new_device(root, vol_args->name); kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -2074,14 +2094,25 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg) if (root->fs_info->sb->s_flags & MS_RDONLY) return -EROFS; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; ret = btrfs_rm_device(root, vol_args->name); kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -3034,6 +3065,76 @@ out: return ret; } +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_balance_args *bargs) +{ + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + + bargs->flags = bctl->flags; + + memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); + memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); + memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys)); +} + +static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ioctl_balance_args *bargs; + struct btrfs_balance_control *bctl; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (fs_info->sb->s_flags & MS_RDONLY) + return -EROFS; + + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + if (arg) { + bargs = memdup_user(arg, sizeof(*bargs)); + if (IS_ERR(bargs)) { + ret = PTR_ERR(bargs); + goto out; + } + } else { + bargs = NULL; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out_bargs; + } + + bctl->fs_info = fs_info; + if (arg) { + memcpy(&bctl->data, &bargs->data, sizeof(bctl->data)); + memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta)); + memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys)); + + bctl->flags = bargs->flags; + } + + ret = btrfs_balance(bctl, bargs); + /* + * bctl is freed in __cancel_balance + */ + if (arg) { + if (copy_to_user(arg, bargs, sizeof(*bargs))) + ret = -EFAULT; + } + +out_bargs: + kfree(bargs); +out: + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -3078,7 +3179,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(root, argp); case BTRFS_IOC_BALANCE: - return btrfs_balance(root->fs_info->dev_root); + return btrfs_ioctl_balance(root, NULL); case BTRFS_IOC_CLONE: return btrfs_ioctl_clone(file, arg, 0, 0, 0); case BTRFS_IOC_CLONE_RANGE: @@ -3110,6 +3211,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_scrub_cancel(root, argp); case BTRFS_IOC_SCRUB_PROGRESS: return btrfs_ioctl_scrub_progress(root, argp); + case BTRFS_IOC_BALANCE_V2: + return btrfs_ioctl_balance(root, argp); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 252ae9915de8..c8b37d2c0d77 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -109,6 +109,47 @@ struct btrfs_ioctl_fs_info_args { __u64 reserved[124]; /* pad to 1k */ }; +/* + * this is packed, because it should be exactly the same as its disk + * byte order counterpart (struct btrfs_disk_balance_args) + */ +struct btrfs_balance_args { + __u64 profiles; + __u64 usage; + __u64 devid; + __u64 pstart; + __u64 pend; + __u64 vstart; + __u64 vend; + + __u64 target; + + __u64 flags; + + __u64 unused[8]; +} __attribute__ ((__packed__)); + +/* report balance progress to userspace */ +struct btrfs_balance_progress { + __u64 expected; /* estimated # of chunks that will be + * relocated to fulfill the request */ + __u64 considered; /* # of chunks we have considered so far */ + __u64 completed; /* # of chunks relocated so far */ +}; + +struct btrfs_ioctl_balance_args { + __u64 flags; /* in/out */ + __u64 state; /* out */ + + struct btrfs_balance_args data; /* in/out */ + struct btrfs_balance_args meta; /* in/out */ + struct btrfs_balance_args sys; /* in/out */ + + struct btrfs_balance_progress stat; /* out */ + + __u64 unused[72]; /* pad to 1k */ +}; + #define BTRFS_INO_LOOKUP_PATH_MAX 4080 struct btrfs_ioctl_ino_lookup_args { __u64 treeid; @@ -272,6 +313,8 @@ struct btrfs_ioctl_logical_ino_args { struct btrfs_ioctl_dev_info_args) #define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \ struct btrfs_ioctl_fs_info_args) +#define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \ + struct btrfs_ioctl_balance_args) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d5fdee56777f..9fc06e6bc51a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1282,7 +1282,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) bool clear_super = false; mutex_lock(&uuid_mutex); - mutex_lock(&root->fs_info->volume_mutex); all_avail = root->fs_info->avail_data_alloc_bits | root->fs_info->avail_system_alloc_bits | @@ -1452,7 +1451,6 @@ error_close: if (bdev) blkdev_put(bdev, FMODE_READ | FMODE_EXCL); out: - mutex_unlock(&root->fs_info->volume_mutex); mutex_unlock(&uuid_mutex); return ret; error_undo: @@ -1629,7 +1627,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) } filemap_write_and_wait(bdev->bd_inode->i_mapping); - mutex_lock(&root->fs_info->volume_mutex); devices = &root->fs_info->fs_devices->devices; /* @@ -1757,8 +1754,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_relocate_sys_chunks(root); BUG_ON(ret); } -out: - mutex_unlock(&root->fs_info->volume_mutex); + return ret; error: blkdev_put(bdev, FMODE_EXCL); @@ -1766,7 +1762,7 @@ error: mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); } - goto out; + return ret; } static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, @@ -2077,6 +2073,35 @@ error: return ret; } +/* + * Should be called with both balance and volume mutexes held to + * serialize other volume operations (add_dev/rm_dev/resize) with + * restriper. Same goes for unset_balance_control. + */ +static void set_balance_control(struct btrfs_balance_control *bctl) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + + BUG_ON(fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = bctl; + spin_unlock(&fs_info->balance_lock); +} + +static void unset_balance_control(struct btrfs_fs_info *fs_info) +{ + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + + BUG_ON(!fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = NULL; + spin_unlock(&fs_info->balance_lock); + + kfree(bctl); +} + static u64 div_factor(u64 num, int factor) { if (factor == 10) @@ -2086,29 +2111,23 @@ static u64 div_factor(u64 num, int factor) return num; } -int btrfs_balance(struct btrfs_root *dev_root) +static int __btrfs_balance(struct btrfs_fs_info *fs_info) { - int ret; - struct list_head *devices = &dev_root->fs_info->fs_devices->devices; + struct btrfs_root *chunk_root = fs_info->chunk_root; + struct btrfs_root *dev_root = fs_info->dev_root; + struct list_head *devices; struct btrfs_device *device; u64 old_size; u64 size_to_free; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root; - struct btrfs_trans_handle *trans; struct btrfs_key found_key; - - if (dev_root->fs_info->sb->s_flags & MS_RDONLY) - return -EROFS; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - mutex_lock(&dev_root->fs_info->volume_mutex); - dev_root = dev_root->fs_info->dev_root; + struct btrfs_trans_handle *trans; + int ret; + int enospc_errors = 0; /* step one make some room on all the devices */ + devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { old_size = device->total_bytes; size_to_free = div_factor(old_size, 1); @@ -2151,12 +2170,14 @@ int btrfs_balance(struct btrfs_root *dev_root) * failed */ if (ret == 0) - break; + BUG(); /* FIXME break ? */ ret = btrfs_previous_item(chunk_root, path, 0, BTRFS_CHUNK_ITEM_KEY); - if (ret) + if (ret) { + ret = 0; break; + } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); @@ -2174,12 +2195,63 @@ int btrfs_balance(struct btrfs_root *dev_root) found_key.offset); if (ret && ret != -ENOSPC) goto error; + if (ret == -ENOSPC) + enospc_errors++; key.offset = found_key.offset - 1; } - ret = 0; + error: btrfs_free_path(path); - mutex_unlock(&dev_root->fs_info->volume_mutex); + if (enospc_errors) { + printk(KERN_INFO "btrfs: %d enospc errors during balance\n", + enospc_errors); + if (!ret) + ret = -ENOSPC; + } + + return ret; +} + +static void __cancel_balance(struct btrfs_fs_info *fs_info) +{ + unset_balance_control(fs_info); +} + +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_balance_args *bargs); + +/* + * Should be called with both balance and volume mutexes held + */ +int btrfs_balance(struct btrfs_balance_control *bctl, + struct btrfs_ioctl_balance_args *bargs) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + int ret; + + if (btrfs_fs_closing(fs_info)) { + ret = -EINVAL; + goto out; + } + + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + + ret = __btrfs_balance(fs_info); + + mutex_lock(&fs_info->balance_mutex); + + if (bargs) { + memset(bargs, 0, sizeof(*bargs)); + update_ioctl_balance_args(fs_info, bargs); + } + + __cancel_balance(fs_info); + + return ret; +out: + kfree(bctl); return ret; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 78f2d4d4f37f..882582385283 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -186,6 +186,17 @@ struct map_lookup { #define map_lookup_size(n) (sizeof(struct map_lookup) + \ (sizeof(struct btrfs_bio_stripe) * (n))) +struct btrfs_balance_args; +struct btrfs_balance_control { + struct btrfs_fs_info *fs_info; + + struct btrfs_balance_args data; + struct btrfs_balance_args meta; + struct btrfs_balance_args sys; + + u64 flags; +}; + int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, u64 end, u64 *length); @@ -228,7 +239,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid, u8 *uuid, u8 *fsid); int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); -int btrfs_balance(struct btrfs_root *dev_root); +int btrfs_balance(struct btrfs_balance_control *bctl, + struct btrfs_ioctl_balance_args *bargs); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From 596410151ed71819b9e8a8018c6c9992796b256d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:48 +0200 Subject: Btrfs: recover balance on mount On mount, if balance item is found, resume balance in a separate kernel thread. Try to be smart to continue roughly where previous balance (or convert) was interrupted. For chunk types that were being converted to some profile we turn on soft convert, in case of a simple balance we turn on usage filter and relocate only less-than-90%-full chunks of that type. These are just heuristics but they help quite a bit, and can be improved in future. Signed-off-by: Ilya Dryomov --- fs/btrfs/disk-io.c | 4 ++ fs/btrfs/volumes.c | 135 ++++++++++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/volumes.h | 2 + 3 files changed, 139 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 190a1b24c902..eb7a11ac5b73 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2427,6 +2427,10 @@ retry_root_backup: if (!err) err = btrfs_orphan_cleanup(fs_info->tree_root); up_read(&fs_info->cleanup_work_sem); + + if (!err) + err = btrfs_recover_balance(fs_info->tree_root); + if (err) { close_ctree(tree_root); return ERR_PTR(err); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4c60ca0ae90b..17e565388de0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include "compat.h" #include "ctree.h" @@ -2164,6 +2165,46 @@ out: return ret; } +/* + * This is a heuristic used to reduce the number of chunks balanced on + * resume after balance was interrupted. + */ +static void update_balance_args(struct btrfs_balance_control *bctl) +{ + /* + * Turn on soft mode for chunk types that were being converted. + */ + if (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->data.flags |= BTRFS_BALANCE_ARGS_SOFT; + if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->sys.flags |= BTRFS_BALANCE_ARGS_SOFT; + if (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->meta.flags |= BTRFS_BALANCE_ARGS_SOFT; + + /* + * Turn on usage filter if is not already used. The idea is + * that chunks that we have already balanced should be + * reasonably full. Don't do it for chunks that are being + * converted - that will keep us from relocating unconverted + * (albeit full) chunks. + */ + if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->data.usage = 90; + } + if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->sys.usage = 90; + } + if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->meta.usage = 90; + } +} + /* * Should be called with both balance and volume mutexes held to * serialize other volume operations (add_dev/rm_dev/resize) with @@ -2626,10 +2667,18 @@ int btrfs_balance(struct btrfs_balance_control *bctl, do_balance: ret = insert_balance_item(fs_info->tree_root, bctl); - if (ret) + if (ret && ret != -EEXIST) goto out; - set_balance_control(bctl); + if (!(bctl->flags & BTRFS_BALANCE_RESUME)) { + BUG_ON(ret == -EEXIST); + set_balance_control(bctl); + } else { + BUG_ON(ret != -EEXIST); + spin_lock(&fs_info->balance_lock); + update_balance_args(bctl); + spin_unlock(&fs_info->balance_lock); + } mutex_unlock(&fs_info->balance_mutex); @@ -2646,7 +2695,89 @@ do_balance: return ret; out: + if (bctl->flags & BTRFS_BALANCE_RESUME) + __cancel_balance(fs_info); + else + kfree(bctl); + return ret; +} + +static int balance_kthread(void *data) +{ + struct btrfs_balance_control *bctl = + (struct btrfs_balance_control *)data; + struct btrfs_fs_info *fs_info = bctl->fs_info; + int ret; + + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + set_balance_control(bctl); + + printk(KERN_INFO "btrfs: continuing balance\n"); + ret = btrfs_balance(bctl, NULL); + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); + return ret; +} + +int btrfs_recover_balance(struct btrfs_root *tree_root) +{ + struct task_struct *tsk; + struct btrfs_balance_control *bctl; + struct btrfs_balance_item *item; + struct btrfs_disk_balance_args disk_bargs; + struct btrfs_path *path; + struct extent_buffer *leaf; + struct btrfs_key key; + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; + } + + key.objectid = BTRFS_BALANCE_OBJECTID; + key.type = BTRFS_BALANCE_ITEM_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + if (ret < 0) + goto out_bctl; + if (ret > 0) { /* ret = -ENOENT; */ + ret = 0; + goto out_bctl; + } + + leaf = path->nodes[0]; + item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); + + bctl->fs_info = tree_root->fs_info; + bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + + btrfs_balance_data(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); + btrfs_balance_meta(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->meta, &disk_bargs); + btrfs_balance_sys(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); + + tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); + if (IS_ERR(tsk)) + ret = PTR_ERR(tsk); + else + goto out; + +out_bctl: kfree(bctl); +out: + btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 6c143c98017a..cd25ea58ec35 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -198,6 +198,7 @@ struct map_lookup { BTRFS_BALANCE_METADATA) #define BTRFS_BALANCE_FORCE (1ULL << 3) +#define BTRFS_BALANCE_RESUME (1ULL << 4) /* * Balance filters @@ -271,6 +272,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); +int btrfs_recover_balance(struct btrfs_root *tree_root); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From 837d5b6e46d1a4af5b6cc8f2fe83cb5de79a2961 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: allow for pausing restriper Implement an ioctl for pausing restriper. This pauses the relocation, but balance is still considered to be "in progress": balance item is not deleted, other volume operations cannot be started, etc. If paused in the middle of profile changing operation we will continue making allocations with the target profile. Add a hook to close_ctree() to pause restriper and free its data structures on unmount. (It's safe to unmount when restriper is in "paused" state, we will resume with the same parameters on the next mount) Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 4 ++++ fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/ioctl.c | 28 +++++++++++++++++++++++++++- fs/btrfs/ioctl.h | 7 +++++++ fs/btrfs/volumes.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++-- fs/btrfs/volumes.h | 1 + 6 files changed, 94 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 99eb2bcd9aa7..1afda75d5414 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1214,7 +1214,10 @@ struct btrfs_fs_info { /* restriper state */ spinlock_t balance_lock; struct mutex balance_mutex; + atomic_t balance_running; + atomic_t balance_pause_req; struct btrfs_balance_control *balance_ctl; + wait_queue_head_t balance_wait_q; unsigned data_chunk_allocations; unsigned metadata_ratio; @@ -2658,6 +2661,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) } static inline void free_fs_info(struct btrfs_fs_info *fs_info) { + kfree(fs_info->balance_ctl); kfree(fs_info->delayed_root); kfree(fs_info->extent_root); kfree(fs_info->tree_root); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index eb7a11ac5b73..8ce837407800 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2004,7 +2004,10 @@ struct btrfs_root *open_ctree(struct super_block *sb, spin_lock_init(&fs_info->balance_lock); mutex_init(&fs_info->balance_mutex); + atomic_set(&fs_info->balance_running, 0); + atomic_set(&fs_info->balance_pause_req, 0); fs_info->balance_ctl = NULL; + init_waitqueue_head(&fs_info->balance_wait_q); sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); @@ -2980,6 +2983,9 @@ int close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* pause restriper - we want to resume on mount */ + btrfs_pause_balance(root->fs_info); + btrfs_scrub_cancel(root); /* wait for any defraggers to finish */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 29b3a94933f0..f572c53dda4f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3072,6 +3072,11 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, bargs->flags = bctl->flags; + if (atomic_read(&fs_info->balance_running)) + bargs->state |= BTRFS_BALANCE_STATE_RUNNING; + if (atomic_read(&fs_info->balance_pause_req)) + bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ; + memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys)); @@ -3103,6 +3108,11 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) bargs = NULL; } + if (fs_info->balance_ctl) { + ret = -EINPROGRESS; + goto out_bargs; + } + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); if (!bctl) { ret = -ENOMEM; @@ -3123,7 +3133,8 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) ret = btrfs_balance(bctl, bargs); /* - * bctl is freed in __cancel_balance + * bctl is freed in __cancel_balance or in free_fs_info if + * restriper was paused all the way until unmount */ if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) @@ -3138,6 +3149,19 @@ out: return ret; } +static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd) { + case BTRFS_BALANCE_CTL_PAUSE: + return btrfs_pause_balance(root->fs_info); + } + + return -EINVAL; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -3216,6 +3240,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_scrub_progress(root, argp); case BTRFS_IOC_BALANCE_V2: return btrfs_ioctl_balance(root, argp); + case BTRFS_IOC_BALANCE_CTL: + return btrfs_ioctl_balance_ctl(root, arg); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index c8b37d2c0d77..e972e11a8d77 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -109,6 +109,9 @@ struct btrfs_ioctl_fs_info_args { __u64 reserved[124]; /* pad to 1k */ }; +/* balance control ioctl modes */ +#define BTRFS_BALANCE_CTL_PAUSE 1 + /* * this is packed, because it should be exactly the same as its disk * byte order counterpart (struct btrfs_disk_balance_args) @@ -137,6 +140,9 @@ struct btrfs_balance_progress { __u64 completed; /* # of chunks relocated so far */ }; +#define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0) +#define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1) + struct btrfs_ioctl_balance_args { __u64 flags; /* in/out */ __u64 state; /* out */ @@ -315,6 +321,7 @@ struct btrfs_ioctl_logical_ino_args { struct btrfs_ioctl_fs_info_args) #define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \ struct btrfs_ioctl_balance_args) +#define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e0160607e6e2..d32660ce753d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2492,6 +2492,11 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { + if (atomic_read(&fs_info->balance_pause_req)) { + ret = -ECANCELED; + goto error; + } + ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0); if (ret < 0) goto error; @@ -2553,6 +2558,11 @@ error: return ret; } +static inline int balance_need_close(struct btrfs_fs_info *fs_info) +{ + return atomic_read(&fs_info->balance_pause_req) == 0; +} + static void __cancel_balance(struct btrfs_fs_info *fs_info) { int ret; @@ -2575,7 +2585,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, u64 allowed; int ret; - if (btrfs_fs_closing(fs_info)) { + if (btrfs_fs_closing(fs_info) || + atomic_read(&fs_info->balance_pause_req)) { ret = -EINVAL; goto out; } @@ -2680,18 +2691,25 @@ do_balance: spin_unlock(&fs_info->balance_lock); } + atomic_inc(&fs_info->balance_running); mutex_unlock(&fs_info->balance_mutex); ret = __btrfs_balance(fs_info); mutex_lock(&fs_info->balance_mutex); + atomic_dec(&fs_info->balance_running); if (bargs) { memset(bargs, 0, sizeof(*bargs)); update_ioctl_balance_args(fs_info, bargs); } - __cancel_balance(fs_info); + if ((ret && ret != -ECANCELED && ret != -ENOSPC) || + balance_need_close(fs_info)) { + __cancel_balance(fs_info); + } + + wake_up(&fs_info->balance_wait_q); return ret; out: @@ -2785,6 +2803,35 @@ out: return ret; } +int btrfs_pause_balance(struct btrfs_fs_info *fs_info) +{ + int ret = 0; + + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + if (atomic_read(&fs_info->balance_running)) { + atomic_inc(&fs_info->balance_pause_req); + mutex_unlock(&fs_info->balance_mutex); + + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + + mutex_lock(&fs_info->balance_mutex); + /* we are good with balance_ctl ripped off from under us */ + BUG_ON(atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_pause_req); + } else { + ret = -ENOTCONN; + } + + mutex_unlock(&fs_info->balance_mutex); + return ret; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index cd25ea58ec35..80953afb12b9 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -273,6 +273,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From a7e99c691af553fc15ac46a51f130b7c59a65f76 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: allow for canceling restriper Implement an ioctl for canceling restriper. Currently we wait until relocation of the current block group is finished, in future this can be done by triggering a commit. Balance item is deleted and no memory about the interrupted balance is kept. Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 1 + fs/btrfs/ioctl.c | 4 ++++ fs/btrfs/ioctl.h | 2 ++ fs/btrfs/volumes.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- fs/btrfs/volumes.h | 1 + 6 files changed, 53 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1afda75d5414..dfc136cc07d7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1216,6 +1216,7 @@ struct btrfs_fs_info { struct mutex balance_mutex; atomic_t balance_running; atomic_t balance_pause_req; + atomic_t balance_cancel_req; struct btrfs_balance_control *balance_ctl; wait_queue_head_t balance_wait_q; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8ce837407800..c23b82d8ec08 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2006,6 +2006,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, mutex_init(&fs_info->balance_mutex); atomic_set(&fs_info->balance_running, 0); atomic_set(&fs_info->balance_pause_req, 0); + atomic_set(&fs_info->balance_cancel_req, 0); fs_info->balance_ctl = NULL; init_waitqueue_head(&fs_info->balance_wait_q); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f572c53dda4f..60852217ce9a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3076,6 +3076,8 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, bargs->state |= BTRFS_BALANCE_STATE_RUNNING; if (atomic_read(&fs_info->balance_pause_req)) bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ; + if (atomic_read(&fs_info->balance_cancel_req)) + bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ; memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); @@ -3157,6 +3159,8 @@ static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd) switch (cmd) { case BTRFS_BALANCE_CTL_PAUSE: return btrfs_pause_balance(root->fs_info); + case BTRFS_BALANCE_CTL_CANCEL: + return btrfs_cancel_balance(root->fs_info); } return -EINVAL; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index e972e11a8d77..cd19d10794b9 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -111,6 +111,7 @@ struct btrfs_ioctl_fs_info_args { /* balance control ioctl modes */ #define BTRFS_BALANCE_CTL_PAUSE 1 +#define BTRFS_BALANCE_CTL_CANCEL 2 /* * this is packed, because it should be exactly the same as its disk @@ -142,6 +143,7 @@ struct btrfs_balance_progress { #define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0) #define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1) +#define BTRFS_BALANCE_STATE_CANCEL_REQ (1ULL << 2) struct btrfs_ioctl_balance_args { __u64 flags; /* in/out */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d32660ce753d..c32667318ae4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2492,7 +2492,8 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { - if (atomic_read(&fs_info->balance_pause_req)) { + if (atomic_read(&fs_info->balance_pause_req) || + atomic_read(&fs_info->balance_cancel_req)) { ret = -ECANCELED; goto error; } @@ -2560,7 +2561,10 @@ error: static inline int balance_need_close(struct btrfs_fs_info *fs_info) { - return atomic_read(&fs_info->balance_pause_req) == 0; + /* cancel requested || normal exit path */ + return atomic_read(&fs_info->balance_cancel_req) || + (atomic_read(&fs_info->balance_pause_req) == 0 && + atomic_read(&fs_info->balance_cancel_req) == 0); } static void __cancel_balance(struct btrfs_fs_info *fs_info) @@ -2586,7 +2590,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, int ret; if (btrfs_fs_closing(fs_info) || - atomic_read(&fs_info->balance_pause_req)) { + atomic_read(&fs_info->balance_pause_req) || + atomic_read(&fs_info->balance_cancel_req)) { ret = -EINVAL; goto out; } @@ -2832,6 +2837,42 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info) return ret; } +int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) +{ + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + atomic_inc(&fs_info->balance_cancel_req); + /* + * if we are running just wait and return, balance item is + * deleted in btrfs_balance in this case + */ + if (atomic_read(&fs_info->balance_running)) { + mutex_unlock(&fs_info->balance_mutex); + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + mutex_lock(&fs_info->balance_mutex); + } else { + /* __cancel_balance needs volume_mutex */ + mutex_unlock(&fs_info->balance_mutex); + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + if (fs_info->balance_ctl) + __cancel_balance(fs_info); + + mutex_unlock(&fs_info->volume_mutex); + } + + BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_cancel_req); + mutex_unlock(&fs_info->balance_mutex); + return 0; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 80953afb12b9..caa9abd218ef 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -274,6 +274,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); int btrfs_recover_balance(struct btrfs_root *tree_root); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); +int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From 0c4e538bccc106872d31b1514570b4dac95fb7f2 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 26 Jan 2012 15:01:12 -0500 Subject: btrfs: mask out gfp flags in releasepage btree_releasepage is a callback and can be passed unknown gfp flags and then they may end up in kmem_cache_alloc called from alloc_extent_state, slab allocator will BUG_ON when there is HIGHMEM or DMA32 flag set. This may happen when btrfs is mounted from a loop device, which masks out __GFP_IO flag. The check in try_release_extent_state 3399 if ((mask & GFP_NOFS) == GFP_NOFS) 3400 mask = GFP_NOFS; will not work and passes unfiltered flags further resulting in crash at mm/slab.c:2963 [<000000000024ae4c>] cache_alloc_refill+0x3b4/0x5c8 [<000000000024c810>] kmem_cache_alloc+0x204/0x294 [<00000000001fd3c2>] mempool_alloc+0x52/0x170 [<000003c000ced0b0>] alloc_extent_state+0x40/0xd4 [btrfs] [<000003c000cee5ae>] __clear_extent_bit+0x38a/0x4cc [btrfs] [<000003c000cee78c>] try_release_extent_state+0x9c/0xd4 [btrfs] [<000003c000cc4c66>] btree_releasepage+0x7e/0xd0 [btrfs] [<0000000000210d84>] shrink_page_list+0x6a0/0x724 [<0000000000211394>] shrink_inactive_list+0x230/0x578 [<0000000000211bb8>] shrink_list+0x6c/0x120 [<0000000000211e4e>] shrink_zone+0x1e2/0x228 [<0000000000211f24>] shrink_zones+0x90/0x254 [<0000000000213410>] do_try_to_free_pages+0xac/0x420 [<0000000000213ae0>] try_to_free_pages+0x13c/0x1b0 [<0000000000204e6c>] __alloc_pages_nodemask+0x5b4/0x9a8 [<00000000001fb04a>] grab_cache_page_write_begin+0x7e/0xe8 Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index da4457f84d78..4c867112b4c8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -961,6 +961,13 @@ static int btree_releasepage(struct page *page, gfp_t gfp_flags) tree = &BTRFS_I(page->mapping->host)->io_tree; map = &BTRFS_I(page->mapping->host)->extent_tree; + /* + * We need to mask out eg. __GFP_HIGHMEM and __GFP_DMA32 as we're doing + * slab allocation from alloc_extent_state down the callchain where + * it'd hit a BUG_ON as those flags are not allowed. + */ + gfp_flags &= ~GFP_SLAB_BUG_MASK; + ret = try_release_extent_state(map, tree, page, gfp_flags); if (!ret) return 0; -- cgit v1.2.3 From 941b2ddf71987ef369389517a7e215dd505fe01e Mon Sep 17 00:00:00 2001 From: Keith Mannthey Date: Tue, 29 Nov 2011 17:44:12 -0800 Subject: btrfs: Sector Size check during Mount Gracefully fail when trying to mount a BTRFS file system that has a sectorsize smaller than PAGE_SIZE. On PPC it is possible to build a FS while using a 4k PAGE_SIZE kernel then boot into a 64K PAGE_SIZE kernel. Presently open_ctree fails in an endless loop and hangs the machine in this situation. My debugging has show this Sector size < Page size to be a non trivial situation and a graceful exit from the situation would be nice for the time being. Signed-off-by: Keith Mannthey --- fs/btrfs/disk-io.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4c867112b4c8..58d0678dfcba 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2258,6 +2258,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, goto fail_sb_buffer; } + if (sectorsize < PAGE_SIZE) { + printk(KERN_WARNING "btrfs: Incompatible sector size " + "found on %s\n", sb->s_id); + goto fail_sb_buffer; + } + mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_sys_array(tree_root); mutex_unlock(&fs_info->chunk_mutex); -- cgit v1.2.3 From a6b0d5c8dbfd428717fc4db4c36757783f391c7b Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Mon, 20 Feb 2012 20:53:43 -0500 Subject: Btrfs: make sure we update latest_bdev When we are setting up the mount, we close all the devices that were not actually part of the metadata we found. But, we don't make sure that one of those devices wasn't fs_devices->latest_bdev, which means we can do a use after free on the one we closed. This updates latest_bdev as it goes. Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/volumes.c | 17 ++++++++++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 58d0678dfcba..b801d29f3f10 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2305,6 +2305,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_close_extra_devices(fs_devices); + if (!fs_devices->latest_bdev) { + printk(KERN_CRIT "btrfs: failed to read devices on %s\n", + sb->s_id); + goto fail_tree_roots; + } + retry_root_backup: blocksize = btrfs_level_size(tree_root, btrfs_super_root_level(disk_super)); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cd040bf3fd87..7eefdef8a14c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -459,12 +459,23 @@ int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device, *next; + struct block_device *latest_bdev = NULL; + u64 latest_devid = 0; + u64 latest_transid = 0; + mutex_lock(&uuid_mutex); again: /* This is the initialized path, it is safe to release the devices. */ list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) { - if (device->in_fs_metadata) + if (device->in_fs_metadata) { + if (!latest_transid || + device->generation > latest_transid) { + latest_devid = device->devid; + latest_transid = device->generation; + latest_bdev = device->bdev; + } continue; + } if (device->bdev) { blkdev_put(device->bdev, device->mode); @@ -487,6 +498,10 @@ again: goto again; } + fs_devices->latest_bdev = latest_bdev; + fs_devices->latest_devid = latest_devid; + fs_devices->latest_trans = latest_transid; + mutex_unlock(&uuid_mutex); return 0; } -- cgit v1.2.3