From 26bdef541d26fd6a5ddffdf8949ace22f94f809f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 16 Nov 2011 11:28:01 +0300
Subject: btrfs scrub: handle -ENOMEM from init_ipath()

init_ipath() can return an ERR_PTR(-ENOMEM).

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
 fs/btrfs/scrub.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'fs/btrfs/scrub.c')

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fab420db5121..c27bcb67f330 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
 	btrfs_release_path(swarn->path);
 
 	ipath = init_ipath(4096, local_root, swarn->path);
+	if (IS_ERR(ipath)) {
+		ret = PTR_ERR(ipath);
+		ipath = NULL;
+		goto err;
+	}
 	ret = paths_from_inode(inum, ipath);
 
 	if (ret < 0)
-- 
cgit v1.2.3


From 0dc3b84a73267f47a75468f924f5d58a840e3152 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
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 <josef@redhat.com>
---
 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/scrub.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 <sbehrens@giantdisaster.de>
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 <sbehrens@giantdisaster.de>
---
 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/scrub.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 4692cf58aa7b81f721c1653d48db99ea41421d58 Mon Sep 17 00:00:00 2001
From: Jan Schmidt <list.btrfs@jan-o-sch.net>
Date: Fri, 2 Dec 2011 14:56:41 +0100
Subject: Btrfs: new backref walking code

The old backref iteration code could only safely be used on commit roots.
Besides this limitation, it had bugs in finding the roots for these
references. This commit replaces large parts of it by btrfs_find_all_roots()
which a) really finds all roots and the correct roots, b) works correctly
under heavy file system load, c) considers delayed refs.

Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
---
 fs/btrfs/backref.c | 354 +++++++++++++++--------------------------------------
 fs/btrfs/ioctl.c   |   8 +-
 fs/btrfs/scrub.c   |   7 +-
 3 files changed, 107 insertions(+), 262 deletions(-)

(limited to 'fs/btrfs/scrub.c')

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 03c30a1836f4..b9a843226de8 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -23,18 +23,6 @@
 #include "transaction.h"
 #include "delayed-ref.h"
 
-struct __data_ref {
-	struct list_head list;
-	u64 inum;
-	u64 root;
-	u64 extent_data_item_offset;
-};
-
-struct __shared_ref {
-	struct list_head list;
-	u64 disk_byte;
-};
-
 /*
  * this structure records all encountered refs on the way up to the root
  */
@@ -964,8 +952,11 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
 	if (found_key->type != BTRFS_EXTENT_ITEM_KEY ||
 	    found_key->objectid > logical ||
-	    found_key->objectid + found_key->offset <= logical)
+	    found_key->objectid + found_key->offset <= logical) {
+		pr_debug("logical %llu is not within any extent\n",
+			 (unsigned long long)logical);
 		return -ENOENT;
+	}
 
 	eb = path->nodes[0];
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
@@ -974,6 +965,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
 
+	pr_debug("logical %llu is at position %llu within the extent (%llu "
+		 "EXTENT_ITEM %llu) flags %#llx size %u\n",
+		 (unsigned long long)logical,
+		 (unsigned long long)(logical - found_key->objectid),
+		 (unsigned long long)found_key->objectid,
+		 (unsigned long long)found_key->offset,
+		 (unsigned long long)flags, item_size);
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		return BTRFS_EXTENT_FLAG_TREE_BLOCK;
 	if (flags & BTRFS_EXTENT_FLAG_DATA)
@@ -1070,128 +1068,11 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 	return 0;
 }
 
-static int __data_list_add(struct list_head *head, u64 inum,
-				u64 extent_data_item_offset, u64 root)
-{
-	struct __data_ref *ref;
-
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	ref->inum = inum;
-	ref->extent_data_item_offset = extent_data_item_offset;
-	ref->root = root;
-	list_add_tail(&ref->list, head);
-
-	return 0;
-}
-
-static int __data_list_add_eb(struct list_head *head, struct extent_buffer *eb,
-				struct btrfs_extent_data_ref *dref)
-{
-	return __data_list_add(head, btrfs_extent_data_ref_objectid(eb, dref),
-				btrfs_extent_data_ref_offset(eb, dref),
-				btrfs_extent_data_ref_root(eb, dref));
-}
-
-static int __shared_list_add(struct list_head *head, u64 disk_byte)
-{
-	struct __shared_ref *ref;
-
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	ref->disk_byte = disk_byte;
-	list_add_tail(&ref->list, head);
-
-	return 0;
-}
-
-static int __iter_shared_inline_ref_inodes(struct btrfs_fs_info *fs_info,
-					   u64 logical, u64 inum,
-					   u64 extent_data_item_offset,
-					   u64 extent_offset,
-					   struct btrfs_path *path,
-					   struct list_head *data_refs,
-					   iterate_extent_inodes_t *iterate,
-					   void *ctx)
-{
-	u64 ref_root;
-	u32 item_size;
-	struct btrfs_key key;
-	struct extent_buffer *eb;
-	struct btrfs_extent_item *ei;
-	struct btrfs_extent_inline_ref *eiref;
-	struct __data_ref *ref;
-	int ret;
-	int type;
-	int last;
-	unsigned long ptr = 0;
-
-	WARN_ON(!list_empty(data_refs));
-	ret = extent_from_logical(fs_info, logical, path, &key);
-	if (ret & BTRFS_EXTENT_FLAG_DATA)
-		ret = -EIO;
-	if (ret < 0)
-		goto out;
-
-	eb = path->nodes[0];
-	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
-	item_size = btrfs_item_size_nr(eb, path->slots[0]);
-
-	ret = 0;
-	ref_root = 0;
-	/*
-	 * as done in iterate_extent_inodes, we first build a list of refs to
-	 * iterate, then free the path and then iterate them to avoid deadlocks.
-	 */
-	do {
-		last = __get_extent_inline_ref(&ptr, eb, ei, item_size,
-						&eiref, &type);
-		if (last < 0) {
-			ret = last;
-			goto out;
-		}
-		if (type == BTRFS_TREE_BLOCK_REF_KEY ||
-		    type == BTRFS_SHARED_BLOCK_REF_KEY) {
-			ref_root = btrfs_extent_inline_ref_offset(eb, eiref);
-			ret = __data_list_add(data_refs, inum,
-						extent_data_item_offset,
-						ref_root);
-		}
-	} while (!ret && !last);
-
-	btrfs_release_path(path);
-
-	if (ref_root == 0) {
-		printk(KERN_ERR "btrfs: failed to find tree block ref "
-			"for shared data backref %llu\n", logical);
-		WARN_ON(1);
-		ret = -EIO;
-	}
-
-out:
-	while (!list_empty(data_refs)) {
-		ref = list_first_entry(data_refs, struct __data_ref, list);
-		list_del(&ref->list);
-		if (!ret)
-			ret = iterate(ref->inum, extent_offset +
-					ref->extent_data_item_offset,
-					ref->root, ctx);
-		kfree(ref);
-	}
-
-	return ret;
-}
-
-static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
-				    u64 logical, u64 orig_extent_item_objectid,
-				    u64 extent_offset, struct btrfs_path *path,
-				    struct list_head *data_refs,
-				    iterate_extent_inodes_t *iterate,
-				    void *ctx)
+static int iterate_leaf_refs(struct btrfs_fs_info *fs_info,
+				struct btrfs_path *path, u64 logical,
+				u64 orig_extent_item_objectid,
+				u64 extent_item_pos, u64 root,
+				iterate_extent_inodes_t *iterate, void *ctx)
 {
 	u64 disk_byte;
 	struct btrfs_key key;
@@ -1199,8 +1080,10 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *eb;
 	int slot;
 	int nritems;
-	int ret;
-	int found = 0;
+	int ret = 0;
+	int extent_type;
+	u64 data_offset;
+	u64 data_len;
 
 	eb = read_tree_block(fs_info->tree_root, logical,
 				fs_info->tree_root->leafsize, 0);
@@ -1218,149 +1101,99 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
 		if (key.type != BTRFS_EXTENT_DATA_KEY)
 			continue;
 		fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
-		if (!fi) {
-			free_extent_buffer(eb);
-			return -EIO;
-		}
+		extent_type = btrfs_file_extent_type(eb, fi);
+		if (extent_type == BTRFS_FILE_EXTENT_INLINE)
+			continue;
+		/* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */
 		disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
-		if (disk_byte != orig_extent_item_objectid) {
-			if (found)
-				break;
-			else
-				continue;
-		}
-		++found;
-		ret = __iter_shared_inline_ref_inodes(fs_info, logical,
-							key.objectid,
-							key.offset,
-							extent_offset, path,
-							data_refs,
-							iterate, ctx);
-		if (ret)
-			break;
-	}
+		if (disk_byte != orig_extent_item_objectid)
+			continue;
 
-	if (!found) {
-		printk(KERN_ERR "btrfs: failed to follow shared data backref "
-			"to parent %llu\n", logical);
-		WARN_ON(1);
-		ret = -EIO;
+		data_offset = btrfs_file_extent_offset(eb, fi);
+		data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+		if (extent_item_pos < data_offset ||
+		    extent_item_pos >= data_offset + data_len)
+			continue;
+
+		pr_debug("ref for %llu resolved, key (%llu EXTEND_DATA %llu), "
+				"root %llu\n", orig_extent_item_objectid,
+				key.objectid, key.offset, root);
+		ret = iterate(key.objectid,
+				key.offset + (extent_item_pos - data_offset),
+				root, ctx);
+		if (ret) {
+			pr_debug("stopping iteration because ret=%d\n", ret);
+			break;
+		}
 	}
 
 	free_extent_buffer(eb);
+
 	return ret;
 }
 
 /*
  * calls iterate() for every inode that references the extent identified by
- * the given parameters. will use the path given as a parameter and return it
- * released.
+ * the given parameters.
  * when the iterator function returns a non-zero value, iteration stops.
+ * path is guaranteed to be in released state when iterate() is called.
  */
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path,
-				u64 extent_item_objectid,
-				u64 extent_offset,
+				u64 extent_item_objectid, u64 extent_item_pos,
 				iterate_extent_inodes_t *iterate, void *ctx)
 {
-	unsigned long ptr = 0;
-	int last;
 	int ret;
-	int type;
-	u64 logical;
-	u32 item_size;
-	struct btrfs_extent_inline_ref *eiref;
-	struct btrfs_extent_data_ref *dref;
-	struct extent_buffer *eb;
-	struct btrfs_extent_item *ei;
-	struct btrfs_key key;
 	struct list_head data_refs = LIST_HEAD_INIT(data_refs);
 	struct list_head shared_refs = LIST_HEAD_INIT(shared_refs);
-	struct __data_ref *ref_d;
-	struct __shared_ref *ref_s;
+	struct btrfs_trans_handle *trans;
+	struct ulist *refs;
+	struct ulist *roots;
+	struct ulist_node *ref_node = NULL;
+	struct ulist_node *root_node = NULL;
+	struct seq_list seq_elem;
+	struct btrfs_delayed_ref_root *delayed_refs;
 
-	eb = path->nodes[0];
-	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
-	item_size = btrfs_item_size_nr(eb, path->slots[0]);
-
-	/* first we iterate the inline refs, ... */
-	do {
-		last = __get_extent_inline_ref(&ptr, eb, ei, item_size,
-						&eiref, &type);
-		if (last == -ENOENT) {
-			ret = 0;
-			break;
-		}
-		if (last < 0) {
-			ret = last;
-			break;
-		}
+	trans = btrfs_join_transaction(fs_info->extent_root);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
-		if (type == BTRFS_EXTENT_DATA_REF_KEY) {
-			dref = (struct btrfs_extent_data_ref *)(&eiref->offset);
-			ret = __data_list_add_eb(&data_refs, eb, dref);
-		} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
-			logical = btrfs_extent_inline_ref_offset(eb, eiref);
-			ret = __shared_list_add(&shared_refs, logical);
-		}
-	} while (!ret && !last);
+	pr_debug("resolving all inodes for extent %llu\n",
+			extent_item_objectid);
 
-	/* ... then we proceed to in-tree references and ... */
-	while (!ret) {
-		++path->slots[0];
-		if (path->slots[0] > btrfs_header_nritems(eb)) {
-			ret = btrfs_next_leaf(fs_info->extent_root, path);
-			if (ret) {
-				if (ret == 1)
-					ret = 0; /* we're done */
-				break;
-			}
-			eb = path->nodes[0];
-		}
-		btrfs_item_key_to_cpu(eb, &key, path->slots[0]);
-		if (key.objectid != extent_item_objectid)
-			break;
-		if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
-			dref = btrfs_item_ptr(eb, path->slots[0],
-						struct btrfs_extent_data_ref);
-			ret = __data_list_add_eb(&data_refs, eb, dref);
-		} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
-			ret = __shared_list_add(&shared_refs, key.offset);
-		}
-	}
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+	btrfs_get_delayed_seq(delayed_refs, &seq_elem);
+	spin_unlock(&delayed_refs->lock);
 
-	btrfs_release_path(path);
+	ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
+				   extent_item_pos, seq_elem.seq,
+				   &refs);
 
-	/*
-	 * ... only at the very end we can process the refs we found. this is
-	 * because the iterator function we call is allowed to make tree lookups
-	 * and we have to avoid deadlocks. additionally, we need more tree
-	 * lookups ourselves for shared data refs.
-	 */
-	while (!list_empty(&data_refs)) {
-		ref_d = list_first_entry(&data_refs, struct __data_ref, list);
-		list_del(&ref_d->list);
-		if (!ret)
-			ret = iterate(ref_d->inum, extent_offset +
-					ref_d->extent_data_item_offset,
-					ref_d->root, ctx);
-		kfree(ref_d);
-	}
+	if (ret)
+		goto out;
 
-	while (!list_empty(&shared_refs)) {
-		ref_s = list_first_entry(&shared_refs, struct __shared_ref,
-					list);
-		list_del(&ref_s->list);
-		if (!ret)
-			ret = __iter_shared_inline_ref(fs_info,
-							ref_s->disk_byte,
-							extent_item_objectid,
-							extent_offset, path,
-							&data_refs,
-							iterate, ctx);
-		kfree(ref_s);
+	while (!ret && (ref_node = ulist_next(refs, ref_node))) {
+		ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, -1,
+						seq_elem.seq, &roots);
+		if (ret)
+			break;
+		while (!ret && (root_node = ulist_next(roots, root_node))) {
+			pr_debug("root %llu references leaf %llu\n",
+					root_node->val, ref_node->val);
+			ret = iterate_leaf_refs(fs_info, path, ref_node->val,
+						extent_item_objectid,
+						extent_item_pos, root_node->val,
+						iterate, ctx);
+		}
 	}
 
+	ulist_free(refs);
+	ulist_free(roots);
+out:
+	btrfs_put_delayed_seq(delayed_refs, &seq_elem);
+	btrfs_end_transaction(trans, fs_info->extent_root);
 	return ret;
 }
 
@@ -1369,19 +1202,20 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 				iterate_extent_inodes_t *iterate, void *ctx)
 {
 	int ret;
-	u64 offset;
+	u64 extent_item_pos;
 	struct btrfs_key found_key;
 
 	ret = extent_from_logical(fs_info, logical, path,
 					&found_key);
+	btrfs_release_path(path);
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		ret = -EINVAL;
 	if (ret < 0)
 		return ret;
 
-	offset = logical - found_key.objectid;
+	extent_item_pos = logical - found_key.objectid;
 	ret = iterate_extent_inodes(fs_info, path, found_key.objectid,
-					offset, iterate, ctx);
+					extent_item_pos, iterate, ctx);
 
 	return ret;
 }
@@ -1426,6 +1260,10 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 		for (cur = 0; cur < btrfs_item_size(eb, item); cur += len) {
 			name_len = btrfs_inode_ref_name_len(eb, iref);
 			/* path must be released before calling iterate()! */
+			pr_debug("following ref at offset %u for inode %llu in "
+				 "tree %llu\n", cur,
+				 (unsigned long long)found_key.objectid,
+				 (unsigned long long)fs_root->objectid);
 			ret = iterate(parent, iref, eb, ctx);
 			if (ret) {
 				free_extent_buffer(eb);
@@ -1466,10 +1304,14 @@ static int inode_to_path(u64 inum, struct btrfs_inode_ref *iref,
 		return PTR_ERR(fspath);
 
 	if (fspath > fspath_min) {
+		pr_debug("path resolved: %s\n", fspath);
 		ipath->fspath->val[i] = (u64)(unsigned long)fspath;
 		++ipath->fspath->elem_cnt;
 		ipath->fspath->bytes_left = fspath - fspath_min;
 	} else {
+		pr_debug("missed path, not enough space. missing bytes: %lu, "
+			 "constructed so far: %s\n",
+			 (unsigned long)(fspath_min - fspath), fspath_min);
 		++ipath->fspath->elem_missed;
 		ipath->fspath->bytes_missing += fspath_min - fspath;
 		ipath->fspath->bytes_left = 0;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c48f2e931ea0..9b0526872b7b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2976,7 +2976,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 {
 	int ret = 0;
 	int size;
-	u64 extent_offset;
+	u64 extent_item_pos;
 	struct btrfs_ioctl_logical_ino_args *loi;
 	struct btrfs_data_container *inodes = NULL;
 	struct btrfs_path *path = NULL;
@@ -3007,15 +3007,17 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 	}
 
 	ret = extent_from_logical(root->fs_info, loi->logical, path, &key);
+	btrfs_release_path(path);
 
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		ret = -ENOENT;
 	if (ret < 0)
 		goto out;
 
-	extent_offset = loi->logical - key.objectid;
+	extent_item_pos = loi->logical - key.objectid;
 	ret = iterate_extent_inodes(root->fs_info, path, key.objectid,
-					extent_offset, build_ino_list, inodes);
+					extent_item_pos, build_ino_list,
+					inodes);
 
 	if (ret < 0)
 		goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index c27bcb67f330..b5edff25a53f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -309,7 +309,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	u8 ref_level;
 	unsigned long ptr = 0;
 	const int bufsize = 4096;
-	u64 extent_offset;
+	u64 extent_item_pos;
 
 	path = btrfs_alloc_path();
 
@@ -329,12 +329,13 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	if (ret < 0)
 		goto out;
 
-	extent_offset = swarn.logical - found_key.objectid;
+	extent_item_pos = swarn.logical - found_key.objectid;
 	swarn.extent_item_size = found_key.offset;
 
 	eb = path->nodes[0];
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
+	btrfs_release_path(path);
 
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
@@ -351,7 +352,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	} else {
 		swarn.path = path;
 		iterate_extent_inodes(fs_info, path, found_key.objectid,
-					extent_offset,
+					extent_item_pos,
 					scrub_print_warning_inode, &swarn);
 	}
 
-- 
cgit v1.2.3


From 859acaf1a29bbacf6256f1159210c8d6df992b33 Mon Sep 17 00:00:00 2001
From: Arne Jansen <sensille@gmx.net>
Date: Thu, 9 Feb 2012 15:09:02 +0100
Subject: btrfs: don't check DUP chunks twice

Because scrub enumerates the dev extent tree to find the chunks to scrub,
it currently finds each DUP chunk twice and also scrubs it twice. This
patch makes sure that scrub_chunk only checks that part of the chunk the
dev extent has been found for. This only changes the behaviour for DUP
chunks.

Reported-and-tested-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Arne Jansen <sensille@gmx.net>
---
 fs/btrfs/scrub.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'fs/btrfs/scrub.c')

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9770cc5bfb76..abc0fbffa510 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1367,7 +1367,8 @@ out:
 }
 
 static noinline_for_stack int scrub_chunk(struct scrub_dev *sdev,
-	u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 length)
+	u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 length,
+	u64 dev_offset)
 {
 	struct btrfs_mapping_tree *map_tree =
 		&sdev->dev->dev_root->fs_info->mapping_tree;
@@ -1391,7 +1392,8 @@ static noinline_for_stack int scrub_chunk(struct scrub_dev *sdev,
 		goto out;
 
 	for (i = 0; i < map->num_stripes; ++i) {
-		if (map->stripes[i].dev == sdev->dev) {
+		if (map->stripes[i].dev == sdev->dev &&
+		    map->stripes[i].physical == dev_offset) {
 			ret = scrub_stripe(sdev, map, i, chunk_offset, length);
 			if (ret)
 				goto out;
@@ -1487,7 +1489,7 @@ int scrub_enumerate_chunks(struct scrub_dev *sdev, u64 start, u64 end)
 			break;
 		}
 		ret = scrub_chunk(sdev, chunk_tree, chunk_objectid,
-				  chunk_offset, length);
+				  chunk_offset, length, found_key.offset);
 		btrfs_put_block_group(cache);
 		if (ret)
 			break;
-- 
cgit v1.2.3