Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "This includes a fairly large change from Josef around data writeback
  completion.  Before, the writeback wasn't completed until the metadata
  insertions for the extent were done, and this made for fairly large
  latency spikes on the last page of each ordered extent.

  We already had a separate mechanism for tracking pending metadata
  insertions, so Josef just needed to tweak things a little to end
  writeback earlier on the page.  Overall it makes us much friendly to
  memory reclaim and lowers latencies quite a lot for synchronous IO.

  Jan Schmidt has finished some background work required to track btree
  blocks as they go through changes in ownership.  It's the missing
  piece he needed for both btrfs send/receive and subvolume quotas.
  Neither of those are ready yet, but the new tracking code is included
  here.  Most of the time, the new code is off.  It is only used by
  scrub and other backref walkers.

  Stefan Behrens has added io failure tracking.  This includes counters
  for which drives are causing the most trouble so the admin (or an
  automated tool) can choose to kick them out.  We're tracking IO
  errors, crc errors, and generation checks we do on each metadata
  block.

  RAID5/6 did miss the cut this time because I'm having trouble with
  corruptions.  I'll nail it down next week and post as a beta testing
  before 3.6"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (58 commits)
  Btrfs: fix tree mod log rewinded level and rewinding of moved keys
  Btrfs: fix tree mod log del_ptr
  Btrfs: add tree_mod_dont_log helper
  Btrfs: add missing spin_lock for insertion into tree mod log
  Btrfs: add inodes before dropping the extent lock in find_all_leafs
  Btrfs: use delayed ref sequence numbers for all fs-tree updates
  Btrfs: fix false positive in check-integrity on unmount
  Btrfs: fix runtime warning in check-integrity check data mode
  Btrfs: set ioprio of scrub readahead to idle
  Btrfs: fix return code in drop_objectid_items
  Btrfs: check to see if the inode is in the log before fsyncing
  Btrfs: return value of btrfs_read_buffer is checked correctly
  Btrfs: read device stats on mount, write modified ones during commit
  Btrfs: add ioctl to get and reset the device stats
  Btrfs: add device counters for detected IO and checksum errors
  btrfs: Drop unused function btrfs_abort_devices()
  Btrfs: fix the same inode id problem when doing auto defragment
  Btrfs: fall back to non-inline if we don't have enough space
  Btrfs: fix how we deal with the orphan block rsv
  Btrfs: convert the inode bit field to use the actual bit operations
  ...

1 files changed, 303 insertions, 3 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1411b99555a4..7782020996fe 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -23,6 +23,7 @@
 #include <linux/random.h>
 #include <linux/iocontext.h>
 #include <linux/capability.h>
+#include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <asm/div64.h>
 #include "compat.h"
@@ -39,6 +40,8 @@ static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				struct btrfs_device *device);
 static int btrfs_relocate_sys_chunks(struct btrfs_root *root);
+static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
+static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
 
 static DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
@@ -361,6 +364,7 @@ static noinline int device_list_add(const char *path,
 			return -ENOMEM;
 		}
 		device->devid = devid;
+		device->dev_stats_valid = 0;
 		device->work.func = pending_bios_fn;
 		memcpy(device->uuid, disk_super->dev_item.uuid,
 		       BTRFS_UUID_SIZE);
@@ -1633,7 +1637,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	int ret = 0;
 
 	if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
-		return -EINVAL;
+		return -EROFS;
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
 				  root->fs_info->bdev_holder);
@@ -4001,13 +4005,58 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	return 0;
 }
 
+static void *merge_stripe_index_into_bio_private(void *bi_private,
+						 unsigned int stripe_index)
+{
+	/*
+	 * with single, dup, RAID0, RAID1 and RAID10, stripe_index is
+	 * at most 1.
+	 * The alternative solution (instead of stealing bits from the
+	 * pointer) would be to allocate an intermediate structure
+	 * that contains the old private pointer plus the stripe_index.
+	 */
+	BUG_ON((((uintptr_t)bi_private) & 3) != 0);
+	BUG_ON(stripe_index > 3);
+	return (void *)(((uintptr_t)bi_private) | stripe_index);
+}
+
+static struct btrfs_bio *extract_bbio_from_bio_private(void *bi_private)
+{
+	return (struct btrfs_bio *)(((uintptr_t)bi_private) & ~((uintptr_t)3));
+}
+
+static unsigned int extract_stripe_index_from_bio_private(void *bi_private)
+{
+	return (unsigned int)((uintptr_t)bi_private) & 3;
+}
+
 static void btrfs_end_bio(struct bio *bio, int err)
 {
-	struct btrfs_bio *bbio = bio->bi_private;
+	struct btrfs_bio *bbio = extract_bbio_from_bio_private(bio->bi_private);
 	int is_orig_bio = 0;
 
-	if (err)
+	if (err) {
 		atomic_inc(&bbio->error);
+		if (err == -EIO || err == -EREMOTEIO) {
+			unsigned int stripe_index =
+				extract_stripe_index_from_bio_private(
+					bio->bi_private);
+			struct btrfs_device *dev;
+
+			BUG_ON(stripe_index >= bbio->num_stripes);
+			dev = bbio->stripes[stripe_index].dev;
+			if (bio->bi_rw & WRITE)
+				btrfs_dev_stat_inc(dev,
+						   BTRFS_DEV_STAT_WRITE_ERRS);
+			else
+				btrfs_dev_stat_inc(dev,
+						   BTRFS_DEV_STAT_READ_ERRS);
+			if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH)
+				btrfs_dev_stat_inc(dev,
+						   BTRFS_DEV_STAT_FLUSH_ERRS);
+			btrfs_dev_stat_print_on_error(dev);
+		}
+	}
 
 	if (bio == bbio->orig_bio)
 		is_orig_bio = 1;
@@ -4149,6 +4198,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 			bio = first_bio;
 		}
 		bio->bi_private = bbio;
+		bio->bi_private = merge_stripe_index_into_bio_private(
+				bio->bi_private, (unsigned int)dev_nr);
 		bio->bi_end_io = btrfs_end_bio;
 		bio->bi_sector = bbio->stripes[dev_nr].physical >> 9;
 		dev = bbio->stripes[dev_nr].dev;
@@ -4509,6 +4560,28 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	return ret;
 }
 
+struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root,
+						   u64 logical, int mirror_num)
+{
+	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
+	int ret;
+	u64 map_length = 0;
+	struct btrfs_bio *bbio = NULL;
+	struct btrfs_device *device;
+
+	BUG_ON(mirror_num == 0);
+	ret = btrfs_map_block(map_tree, WRITE, logical, &map_length, &bbio,
+			      mirror_num);
+	if (ret) {
+		BUG_ON(bbio != NULL);
+		return NULL;
+	}
+	BUG_ON(mirror_num != bbio->mirror_num);
+	device = bbio->stripes[mirror_num - 1].dev;
+	kfree(bbio);
+	return device;
+}
+
 int btrfs_read_chunk_tree(struct btrfs_root *root)
 {
 	struct btrfs_path *path;
@@ -4583,3 +4656,230 @@ error:
 	btrfs_free_path(path);
 	return ret;
 }
+
+static void __btrfs_reset_dev_stats(struct btrfs_device *dev)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
+		btrfs_dev_stat_reset(dev, i);
+}
+
+int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	struct btrfs_root *dev_root = fs_info->dev_root;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct extent_buffer *eb;
+	int slot;
+	int ret = 0;
+	struct btrfs_device *device;
+	struct btrfs_path *path = NULL;
+	int i;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		int item_size;
+		struct btrfs_dev_stats_item *ptr;
+
+		key.objectid = 0;
+		key.type = BTRFS_DEV_STATS_KEY;
+		key.offset = device->devid;
+		ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
+		if (ret) {
+			printk(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n",
+			       device->name, (unsigned long long)device->devid);
+			__btrfs_reset_dev_stats(device);
+			device->dev_stats_valid = 1;
+			btrfs_release_path(path);
+			continue;
+		}
+		slot = path->slots[0];
+		eb = path->nodes[0];
+		btrfs_item_key_to_cpu(eb, &found_key, slot);
+		item_size = btrfs_item_size_nr(eb, slot);
+
+		ptr = btrfs_item_ptr(eb, slot,
+				     struct btrfs_dev_stats_item);
+
+		for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
+			if (item_size >= (1 + i) * sizeof(__le64))
+				btrfs_dev_stat_set(device, i,
+					btrfs_dev_stats_value(eb, ptr, i));
+			else
+				btrfs_dev_stat_reset(device, i);
+		}
+
+		device->dev_stats_valid = 1;
+		btrfs_dev_stat_print_on_load(device);
+		btrfs_release_path(path);
+	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
+out:
+	btrfs_free_path(path);
+	return ret < 0 ? ret : 0;
+}
+
+static int update_dev_stat_item(struct btrfs_trans_handle *trans,
+				struct btrfs_root *dev_root,
+				struct btrfs_device *device)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct extent_buffer *eb;
+	struct btrfs_dev_stats_item *ptr;
+	int ret;
+	int i;
+
+	key.objectid = 0;
+	key.type = BTRFS_DEV_STATS_KEY;
+	key.offset = device->devid;
+
+	path = btrfs_alloc_path();
+	BUG_ON(!path);
+	ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
+	if (ret < 0) {
+		printk(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n",
+		       ret, device->name);
+		goto out;
+	}
+
+	if (ret == 0 &&
+	    btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) {
+		/* need to delete old one and insert a new one */
+		ret = btrfs_del_item(trans, dev_root, path);
+		if (ret != 0) {
+			printk(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n",
+			       device->name, ret);
+			goto out;
+		}
+		ret = 1;
+	}
+
+	if (ret == 1) {
+		/* need to insert a new item */
+		btrfs_release_path(path);
+		ret = btrfs_insert_empty_item(trans, dev_root, path,
+					      &key, sizeof(*ptr));
+		if (ret < 0) {
+			printk(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n",
+			       device->name, ret);
+			goto out;
+		}
+	}
+
+	eb = path->nodes[0];
+	ptr = btrfs_item_ptr(eb, path->slots[0], struct btrfs_dev_stats_item);
+	for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
+		btrfs_set_dev_stats_value(eb, ptr, i,
+					  btrfs_dev_stat_read(device, i));
+	btrfs_mark_buffer_dirty(eb);
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * called from commit_transaction. Writes all changed device stats to disk.
+ */
+int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
+			struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *dev_root = fs_info->dev_root;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_device *device;
+	int ret = 0;
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		if (!device->dev_stats_valid || !device->dev_stats_dirty)
+			continue;
+
+		ret = update_dev_stat_item(trans, dev_root, device);
+		if (!ret)
+			device->dev_stats_dirty = 0;
+	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
+	return ret;
+}
+
+void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index)
+{
+	btrfs_dev_stat_inc(dev, index);
+	btrfs_dev_stat_print_on_error(dev);
+}
+
+void btrfs_dev_stat_print_on_error(struct btrfs_device *dev)
+{
+	if (!dev->dev_stats_valid)
+		return;
+	printk_ratelimited(KERN_ERR
+			   "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+			   dev->name,
+			   btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
+			   btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
+			   btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS),
+			   btrfs_dev_stat_read(dev,
+					       BTRFS_DEV_STAT_CORRUPTION_ERRS),
+			   btrfs_dev_stat_read(dev,
+					       BTRFS_DEV_STAT_GENERATION_ERRS));
+}
+
+static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
+{
+	printk(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+	       dev->name,
+	       btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
+	       btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
+	       btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS),
+	       btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS),
+	       btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS));
+}
+
+int btrfs_get_dev_stats(struct btrfs_root *root,
+			struct btrfs_ioctl_get_dev_stats *stats,
+			int reset_after_read)
+{
+	struct btrfs_device *dev;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
+	int i;
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	dev = btrfs_find_device(root, stats->devid, NULL, NULL);
+	mutex_unlock(&fs_devices->device_list_mutex);
+
+	if (!dev) {
+		printk(KERN_WARNING
+		       "btrfs: get dev_stats failed, device not found\n");
+		return -ENODEV;
+	} else if (!dev->dev_stats_valid) {
+		printk(KERN_WARNING
+		       "btrfs: get dev_stats failed, not yet valid\n");
+		return -ENODEV;
+	} else if (reset_after_read) {
+		for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
+			if (stats->nr_items > i)
+				stats->values[i] =
+					btrfs_dev_stat_read_and_reset(dev, i);
+			else
+				btrfs_dev_stat_reset(dev, i);
+		}
+	} else {
+		for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
+			if (stats->nr_items > i)
+				stats->values[i] = btrfs_dev_stat_read(dev, i);
+	}
+	if (stats->nr_items > BTRFS_DEV_STAT_VALUES_MAX)
+		stats->nr_items = BTRFS_DEV_STAT_VALUES_MAX;
+	return 0;
+}