Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...

1 files changed, 41 insertions, 86 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b6b00338037c..9c20049d1fec 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -164,24 +164,12 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
  */
 enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags)
 {
-	if (flags & BTRFS_BLOCK_GROUP_RAID10)
-		return BTRFS_RAID_RAID10;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID1)
-		return BTRFS_RAID_RAID1;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
-		return BTRFS_RAID_RAID1C3;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID1C4)
-		return BTRFS_RAID_RAID1C4;
-	else if (flags & BTRFS_BLOCK_GROUP_DUP)
-		return BTRFS_RAID_DUP;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID0)
-		return BTRFS_RAID_RAID0;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID5)
-		return BTRFS_RAID_RAID5;
-	else if (flags & BTRFS_BLOCK_GROUP_RAID6)
-		return BTRFS_RAID_RAID6;
-
-	return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
+	const u64 profile = (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+
+	if (!profile)
+		return BTRFS_RAID_SINGLE;
+
+	return BTRFS_BG_FLAG_TO_INDEX(profile);
 }
 
 const char *btrfs_bg_type_to_raid_name(u64 flags)
@@ -4062,13 +4050,6 @@ static inline int validate_convert_profile(struct btrfs_fs_info *fs_info,
 	if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT))
 		return true;
 
-	if (fs_info->sectorsize < PAGE_SIZE &&
-		bargs->target & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-		btrfs_err(fs_info,
-		"RAID56 is not yet supported for sectorsize %u with page size %lu",
-			  fs_info->sectorsize, PAGE_SIZE);
-		return false;
-	}
 	/* Profile is valid and does not have bits outside of the allowed set */
 	if (alloc_profile_is_valid(bargs->target, 1) &&
 	    (bargs->target & ~allowed) == 0)
@@ -6312,7 +6293,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
 	u64 offset;
 	u64 stripe_offset;
 	u64 stripe_nr;
-	u64 stripe_len;
+	u32 stripe_len;
 	u64 raid56_full_stripe_start = (u64)-1;
 	int data_stripes;
 
@@ -6323,19 +6304,13 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
 	offset = logical - em->start;
 	/* Len of a stripe in a chunk */
 	stripe_len = map->stripe_len;
-	/* Stripe where this block falls in */
-	stripe_nr = div64_u64(offset, stripe_len);
-	/* Offset of stripe in the chunk */
-	stripe_offset = stripe_nr * stripe_len;
-	if (offset < stripe_offset) {
-		btrfs_crit(fs_info,
-"stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu",
-			stripe_offset, offset, em->start, logical, stripe_len);
-		return -EINVAL;
-	}
+	/*
+	 * Stripe_nr is where this block falls in
+	 * stripe_offset is the offset of this block in its stripe.
+	 */
+	stripe_nr = div64_u64_rem(offset, stripe_len, &stripe_offset);
+	ASSERT(stripe_offset < U32_MAX);
 
-	/* stripe_offset is the offset of this block in its stripe */
-	stripe_offset = offset - stripe_offset;
 	data_stripes = nr_data_stripes(map);
 
 	/* Only stripe based profiles needs to check against stripe length. */
@@ -6737,11 +6712,11 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 		bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
 		(unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
 		dev->devid, bio->bi_iter.bi_size);
-	bio_set_dev(bio, dev->bdev);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 
-	btrfsic_submit_bio(bio);
+	btrfsic_check_bio(bio);
+	submit_bio(bio);
 }
 
 static void bioc_error(struct btrfs_io_context *bioc, struct bio *bio, u64 logical)
@@ -6823,10 +6798,12 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			continue;
 		}
 
-		if (dev_nr < total_devs - 1)
-			bio = btrfs_bio_clone(first_bio);
-		else
+		if (dev_nr < total_devs - 1) {
+			bio = btrfs_bio_clone(dev->bdev, first_bio);
+		} else {
 			bio = first_bio;
+			bio_set_dev(bio, dev->bdev);
+		}
 
 		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
 	}
@@ -7359,7 +7336,6 @@ static int read_one_dev(struct extent_buffer *leaf,
 
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_super_block *super_copy = fs_info->super_copy;
 	struct extent_buffer *sb;
 	struct btrfs_disk_key *disk_key;
@@ -7375,30 +7351,16 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
 	struct btrfs_key key;
 
 	ASSERT(BTRFS_SUPER_INFO_SIZE <= fs_info->nodesize);
+
 	/*
-	 * This will create extent buffer of nodesize, superblock size is
-	 * fixed to BTRFS_SUPER_INFO_SIZE. If nodesize > sb size, this will
-	 * overallocate but we can keep it as-is, only the first page is used.
+	 * We allocated a dummy extent, just to use extent buffer accessors.
+	 * There will be unused space after BTRFS_SUPER_INFO_SIZE, but
+	 * that's fine, we will not go beyond system chunk array anyway.
 	 */
-	sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET,
-					  root->root_key.objectid, 0);
-	if (IS_ERR(sb))
-		return PTR_ERR(sb);
+	sb = alloc_dummy_extent_buffer(fs_info, BTRFS_SUPER_INFO_OFFSET);
+	if (!sb)
+		return -ENOMEM;
 	set_extent_buffer_uptodate(sb);
-	/*
-	 * The sb extent buffer is artificial and just used to read the system array.
-	 * set_extent_buffer_uptodate() call does not properly mark all it's
-	 * pages up-to-date when the page is larger: extent does not cover the
-	 * whole page and consequently check_page_uptodate does not find all
-	 * the page's extents up-to-date (the hole beyond sb),
-	 * write_extent_buffer then triggers a WARN_ON.
-	 *
-	 * Regular short extents go through mark_extent_buffer_dirty/writeback cycle,
-	 * but sb spans only this function. Add an explicit SetPageUptodate call
-	 * to silence the warning eg. on PowerPC 64.
-	 */
-	if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE)
-		SetPageUptodate(sb->pages[0]);
 
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
 	array_size = btrfs_super_sys_array_size(super_copy);
@@ -7561,6 +7523,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	struct btrfs_key found_key;
 	int ret;
 	int slot;
+	int iter_ret = 0;
 	u64 total_dev = 0;
 	u64 last_ra_node = 0;
 
@@ -7604,30 +7567,18 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
 	key.offset = 0;
 	key.type = 0;
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto error;
-	while (1) {
-		struct extent_buffer *node;
+	btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) {
+		struct extent_buffer *node = path->nodes[1];
 
 		leaf = path->nodes[0];
 		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret == 0)
-				continue;
-			if (ret < 0)
-				goto error;
-			break;
-		}
-		node = path->nodes[1];
+
 		if (node) {
 			if (last_ra_node != node->start) {
 				readahead_tree_node_children(node);
 				last_ra_node = node->start;
 			}
 		}
-		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 		if (found_key.type == BTRFS_DEV_ITEM_KEY) {
 			struct btrfs_dev_item *dev_item;
 			dev_item = btrfs_item_ptr(leaf, slot,
@@ -7652,7 +7603,11 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 			if (ret)
 				goto error;
 		}
-		path->slots[0]++;
+	}
+	/* Catch error found during iteration */
+	if (iter_ret < 0) {
+		ret = iter_ret;
+		goto error;
 	}
 
 	/*
@@ -7660,12 +7615,12 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	 * do another round of validation checks.
 	 */
 	if (total_dev != fs_info->fs_devices->total_devices) {
-		btrfs_err(fs_info,
-	   "super_num_devices %llu mismatch with num_devices %llu found here",
+		btrfs_warn(fs_info,
+"super block num_devices %llu mismatch with DEV_ITEM count %llu, will be repaired on next transaction commit",
 			  btrfs_super_num_devices(fs_info->super_copy),
 			  total_dev);
-		ret = -EINVAL;
-		goto error;
+		fs_info->fs_devices->total_devices = total_dev;
+		btrfs_set_super_num_devices(fs_info->super_copy, total_dev);
 	}
 	if (btrfs_super_total_bytes(fs_info->super_copy) <
 	    fs_info->fs_devices->total_rw_bytes) {
@@ -8277,7 +8232,7 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr)
 
 static int relocating_repair_kthread(void *data)
 {
-	struct btrfs_block_group *cache = (struct btrfs_block_group *)data;
+	struct btrfs_block_group *cache = data;
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 target;
 	int ret = 0;