Merge tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The highlights of this round are integrations with fs-verity and
  idmapped mounts, the rest is usual mix of minor improvements, speedups
  and cleanups.

  There are some patches outside of btrfs, namely updating some VFS
  interfaces, all straightforward and acked.

  Features:

   - fs-verity support, using standard ioctls, backward compatible with
     read-only limitation on inodes with previously enabled fs-verity

   - idmapped mount support

   - make mount with rescue=ibadroots more tolerant to partially damaged
     trees

   - allow raid0 on a single device and raid10 on two devices,
     degenerate cases but might be useful as an intermediate step during
     conversion to other profiles

   - zoned mode block group auto reclaim can be disabled via sysfs knob

  Performance improvements:

   - continue readahead of node siblings even if target node is in
     memory, could speed up full send (on sample test +11%)

   - batching of delayed items can speed up creating many files

   - fsync/tree-log speedups
       - avoid unnecessary work (gains +2% throughput, -2% run time on
         sample load)
       - reduced lock contention on renames (on dbench +4% throughput,
         up to -30% latency)

  Fixes:

   - various zoned mode fixes

   - preemptive flushing threshold tuning, avoid excessive work on
     almost full filesystems

  Core:

   - continued subpage support, preparation for implementing remaining
     features like compression and defragmentation; with some
     limitations, write is now enabled on 64K page systems with 4K
     sectors, still considered experimental
       - no readahead on compressed reads
       - inline extents disabled
       - disabled raid56 profile conversion and mount

   - improved flushing logic, fixing early ENOSPC on some workloads

   - inode flags have been internally split to read-only and read-write
     incompat bit parts, used by fs-verity

   - new tree items for fs-verity
       - descriptor item
       - Merkle tree item

   - inode operations extended to be namespace-aware

   - cleanups and refactoring

  Generic code changes:

   - fs: new export filemap_fdatawrite_wbc

   - fs: removed sync_inode

   - block: bio_trim argument type fixups

   - vfs: add namespace-aware lookup"

* tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (114 commits)
  btrfs: reset replace target device to allocation state on close
  btrfs: zoned: fix ordered extent boundary calculation
  btrfs: do not do preemptive flushing if the majority is global rsv
  btrfs: reduce the preemptive flushing threshold to 90%
  btrfs: tree-log: check btrfs_lookup_data_extent return value
  btrfs: avoid unnecessarily logging directories that had no changes
  btrfs: allow idmapped mount
  btrfs: handle ACLs on idmapped mounts
  btrfs: allow idmapped INO_LOOKUP_USER ioctl
  btrfs: allow idmapped SUBVOL_SETFLAGS ioctl
  btrfs: allow idmapped SET_RECEIVED_SUBVOL ioctls
  btrfs: relax restrictions for SNAP_DESTROY_V2 with subvolids
  btrfs: allow idmapped SNAP_DESTROY ioctls
  btrfs: allow idmapped SNAP_CREATE/SUBVOL_CREATE ioctls
  btrfs: check whether fsgid/fsuid are mapped during subvolume creation
  btrfs: allow idmapped permission inode op
  btrfs: allow idmapped setattr inode op
  btrfs: allow idmapped tmpfile inode op
  btrfs: allow idmapped symlink inode op
  btrfs: allow idmapped mkdir inode op
  ...

1 files changed, 201 insertions, 105 deletions

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fc831597cb22..914d403b4415 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -24,6 +24,7 @@
 #include "block-group.h"
 #include "backref.h"
 #include "misc.h"
+#include "subpage.h"
 
 /*
  * Relocation overview
@@ -2781,10 +2782,70 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 	u64 num_bytes;
 	int nr;
 	int ret = 0;
+	u64 i_size = i_size_read(&inode->vfs_inode);
 	u64 prealloc_start = cluster->start - offset;
 	u64 prealloc_end = cluster->end - offset;
 	u64 cur_offset = prealloc_start;
 
+	/*
+	 * For subpage case, previous i_size may not be aligned to PAGE_SIZE.
+	 * This means the range [i_size, PAGE_END + 1) is filled with zeros by
+	 * btrfs_do_readpage() call of previously relocated file cluster.
+	 *
+	 * If the current cluster starts in the above range, btrfs_do_readpage()
+	 * will skip the read, and relocate_one_page() will later writeback
+	 * the padding zeros as new data, causing data corruption.
+	 *
+	 * Here we have to manually invalidate the range (i_size, PAGE_END + 1).
+	 */
+	if (!IS_ALIGNED(i_size, PAGE_SIZE)) {
+		struct address_space *mapping = inode->vfs_inode.i_mapping;
+		struct btrfs_fs_info *fs_info = inode->root->fs_info;
+		const u32 sectorsize = fs_info->sectorsize;
+		struct page *page;
+
+		ASSERT(sectorsize < PAGE_SIZE);
+		ASSERT(IS_ALIGNED(i_size, sectorsize));
+
+		/*
+		 * Subpage can't handle page with DIRTY but without UPTODATE
+		 * bit as it can lead to the following deadlock:
+		 *
+		 * btrfs_readpage()
+		 * | Page already *locked*
+		 * |- btrfs_lock_and_flush_ordered_range()
+		 *    |- btrfs_start_ordered_extent()
+		 *       |- extent_write_cache_pages()
+		 *          |- lock_page()
+		 *             We try to lock the page we already hold.
+		 *
+		 * Here we just writeback the whole data reloc inode, so that
+		 * we will be ensured to have no dirty range in the page, and
+		 * are safe to clear the uptodate bits.
+		 *
+		 * This shouldn't cause too much overhead, as we need to write
+		 * the data back anyway.
+		 */
+		ret = filemap_write_and_wait(mapping);
+		if (ret < 0)
+			return ret;
+
+		clear_extent_bits(&inode->io_tree, i_size,
+				  round_up(i_size, PAGE_SIZE) - 1,
+				  EXTENT_UPTODATE);
+		page = find_lock_page(mapping, i_size >> PAGE_SHIFT);
+		/*
+		 * If page is freed we don't need to do anything then, as we
+		 * will re-read the whole page anyway.
+		 */
+		if (page) {
+			btrfs_subpage_clear_uptodate(fs_info, page, i_size,
+					round_up(i_size, PAGE_SIZE) - i_size);
+			unlock_page(page);
+			put_page(page);
+		}
+	}
+
 	BUG_ON(cluster->start != cluster->boundary[0]);
 	ret = btrfs_alloc_data_chunk_ondemand(inode,
 					      prealloc_end + 1 - prealloc_start);
@@ -2886,19 +2947,149 @@ noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
 }
 ALLOW_ERROR_INJECTION(btrfs_should_cancel_balance, TRUE);
 
-static int relocate_file_extent_cluster(struct inode *inode,
-					struct file_extent_cluster *cluster)
+static u64 get_cluster_boundary_end(struct file_extent_cluster *cluster,
+				    int cluster_nr)
+{
+	/* Last extent, use cluster end directly */
+	if (cluster_nr >= cluster->nr - 1)
+		return cluster->end;
+
+	/* Use next boundary start*/
+	return cluster->boundary[cluster_nr + 1] - 1;
+}
+
+static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
+			     struct file_extent_cluster *cluster,
+			     int *cluster_nr, unsigned long page_index)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	u64 offset = BTRFS_I(inode)->index_cnt;
+	const unsigned long last_index = (cluster->end - offset) >> PAGE_SHIFT;
+	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
+	struct page *page;
 	u64 page_start;
 	u64 page_end;
+	u64 cur;
+	int ret;
+
+	ASSERT(page_index <= last_index);
+	page = find_lock_page(inode->i_mapping, page_index);
+	if (!page) {
+		page_cache_sync_readahead(inode->i_mapping, ra, NULL,
+				page_index, last_index + 1 - page_index);
+		page = find_or_create_page(inode->i_mapping, page_index, mask);
+		if (!page)
+			return -ENOMEM;
+	}
+	ret = set_page_extent_mapped(page);
+	if (ret < 0)
+		goto release_page;
+
+	if (PageReadahead(page))
+		page_cache_async_readahead(inode->i_mapping, ra, NULL, page,
+				   page_index, last_index + 1 - page_index);
+
+	if (!PageUptodate(page)) {
+		btrfs_readpage(NULL, page);
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			ret = -EIO;
+			goto release_page;
+		}
+	}
+
+	page_start = page_offset(page);
+	page_end = page_start + PAGE_SIZE - 1;
+
+	/*
+	 * Start from the cluster, as for subpage case, the cluster can start
+	 * inside the page.
+	 */
+	cur = max(page_start, cluster->boundary[*cluster_nr] - offset);
+	while (cur <= page_end) {
+		u64 extent_start = cluster->boundary[*cluster_nr] - offset;
+		u64 extent_end = get_cluster_boundary_end(cluster,
+						*cluster_nr) - offset;
+		u64 clamped_start = max(page_start, extent_start);
+		u64 clamped_end = min(page_end, extent_end);
+		u32 clamped_len = clamped_end + 1 - clamped_start;
+
+		/* Reserve metadata for this range */
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+						      clamped_len);
+		if (ret)
+			goto release_page;
+
+		/* Mark the range delalloc and dirty for later writeback */
+		lock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end);
+		ret = btrfs_set_extent_delalloc(BTRFS_I(inode), clamped_start,
+						clamped_end, 0, NULL);
+		if (ret) {
+			clear_extent_bits(&BTRFS_I(inode)->io_tree,
+					clamped_start, clamped_end,
+					EXTENT_LOCKED | EXTENT_BOUNDARY);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+							clamped_len, true);
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+						       clamped_len);
+			goto release_page;
+		}
+		btrfs_page_set_dirty(fs_info, page, clamped_start, clamped_len);
+
+		/*
+		 * Set the boundary if it's inside the page.
+		 * Data relocation requires the destination extents to have the
+		 * same size as the source.
+		 * EXTENT_BOUNDARY bit prevents current extent from being merged
+		 * with previous extent.
+		 */
+		if (in_range(cluster->boundary[*cluster_nr] - offset,
+			     page_start, PAGE_SIZE)) {
+			u64 boundary_start = cluster->boundary[*cluster_nr] -
+						offset;
+			u64 boundary_end = boundary_start +
+					   fs_info->sectorsize - 1;
+
+			set_extent_bits(&BTRFS_I(inode)->io_tree,
+					boundary_start, boundary_end,
+					EXTENT_BOUNDARY);
+		}
+		unlock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), clamped_len);
+		cur += clamped_len;
+
+		/* Crossed extent end, go to next extent */
+		if (cur >= extent_end) {
+			(*cluster_nr)++;
+			/* Just finished the last extent of the cluster, exit. */
+			if (*cluster_nr >= cluster->nr)
+				break;
+		}
+	}
+	unlock_page(page);
+	put_page(page);
+
+	balance_dirty_pages_ratelimited(inode->i_mapping);
+	btrfs_throttle(fs_info);
+	if (btrfs_should_cancel_balance(fs_info))
+		ret = -ECANCELED;
+	return ret;
+
+release_page:
+	unlock_page(page);
+	put_page(page);
+	return ret;
+}
+
+static int relocate_file_extent_cluster(struct inode *inode,
+					struct file_extent_cluster *cluster)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 offset = BTRFS_I(inode)->index_cnt;
 	unsigned long index;
 	unsigned long last_index;
-	struct page *page;
 	struct file_ra_state *ra;
-	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
-	int nr = 0;
+	int cluster_nr = 0;
 	int ret = 0;
 
 	if (!cluster->nr)
@@ -2919,109 +3110,14 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	if (ret)
 		goto out;
 
-	index = (cluster->start - offset) >> PAGE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_SHIFT;
-	while (index <= last_index) {
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-				PAGE_SIZE);
-		if (ret)
-			goto out;
-
-		page = find_lock_page(inode->i_mapping, index);
-		if (!page) {
-			page_cache_sync_readahead(inode->i_mapping,
-						  ra, NULL, index,
-						  last_index + 1 - index);
-			page = find_or_create_page(inode->i_mapping, index,
-						   mask);
-			if (!page) {
-				btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							PAGE_SIZE, true);
-				btrfs_delalloc_release_extents(BTRFS_I(inode),
-							PAGE_SIZE);
-				ret = -ENOMEM;
-				goto out;
-			}
-		}
-		ret = set_page_extent_mapped(page);
-		if (ret < 0) {
-			btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							PAGE_SIZE, true);
-			btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-			unlock_page(page);
-			put_page(page);
-			goto out;
-		}
-
-		if (PageReadahead(page)) {
-			page_cache_async_readahead(inode->i_mapping,
-						   ra, NULL, page, index,
-						   last_index + 1 - index);
-		}
-
-		if (!PageUptodate(page)) {
-			btrfs_readpage(NULL, page);
-			lock_page(page);
-			if (!PageUptodate(page)) {
-				unlock_page(page);
-				put_page(page);
-				btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							PAGE_SIZE, true);
-				btrfs_delalloc_release_extents(BTRFS_I(inode),
-							       PAGE_SIZE);
-				ret = -EIO;
-				goto out;
-			}
-		}
-
-		page_start = page_offset(page);
-		page_end = page_start + PAGE_SIZE - 1;
-
-		lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
-
-		if (nr < cluster->nr &&
-		    page_start + offset == cluster->boundary[nr]) {
-			set_extent_bits(&BTRFS_I(inode)->io_tree,
-					page_start, page_end,
-					EXTENT_BOUNDARY);
-			nr++;
-		}
-
-		ret = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start,
-						page_end, 0, NULL);
-		if (ret) {
-			unlock_page(page);
-			put_page(page);
-			btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							 PAGE_SIZE, true);
-			btrfs_delalloc_release_extents(BTRFS_I(inode),
-			                               PAGE_SIZE);
-
-			clear_extent_bits(&BTRFS_I(inode)->io_tree,
-					  page_start, page_end,
-					  EXTENT_LOCKED | EXTENT_BOUNDARY);
-			goto out;
-
-		}
-		set_page_dirty(page);
-
-		unlock_extent(&BTRFS_I(inode)->io_tree,
-			      page_start, page_end);
-		unlock_page(page);
-		put_page(page);
-
-		index++;
-		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-		balance_dirty_pages_ratelimited(inode->i_mapping);
-		btrfs_throttle(fs_info);
-		if (btrfs_should_cancel_balance(fs_info)) {
-			ret = -ECANCELED;
-			goto out;
-		}
-	}
-	WARN_ON(nr != cluster->nr);
+	for (index = (cluster->start - offset) >> PAGE_SHIFT;
+	     index <= last_index && !ret; index++)
+		ret = relocate_one_page(inode, ra, cluster, &cluster_nr, index);
 	if (btrfs_is_zoned(fs_info) && !ret)
 		ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+	if (ret == 0)
+		WARN_ON(cluster_nr != cluster->nr);
 out:
 	kfree(ra);
 	return ret;