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, 85 insertions, 13 deletions

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index f79bf85f2439..5ada02e0e629 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -493,6 +493,11 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 	long time_left;
 	int loops;
 
+	delalloc_bytes = percpu_counter_sum_positive(&fs_info->delalloc_bytes);
+	ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
+	if (delalloc_bytes == 0 && ordered_bytes == 0)
+		return;
+
 	/* Calc the number of the pages we need flush for space reservation */
 	if (to_reclaim == U64_MAX) {
 		items = U64_MAX;
@@ -500,22 +505,21 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 		/*
 		 * to_reclaim is set to however much metadata we need to
 		 * reclaim, but reclaiming that much data doesn't really track
-		 * exactly, so increase the amount to reclaim by 2x in order to
-		 * make sure we're flushing enough delalloc to hopefully reclaim
-		 * some metadata reservations.
+		 * exactly.  What we really want to do is reclaim full inode's
+		 * worth of reservations, however that's not available to us
+		 * here.  We will take a fraction of the delalloc bytes for our
+		 * flushing loops and hope for the best.  Delalloc will expand
+		 * the amount we write to cover an entire dirty extent, which
+		 * will reclaim the metadata reservation for that range.  If
+		 * it's not enough subsequent flush stages will be more
+		 * aggressive.
 		 */
+		to_reclaim = max(to_reclaim, delalloc_bytes >> 3);
 		items = calc_reclaim_items_nr(fs_info, to_reclaim) * 2;
-		to_reclaim = items * EXTENT_SIZE_PER_ITEM;
 	}
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 
-	delalloc_bytes = percpu_counter_sum_positive(
-						&fs_info->delalloc_bytes);
-	ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
-	if (delalloc_bytes == 0 && ordered_bytes == 0)
-		return;
-
 	/*
 	 * If we are doing more ordered than delalloc we need to just wait on
 	 * ordered extents, otherwise we'll waste time trying to flush delalloc
@@ -528,9 +532,49 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 	while ((delalloc_bytes || ordered_bytes) && loops < 3) {
 		u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
 		long nr_pages = min_t(u64, temp, LONG_MAX);
+		int async_pages;
 
 		btrfs_start_delalloc_roots(fs_info, nr_pages, true);
 
+		/*
+		 * We need to make sure any outstanding async pages are now
+		 * processed before we continue.  This is because things like
+		 * sync_inode() try to be smart and skip writing if the inode is
+		 * marked clean.  We don't use filemap_fwrite for flushing
+		 * because we want to control how many pages we write out at a
+		 * time, thus this is the only safe way to make sure we've
+		 * waited for outstanding compressed workers to have started
+		 * their jobs and thus have ordered extents set up properly.
+		 *
+		 * This exists because we do not want to wait for each
+		 * individual inode to finish its async work, we simply want to
+		 * start the IO on everybody, and then come back here and wait
+		 * for all of the async work to catch up.  Once we're done with
+		 * that we know we'll have ordered extents for everything and we
+		 * can decide if we wait for that or not.
+		 *
+		 * If we choose to replace this in the future, make absolutely
+		 * sure that the proper waiting is being done in the async case,
+		 * as there have been bugs in that area before.
+		 */
+		async_pages = atomic_read(&fs_info->async_delalloc_pages);
+		if (!async_pages)
+			goto skip_async;
+
+		/*
+		 * We don't want to wait forever, if we wrote less pages in this
+		 * loop than we have outstanding, only wait for that number of
+		 * pages, otherwise we can wait for all async pages to finish
+		 * before continuing.
+		 */
+		if (async_pages > nr_pages)
+			async_pages -= nr_pages;
+		else
+			async_pages = 0;
+		wait_event(fs_info->async_submit_wait,
+			   atomic_read(&fs_info->async_delalloc_pages) <=
+			   async_pages);
+skip_async:
 		loops++;
 		if (wait_ordered && !trans) {
 			btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
@@ -595,8 +639,11 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		break;
 	case FLUSH_DELALLOC:
 	case FLUSH_DELALLOC_WAIT:
+	case FLUSH_DELALLOC_FULL:
+		if (state == FLUSH_DELALLOC_FULL)
+			num_bytes = U64_MAX;
 		shrink_delalloc(fs_info, space_info, num_bytes,
-				state == FLUSH_DELALLOC_WAIT, for_preempt);
+				state != FLUSH_DELALLOC, for_preempt);
 		break;
 	case FLUSH_DELAYED_REFS_NR:
 	case FLUSH_DELAYED_REFS:
@@ -686,7 +733,7 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 {
 	u64 global_rsv_size = fs_info->global_block_rsv.reserved;
 	u64 ordered, delalloc;
-	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
+	u64 thresh = div_factor_fine(space_info->total_bytes, 90);
 	u64 used;
 
 	/* If we're just plain full then async reclaim just slows us down. */
@@ -694,6 +741,20 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 	     global_rsv_size) >= thresh)
 		return false;
 
+	used = space_info->bytes_may_use + space_info->bytes_pinned;
+
+	/* The total flushable belongs to the global rsv, don't flush. */
+	if (global_rsv_size >= used)
+		return false;
+
+	/*
+	 * 128MiB is 1/4 of the maximum global rsv size.  If we have less than
+	 * that devoted to other reservations then there's no sense in flushing,
+	 * we don't have a lot of things that need flushing.
+	 */
+	if (used - global_rsv_size <= SZ_128M)
+		return false;
+
 	/*
 	 * We have tickets queued, bail so we don't compete with the async
 	 * flushers.
@@ -824,6 +885,8 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info,
 	struct reserve_ticket *ticket;
 	u64 tickets_id = space_info->tickets_id;
 
+	trace_btrfs_fail_all_tickets(fs_info, space_info);
+
 	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(fs_info, "cannot satisfy tickets, dumping space info");
 		__btrfs_dump_space_info(fs_info, space_info);
@@ -905,6 +968,14 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 		}
 
 		/*
+		 * We do not want to empty the system of delalloc unless we're
+		 * under heavy pressure, so allow one trip through the flushing
+		 * logic before we start doing a FLUSH_DELALLOC_FULL.
+		 */
+		if (flush_state == FLUSH_DELALLOC_FULL && !commit_cycles)
+			flush_state++;
+
+		/*
 		 * We don't want to force a chunk allocation until we've tried
 		 * pretty hard to reclaim space.  Think of the case where we
 		 * freed up a bunch of space and so have a lot of pinned space
@@ -1067,7 +1138,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
  *   so if we now have space to allocate do the force chunk allocation.
  */
 static const enum btrfs_flush_state data_flush_states[] = {
-	FLUSH_DELALLOC_WAIT,
+	FLUSH_DELALLOC_FULL,
 	RUN_DELAYED_IPUTS,
 	COMMIT_TRANS,
 	ALLOC_CHUNK_FORCE,
@@ -1156,6 +1227,7 @@ static const enum btrfs_flush_state evict_flush_states[] = {
 	FLUSH_DELAYED_REFS,
 	FLUSH_DELALLOC,
 	FLUSH_DELALLOC_WAIT,
+	FLUSH_DELALLOC_FULL,
 	ALLOC_CHUNK,
 	COMMIT_TRANS,
 };