Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.15-rc7).

Conflicts:

tools/testing/selftests/drivers/net/hw/ncdevmem.c
  97c4e094a4b2 ("tests/ncdevmem: Fix double-free of queue array")
  2f1a805f32ba ("selftests: ncdevmem: Implement devmem TCP TX")
https://lore.kernel.org/20250514122900.1e77d62d@canb.auug.org.au

Adjacent changes:

net/core/devmem.c
net/core/devmem.h
  0afc44d8cdf6 ("net: devmem: fix kernel panic when netlink socket close after module unload")
  bd61848900bf ("net: devmem: Implement TX path")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

36 files changed, 316 insertions, 124 deletions

diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index effafc3e0ced..7ec022e9361a 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1422,11 +1422,31 @@ alloc_done:
 
 	wp->sectors_free = UINT_MAX;
 
-	open_bucket_for_each(c, &wp->ptrs, ob, i)
+	open_bucket_for_each(c, &wp->ptrs, ob, i) {
+		/*
+		 * Ensure proper write alignment - either due to misaligned
+		 * bucket sizes (from buggy bcachefs-tools), or writes that mix
+		 * logical/physical alignment:
+		 */
+		struct bch_dev *ca = ob_dev(c, ob);
+		u64 offset = bucket_to_sector(ca, ob->bucket) +
+			ca->mi.bucket_size -
+			ob->sectors_free;
+		unsigned align = round_up(offset, block_sectors(c)) - offset;
+
+		ob->sectors_free = max_t(int, 0, ob->sectors_free - align);
+
 		wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
+	}
 
 	wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
 
+	/* Did alignment use up space in an open_bucket? */
+	if (unlikely(!wp->sectors_free)) {
+		bch2_alloc_sectors_done(c, wp);
+		goto retry;
+	}
+
 	BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
 
 	return 0;
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 5fd4a58d2ad2..60782f3e5aec 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -41,6 +41,7 @@ void bch2_btree_node_io_unlock(struct btree *b)
 
 	clear_btree_node_write_in_flight_inner(b);
 	clear_btree_node_write_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
 }
 
@@ -1400,6 +1401,7 @@ start:
 
 	printbuf_exit(&buf);
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1595,6 +1597,7 @@ fsck_err:
 	printbuf_exit(&buf);
 
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1721,6 +1724,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 		set_btree_node_read_error(b);
 		bch2_btree_lost_data(c, b->c.btree_id);
 		clear_btree_node_read_in_flight(b);
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 		printbuf_exit(&buf);
 		return;
@@ -2061,8 +2065,10 @@ static void __btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start
 
 	if (new & (1U << BTREE_NODE_write_in_flight))
 		__bch2_btree_node_write(c, b, BTREE_WRITE_ALREADY_STARTED|type);
-	else
+	else {
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
+	}
 }
 
 static void btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start_time)
@@ -2175,6 +2181,7 @@ static void btree_node_write_endio(struct bio *bio)
 	}
 
 	clear_btree_node_write_in_flight_inner(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight_inner);
 	INIT_WORK(&wb->work, btree_node_write_work);
 	queue_work(c->btree_io_complete_wq, &wb->work);
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 8d75b27a1418..af1532de4a37 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -44,6 +44,7 @@ static inline void bucket_unlock(struct bucket *b)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
 }
 
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 62d27e04d763..51893e1ee874 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -160,6 +160,7 @@ static inline void gc_stripe_unlock(struct gc_stripe *s)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &s->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &s->lock, BUCKET_LOCK_BITNR);
 }
 
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index a615e4852ded..d9ebffa5b3a2 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -269,7 +269,7 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_downgrade)			\
 	x(BCH_ERR_invalid,		invalid_bkey)				\
 	x(BCH_ERR_operation_blocked,    nocow_lock_blocked)			\
-	x(EIO,				journal_shutdown)			\
+	x(EROFS,			journal_shutdown)			\
 	x(EIO,				journal_flush_err)			\
 	x(EIO,				journal_write_err)			\
 	x(EIO,				btree_node_read_err)			\
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index dca2b8425cc0..e597fb9c9823 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1056,8 +1056,9 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke
 static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts,
 			    struct bch_extent_ptr *ptr)
 {
-	if (!opts->promote_target ||
-	    !bch2_dev_in_target(c, ptr->dev, opts->promote_target))
+	unsigned target = opts->promote_target ?: opts->foreground_target;
+
+	if (target && !bch2_dev_in_target(c, ptr->dev, target))
 		return false;
 
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 113db85b6ef9..b6801861c66f 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -2502,10 +2502,9 @@ static int bch2_fs_get_tree(struct fs_context *fc)
 
 	bch2_opts_apply(&c->opts, opts);
 
-	/*
-	 * need to initialise sb and set c->vfs_sb _before_ starting fs,
-	 * for blk_holder_ops
-	 */
+	ret = bch2_fs_start(c);
+	if (ret)
+		goto err_stop_fs;
 
 	sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
 	ret = PTR_ERR_OR_ZERO(sb);
@@ -2567,10 +2566,6 @@ got_sb:
 
 	sb->s_shrink->seeks = 0;
 
-	ret = bch2_fs_start(c);
-	if (ret)
-		goto err_put_super;
-
 #ifdef CONFIG_UNICODE
 	sb->s_encoding = c->cf_encoding;
 #endif
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 63cdf885c9e2..ded18a94ed02 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -19,6 +19,7 @@
 
 #include <linux/ioprio.h>
 #include <linux/string_choices.h>
+#include <linux/sched/sysctl.h>
 
 void bch2_journal_pos_from_member_info_set(struct bch_fs *c)
 {
@@ -1262,7 +1263,8 @@ int bch2_journal_read(struct bch_fs *c,
 			degraded = true;
 	}
 
-	closure_sync(&jlist.cl);
+	while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2))
+		;
 
 	if (jlist.ret)
 		return jlist.ret;
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index ea670c3c43d8..976464d8a695 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -266,10 +266,11 @@ out:
 
 static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
 {
-	bool ret;
-
 	spin_lock(&j->lock);
-	ret = ja->discard_idx != ja->dirty_idx_ondisk;
+	unsigned min_free = max(4, ja->nr / 8);
+
+	bool ret = bch2_journal_dev_buckets_available(j, ja, journal_space_discarded) < min_free &&
+		ja->discard_idx != ja->dirty_idx_ondisk;
 	spin_unlock(&j->lock);
 
 	return ret;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index fc396b9fa754..dfdbb9259985 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -784,7 +784,8 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
 		goto err;
 
 	ret = bch2_btree_write_buffer_tryflush(trans);
-	bch_err_msg(c, ret, "flushing btree write buffer");
+	if (!bch2_err_matches(ret, EROFS))
+		bch_err_msg(c, ret, "flushing btree write buffer");
 	if (ret)
 		goto err;
 
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 27943082c093..84a37d971ffd 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -377,6 +377,11 @@ void bch2_fs_read_only(struct bch_fs *c)
 		bch_verbose(c, "marking filesystem clean");
 		bch2_fs_mark_clean(c);
 	} else {
+		/* Make sure error counts/counters are persisted */
+		mutex_lock(&c->sb_lock);
+		bch2_write_super(c);
+		mutex_unlock(&c->sb_lock);
+
 		bch_verbose(c, "done going read-only, filesystem not clean");
 	}
 }
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index dea73bc1cb51..314a24d15d4e 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -455,8 +455,10 @@ ssize_t bch2_stdio_redirect_vprintf(struct stdio_redirect *stdio, bool nonblocki
 	struct stdio_buf *buf = &stdio->output;
 	unsigned long flags;
 	ssize_t ret;
-
 again:
+	if (stdio->done)
+		return -EPIPE;
+
 	spin_lock_irqsave(&buf->lock, flags);
 	ret = bch2_darray_vprintf(&buf->buf, GFP_NOWAIT, fmt, args);
 	spin_unlock_irqrestore(&buf->lock, flags);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 584fa89bc877..4c1ea6b52a53 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -830,6 +830,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
 	struct elf_phdr *elf_property_phdata = NULL;
 	unsigned long elf_brk;
+	bool brk_moved = false;
 	int retval, i;
 	unsigned long elf_entry;
 	unsigned long e_entry;
@@ -1097,15 +1098,19 @@ out_free_interp:
 			/* Calculate any requested alignment. */
 			alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
 
-			/*
-			 * There are effectively two types of ET_DYN
-			 * binaries: programs (i.e. PIE: ET_DYN with PT_INTERP)
-			 * and loaders (ET_DYN without PT_INTERP, since they
-			 * _are_ the ELF interpreter). The loaders must
-			 * be loaded away from programs since the program
-			 * may otherwise collide with the loader (especially
-			 * for ET_EXEC which does not have a randomized
-			 * position). For example to handle invocations of
+			/**
+			 * DOC: PIE handling
+			 *
+			 * There are effectively two types of ET_DYN ELF
+			 * binaries: programs (i.e. PIE: ET_DYN with
+			 * PT_INTERP) and loaders (i.e. static PIE: ET_DYN
+			 * without PT_INTERP, usually the ELF interpreter
+			 * itself). Loaders must be loaded away from programs
+			 * since the program may otherwise collide with the
+			 * loader (especially for ET_EXEC which does not have
+			 * a randomized position).
+			 *
+			 * For example, to handle invocations of
 			 * "./ld.so someprog" to test out a new version of
 			 * the loader, the subsequent program that the
 			 * loader loads must avoid the loader itself, so
@@ -1118,6 +1123,9 @@ out_free_interp:
 			 * ELF_ET_DYN_BASE and loaders are loaded into the
 			 * independently randomized mmap region (0 load_bias
 			 * without MAP_FIXED nor MAP_FIXED_NOREPLACE).
+			 *
+			 * See below for "brk" handling details, which is
+			 * also affected by program vs loader and ASLR.
 			 */
 			if (interpreter) {
 				/* On ET_DYN with PT_INTERP, we do the ASLR. */
@@ -1234,8 +1242,6 @@ out_free_interp:
 	start_data += load_bias;
 	end_data += load_bias;
 
-	current->mm->start_brk = current->mm->brk = ELF_PAGEALIGN(elf_brk);
-
 	if (interpreter) {
 		elf_entry = load_elf_interp(interp_elf_ex,
 					    interpreter,
@@ -1291,27 +1297,44 @@ out_free_interp:
 	mm->end_data = end_data;
 	mm->start_stack = bprm->p;
 
-	if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) {
+	/**
+	 * DOC: "brk" handling
+	 *
+	 * For architectures with ELF randomization, when executing a
+	 * loader directly (i.e. static PIE: ET_DYN without PT_INTERP),
+	 * move the brk area out of the mmap region and into the unused
+	 * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide
+	 * early with the stack growing down or other regions being put
+	 * into the mmap region by the kernel (e.g. vdso).
+	 *
+	 * In the CONFIG_COMPAT_BRK case, though, everything is turned
+	 * off because we're not allowed to move the brk at all.
+	 */
+	if (!IS_ENABLED(CONFIG_COMPAT_BRK) &&
+	    IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
+	    elf_ex->e_type == ET_DYN && !interpreter) {
+		elf_brk = ELF_ET_DYN_BASE;
+		/* This counts as moving the brk, so let brk(2) know. */
+		brk_moved = true;
+	}
+	mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk);
+
+	if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) {
 		/*
-		 * For architectures with ELF randomization, when executing
-		 * a loader directly (i.e. no interpreter listed in ELF
-		 * headers), move the brk area out of the mmap region
-		 * (since it grows up, and may collide early with the stack
-		 * growing down), and into the unused ELF_ET_DYN_BASE region.
+		 * If we didn't move the brk to ELF_ET_DYN_BASE (above),
+		 * leave a gap between .bss and brk.
 		 */
-		if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
-		    elf_ex->e_type == ET_DYN && !interpreter) {
-			mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
-		} else {
-			/* Otherwise leave a gap between .bss and brk. */
+		if (!brk_moved)
 			mm->brk = mm->start_brk = mm->brk + PAGE_SIZE;
-		}
 
 		mm->brk = mm->start_brk = arch_randomize_brk(mm);
+		brk_moved = true;
+	}
+
 #ifdef compat_brk_randomized
+	if (brk_moved)
 		current->brk_randomized = 1;
 #endif
-	}
 
 	if (current->personality & MMAP_PAGE_ZERO) {
 		/* Why this, you ask???  Well SVr4 maps page 0 as read-only,
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index d6eef4bd9e9d..de23c4b3515e 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -94,8 +94,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				  struct btrfs_block_group *block_group)
 {
 	lockdep_assert_held(&discard_ctl->lock);
-	if (!btrfs_run_discard_work(discard_ctl))
-		return;
 
 	if (list_empty(&block_group->discard_list) ||
 	    block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) {
@@ -118,6 +116,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	if (!btrfs_is_block_group_data_only(block_group))
 		return;
 
+	if (!btrfs_run_discard_work(discard_ctl))
+		return;
+
 	spin_lock(&discard_ctl->lock);
 	__add_to_discard_list(discard_ctl, block_group);
 	spin_unlock(&discard_ctl->lock);
@@ -244,6 +245,18 @@ again:
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group)) {
 				__add_to_discard_list(discard_ctl, block_group);
+				/*
+				 * The block group must have been moved to other
+				 * discard list even if discard was disabled in
+				 * the meantime or a transaction abort happened,
+				 * otherwise we can end up in an infinite loop,
+				 * always jumping into the 'again' label and
+				 * keep getting this block group over and over
+				 * in case there are no other block groups in
+				 * the discard lists.
+				 */
+				ASSERT(block_group->discard_index !=
+				       BTRFS_DISCARD_INDEX_UNUSED);
 			} else {
 				list_del_init(&block_group->discard_list);
 				btrfs_put_block_group(block_group);
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index bcca43046064..7baa2ed45198 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -300,6 +300,7 @@ enum {
 #define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR		0ULL
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
+#define BTRFS_WARNING_COMMIT_INTERVAL	(300)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)
 
 struct btrfs_dev_replace {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index bdafe4d4c4a5..90f5da3c520a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1109,6 +1109,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	struct extent_state *cached = NULL;
 	struct extent_map *em;
 	int ret = 0;
+	bool free_pages = false;
 	u64 start = async_extent->start;
 	u64 end = async_extent->start + async_extent->ram_size - 1;
 
@@ -1129,7 +1130,10 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	}
 
 	if (async_extent->compress_type == BTRFS_COMPRESS_NONE) {
+		ASSERT(!async_extent->folios);
+		ASSERT(async_extent->nr_folios == 0);
 		submit_uncompressed_range(inode, async_extent, locked_folio);
+		free_pages = true;
 		goto done;
 	}
 
@@ -1145,6 +1149,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 		 * fall back to uncompressed.
 		 */
 		submit_uncompressed_range(inode, async_extent, locked_folio);
+		free_pages = true;
 		goto done;
 	}
 
@@ -1186,6 +1191,8 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 done:
 	if (async_chunk->blkcg_css)
 		kthread_associate_blkcg(NULL);
+	if (free_pages)
+		free_async_extent_pages(async_extent);
 	kfree(async_extent);
 	return;
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7121d8c7a318..7310e2fa8526 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -569,6 +569,10 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 	case Opt_commit_interval:
 		ctx->commit_interval = result.uint_32;
+		if (ctx->commit_interval > BTRFS_WARNING_COMMIT_INTERVAL) {
+			btrfs_warn(NULL, "excessive commit interval %u, use with care",
+				   ctx->commit_interval);
+		}
 		if (ctx->commit_interval == 0)
 			ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 		break;
diff --git a/fs/buffer.c b/fs/buffer.c
index 7be23ff20b27..7ba1807145aa 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1220,10 +1220,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh)
 	/* FIXME: do we need to set this in both places? */
 	if (bh->b_folio && bh->b_folio->mapping)
 		mapping_set_error(bh->b_folio->mapping, -EIO);
-	if (bh->b_assoc_map) {
+	if (bh->b_assoc_map)
 		mapping_set_error(bh->b_assoc_map, -EIO);
-		errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
-	}
 }
 EXPORT_SYMBOL(mark_buffer_write_io_error);
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 4bc264b854c4..d4dbffdedd08 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -2111,9 +2111,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 
 		write_unlock_irq(&ep->lock);
 
-		if (!eavail && ep_schedule_timeout(to))
-			timed_out = !schedule_hrtimeout_range(to, slack,
-							      HRTIMER_MODE_ABS);
+		if (!eavail)
+			timed_out = !ep_schedule_timeout(to) ||
+				!schedule_hrtimeout_range(to, slack,
+							  HRTIMER_MODE_ABS);
 		__set_current_state(TASK_RUNNING);
 
 		/*
diff --git a/fs/namespace.c b/fs/namespace.c
index 98a5cd756e9a..1b466c54a357 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -787,15 +787,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 		return 0;
 	mnt = real_mount(bastard);
 	mnt_add_count(mnt, 1);
-	smp_mb();			// see mntput_no_expire()
+	smp_mb();		// see mntput_no_expire() and do_umount()
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
-	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
-		mnt_add_count(mnt, -1);
-		return 1;
-	}
 	lock_mount_hash();
-	if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+	if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) {
 		mnt_add_count(mnt, -1);
 		unlock_mount_hash();
 		return 1;
@@ -2048,6 +2044,7 @@ static int do_umount(struct mount *mnt, int flags)
 			umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
+		smp_mb(); // paired with __legitimize_mnt()
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
@@ -3560,7 +3557,8 @@ static int can_move_mount_beneath(const struct path *from,
 	 * @mnt_from itself. This defeats the whole purpose of mounting
 	 * @mnt_from beneath @mnt_to.
 	 */
-	if (propagation_would_overmount(parent_mnt_to, mnt_from, mp))
+	if (check_mnt(mnt_from) &&
+	    propagation_would_overmount(parent_mnt_to, mnt_from, mp))
 		return -EINVAL;
 
 	return 0;
@@ -3718,15 +3716,14 @@ static int do_move_mount(struct path *old_path,
 	if (err)
 		goto out;
 
-	if (is_anon_ns(ns))
-		ns->mntns_flags &= ~MNTNS_PROPAGATING;
-
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
 	if (attached)
 		put_mountpoint(old_mp);
 out:
+	if (is_anon_ns(ns))
+		ns->mntns_flags &= ~MNTNS_PROPAGATING;
 	unlock_mount(mp);
 	if (!err) {
 		if (attached) {
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index cb01ea81724d..d0bcf744c553 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	int blocksize;
 	int err;
 
-	down_write(&nilfs->ns_sem);
-
 	blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
 	if (!blocksize) {
 		nilfs_err(sb, "unable to set blocksize");
@@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	set_nilfs_init(nilfs);
 	err = 0;
  out:
-	up_write(&nilfs->ns_sem);
 	return err;
 
  failed_sbh:
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b548c7..821cb7874685 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
 		if (IS_ERR(folios[numfolios])) {
 			ret = PTR_ERR(folios[numfolios]);
 			mlog_errno(ret);
+			folios[numfolios] = NULL;
 			goto out;
 		}
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index c7a9729dc9d0..e5f58ff2175f 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	struct ocfs2_recovery_map *rm;
 
 	mutex_init(&osb->recovery_lock);
-	osb->disable_recovery = 0;
+	osb->recovery_state = OCFS2_REC_ENABLED;
 	osb->recovery_thread_task = NULL;
 	init_waitqueue_head(&osb->recovery_event);
 
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	return 0;
 }
 
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
 static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
 {
-	mb();
 	return osb->recovery_thread_task != NULL;
 }
 
-void ocfs2_recovery_exit(struct ocfs2_super *osb)
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+				   enum ocfs2_recovery_state state)
 {
-	struct ocfs2_recovery_map *rm;
-
-	/* disable any new recovery threads and wait for any currently
-	 * running ones to exit. Do this before setting the vol_state. */
 	mutex_lock(&osb->recovery_lock);
-	osb->disable_recovery = 1;
+	/*
+	 * If recovery thread is not running, we can directly transition to
+	 * final state.
+	 */
+	if (!ocfs2_recovery_thread_running(osb)) {
+		osb->recovery_state = state + 1;
+		goto out_lock;
+	}
+	osb->recovery_state = state;
+	/* Wait for recovery thread to acknowledge state transition */
+	wait_event_cmd(osb->recovery_event,
+		       !ocfs2_recovery_thread_running(osb) ||
+				osb->recovery_state >= state + 1,
+		       mutex_unlock(&osb->recovery_lock),
+		       mutex_lock(&osb->recovery_lock));
+out_lock:
 	mutex_unlock(&osb->recovery_lock);
-	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
 
-	/* At this point, we know that no more recovery threads can be
-	 * launched, so wait for any recovery completion work to
-	 * complete. */
+	/*
+	 * At this point we know that no more recovery work can be queued so
+	 * wait for any recovery completion work to complete.
+	 */
 	if (osb->ocfs2_wq)
 		flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+	ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
+void ocfs2_recovery_exit(struct ocfs2_super *osb)
+{
+	struct ocfs2_recovery_map *rm;
+
+	/* disable any new recovery threads and wait for any currently
+	 * running ones to exit. Do this before setting the vol_state. */
+	ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
 		}
 	}
 restart:
+	if (quota_enabled) {
+		mutex_lock(&osb->recovery_lock);
+		/* Confirm that recovery thread will no longer recover quotas */
+		if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+			osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+			wake_up(&osb->recovery_event);
+		}
+		if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+			quota_enabled = 0;
+		mutex_unlock(&osb->recovery_lock);
+	}
+
 	status = ocfs2_super_lock(osb, 1);
 	if (status < 0) {
 		mlog_errno(status);
@@ -1569,27 +1603,29 @@ bail:
 
 	ocfs2_free_replay_slots(osb);
 	osb->recovery_thread_task = NULL;
-	mb(); /* sync with ocfs2_recovery_thread_running */
+	if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+		osb->recovery_state = OCFS2_REC_DISABLED;
 	wake_up(&osb->recovery_event);
 
 	mutex_unlock(&osb->recovery_lock);
 
-	if (quota_enabled)
-		kfree(rm_quota);
+	kfree(rm_quota);
 
 	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 {
+	int was_set = -1;
+
 	mutex_lock(&osb->recovery_lock);
+	if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+		was_set = ocfs2_recovery_map_set(osb, node_num);
 
 	trace_ocfs2_recovery_thread(node_num, osb->node_num,
-		osb->disable_recovery, osb->recovery_thread_task,
-		osb->disable_recovery ?
-		-1 : ocfs2_recovery_map_set(osb, node_num));
+		osb->recovery_state, osb->recovery_thread_task, was_set);
 
-	if (osb->disable_recovery)
+	if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
 		goto out;
 
 	if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35dc5e0..6397170f302f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
 
 int ocfs2_recovery_init(struct ocfs2_super *osb);
 void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
 
 int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
 void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c52768132d..6aaa94c554c1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
 void ocfs2_initialize_journal_triggers(struct super_block *sb,
 				       struct ocfs2_triggers triggers[]);
 
+enum ocfs2_recovery_state {
+	OCFS2_REC_ENABLED = 0,
+	OCFS2_REC_QUOTA_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+	 * ocfs2_recovery_disable_quota() to work.
+	 */
+	OCFS2_REC_QUOTA_DISABLED,
+	OCFS2_REC_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+	 */
+	OCFS2_REC_DISABLED,
+};
+
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
 	struct ocfs2_recovery_map *recovery_map;
 	struct ocfs2_replay_map *replay_map;
 	struct task_struct *recovery_thread_task;
-	int disable_recovery;
+	enum ocfs2_recovery_state recovery_state;
 	wait_queue_head_t checkpoint_event;
 	struct ocfs2_journal *journal;
 	unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d888c131..e272429da3db 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ out:
 
 /* Sync changes in local quota file into global quota file and
  * reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
 static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 					  int type,
 					  struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 {
 	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
 					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
-	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct buffer_head *bh;
 	handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
 	       "slot %u\n", osb->dev_str, slot_num);
 
-	down_read(&sb->s_umount);
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
@@ -677,7 +674,6 @@ out_put:
 			break;
 	}
 out:
-	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 	ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
 
 	/*
-	 * s_umount held in exclusive mode protects us against racing with
-	 * recovery thread...
+	 * ocfs2_dismount_volume() has already aborted quota recovery...
 	 */
 	if (oinfo->dqi_rec) {
 		ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f0de2a..6ac4dcd54588 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
 					       ac, cl);
-	if (PTR_ERR(bg_bh) == -ENOSPC)
+	if (PTR_ERR(bg_bh) == -ENOSPC) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
 		bg_bh = ocfs2_block_group_alloc_discontig(handle,
 							  alloc_inode,
 							  ac, cl);
+	}
 	if (IS_ERR(bg_bh)) {
 		status = PTR_ERR(bg_bh);
 		bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 {
 	int status;
 	u16 chain;
+	u32 contig_bits;
 	u64 next_group;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	status = -ENOSPC;
 	/* for now, the chain search is a bit simplistic. We just use
 	 * the 1st group with any empty bits. */
-	while ((status = ac->ac_group_search(alloc_inode, group_bh,
-					     bits_wanted, min_bits,
-					     ac->ac_max_block,
-					     res)) == -ENOSPC) {
+	while (1) {
+		if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+			contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+			if (!contig_bits)
+				contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+						le16_to_cpu(bg->bg_bits), 0);
+			if (bits_wanted > contig_bits && contig_bits >= min_bits)
+				bits_wanted = contig_bits;
+		}
+
+		status = ac->ac_group_search(alloc_inode, group_bh,
+				bits_wanted, min_bits,
+				ac->ac_max_block, res);
+		if (status != -ENOSPC)
+			break;
 		if (!bg->bg_next_group)
 			break;
 
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	victim = ocfs2_find_victim_chain(cl);
 	ac->ac_chain = victim;
 
+search:
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 		}
 	}
 
+	/* Chains can't supply the bits_wanted contiguous space.
+	 * We should switch to using every single bit when allocating
+	 * from the global bitmap. */
+	if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+	    status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+		ac->ac_chain = victim;
+		goto search;
+	}
+
 set_hint:
 	if (status != -ENOSPC) {
 		/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
 	BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
 
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
-	       && ac->ac_which != OCFS2_AC_USE_MAIN);
+	       && ac->ac_which != OCFS2_AC_USE_MAIN
+	       && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
 
 	if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
 		WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b834857d..bcf2ed4a8631 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
 #define OCFS2_AC_USE_MAIN  2
 #define OCFS2_AC_USE_INODE 3
 #define OCFS2_AC_USE_META  4
+#define OCFS2_AC_USE_MAIN_DISCONTIG  5
 	u32    ac_which;
 
 	/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022f3082..3d2533950bae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
+	/* Stop quota recovery so that we can disable quotas */
+	ocfs2_recovery_disable_quota(osb);
+
 	ocfs2_disable_quotas(osb);
 
 	/* All dquots should be freed by now */
diff --git a/fs/pnode.c b/fs/pnode.c
index 7a062a5de10e..fb77427df39e 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -150,7 +150,7 @@ static struct mount *propagation_next(struct mount *m,
 					 struct mount *origin)
 {
 	/* are there any slaves of this mount? */
-	if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 		return first_slave(m);
 
 	while (1) {
@@ -174,7 +174,7 @@ static struct mount *skip_propagation_subtree(struct mount *m,
 	 * Advance m such that propagation_next will not return
 	 * the slaves of m.
 	 */
-	if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 		m = last_slave(m);
 
 	return m;
@@ -185,7 +185,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 	while (1) {
 		while (1) {
 			struct mount *next;
-			if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 				return first_slave(m);
 			next = next_peer(m);
 			if (m->mnt_group_id == origin->mnt_group_id) {
@@ -226,11 +226,15 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
 	struct mount *child;
 	int type;
 	/* skip ones added by this propagate_mnt() */
-	if (IS_MNT_PROPAGATED(m))
+	if (IS_MNT_NEW(m))
 		return 0;
-	/* skip if mountpoint isn't covered by it */
+	/* skip if mountpoint isn't visible in m */
 	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
 		return 0;
+	/* skip if m is in the anon_ns we are emptying */
+	if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING)
+		return 0;
+
 	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
@@ -380,9 +384,6 @@ bool propagation_would_overmount(const struct mount *from,
 	if (!IS_MNT_SHARED(from))
 		return false;
 
-	if (IS_MNT_PROPAGATED(to))
-		return false;
-
 	if (to->mnt.mnt_root != mp->m_dentry)
 		return false;
 
diff --git a/fs/pnode.h b/fs/pnode.h
index ddafe0d087ca..34b6247af01d 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -12,7 +12,7 @@
 
 #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
 #define IS_MNT_SLAVE(m) ((m)->mnt_master)
-#define IS_MNT_PROPAGATED(m) (!(m)->mnt_ns || ((m)->mnt_ns->mntns_flags & MNTNS_PROPAGATING))
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
 #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index fe738623cf1b..240d82c6f908 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 {
 	struct cached_fid *cfid;
 
-	spin_lock(&cfids->cfid_list_lock);
 	list_for_each_entry(cfid, &cfids->entries, entry) {
 		if (!strcmp(cfid->path, path)) {
 			/*
@@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 			 * being deleted due to a lease break.
 			 */
 			if (!cfid->time || !cfid->has_lease) {
-				spin_unlock(&cfids->cfid_list_lock);
 				return NULL;
 			}
 			kref_get(&cfid->refcount);
-			spin_unlock(&cfids->cfid_list_lock);
 			return cfid;
 		}
 	}
 	if (lookup_only) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	if (cfids->num_entries >= max_cached_dirs) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid = init_cached_dir(path);
 	if (cfid == NULL) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid->cfids = cfids;
@@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 	 */
 	cfid->has_lease = true;
 
-	spin_unlock(&cfids->cfid_list_lock);
 	return cfid;
 }
 
@@ -187,8 +180,10 @@ replay_again:
 	if (!utf16_path)
 		return -ENOMEM;
 
+	spin_lock(&cfids->cfid_list_lock);
 	cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs);
 	if (cfid == NULL) {
+		spin_unlock(&cfids->cfid_list_lock);
 		kfree(utf16_path);
 		return -ENOENT;
 	}
@@ -197,7 +192,6 @@ replay_again:
 	 * Otherwise, it is either a new entry or laundromat worker removed it
 	 * from @cfids->entries.  Caller will put last reference if the latter.
 	 */
-	spin_lock(&cfids->cfid_list_lock);
 	if (cfid->has_lease && cfid->time) {
 		spin_unlock(&cfids->cfid_list_lock);
 		*ret_cfid = cfid;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 57d9bfbadd97..2a3e46b8e15a 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -666,6 +666,8 @@ finished:
 		/* smb2_parse_contexts() fills idata->fi.IndexNumber */
 		rc = smb2_parse_contexts(server, &rsp_iov[0], &oparms->fid->epoch,
 					 oparms->fid->lease_key, &oplock, &idata->fi, NULL);
+		if (rc)
+			cifs_dbg(VFS, "rc: %d parsing context of compound op\n", rc);
 	}
 
 	for (i = 0; i < num_cmds; i++) {
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 4f33a4a48886..b4071c9cf8c9 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -115,7 +115,7 @@ void udf_truncate_tail_extent(struct inode *inode)
 	}
 	/* This inode entry is in-memory only and thus we don't have to mark
 	 * the inode dirty */
-	if (ret == 0)
+	if (ret >= 0)
 		iinfo->i_lenExtents = inode->i_size;
 	brelse(epos.bh);
 }
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f94346199..22f4bf956ba1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
 	user_uffdio_poison = (struct uffdio_poison __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
 
 	user_uffdio_move = (struct uffdio_move __user *) arg;
 
-	if (atomic_read(&ctx->mmap_changing))
-		return -EAGAIN;
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_move->move)))
+			return -EFAULT;
+		goto out;
+	}
 
 	if (copy_from_user(&uffdio_move, user_uffdio_move,
 			   /* don't copy "move" last field */
diff --git a/fs/xattr.c b/fs/xattr.c
index fabb2a04501e..8ec5b0204bfd 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name)
 	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
+static bool xattr_is_maclabel(const char *name)
+{
+	const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+
+	return !strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN) &&
+		security_ismaclabel(suffix);
+}
+
 /**
  * simple_xattr_list - list all xattr objects
  * @inode: inode from which to get the xattrs
@@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	if (err)
 		return err;
 
+	err = security_inode_listsecurity(inode, buffer, remaining_size);
+	if (err < 0)
+		return err;
+
+	if (buffer) {
+		if (remaining_size < err)
+			return -ERANGE;
+		buffer += err;
+	}
+	remaining_size -= err;
+
 	read_lock(&xattrs->lock);
 	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
 		xattr = rb_entry(rbp, struct simple_xattr, rb_node);
@@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 		if (!trusted && xattr_is_trusted(xattr->name))
 			continue;
 
+		/* skip MAC labels; these are provided by LSM above */
+		if (xattr_is_maclabel(xattr->name))
+			continue;
+
 		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
 		if (err)
 			break;