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

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

18 files changed, 49 insertions, 97 deletions

diff --git a/fs/afs/write.c b/fs/afs/write.c
index 50371207f327..c9195fc67fd8 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -169,11 +169,14 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 	unsigned int f, from = pos & (PAGE_SIZE - 1);
 	unsigned int t, to = from + copied;
 	loff_t i_size, maybe_i_size;
-	int ret;
+	int ret = 0;
 
 	_enter("{%llx:%llu},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
 
+	if (copied == 0)
+		goto out;
+
 	maybe_i_size = pos + copied;
 
 	i_size = i_size_read(&vnode->vfs_inode);
diff --git a/fs/aio.c b/fs/aio.c
index c45c20d87538..6a21d8919409 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 		 * we return to userspace.
 		 */
 		if (S_ISREG(file_inode(file)->i_mode)) {
-			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+			sb_start_write(file_inode(file)->i_sb);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		}
 		req->ki_flags |= IOCB_WRITE;
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index 89bffa82ed74..c57bebfa48fe 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -74,7 +74,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci)
 	int i;
 
 	/* The file must need contents encryption, not filenames encryption */
-	if (!fscrypt_needs_contents_encryption(inode))
+	if (!S_ISREG(inode->i_mode))
 		return 0;
 
 	/* The crypto mode must have a blk-crypto counterpart */
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1b399cafb15a..bf9429484462 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1231,13 +1231,13 @@ struct ext4_inode_info {
 						      blocks */
 #define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
 						      file systems */
-#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
-#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
-
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
 #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+#define EXT4_MOUNT2_DAX_NEVER		0x00000020 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE		0x00000040 /* For printing options only */
+
 
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c3b864588a0b..6633b20224d5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -289,18 +289,7 @@ void ext4_superblock_csum_set(struct super_block *sb)
 	if (!ext4_has_metadata_csum(sb))
 		return;
 
-	/*
-	 * Locking the superblock prevents the scenario
-	 * where:
-	 *  1) a first thread pauses during checksum calculation.
-	 *  2) a second thread updates the superblock, recalculates
-	 *     the checksum, and updates s_checksum
-	 *  3) the first thread resumes and finishes its checksum calculation
-	 *     and updates s_checksum with a potentially stale or torn value.
-	 */
-	lock_buffer(EXT4_SB(sb)->s_sbh);
 	es->s_checksum = ext4_superblock_csum(sb, es);
-	unlock_buffer(EXT4_SB(sb)->s_sbh);
 }
 
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9cd2ecad07db..cc4f987687f3 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -77,7 +77,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 	if (error)
 		return error;
 	if (!buffer_mapped(bh_result))
-		return -EIO;
+		return -ENODATA;
 	return 0;
 }
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 8dff9cbd0a87..62d9081d1e26 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1301,12 +1301,8 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
 	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
 
 	ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp);
-	if (!ret && iomap.type == IOMAP_HOLE) {
-		if (create)
-			ret = gfs2_iomap_alloc(inode, &iomap, &mp);
-		else
-			ret = -ENODATA;
-	}
+	if (create && !ret && iomap.type == IOMAP_HOLE)
+		ret = gfs2_iomap_alloc(inode, &iomap, &mp);
 	release_metapath(&mp);
 	if (ret)
 		goto out;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 6c1432d78dce..67f2921ae8d4 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -571,7 +571,18 @@ static int freeze_go_sync(struct gfs2_glock *gl)
 	int error = 0;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
+	/*
+	 * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
+	 * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
+	 * all the nodes should have the freeze glock in SH mode and they all
+	 * call do_xmote: One for EX and the others for UN. They ALL must
+	 * freeze locally, and they ALL must queue freeze work. The freeze_work
+	 * calls freeze_func, which tries to reacquire the freeze glock in SH,
+	 * effectively waiting for the thaw on the node who holds it in EX.
+	 * Once thawed, the work func acquires the freeze glock in
+	 * SH and everybody goes back to thawed.
+	 */
+	if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) {
 		atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
 		error = freeze_super(sdp->sd_vfs);
 		if (error) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 9133b3178677..2e9314091c81 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -132,6 +132,8 @@ __acquires(&sdp->sd_ail_lock)
 		spin_unlock(&sdp->sd_ail_lock);
 		ret = generic_writepages(mapping, wbc);
 		spin_lock(&sdp->sd_ail_lock);
+		if (ret == -ENODATA) /* if a jdata write into a new hole */
+			ret = 0; /* ignore it */
 		if (ret || wbc->nr_to_write <= 0)
 			break;
 		return -EBUSY;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 92d799a193b8..f7addc6197ed 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -2529,13 +2529,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
 
 	rbm.rgd = rgd;
 	error = gfs2_rbm_from_block(&rbm, no_addr);
-	if (WARN_ON_ONCE(error))
-		goto fail;
-
-	if (gfs2_testbit(&rbm, false) != type)
-		error = -ESTALE;
+	if (!WARN_ON_ONCE(error)) {
+		if (gfs2_testbit(&rbm, false) != type)
+			error = -ESTALE;
+	}
 
 	gfs2_glock_dq_uninit(&rgd_gh);
+
 fail:
 	return error;
 }
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8018c7076b25..4ead291b2976 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3547,8 +3547,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	 * we return to userspace.
 	 */
 	if (req->flags & REQ_F_ISREG) {
-		__sb_start_write(file_inode(req->file)->i_sb,
-					SB_FREEZE_WRITE, true);
+		sb_start_write(file_inode(req->file)->i_sb);
 		__sb_writers_release(file_inode(req->file)->i_sb,
 					SB_FREEZE_WRITE);
 	}
@@ -9226,6 +9225,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 		 * to a power-of-two, if it isn't already. We do NOT impose
 		 * any cq vs sq ring sizing.
 		 */
+		p->cq_entries = roundup_pow_of_two(p->cq_entries);
 		if (p->cq_entries < p->sq_entries)
 			return -EINVAL;
 		if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
@@ -9233,7 +9233,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 				return -EINVAL;
 			p->cq_entries = IORING_MAX_CQ_ENTRIES;
 		}
-		p->cq_entries = roundup_pow_of_two(p->cq_entries);
 	} else {
 		p->cq_entries = 2 * p->sq_entries;
 	}
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 1d91dd1e8711..2febc76e9de7 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1713,6 +1713,7 @@ static void ocfs2_inode_init_once(void *data)
 
 	oi->ip_blkno = 0ULL;
 	oi->ip_clusters = 0;
+	oi->ip_next_orphan = NULL;
 
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 
diff --git a/fs/super.c b/fs/super.c
index a51c2083cd6b..98bb0629ee10 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1631,55 +1631,6 @@ int super_setup_bdi(struct super_block *sb)
 }
 EXPORT_SYMBOL(super_setup_bdi);
 
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
-{
-	bool force_trylock = false;
-	int ret = 1;
-
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * We want lockdep to tell us about possible deadlocks with freezing
-	 * but it's it bit tricky to properly instrument it. Getting a freeze
-	 * protection works as getting a read lock but there are subtle
-	 * problems. XFS for example gets freeze protection on internal level
-	 * twice in some cases, which is OK only because we already hold a
-	 * freeze protection also on higher level. Due to these cases we have
-	 * to use wait == F (trylock mode) which must not fail.
-	 */
-	if (wait) {
-		int i;
-
-		for (i = 0; i < level - 1; i++)
-			if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
-				force_trylock = true;
-				break;
-			}
-	}
-#endif
-	if (wait && !force_trylock)
-		percpu_down_read(sb->s_writers.rw_sem + level-1);
-	else
-		ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
-	WARN_ON(force_trylock && !ret);
-	return ret;
-}
-EXPORT_SYMBOL(__sb_start_write);
-
 /**
  * sb_wait_write - wait until all writers to given file system finish
  * @sb: the super for which we wait
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 340c83f76c80..2668ebe02865 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared(
 	 * record for our insertion point. This will also give us the record for
 	 * start block contiguity tests.
 	 */
-	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
+	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext,
 			&PREV, &i);
 	if (error)
 		goto done;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index beb81c84a937..577a66381327 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -243,8 +243,8 @@ xfs_rmapbt_key_diff(
 	else if (y > x)
 		return -1;
 
-	x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset));
-	y = rec->rm_offset;
+	x = be64_to_cpu(kp->rm_offset);
+	y = xfs_rmap_irec_offset_pack(rec);
 	if (x > y)
 		return 1;
 	else if (y > x)
@@ -275,8 +275,8 @@ xfs_rmapbt_diff_two_keys(
 	else if (y > x)
 		return -1;
 
-	x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset));
-	y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset));
+	x = be64_to_cpu(kp1->rm_offset);
+	y = be64_to_cpu(kp2->rm_offset);
 	if (x > y)
 		return 1;
 	else if (y > x)
@@ -390,8 +390,8 @@ xfs_rmapbt_keys_inorder(
 		return 1;
 	else if (a > b)
 		return 0;
-	a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset));
-	b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset));
+	a = be64_to_cpu(k1->rmap.rm_offset);
+	b = be64_to_cpu(k2->rmap.rm_offset);
 	if (a <= b)
 		return 1;
 	return 0;
@@ -420,8 +420,8 @@ xfs_rmapbt_recs_inorder(
 		return 1;
 	else if (a > b)
 		return 0;
-	a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset));
-	b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset));
+	a = be64_to_cpu(r1->rmap.rm_offset);
+	b = be64_to_cpu(r2->rmap.rm_offset);
 	if (a <= b)
 		return 1;
 	return 0;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 955302e7cdde..412e2ec55e38 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -113,6 +113,8 @@ xchk_bmap_get_rmap(
 
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
+	if (irec->br_state == XFS_EXT_UNWRITTEN)
+		rflags |= XFS_RMAP_UNWRITTEN;
 
 	/*
 	 * CoW staging extents are owned (on disk) by the refcountbt, so
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index beaeb6fa3119..dd672e6bbc75 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -170,7 +170,6 @@ xchk_refcountbt_process_rmap_fragments(
 	 */
 	INIT_LIST_HEAD(&worklist);
 	rbno = NULLAGBLOCK;
-	nr = 1;
 
 	/* Make sure the fragments actually /are/ in agbno order. */
 	bno = 0;
@@ -184,15 +183,14 @@ xchk_refcountbt_process_rmap_fragments(
 	 * Find all the rmaps that start at or before the refc extent,
 	 * and put them on the worklist.
 	 */
+	nr = 0;
 	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
-		if (frag->rm.rm_startblock > refchk->bno)
-			goto done;
+		if (frag->rm.rm_startblock > refchk->bno || nr > target_nr)
+			break;
 		bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
 		if (bno < rbno)
 			rbno = bno;
 		list_move_tail(&frag->list, &worklist);
-		if (nr == target_nr)
-			break;
 		nr++;
 	}
 
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index b101feb2aab4..f3082a957d5e 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -134,7 +134,7 @@ xfs_fs_map_blocks(
 		goto out_unlock;
 	error = invalidate_inode_pages2(inode->i_mapping);
 	if (WARN_ON_ONCE(error))
-		return error;
+		goto out_unlock;
 
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);