Merge tag 'gfs2-v5.13-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull gfs2 fixes from Andreas Gruenbacher:
 "Various gfs2 fixes"

* tag 'gfs2-v5.13-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
  gfs2: Fix use-after-free in gfs2_glock_shrink_scan
  gfs2: Fix mmap locking for write faults
  gfs2: Clean up revokes on normal withdraws
  gfs2: fix a deadlock on withdraw-during-mount
  gfs2: fix scheduling while atomic bug in glocks
  gfs2: Fix I_NEW check in gfs2_dinode_in
  gfs2: Prevent direct-I/O write fallback errors from getting lost

8 files changed, 44 insertions, 11 deletions

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a0b542d84cd9..8a35a0196b6d 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -540,9 +540,11 @@ static vm_fault_t gfs2_fault(struct vm_fault *vmf)
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	vm_fault_t ret;
+	u16 state;
 	int err;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	state = (vmf->flags & FAULT_FLAG_WRITE) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
+	gfs2_holder_init(ip->i_gl, state, 0, &gh);
 	err = gfs2_glock_nq(&gh);
 	if (err) {
 		ret = block_page_mkwrite_return(err);
@@ -911,8 +913,11 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		current->backing_dev_info = inode_to_bdi(inode);
 		buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
 		current->backing_dev_info = NULL;
-		if (unlikely(buffered <= 0))
+		if (unlikely(buffered <= 0)) {
+			if (!ret)
+				ret = buffered;
 			goto out_unlock;
+		}
 
 		/*
 		 * We need to ensure that the page cache pages are written to
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ea7fc5c641c7..d9cb261f55b0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -582,6 +582,16 @@ out_locked:
 	spin_unlock(&gl->gl_lockref.lock);
 }
 
+static bool is_system_glock(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+	if (gl == m_ip->i_gl)
+		return true;
+	return false;
+}
+
 /**
  * do_xmote - Calls the DLM to change the state of a lock
  * @gl: The lock state
@@ -671,17 +681,25 @@ skip_inval:
 	 * to see sd_log_error and withdraw, and in the meantime, requeue the
 	 * work for later.
 	 *
+	 * We make a special exception for some system glocks, such as the
+	 * system statfs inode glock, which needs to be granted before the
+	 * gfs2_quotad daemon can exit, and that exit needs to finish before
+	 * we can unmount the withdrawn file system.
+	 *
 	 * However, if we're just unlocking the lock (say, for unmount, when
 	 * gfs2_gl_hash_clear calls clear_glock) and recovery is complete
 	 * then it's okay to tell dlm to unlock it.
 	 */
 	if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp)))
 		gfs2_withdraw_delayed(sdp);
-	if (glock_blocked_by_withdraw(gl)) {
-		if (target != LM_ST_UNLOCKED ||
-		    test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags)) {
+	if (glock_blocked_by_withdraw(gl) &&
+	    (target != LM_ST_UNLOCKED ||
+	     test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags))) {
+		if (!is_system_glock(gl)) {
 			gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD);
 			goto out;
+		} else {
+			clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
 		}
 	}
 
@@ -1466,9 +1484,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	    glock_blocked_by_withdraw(gl) &&
 	    gh->gh_gl != sdp->sd_jinode_gl) {
 		sdp->sd_glock_dqs_held++;
+		spin_unlock(&gl->gl_lockref.lock);
 		might_sleep();
 		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
 			    TASK_UNINTERRUPTIBLE);
+		spin_lock(&gl->gl_lockref.lock);
 	}
 	if (gh->gh_flags & GL_NOCACHE)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1775,6 +1795,7 @@ __acquires(&lru_lock)
 	while(!list_empty(list)) {
 		gl = list_first_entry(list, struct gfs2_glock, gl_lru);
 		list_del_init(&gl->gl_lru);
+		clear_bit(GLF_LRU, &gl->gl_flags);
 		if (!spin_trylock(&gl->gl_lockref.lock)) {
 add_back_to_lru:
 			list_add(&gl->gl_lru, &lru_list);
@@ -1820,7 +1841,6 @@ static long gfs2_scan_glock_lru(int nr)
 		if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
 			list_move(&gl->gl_lru, &dispose);
 			atomic_dec(&lru_count);
-			clear_bit(GLF_LRU, &gl->gl_flags);
 			freed++;
 			continue;
 		}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 454095e9fedf..54d3fbeb3002 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -396,7 +396,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	struct timespec64 atime;
 	u16 height, depth;
 	umode_t mode = be32_to_cpu(str->di_mode);
-	bool is_new = ip->i_inode.i_flags & I_NEW;
+	bool is_new = ip->i_inode.i_state & I_NEW;
 
 	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
 		goto corrupt;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 97d54e581a7b..42c15cfc0821 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -926,10 +926,10 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 }
 
 /**
- * ail_drain - drain the ail lists after a withdraw
+ * gfs2_ail_drain - drain the ail lists after a withdraw
  * @sdp: Pointer to GFS2 superblock
  */
-static void ail_drain(struct gfs2_sbd *sdp)
+void gfs2_ail_drain(struct gfs2_sbd *sdp)
 {
 	struct gfs2_trans *tr;
 
@@ -956,6 +956,7 @@ static void ail_drain(struct gfs2_sbd *sdp)
 		list_del(&tr->tr_list);
 		gfs2_trans_free(sdp, tr);
 	}
+	gfs2_drain_revokes(sdp);
 	spin_unlock(&sdp->sd_ail_lock);
 }
 
@@ -1162,7 +1163,6 @@ out_withdraw:
 	if (tr && list_empty(&tr->tr_list))
 		list_add(&tr->tr_list, &sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
-	ail_drain(sdp); /* frees all transactions */
 	tr = NULL;
 	goto out_end;
 }
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index eea58015710e..fc905c2af53c 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -93,5 +93,6 @@ extern int gfs2_logd(void *data);
 extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl);
 extern void gfs2_flush_revokes(struct gfs2_sbd *sdp);
+extern void gfs2_ail_drain(struct gfs2_sbd *sdp);
 
 #endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 221e7118cc3b..8ee05d25dfa6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -885,7 +885,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	gfs2_log_write_page(sdp, page);
 }
 
-static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+void gfs2_drain_revokes(struct gfs2_sbd *sdp)
 {
 	struct list_head *head = &sdp->sd_log_revokes;
 	struct gfs2_bufdata *bd;
@@ -900,6 +900,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	}
 }
 
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	gfs2_drain_revokes(sdp);
+}
+
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
 				  struct gfs2_log_header_host *head, int pass)
 {
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 31b6dd0d2e5d..f707601597dc 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -20,6 +20,7 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf);
 extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 			   struct gfs2_log_header_host *head, bool keep_cache);
+extern void gfs2_drain_revokes(struct gfs2_sbd *sdp);
 static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
 {
 	return sdp->sd_ldptrs;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 3e08027a6c81..f4325b44956d 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -131,6 +131,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc)
 		return;
 
+	gfs2_ail_drain(sdp); /* frees all transactions */
 	inode = sdp->sd_jdesc->jd_inode;
 	ip = GFS2_I(inode);
 	i_gl = ip->i_gl;