Merge tag 'dax-fixes-5.13-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull dax fixes from Dan Williams:
 "A fix for a hang condition due to missed wakeups in the filesystem-dax
  core when exercised by virtiofs.

  This bug has been there from the beginning, but the condition has
  not triggered on other filesystems since they hold a lock over
  invalidation events"

* tag 'dax-fixes-5.13-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  dax: Wake up all waiters after invalidating dax entry
  dax: Add a wakeup mode parameter to put_unlocked_entry()
  dax: Add an enum for specifying dax wakup mode

1 files changed, 23 insertions, 12 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 69216241392f..62352cbcf0f4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -144,6 +144,16 @@ struct wait_exceptional_entry_queue {
 	struct exceptional_entry_key key;
 };
 
+/**
+ * enum dax_wake_mode: waitqueue wakeup behaviour
+ * @WAKE_ALL: wake all waiters in the waitqueue
+ * @WAKE_NEXT: wake only the first waiter in the waitqueue
+ */
+enum dax_wake_mode {
+	WAKE_ALL,
+	WAKE_NEXT,
+};
+
 static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
 		void *entry, struct exceptional_entry_key *key)
 {
@@ -182,7 +192,8 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait,
  * The important information it's conveying is whether the entry at
  * this index used to be a PMD entry.
  */
-static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all)
+static void dax_wake_entry(struct xa_state *xas, void *entry,
+			   enum dax_wake_mode mode)
 {
 	struct exceptional_entry_key key;
 	wait_queue_head_t *wq;
@@ -196,7 +207,7 @@ static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all)
 	 * must be in the waitqueue and the following check will see them.
 	 */
 	if (waitqueue_active(wq))
-		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+		__wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key);
 }
 
 /*
@@ -264,11 +275,11 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry)
 	finish_wait(wq, &ewait.wait);
 }
 
-static void put_unlocked_entry(struct xa_state *xas, void *entry)
+static void put_unlocked_entry(struct xa_state *xas, void *entry,
+			       enum dax_wake_mode mode)
 {
-	/* If we were the only waiter woken, wake the next one */
 	if (entry && !dax_is_conflict(entry))
-		dax_wake_entry(xas, entry, false);
+		dax_wake_entry(xas, entry, mode);
 }
 
 /*
@@ -286,7 +297,7 @@ static void dax_unlock_entry(struct xa_state *xas, void *entry)
 	old = xas_store(xas, entry);
 	xas_unlock_irq(xas);
 	BUG_ON(!dax_is_locked(old));
-	dax_wake_entry(xas, entry, false);
+	dax_wake_entry(xas, entry, WAKE_NEXT);
 }
 
 /*
@@ -524,7 +535,7 @@ retry:
 
 		dax_disassociate_entry(entry, mapping, false);
 		xas_store(xas, NULL);	/* undo the PMD join */
-		dax_wake_entry(xas, entry, true);
+		dax_wake_entry(xas, entry, WAKE_ALL);
 		mapping->nrpages -= PG_PMD_NR;
 		entry = NULL;
 		xas_set(xas, index);
@@ -622,7 +633,7 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping,
 			entry = get_unlocked_entry(&xas, 0);
 		if (entry)
 			page = dax_busy_page(entry);
-		put_unlocked_entry(&xas, entry);
+		put_unlocked_entry(&xas, entry, WAKE_NEXT);
 		if (page)
 			break;
 		if (++scanned % XA_CHECK_SCHED)
@@ -664,7 +675,7 @@ static int __dax_invalidate_entry(struct address_space *mapping,
 	mapping->nrpages -= 1UL << dax_entry_order(entry);
 	ret = 1;
 out:
-	put_unlocked_entry(&xas, entry);
+	put_unlocked_entry(&xas, entry, WAKE_ALL);
 	xas_unlock_irq(&xas);
 	return ret;
 }
@@ -937,13 +948,13 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
 	xas_lock_irq(xas);
 	xas_store(xas, entry);
 	xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
-	dax_wake_entry(xas, entry, false);
+	dax_wake_entry(xas, entry, WAKE_NEXT);
 
 	trace_dax_writeback_one(mapping->host, index, count);
 	return ret;
 
  put_unlocked:
-	put_unlocked_entry(xas, entry);
+	put_unlocked_entry(xas, entry, WAKE_NEXT);
 	return ret;
 }
 
@@ -1684,7 +1695,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 	/* Did we race with someone splitting entry or so? */
 	if (!entry || dax_is_conflict(entry) ||
 	    (order == 0 && !dax_is_pte_entry(entry))) {
-		put_unlocked_entry(&xas, entry);
+		put_unlocked_entry(&xas, entry, WAKE_NEXT);
 		xas_unlock_irq(&xas);
 		trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
 						      VM_FAULT_NOPAGE);