Merge branch 'android11-5.4' into 'android11-5.4-lts'

Sync up with android11-5.4 for the following commits:

ec1b6ab9fe BACKPORT: blk-mq: fix is_flush_rq
c9a3b51b07 BACKPORT: blk-mq: clearing flush request reference in tags->rqs[]
bb96e7f45d BACKPORT: blk-mq: clear stale request in tags->rq[] before freeing one request pool
a5d38e7c26 BACKPORT: blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter
734c36bc54 ANDROID: gki_defconfig: set DEFAULT_MMAP_MIN_ADDR=32768

Change-Id: Id6944de3e605f6a96ce03dddaa1f075cf68f24e6
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

arch/arm64/configs/gki_defconfig

@@ -99,6 +99,7 @@ CONFIG_GKI_OPT_FEATURES=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=y
 CONFIG_MEMORY_HOTPLUG=y
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
 CONFIG_CLEANCACHE=y
 CONFIG_CMA=y
 CONFIG_CMA_AREAS=16

arch/x86/configs/gki_defconfig

@@ -77,6 +77,7 @@ CONFIG_GKI_HACKS_TO_FIX=y
 CONFIG_GKI_OPT_FEATURES=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=y
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
 CONFIG_CLEANCACHE=y
 CONFIG_CMA=y
 CONFIG_CMA_AREAS=16

block/blk-flush.c

@@ -252,6 +252,11 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
+bool is_flush_rq(struct request *rq)
+{
+	return rq->end_io == flush_end_io;
+}
+
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked

block/blk-mq-tag.c

@@ -212,6 +212,22 @@ struct bt_iter_data {
 	bool reserved;
 };
 
+static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
+		unsigned int bitnr)
+{
+	struct request *rq;
+	unsigned long flags;
+	struct ext_blk_mq_tags *etags;
+
+	etags = container_of(tags, struct ext_blk_mq_tags, tags);
+	spin_lock_irqsave(&etags->lock, flags);
+	rq = tags->rqs[bitnr];
+	if (!rq || !refcount_inc_not_zero(&rq->ref))
+		rq = NULL;
+	spin_unlock_irqrestore(&etags->lock, flags);
+	return rq;
+}
+
 static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 {
 	struct bt_iter_data *iter_data = data;
@@ -219,18 +235,23 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	struct blk_mq_tags *tags = hctx->tags;
 	bool reserved = iter_data->reserved;
 	struct request *rq;
+	bool ret = true;
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
-	rq = tags->rqs[bitnr];
 
 	/*
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assigning ->rqs[].
 	 */
-	if (rq && rq->q == hctx->queue)
-		return iter_data->fn(hctx, rq, iter_data->data, reserved);
-	return true;
+	rq = blk_mq_find_and_get_req(tags, bitnr);
+	if (!rq)
+		return true;
+
+	if (rq->q == hctx->queue && rq->mq_hctx == hctx)
+		ret = iter_data->fn(hctx, rq, iter_data->data, reserved);
+	blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -273,6 +294,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	struct blk_mq_tags *tags = iter_data->tags;
 	bool reserved = iter_data->reserved;
 	struct request *rq;
+	bool ret = true;
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
@@ -281,11 +303,13 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assining ->rqs[].
 	 */
-	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_request_started(rq))
-		return iter_data->fn(rq, iter_data->data, reserved);
-
-	return true;
+	rq = blk_mq_find_and_get_req(tags, bitnr);
+	if (!rq)
+		return true;
+	if (blk_mq_request_started(rq))
+		ret = iter_data->fn(rq, iter_data->data, reserved);
+	blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -342,6 +366,9 @@ static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
  *		indicates whether or not @rq is a reserved request. Return
  *		true to continue iterating tags, false to stop.
  * @priv:	Will be passed as second argument to @fn.
+ *
+ * We grab one request reference before calling @fn and release it after
+ * @fn returns.
  */
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)
@@ -465,18 +492,21 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     int node, int alloc_policy)
 {
 	struct blk_mq_tags *tags;
+	struct ext_blk_mq_tags *etags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
 		pr_err("blk-mq: tag depth too large\n");
 		return NULL;
 	}
 
-	tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);
-	if (!tags)
+	etags = kzalloc_node(sizeof(*etags), GFP_KERNEL, node);
+	if (!etags)
 		return NULL;
 
+	tags = &etags->tags;
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
+	spin_lock_init(&etags->lock);
 
 	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
 }

block/blk-mq-tag.h

@@ -21,6 +21,21 @@ struct blk_mq_tags {
 	struct list_head page_list;
 };
 
+/*
+ * Extended tag address space map. This was needed
+ * to add a spinlock to blk_mq_tags in a KMI compliant
+ * way (no changes could be made to struct blk_mq_tags).
+ */
+struct ext_blk_mq_tags {
+	struct blk_mq_tags tags;
+
+	 /*
+	  * used to clear request reference in rqs[] before freeing one
+	  * request pool
+	  */
+	spinlock_t lock;
+};
+
 
 extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);

block/blk-mq.c

@@ -886,6 +886,14 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 	return false;
 }
 
+void blk_mq_put_rq_ref(struct request *rq)
+{
+	if (is_flush_rq(rq))
+		rq->end_io(rq, 0);
+	else if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
+}
+
 static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
@@ -919,11 +927,7 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
 
-	if (is_flush_rq(rq, hctx))
-		rq->end_io(rq, 0);
-	else if (refcount_dec_and_test(&rq->ref))
-		__blk_mq_free_request(rq);
-
+	blk_mq_put_rq_ref(rq);
 	return true;
 }
 
@@ -1971,6 +1975,47 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 	}
 }
 
+static size_t order_to_size(unsigned int order)
+{
+	return (size_t)PAGE_SIZE << order;
+}
+
+/* called before freeing request pool in @tags */
+static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set,
+		struct blk_mq_tags *tags, unsigned int hctx_idx)
+{
+	struct blk_mq_tags *drv_tags = set->tags[hctx_idx];
+	struct ext_blk_mq_tags *drv_etags;
+	struct page *page;
+	unsigned long flags;
+
+	list_for_each_entry(page, &tags->page_list, lru) {
+		unsigned long start = (unsigned long)page_address(page);
+		unsigned long end = start + order_to_size(page->private);
+		int i;
+
+		for (i = 0; i < set->queue_depth; i++) {
+			struct request *rq = drv_tags->rqs[i];
+			unsigned long rq_addr = (unsigned long)rq;
+
+			if (rq_addr >= start && rq_addr < end) {
+				WARN_ON_ONCE(refcount_read(&rq->ref) != 0);
+				cmpxchg(&drv_tags->rqs[i], rq, NULL);
+			}
+		}
+	}
+
+	/*
+	 * Wait until all pending iteration is done.
+	 *
+	 * Request reference is cleared and it is guaranteed to be observed
+	 * after the ->lock is released.
+	 */
+	drv_etags = container_of(drv_tags, struct ext_blk_mq_tags, tags);
+	spin_lock_irqsave(&drv_etags->lock, flags);
+	spin_unlock_irqrestore(&drv_etags->lock, flags);
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -2096,6 +2141,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		}
 	}
 
+	blk_mq_clear_rq_mapping(set, tags, hctx_idx);
+
 	while (!list_empty(&tags->page_list)) {
 		page = list_first_entry(&tags->page_list, struct page, lru);
 		list_del_init(&page->lru);
@@ -2155,11 +2202,6 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	return tags;
 }
 
-static size_t order_to_size(unsigned int order)
-{
-	return (size_t)PAGE_SIZE << order;
-}
-
 static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
 			       unsigned int hctx_idx, int node)
 {
@@ -2292,16 +2334,51 @@ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 					    &hctx->cpuhp_dead);
 }
 
+/*
+ * Before freeing hw queue, clearing the flush request reference in
+ * tags->rqs[] for avoiding potential UAF.
+ */
+static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
+		unsigned int queue_depth, struct request *flush_rq)
+{
+	int i;
+	unsigned long flags;
+	struct ext_blk_mq_tags *etags;
+
+	/* The hw queue may not be mapped yet */
+	if (!tags)
+		return;
+
+	WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0);
+
+	for (i = 0; i < queue_depth; i++)
+		cmpxchg(&tags->rqs[i], flush_rq, NULL);
+
+	/*
+	 * Wait until all pending iteration is done.
+	 *
+	 * Request reference is cleared and it is guaranteed to be observed
+	 * after the ->lock is released.
+	 */
+	etags = container_of(tags, struct ext_blk_mq_tags, tags);
+	spin_lock_irqsave(&etags->lock, flags);
+	spin_unlock_irqrestore(&etags->lock, flags);
+}
+
 /* hctx->ctxs will be freed in queue's release handler */
 static void blk_mq_exit_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	struct request *flush_rq = hctx->fq->flush_rq;
+
 	if (blk_mq_hw_queue_mapped(hctx))
 		blk_mq_tag_idle(hctx);
 
+	blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+			set->queue_depth, flush_rq);
 	if (set->ops->exit_request)
-		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
+		set->ops->exit_request(set, flush_rq, hctx_idx);
 
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);

block/blk-mq.h

@@ -47,6 +47,7 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
+void blk_mq_put_rq_ref(struct request *rq);
 
 /*
  * Internal helpers for allocating/freeing the request map

block/blk.h

@@ -49,11 +49,7 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
-static inline bool
-is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
-{
-	return hctx->fq->flush_rq == req;
-}
+bool is_flush_rq(struct request *req);
 
 struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 		int node, int cmd_size, gfp_t flags);