Merge branch 'for-4.14/block-postmerge' of git://git.kernel.dk/linux-block

Pull followup block layer updates from Jens Axboe:
 "I ended up splitting the main pull request for this series into two,
  mainly because of clashes between NVMe fixes that went into 4.13 after
  the for-4.14 branches were split off. This pull request is mostly
  NVMe, but not exclusively. In detail, it contains:

   - Two pull request for NVMe changes from Christoph. Nothing new on
     the feature front, basically just fixes all over the map for the
     core bits, transport, rdma, etc.

   - Series from Bart, cleaning up various bits in the BFQ scheduler.

   - Series of bcache fixes, which has been lingering for a release or
     two. Coly sent this in, but patches from various people in this
     area.

   - Set of patches for BFQ from Paolo himself, updating both
     documentation and fixing some corner cases in performance.

   - Series from Omar, attempting to now get the 4k loop support
     correct. Our confidence level is higher this time.

   - Series from Shaohua for loop as well, improving O_DIRECT
     performance and fixing a use-after-free"

* 'for-4.14/block-postmerge' of git://git.kernel.dk/linux-block: (74 commits)
  bcache: initialize dirty stripes in flash_dev_run()
  loop: set physical block size to logical block size
  bcache: fix bch_hprint crash and improve output
  bcache: Update continue_at() documentation
  bcache: silence static checker warning
  bcache: fix for gc and write-back race
  bcache: increase the number of open buckets
  bcache: Correct return value for sysfs attach errors
  bcache: correct cache_dirty_target in __update_writeback_rate()
  bcache: gc does not work when triggering by manual command
  bcache: Don't reinvent the wheel but use existing llist API
  bcache: do not subtract sectors_to_gc for bypassed IO
  bcache: fix sequential large write IO bypass
  bcache: Fix leak of bdev reference
  block/loop: remove unused field
  block/loop: fix use after free
  bfq: Use icq_to_bic() consistently
  bfq: Suppress compiler warnings about comparisons
  bfq: Check kstrtoul() return value
  bfq: Declare local functions static
  ...

4 files changed, 116 insertions, 72 deletions

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 78b2e0d..ceefb9a 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -206,7 +206,7 @@ static void bfqg_get(struct bfq_group *bfqg)
 	bfqg->ref++;
 }
 
-void bfqg_put(struct bfq_group *bfqg)
+static void bfqg_put(struct bfq_group *bfqg)
 {
 	bfqg->ref--;
 
@@ -385,7 +385,7 @@ static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
 	return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
 }
 
-struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
+static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
 {
 	struct bfq_group_data *bgd;
 
@@ -395,7 +395,7 @@ struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
 	return &bgd->pd;
 }
 
-void bfq_cpd_init(struct blkcg_policy_data *cpd)
+static void bfq_cpd_init(struct blkcg_policy_data *cpd)
 {
 	struct bfq_group_data *d = cpd_to_bfqgd(cpd);
 
@@ -403,12 +403,12 @@ void bfq_cpd_init(struct blkcg_policy_data *cpd)
 		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
 }
 
-void bfq_cpd_free(struct blkcg_policy_data *cpd)
+static void bfq_cpd_free(struct blkcg_policy_data *cpd)
 {
 	kfree(cpd_to_bfqgd(cpd));
 }
 
-struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
 {
 	struct bfq_group *bfqg;
 
@@ -426,7 +426,7 @@ struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
 	return &bfqg->pd;
 }
 
-void bfq_pd_init(struct blkg_policy_data *pd)
+static void bfq_pd_init(struct blkg_policy_data *pd)
 {
 	struct blkcg_gq *blkg = pd_to_blkg(pd);
 	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
@@ -445,7 +445,7 @@ void bfq_pd_init(struct blkg_policy_data *pd)
 	bfqg->rq_pos_tree = RB_ROOT;
 }
 
-void bfq_pd_free(struct blkg_policy_data *pd)
+static void bfq_pd_free(struct blkg_policy_data *pd)
 {
 	struct bfq_group *bfqg = pd_to_bfqg(pd);
 
@@ -453,7 +453,7 @@ void bfq_pd_free(struct blkg_policy_data *pd)
 	bfqg_put(bfqg);
 }
 
-void bfq_pd_reset_stats(struct blkg_policy_data *pd)
+static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
 {
 	struct bfq_group *bfqg = pd_to_bfqg(pd);
 
@@ -740,7 +740,7 @@ static void bfq_reparent_active_entities(struct bfq_data *bfqd,
  * blkio already grabs the queue_lock for us, so no need to use
  * RCU-based magic
  */
-void bfq_pd_offline(struct blkg_policy_data *pd)
+static void bfq_pd_offline(struct blkg_policy_data *pd)
 {
 	struct bfq_service_tree *st;
 	struct bfq_group *bfqg = pd_to_bfqg(pd);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 6a7a26b..a4783da 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -239,7 +239,7 @@ static int T_slow[2];
 static int T_fast[2];
 static int device_speed_thresh[2];
 
-#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
+#define RQ_BIC(rq)		icq_to_bic((rq)->elv.priv[0])
 #define RQ_BFQQ(rq)		((rq)->elv.priv[1])
 
 struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
@@ -720,7 +720,7 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
 		entity->budget = new_budget;
 		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
 					 new_budget);
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, false);
 	}
 }
 
@@ -2563,7 +2563,7 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 		bfq_del_bfqq_busy(bfqd, bfqq, true);
 	} else {
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, true);
 		/*
 		 * Resort priority tree of potential close cooperators.
 		 */
@@ -3780,6 +3780,7 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 	default:
 		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
 			"bfq: bad prio class %d\n", ioprio_class);
+		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*
 		 * No prio set, inherit CPU scheduling settings.
@@ -4801,13 +4802,15 @@ static ssize_t bfq_var_show(unsigned int var, char *page)
 	return sprintf(page, "%u\n", var);
 }
 
-static void bfq_var_store(unsigned long *var, const char *page)
+static int bfq_var_store(unsigned long *var, const char *page)
 {
 	unsigned long new_val;
 	int ret = kstrtoul(page, 10, &new_val);
 
-	if (ret == 0)
-		*var = new_val;
+	if (ret)
+		return ret;
+	*var = new_val;
+	return 0;
 }
 
 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
@@ -4848,12 +4851,16 @@ static ssize_t								\
 __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct bfq_data *bfqd = e->elevator_data;			\
-	unsigned long uninitialized_var(__data);			\
-	bfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	unsigned long __data, __min = (MIN), __max = (MAX);		\
+	int ret;							\
+									\
+	ret = bfq_var_store(&__data, (page));				\
+	if (ret)							\
+		return ret;						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	if (__CONV == 1)						\
 		*(__PTR) = msecs_to_jiffies(__data);			\
 	else if (__CONV == 2)						\
@@ -4876,12 +4883,16 @@ STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
 {									\
 	struct bfq_data *bfqd = e->elevator_data;			\
-	unsigned long uninitialized_var(__data);			\
-	bfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	unsigned long __data, __min = (MIN), __max = (MAX);		\
+	int ret;							\
+									\
+	ret = bfq_var_store(&__data, (page));				\
+	if (ret)							\
+		return ret;						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
 	return count;							\
 }
@@ -4893,9 +4904,12 @@ static ssize_t bfq_max_budget_store(struct elevator_queue *e,
 				    const char *page, size_t count)
 {
 	struct bfq_data *bfqd = e->elevator_data;
-	unsigned long uninitialized_var(__data);
+	unsigned long __data;
+	int ret;
 
-	bfq_var_store(&__data, (page));
+	ret = bfq_var_store(&__data, (page));
+	if (ret)
+		return ret;
 
 	if (__data == 0)
 		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
@@ -4918,9 +4932,12 @@ static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
 				      const char *page, size_t count)
 {
 	struct bfq_data *bfqd = e->elevator_data;
-	unsigned long uninitialized_var(__data);
+	unsigned long __data;
+	int ret;
 
-	bfq_var_store(&__data, (page));
+	ret = bfq_var_store(&__data, (page));
+	if (ret)
+		return ret;
 
 	if (__data < 1)
 		__data = 1;
@@ -4938,9 +4955,12 @@ static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
 				     const char *page, size_t count)
 {
 	struct bfq_data *bfqd = e->elevator_data;
-	unsigned long uninitialized_var(__data);
+	unsigned long __data;
+	int ret;
 
-	bfq_var_store(&__data, (page));
+	ret = bfq_var_store(&__data, (page));
+	if (ret)
+		return ret;
 
 	if (__data > 1)
 		__data = 1;
@@ -4957,9 +4977,12 @@ static ssize_t bfq_low_latency_store(struct elevator_queue *e,
 				     const char *page, size_t count)
 {
 	struct bfq_data *bfqd = e->elevator_data;
-	unsigned long uninitialized_var(__data);
+	unsigned long __data;
+	int ret;
 
-	bfq_var_store(&__data, (page));
+	ret = bfq_var_store(&__data, (page));
+	if (ret)
+		return ret;
 
 	if (__data > 1)
 		__data = 1;
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index cc4ea85..ac0809c 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -817,7 +817,6 @@ extern const int bfq_timeout;
 struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
 void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
 struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
-void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 			  struct rb_root *root);
@@ -917,7 +916,8 @@ void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			 bool ins_into_idle_tree, bool expiration);
 void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
-void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		      bool expiration);
 void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		       bool expiration);
 void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 911aa74..414ba68 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -44,7 +44,8 @@ static unsigned int bfq_class_idx(struct bfq_entity *entity)
 		BFQ_DEFAULT_GRP_CLASS - 1;
 }
 
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 bool expiration);
 
 static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
 
@@ -54,6 +55,8 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
  * @new_entity: if not NULL, pointer to the entity whose activation,
  *		requeueing or repositionig triggered the invocation of
  *		this function.
+ * @expiration: id true, this function is being invoked after the
+ *             expiration of the in-service entity
  *
  * This function is called to update sd->next_in_service, which, in
  * its turn, may change as a consequence of the insertion or
@@ -72,19 +75,20 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
  * entity.
  */
 static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
-				       struct bfq_entity *new_entity)
+				       struct bfq_entity *new_entity,
+				       bool expiration)
 {
 	struct bfq_entity *next_in_service = sd->next_in_service;
 	bool parent_sched_may_change = false;
+	bool change_without_lookup = false;
 
 	/*
 	 * If this update is triggered by the activation, requeueing
 	 * or repositiong of an entity that does not coincide with
 	 * sd->next_in_service, then a full lookup in the active tree
 	 * can be avoided. In fact, it is enough to check whether the
-	 * just-modified entity has a higher priority than
-	 * sd->next_in_service, or, even if it has the same priority
-	 * as sd->next_in_service, is eligible and has a lower virtual
+	 * just-modified entity has the same priority as
+	 * sd->next_in_service, is eligible and has a lower virtual
 	 * finish time than sd->next_in_service. If this compound
 	 * condition holds, then the new entity becomes the new
 	 * next_in_service. Otherwise no change is needed.
@@ -96,13 +100,12 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 		 * set to true, and left as true if
 		 * sd->next_in_service is NULL.
 		 */
-		bool replace_next = true;
+		change_without_lookup = true;
 
 		/*
 		 * If there is already a next_in_service candidate
-		 * entity, then compare class priorities or timestamps
-		 * to decide whether to replace sd->service_tree with
-		 * new_entity.
+		 * entity, then compare timestamps to decide whether
+		 * to replace sd->service_tree with new_entity.
 		 */
 		if (next_in_service) {
 			unsigned int new_entity_class_idx =
@@ -110,32 +113,26 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 			struct bfq_service_tree *st =
 				sd->service_tree + new_entity_class_idx;
 
-			/*
-			 * For efficiency, evaluate the most likely
-			 * sub-condition first.
-			 */
-			replace_next =
+			change_without_lookup =
 				(new_entity_class_idx ==
 				 bfq_class_idx(next_in_service)
 				 &&
 				 !bfq_gt(new_entity->start, st->vtime)
 				 &&
 				 bfq_gt(next_in_service->finish,
-					new_entity->finish))
-				||
-				new_entity_class_idx <
-				bfq_class_idx(next_in_service);
+					new_entity->finish));
 		}
 
-		if (replace_next)
+		if (change_without_lookup)
 			next_in_service = new_entity;
-	} else /* invoked because of a deactivation: lookup needed */
-		next_in_service = bfq_lookup_next_entity(sd);
+	}
+
+	if (!change_without_lookup) /* lookup needed */
+		next_in_service = bfq_lookup_next_entity(sd, expiration);
 
-	if (next_in_service) {
+	if (next_in_service)
 		parent_sched_may_change = !sd->next_in_service ||
 			bfq_update_parent_budget(next_in_service);
-	}
 
 	sd->next_in_service = next_in_service;
 
@@ -1127,10 +1124,12 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
  * @requeue: true if this is a requeue, which implies that bfqq is
  *	     being expired; thus ALL its ancestors stop being served and must
  *	     therefore be requeued
+ * @expiration: true if this function is being invoked in the expiration path
+ *             of the in-service queue
  */
 static void bfq_activate_requeue_entity(struct bfq_entity *entity,
 					bool non_blocking_wait_rq,
-					bool requeue)
+					bool requeue, bool expiration)
 {
 	struct bfq_sched_data *sd;
 
@@ -1138,7 +1137,8 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
 		sd = entity->sched_data;
 		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
 
-		if (!bfq_update_next_in_service(sd, entity) && !requeue)
+		if (!bfq_update_next_in_service(sd, entity, expiration) &&
+		    !requeue)
 			break;
 	}
 }
@@ -1194,6 +1194,8 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
  * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
  * @entity: the entity to deactivate.
  * @ins_into_idle_tree: true if the entity can be put into the idle tree
+ * @expiration: true if this function is being invoked in the expiration path
+ *             of the in-service queue
  */
 static void bfq_deactivate_entity(struct bfq_entity *entity,
 				  bool ins_into_idle_tree,
@@ -1222,7 +1224,7 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 			 * then, since entity has just been
 			 * deactivated, a new one must be found.
 			 */
-			bfq_update_next_in_service(sd, NULL);
+			bfq_update_next_in_service(sd, NULL, expiration);
 
 		if (sd->next_in_service || sd->in_service_entity) {
 			/*
@@ -1281,7 +1283,7 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 		__bfq_requeue_entity(entity);
 
 		sd = entity->sched_data;
-		if (!bfq_update_next_in_service(sd, entity) &&
+		if (!bfq_update_next_in_service(sd, entity, expiration) &&
 		    !expiration)
 			/*
 			 * next_in_service unchanged or not causing
@@ -1416,12 +1418,14 @@ __bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
 /**
  * bfq_lookup_next_entity - return the first eligible entity in @sd.
  * @sd: the sched_data.
+ * @expiration: true if we are on the expiration path of the in-service queue
  *
  * This function is invoked when there has been a change in the trees
- * for sd, and we need know what is the new next entity after this
- * change.
+ * for sd, and we need to know what is the new next entity to serve
+ * after this change.
  */
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 bool expiration)
 {
 	struct bfq_service_tree *st = sd->service_tree;
 	struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
@@ -1448,8 +1452,24 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
 	 * class, unless the idle class needs to be served.
 	 */
 	for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+		/*
+		 * If expiration is true, then bfq_lookup_next_entity
+		 * is being invoked as a part of the expiration path
+		 * of the in-service queue. In this case, even if
+		 * sd->in_service_entity is not NULL,
+		 * sd->in_service_entiy at this point is actually not
+		 * in service any more, and, if needed, has already
+		 * been properly queued or requeued into the right
+		 * tree. The reason why sd->in_service_entity is still
+		 * not NULL here, even if expiration is true, is that
+		 * sd->in_service_entiy is reset as a last step in the
+		 * expiration path. So, if expiration is true, tell
+		 * __bfq_lookup_next_entity that there is no
+		 * sd->in_service_entity.
+		 */
 		entity = __bfq_lookup_next_entity(st + class_idx,
-						  sd->in_service_entity);
+						  sd->in_service_entity &&
+						  !expiration);
 
 		if (entity)
 			break;
@@ -1562,7 +1582,7 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	for_each_entity(entity) {
 		struct bfq_sched_data *sd = entity->sched_data;
 
-		if (!bfq_update_next_in_service(sd, NULL))
+		if (!bfq_update_next_in_service(sd, NULL, false))
 			break;
 	}
 
@@ -1610,16 +1630,17 @@ void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	struct bfq_entity *entity = &bfqq->entity;
 
 	bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
-				    false);
+				    false, false);
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
 }
 
-void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		      bool expiration)
 {
 	struct bfq_entity *entity = &bfqq->entity;
 
 	bfq_activate_requeue_entity(entity, false,
-				    bfqq == bfqd->in_service_queue);
+				    bfqq == bfqd->in_service_queue, expiration);
 }
 
 /*