1 files changed, 140 insertions, 57 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 458ac54e7b20..defcc964ecab 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -484,15 +484,17 @@ static wait_queue_head_t ublk_idr_wq;	/* wait until one idr is freed */
 
 static DEFINE_MUTEX(ublk_ctl_mutex);
 
+
+#define UBLK_MAX_UBLKS UBLK_MINORS
+
 /*
- * Max ublk devices allowed to add
+ * Max unprivileged ublk devices allowed to add
  *
  * It can be extended to one per-user limit in future or even controlled
  * by cgroup.
  */
-#define UBLK_MAX_UBLKS UBLK_MINORS
-static unsigned int ublks_max = 64;
-static unsigned int ublks_added;	/* protected by ublk_ctl_mutex */
+static unsigned int unprivileged_ublks_max = 64;
+static unsigned int unprivileged_ublks_added; /* protected by ublk_ctl_mutex */
 
 static struct miscdevice ublk_misc;
 
@@ -681,22 +683,44 @@ static int ublk_max_cmd_buf_size(void)
 	return __ublk_queue_cmd_buf_size(UBLK_MAX_QUEUE_DEPTH);
 }
 
-static inline bool ublk_queue_can_use_recovery_reissue(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O outstanding to the ublk server when it exits be reissued?
+ * If not, outstanding I/O will get errors.
+ */
+static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub)
 {
-	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
-			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
+	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
+	       (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE);
 }
 
-static inline bool ublk_queue_can_use_recovery(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O issued while there is no ublk server queue? If not, I/O
+ * issued while there is no ublk server will get errors.
+ */
+static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub)
+{
+	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+}
+
+/*
+ * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy
+ * of the device flags for smaller cache footprint - better for fast
+ * paths.
+ */
+static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq)
 {
 	return ubq->flags & UBLK_F_USER_RECOVERY;
 }
 
-static inline bool ublk_can_use_recovery(struct ublk_device *ub)
+/*
+ * Should ublk devices be stopped (i.e. no recovery possible) when the
+ * ublk server exits? If not, devices can be used again by a future
+ * incarnation of a ublk server via the start_recovery/end_recovery
+ * commands.
+ */
+static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub)
 {
-	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+	return !(ub->dev_info.flags & UBLK_F_USER_RECOVERY);
 }
 
 static void ublk_free_disk(struct gendisk *disk)
@@ -1059,6 +1083,25 @@ static void ublk_complete_rq(struct kref *ref)
 	__ublk_complete_rq(req);
 }
 
+static void ublk_do_fail_rq(struct request *req)
+{
+	struct ublk_queue *ubq = req->mq_hctx->driver_data;
+
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+		blk_mq_requeue_request(req, false);
+	else
+		__ublk_complete_rq(req);
+}
+
+static void ublk_fail_rq_fn(struct kref *ref)
+{
+	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
+			ref);
+	struct request *req = blk_mq_rq_from_pdu(data);
+
+	ublk_do_fail_rq(req);
+}
+
 /*
  * Since __ublk_rq_task_work always fails requests immediately during
  * exiting, __ublk_fail_req() is only called from abort context during
@@ -1072,10 +1115,13 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 {
 	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
 
-	if (ublk_queue_can_use_recovery_reissue(ubq))
-		blk_mq_requeue_request(req, false);
-	else
-		ublk_put_req_ref(ubq, req);
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_put(&data->ref, ublk_fail_rq_fn);
+	} else {
+		ublk_do_fail_rq(req);
+	}
 }
 
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,
@@ -1100,7 +1146,7 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq,
 		struct request *rq)
 {
 	/* We cannot process this rq so just requeue it. */
-	if (ublk_queue_can_use_recovery(ubq))
+	if (ublk_nosrv_dev_should_queue_io(ubq->dev))
 		blk_mq_requeue_request(rq, false);
 	else
 		blk_mq_end_request(rq, BLK_STS_IOERR);
@@ -1245,10 +1291,10 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 		struct ublk_device *ub = ubq->dev;
 
 		if (ublk_abort_requests(ub, ubq)) {
-			if (ublk_can_use_recovery(ub))
-				schedule_work(&ub->quiesce_work);
-			else
+			if (ublk_nosrv_should_stop_dev(ub))
 				schedule_work(&ub->stop_work);
+			else
+				schedule_work(&ub->quiesce_work);
 		}
 		return BLK_EH_DONE;
 	}
@@ -1277,7 +1323,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * Note: force_abort is guaranteed to be seen because it is set
 	 * before request queue is unqiuesced.
 	 */
-	if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort))
+	if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort))
 		return BLK_STS_IOERR;
 
 	if (unlikely(ubq->canceling)) {
@@ -1416,17 +1462,27 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 	}
 }
 
+/* Must be called when queue is frozen */
+static bool ublk_mark_queue_canceling(struct ublk_queue *ubq)
+{
+	bool canceled;
+
+	spin_lock(&ubq->cancel_lock);
+	canceled = ubq->canceling;
+	if (!canceled)
+		ubq->canceling = true;
+	spin_unlock(&ubq->cancel_lock);
+
+	return canceled;
+}
+
 static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 {
+	bool was_canceled = ubq->canceling;
 	struct gendisk *disk;
 
-	spin_lock(&ubq->cancel_lock);
-	if (ubq->canceling) {
-		spin_unlock(&ubq->cancel_lock);
+	if (was_canceled)
 		return false;
-	}
-	ubq->canceling = true;
-	spin_unlock(&ubq->cancel_lock);
 
 	spin_lock(&ub->lock);
 	disk = ub->ub_disk;
@@ -1438,14 +1494,23 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 	if (!disk)
 		return false;
 
-	/* Now we are serialized with ublk_queue_rq() */
+	/*
+	 * Now we are serialized with ublk_queue_rq()
+	 *
+	 * Make sure that ubq->canceling is set when queue is frozen,
+	 * because ublk_queue_rq() has to rely on this flag for avoiding to
+	 * touch completed uring_cmd
+	 */
 	blk_mq_quiesce_queue(disk->queue);
-	/* abort queue is for making forward progress */
-	ublk_abort_queue(ub, ubq);
+	was_canceled = ublk_mark_queue_canceling(ubq);
+	if (!was_canceled) {
+		/* abort queue is for making forward progress */
+		ublk_abort_queue(ub, ubq);
+	}
 	blk_mq_unquiesce_queue(disk->queue);
 	put_device(disk_to_dev(disk));
 
-	return true;
+	return !was_canceled;
 }
 
 static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
@@ -1498,10 +1563,10 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	ublk_cancel_cmd(ubq, io, issue_flags);
 
 	if (need_schedule) {
-		if (ublk_can_use_recovery(ub))
-			schedule_work(&ub->quiesce_work);
-		else
+		if (ublk_nosrv_should_stop_dev(ub))
 			schedule_work(&ub->stop_work);
+		else
+			schedule_work(&ub->quiesce_work);
 	}
 }
 
@@ -1621,7 +1686,7 @@ static void ublk_stop_dev(struct ublk_device *ub)
 	mutex_lock(&ub->mutex);
 	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
 		goto unlock;
-	if (ublk_can_use_recovery(ub)) {
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
 		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
 			__ublk_quiesce_dev(ub);
 		ublk_unquiesce_dev(ub);
@@ -1816,10 +1881,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	return -EIOCBQUEUED;
 
  out:
-	io_uring_cmd_done(cmd, ret, 0, issue_flags);
 	pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n",
 			__func__, cmd_op, tag, ret, io->flags);
-	return -EIOCBQUEUED;
+	return ret;
 }
 
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
@@ -1875,7 +1939,10 @@ static inline int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
 static void ublk_ch_uring_cmd_cb(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
-	ublk_ch_uring_cmd_local(cmd, issue_flags);
+	int ret = ublk_ch_uring_cmd_local(cmd, issue_flags);
+
+	if (ret != -EIOCBQUEUED)
+		io_uring_cmd_done(cmd, ret, 0, issue_flags);
 }
 
 static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
@@ -2049,7 +2116,7 @@ static void ublk_deinit_queues(struct ublk_device *ub)
 
 	for (i = 0; i < nr_queues; i++)
 		ublk_deinit_queue(ub, i);
-	kfree(ub->__queues);
+	kvfree(ub->__queues);
 }
 
 static int ublk_init_queues(struct ublk_device *ub)
@@ -2060,7 +2127,7 @@ static int ublk_init_queues(struct ublk_device *ub)
 	int i, ret = -ENOMEM;
 
 	ub->queue_size = ubq_size;
-	ub->__queues = kcalloc(nr_queues, ubq_size, GFP_KERNEL);
+	ub->__queues = kvcalloc(nr_queues, ubq_size, GFP_KERNEL);
 	if (!ub->__queues)
 		return ret;
 
@@ -2140,7 +2207,8 @@ static int ublk_add_chdev(struct ublk_device *ub)
 	if (ret)
 		goto fail;
 
-	ublks_added++;
+	if (ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV)
+		unprivileged_ublks_added++;
 	return 0;
  fail:
 	put_device(dev);
@@ -2178,12 +2246,17 @@ static int ublk_add_tag_set(struct ublk_device *ub)
 
 static void ublk_remove(struct ublk_device *ub)
 {
+	bool unprivileged;
+
 	ublk_stop_dev(ub);
 	cancel_work_sync(&ub->stop_work);
 	cancel_work_sync(&ub->quiesce_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
+	unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
 	ublk_put_device(ub);
-	ublks_added--;
+
+	if (unprivileged)
+		unprivileged_ublks_added--;
 }
 
 static struct ublk_device *ublk_get_device_from_id(int idx)
@@ -2384,6 +2457,10 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	if (copy_from_user(&info, argp, sizeof(info)))
 		return -EFAULT;
 
+	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth ||
+	    info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues)
+		return -EINVAL;
+
 	if (capable(CAP_SYS_ADMIN))
 		info.flags &= ~UBLK_F_UNPRIVILEGED_DEV;
 	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
@@ -2432,7 +2509,8 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 		return ret;
 
 	ret = -EACCES;
-	if (ublks_added >= ublks_max)
+	if ((info.flags & UBLK_F_UNPRIVILEGED_DEV) &&
+	    unprivileged_ublks_added >= unprivileged_ublks_max)
 		goto out_unlock;
 
 	ret = -ENOMEM;
@@ -2665,9 +2743,12 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	if (ph.len > sizeof(struct ublk_params))
 		ph.len = sizeof(struct ublk_params);
 
-	/* parameters can only be changed when device isn't live */
 	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
+	if (test_bit(UB_STATE_USED, &ub->state)) {
+		/*
+		 * Parameters can only be changed when device hasn't
+		 * been started yet
+		 */
 		ret = -EACCES;
 	} else if (copy_from_user(&ub->params, argp, ph.len)) {
 		ret = -EFAULT;
@@ -2716,7 +2797,7 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 	int i;
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 	if (!ub->nr_queues_ready)
 		goto out_unlock;
@@ -2769,7 +2850,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 
 	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
@@ -2990,10 +3071,9 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	if (ub)
 		ublk_put_device(ub);
  out:
-	io_uring_cmd_done(cmd, ret, 0, issue_flags);
 	pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n",
 			__func__, ret, cmd->cmd_op, header->dev_id, header->queue_id);
-	return -EIOCBQUEUED;
+	return ret;
 }
 
 static const struct file_operations ublk_ctl_fops = {
@@ -3057,23 +3137,26 @@ static void __exit ublk_exit(void)
 module_init(ublk_init);
 module_exit(ublk_exit);
 
-static int ublk_set_max_ublks(const char *buf, const struct kernel_param *kp)
+static int ublk_set_max_unprivileged_ublks(const char *buf,
+					   const struct kernel_param *kp)
 {
 	return param_set_uint_minmax(buf, kp, 0, UBLK_MAX_UBLKS);
 }
 
-static int ublk_get_max_ublks(char *buf, const struct kernel_param *kp)
+static int ublk_get_max_unprivileged_ublks(char *buf,
+					   const struct kernel_param *kp)
 {
-	return sysfs_emit(buf, "%u\n", ublks_max);
+	return sysfs_emit(buf, "%u\n", unprivileged_ublks_max);
 }
 
-static const struct kernel_param_ops ublk_max_ublks_ops = {
-	.set = ublk_set_max_ublks,
-	.get = ublk_get_max_ublks,
+static const struct kernel_param_ops ublk_max_unprivileged_ublks_ops = {
+	.set = ublk_set_max_unprivileged_ublks,
+	.get = ublk_get_max_unprivileged_ublks,
 };
 
-module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644);
-MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)");
+module_param_cb(ublks_max, &ublk_max_unprivileged_ublks_ops,
+		&unprivileged_ublks_max, 0644);
+MODULE_PARM_DESC(ublks_max, "max number of unprivileged ublk devices allowed to add(default: 64)");
 
 MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>");
 MODULE_DESCRIPTION("Userspace block device");