Merge tag 'for-linus-20190524' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Keith, with fixes from a few folks.

 - bio and sbitmap before atomic barrier fixes (Andrea)

 - Hang fix for blk-mq freeze and unfreeze (Bob)

 - Single segment count regression fix (Christoph)

 - AoE now has a new maintainer

 - tools/io_uring/ Makefile fix, and sync with liburing (me)

* tag 'for-linus-20190524' of git://git.kernel.dk/linux-block: (23 commits)
  tools/io_uring: sync with liburing
  tools/io_uring: fix Makefile for pthread library link
  blk-mq: fix hang caused by freeze/unfreeze sequence
  block: remove the bi_seg_{front,back}_size fields in struct bio
  block: remove the segment size check in bio_will_gap
  block: force an unlimited segment size on queues with a virt boundary
  block: don't decrement nr_phys_segments for physically contigous segments
  sbitmap: fix improper use of smp_mb__before_atomic()
  bio: fix improper use of smp_mb__before_atomic()
  aoe: list new maintainer for aoe driver
  nvme-pci: use blk-mq mapping for unmanaged irqs
  nvme: update MAINTAINERS
  nvme: copy MTFA field from identify controller
  nvme: fix memory leak for power latency tolerance
  nvme: release namespace SRCU protection before performing controller ioctls
  nvme: merge nvme_ns_ioctl into nvme_ioctl
  nvme: remove the ifdef around nvme_nvm_ioctl
  nvme: fix srcu locking on error return in nvme_get_ns_from_disk
  nvme: Fix known effects
  nvme-pci: Sync queues on reset
  ...

3 files changed, 76 insertions, 41 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7da80f375315..1b7c2afd84cb 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1257,9 +1257,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return 0;
 	}
 
-	effects |= nvme_known_admin_effects(opcode);
 	if (ctrl->effects)
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+	effects |= nvme_known_admin_effects(opcode);
 
 	/*
 	 * For simplicity, IO to all namespaces is quiesced even if the command
@@ -1361,9 +1361,14 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 {
 #ifdef CONFIG_NVME_MULTIPATH
 	if (disk->fops == &nvme_ns_head_ops) {
+		struct nvme_ns *ns;
+
 		*head = disk->private_data;
 		*srcu_idx = srcu_read_lock(&(*head)->srcu);
-		return nvme_find_path(*head);
+		ns = nvme_find_path(*head);
+		if (!ns)
+			srcu_read_unlock(&(*head)->srcu, *srcu_idx);
+		return ns;
 	}
 #endif
 	*head = NULL;
@@ -1377,42 +1382,56 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 		srcu_read_unlock(&head->srcu, idx);
 }
 
-static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned cmd, unsigned long arg)
+static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
+		unsigned int cmd, unsigned long arg)
 {
+	struct nvme_ns_head *head = NULL;
+	void __user *argp = (void __user *)arg;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
+
+	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
+	if (unlikely(!ns))
+		return -EWOULDBLOCK;
+
+	/*
+	 * Handle ioctls that apply to the controller instead of the namespace
+	 * seperately and drop the ns SRCU reference early.  This avoids a
+	 * deadlock when deleting namespaces using the passthrough interface.
+	 */
+	if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
+		struct nvme_ctrl *ctrl = ns->ctrl;
+
+		nvme_get_ctrl(ns->ctrl);
+		nvme_put_ns_from_disk(head, srcu_idx);
+
+		if (cmd == NVME_IOCTL_ADMIN_CMD)
+			ret = nvme_user_cmd(ctrl, NULL, argp);
+		else
+			ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+
+		nvme_put_ctrl(ctrl);
+		return ret;
+	}
+
 	switch (cmd) {
 	case NVME_IOCTL_ID:
 		force_successful_syscall_return();
-		return ns->head->ns_id;
-	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
+		ret = ns->head->ns_id;
+		break;
 	case NVME_IOCTL_IO_CMD:
-		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
+		ret = nvme_user_cmd(ns->ctrl, ns, argp);
+		break;
 	case NVME_IOCTL_SUBMIT_IO:
-		return nvme_submit_io(ns, (void __user *)arg);
+		ret = nvme_submit_io(ns, argp);
+		break;
 	default:
-#ifdef CONFIG_NVM
 		if (ns->ndev)
-			return nvme_nvm_ioctl(ns, cmd, arg);
-#endif
-		if (is_sed_ioctl(cmd))
-			return sed_ioctl(ns->ctrl->opal_dev, cmd,
-					 (void __user *) arg);
-		return -ENOTTY;
+			ret = nvme_nvm_ioctl(ns, cmd, arg);
+		else
+			ret = -ENOTTY;
 	}
-}
-
-static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct nvme_ns_head *head = NULL;
-	struct nvme_ns *ns;
-	int srcu_idx, ret;
 
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		ret = -EWOULDBLOCK;
-	else
-		ret = nvme_ns_ioctl(ns, cmd, arg);
 	nvme_put_ns_from_disk(head, srcu_idx);
 	return ret;
 }
@@ -2557,6 +2576,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->oncs = le16_to_cpu(id->oncs);
+	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
@@ -3681,6 +3701,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	dev_pm_qos_hide_latency_tolerance(ctrl->device);
 	cdev_device_del(&ctrl->cdev, ctrl->device);
 }
 EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
@@ -3880,6 +3901,18 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
+
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_sync_queue(ns->queue);
+	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_queues);
+
 /*
  * Check we didn't inadvertently grow the command structure sizes:
  */
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 5ee75b5ff83f..55553d293a98 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -441,6 +441,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 2a8708c9ac18..f562154551ce 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -464,7 +464,7 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 		 * affinity), so use the regular blk-mq cpu mapping
 		 */
 		map->queue_offset = qoff;
-		if (i != HCTX_TYPE_POLL)
+		if (i != HCTX_TYPE_POLL && offset)
 			blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
 		else
 			blk_mq_map_queues(map);
@@ -1257,7 +1257,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd;
-	bool shutdown = false;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 	/* If PCI error recovery process is happening, we cannot reset or
@@ -1294,17 +1293,18 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
 	switch (dev->ctrl.state) {
-	case NVME_CTRL_DELETING:
-		shutdown = true;
-		/* fall through */
 	case NVME_CTRL_CONNECTING:
-	case NVME_CTRL_RESETTING:
+		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+		/* fall through */
+	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, shutdown);
+		nvme_dev_disable(dev, true);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
+	case NVME_CTRL_RESETTING:
+		return BLK_EH_RESET_TIMER;
 	default:
 		break;
 	}
@@ -2376,7 +2376,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
-	bool dead = true;
+	bool dead = true, freeze = false;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	mutex_lock(&dev->shutdown_lock);
@@ -2384,8 +2384,10 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 		u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 		if (dev->ctrl.state == NVME_CTRL_LIVE ||
-		    dev->ctrl.state == NVME_CTRL_RESETTING)
+		    dev->ctrl.state == NVME_CTRL_RESETTING) {
+			freeze = true;
 			nvme_start_freeze(&dev->ctrl);
+		}
 		dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
 			pdev->error_state  != pci_channel_io_normal);
 	}
@@ -2394,10 +2396,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	 * Give the controller a chance to complete all entered requests if
 	 * doing a safe shutdown.
 	 */
-	if (!dead) {
-		if (shutdown)
-			nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
-	}
+	if (!dead && shutdown && freeze)
+		nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
 
 	nvme_stop_queues(&dev->ctrl);
 
@@ -2492,6 +2492,7 @@ static void nvme_reset_work(struct work_struct *work)
 	 */
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
+	nvme_sync_queues(&dev->ctrl);
 
 	mutex_lock(&dev->shutdown_lock);
 	result = nvme_pci_enable(dev);