NVMe: Simplify device resume on io queue failure

Releasing IO queues and disks was done in a work queue outside the
controller resume context to delete namespaces if the controller failed
after a resume from suspend. This is unnecessary since we can resume
a device asynchronously.

This patch makes resume use probe_work so it can directly remove
namespaces if the device is manageable but not IO capable. Since the
deleting disks was the only reason we had the convoluted "reset_workfn",
this patch removes that unnecessary indirection.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 904b54fcbbcd7ae1517253ed7a6556f4d7f96ec0..bf35846558c8e349e8c7bc72089c08a0ed74cf23 100644 (file)
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -1285,7 +1285,6 @@ static void nvme_abort_req(struct request *req)
                list_del_init(&dev->node);
                dev_warn(dev->dev, "I/O %d QID %d timeout, reset controller\n",
                                                        req->tag, nvmeq->qid);
-               dev->reset_workfn = nvme_reset_failed_dev;
                queue_work(nvme_workq, &dev->reset_work);
  out:
                spin_unlock_irqrestore(&dev_list_lock, flags);
@@ -2089,7 +2088,6 @@ static int nvme_kthread(void *data)
                                dev_warn(dev->dev,
                                        "Failed status: %x, reset controller\n",
                                        readl(&dev->bar->csts));
-                               dev->reset_workfn = nvme_reset_failed_dev;
                                queue_work(nvme_workq, &dev->reset_work);
                                continue;
                        }
@@ -3025,14 +3023,6 @@ static int nvme_remove_dead_ctrl(void *arg)
        return 0;
 }
 
-static void nvme_remove_disks(struct work_struct *ws)
-{
-       struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
-
-       nvme_free_queues(dev, 1);
-       nvme_dev_remove(dev);
-}
-
 static int nvme_dev_resume(struct nvme_dev *dev)
 {
        int ret;
@@ -3041,10 +3031,9 @@ static int nvme_dev_resume(struct nvme_dev *dev)
        if (ret)
                return ret;
        if (dev->online_queues < 2) {
-               spin_lock(&dev_list_lock);
-               dev->reset_workfn = nvme_remove_disks;
-               queue_work(nvme_workq, &dev->reset_work);
-               spin_unlock(&dev_list_lock);
+               dev_warn(dev->dev, "IO queues not created\n");
+               nvme_free_queues(dev, 1);
+               nvme_dev_remove(dev);
        } else {
                nvme_unfreeze_queues(dev);
                nvme_dev_add(dev);
@@ -3091,12 +3080,6 @@ static void nvme_reset_failed_dev(struct work_struct *ws)
        nvme_dev_reset(dev);
 }
 
-static void nvme_reset_workfn(struct work_struct *work)
-{
-       struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
-       dev->reset_workfn(work);
-}
-
 static int nvme_reset(struct nvme_dev *dev)
 {
        int ret = -EBUSY;
@@ -3106,7 +3089,6 @@ static int nvme_reset(struct nvme_dev *dev)
 
        spin_lock(&dev_list_lock);
        if (!work_pending(&dev->reset_work)) {
-               dev->reset_workfn = nvme_reset_failed_dev;
                queue_work(nvme_workq, &dev->reset_work);
                ret = 0;
        }
@@ -3159,8 +3141,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
                goto free;
 
        INIT_LIST_HEAD(&dev->namespaces);
-       dev->reset_workfn = nvme_reset_failed_dev;
-       INIT_WORK(&dev->reset_work, nvme_reset_workfn);
+       INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
        dev->dev = get_device(&pdev->dev);
        pci_set_drvdata(pdev, dev);
        result = nvme_set_instance(dev);
@@ -3223,7 +3204,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
        if (prepare)
                nvme_dev_shutdown(dev);
        else
-               nvme_dev_resume(dev);
+               schedule_work(&dev->probe_work);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
@@ -3277,10 +3258,7 @@ static int nvme_resume(struct device *dev)
        struct pci_dev *pdev = to_pci_dev(dev);
        struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-       if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
-               ndev->reset_workfn = nvme_reset_failed_dev;
-               queue_work(nvme_workq, &ndev->reset_work);
-       }
+       schedule_work(&ndev->probe_work);
        return 0;
 }
 #endif

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 992b9c11867882fe9aa2e54a239939f237cef9fb..7725b4c8b718a5a5e628d0327ba484603a520bb6 100644 (file)
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -104,7 +104,6 @@ struct nvme_dev {
        struct list_head namespaces;
        struct kref kref;
        struct device *device;
-       work_func_t reset_workfn;
        struct work_struct reset_work;
        struct work_struct probe_work;
        struct work_struct scan_work;