NVMe: Don't unmap controller registers on reset

Commit b00a726a9fd82ddd4c10344e46f0d371e1674303 upstream.

Unmapping the registers on reset or shutdown is not necessary. Keeping
the mapping simplifies reset handling.

This was backported to 4.4 stable tree because it prevents a race
between the reset_work and the shutdown hook, that may provoke the Oops
below, in the nvme_wait_ready function.

The Oops is easily reproducible on systems that will kexec/reboot
immediately after booting, which is actually the common use case for
kexec based bootloaders, like Petitboot.  This patch removes the
unnecessary early unmapping of the PCI configuration in the shutdown
hook, allowing a proper handling of the reset work.

Unable to handle kernel paging request for data at address 0x0000001c
Faulting instruction address: 0xd000000000720b38
cpu 0x1b: Vector: 300 (Data Access) at [c000007f7a9a38a0]
    pc: d000000000720b38: nvme_wait_ready+0x50/0x120 [nvme]
    lr: d000000000720b7c: nvme_wait_ready+0x94/0x120 [nvme]
    sp: c000007f7a9a3b20
   msr: 9000000000009033
   dar: 1c
 dsisr: 40000000
  current = 0xc000007f7a926c80
  paca    = 0xc00000000fe85100   softe: 0        irq_happened: 0x01
    pid   = 2608, comm = kworker/27:1
enter ? for help
[c000007f7a9a3bb0] d00000000072572c nvme_setup_io_queues+0xc08/0x1218 [nvme]
[c000007f7a9a3c70] c00000000006bbd8 process_one_work+0x228/0x378
[c000007f7a9a3d00] c00000000006c050 worker_thread+0x2e0/0x420
[c000007f7a9a3d80] c00000000007161c kthread+0xfc/0x108
[c000007f7a9a3e30] c0000000000094b4 ret_from_kernel_thread+0x5c/0xa8

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
	[Backport to v4.4.y]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0c67b57be83c4630a89c670acbbd150b65ec667f..289a5df0d44ad9225ee34bed0b5847ea5547fc3d 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2672,10 +2672,10 @@ static int nvme_dev_add(struct nvme_dev *dev)
        return 0;
 }
 
-static int nvme_dev_map(struct nvme_dev *dev)
+static int nvme_pci_enable(struct nvme_dev *dev)
 {
        u64 cap;
-       int bars, result = -ENOMEM;
+       int result = -ENOMEM;
        struct pci_dev *pdev = to_pci_dev(dev->dev);
 
        if (pci_enable_device_mem(pdev))
@@ -2683,24 +2683,14 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
        dev->entry[0].vector = pdev->irq;
        pci_set_master(pdev);
-       bars = pci_select_bars(pdev, IORESOURCE_MEM);
-       if (!bars)
-               goto disable_pci;
-
-       if (pci_request_selected_regions(pdev, bars, "nvme"))
-               goto disable_pci;
 
        if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
            dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
                goto disable;
 
-       dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
-       if (!dev->bar)
-               goto disable;
-
        if (readl(&dev->bar->csts) == -1) {
                result = -ENODEV;
-               goto unmap;
+               goto disable;
        }
 
        /*
@@ -2710,7 +2700,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
        if (!pdev->irq) {
                result = pci_enable_msix(pdev, dev->entry, 1);
                if (result < 0)
-                       goto unmap;
+                       goto disable;
        }
 
        cap = lo_hi_readq(&dev->bar->cap);
@@ -2734,17 +2724,20 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
        return 0;
 
- unmap:
-       iounmap(dev->bar);
-       dev->bar = NULL;
  disable:
        pci_release_regions(pdev);
- disable_pci:
-       pci_disable_device(pdev);
+
        return result;
 }
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
+{
+       if (dev->bar)
+               iounmap(dev->bar);
+       pci_release_regions(to_pci_dev(dev->dev));
+}
+
+static void nvme_pci_disable(struct nvme_dev *dev)
 {
        struct pci_dev *pdev = to_pci_dev(dev->dev);
 
@@ -2753,12 +2746,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev)
        else if (pdev->msix_enabled)
                pci_disable_msix(pdev);
 
-       if (dev->bar) {
-               iounmap(dev->bar);
-               dev->bar = NULL;
-               pci_release_regions(pdev);
-       }
-
        if (pci_is_enabled(pdev))
                pci_disable_device(pdev);
 }
@@ -2962,7 +2949,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 
        nvme_dev_list_remove(dev);
 
-       if (dev->bar) {
+       if (pci_is_enabled(to_pci_dev(dev->dev))) {
                nvme_freeze_queues(dev);
                csts = readl(&dev->bar->csts);
        }
@@ -2976,7 +2963,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
                nvme_shutdown_ctrl(dev);
                nvme_disable_queue(dev, 0);
        }
-       nvme_dev_unmap(dev);
+       nvme_pci_disable(dev);
 
        for (i = dev->queue_count - 1; i >= 0; i--)
                nvme_clear_queue(dev->queues[i]);
@@ -3136,7 +3123,7 @@ static void nvme_probe_work(struct work_struct *work)
        bool start_thread = false;
        int result;
 
-       result = nvme_dev_map(dev);
+       result = nvme_pci_enable(dev);
        if (result)
                goto out;
 
@@ -3292,6 +3279,27 @@ static ssize_t nvme_sysfs_reset(struct device *dev,
 }
 static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
 
+static int nvme_dev_map(struct nvme_dev *dev)
+{
+       int bars;
+       struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+       bars = pci_select_bars(pdev, IORESOURCE_MEM);
+       if (!bars)
+               return -ENODEV;
+       if (pci_request_selected_regions(pdev, bars, "nvme"))
+               return -ENODEV;
+
+       dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+       if (!dev->bar)
+               goto release;
+
+       return 0;
+release:
+       pci_release_regions(pdev);
+       return -ENODEV;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
        int node, result = -ENOMEM;
@@ -3317,6 +3325,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
        INIT_WORK(&dev->reset_work, nvme_reset_work);
        dev->dev = get_device(&pdev->dev);
        pci_set_drvdata(pdev, dev);
+
+       result = nvme_dev_map(dev);
+       if (result)
+               goto free;
+
        result = nvme_set_instance(dev);
        if (result)
                goto put_pci;
@@ -3355,6 +3368,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
        nvme_release_instance(dev);
  put_pci:
        put_device(dev->dev);
+       nvme_dev_unmap(dev);
  free:
        kfree(dev->queues);
        kfree(dev->entry);
@@ -3398,6 +3412,7 @@ static void nvme_remove(struct pci_dev *pdev)
        nvme_free_queues(dev, 0);
        nvme_release_cmb(dev);
        nvme_release_prp_pools(dev);
+       nvme_dev_unmap(dev);
        kref_put(&dev->kref, nvme_free_dev);
 }