lkml.org 
[lkml]   [2014]   [Jul]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 3/3] vfio-pci: Attempt bus/slot reset on release
Date
Each time a device is released, mark whether a local reset was
successful or whether a bus/slot reset is needed. If a reset is
needed and all of the affected devices are bound to vfio-pci and
unused, allow the reset. This is most useful when the userspace
driver is killed and releases all the devices in an unclean state,
such as when a QEMU VM quits.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---

drivers/vfio/pci/vfio_pci.c | 112 +++++++++++++++++++++++++++++++++++
drivers/vfio/pci/vfio_pci_private.h | 1
2 files changed, 113 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index c4949a7..f95b90f 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -39,6 +39,8 @@ MODULE_PARM_DESC(nointxmask,

static DEFINE_MUTEX(driver_lock);

+static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
+
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
@@ -123,6 +125,8 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
vdev->barmap[bar] = NULL;
}

+ vdev->needs_reset = true;
+
/*
* If we have saved state, restore it. If we can reset the device,
* even better. Resetting with current state seems better than
@@ -154,11 +158,15 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
if (ret)
pr_warn("%s: Failed to reset device %s (%d)\n",
__func__, dev_name(&pdev->dev), ret);
+ else
+ vdev->needs_reset = false;
}

pci_restore_state(pdev);
out:
pci_disable_device(pdev);
+
+ vfio_pci_try_bus_reset(vdev);
}

static void vfio_pci_release(void *device_data)
@@ -917,6 +925,110 @@ static struct pci_driver vfio_pci_driver = {
.err_handler = &vfio_err_handlers,
};

+/*
+ * Test whether a reset is necessary and possible. We mark devices as
+ * needs_reset when they are released, but don't have a function-local reset
+ * available. If any of these exist in the affected devices, we want to do
+ * a bus/slot reset. We also need all of the affected devices to be unused,
+ * so we abort if any device has a non-zero refcnt. driver_lock prevents a
+ * device from being opened during the scan or unbound from vfio-pci.
+ */
+static int vfio_pci_test_bus_reset(struct pci_dev *pdev, void *data)
+{
+ bool *needs_reset = data;
+ struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver);
+ int ret = -EBUSY;
+
+ if (pci_drv == &vfio_pci_driver) {
+ struct vfio_device *device;
+ struct vfio_pci_device *vdev;
+
+ device = vfio_device_get_from_dev(&pdev->dev);
+ if (!device)
+ return ret;
+
+ vdev = vfio_device_data(device);
+ if (vdev) {
+ if (vdev->needs_reset)
+ *needs_reset = true;
+
+ if (!vdev->refcnt)
+ ret = 0;
+ }
+
+ vfio_device_put(device);
+ }
+
+ /*
+ * TODO: vfio-core considers groups to be viable even if some devices
+ * are attached to known drivers, like pci-stub or pcieport. We can't
+ * freeze devices from being unbound to those drivers like we can
+ * here though, so it would be racy to test for them. We also can't
+ * use device_lock() to prevent changes as that would interfere with
+ * PCI-core taking device_lock during bus reset. For now, we require
+ * devices to be bound to vfio-pci to get a bus/slot reset on release.
+ */
+
+ return ret;
+}
+
+/* Clear needs_reset on all affected devices after successful bus/slot reset */
+static int vfio_pci_clear_needs_reset(struct pci_dev *pdev, void *data)
+{
+ struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver);
+
+ if (pci_drv == &vfio_pci_driver) {
+ struct vfio_device *device;
+ struct vfio_pci_device *vdev;
+
+ device = vfio_device_get_from_dev(&pdev->dev);
+ if (!device)
+ return 0;
+
+ vdev = vfio_device_data(device);
+ if (vdev)
+ vdev->needs_reset = false;
+
+ vfio_device_put(device);
+ }
+
+ return 0;
+}
+
+/*
+ * Attempt to do a bus/slot reset if there are devices affected by a reset for
+ * this device that are needs_reset and all of the affected devices are unused
+ * (!refcnt). Callers of this function are required to hold driver_lock such
+ * that devices can not be unbound from vfio-pci or opened by a user while we
+ * test for and perform a bus/slot reset.
+ */
+static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
+{
+ bool needs_reset = false, slot = false;
+ int ret;
+
+ if (!pci_probe_reset_slot(vdev->pdev->slot))
+ slot = true;
+ else if (pci_probe_reset_bus(vdev->pdev->bus))
+ return;
+
+ if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
+ vfio_pci_test_bus_reset,
+ &needs_reset, slot) || !needs_reset)
+ return;
+
+ if (slot)
+ ret = pci_try_reset_slot(vdev->pdev->slot);
+ else
+ ret = pci_try_reset_bus(vdev->pdev->bus);
+
+ if (ret)
+ return;
+
+ vfio_pci_for_each_slot_or_bus(vdev->pdev,
+ vfio_pci_clear_needs_reset, NULL, slot);
+}
+
static void __exit vfio_pci_cleanup(void)
{
pci_unregister_driver(&vfio_pci_driver);
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 31e7a30..671c17a 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -54,6 +54,7 @@ struct vfio_pci_device {
bool extended_caps;
bool bardirty;
bool has_vga;
+ bool needs_reset;
struct pci_saved_state *pci_saved_state;
int refcnt;
struct eventfd_ctx *err_trigger;


\
 
 \ /
  Last update: 2014-07-16 21:41    [W:0.052 / U:0.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site