@@ -26,6 +26,7 @@
* DEALINGS IN THE SOFTWARE.
*/
+#include <linux/bitops.h>
#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/module.h>
@@ -33,6 +34,7 @@
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/slab.h>
+#include <linux/sprintf.h>
#include <linux/srcu.h>
#include <linux/xarray.h>
@@ -497,6 +499,70 @@ void drm_dev_unplug(struct drm_device *dev)
}
EXPORT_SYMBOL(drm_dev_unplug);
+/*
+ * Available recovery methods for wedged device. To be sent along with device
+ * wedged uevent.
+ */
+static const char *drm_get_wedge_recovery(unsigned int opt)
+{
+ switch (BIT(opt)) {
+ case DRM_WEDGE_RECOVERY_NONE:
+ return "none";
+ case DRM_WEDGE_RECOVERY_REBIND:
+ return "rebind";
+ case DRM_WEDGE_RECOVERY_BUS_RESET:
+ return "bus-reset";
+ default:
+ return NULL;
+ }
+}
+
+/**
+ * drm_dev_wedged_event - generate a device wedged uevent
+ * @dev: DRM device
+ * @method: method(s) to be used for recovery
+ *
+ * This generates a device wedged uevent for the DRM device specified by @dev.
+ * Recovery @method\(s) of choice will be sent in the uevent environment as
+ * ``WEDGED=<method1>[,<method2>]`` in order of less to more side-effects. If
+ * caller is unsure about recovery or @method is unknown (0), ``WEDGED=unknown``
+ * will be sent instead.
+ *
+ * Refer to 'Device Wedging' chapter in Documentation/gpu/drm-uapi.rst for more
+ * details.
+ *
+ * Returns: 0 on success, negative error code otherwise.
+ */
+int drm_dev_wedged_event(struct drm_device *dev, unsigned long method)
+{
+ const char *recovery = NULL;
+ unsigned int len, opt;
+ /* Event string length up to 28+ characters with available methods */
+ char event_string[32];
+ char *envp[] = { event_string, NULL };
+
+ len = scnprintf(event_string, sizeof(event_string), "%s", "WEDGED=");
+
+ for_each_set_bit(opt, &method, BITS_PER_TYPE(method)) {
+ recovery = drm_get_wedge_recovery(opt);
+ if (drm_WARN(dev, !recovery, "device wedged, invalid recovery method %u\n", opt))
+ break;
+
+ len += scnprintf(event_string + len, sizeof(event_string), "%s,", recovery);
+ }
+
+ if (recovery)
+ /* Get rid of trailing comma */
+ event_string[len - 1] = '\0';
+ else
+ /* Caller is unsure about recovery, do the best we can at this point. */
+ snprintf(event_string, sizeof(event_string), "%s", "WEDGED=unknown");
+
+ drm_info(dev, "device wedged, needs recovery\n");
+ return kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp);
+}
+EXPORT_SYMBOL(drm_dev_wedged_event);
+
/*
* DRM internal mount
* We want to be able to allocate our own "struct address_space" to control
@@ -21,6 +21,14 @@ struct inode;
struct pci_dev;
struct pci_controller;
+/*
+ * Recovery methods for wedged device in order of less to more side-effects.
+ * To be used with drm_dev_wedged_event() as recovery @method. Callers can
+ * use any one, multiple (or'd) or none depending on their needs.
+ */
+#define DRM_WEDGE_RECOVERY_NONE BIT(0) /* optional telemetry collection */
+#define DRM_WEDGE_RECOVERY_REBIND BIT(1) /* unbind + bind driver */
+#define DRM_WEDGE_RECOVERY_BUS_RESET BIT(2) /* unbind + reset bus device + bind */
/**
* enum switch_power_state - power state of drm device
@@ -479,6 +479,7 @@ void drm_put_dev(struct drm_device *dev);
bool drm_dev_enter(struct drm_device *dev, int *idx);
void drm_dev_exit(int idx);
void drm_dev_unplug(struct drm_device *dev);
+int drm_dev_wedged_event(struct drm_device *dev, unsigned long method);
/**
* drm_dev_is_unplugged - is a DRM device unplugged
Introduce device wedged event, which notifies userspace of 'wedged' (hanged/unusable) state of the DRM device through a uevent. This is useful especially in cases where the device is no longer operating as expected and has become unrecoverable from driver context. Purpose of this implementation is to provide drivers a generic way to recover with the help of userspace intervention without taking any drastic measures in the driver. A 'wedged' device is basically a dead device that needs attention. The uevent is the notification that is sent to userspace along with a hint about what could possibly be attempted to recover the device and bring it back to usable state. Different drivers may have different ideas of a 'wedged' device depending on their hardware implementation, and hence the vendor agnostic nature of the event. It is up to the drivers to decide when they see the need for device recovery and how they want to recover from the available methods. Driver prerequisites -------------------- The driver, before opting for recovery, needs to make sure that the 'wedged' device doesn't harm the system as a whole by taking care of the prerequisites. Necessary actions must include disabling DMA to system memory as well as any communication channels with other devices. Further, the driver must ensure that all dma_fences are signalled and any device state that the core kernel might depend on is cleaned up. Any existing mmap should be invalidated and page faults should be redirected to a dummy page. Once the event is sent, the device must be kept in 'wedged' state until the recovery is performed. New accesses to the device (IOCTLs) should be blocked, preferably with an error code that resembles the type of failure the device has encountered. This will signify the reason for wedging, which can be reported to the application if needed. Recovery -------- Current implementation defines three recovery methods, out of which, drivers can use any one, multiple or none. Method(s) of choice will be sent in the uevent environment as ``WEDGED=<method1>[,<method2>]`` in order of less to more side-effects. If driver is unsure about recovery or method is unknown (like soft/hard reboot, firmware flashing, hardware replacement or any other procedure which can't be attempted on the fly), ``WEDGED=unknown`` will be sent instead. Userspace consumers can parse this event and attempt recovery as per the following expectations. =============== ================================ Recovery method Consumer expectations =============== ================================ none optional telemetry collection rebind unbind + bind driver bus-reset unbind + reset bus device + bind unknown admin/user policy =============== ================================ The only exception to this is ``WEDGED=none``, which signifies that the device was temporarily 'wedged' at some point but was able to recover using device specific methods like reset. No explicit device recovery is expected from the consumer in this case, but it can still take additional steps like gathering telemetry information (devcoredump, syslog). This is useful because the first hang is usually the most critical one which can result in consequential hangs or complete wedging. Consumer prerequisites ---------------------- It is the responsibility of the consumer to make sure that the device or its resources are not in use by any process before attempting recovery. With IOCTLs blocked and device already 'wedged', all device memory should be unmapped and file descriptors should be closed to prevent leaks. Example ------- Udev rule:: SUBSYSTEM=="drm", ENV{WEDGED}=="rebind", DEVPATH=="*/drm/card[0-9]", RUN+="/path/to/rebind.sh $env{DEVPATH}" Recovery script:: #!/bin/sh DEVPATH=$(readlink -f /sys/$1/device) DEVICE=$(basename $DEVPATH) DRIVER=$(readlink -f $DEVPATH/driver) echo -n $DEVICE > $DRIVER/unbind sleep 1 echo -n $DEVICE > $DRIVER/bind Customization ------------- Although basic recovery is possible with a simple script, admin/users can define custom policies around recovery action. For example, if the driver supports multiple recovery methods, consumers can opt for the suitable one based on policy definition. Consumers can also choose to have the device available for debugging or additional data collection before performing the recovery. This is useful especially when the driver is unsure about recovery or method is unknown. v4: s/drm_dev_wedged/drm_dev_wedged_event Use drm_info() (Jani) Kernel doc adjustment (Aravind) v5: Send recovery method with uevent (Lina) v6: Access wedge_recovery_opts[] using helper function (Jani) Use snprintf() (Jani) v7: Convert recovery helpers into regular functions (Andy, Jani) Aesthetic adjustments (Andy) Handle invalid method cases v8: Allow sending multiple methods with uevent (Lucas, Michal) static_assert() globally (Andy) v9: Provide 'none' method for reset cases (Christian) Provide recovery opts using switch cases Signed-off-by: Raag Jadav <raag.jadav@intel.com> --- drivers/gpu/drm/drm_drv.c | 66 +++++++++++++++++++++++++++++++++++++++ include/drm/drm_device.h | 8 +++++ include/drm/drm_drv.h | 1 + 3 files changed, 75 insertions(+)