drm/xe: Remove devcoredump during driver release

This will remove devcoredump from file system and free its resources
during driver unload.

This fix the driver unload after gpu hang happened, otherwise this
it would report that Xe KMD is still in use and it would leave the
kernel in a state that Xe KMD can't be unload without a reboot.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Acked-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240409200206.108452-2-jose.souza@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 283ca7518aff202cc3862165f4171349c30fa742..3d7980232be1c37de0ad73e15fbe12297b1bddd2 100644 (file)
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -9,6 +9,8 @@
 #include <linux/devcoredump.h>
 #include <generated/utsrelease.h>
 
+#include <drm/drm_managed.h>
+
 #include "xe_device.h"
 #include "xe_exec_queue.h"
 #include "xe_force_wake.h"
@@ -235,5 +237,14 @@ void xe_devcoredump(struct xe_sched_job *job)
        dev_coredumpm(xe->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL,
                      xe_devcoredump_read, xe_devcoredump_free);
 }
-#endif
 
+static void xe_driver_devcoredump_fini(struct drm_device *drm, void *arg)
+{
+       dev_coredump_put(drm->dev);
+}
+
+int xe_devcoredump_init(struct xe_device *xe)
+{
+       return drmm_add_action_or_reset(&xe->drm, xe_driver_devcoredump_fini, xe);
+}
+#endif

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index df8671f0b5eb2fcffe7145cc28d89056c6980817..e2fa65ce0932267a18b7c3c2dc002f7cab022d07 100644 (file)
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -11,10 +11,16 @@ struct xe_sched_job;
 
 #ifdef CONFIG_DEV_COREDUMP
 void xe_devcoredump(struct xe_sched_job *job);
+int xe_devcoredump_init(struct xe_device *xe);
 #else
 static inline void xe_devcoredump(struct xe_sched_job *job)
 {
 }
+
+static inline int xe_devcoredump_init(struct xe_device *xe)
+{
+       return 0;
+}
 #endif
 
 #endif

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 927e1370e2a031400a406ee6f70c5cd90b5e6e58..d85a2ba0a05711315f55b52e959b2ce6ae4aa037 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -20,6 +20,7 @@
 #include "regs/xe_regs.h"
 #include "xe_bo.h"
 #include "xe_debugfs.h"
+#include "xe_devcoredump.h"
 #include "xe_dma_buf.h"
 #include "xe_drm_client.h"
 #include "xe_drv.h"
@@ -579,6 +580,9 @@ int xe_device_probe(struct xe_device *xe)
                        return err;
        }
 
+       err = xe_devcoredump_init(xe);
+       if (err)
+               return err;
        err = drmm_add_action_or_reset(&xe->drm, xe_driver_flr_fini, xe);
        if (err)
                return err;