drm/xe: Fix fault on fd close after unbind

If userspace holds an fd open, unbinds the device and then closes it,
the driver shouldn't try to access the hardware. Protect it by using
drm_dev_enter()/drm_dev_exit(). This fixes the following page fault:

<6> [IGT] xe_wedged: exiting, ret=98
<1> BUG: unable to handle page fault for address: ffffc901bc5e508c
<1> #PF: supervisor read access in kernel mode
<1> #PF: error_code(0x0000) - not-present page
...
<4>   xe_lrc_update_timestamp+0x1c/0xd0 [xe]
<4>   xe_exec_queue_update_run_ticks+0x50/0xb0 [xe]
<4>   xe_exec_queue_fini+0x16/0xb0 [xe]
<4>   __guc_exec_queue_fini_async+0xc4/0x190 [xe]
<4>   guc_exec_queue_fini_async+0xa0/0xe0 [xe]
<4>   guc_exec_queue_fini+0x23/0x40 [xe]
<4>   xe_exec_queue_destroy+0xb3/0xf0 [xe]
<4>   xe_file_close+0xd4/0x1a0 [xe]
<4>   drm_file_free+0x210/0x280 [drm]
<4>   drm_close_helper.isra.0+0x6d/0x80 [drm]
<4>   drm_release_noglobal+0x20/0x90 [drm]

Fixes: 83db047d9425 ("drm/xe: Stop accumulating LRC timestamp on job_free")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3421
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218053122.2730195-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 9c94be5719008a269f0b659d7b10c70718fc4ab2..8005530b5e51e9af71327183f23cca79da14c510 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -8,6 +8,7 @@
 #include <linux/nospec.h>
 
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <uapi/drm/xe_drm.h>
 
@@ -768,9 +769,11 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
  */
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
+       struct xe_device *xe = gt_to_xe(q->gt);
        struct xe_file *xef;
        struct xe_lrc *lrc;
        u32 old_ts, new_ts;
+       int idx;
 
        /*
         * Jobs that are run during driver load may use an exec_queue, but are
@@ -780,6 +783,10 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
        if (!q->vm || !q->vm->xef)
                return;
 
+       /* Synchronize with unbind while holding the xe file open */
+       if (!drm_dev_enter(&xe->drm, &idx))
+               return;
+
        xef = q->vm->xef;
 
        /*
@@ -793,6 +800,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
        lrc = q->lrc[0];
        new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
        xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
+
+       drm_dev_exit(idx);
 }
 
 /**