drm/i915: Fix gt reset with GuC submission is disabled

Currently intel_gt_reset() kills the GuC and then resets requested
engines. This is problematic because there is a dedicated CSB FIFO
which only GuC can access and if that FIFO fills up, the hardware
will block on the next context switch until there is space that means
the system is effectively hung. If an engine is reset whilst actively
executing a context, a CSB entry will be sent to say that the context
has gone idle. Thus if reset happens on a very busy system then
killing GuC before killing the engines will lead to deadlock because
of filled up CSB FIFO.

To address this issue, the GuC should be killed only after resetting
the requested engines and before calling intel_gt_init_hw().

v2: Improve commit message(John)

Cc: John Harrison <[email protected]>
Signed-off-by: Nirmoy Das <[email protected]>
Reviewed-by: John Harrison <[email protected]>
Reviewed-by: Andi Shyti <[email protected]>
Signed-off-by: Andi Shyti <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 6990cb5c89ae9129fad852ceae4abe9f53faef56..de775f8ddc2a58f7db2ecd052c82c42ad3987113 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -879,8 +879,17 @@ static intel_engine_mask_t reset_prepare(struct intel_gt *gt)
        intel_engine_mask_t awake = 0;
        enum intel_engine_id id;
 
-       /* For GuC mode, ensure submission is disabled before stopping ring */
-       intel_uc_reset_prepare(&gt->uc);
+       /**
+        * For GuC mode with submission enabled, ensure submission
+        * is disabled before stopping ring.
+        *
+        * For GuC mode with submission disabled, ensure that GuC is not
+        * sanitized, do that after engine reset. reset_prepare()
+        * is followed by engine reset which in this mode requires GuC to
+        * process any CSB FIFO entries generated by the resets.
+        */
+       if (intel_uc_uses_guc_submission(&gt->uc))
+               intel_uc_reset_prepare(&gt->uc);
 
        for_each_engine(engine, gt, id) {
                if (intel_engine_pm_get_if_awake(engine))
@@ -1226,6 +1235,9 @@ void intel_gt_reset(struct intel_gt *gt,
 
        intel_overlay_reset(gt->i915);
 
+       /* sanitize uC after engine reset */
+       if (!intel_uc_uses_guc_submission(&gt->uc))
+               intel_uc_reset_prepare(&gt->uc);
        /*
         * Next we need to restore the context, but we don't use those
         * yet either...