drm/i915: No TLB invalidation on wedged GT

It is not an error for GuC TLB invalidations to fail when the GT is
wedged or disabled, so do not process a wait failure as one in
guc_send_invalidate_tlb.

Signed-off-by: Fei Yang <fei.yang@intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
CC: John Harrison <john.c.harrison@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231017180806.3054290-6-jonathan.cavitt@intel.com

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 1b04b1692e48d168754364bf2095e88e54b8c2e8..d37698bd6b91aeb1b39ffe729a1cbd76463d361e 100644 (file)
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -32,6 +32,7 @@
 
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "i915_irq.h"
 #include "i915_trace.h"
 
 /**
@@ -1935,6 +1936,12 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 
        /* GuC is blown away, drop all references to contexts */
        xa_destroy(&guc->context_lookup);
+
+       /*
+        * Wedged GT won't respond to any TLB invalidation request. Simply
+        * release all the blocked waiters.
+        */
+       wake_up_all_tlb_invalidate(guc);
 }
 
 void intel_guc_submission_reset_finish(struct intel_guc *guc)
@@ -4749,10 +4756,19 @@ static long must_wait_woken(struct wait_queue_entry *wq_entry, long timeout)
        return timeout;
 }
 
+static bool intel_gt_is_enabled(const struct intel_gt *gt)
+{
+       /* Check if GT is wedged or suspended */
+       if (intel_gt_is_wedged(gt) || !intel_irqs_enabled(gt->i915))
+               return false;
+       return true;
+}
+
 static int guc_send_invalidate_tlb(struct intel_guc *guc,
                                   enum intel_guc_tlb_invalidation_type type)
 {
        struct intel_guc_tlb_wait _wq, *wq = &_wq;
+       struct intel_gt *gt = guc_to_gt(guc);
        DEFINE_WAIT_FUNC(wait, woken_wake_function);
        int err;
        u32 seqno;
@@ -4766,6 +4782,13 @@ static int guc_send_invalidate_tlb(struct intel_guc *guc,
        };
        u32 size = ARRAY_SIZE(action);
 
+       /*
+        * Early guard against GT enablement.  TLB invalidation should not be
+        * attempted if the GT is disabled due to suspend/wedge.
+        */
+       if (!intel_gt_is_enabled(gt))
+               return -EINVAL;
+
        init_waitqueue_head(&_wq.wq);
 
        if (xa_alloc_cyclic_irq(&guc->tlb_lookup, &seqno, wq,
@@ -4798,7 +4821,14 @@ static int guc_send_invalidate_tlb(struct intel_guc *guc,
        if (err)
                goto out;
 
-       if (!must_wait_woken(&wait, intel_guc_ct_max_queue_time_jiffies())) {
+       /*
+        * Late guard against GT enablement.  It is not an error for the TLB
+        * invalidation to time out if the GT is disabled during the process
+        * due to suspend/wedge.  In fact, the TLB invalidation is cancelled
+        * in this case.
+        */
+       if (!must_wait_woken(&wait, intel_guc_ct_max_queue_time_jiffies()) &&
+           intel_gt_is_enabled(gt)) {
                guc_err(guc,
                        "TLB invalidation response timed out for seqno %u\n", seqno);
                err = -ETIME;