[PATCH 1/4] drm/i915: Verify workarounds immediately after application

[PATCH 1/4] drm/i915: Verify workarounds immediately after application

[Chris Wilson]

Immediately after writing the workaround, verify that it stuck in the
register.

References: https://bugs.freedesktop.org/show_bug.cgi?id=108954
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/intel_workarounds.c | 32 +++++++++++++-----------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index ccaf63679435..1c54b5030807 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -913,6 +913,20 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 	return fw;
 }
 
+static bool
+wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
+{
+	if ((cur ^ wa->val) & wa->mask) {
+		DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
+			  name, from, i915_mmio_reg_offset(wa->reg), cur,
+			  cur & wa->mask, wa->val, wa->mask);
+
+		return false;
+	}
+
+	return true;
+}
+
 static void
 wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 {
@@ -931,6 +945,10 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
 		intel_uncore_rmw_fw(uncore, wa->reg, wa->mask, wa->val);
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+			wa_verify(wa,
+				  intel_uncore_read_fw(uncore, wa->reg),
+				  wal->name, "applictation");
 	}
 
 	intel_uncore_forcewake_put__locked(uncore, fw);
@@ -942,20 +960,6 @@ void intel_gt_apply_workarounds(struct drm_i915_private *i915)
 	wa_list_apply(&i915->uncore, &i915->gt_wa_list);
 }
 
-static bool
-wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
-{
-	if ((cur ^ wa->val) & wa->mask) {
-		DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
-			  name, from, i915_mmio_reg_offset(wa->reg), cur,
-			  cur & wa->mask, wa->val, wa->mask);
-
-		return false;
-	}
-
-	return true;
-}
-
 static bool wa_list_verify(struct intel_uncore *uncore,
 			   const struct i915_wa_list *wal,
 			   const char *from)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/4] drm/i915: Verify the engine workarounds stick on application

[Chris Wilson]

Read the engine workarounds back using the GPU after loading the initial
context state to verify that we are setting them correctly, and bail if
it fails.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c               |   6 +
 drivers/gpu/drm/i915/intel_workarounds.c      | 120 ++++++++++++++++++
 drivers/gpu/drm/i915/intel_workarounds.h      |   2 +
 .../drm/i915/selftests/intel_workarounds.c    |  53 +-------
 4 files changed, 134 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0a818a60ad31..95ae69753e91 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4717,6 +4717,12 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		i915_request_add(rq);
 		if (err)
 			goto err_active;
+
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) &&
+		    intel_engine_verify_workarounds(engine, "load")) {
+			err = -EIO;
+			goto err_active;
+		}
 	}
 
 	/* Flush the default context image to memory, and enable powersaving. */
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 1c54b5030807..db99f2e676bb 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -1259,6 +1259,126 @@ void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
 	wa_list_apply(engine->uncore, &engine->wa_list);
 }
 
+static struct i915_vma *
+create_scratch(struct i915_address_space *vm, int count)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	unsigned int size;
+	int err;
+
+	size = round_up(count * 4, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0,
+			   i915_vma_is_ggtt(vma) ? PIN_GLOBAL : PIN_USER);
+	if (err)
+		goto err_obj;
+
+	return vma;
+
+err_obj:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static int
+wa_list_srm(struct i915_request *rq,
+	    const struct i915_wa_list *wal,
+	    struct i915_vma *vma)
+{
+	const struct i915_wa *wa;
+	u32 srm, *cs;
+	int i;
+
+	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		srm++;
+
+	cs = intel_ring_begin(rq, 4 * wal->count);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
+		*cs++ = srm;
+		*cs++ = i915_mmio_reg_offset(wa->reg);
+		*cs++ = i915_ggtt_offset(vma) + sizeof(u32) * i;
+		*cs++ = 0;
+	}
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int engine_wa_list_verify(struct intel_engine_cs *engine,
+				 const struct i915_wa_list * const wal,
+				 const char *from)
+{
+	const struct i915_wa *wa;
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	unsigned int i;
+	u32 *results;
+	int err;
+
+	if (!wal->count)
+		return 0;
+
+	vma = create_scratch(&engine->i915->ggtt.vm, wal->count);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	rq = i915_request_alloc(engine, engine->kernel_context->gem_context);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_vma;
+	}
+
+	err = wa_list_srm(rq, wal, vma);
+	if (err)
+		goto err_vma;
+
+	i915_request_add(rq);
+	if (i915_request_wait(rq, I915_WAIT_LOCKED, HZ / 5) < 0) {
+		err = -ETIME;
+		goto err_vma;
+	}
+
+	results = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+	if (IS_ERR(results)) {
+		err = PTR_ERR(results);
+		goto err_vma;
+	}
+
+	err = 0;
+	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
+		if (!wa_verify(wa, results[i], wal->name, from))
+			err = -ENXIO;
+
+	i915_gem_object_unpin_map(vma->obj);
+
+err_vma:
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
+	return err;
+}
+
+int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
+				    const char *from)
+{
+	return engine_wa_list_verify(engine, &engine->wa_list, from);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/intel_workarounds.c"
 #endif
diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h
index 34eee5ec511e..fdf7ebb90f28 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.h
+++ b/drivers/gpu/drm/i915/intel_workarounds.h
@@ -30,5 +30,7 @@ void intel_engine_apply_whitelist(struct intel_engine_cs *engine);
 
 void intel_engine_init_workarounds(struct intel_engine_cs *engine);
 void intel_engine_apply_workarounds(struct intel_engine_cs *engine);
+int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
+				    const char *from);
 
 #endif
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 567b6f8dae86..a363748a7a4f 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -340,49 +340,6 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	return err;
 }
 
-static struct i915_vma *create_scratch(struct i915_gem_context *ctx)
-{
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	void *ptr;
-	int err;
-
-	obj = i915_gem_object_create_internal(ctx->i915, PAGE_SIZE);
-	if (IS_ERR(obj))
-		return ERR_CAST(obj);
-
-	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
-
-	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
-		goto err_obj;
-	}
-	memset(ptr, 0xc5, PAGE_SIZE);
-	i915_gem_object_flush_map(obj);
-	i915_gem_object_unpin_map(obj);
-
-	vma = i915_vma_instance(obj, &ctx->ppgtt->vm, NULL);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err_obj;
-	}
-
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
-		goto err_obj;
-
-	err = i915_gem_object_set_to_cpu_domain(obj, false);
-	if (err)
-		goto err_obj;
-
-	return vma;
-
-err_obj:
-	i915_gem_object_put(obj);
-	return ERR_PTR(err);
-}
-
 static struct i915_vma *create_batch(struct i915_gem_context *ctx)
 {
 	struct drm_i915_gem_object *obj;
@@ -475,7 +432,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 	int err = 0, i, v;
 	u32 *cs, *results;
 
-	scratch = create_scratch(ctx);
+	scratch = create_scratch(&ctx->ppgtt->vm, 2 * ARRAY_SIZE(values) + 1);
 	if (IS_ERR(scratch))
 		return PTR_ERR(scratch);
 
@@ -752,9 +709,11 @@ static bool verify_gt_engine_wa(struct drm_i915_private *i915,
 
 	ok &= wa_list_verify(&i915->uncore, &lists->gt_wa_list, str);
 
-	for_each_engine(engine, i915, id)
-		ok &= wa_list_verify(engine->uncore,
-				     &lists->engine[id].wa_list, str);
+	for_each_engine(engine, i915, id) {
+		ok &= engine_wa_list_verify(engine,
+					    &lists->engine[id].wa_list,
+					    str) == 0;
+	}
 
 	return ok;
 }
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 2/4] drm/i915: Verify the engine workarounds stick on application

[Tvrtko Ursulin]

On 13/04/2019 13:58, Chris Wilson wrote:
> Read the engine workarounds back using the GPU after loading the initial
> context state to verify that we are setting them correctly, and bail if
> it fails.

Aren't the context wa/ ones we expect to see saved in the context? As 
such, what difference do you expect to see between mmio and srm 
verification? Should even both be done?

> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
>   drivers/gpu/drm/i915/i915_gem.c               |   6 +
>   drivers/gpu/drm/i915/intel_workarounds.c      | 120 ++++++++++++++++++
>   drivers/gpu/drm/i915/intel_workarounds.h      |   2 +
>   .../drm/i915/selftests/intel_workarounds.c    |  53 +-------
>   4 files changed, 134 insertions(+), 47 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 0a818a60ad31..95ae69753e91 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4717,6 +4717,12 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
>   		i915_request_add(rq);
>   		if (err)
>   			goto err_active;
> +
> +		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) &&
> +		    intel_engine_verify_workarounds(engine, "load")) {
> +			err = -EIO;
> +			goto err_active;

I am not sure that wedging is required even if only in debug builds. Is 
DRM_ERROR not enough to flag failures?

> +		}
>   	}
>   
>   	/* Flush the default context image to memory, and enable powersaving. */
> diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
> index 1c54b5030807..db99f2e676bb 100644
> --- a/drivers/gpu/drm/i915/intel_workarounds.c
> +++ b/drivers/gpu/drm/i915/intel_workarounds.c
> @@ -1259,6 +1259,126 @@ void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
>   	wa_list_apply(engine->uncore, &engine->wa_list);
>   }
>   
> +static struct i915_vma *
> +create_scratch(struct i915_address_space *vm, int count)
> +{
> +	struct drm_i915_gem_object *obj;
> +	struct i915_vma *vma;
> +	unsigned int size;
> +	int err;
> +
> +	size = round_up(count * 4, PAGE_SIZE);
> +	obj = i915_gem_object_create_internal(vm->i915, size);
> +	if (IS_ERR(obj))
> +		return ERR_CAST(obj);
> +
> +	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
> +
> +	vma = i915_vma_instance(obj, vm, NULL);
> +	if (IS_ERR(vma)) {
> +		err = PTR_ERR(vma);
> +		goto err_obj;
> +	}
> +
> +	err = i915_vma_pin(vma, 0, 0,
> +			   i915_vma_is_ggtt(vma) ? PIN_GLOBAL : PIN_USER);
> +	if (err)
> +		goto err_obj;
> +
> +	return vma;
> +
> +err_obj:
> +	i915_gem_object_put(obj);
> +	return ERR_PTR(err);
> +}
> +
> +static int
> +wa_list_srm(struct i915_request *rq,
> +	    const struct i915_wa_list *wal,
> +	    struct i915_vma *vma)
> +{
> +	const struct i915_wa *wa;
> +	u32 srm, *cs;
> +	int i;
> +
> +	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
> +	if (INTEL_GEN(rq->i915) >= 8)
> +		srm++;
> +
> +	cs = intel_ring_begin(rq, 4 * wal->count);
> +	if (IS_ERR(cs))
> +		return PTR_ERR(cs);
> +
> +	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
> +		*cs++ = srm;
> +		*cs++ = i915_mmio_reg_offset(wa->reg);
> +		*cs++ = i915_ggtt_offset(vma) + sizeof(u32) * i;
> +		*cs++ = 0;
> +	}
> +	intel_ring_advance(rq, cs);
> +
> +	return 0;
> +}
> +
> +static int engine_wa_list_verify(struct intel_engine_cs *engine,
> +				 const struct i915_wa_list * const wal,
> +				 const char *from)
> +{
> +	const struct i915_wa *wa;
> +	struct i915_request *rq;
> +	struct i915_vma *vma;
> +	unsigned int i;
> +	u32 *results;
> +	int err;
> +
> +	if (!wal->count)
> +		return 0;
> +
> +	vma = create_scratch(&engine->i915->ggtt.vm, wal->count);
> +	if (IS_ERR(vma))
> +		return PTR_ERR(vma);
> +
> +	rq = i915_request_alloc(engine, engine->kernel_context->gem_context);
> +	if (IS_ERR(rq)) {
> +		err = PTR_ERR(rq);
> +		goto err_vma;
> +	}
> +
> +	err = wa_list_srm(rq, wal, vma);
> +	if (err)
> +		goto err_vma;
> +
> +	i915_request_add(rq);
> +	if (i915_request_wait(rq, I915_WAIT_LOCKED, HZ / 5) < 0) {
> +		err = -ETIME;
> +		goto err_vma;
> +	}
> +
> +	results = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
> +	if (IS_ERR(results)) {
> +		err = PTR_ERR(results);
> +		goto err_vma;
> +	}
> +
> +	err = 0;
> +	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
> +		if (!wa_verify(wa, results[i], wal->name, from))
> +			err = -ENXIO;
> +
> +	i915_gem_object_unpin_map(vma->obj);
> +
> +err_vma:
> +	i915_vma_unpin(vma);
> +	i915_vma_put(vma);
> +	return err;
> +}
> +
> +int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
> +				    const char *from)
> +{
> +	return engine_wa_list_verify(engine, &engine->wa_list, from);
> +}
> +
>   #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
>   #include "selftests/intel_workarounds.c"
>   #endif
> diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h
> index 34eee5ec511e..fdf7ebb90f28 100644
> --- a/drivers/gpu/drm/i915/intel_workarounds.h
> +++ b/drivers/gpu/drm/i915/intel_workarounds.h
> @@ -30,5 +30,7 @@ void intel_engine_apply_whitelist(struct intel_engine_cs *engine);
>   
>   void intel_engine_init_workarounds(struct intel_engine_cs *engine);
>   void intel_engine_apply_workarounds(struct intel_engine_cs *engine);
> +int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
> +				    const char *from);
>   
>   #endif
> diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
> index 567b6f8dae86..a363748a7a4f 100644
> --- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
> +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
> @@ -340,49 +340,6 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
>   	return err;
>   }
>   
> -static struct i915_vma *create_scratch(struct i915_gem_context *ctx)
> -{
> -	struct drm_i915_gem_object *obj;
> -	struct i915_vma *vma;
> -	void *ptr;
> -	int err;
> -
> -	obj = i915_gem_object_create_internal(ctx->i915, PAGE_SIZE);
> -	if (IS_ERR(obj))
> -		return ERR_CAST(obj);
> -
> -	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
> -
> -	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
> -	if (IS_ERR(ptr)) {
> -		err = PTR_ERR(ptr);
> -		goto err_obj;
> -	}
> -	memset(ptr, 0xc5, PAGE_SIZE);
> -	i915_gem_object_flush_map(obj);
> -	i915_gem_object_unpin_map(obj);
> -
> -	vma = i915_vma_instance(obj, &ctx->ppgtt->vm, NULL);
> -	if (IS_ERR(vma)) {
> -		err = PTR_ERR(vma);
> -		goto err_obj;
> -	}
> -
> -	err = i915_vma_pin(vma, 0, 0, PIN_USER);
> -	if (err)
> -		goto err_obj;
> -
> -	err = i915_gem_object_set_to_cpu_domain(obj, false);
> -	if (err)
> -		goto err_obj;
> -
> -	return vma;
> -
> -err_obj:
> -	i915_gem_object_put(obj);
> -	return ERR_PTR(err);
> -}
> -
>   static struct i915_vma *create_batch(struct i915_gem_context *ctx)
>   {
>   	struct drm_i915_gem_object *obj;
> @@ -475,7 +432,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
>   	int err = 0, i, v;
>   	u32 *cs, *results;
>   
> -	scratch = create_scratch(ctx);
> +	scratch = create_scratch(&ctx->ppgtt->vm, 2 * ARRAY_SIZE(values) + 1);
>   	if (IS_ERR(scratch))
>   		return PTR_ERR(scratch);
>   
> @@ -752,9 +709,11 @@ static bool verify_gt_engine_wa(struct drm_i915_private *i915,
>   
>   	ok &= wa_list_verify(&i915->uncore, &lists->gt_wa_list, str);
>   
> -	for_each_engine(engine, i915, id)
> -		ok &= wa_list_verify(engine->uncore,
> -				     &lists->engine[id].wa_list, str);
> +	for_each_engine(engine, i915, id) {
> +		ok &= engine_wa_list_verify(engine,
> +					    &lists->engine[id].wa_list,
> +					    str) == 0;
> +	}
>   
>   	return ok;
>   }
> 

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 2/4] drm/i915: Verify the engine workarounds stick on application

[Chris Wilson]

Quoting Tvrtko Ursulin (2019-04-15 11:41:43)
> 
> On 13/04/2019 13:58, Chris Wilson wrote:
> > Read the engine workarounds back using the GPU after loading the initial
> > context state to verify that we are setting them correctly, and bail if
> > it fails.
> 
> Aren't the context wa/ ones we expect to see saved in the context? As 
> such, what difference do you expect to see between mmio and srm 
> verification? Should even both be done?

I was following a hunch that maybe these were being saved in the
powercontext and so we needed an active engine to be able to read --
just ruling out that maybe forcewake wasn't enough.

> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> > ---
> >   drivers/gpu/drm/i915/i915_gem.c               |   6 +
> >   drivers/gpu/drm/i915/intel_workarounds.c      | 120 ++++++++++++++++++
> >   drivers/gpu/drm/i915/intel_workarounds.h      |   2 +
> >   .../drm/i915/selftests/intel_workarounds.c    |  53 +-------
> >   4 files changed, 134 insertions(+), 47 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index 0a818a60ad31..95ae69753e91 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -4717,6 +4717,12 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
> >               i915_request_add(rq);
> >               if (err)
> >                       goto err_active;
> > +
> > +             if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) &&
> > +                 intel_engine_verify_workarounds(engine, "load")) {
> > +                     err = -EIO;
> > +                     goto err_active;
> 
> I am not sure that wedging is required even if only in debug builds. Is 
> DRM_ERROR not enough to flag failures?

My thinking was if we can't apply workarounds to avoid known issues in HW,
further testing of HW was suspect.

Make the error as obnoxious as possible so that we have no choice but to
fix it before carrying on with testing.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 2/4] drm/i915: Verify the engine workarounds stick on application

[Chris Wilson]

Quoting Chris Wilson (2019-04-15 11:45:47)
> Quoting Tvrtko Ursulin (2019-04-15 11:41:43)
> > 
> > On 13/04/2019 13:58, Chris Wilson wrote:
> > > Read the engine workarounds back using the GPU after loading the initial
> > > context state to verify that we are setting them correctly, and bail if
> > > it fails.
> > 
> > Aren't the context wa/ ones we expect to see saved in the context? As 
> > such, what difference do you expect to see between mmio and srm 
> > verification? Should even both be done?
> 
> I was following a hunch that maybe these were being saved in the
> powercontext and so we needed an active engine to be able to read --
> just ruling out that maybe forcewake wasn't enough.

And yes, we do end up doing both read method to verify the writes :)
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 3/4] drm/i915: Make workaround verification *optional*

[Chris Wilson]

Sometimes the HW doesn't even play fair, and completely forgets about
register writes. Skip verifying known troublemakers.

References: https://bugs.freedesktop.org/show_bug.cgi?id=108954
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/intel_workarounds.c      | 40 ++++++++++++++-----
 .../gpu/drm/i915/intel_workarounds_types.h    |  7 ++--
 2 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index db99f2e676bb..ba58be05f58c 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -122,6 +122,7 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
 			wal->wa_count++;
 			wa_->val |= wa->val;
 			wa_->mask |= wa->mask;
+			wa_->read |= wa->read;
 			return;
 		}
 	}
@@ -146,9 +147,10 @@ wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
 		   u32 val)
 {
 	struct i915_wa wa = {
-		.reg = reg,
+		.reg  = reg,
 		.mask = mask,
-		.val = val
+		.val  = val,
+		.read = mask,
 	};
 
 	_wa_add(wal, &wa);
@@ -172,6 +174,19 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 	wa_write_masked_or(wal, reg, val, val);
 }
 
+static void
+ignore_wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, u32 val)
+{
+	struct i915_wa wa = {
+		.reg  = reg,
+		.mask = mask,
+		.val  = val,
+		/* Bonkers HW, skip verifying */
+	};
+
+	_wa_add(wal, &wa);
+}
+
 #define WA_SET_BIT_MASKED(addr, mask) \
 	wa_write_masked_or(wal, (addr), (mask), _MASKED_BIT_ENABLE(mask))
 
@@ -916,10 +931,11 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 static bool
 wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
 {
-	if ((cur ^ wa->val) & wa->mask) {
+	if ((cur ^ wa->val) & wa->read) {
 		DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
-			  name, from, i915_mmio_reg_offset(wa->reg), cur,
-			  cur & wa->mask, wa->val, wa->mask);
+			  name, from, i915_mmio_reg_offset(wa->reg),
+			  cur, cur & wa->read,
+			  wa->val, wa->mask);
 
 		return false;
 	}
@@ -1122,9 +1138,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE);
 
 		/* WaPipelineFlushCoherentLines:icl */
-		wa_write_or(wal,
-			    GEN8_L3SQCREG4,
-			    GEN8_LQSC_FLUSH_COHERENT_LINES);
+		ignore_wa_write_or(wal,
+				   GEN8_L3SQCREG4,
+				   GEN8_LQSC_FLUSH_COHERENT_LINES,
+				   GEN8_LQSC_FLUSH_COHERENT_LINES);
 
 		/*
 		 * Wa_1405543622:icl
@@ -1151,9 +1168,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * Wa_1405733216:icl
 		 * Formerly known as WaDisableCleanEvicts
 		 */
-		wa_write_or(wal,
-			    GEN8_L3SQCREG4,
-			    GEN11_LQSC_CLEAN_EVICT_DISABLE);
+		ignore_wa_write_or(wal,
+				   GEN8_L3SQCREG4,
+				   GEN11_LQSC_CLEAN_EVICT_DISABLE,
+				   GEN11_LQSC_CLEAN_EVICT_DISABLE);
 
 		/* WaForwardProgressSoftReset:icl */
 		wa_write_or(wal,
diff --git a/drivers/gpu/drm/i915/intel_workarounds_types.h b/drivers/gpu/drm/i915/intel_workarounds_types.h
index 30918da180ff..42ac1fb99572 100644
--- a/drivers/gpu/drm/i915/intel_workarounds_types.h
+++ b/drivers/gpu/drm/i915/intel_workarounds_types.h
@@ -12,9 +12,10 @@
 #include "i915_reg.h"
 
 struct i915_wa {
-	i915_reg_t	  reg;
-	u32		  mask;
-	u32		  val;
+	i915_reg_t	reg;
+	u32		mask;
+	u32		val;
+	u32		read;
 };
 
 struct i915_wa_list {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 4/4] drm/i915/selftests: Skip live timeline/suspend tests if wedged

[Chris Wilson]

If the driver is wedged, we can not issue the requests to exercise the
timelines or the system across suspend, so skip the tests. live_hangcheck
is there to fail if we cannot recover.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/selftests/i915_gem.c      | 3 +++
 drivers/gpu/drm/i915/selftests/i915_timeline.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 50bb7bbd26d3..6fd70d326468 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -215,5 +215,8 @@ int i915_gem_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_gem_hibernate),
 	};
 
+	if (i915_terminally_wedged(i915))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_timeline.c b/drivers/gpu/drm/i915/selftests/i915_timeline.c
index 8e7bcaa1eb66..bd96afcadfe7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/i915_timeline.c
@@ -838,5 +838,8 @@ int i915_timeline_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_hwsp_wrap),
 	};
 
+	if (i915_terminally_wedged(i915))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 4/4] drm/i915/selftests: Skip live timeline/suspend tests if wedged

[Tvrtko Ursulin]

On 13/04/2019 13:58, Chris Wilson wrote:
> If the driver is wedged, we can not issue the requests to exercise the
> timelines or the system across suspend, so skip the tests. live_hangcheck
> is there to fail if we cannot recover.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/selftests/i915_gem.c      | 3 +++
>   drivers/gpu/drm/i915/selftests/i915_timeline.c | 3 +++
>   2 files changed, 6 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
> index 50bb7bbd26d3..6fd70d326468 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_gem.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
> @@ -215,5 +215,8 @@ int i915_gem_live_selftests(struct drm_i915_private *i915)
>   		SUBTEST(igt_gem_hibernate),
>   	};
>   
> +	if (i915_terminally_wedged(i915))
> +		return 0;
> +
>   	return i915_subtests(tests, i915);
>   }
> diff --git a/drivers/gpu/drm/i915/selftests/i915_timeline.c b/drivers/gpu/drm/i915/selftests/i915_timeline.c
> index 8e7bcaa1eb66..bd96afcadfe7 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_timeline.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_timeline.c
> @@ -838,5 +838,8 @@ int i915_timeline_live_selftests(struct drm_i915_private *i915)
>   		SUBTEST(live_hwsp_wrap),
>   	};
>   
> +	if (i915_terminally_wedged(i915))
> +		return 0;
> +
>   	return i915_subtests(tests, i915);
>   }
> 

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.BAT: success for series starting with [1/4] drm/i915: Verify workarounds immediately after application

[Patchwork]

== Series Details ==

Series: series starting with [1/4] drm/i915: Verify workarounds immediately after application
URL   : https://patchwork.freedesktop.org/series/59434/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_5927 -> Patchwork_12793
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://patchwork.freedesktop.org/api/1.0/series/59434/revisions/1/mbox/

Known issues
------------

  Here are the changes found in Patchwork_12793 that come from known issues:

### IGT changes ###

#### Possible fixes ####

  * igt@i915_selftest@live_evict:
    - fi-bsw-kefka:       DMESG-WARN [fdo#107709] -> PASS

  * igt@kms_busy@basic-flip-c:
    - fi-skl-6770hq:      SKIP [fdo#109271] / [fdo#109278] -> PASS +2

  * igt@kms_flip@basic-flip-vs-dpms:
    - fi-skl-6770hq:      SKIP [fdo#109271] -> PASS +23

  
  [fdo#107709]: https://bugs.freedesktop.org/show_bug.cgi?id=107709
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109278]: https://bugs.freedesktop.org/show_bug.cgi?id=109278


Participating hosts (48 -> 41)
------------------------------

  Missing    (7): fi-kbl-soraka fi-byt-squawks fi-bsw-cyan fi-kbl-7500u fi-ctg-p8600 fi-icl-y fi-bdw-samus 


Build changes
-------------

    * Linux: CI_DRM_5927 -> Patchwork_12793

  CI_DRM_5927: d4c5510b1c590155f09d6582266341dd3d82701f @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4945: a52cc643cfe6733465cfc9ccb3d21cbdc4fd7506 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_12793: 3777ac5c4c3dd1422a7c18d1ce6c56f301e8a5ae @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

3777ac5c4c3d drm/i915/selftests: Skip live timeline/suspend tests if wedged
6817f8402704 drm/i915: Make workaround verification *optional*
8adab21c1005 drm/i915: Verify the engine workarounds stick on application
5b0ec5fc16cf drm/i915: Verify workarounds immediately after application

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12793/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.IGT: success for series starting with [1/4] drm/i915: Verify workarounds immediately after application

[Patchwork]

== Series Details ==

Series: series starting with [1/4] drm/i915: Verify workarounds immediately after application
URL   : https://patchwork.freedesktop.org/series/59434/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_5927_full -> Patchwork_12793_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

Known issues
------------

  Here are the changes found in Patchwork_12793_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_exec_schedule@deep-bsd:
    - shard-snb:          NOTRUN -> SKIP [fdo#109271] +78

  * igt@i915_pm_rpm@cursor-dpms:
    - shard-skl:          PASS -> INCOMPLETE [fdo#107807] +1

  * igt@i915_pm_rpm@gem-idle:
    - shard-skl:          NOTRUN -> INCOMPLETE [fdo#107807]

  * igt@i915_suspend@fence-restore-untiled:
    - shard-apl:          PASS -> DMESG-WARN [fdo#108566] +3

  * igt@kms_busy@extended-modeset-hang-oldfb-render-d:
    - shard-skl:          NOTRUN -> SKIP [fdo#109271] / [fdo#109278] +6

  * igt@kms_busy@extended-pageflip-hang-newfb-render-c:
    - shard-snb:          NOTRUN -> SKIP [fdo#109271] / [fdo#109278] +8

  * igt@kms_cursor_crc@cursor-256x256-suspend:
    - shard-skl:          PASS -> INCOMPLETE [fdo#104108] / [fdo#107773]

  * igt@kms_cursor_crc@cursor-64x64-suspend:
    - shard-skl:          PASS -> INCOMPLETE [fdo#104108]

  * igt@kms_flip@plain-flip-fb-recreate-interruptible:
    - shard-skl:          PASS -> FAIL [fdo#100368]

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-render:
    - shard-iclb:         PASS -> FAIL [fdo#103167] +1

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-mmap-wc:
    - shard-iclb:         PASS -> FAIL [fdo#109247] +6

  * igt@kms_frontbuffer_tracking@psr-2p-primscrn-pri-shrfb-draw-mmap-wc:
    - shard-apl:          NOTRUN -> SKIP [fdo#109271]

  * igt@kms_lease@atomic_implicit_crtc:
    - shard-skl:          NOTRUN -> FAIL [fdo#110279]

  * igt@kms_plane@pixel-format-pipe-b-planes-source-clamping:
    - shard-glk:          PASS -> SKIP [fdo#109271]

  * igt@kms_plane@plane-panning-bottom-right-suspend-pipe-b-planes:
    - shard-kbl:          PASS -> DMESG-WARN [fdo#108566] +3

  * igt@kms_plane_alpha_blend@pipe-c-coverage-7efc:
    - shard-skl:          NOTRUN -> FAIL [fdo#110403]

  * igt@kms_plane_lowres@pipe-a-tiling-x:
    - shard-iclb:         PASS -> FAIL [fdo#103166]

  * igt@kms_plane_scaling@pipe-a-scaler-with-clipping-clamping:
    - shard-glk:          PASS -> SKIP [fdo#109271] / [fdo#109278]

  * igt@kms_psr2_su@frontbuffer:
    - shard-iclb:         PASS -> SKIP [fdo#109642]

  * igt@kms_psr@psr2_no_drrs:
    - shard-iclb:         PASS -> SKIP [fdo#109441] +1

  * igt@kms_psr@sprite_blt:
    - shard-iclb:         PASS -> FAIL [fdo#107383] / [fdo#110215]

  * igt@kms_rotation_crc@multiplane-rotation-cropping-top:
    - shard-kbl:          PASS -> FAIL [fdo#109016] +1

  * igt@kms_setmode@basic:
    - shard-apl:          PASS -> FAIL [fdo#99912]

  * igt@kms_vrr@flip-suspend:
    - shard-skl:          NOTRUN -> SKIP [fdo#109271] +51

  * igt@perf_pmu@rc6:
    - shard-kbl:          PASS -> SKIP [fdo#109271]

  
#### Possible fixes ####

  * igt@i915_pm_rpm@gem-evict-pwrite:
    - shard-skl:          INCOMPLETE [fdo#107807] -> PASS

  * igt@i915_selftest@live_workarounds:
    - shard-iclb:         DMESG-FAIL [fdo#108954] -> PASS

  * igt@i915_suspend@debugfs-reader:
    - shard-apl:          DMESG-WARN [fdo#108566] -> PASS +11

  * igt@kms_flip@flip-vs-suspend-interruptible:
    - shard-apl:          INCOMPLETE [fdo#103927] -> PASS

  * igt@kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-render:
    - shard-iclb:         FAIL [fdo#103167] -> PASS +3

  * igt@kms_frontbuffer_tracking@fbc-1p-primscrn-cur-indfb-draw-mmap-cpu:
    - shard-snb:          SKIP [fdo#109271] -> PASS +2

  * igt@kms_frontbuffer_tracking@fbc-suspend:
    - shard-kbl:          DMESG-WARN [fdo#108566] -> PASS +2

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-indfb-draw-pwrite:
    - shard-iclb:         FAIL [fdo#109247] -> PASS +6

  * igt@kms_plane_alpha_blend@pipe-b-constant-alpha-min:
    - shard-skl:          FAIL [fdo#108145] -> PASS

  * igt@kms_plane_scaling@pipe-a-scaler-with-rotation:
    - shard-glk:          SKIP [fdo#109271] / [fdo#109278] -> PASS

  * igt@kms_psr@cursor_mmap_cpu:
    - shard-iclb:         FAIL [fdo#107383] / [fdo#110215] -> PASS +1

  * igt@kms_psr@psr2_sprite_blt:
    - shard-iclb:         SKIP [fdo#109441] -> PASS +2

  * igt@kms_sysfs_edid_timing:
    - shard-iclb:         FAIL [fdo#100047] -> PASS

  
  [fdo#100047]: https://bugs.freedesktop.org/show_bug.cgi?id=100047
  [fdo#100368]: https://bugs.freedesktop.org/show_bug.cgi?id=100368
  [fdo#103166]: https://bugs.freedesktop.org/show_bug.cgi?id=103166
  [fdo#103167]: https://bugs.freedesktop.org/show_bug.cgi?id=103167
  [fdo#103927]: https://bugs.freedesktop.org/show_bug.cgi?id=103927
  [fdo#104108]: https://bugs.freedesktop.org/show_bug.cgi?id=104108
  [fdo#107383]: https://bugs.freedesktop.org/show_bug.cgi?id=107383
  [fdo#107773]: https://bugs.freedesktop.org/show_bug.cgi?id=107773
  [fdo#107807]: https://bugs.freedesktop.org/show_bug.cgi?id=107807
  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#108566]: https://bugs.freedesktop.org/show_bug.cgi?id=108566
  [fdo#108954]: https://bugs.freedesktop.org/show_bug.cgi?id=108954
  [fdo#109016]: https://bugs.freedesktop.org/show_bug.cgi?id=109016
  [fdo#109247]: https://bugs.freedesktop.org/show_bug.cgi?id=109247
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109278]: https://bugs.freedesktop.org/show_bug.cgi?id=109278
  [fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
  [fdo#109642]: https://bugs.freedesktop.org/show_bug.cgi?id=109642
  [fdo#110215]: https://bugs.freedesktop.org/show_bug.cgi?id=110215
  [fdo#110279]: https://bugs.freedesktop.org/show_bug.cgi?id=110279
  [fdo#110403]: https://bugs.freedesktop.org/show_bug.cgi?id=110403
  [fdo#99912]: https://bugs.freedesktop.org/show_bug.cgi?id=99912


Participating hosts (10 -> 9)
------------------------------

  Missing    (1): shard-hsw 


Build changes
-------------

    * Linux: CI_DRM_5927 -> Patchwork_12793

  CI_DRM_5927: d4c5510b1c590155f09d6582266341dd3d82701f @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4945: a52cc643cfe6733465cfc9ccb3d21cbdc4fd7506 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_12793: 3777ac5c4c3dd1422a7c18d1ce6c56f301e8a5ae @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_12793/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/4] drm/i915: Verify workarounds immediately after application

[Chris Wilson]

Immediately after writing the workaround, verify that it stuck in the
register.

References: https://bugs.freedesktop.org/show_bug.cgi?id=108954
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/intel_workarounds.c | 32 +++++++++++++-----------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index ccaf63679435..1c54b5030807 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -913,6 +913,20 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 	return fw;
 }
 
+static bool
+wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
+{
+	if ((cur ^ wa->val) & wa->mask) {
+		DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
+			  name, from, i915_mmio_reg_offset(wa->reg), cur,
+			  cur & wa->mask, wa->val, wa->mask);
+
+		return false;
+	}
+
+	return true;
+}
+
 static void
 wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 {
@@ -931,6 +945,10 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
 		intel_uncore_rmw_fw(uncore, wa->reg, wa->mask, wa->val);
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+			wa_verify(wa,
+				  intel_uncore_read_fw(uncore, wa->reg),
+				  wal->name, "applictation");
 	}
 
 	intel_uncore_forcewake_put__locked(uncore, fw);
@@ -942,20 +960,6 @@ void intel_gt_apply_workarounds(struct drm_i915_private *i915)
 	wa_list_apply(&i915->uncore, &i915->gt_wa_list);
 }
 
-static bool
-wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
-{
-	if ((cur ^ wa->val) & wa->mask) {
-		DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
-			  name, from, i915_mmio_reg_offset(wa->reg), cur,
-			  cur & wa->mask, wa->val, wa->mask);
-
-		return false;
-	}
-
-	return true;
-}
-
 static bool wa_list_verify(struct intel_uncore *uncore,
 			   const struct i915_wa_list *wal,
 			   const char *from)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/4] drm/i915: Verify the engine workarounds stick on application

[Chris Wilson]

Read the engine workarounds back using the GPU after loading the initial
context state to verify that we are setting them correctly, and bail if
it fails.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c               |   6 +
 drivers/gpu/drm/i915/intel_workarounds.c      | 120 ++++++++++++++++++
 drivers/gpu/drm/i915/intel_workarounds.h      |   2 +
 .../drm/i915/selftests/intel_workarounds.c    |  53 +-------
 4 files changed, 134 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0a818a60ad31..95ae69753e91 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4717,6 +4717,12 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		i915_request_add(rq);
 		if (err)
 			goto err_active;
+
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) &&
+		    intel_engine_verify_workarounds(engine, "load")) {
+			err = -EIO;
+			goto err_active;
+		}
 	}
 
 	/* Flush the default context image to memory, and enable powersaving. */
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 1c54b5030807..db99f2e676bb 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -1259,6 +1259,126 @@ void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
 	wa_list_apply(engine->uncore, &engine->wa_list);
 }
 
+static struct i915_vma *
+create_scratch(struct i915_address_space *vm, int count)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	unsigned int size;
+	int err;
+
+	size = round_up(count * 4, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0,
+			   i915_vma_is_ggtt(vma) ? PIN_GLOBAL : PIN_USER);
+	if (err)
+		goto err_obj;
+
+	return vma;
+
+err_obj:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static int
+wa_list_srm(struct i915_request *rq,
+	    const struct i915_wa_list *wal,
+	    struct i915_vma *vma)
+{
+	const struct i915_wa *wa;
+	u32 srm, *cs;
+	int i;
+
+	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		srm++;
+
+	cs = intel_ring_begin(rq, 4 * wal->count);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
+		*cs++ = srm;
+		*cs++ = i915_mmio_reg_offset(wa->reg);
+		*cs++ = i915_ggtt_offset(vma) + sizeof(u32) * i;
+		*cs++ = 0;
+	}
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int engine_wa_list_verify(struct intel_engine_cs *engine,
+				 const struct i915_wa_list * const wal,
+				 const char *from)
+{
+	const struct i915_wa *wa;
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	unsigned int i;
+	u32 *results;
+	int err;
+
+	if (!wal->count)
+		return 0;
+
+	vma = create_scratch(&engine->i915->ggtt.vm, wal->count);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	rq = i915_request_alloc(engine, engine->kernel_context->gem_context);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_vma;
+	}
+
+	err = wa_list_srm(rq, wal, vma);
+	if (err)
+		goto err_vma;
+
+	i915_request_add(rq);
+	if (i915_request_wait(rq, I915_WAIT_LOCKED, HZ / 5) < 0) {
+		err = -ETIME;
+		goto err_vma;
+	}
+
+	results = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+	if (IS_ERR(results)) {
+		err = PTR_ERR(results);
+		goto err_vma;
+	}
+
+	err = 0;
+	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
+		if (!wa_verify(wa, results[i], wal->name, from))
+			err = -ENXIO;
+
+	i915_gem_object_unpin_map(vma->obj);
+
+err_vma:
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
+	return err;
+}
+
+int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
+				    const char *from)
+{
+	return engine_wa_list_verify(engine, &engine->wa_list, from);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/intel_workarounds.c"
 #endif
diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h
index 34eee5ec511e..fdf7ebb90f28 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.h
+++ b/drivers/gpu/drm/i915/intel_workarounds.h
@@ -30,5 +30,7 @@ void intel_engine_apply_whitelist(struct intel_engine_cs *engine);
 
 void intel_engine_init_workarounds(struct intel_engine_cs *engine);
 void intel_engine_apply_workarounds(struct intel_engine_cs *engine);
+int intel_engine_verify_workarounds(struct intel_engine_cs *engine,
+				    const char *from);
 
 #endif
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 567b6f8dae86..a363748a7a4f 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -340,49 +340,6 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	return err;
 }
 
-static struct i915_vma *create_scratch(struct i915_gem_context *ctx)
-{
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	void *ptr;
-	int err;
-
-	obj = i915_gem_object_create_internal(ctx->i915, PAGE_SIZE);
-	if (IS_ERR(obj))
-		return ERR_CAST(obj);
-
-	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
-
-	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
-		goto err_obj;
-	}
-	memset(ptr, 0xc5, PAGE_SIZE);
-	i915_gem_object_flush_map(obj);
-	i915_gem_object_unpin_map(obj);
-
-	vma = i915_vma_instance(obj, &ctx->ppgtt->vm, NULL);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err_obj;
-	}
-
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
-		goto err_obj;
-
-	err = i915_gem_object_set_to_cpu_domain(obj, false);
-	if (err)
-		goto err_obj;
-
-	return vma;
-
-err_obj:
-	i915_gem_object_put(obj);
-	return ERR_PTR(err);
-}
-
 static struct i915_vma *create_batch(struct i915_gem_context *ctx)
 {
 	struct drm_i915_gem_object *obj;
@@ -475,7 +432,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 	int err = 0, i, v;
 	u32 *cs, *results;
 
-	scratch = create_scratch(ctx);
+	scratch = create_scratch(&ctx->ppgtt->vm, 2 * ARRAY_SIZE(values) + 1);
 	if (IS_ERR(scratch))
 		return PTR_ERR(scratch);
 
@@ -752,9 +709,11 @@ static bool verify_gt_engine_wa(struct drm_i915_private *i915,
 
 	ok &= wa_list_verify(&i915->uncore, &lists->gt_wa_list, str);
 
-	for_each_engine(engine, i915, id)
-		ok &= wa_list_verify(engine->uncore,
-				     &lists->engine[id].wa_list, str);
+	for_each_engine(engine, i915, id) {
+		ok &= engine_wa_list_verify(engine,
+					    &lists->engine[id].wa_list,
+					    str) == 0;
+	}
 
 	return ok;
 }
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx