Merge tag 'drm-intel-gt-next-2021-12-09' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Core Changes:

- Fix PENDING_ERROR leak in dma_fence_array_signaled() (Thomas Hellström)

Driver Changes:

- Fix runtime PM handling during PXP suspend (Tejas Upadhyay)
- Improve eviction performance on discrete by implementing async TTM moves (Thomas Hellström, Maarten Lankhorst)
- Improve robustness of error capture under memory pressure (Thomas Hellström)
- Fix GuC PMU versus GPU reset handling (Umesh Nerlige Ramappa)
- Use per device iommu check (Tvrtko Ursulin)
- Make error capture work with async migration (Thomas Hellström)
- Revert incorrect implementation of Wa_1508744258 causing hangs (José Roberto de Souza)
- Disable coarse power gating on some DG2 steppings workaround (Matt Roper)
- Add IC cache invalidation workaround on DG2 (Ramalingam C)
- Move two Icelake workarounds to the right place (Raviteja Goud Talla)
- Fix error pointer dereference in i915_gem_do_execbuffer() (Dan Carpenter)
- Fixup a couple of generic and DG2 specific issues in migration code (Matthew Auld)

- Fix kernel-doc warnings in i915_drm_object.c (Randy Dunlap)
- Drop stealing of bits from i915_sw_fence function pointer (Matthew Brost)
- Introduce new macros for i915 PTE (Michael Cheng)
- Prep work for engine reset by reset domain lookup (Tejas Upadhyay)

- Fixup drm-intel-gt-next build failure (Matthew Auld)
- Fix live_engine_busy_stats selftests in GuC mode (Umesh Nerlige Ramappa)
- Remove dma_resv_prune (Maarten Lankhorst)
- Preserve huge pages enablement after driver reload (Matthew Auld)
- Fix a NULL pointer dereference in igt_request_rewind() (selftests) (Zhou Qingyang)
- Add workaround numbers to GEN7_COMMON_SLICE_CHICKEN1 whitelisting (José Roberto de Souza)
- Increase timeouts in i915_gem_contexts selftests to handle GuC being slower (Bruce Chang)

Signed-off-by: Dave Airlie <[email protected]>

# Conflicts:
#	drivers/gpu/drm/i915/display/intel_fbc.c
From: Tvrtko Ursulin <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/YbIBOeqhn+nPzaYD@tursulin-mobl2

Author: airlied

MAINTAINERS

@@ -9496,6 +9496,7 @@ INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
 M:	Jani Nikula <[email protected]>
 M:	Joonas Lahtinen <[email protected]>
 M:	Rodrigo Vivi <[email protected]>
+M:	Tvrtko Ursulin <[email protected]>
 L:	[email protected]
 S:	Supported
 W:	https://01.org/linuxgraphics/

drivers/dma-buf/dma-fence-array.c

@@ -104,7 +104,11 @@ static bool dma_fence_array_signaled(struct dma_fence *fence)
 {
 	struct dma_fence_array *array = to_dma_fence_array(fence);
 
-	return atomic_read(&array->num_pending) <= 0;
+	if (atomic_read(&array->num_pending) > 0)
+		return false;
+
+	dma_fence_array_clear_pending_error(array);
+	return true;
 }
 
 static void dma_fence_array_release(struct dma_fence *fence)

drivers/gpu/drm/i915/Makefile

@@ -153,6 +153,7 @@ gem-y += \
 	gem/i915_gem_throttle.o \
 	gem/i915_gem_tiling.o \
 	gem/i915_gem_ttm.o \
+	gem/i915_gem_ttm_move.o \
 	gem/i915_gem_ttm_pm.o \
 	gem/i915_gem_userptr.o \
 	gem/i915_gem_wait.o \
@@ -172,6 +173,7 @@ i915-y += \
 	  i915_trace_points.o \
 	  i915_ttm_buddy_manager.o \
 	  i915_vma.o \
+	  i915_vma_snapshot.o \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support

drivers/gpu/drm/i915/display/intel_bw.c

@@ -634,7 +634,7 @@ static unsigned int intel_bw_data_rate(struct drm_i915_private *dev_priv,
 	for_each_pipe(dev_priv, pipe)
 		data_rate += bw_state->data_rate[pipe];
 
-	if (DISPLAY_VER(dev_priv) >= 13 && intel_vtd_active())
+	if (DISPLAY_VER(dev_priv) >= 13 && intel_vtd_active(dev_priv))
 		data_rate = data_rate * 105 / 100;
 
 	return data_rate;

drivers/gpu/drm/i915/display/intel_display.c

@@ -1293,7 +1293,7 @@ static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
 
-	return crtc_state->uapi.async_flip && intel_vtd_active() &&
+	return crtc_state->uapi.async_flip && intel_vtd_active(i915) &&
 		(DISPLAY_VER(i915) == 9 || IS_BROADWELL(i915) || IS_HASWELL(i915));
 }
 
@@ -8815,7 +8815,7 @@ static void intel_atomic_commit_work(struct work_struct *work)
 	intel_atomic_commit_tail(state);
 }
 
-static int __i915_sw_fence_call
+static int
 intel_atomic_commit_ready(struct i915_sw_fence *fence,
 			  enum i915_sw_fence_notify notify)
 {

drivers/gpu/drm/i915/display/intel_fbc.c

@@ -1677,7 +1677,7 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *i915)
 static bool need_fbc_vtd_wa(struct drm_i915_private *i915)
 {
 	/* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */
-	if (intel_vtd_active() &&
+	if (intel_vtd_active(i915) &&
 	    (IS_SKYLAKE(i915) || IS_BROXTON(i915))) {
 		drm_info(&i915->drm,
 			 "Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n");

drivers/gpu/drm/i915/gem/i915_gem_clflush.c

@@ -69,10 +69,16 @@ static struct clflush *clflush_work_create(struct drm_i915_gem_object *obj)
 bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			     unsigned int flags)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct clflush *clflush;
 
 	assert_object_held(obj);
 
+	if (IS_DGFX(i915)) {
+		WARN_ON_ONCE(obj->cache_dirty);
+		return false;
+	}
+
 	/*
 	 * Stolen memory is always coherent with the GPU as it is explicitly
 	 * marked as wc by the system, or the system is cache-coherent.
@@ -105,16 +111,24 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	if (clflush) {
 		i915_sw_fence_await_reservation(&clflush->base.chain,
 						obj->base.resv, NULL, true,
-						i915_fence_timeout(to_i915(obj->base.dev)),
+						i915_fence_timeout(i915),
 						I915_FENCE_GFP);
 		dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma);
 		dma_fence_work_commit(&clflush->base);
+		/*
+		 * We must have successfully populated the pages(since we are
+		 * holding a pin on the pages as per the flush worker) to reach
+		 * this point, which must mean we have already done the required
+		 * flush-on-acquire, hence resetting cache_dirty here should be
+		 * safe.
+		 */
+		obj->cache_dirty = false;
 	} else if (obj->mm.pages) {
 		__do_clflush(obj);
+		obj->cache_dirty = false;
 	} else {
 		GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
 	}
 
-	obj->cache_dirty = false;
 	return true;
 }

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1001,7 +1001,7 @@ static void free_engines_rcu(struct rcu_head *rcu)
 	free_engines(engines);
 }
 
-static int __i915_sw_fence_call
+static int
 engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
 	struct i915_gem_engines *engines =

drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c

@@ -248,8 +248,19 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
-	/* XXX: consider doing a vmap flush or something */
-	if (!HAS_LLC(i915) || i915_gem_object_can_bypass_llc(obj))
+	/*
+	 * DG1 is special here since it still snoops transactions even with
+	 * CACHE_NONE. This is not the case with other HAS_SNOOP platforms. We
+	 * might need to revisit this as we add new discrete platforms.
+	 *
+	 * XXX: Consider doing a vmap flush or something, where possible.
+	 * Currently we just do a heavy handed wbinvd_on_all_cpus() here since
+	 * the underlying sg_table might not even point to struct pages, so we
+	 * can't just call drm_clflush_sg or similar, like we do elsewhere in
+	 * the driver.
+	 */
+	if (i915_gem_object_can_bypass_llc(obj) ||
+	    (!HAS_LLC(i915) && !IS_DG1(i915)))
 		wbinvd_on_all_cpus();
 
 	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -18,10 +18,32 @@
 
 static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
+	if (IS_DGFX(i915))
+		return false;
+
 	return !(obj->cache_level == I915_CACHE_NONE ||
 		 obj->cache_level == I915_CACHE_WT);
 }
 
+bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
+	if (obj->cache_dirty)
+		return false;
+
+	if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
+		return true;
+
+	if (IS_DGFX(i915))
+		return false;
+
+	/* Currently in use by HW (display engine)? Keep flushed. */
+	return i915_gem_object_is_framebuffer(obj);
+}
+
 static void
 flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 {