Merge tag 'drm-intel-fixes-2021-01-07' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

drm/i915 fixes for v5.11-rc3:
- Use per-connector PM QoS tracking for DP aux communication
- GuC firmware fix for older Cometlakes
- Clear the gpu reloc and shadow batches

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/877dop18zf.fsf@intel.com

7 files changed, 22 insertions, 29 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index ce82d654d0f2..34d78c654df3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1436,6 +1436,9 @@ struct intel_dp {
 		bool ycbcr_444_to_420;
 	} dfp;
 
+	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
+	struct pm_qos_request pm_qos;
+
 	/* Display stream compression testing */
 	bool force_dsc_en;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 2165398d2c7c..37f1a10fd021 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1489,7 +1489,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	 * lowest possible wakeup latency and so prevent the cpu from going into
 	 * deep sleep states.
 	 */
-	cpu_latency_qos_update_request(&i915->pm_qos, 0);
+	cpu_latency_qos_update_request(&intel_dp->pm_qos, 0);
 
 	intel_dp_check_edp(intel_dp);
 
@@ -1622,7 +1622,7 @@ done:
 
 	ret = recv_bytes;
 out:
-	cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);
@@ -1898,6 +1898,9 @@ static i915_reg_t tgl_aux_data_reg(struct intel_dp *intel_dp, int index)
 static void
 intel_dp_aux_fini(struct intel_dp *intel_dp)
 {
+	if (cpu_latency_qos_request_active(&intel_dp->pm_qos))
+		cpu_latency_qos_remove_request(&intel_dp->pm_qos);
+
 	kfree(intel_dp->aux.name);
 }
 
@@ -1950,6 +1953,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp)
 					       encoder->base.name);
 
 	intel_dp->aux.transfer = intel_dp_aux_transfer;
+	cpu_latency_qos_add_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
 }
 
 bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bcc80f428172..bd3046e5a934 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1046,7 +1046,7 @@ static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cach
 	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
 	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	intel_gt_chipset_flush(cache->rq->engine->gt);
@@ -1296,6 +1296,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_pool;
 	}
 
+	memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
+
 	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 180c23e2e25e..602f1a0bc587 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -53,6 +53,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 49, 0, 1), huc_def(icl,  9, 0, 0)) \
 	fw_def(COMETLAKE,   5, guc_def(cml, 49, 0, 1), huc_def(cml,  4, 0, 0)) \
+	fw_def(COMETLAKE,   0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
 	fw_def(COFFEELAKE,  0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
 	fw_def(GEMINILAKE,  0, guc_def(glk, 49, 0, 1), huc_def(glk,  4, 0, 0)) \
 	fw_def(KABYLAKE,    0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 93265951fdbb..b0899b665e85 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1166,7 +1166,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		}
 	}
 	if (IS_ERR(src)) {
-		unsigned long x, n;
+		unsigned long x, n, remain;
 		void *ptr;
 
 		/*
@@ -1177,14 +1177,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		 * We don't care about copying too much here as we only
 		 * validate up to the end of the batch.
 		 */
+		remain = length;
 		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
-			length = round_up(length,
+			remain = round_up(remain,
 					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
 		x = offset_in_page(offset);
-		for (n = offset >> PAGE_SHIFT; length; n++) {
-			int len = min(length, PAGE_SIZE - x);
+		for (n = offset >> PAGE_SHIFT; remain; n++) {
+			int len = min(remain, PAGE_SIZE - x);
 
 			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
 			if (needs_clflush)
@@ -1193,13 +1194,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 			kunmap_atomic(src);
 
 			ptr += len;
-			length -= len;
+			remain -= len;
 			x = 0;
 		}
 	}
 
 	i915_gem_object_unpin_pages(src_obj);
 
+	memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
+
 	/* dst_obj is returned with vmap pinned */
 	return dst;
 }
@@ -1392,11 +1395,6 @@ static unsigned long *alloc_whitelist(u32 batch_length)
 
 #define LENGTH_BIAS 2
 
-static bool shadow_needs_clflush(struct drm_i915_gem_object *obj)
-{
-	return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
-}
-
 /**
  * intel_engine_cmd_parser() - parse a batch buffer for privilege violations
  * @engine: the engine on which the batch is to execute
@@ -1538,16 +1536,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 				ret = 0; /* allow execution */
 			}
 		}
-
-		if (shadow_needs_clflush(shadow->obj))
-			drm_clflush_virt_range(batch_end, 8);
 	}
 
-	if (shadow_needs_clflush(shadow->obj)) {
-		void *ptr = page_mask_bits(shadow->obj->mm.mapping);
-
-		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
-	}
+	i915_gem_object_flush_map(shadow->obj);
 
 	if (!IS_ERR_OR_NULL(jump_whitelist))
 		kfree(jump_whitelist);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 320856b665a1..88ad754962af 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -578,8 +578,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 
 	pci_set_master(pdev);
 
-	cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
-
 	intel_gt_init_workarounds(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -626,7 +624,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 err_msi:
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 err_mem_regions:
 	intel_memory_regions_driver_release(dev_priv);
 err_ggtt:
@@ -648,8 +645,6 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv)
 
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-
-	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a3ee4f9dc0a..632c713227dc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -891,9 +891,6 @@ struct drm_i915_private {
 
 	bool display_irqs_enabled;
 
-	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
-	struct pm_qos_request pm_qos;
-
 	/* Sideband mailbox protection */
 	struct mutex sb_lock;
 	struct pm_qos_request sb_qos;