[PATCH 3/6] drm/i915/guc: Implement dynamic WOPCM partitioning

Jackie Li yaodong.li at intel.com
Mon Dec 18 17:58:05 UTC 2017


Hardware may have specific restrictions on GuC WOPCM partition
size versus HuC firmware size. With static WOPCM partitioning,
there's no way to adjust the GuC WOPCM partition size based on
the actual HuC firmware size, so that GuC/HuC loading failure
would occur even if there was enough WOPCM space for both
GuC and HuC firmware.

This patch enables the dynamic calculation of the WOPCM aperture
sizes used by GuC and HuC firmware. GuC WOPCM offset is set to
HuC size + reserved WOPCM size. GuC WOPCM size is set to
total WOPCM size - GuC WOPCM offset - RC6CTX size. In this case,
GuC WOPCM offset will be updated based on the size of HuC firmware
while GuC WOPCM size will be set to use all the remaining WOPCM space.

v2:
 - Removed intel_wopcm_init (Ville/Sagar/Joonas)
 - Renamed and Moved the intel_wopcm_partition into intel_guc (Sagar)
 - Removed unnecessary function calls (Joonas)
 - Init GuC WOPCM partition as soon as firmware fetching is completed

v3:
 - Fixed indentation issues (Chris)
 - Removed layering violation code (Chris/Michal)
 - Created separat files for GuC wopcm code  (Michal)
 - Used inline function to avoid code duplication (Michal)

v4:
 - Preset the GuC WOPCM top during early GuC init (Chris)
 - Fail intel_uc_init_hw() as soon as GuC WOPCM partitioning failed
---
 drivers/gpu/drm/i915/i915_gem_context.c |   9 +--
 drivers/gpu/drm/i915/intel_guc.c        |   5 +-
 drivers/gpu/drm/i915/intel_guc.h        |  12 ++--
 drivers/gpu/drm/i915/intel_guc_wopcm.c  | 105 +++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_guc_wopcm.h  |  40 ++++++++++--
 drivers/gpu/drm/i915/intel_huc.c        |   2 +-
 drivers/gpu/drm/i915/intel_uc.c         |  10 ++-
 drivers/gpu/drm/i915/intel_uc_fw.c      |  11 +++-
 drivers/gpu/drm/i915/intel_uc_fw.h      |  16 +++++
 9 files changed, 178 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 648e753..b485794 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -312,12 +312,13 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->desc_template =
 		default_desc_template(dev_priv, dev_priv->mm.aliasing_ppgtt);
 
-	/* GuC requires the ring to be placed above GUC_WOPCM_TOP. If GuC is not
-	 * present or not in use we still need a small bias as ring wraparound
-	 * at offset 0 sometimes hangs. No idea why.
+	/*
+	 * GuC requires the ring to be placed above GuC WOPCM top. If GuC is not
+-	 * present or not in use we still need a small bias as ring wraparound
+-	 * at offset 0 sometimes hangs. No idea why.
 	 */
 	if (USES_GUC(dev_priv))
-		ctx->ggtt_offset_bias = GUC_WOPCM_TOP;
+		ctx->ggtt_offset_bias = dev_priv->guc.wopcm.top;
 	else
 		ctx->ggtt_offset_bias = I915_GTT_PAGE_SIZE;
 
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 2d5cca9..0240c15 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -63,6 +63,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 {
 	intel_guc_fw_init_early(guc);
 	intel_guc_ct_init_early(&guc->ct);
+	intel_guc_wopcm_init_early(&guc->wopcm);
 
 	mutex_init(&guc->send_mutex);
 	guc->send = intel_guc_send_nop;
@@ -447,7 +448,7 @@ int intel_guc_resume(struct drm_i915_private *dev_priv)
  * This is a wrapper to create an object for use with the GuC. In order to
  * use it inside the GuC, an object needs to be pinned lifetime, so we allocate
  * both some backing storage and a range inside the Global GTT. We must pin
- * it in the GGTT somewhere other than than [0, GUC_WOPCM_TOP) because that
+ * it in the GGTT somewhere other than than [0, GuC WOPCM top) because that
  * range is reserved inside GuC.
  *
  * Return:	A i915_vma if successful, otherwise an ERR_PTR.
@@ -468,7 +469,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 		goto err;
 
 	ret = i915_vma_pin(vma, 0, PAGE_SIZE,
-			   PIN_GLOBAL | PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+			   PIN_GLOBAL | PIN_OFFSET_BIAS | guc->wopcm.top);
 	if (ret) {
 		vma = ERR_PTR(ret);
 		goto err;
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index b7e2a18..ea35911 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -49,6 +49,7 @@ struct intel_guc {
 	struct intel_uc_fw fw;
 	struct intel_guc_log log;
 	struct intel_guc_ct ct;
+	struct intel_guc_wopcm wopcm;
 
 	/* Log snapshot if GuC errors during load */
 	struct drm_i915_gem_object *load_err_log;
@@ -105,10 +106,10 @@ static inline void intel_guc_notify(struct intel_guc *guc)
  * @guc: intel guc.
  * @vma: i915 graphics virtual memory area.
  *
- * GuC does not allow any gfx GGTT address that falls into range [0, WOPCM_TOP),
- * which is reserved for Boot ROM, SRAM and WOPCM. Currently this top address is
- * 512K. In order to exclude 0-512K address space from GGTT, all gfx objects
- * used by GuC is pinned with PIN_OFFSET_BIAS along with size of WOPCM.
+ * GuC does not allow any gfx GGTT address that falls into range
+ * [0, GuC WOPCM top), which is reserved for Boot ROM, SRAM and WOPCM.
+ * All gfx objects used by GuC is pinned with PIN_OFFSET_BIAS along with
+ * top of WOPCM.
  *
  * Return: GGTT offset that meets the GuC gfx address requirement.
  */
@@ -117,7 +118,8 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 {
 	u32 offset = i915_ggtt_offset(vma);
 
-	GEM_BUG_ON(offset < GUC_WOPCM_TOP);
+	GEM_BUG_ON(!guc->wopcm.valid);
+	GEM_BUG_ON(offset < guc->wopcm.top);
 	GEM_BUG_ON(range_overflows_t(u64, offset, vma->size, GUC_GGTT_TOP));
 
 	return offset;
diff --git a/drivers/gpu/drm/i915/intel_guc_wopcm.c b/drivers/gpu/drm/i915/intel_guc_wopcm.c
index 87643a0..60a6afe 100644
--- a/drivers/gpu/drm/i915/intel_guc_wopcm.c
+++ b/drivers/gpu/drm/i915/intel_guc_wopcm.c
@@ -25,23 +25,108 @@
 #include "intel_guc_wopcm.h"
 #include "i915_drv.h"
 
+static inline u32 guc_reserved_wopcm_size(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+
+	/* On BXT, the top of WOPCM is reserved for RC6 context */
+	if (IS_GEN9_LP(i915))
+		return BXT_WOPCM_RC6_RESERVED;
+
+	return 0;
+}
+
+static inline int gen9_wocpm_size_check(struct drm_i915_private *i915)
+{
+	struct intel_guc_wopcm *wopcm = &i915->guc.wopcm;
+	u32 wopcm_base;
+	u32 delta;
+
+	/*
+	 * Check hardware restriction on Gen9
+	 * GuC WOPCM size is at least 4 bytes larger than GuC WOPCM base due
+	 * to hardware limitation on Gen9.
+	 */
+	wopcm_base = wopcm->offset + GEN9_GUC_WOPCM_OFFSET;
+	if (unlikely(wopcm_base > wopcm->size))
+		return -E2BIG;
+
+	delta = wopcm->size - wopcm_base;
+	if (unlikely(delta < GEN9_GUC_WOPCM_DELTA))
+		return -E2BIG;
+
+	return 0;
+}
+
+static inline int guc_wopcm_size_check(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+
+	if (IS_GEN9(i915))
+		return gen9_wocpm_size_check(i915);
+
+	return 0;
+}
+
 /*
- * intel_guc_wopcm_size() - Get the size of GuC WOPCM.
+ * intel_guc_wopcm_init() - Initialize the GuC WOPCM partition.
  * @guc: intel guc.
+ * @guc_fw_size: size of GuC firmware.
+ * @huc_fw_size: size of HuC firmware.
  *
- * Get the platform specific GuC WOPCM size.
+ * This function tries to initialize the WOPCM partition based on HuC firmware
+ * size and the reserved WOPCM memory size.
  *
- * Return: size of the GuC WOPCM.
+ * Return: 0 on success, non-zero error code on failure.
  */
-u32 intel_guc_wopcm_size(struct intel_guc *guc)
+int intel_guc_init_wopcm(struct intel_guc *guc, u32 guc_fw_size,
+			 u32 huc_fw_size)
 {
-	struct drm_i915_private *i915 = guc_to_i915(guc);
+	u32 reserved = guc_reserved_wopcm_size(guc);
+	u32 offset, size, top;
+	int err;
 
-	u32 wopcm_size = GUC_WOPCM_TOP;
+	if (guc->wopcm.valid)
+		return 0;
 
-	/* On BXT, the top of WOPCM is reserved for RC6 context */
-	if (IS_GEN9_LP(i915))
-		wopcm_size -= BXT_GUC_WOPCM_RC6_RESERVED;
+	if (!guc_fw_size)
+		return -EINVAL;
+
+	if (reserved >= WOPCM_DEFAULT_SIZE)
+		return -E2BIG;
+
+	offset = huc_fw_size + WOPCM_RESERVED_SIZE;
+	if (offset >= WOPCM_DEFAULT_SIZE)
+		return -E2BIG;
+
+	/* Hardware requires GuC WOPCM offset needs to be 16K aligned. */
+	offset = ALIGN(offset, WOPCM_OFFSET_ALIGNMENT);
+	if ((offset + reserved) >= WOPCM_DEFAULT_SIZE)
+		return -E2BIG;
+
+	top = WOPCM_DEFAULT_SIZE - offset;
+	size = top - reserved;
+
+	/*
+	 * GuC size needs to be less than or equal to GuC WOPCM size.
+	 * Need extra 8K stack for GuC.
+	 */
+	if ((guc_fw_size + GUC_WOPCM_STACK_RESERVED) > size)
+		return -E2BIG;
+
+	guc->wopcm.offset = offset;
+	guc->wopcm.size = size;
+	guc->wopcm.top = top;
+
+	/* Check platform specific restrictions */
+	err = guc_wopcm_size_check(guc);
+	if (err)
+		return err;
+
+	guc->wopcm.valid = true;
+
+	DRM_DEBUG_DRIVER("GuC WOPCM offset %dKB, size %dKB, top %dKB\n",
+			 offset >> 10, size >> 10, top >> 10);
 
-	return wopcm_size;
+	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_wopcm.h b/drivers/gpu/drm/i915/intel_guc_wopcm.h
index 595fb1c..2f9d03a 100644
--- a/drivers/gpu/drm/i915/intel_guc_wopcm.h
+++ b/drivers/gpu/drm/i915/intel_guc_wopcm.h
@@ -29,11 +29,41 @@
 
 struct intel_guc;
 
-#define   GUC_WOPCM_OFFSET_VALUE	0x80000	/* 512KB */
-/* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */
-#define GUC_WOPCM_TOP			(0x80 << 12)	/* 512KB */
-#define BXT_GUC_WOPCM_RC6_RESERVED	(0x10 << 12)	/* 64KB  */
+/* Default WOPCM size 1MB */
+#define WOPCM_DEFAULT_SIZE		(0x1 << 20)
+/* Reserved WOPCM size 16KB */
+#define WOPCM_RESERVED_SIZE		(0x4000)
+/* GUC WOPCM Offset need to be 16KB aligned */
+#define WOPCM_OFFSET_ALIGNMENT		(0x4000)
+/* 8KB stack reserved for GuC FW*/
+#define GUC_WOPCM_STACK_RESERVED	(0x2000)
+/* 24KB WOPCM reserved for RC6 CTX on BXT */
+#define BXT_WOPCM_RC6_RESERVED		(0x6000)
 
-u32 intel_guc_wopcm_size(struct intel_guc *guc);
+#define GEN9_GUC_WOPCM_DELTA		4
+#define GEN9_GUC_WOPCM_OFFSET		(0x24000)
+
+struct intel_guc_wopcm {
+	u32 offset;
+	u32 size;
+	u32 top;
+	bool valid;
+};
+
+/*
+ * intel_guc_wopcm_init_early() - Early initialization of the GuC WOPCM.
+ * @wopcm: GuC WOPCM.
+ *
+ * Setup the GuC WOPCM top to the top of the overall WOPCM. This will guarantee
+ * that the allocation of the GuC accessible objects won't fall into WOPCM when
+ * GuC partition isn't present.
+ *
+ */
+static inline void intel_guc_wopcm_init_early(struct intel_guc_wopcm *wopcm)
+{
+	wopcm->top = WOPCM_DEFAULT_SIZE;
+}
+
+int intel_guc_init_wopcm(struct intel_guc *guc, u32 guc_size, u32 huc_size);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 6482174..dda2955 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -217,7 +217,7 @@ int intel_huc_auth(struct intel_huc *huc)
 		return -ENOEXEC;
 
 	vma = i915_gem_object_ggtt_pin(huc->fw.obj, NULL, 0, 0,
-				PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+				PIN_OFFSET_BIAS | guc->wopcm.top);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		DRM_ERROR("HuC: Failed to pin huc fw object %d\n", ret);
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 23e0c8c..f6745f3 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -263,6 +263,8 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 	struct intel_huc *huc = &dev_priv->huc;
+	u32 guc_fw_size = intel_uc_fw_get_size(&guc->fw);
+	u32 huc_fw_size = intel_uc_fw_get_size(&huc->fw);
 	int ret, attempts;
 
 	if (!USES_GUC(dev_priv))
@@ -270,13 +272,17 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 
+	ret = intel_guc_init_wopcm(guc, guc_fw_size, huc_fw_size);
+	if (ret)
+		goto err_out;
+
 	guc_disable_communication(guc);
 	gen9_reset_guc_interrupts(dev_priv);
 
 	/* init WOPCM */
-	I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(guc));
+	I915_WRITE(GUC_WOPCM_SIZE, guc->wopcm.size);
 	I915_WRITE(DMA_GUC_WOPCM_OFFSET,
-		   GUC_WOPCM_OFFSET_VALUE | HUC_LOADING_AGENT_GUC);
+		   guc->wopcm.offset | HUC_LOADING_AGENT_GUC);
 
 	/* WaEnableuKernelHeaderValidFix:skl */
 	/* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */
diff --git a/drivers/gpu/drm/i915/intel_uc_fw.c b/drivers/gpu/drm/i915/intel_uc_fw.c
index 24945cf..791263a 100644
--- a/drivers/gpu/drm/i915/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/intel_uc_fw.c
@@ -95,9 +95,13 @@ void intel_uc_fw_fetch(struct drm_i915_private *dev_priv,
 	uc_fw->ucode_offset = uc_fw->header_offset + uc_fw->header_size;
 	uc_fw->ucode_size = (css->size_dw - css->header_size_dw) * sizeof(u32);
 
-	/* Header and uCode will be loaded to WOPCM */
+	/*
+	 * Header and uCode will be loaded to WOPCM
+	 * Only check the size against the overall available WOPCM here. Will
+	 * continue to check the size during WOPCM partition calculation.
+	 */
 	size = uc_fw->header_size + uc_fw->ucode_size;
-	if (size > intel_guc_wopcm_size(&dev_priv->guc)) {
+	if (size > WOPCM_DEFAULT_SIZE) {
 		DRM_WARN("%s: Firmware is too large to fit in WOPCM\n",
 			 intel_uc_fw_type_repr(uc_fw->type));
 		err = -E2BIG;
@@ -207,6 +211,7 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
 		       int (*xfer)(struct intel_uc_fw *uc_fw,
 				   struct i915_vma *vma))
 {
+	struct drm_i915_private *i915 = to_i915(uc_fw->obj->base.dev);
 	struct i915_vma *vma;
 	int err;
 
@@ -230,7 +235,7 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
 	}
 
 	vma = i915_gem_object_ggtt_pin(uc_fw->obj, NULL, 0, 0,
-				       PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+				       PIN_OFFSET_BIAS | i915->guc.wopcm.top);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		DRM_DEBUG_DRIVER("%s fw ggtt-pin err=%d\n",
diff --git a/drivers/gpu/drm/i915/intel_uc_fw.h b/drivers/gpu/drm/i915/intel_uc_fw.h
index d5fd460..d00d888 100644
--- a/drivers/gpu/drm/i915/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/intel_uc_fw.h
@@ -115,6 +115,22 @@ static inline bool intel_uc_fw_is_selected(struct intel_uc_fw *uc_fw)
 	return uc_fw->path != NULL;
 }
 
+/*
+ * intel_uc_fw_get_size() - Get the size of the firmware.
+ * @uc_fw: intel_uc_fw structure.
+ *
+ * Get the size of the firmware that will be placed in WOPCM.
+ *
+ * Return: Zero on invalid firmware status. actual size on success.
+ */
+static inline u32 intel_uc_fw_get_size(struct intel_uc_fw *uc_fw)
+{
+	if (uc_fw->fetch_status != INTEL_UC_FIRMWARE_SUCCESS)
+		return 0;
+
+	return uc_fw->header_size + uc_fw->ucode_size;
+}
+
 void intel_uc_fw_fetch(struct drm_i915_private *dev_priv,
 		       struct intel_uc_fw *uc_fw);
 int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
-- 
2.7.4



More information about the Intel-gfx-trybot mailing list