drm/i915: Implement dynamic GuC WOPCM offset and size calculation

Hardware may have specific restrictions on GuC WOPCM offset and size. On Gen9, the value of the GuC WOPCM size register needs to be larger than the value of GuC WOPCM offset register + a Gen9 specific offset (144KB) for reserved GuC WOPCM. Fail to enforce such a restriction on GuC WOPCM size will lead to GuC firmware execution failures. On the other hand, with current static GuC WOPCM offset and size values (512KB for both offset and size), the GuC WOPCM size verification will fail on Gen9 even if it can be fixed by lowering the GuC WOPCM offset by calculating its value based on HuC firmware size (which is likely less than 200KB on Gen9), so that we can have a GuC WOPCM size value which is large enough to pass the GuC WOPCM size check. This patch updates the reserved GuC WOPCM size for RC6 context on Gen9 to 24KB to strictly align with the Gen9 GuC WOPCM layout. It also adds support to verify the GuC WOPCM size aganist the Gen9 hardware restrictions. To meet all above requirements, let's provide dynamic partitioning of the WOPCM that will be based on platform specific HuC/GuC firmware sizes. 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 v5: - Moved GuC DMA WOPCM register updating code into intel_wopcm.c - Took care of the locking status before writing to GuC DMA Write-Once registers. (Joonas) v6: - Made sure the GuC WOPCM size to be multiple of 4K (4K aligned) v8: - Updated comments and fixed naming issues (Sagar/Joonas) - Updated commit message to include more description about the hardware restriction on GuC WOPCM size (Sagar) v9: - Minor changes variable names and code comments (Sagar) - Added detailed GuC WOPCM layout drawing (Sagar/Michal) - Refined macro definitions to be reader friendly (Michal) - Removed redundent check to valid flag (Michal) - Unified first parameter for exported GuC WOPCM functions (Michal) - Refined the name and parameter list of hardware restriction checking functions (Michal) v10: - Used shorter function name for internal functions (Joonas) - Moved init-ealry function into c file (Joonas) - Consolidated and removed redundant size checks (Joonas/Michal) - Removed unnecessary unlikely() from code which is only called once during boot (Joonas) - More fixes to kernel-doc format and content (Michal) - Avoided the use of PAGE_MASK for 4K pages (Michal) - Added error log messages to error paths (Michal) v11: - Replaced intel_guc_wopcm with more generic intel_wopcm and attached intel_wopcm to drm_i915_private instead intel_guc (Michal) - dynamic calculation of GuC non-wopcm memory start (a.k.a WOPCM Top offset from GuC WOPCM base) (Michal) - Moved WOPCM marco definitions into .c source file (Michal) - Exported WOPCM layout diagram as kernel-doc (Michal) v12: - Updated naming, function kernel-doc to align with new changes (Michal) v13: - Updated the ordering of s-o-b/cc/r-b tags (Sagar) - Corrected one tense error in comment (Sagar) - Corrected typos and removed spurious comments (Joonas) Bspec: 12690 Signed-off-by: Jackie Li <yaodong.li@intel.com> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com> Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com> Cc: Sujaritha Sundaresan <sujaritha.sundaresan@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: John Spotswood <john.a.spotswood@intel.com> Cc: Oscar Mateo <oscar.mateo@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com> (v8) Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> (v9) Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com> (v11) Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> (v12) Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/1520987574-19351-2-git-send-email-yaodong.li@intel.com
andr2000 · Mar 14, 2018 · 6b0478f · 6b0478f
1 parent 3c009e3
commit 6b0478f
Show file tree

Hide file tree

Showing 14 changed files with 321 additions and 41 deletions.
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
@@ -79,7 +79,8 @@ i915-y += i915_cmd_parser.o \
 	  intel_lrc.o \
 	  intel_mocs.o \
 	  intel_ringbuffer.o \
-	  intel_uncore.o
+	  intel_uncore.o \
+	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
 i915-y += intel_uc.o \

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
@@ -919,6 +919,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	mutex_init(&dev_priv->wm.wm_mutex);
 	mutex_init(&dev_priv->pps_mutex);
 
+	intel_wopcm_init_early(&dev_priv->wopcm);
 	intel_uc_init_early(dev_priv);
 	i915_memcpy_init_early(dev_priv);
 

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
@@ -64,6 +64,7 @@
 #include "intel_opregion.h"
 #include "intel_ringbuffer.h"
 #include "intel_uncore.h"
+#include "intel_wopcm.h"
 #include "intel_uc.h"
 
 #include "i915_gem.h"
@@ -1589,6 +1590,8 @@ struct drm_i915_private {
 
 	struct intel_gvt *gvt;
 
+	struct intel_wopcm wopcm;
+
 	struct intel_huc huc;
 	struct intel_guc guc;
 
@@ -2121,6 +2124,11 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev)
 	return to_i915(dev_get_drvdata(kdev));
 }
 
+static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm)
+{
+	return container_of(wopcm, struct drm_i915_private, wopcm);
+}
+
 static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
 {
 	return container_of(guc, struct drm_i915_private, guc);

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
@@ -5294,6 +5294,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
+	ret = intel_wopcm_init(&dev_priv->wopcm);
+	if (ret)
+		return ret;
+
 	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -318,12 +318,13 @@ __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
+	/*
+	 * GuC requires the ring to be placed in Non-WOPCM memory. 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.ggtt_pin_bias;
 	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
@@ -492,6 +492,57 @@ int intel_guc_resume(struct intel_guc *guc)
 	return intel_guc_send(guc, data, ARRAY_SIZE(data));
 }
 
+/**
+ * DOC: GuC Address Space
+ *
+ * The layout of GuC address space is shown as below:
+ *
+ *    +==============> +====================+ <== GUC_GGTT_TOP
+ *    ^                |                    |
+ *    |                |                    |
+ *    |                |        DRAM        |
+ *    |                |       Memory       |
+ *    |                |                    |
+ *   GuC               |                    |
+ * Address  +========> +====================+ <== WOPCM Top
+ *  Space   ^          |   HW contexts RSVD |
+ *    |     |          |        WOPCM       |
+ *    |     |     +==> +--------------------+ <== GuC WOPCM Top
+ *    |    GuC    ^    |                    |
+ *    |    GGTT   |    |                    |
+ *    |    Pin   GuC   |        GuC         |
+ *    |    Bias WOPCM  |       WOPCM        |
+ *    |     |    Size  |                    |
+ *    |     |     |    |                    |
+ *    v     v     v    |                    |
+ *    +=====+=====+==> +====================+ <== GuC WOPCM Base
+ *                     |   Non-GuC WOPCM    |
+ *                     |   (HuC/Reserved)   |
+ *                     +====================+ <== WOPCM Base
+ *
+ * The lower part [0, GuC ggtt_pin_bias) is mapped to WOPCM which consists of
+ * GuC WOPCM and WOPCM reserved for other usage (e.g.RC6 context). The value of
+ * the GuC ggtt_pin_bias is determined by the actually GuC WOPCM size which is
+ * set in GUC_WOPCM_SIZE register.
+ */
+
+/**
+ * intel_guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
+ * @guc: intel_guc structure.
+ *
+ * This function will calculate and initialize the ggtt_pin_bias value based on
+ * overall WOPCM size and GuC WOPCM size.
+ */
+void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+
+	GEM_BUG_ON(!i915->wopcm.size);
+	GEM_BUG_ON(i915->wopcm.size < i915->wopcm.guc.base);
+
+	guc->ggtt_pin_bias = i915->wopcm.size - i915->wopcm.guc.base;
+}
+
 /**
  * intel_guc_allocate_vma() - Allocate a GGTT VMA for GuC usage
  * @guc:	the guc
@@ -500,7 +551,7 @@ int intel_guc_resume(struct intel_guc *guc)
  * 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 ggtt_pin_bias) because that
  * range is reserved inside GuC.
  *
  * Return:	A i915_vma if successful, otherwise an ERR_PTR.
@@ -521,7 +572,7 @@ 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->ggtt_pin_bias);
 	if (ret) {
 		vma = ERR_PTR(ret);
 		goto err;
@@ -533,14 +584,3 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 	i915_gem_object_put(obj);
 	return vma;
 }
-
-u32 intel_guc_wopcm_size(struct drm_i915_private *dev_priv)
-{
-	u32 wopcm_size = GUC_WOPCM_TOP;
-
-	/* On BXT, the top of WOPCM is reserved for RC6 context */
-	if (IS_GEN9_LP(dev_priv))
-		wopcm_size -= BXT_GUC_WOPCM_RC6_RESERVED;
-
-	return wopcm_size;
-}
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
@@ -49,6 +49,9 @@ struct intel_guc {
 	struct intel_guc_log log;
 	struct intel_guc_ct ct;
 
+	/* Offset where Non-WOPCM memory starts. */
+	u32 ggtt_pin_bias;
+
 	/* Log snapshot if GuC errors during load */
 	struct drm_i915_gem_object *load_err_log;
 
@@ -108,19 +111,20 @@ static inline void intel_guc_notify(struct intel_guc *guc)
  * @guc: intel_guc structure.
  * @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 ggtt_pin_bias), which is reserved for Boot ROM, SRAM and WOPCM.
+ * Currently, in order to exclude [0, GuC ggtt_pin_bias) address space from
+ * GGTT, all gfx objects used by GuC are allocated with intel_guc_allocate_vma()
+ * and pinned with PIN_OFFSET_BIAS along with the value of GuC ggtt_pin_bias.
  *
- * Return: GGTT offset that meets the GuC gfx address requirement.
+ * Return: GGTT offset of the @vma.
  */
 static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 					struct i915_vma *vma)
 {
 	u32 offset = i915_ggtt_offset(vma);
 
-	GEM_BUG_ON(offset < GUC_WOPCM_TOP);
+	GEM_BUG_ON(offset < guc->ggtt_pin_bias);
 	GEM_BUG_ON(range_overflows_t(u64, offset, vma->size, GUC_GGTT_TOP));
 
 	return offset;
@@ -129,6 +133,7 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 void intel_guc_init_early(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_init_params(struct intel_guc *guc);
+void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc);
 int intel_guc_init_wq(struct intel_guc *guc);
 void intel_guc_fini_wq(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
@@ -141,7 +146,6 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset);
 int intel_guc_suspend(struct intel_guc *guc);
 int intel_guc_resume(struct intel_guc *guc);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
-u32 intel_guc_wopcm_size(struct drm_i915_private *dev_priv);
 
 static inline int intel_guc_sanitize(struct intel_guc *guc)
 {

diff --git a/drivers/gpu/drm/i915/intel_guc_reg.h b/drivers/gpu/drm/i915/intel_guc_reg.h
@@ -68,17 +68,15 @@
 #define DMA_GUC_WOPCM_OFFSET		_MMIO(0xc340)
 #define   HUC_LOADING_AGENT_VCR		  (0<<1)
 #define   HUC_LOADING_AGENT_GUC		  (1<<1)
-#define   GUC_WOPCM_OFFSET_VALUE	  0x80000	/* 512KB */
+#define   GUC_WOPCM_OFFSET_SHIFT	14
 #define GUC_MAX_IDLE_COUNT		_MMIO(0xC3E4)
 
 #define HUC_STATUS2             _MMIO(0xD3B0)
 #define   HUC_FW_VERIFIED       (1<<7)
 
-/* Defines WOPCM space available to GuC firmware */
 #define GUC_WOPCM_SIZE			_MMIO(0xc050)
-/* 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  */
+#define   GUC_WOPCM_SIZE_SHIFT		12
+#define   GUC_WOPCM_SIZE_MASK		  (0xfffff << GUC_WOPCM_SIZE_SHIFT)
 
 #define GEN8_GT_PM_CONFIG		_MMIO(0x138140)
 #define GEN9LP_GT_PM_CONFIG		_MMIO(0x138140)

diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
@@ -55,7 +55,7 @@ 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->ggtt_pin_bias);
 	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
@@ -272,6 +272,8 @@ int intel_uc_init_misc(struct drm_i915_private *dev_priv)
 	if (!USES_GUC(dev_priv))
 		return 0;
 
+	intel_guc_init_ggtt_pin_bias(guc);
+
 	ret = intel_guc_init_wq(guc);
 	if (ret)
 		return ret;
@@ -366,9 +368,9 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	gen9_reset_guc_interrupts(dev_priv);
 
 	/* init WOPCM */
-	I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(dev_priv));
+	I915_WRITE(GUC_WOPCM_SIZE, dev_priv->wopcm.guc.size);
 	I915_WRITE(DMA_GUC_WOPCM_OFFSET,
-		   GUC_WOPCM_OFFSET_VALUE | HUC_LOADING_AGENT_GUC);
+		   dev_priv->wopcm.guc.base | 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
@@ -95,15 +95,6 @@ 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 */
-	size = uc_fw->header_size + uc_fw->ucode_size;
-	if (size > intel_guc_wopcm_size(dev_priv)) {
-		DRM_WARN("%s: Firmware is too large to fit in WOPCM\n",
-			 intel_uc_fw_type_repr(uc_fw->type));
-		err = -E2BIG;
-		goto fail;
-	}
-
 	/* now RSA */
 	if (css->key_size_dw != UOS_RSA_SCRATCH_COUNT) {
 		DRM_WARN("%s: Mismatched firmware RSA key size (%u)\n",
@@ -208,6 +199,7 @@ 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;
 
@@ -231,7 +223,8 @@ 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.ggtt_pin_bias);
 	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
@@ -121,6 +121,22 @@ static inline void intel_uc_fw_sanitize(struct intel_uc_fw *uc_fw)
 		uc_fw->load_status = INTEL_UC_FIRMWARE_PENDING;
 }
 
+/**
+ * intel_uc_fw_get_upload_size() - Get size of firmware needed to be uploaded.
+ * @uc_fw: uC firmware.
+ *
+ * Get the size of the firmware and header that will be uploaded to WOPCM.
+ *
+ * Return: Upload firmware size, or zero on firmware fetch failure.
+ */
+static inline u32 intel_uc_fw_get_upload_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,