drm/i915/icl: new context descriptor support

Starting from Gen11 the context descriptor format has been updated in
the HW. The hw_id field has been considerably reduced in size and engine
class and instance fields have been added.

There is a slight name clashing issue because the field that we call
hw_id is actually called SW Context ID in the specs for Gen11+.

With the current size of the hw_id field we can have a maximum of 2k
contexts at any time, but we could use the sw_counter field (which is sw
defined) to increase that because the HW requirement is that
engine_id + sw id + sw_counter is a unique number.
GuC uses a similar method to support more contexts but does its tracking
at lrc level. To avoid doing an implementation that will need to be
reworked once GuC support lands, defer it for now and mark it as TODO.

v2: rebased, add documentation, fix GEN11_ENGINE_INSTANCE_SHIFT
v3: rebased, bring back lost code from i915_gem_context.c
v4: make TODO comment more generic
v5: be consistent with bit ordering, add extra checks (Chris)

Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180302161501.28594-3-mika.kuoppala@linux.intel.com
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

drivers/gpu/drm/i915/i915_drv.h

@@ -2103,6 +2103,7 @@ struct drm_i915_private {
 		 */
 		struct ida hw_ida;
 #define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+#define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
 	} contexts;
 
 	u32 fdi_rx_config;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -211,9 +211,15 @@ static void context_close(struct i915_gem_context *ctx)
 static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out)
 {
 	int ret;
+	unsigned int max;
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		max = GEN11_MAX_CONTEXT_HW_ID;
+	else
+		max = MAX_CONTEXT_HW_ID;
 
 	ret = ida_simple_get(&dev_priv->contexts.hw_ida,
-			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
+			     0, max, GFP_KERNEL);
 	if (ret < 0) {
 		/* Contexts are only released when no longer active.
 		 * Flush any pending retires to hopefully release some
@@ -221,7 +227,7 @@ static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out)
 		 */
 		i915_retire_requests(dev_priv);
 		ret = ida_simple_get(&dev_priv->contexts.hw_ida,
-				     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
+				     0, max, GFP_KERNEL);
 		if (ret < 0)
 			return ret;
 	}
@@ -463,6 +469,7 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 
 	/* Using the simple ida interface, the max is limited by sizeof(int) */
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > INT_MAX);
+	BUILD_BUG_ON(GEN11_MAX_CONTEXT_HW_ID > INT_MAX);
 	ida_init(&dev_priv->contexts.hw_ida);
 
 	/* lowest priority; idle task */

drivers/gpu/drm/i915/i915_reg.h

@@ -3912,6 +3912,12 @@ enum {
 
 #define GEN8_CTX_ID_SHIFT 32
 #define GEN8_CTX_ID_WIDTH 21
+#define GEN11_SW_CTX_ID_SHIFT 37
+#define GEN11_SW_CTX_ID_WIDTH 11
+#define GEN11_ENGINE_CLASS_SHIFT 61
+#define GEN11_ENGINE_CLASS_WIDTH 3
+#define GEN11_ENGINE_INSTANCE_SHIFT 48
+#define GEN11_ENGINE_INSTANCE_WIDTH 6
 
 #define CHV_CLK_CTL1			_MMIO(0x101100)
 #define VLV_CLK_CTL2			_MMIO(0x101104)

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -234,6 +234,9 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
 	class_info = &intel_engine_classes[info->class];
 
+	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
+	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
+
 	if (GEM_WARN_ON(info->class > MAX_ENGINE_CLASS))
 		return -EINVAL;
 

drivers/gpu/drm/i915/intel_lrc.c

@@ -204,6 +204,18 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  *      bits 32-52:    ctx ID, a globally unique tag
  *      bits 53-54:    mbz, reserved for use by hardware
  *      bits 55-63:    group ID, currently unused and set to 0
+ *
+ * Starting from Gen11, the upper dword of the descriptor has a new format:
+ *
+ *      bits 32-36:    reserved
+ *      bits 37-47:    SW context ID
+ *      bits 48:53:    engine instance
+ *      bit 54:        mbz, reserved for use by hardware
+ *      bits 55-60:    SW counter
+ *      bits 61-63:    engine class
+ *
+ * engine info, SW context ID and SW counter need to form a unique number
+ * (Context ID) per lrc.
  */
 static void
 intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
@@ -212,12 +224,32 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 	struct intel_context *ce = &ctx->engine[engine->id];
 	u64 desc;
 
-	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (1<<GEN8_CTX_ID_WIDTH));
+	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
+	BUILD_BUG_ON(GEN11_MAX_CONTEXT_HW_ID > (BIT(GEN11_SW_CTX_ID_WIDTH)));
 
 	desc = ctx->desc_template;				/* bits  0-11 */
+	GEM_BUG_ON(desc & GENMASK_ULL(63, 12));
+
 	desc |= i915_ggtt_offset(ce->state) + LRC_HEADER_PAGES * PAGE_SIZE;
 								/* bits 12-31 */
-	desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;		/* bits 32-52 */
+	GEM_BUG_ON(desc & GENMASK_ULL(63, 32));
+
+	if (INTEL_GEN(ctx->i915) >= 11) {
+		GEM_BUG_ON(ctx->hw_id >= BIT(GEN11_SW_CTX_ID_WIDTH));
+		desc |= (u64)ctx->hw_id << GEN11_SW_CTX_ID_SHIFT;
+								/* bits 37-47 */
+
+		desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT;
+								/* bits 48-53 */
+
+		/* TODO: decide what to do with SW counter (bits 55-60) */
+
+		desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT;
+								/* bits 61-63 */
+	} else {
+		GEM_BUG_ON(ctx->hw_id >= BIT(GEN8_CTX_ID_WIDTH));
+		desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;	/* bits 32-52 */
+	}
 
 	ce->lrc_desc = desc;
 }