drm/i915: Remove logical HW ID

With the introduction of ctx->engines[] we allow multiple logical
contexts to be used on the same engine (e.g. with virtual engines).
According to bspec, aach logical context requires a unique tag in order
for context-switching to occur correctly between them. [Simple
experiments show that it is not so easy to trick the HW into performing
a lite-restore with matching logical IDs, though my memory from early
Broadwell experiments do suggest that it should be generating
lite-restores.]

We only need to keep a unique tag for the active lifetime of the
context, and for as long as we need to identify that context. The HW
uses the tag to determine if it should use a lite-restore (why not the
LRCA?) and passes the tag back for various status identifies. The only
status we need to track is for OA, so when using perf, we assign the
specific context a unique tag.

v2: Calculate required number of tags to fill ELSP.

Fixes: 976b55f0e1db ("drm/i915: Allow a context to define its set of engines")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111895
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-14-chris@chris-wilson.co.uk

4 files changed, 22 insertions, 21 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index bf9cedfccbf0..6959b05ae5f8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -58,6 +58,7 @@ struct intel_context {
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
+	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	unsigned int active_count; /* protected by timeline->mutex */
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 943f0663837e..6199064f332b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -303,10 +303,12 @@ struct intel_engine_cs {
 	u8 uabi_class;
 	u8 uabi_instance;
 
+	u32 uabi_capabilities;
 	u32 context_size;
 	u32 mmio_base;
 
-	u32 uabi_capabilities;
+	unsigned int context_tag;
+#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS)
 
 	struct rb_node uabi_node;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 3cfea1758fd2..468438fb47af 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -440,12 +440,8 @@ assert_priority_queue(const struct i915_request *prev,
 static u64
 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 {
-	struct i915_gem_context *ctx = ce->gem_context;
 	u64 desc;
 
-	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 = INTEL_LEGACY_32B_CONTEXT;
 	if (i915_vm_is_4lvl(ce->vm))
 		desc = INTEL_LEGACY_64B_CONTEXT;
@@ -463,20 +459,11 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	 * anything below.
 	 */
 	if (INTEL_GEN(engine->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 */
 	}
 
 	return desc;
@@ -985,6 +972,18 @@ __execlists_schedule_in(struct i915_request *rq)
 
 	intel_context_get(ce);
 
+	if (ce->tag) {
+		/* Use a fixed tag for OA and friends */
+		ce->lrc_desc |= (u64)ce->tag << 32;
+	} else {
+		/* We don't need a strict matching tag, just different values */
+		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
+		ce->lrc_desc |=
+			(u64)(engine->context_tag++ % NUM_CONTEXT_TAG) <<
+			GEN11_SW_CTX_ID_SHIFT;
+		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
+	}
+
 	intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -2114,7 +2113,6 @@ static void execlists_context_unpin(struct intel_context *ce)
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_PN * PAGE_SIZE,
 		      ce->engine);
 
-	i915_gem_context_unpin_hw_id(ce->gem_context);
 	i915_gem_object_unpin_map(ce->state->obj);
 	intel_ring_reset(ce->ring, ce->ring->tail);
 }
@@ -2164,18 +2162,12 @@ __execlists_context_pin(struct intel_context *ce,
 		goto unpin_active;
 	}
 
-	ret = i915_gem_context_pin_hw_id(ce->gem_context);
-	if (ret)
-		goto unpin_map;
-
 	ce->lrc_desc = lrc_descriptor(ce, engine);
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine);
 
 	return 0;
 
-unpin_map:
-	i915_gem_object_unpin_map(ce->state->obj);
 unpin_active:
 	intel_context_active_release(ce);
 err:
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 66ac616361c1..99dc576a4e25 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -66,6 +66,12 @@ struct intel_engine_cs;
 #define GEN11_CSB_READ_PTR_MASK (GEN11_CSB_PTR_MASK << 8)
 #define GEN11_CSB_WRITE_PTR_MASK (GEN11_CSB_PTR_MASK << 0)
 
+#define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */
+#define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
+/* in Gen12 ID 0x7FF is reserved to indicate idle */
+#define GEN12_MAX_CONTEXT_HW_ID	(GEN11_MAX_CONTEXT_HW_ID - 1)
+
 enum {
 	INTEL_CONTEXT_SCHEDULE_IN = 0,
 	INTEL_CONTEXT_SCHEDULE_OUT,