drm/i915: Record the default hw state after reset upon load

Take a copy of the HW state after a reset upon module loading by
executing a context switch from a blank context to the kernel context,
thus saving the default hw state over the blank context image.
We can then use the default hw state to initialise any future context,
ensuring that each starts with the default view of hw state.

v2: Unmap our default state from the GTT after stealing it from the
context. This should stop us from accidentally overwriting it via the
GTT (and frees up some precious GTT space).

Testcase: igt/gem_ctx_isolation
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110142634.10551-7-chris@chris-wilson.co.uk

1 files changed, 24 insertions, 14 deletions

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 1baaab3..0c93f27 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1180,7 +1180,6 @@ static int execlists_request_alloc(struct drm_i915_gem_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	struct intel_context *ce = &request->ctx->engine[engine->id];
 	u32 *cs;
-	int ret;
 
 	GEM_BUG_ON(!ce->pin_count);
 
@@ -1194,14 +1193,6 @@ static int execlists_request_alloc(struct drm_i915_gem_request *request)
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
-	if (!ce->initialised) {
-		ret = engine->init_context(request);
-		if (ret)
-			return ret;
-
-		ce->initialised = true;
-	}
-
 	/* Note that after this point, we have committed to using
 	 * this request as it is being used to both track the
 	 * state of engine initialisation and liveness of the
@@ -2133,7 +2124,6 @@ static void execlists_init_reg_state(u32 *regs,
 
 	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(engine),
 		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
-				   CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
 				   (HAS_RESOURCE_STREAMER(dev_priv) ?
 				   CTX_CTRL_RS_CTX_ENABLE : 0)));
 	CTX_REG(regs, CTX_RING_HEAD, RING_HEAD(base), 0);
@@ -2210,6 +2200,7 @@ populate_lr_context(struct i915_gem_context *ctx,
 		    struct intel_ring *ring)
 {
 	void *vaddr;
+	u32 *regs;
 	int ret;
 
 	ret = i915_gem_object_set_to_cpu_domain(ctx_obj, true);
@@ -2226,11 +2217,31 @@ populate_lr_context(struct i915_gem_context *ctx,
 	}
 	ctx_obj->mm.dirty = true;
 
+	if (engine->default_state) {
+		/*
+		 * We only want to copy over the template context state;
+		 * skipping over the headers reserved for GuC communication,
+		 * leaving those as zero.
+		 */
+		const unsigned long start = LRC_HEADER_PAGES * PAGE_SIZE;
+		void *defaults;
+
+		defaults = i915_gem_object_pin_map(engine->default_state,
+						   I915_MAP_WB);
+		if (IS_ERR(defaults))
+			return PTR_ERR(defaults);
+
+		memcpy(vaddr + start, defaults + start, engine->context_size);
+		i915_gem_object_unpin_map(engine->default_state);
+	}
+
 	/* The second page of the context object contains some fields which must
 	 * be set up prior to the first execution. */
-
-	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
-				 ctx, engine, ring);
+	regs = vaddr + LRC_STATE_PN * PAGE_SIZE;
+	execlists_init_reg_state(regs, ctx, engine, ring);
+	if (!engine->default_state)
+		regs[CTX_CONTEXT_CONTROL + 1] |=
+			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
 	i915_gem_object_unpin_map(ctx_obj);
 
@@ -2283,7 +2294,6 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 
 	ce->ring = ring;
 	ce->state = vma;
-	ce->initialised |= engine->init_context == NULL;
 
 	return 0;