drm/i915/mocs: Program MOCS for all engines on init

Allow for the MOCS to be programmed for all engines.
Currently we program the MOCS when the first render batch
goes through. This works on most platforms but fails on
platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines
on init and the RCS is programmed again within the initial batch. This
is done for predictable consistency with regards to the hardware
context.

Hardware context loading sets the values of the MOCS for RCS
and L3CC. Programming them from within the batch makes sure that
the render context is valid, no matter what the previous state of
the saved-context was.

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

Testcase: igt/gem_mocs_settings
Signed-off-by: Peter Antoine <peter.antoine@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1460556205-6644-1-git-send-email-chris@chris-wilson.co.uk

4 files changed, 122 insertions, 40 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0bafe7d2cc4e..6ce2c31b9a81 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -32,6 +32,7 @@
 #include "i915_vgpu.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
+#include "intel_mocs.h"
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -4915,6 +4916,8 @@ i915_gem_init_hw(struct drm_device *dev)
 			goto out;
 	}
 
+	intel_mocs_init_l3cc_table(dev);
+
 	/* We can't enable contexts until all firmware is loaded */
 	if (HAS_GUC_UCODE(dev)) {
 		ret = intel_guc_ucode_load(dev);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7693efa3f15c..1562a75ac9d1 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1626,7 +1626,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 
 	intel_engine_init_hangcheck(engine);
 
-	return 0;
+	return intel_mocs_init_engine(engine);
 }
 
 static int gen8_init_render_ring(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c
index 7c7ac0aa192a..23b8545ad6b0 100644
--- a/drivers/gpu/drm/i915/intel_mocs.c
+++ b/drivers/gpu/drm/i915/intel_mocs.c
@@ -128,9 +128,9 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 
 /**
  * get_mocs_settings()
- * @dev:        DRM device.
+ * @dev_priv:	i915 device.
  * @table:      Output table that will be made to point at appropriate
- *              MOCS values for the device.
+ *	      MOCS values for the device.
  *
  * This function will return the values of the MOCS table that needs to
  * be programmed for the platform. It will return the values that need
@@ -138,21 +138,21 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
  *
  * Return: true if there are applicable MOCS settings for the device.
  */
-static bool get_mocs_settings(struct drm_device *dev,
+static bool get_mocs_settings(struct drm_i915_private *dev_priv,
 			      struct drm_i915_mocs_table *table)
 {
 	bool result = false;
 
-	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		table->size  = ARRAY_SIZE(skylake_mocs_table);
 		table->table = skylake_mocs_table;
 		result = true;
-	} else if (IS_BROXTON(dev)) {
+	} else if (IS_BROXTON(dev_priv)) {
 		table->size  = ARRAY_SIZE(broxton_mocs_table);
 		table->table = broxton_mocs_table;
 		result = true;
 	} else {
-		WARN_ONCE(INTEL_INFO(dev)->gen >= 9,
+		WARN_ONCE(INTEL_INFO(dev_priv)->gen >= 9,
 			  "Platform that should have a MOCS table does not.\n");
 	}
 
@@ -179,10 +179,49 @@ static i915_reg_t mocs_register(enum intel_engine_id ring, int index)
 }
 
 /**
+ * intel_mocs_init_engine() - emit the mocs control table
+ * @engine:	The engine for whom to emit the registers.
+ *
+ * This function simply emits a MI_LOAD_REGISTER_IMM command for the
+ * given table starting at the given address.
+ *
+ * Return: 0 on success, otherwise the error status.
+ */
+int intel_mocs_init_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_mocs_table table;
+	unsigned int index;
+
+	if (!get_mocs_settings(dev_priv, &table))
+		return 0;
+
+	if (WARN_ON(table.size > GEN9_NUM_MOCS_ENTRIES))
+		return -ENODEV;
+
+	for (index = 0; index < table.size; index++)
+		I915_WRITE(mocs_register(engine->id, index),
+			   table.table[index].control_value);
+
+	/*
+	 * Ok, now set the unused entries to uncached. These entries
+	 * are officially undefined and no contract for the contents
+	 * and settings is given for these entries.
+	 *
+	 * Entry 0 in the table is uncached - so we are just writing
+	 * that value to all the used entries.
+	 */
+	for (; index < GEN9_NUM_MOCS_ENTRIES; index++)
+		I915_WRITE(mocs_register(engine->id, index),
+			   table.table[0].control_value);
+
+	return 0;
+}
+
+/**
  * emit_mocs_control_table() - emit the mocs control table
  * @req:	Request to set up the MOCS table for.
  * @table:	The values to program into the control regs.
- * @ring:	The engine for whom to emit the registers.
  *
  * This function simply emits a MI_LOAD_REGISTER_IMM command for the
  * given table starting at the given address.
@@ -190,10 +229,10 @@ static i915_reg_t mocs_register(enum intel_engine_id ring, int index)
  * Return: 0 on success, otherwise the error status.
  */
 static int emit_mocs_control_table(struct drm_i915_gem_request *req,
-				   const struct drm_i915_mocs_table *table,
-				   enum intel_engine_id ring)
+				   const struct drm_i915_mocs_table *table)
 {
 	struct intel_ringbuffer *ringbuf = req->ringbuf;
+	enum intel_engine_id engine = req->engine->id;
 	unsigned int index;
 	int ret;
 
@@ -210,7 +249,8 @@ static int emit_mocs_control_table(struct drm_i915_gem_request *req,
 				MI_LOAD_REGISTER_IMM(GEN9_NUM_MOCS_ENTRIES));
 
 	for (index = 0; index < table->size; index++) {
-		intel_logical_ring_emit_reg(ringbuf, mocs_register(ring, index));
+		intel_logical_ring_emit_reg(ringbuf,
+					    mocs_register(engine, index));
 		intel_logical_ring_emit(ringbuf,
 					table->table[index].control_value);
 	}
@@ -224,8 +264,10 @@ static int emit_mocs_control_table(struct drm_i915_gem_request *req,
 	 * that value to all the used entries.
 	 */
 	for (; index < GEN9_NUM_MOCS_ENTRIES; index++) {
-		intel_logical_ring_emit_reg(ringbuf, mocs_register(ring, index));
-		intel_logical_ring_emit(ringbuf, table->table[0].control_value);
+		intel_logical_ring_emit_reg(ringbuf,
+					    mocs_register(engine, index));
+		intel_logical_ring_emit(ringbuf,
+					table->table[0].control_value);
 	}
 
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
@@ -234,6 +276,14 @@ static int emit_mocs_control_table(struct drm_i915_gem_request *req,
 	return 0;
 }
 
+static inline u32 l3cc_combine(const struct drm_i915_mocs_table *table,
+			       u16 low,
+			       u16 high)
+{
+	return table->table[low].l3cc_value |
+	       table->table[high].l3cc_value << 16;
+}
+
 /**
  * emit_mocs_l3cc_table() - emit the mocs control table
  * @req:	Request to set up the MOCS table for.
@@ -249,11 +299,7 @@ static int emit_mocs_l3cc_table(struct drm_i915_gem_request *req,
 				const struct drm_i915_mocs_table *table)
 {
 	struct intel_ringbuffer *ringbuf = req->ringbuf;
-	unsigned int count;
 	unsigned int i;
-	u32 value;
-	u32 filler = (table->table[0].l3cc_value & 0xffff) |
-			((table->table[0].l3cc_value & 0xffff) << 16);
 	int ret;
 
 	if (WARN_ON(table->size > GEN9_NUM_MOCS_ENTRIES))
@@ -268,20 +314,18 @@ static int emit_mocs_l3cc_table(struct drm_i915_gem_request *req,
 	intel_logical_ring_emit(ringbuf,
 			MI_LOAD_REGISTER_IMM(GEN9_NUM_MOCS_ENTRIES / 2));
 
-	for (i = 0, count = 0; i < table->size / 2; i++, count += 2) {
-		value = (table->table[count].l3cc_value & 0xffff) |
-			((table->table[count + 1].l3cc_value & 0xffff) << 16);
-
+	for (i = 0; i < table->size/2; i++) {
 		intel_logical_ring_emit_reg(ringbuf, GEN9_LNCFCMOCS(i));
-		intel_logical_ring_emit(ringbuf, value);
+		intel_logical_ring_emit(ringbuf,
+					l3cc_combine(table, 2*i, 2*i+1));
 	}
 
 	if (table->size & 0x01) {
 		/* Odd table size - 1 left over */
-		value = (table->table[count].l3cc_value & 0xffff) |
-			((table->table[0].l3cc_value & 0xffff) << 16);
-	} else
-		value = filler;
+		intel_logical_ring_emit_reg(ringbuf, GEN9_LNCFCMOCS(i));
+		intel_logical_ring_emit(ringbuf, l3cc_combine(table, 2*i, 0));
+		i++;
+	}
 
 	/*
 	 * Now set the rest of the table to uncached - use entry 0 as
@@ -290,9 +334,7 @@ static int emit_mocs_l3cc_table(struct drm_i915_gem_request *req,
 	 */
 	for (; i < GEN9_NUM_MOCS_ENTRIES / 2; i++) {
 		intel_logical_ring_emit_reg(ringbuf, GEN9_LNCFCMOCS(i));
-		intel_logical_ring_emit(ringbuf, value);
-
-		value = filler;
+		intel_logical_ring_emit(ringbuf, l3cc_combine(table, 0, 0));
 	}
 
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
@@ -302,6 +344,47 @@ static int emit_mocs_l3cc_table(struct drm_i915_gem_request *req,
 }
 
 /**
+ * intel_mocs_init_l3cc_table() - program the mocs control table
+ * @dev:      The the device to be programmed.
+ *
+ * This function simply programs the mocs registers for the given table
+ * starting at the given address. This register set is  programmed in pairs.
+ *
+ * These registers may get programmed more than once, it is simpler to
+ * re-program 32 registers than maintain the state of when they were programmed.
+ * We are always reprogramming with the same values and this only on context
+ * start.
+ *
+ * Return: Nothing.
+ */
+void intel_mocs_init_l3cc_table(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_mocs_table table;
+	unsigned int i;
+
+	if (!get_mocs_settings(dev_priv, &table))
+		return;
+
+	for (i = 0; i < table.size/2; i++)
+		I915_WRITE(GEN9_LNCFCMOCS(i), l3cc_combine(&table, 2*i, 2*i+1));
+
+	/* Odd table size - 1 left over */
+	if (table.size & 0x01) {
+		I915_WRITE(GEN9_LNCFCMOCS(i), l3cc_combine(&table, 2*i, 0));
+		i++;
+	}
+
+	/*
+	 * Now set the rest of the table to uncached - use entry 0 as
+	 * this will be uncached. Leave the last pair as initialised as
+	 * they are reserved by the hardware.
+	 */
+	for (; i < (GEN9_NUM_MOCS_ENTRIES / 2); i++)
+		I915_WRITE(GEN9_LNCFCMOCS(i), l3cc_combine(&table, 0, 0));
+}
+
+/**
  * intel_rcs_context_init_mocs() - program the MOCS register.
  * @req:	Request to set up the MOCS tables for.
  *
@@ -322,17 +405,11 @@ int intel_rcs_context_init_mocs(struct drm_i915_gem_request *req)
 	struct drm_i915_mocs_table t;
 	int ret;
 
-	if (get_mocs_settings(req->engine->dev, &t)) {
-		struct drm_i915_private *dev_priv = req->i915;
-		struct intel_engine_cs *engine;
-		enum intel_engine_id id;
-
-		/* Program the control registers */
-		for_each_engine_id(engine, dev_priv, id) {
-			ret = emit_mocs_control_table(req, &t, id);
-			if (ret)
-				return ret;
-		}
+	if (get_mocs_settings(req->i915, &t)) {
+		/* Program the RCS control registers */
+		ret = emit_mocs_control_table(req, &t);
+		if (ret)
+			return ret;
 
 		/* Now program the l3cc registers */
 		ret = emit_mocs_l3cc_table(req, &t);
diff --git a/drivers/gpu/drm/i915/intel_mocs.h b/drivers/gpu/drm/i915/intel_mocs.h
index 76e45b1748b3..4640299e04ec 100644
--- a/drivers/gpu/drm/i915/intel_mocs.h
+++ b/drivers/gpu/drm/i915/intel_mocs.h
@@ -53,5 +53,7 @@
 #include "i915_drv.h"
 
 int intel_rcs_context_init_mocs(struct drm_i915_gem_request *req);
+void intel_mocs_init_l3cc_table(struct drm_device *dev);
+int intel_mocs_init_engine(struct intel_engine_cs *ring);
 
 #endif