drm/i915: Report enabled slices on Haswell GT3

Batchbuffers constructed by userspace can conditionalise their URB
allocations through the use of the MI_SET_PREDICATE command. This
command can read the MI_PREDICATE_RESULT_2 register to see how many
slices are enabled on GT3, and by virtue of the result, scale their
memory allocations to fit enabled memory.

Of course, this only works if the kernel sets the appropriate bit in the
register first.

v2: Better commit subject and message by Chris Wilson.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Credits-to: Yejun Guo <yejun.guo@intel.com>
Signed-off-by: NRodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_drv.h

@@ -1603,6 +1603,8 @@ struct drm_i915_file_private {
 				 ((dev)->pci_device & 0xFF00) == 0x0C00)
 #define IS_ULT(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pci_device & 0xFF00) == 0x0A00)
+#define IS_HSW_GT3(dev)		(IS_HASWELL(dev) && \
+				 ((dev)->pci_device & 0x00F0) == 0x0020)
 
 /*
  * The genX designation typically refers to the render engine, so render

drivers/gpu/drm/i915/i915_gem.c

@@ -4331,6 +4331,11 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (dev_priv->ellc_size)
 		I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf));
 
+	if (IS_HSW_GT3(dev))
+		I915_WRITE(MI_PREDICATE_RESULT_2, LOWER_SLICE_ENABLED);
+	else
+		I915_WRITE(MI_PREDICATE_RESULT_2, LOWER_SLICE_DISABLED);
+
 	if (HAS_PCH_NOP(dev)) {
 		u32 temp = I915_READ(GEN7_MSG_CTL);
 		temp &= ~(WAIT_FOR_PCH_FLR_ACK | WAIT_FOR_PCH_RESET_ACK);

drivers/gpu/drm/i915/i915_reg.h

@@ -264,6 +264,11 @@
 #define  MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
 #define  MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
 #define  MI_SEMAPHORE_SYNC_INVALID  (3<<16)
+
+#define MI_PREDICATE_RESULT_2	(0x2214)
+#define  LOWER_SLICE_ENABLED	(1<<0)
+#define  LOWER_SLICE_DISABLED	(0<<0)
+
 /*
  * 3D instructions used by the kernel
  */