drm/i915/hsw: Disable L3 caching of atomic memory operations.

Otherwise using any atomic memory operation will lock up the GPU due
to a Haswell hardware bug.

v2: Use the _MASKED_BIT_ENABLE macro.  Drop drm parameter definition.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: <stable@vger.kernel.org>
[danvet: Fix checkpatch fail.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -3881,6 +3881,9 @@
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
 
+#define HSW_SCRATCH1				0xb038
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+
 #define HSW_FUSE_STRAP		0x42014
 #define  HSW_CDCLK_LIMIT	(1 << 24)
 
@@ -4728,6 +4731,9 @@
 #define GEN7_ROW_CHICKEN2_GT2		0xf4f4
 #define   DOP_CLOCK_GATING_DISABLE	(1<<0)
 
+#define HSW_ROW_CHICKEN3		0xe49c
+#define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
+
 #define G4X_AUD_VID_DID			(dev_priv->info->display_mmio_offset + 0x62020)
 #define INTEL_AUDIO_DEVCL		0x808629FB
 #define INTEL_AUDIO_DEVBLC		0x80862801

drivers/gpu/drm/i915/intel_pm.c

@@ -4953,6 +4953,11 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
 			GEN7_WA_L3_CHICKEN_MODE);
 
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+	I915_WRITE(HSW_ROW_CHICKEN3,
+		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |