[Intel-gfx] [PATCH v2 2/2] drm/i915:gen9: Add disable gather at set shader w/a

[Arun Siluvery]

This WA is implemented in init_context as well as WA batch init.
There are also some dependent bits need to be set in other registers
for this to be complete.

v2: behaviour of disable gather at set shader bit can be specified by
two different registers, use a better option (Ben).

Cc: Ben Widawsky <benjamin.widawsky at intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h         |  5 +++++
 drivers/gpu/drm/i915/intel_lrc.c        |  8 ++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++++++++++++++
 3 files changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8991cd5..8719a5a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1721,6 +1721,10 @@ enum skl_disp_power_wells {
 #define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1<<2) /* 85x only */
 #define FW_BLC		0x020d8
 #define FW_BLC2		0x020dc
+#define GEN7_RS_CHICKEN  0x20DC
+#define   GEN9_RS_CHICKEN_DISABLE_GATHER_AT_SHADER (1<<2)
+#define GEN7_FF_SLICE_CHICKEN1    0x20E0
+#define   GEN9_PER_CTX_DISABLE_GATHER_CONTROL  (1<<15)
 #define FW_BLC_SELF	0x020e0 /* 915+ only */
 #define   FW_BLC_SELF_EN_MASK      (1<<31)
 #define   FW_BLC_SELF_FIFO_MASK    (1<<16) /* 945 only */
@@ -5836,6 +5840,7 @@ enum skl_disp_power_wells {
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
 # define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
 #define COMMON_SLICE_CHICKEN2			0x7014
+#define  GEN9_DISABLE_GATHER_SET_SHADER_SLICE   (1<<12)
 # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
 
 #define HIZ_CHICKEN					0x7018
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 9faad82..d3a03f3 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1292,6 +1292,14 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *ring,
 	struct drm_device *dev = ring->dev;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
+	/* WA to reset "disable gather at set shader slice" bit */
+	if (IS_SKYLAKE(dev)) {
+		wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
+		wa_ctx_emit(batch, index, COMMON_SLICE_CHICKEN2);
+		wa_ctx_emit(batch, index,
+			    _MASKED_BIT_DISABLE(GEN9_DISABLE_GATHER_SET_SHADER_SLICE));
+	}
+
 	/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
 	if ((IS_SKYLAKE(dev) && (INTEL_REVID(dev) <= SKL_REVID_B0)) ||
 	    (IS_BROXTON(dev) && (INTEL_REVID(dev) == BXT_REVID_A0))) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index dcd1b8f..5e8e5f9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -985,6 +985,17 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
 	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
 
+	/* WA to gather at set shader - skl,bxt
+	 * These are dependent bits need to be set for the WA.
+	 */
+	if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) > SKL_REVID_D0) ||
+	    (IS_BROXTON(dev) && INTEL_REVID(dev) > BXT_REVID_A0)) {
+		WA_SET_BIT_MASKED(GEN7_FF_SLICE_CHICKEN1,
+				  GEN9_PER_CTX_DISABLE_GATHER_CONTROL);
+		WA_SET_BIT_MASKED(GEN7_RS_CHICKEN,
+				  GEN9_RS_CHICKEN_DISABLE_GATHER_AT_SHADER);
+	}
+
 	return 0;
 }
 
@@ -1068,6 +1079,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 				  HDC_FENCE_DEST_SLM_DISABLE |
 				  HDC_BARRIER_PERFORMANCE_DISABLE);
 
+	/* WA to Disable gather at set shader - skl
+	 * This bit needs to be reset in Per ctx WA batch and it is also
+	 * dependent on other bits in different register, all of them need
+	 * be set for the WA to be complete.
+	 */
+	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN9_DISABLE_GATHER_SET_SHADER_SLICE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
-- 
1.9.1