drm/i915/gen12: Invalidate aux table entries forcibly

Aux table invalidation can fail on update. So
next access may cause memory access to be into stale entry.

Proposed workaround is to invalidate entries between
all batchbuffers.

v2: correct register address (Yang)
v3: respect the order (Chris)

References bspec#43904, hsdes#1809175790
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chuansheng Liu <chuansheng.liu@intel.com>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Cc: Yang A Shi <yang.a.shi@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200506165310.1239-1-mika.kuoppala@linux.intel.com

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -4539,6 +4539,17 @@ static u32 preparser_disable(bool state)
 	return MI_ARB_CHECK | 1 << 8 | state;
 }
 
+static u32 *
+gen12_emit_aux_table_inv(struct i915_request *rq, u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(GEN12_GFX_CCS_AUX_NV);
+	*cs++ = AUX_INV;
+	*cs++ = MI_NOOP;
+
+	return cs;
+}
+
 static int gen12_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
@@ -4587,7 +4598,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		flags |= PIPE_CONTROL_CS_STALL;
 
-		cs = intel_ring_begin(request, 8);
+		cs = intel_ring_begin(request, 8 + 4);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
@@ -4600,6 +4611,9 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
+		/* hsdes: 1809175790 */
+		cs = gen12_emit_aux_table_inv(request, cs);
+
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
 	}

drivers/gpu/drm/i915/i915_reg.h

@@ -2557,6 +2557,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
 #define GEN12_PAT_INDEX(index)	_MMIO(0x4800 + (index) * 4)
 #define BSD_HWS_PGA_GEN7	_MMIO(0x04180)
+#define GEN12_GFX_CCS_AUX_NV	_MMIO(0x4208)
+#define   AUX_INV		REG_BIT(0)
 #define BLT_HWS_PGA_GEN7	_MMIO(0x04280)
 #define VEBOX_HWS_PGA_GEN7	_MMIO(0x04380)
 #define RING_ACTHD(base)	_MMIO((base) + 0x74)