drm/i915: Use indirect ctx bb to mend CMD_BUF_CCTL

Use indirect ctx bb to load cmd buffer control value
from context image to avoid corruption.

v2: add to lrc layout (Chris)
v3: end to a cacheline (Chris)
v4: add to lrc fixed (Chris)
v5: value in offset+1

Testcase: igt/i915_selftest/gt_lrc
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/20200424230632.30333-1-mika.kuoppala@linux.intel.com

3 files changed, 115 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a2fc4ad06deb..c8014c265ffb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -294,6 +294,19 @@ static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
 	return x + 2;
 }
 
+static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
+{
+	if (engine->class != RENDER_CLASS)
+		return -1;
+
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0xb6;
+	else if (INTEL_GEN(engine->i915) >= 11)
+		return 0xaa;
+	else
+		return -1;
+}
+
 static u32
 lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 {
@@ -607,7 +620,7 @@ static void set_offsets(u32 *regs,
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END(x) 0, (x)
+#define END(total_state_size) 0, (total_state_size)
 {
 	const u32 base = engine->mmio_base;
 
@@ -1015,8 +1028,63 @@ static const u8 gen12_rcs_offsets[] = {
 	NOP(6),
 	LRI(1, 0),
 	REG(0x0c8),
+	NOP(3 + 9 + 1),
+
+	LRI(51, POSTED),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG(0x028),
+	REG(0x09c),
+	REG(0x0c0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x068),
+	REG(0x084),
+	NOP(1),
 
-	END(80)
+	END(192)
 };
 
 #undef END
@@ -3247,6 +3315,38 @@ gen12_emit_restore_scratch(const struct intel_context *ce, u32 *cs)
 }
 
 static u32 *
+gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs)
+{
+	GEM_BUG_ON(lrc_ring_cmd_buf_cctl(ce->engine) == -1);
+
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
+		(lrc_ring_cmd_buf_cctl(ce->engine) + 1) * sizeof(u32);
+	*cs++ = 0;
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO |
+		MI_LRI_LRM_CS_MMIO;
+	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+	*cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
+{
+	cs = gen12_emit_timestamp_wa(ce, cs);
+	cs = gen12_emit_cmd_buf_wa(ce, cs);
+	cs = gen12_emit_restore_scratch(ce, cs);
+
+	return cs;
+}
+
+static u32 *
 gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
 {
 	cs = gen12_emit_timestamp_wa(ce, cs);
@@ -3317,9 +3417,15 @@ __execlists_update_reg_state(const struct intel_context *ce,
 	}
 
 	if (ce->wa_bb_page) {
+		u32 *(*fn)(const struct intel_context *ce, u32 *cs);
+
+		fn = gen12_emit_indirect_ctx_xcs;
+		if (ce->engine->class == RENDER_CLASS)
+			fn = gen12_emit_indirect_ctx_rcs;
+
 		/* Mutually exclusive wrt to global indirect bb */
 		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
-		setup_indirect_ctx_bb(ce, engine, gen12_emit_indirect_ctx_xcs);
+		setup_indirect_ctx_bb(ce, engine, fn);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index d47dcd754f65..d3fa91aed7de 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -4618,6 +4618,11 @@ static int live_lrc_fixed(void *arg)
 				lrc_ring_gpr0(engine),
 				"RING_CS_GPR0"
 			},
+			{
+				i915_mmio_reg_offset(RING_CMD_BUF_CCTL(engine->mmio_base)),
+				lrc_ring_cmd_buf_cctl(engine),
+				"RING_CMD_BUF_CCTL"
+			},
 			{ },
 		}, *t;
 		u32 *hw;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 981b52aa5ed8..96d9f8853343 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2657,6 +2657,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
 #define RING_INSTPM(base)	_MMIO((base) + 0xc0)
 #define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
+#define RING_CMD_BUF_CCTL(base) _MMIO((base) + 0x84)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)