[Intel-gfx] [PATCH v7] drm/i915: Add Wa_18022495364

[Dnyaneshwar Bhadane]

Invalidate instruction and State cache bit using INDIRECT_CTX on
every gpu context switch for gen12.
The goal of this workaround is to actually perform an explicit
invalidation of that cache (by re-writing the register) during every GPU
context switch, which is accomplished via a "workaround batchbuffer"
that's attached to the context via INDIRECT_CTX. (Matt Roper)
BSpec: 11354

Please refer [1] for more reviews and comment on the same patch

[1] https://patchwork.freedesktop.org/series/123377/

v2:
- Remove extra parentheses from the condition (Lucas)
- Align spacing and new line (Lucas)

v3:
- Fix commit message.

v4:
- Only Gen12 changes are kept and Remove DG2+ condition (Matt Roper)
- Fix the commit message for r-b (Matt Roper)
- Rename the register bit in define

v5:
- Move out this workaround from golden context init (Matt Roper)
- Use INDIRECT_CTX to set bit on each GPU context switch (Matt Roper)

v6:
- Change IP Version base condition for Gen12 (Matt Roper)
- Made imperative form of commit version messages (Suraj)
- s/Added/Add in patch header (Suraj)

v7: 
- In version descriptions s/Ropper/Roper (Matt Atwood)

Cc: Lucas De Marchi <lucas.demarchi at intel.com>
Cc: Matt Roper <matthew.d.roper at intel.com>
Cc: Suraj Kandpal <suraj.kandpal at intel.com>
Cc: Matt Atwood <matthew.s.atwood at intel.com>
Signed-off-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane at intel.com>
Reviewed-by: Matt Roper <matthew.d.roper at intel.com>

---
 drivers/gpu/drm/i915/gt/intel_gt_regs.h |  2 ++
 drivers/gpu/drm/i915/gt/intel_lrc.c     | 13 +++++++++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index a00ff51c681d..0d5260d126d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -164,6 +164,8 @@
 #define GEN9_CSFE_CHICKEN1_RCS			_MMIO(0x20d4)
 #define   GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE	(1 << 2)
 #define   GEN11_ENABLE_32_PLANE_MODE		(1 << 7)
+#define GEN12_CS_DEBUG_MODE2			_MMIO(0x20d8)
+#define   INSTRUCTION_STATE_CACHE_INVALIDATE	REG_BIT(6)
 
 #define GEN7_FF_SLICE_CS_CHICKEN1		_MMIO(0x20e0)
 #define   GEN9_FFSC_PERCTX_PREEMPT_CTRL		(1 << 14)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b99efa348ad1..56c916730e9b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1333,6 +1333,15 @@ dg2_emit_draw_watermark_setting(u32 *cs)
 	return cs;
 }
 
+static u32 *
+gen12_invalidate_state_cache(u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(GEN12_CS_DEBUG_MODE2);
+	*cs++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE);
+	return cs;
+}
+
 static u32 *
 gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 {
@@ -1346,6 +1355,10 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 
 	cs = gen12_emit_aux_table_inv(ce->engine, cs);
 
+	/* Wa_18022495364 */
+	if (IS_GFX_GT_IP_RANGE(ce->engine->gt, IP_VER(12, 0), IP_VER(12, 10)))
+		cs = gen12_invalidate_state_cache(cs);
+
 	/* Wa_16014892111 */
 	if (IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) ||
 	    IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 71), STEP_A0, STEP_B0) ||
-- 
2.34.1