From: Jonathan Cavitt <jonathan.cavitt@xxxxxxxxx> For platforms that use Aux CCS, wait for aux invalidation to complete by checking the aux invalidation register bit is cleared. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Jonathan Cavitt <jonathan.cavitt@xxxxxxxxx> Signed-off-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx> Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 17 +++++++++++++---- drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index e10e1ad0e841f..83cddd9cb8b56 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -174,6 +174,16 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv *cs++ = AUX_INV; *cs++ = MI_NOOP; + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0; + *cs++ = MI_NOOP; + return cs; } @@ -274,10 +284,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + count = 8; if (!HAS_FLAT_CCS(rq->engine->i915)) - count = 8 + 4; - else - count = 8; + count += 10; cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -320,7 +329,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) aux_inv = rq->engine->mask & ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); if (aux_inv) - cmd += 4; + cmd += 10; } } diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 5d143e2a8db03..02125a1db2796 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -121,6 +121,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) -- 2.40.1