diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index cf3c6cecc8eeb359ca82aca9a4e814c0f079a9c4..1093dcf36f63b9c7c98f1e8eac95e30b0fbbe46e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -24,9 +24,10 @@ void intel_gt_chipset_flush(struct intel_gt *gt); int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size); void intel_gt_fini_scratch(struct intel_gt *gt); -static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt) +static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt, + enum intel_gt_scratch_field field) { - return i915_ggtt_offset(gt->scratch); + return i915_ggtt_offset(gt->scratch) + field; } #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 37da428bef626e666ed5e22ef761006cdbcfeb15..3563ce97010278741c6545290332a78827c9aa05 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -60,4 +60,19 @@ struct intel_gt { u32 pm_ier; }; +enum intel_gt_scratch_field { + /* 8 bytes */ + INTEL_GT_SCRATCH_FIELD_DEFAULT = 0, + + /* 8 bytes */ + INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA = 128, + + /* 8 bytes */ + INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH = 128, + + /* 8 bytes */ + INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA = 256, + +}; + #endif /* __INTEL_GT_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index e1ae1399c72bb739bdfb2f01fd3503c6b82c4ec9..dec735405195bcb012b40c6a9d15a3d618103465 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1782,7 +1782,8 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) /* NB no one else is allowed to scribble over scratch + 256! */ *batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = intel_gt_scratch_offset(engine->gt) + 256; + *batch++ = intel_gt_scratch_offset(engine->gt, + INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA); *batch++ = 0; *batch++ = MI_LOAD_REGISTER_IMM(1); @@ -1796,12 +1797,19 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = intel_gt_scratch_offset(engine->gt) + 256; + *batch++ = intel_gt_scratch_offset(engine->gt, + INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA); *batch++ = 0; return batch; } +static u32 slm_offset(struct intel_engine_cs *engine) +{ + return intel_gt_scratch_offset(engine->gt, + INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA); +} + /* * Typically we only have one indirect_ctx and per_ctx batch buffer which are * initialized at the beginning and shared across all contexts but this field @@ -1833,8 +1841,7 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - intel_gt_scratch_offset(engine->gt) + - 2 * CACHELINE_BYTES); + slm_offset(engine)); *batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -2528,7 +2535,8 @@ static int gen8_emit_flush_render(struct i915_request *request, { struct intel_engine_cs *engine = request->engine; u32 scratch_addr = - intel_gt_scratch_offset(engine->gt) + 2 * CACHELINE_BYTES; + intel_gt_scratch_offset(engine->gt, + INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH); bool vf_flush_wa = false, dc_flush_wa = false; u32 *cs, flags = 0; int len; diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c index b33cfc56f623c193108f5476b1f00e8a5b11a575..a98652e4055ced7387f6f7c3f8277a5d57b71b1f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -76,7 +76,8 @@ gen2_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = cmd; while (num_store_dw--) { *cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; - *cs++ = intel_gt_scratch_offset(rq->engine->gt); + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT); *cs++ = 0; } *cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH; @@ -149,7 +150,8 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) */ if (mode & EMIT_INVALIDATE) { *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -158,7 +160,8 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -212,7 +215,8 @@ static int gen6_emit_post_sync_nonzero_flush(struct i915_request *rq) { u32 scratch_addr = - intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; + intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH); u32 *cs; cs = intel_ring_begin(rq, 6); @@ -246,7 +250,8 @@ static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { u32 scratch_addr = - intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; + intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH); u32 *cs, flags = 0; int ret; @@ -304,7 +309,8 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) *cs++ = GFX_OP_PIPE_CONTROL(4); *cs++ = PIPE_CONTROL_QW_WRITE; - *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; @@ -349,7 +355,8 @@ static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { u32 scratch_addr = - intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; + intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH); u32 *cs, flags = 0; /* @@ -1078,7 +1085,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = intel_gt_scratch_offset(rq->engine->gt); + u32 *cs, cs_offset = + intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT); GEM_BUG_ON(rq->engine->gt->scratch->size < I830_WA_SIZE); @@ -1522,7 +1531,8 @@ static int flush_pd_dir(struct i915_request *rq) /* Stall until the page table load is complete */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base)); - *cs++ = intel_gt_scratch_offset(rq->engine->gt); + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1638,7 +1648,8 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* Insert a delay before the next switch! */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(last_reg); - *cs++ = intel_gt_scratch_offset(rq->engine->gt); + *cs++ = intel_gt_scratch_offset(rq->engine->gt, + INTEL_GT_SCRATCH_FIELD_DEFAULT); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;