diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index e30212e219ec..4961f74fd902 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -734,7 +734,7 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine) struct measure_breadcrumb *frame; int dw = -ENOMEM; - GEM_BUG_ON(!engine->i915->gt.scratch); + GEM_BUG_ON(!engine->gt->scratch); frame = kzalloc(sizeof(*frame), GFP_KERNEL); if (!frame) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index e22ee3e823fa..8cca6b22b386 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -203,3 +203,41 @@ void intel_gt_chipset_flush(struct intel_gt *gt) if (INTEL_GEN(gt->i915) < 6) intel_gtt_chipset_flush(); } + +int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size) +{ + struct drm_i915_private *i915 = gt->i915; + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int ret; + + obj = i915_gem_object_create_stolen(i915, size); + if (!obj) + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) { + DRM_ERROR("Failed to allocate scratch page\n"); + return PTR_ERR(obj); + } + + vma = i915_vma_instance(obj, >->ggtt->vm, NULL); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unref; + } + + ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); + if (ret) + goto err_unref; + + gt->scratch = vma; + return 0; + +err_unref: + i915_gem_object_put(obj); + return ret; +} + +void intel_gt_fini_scratch(struct intel_gt *gt) +{ + i915_vma_unpin_and_release(>->scratch, 0); +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 29cd15be6a01..cf3c6cecc8ee 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -21,4 +21,12 @@ void intel_gt_clear_error_registers(struct intel_gt *gt, void intel_gt_flush_ggtt_writes(struct intel_gt *gt); 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) +{ + return i915_ggtt_offset(gt->scratch); +} + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 3abcec3e4e0e..b3e0e25c5d80 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -135,6 +135,7 @@ #include "gem/i915_gem_context.h" +#include "gt/intel_gt.h" #include "i915_drv.h" #include "i915_gem_render_state.h" #include "i915_vgpu.h" @@ -1756,7 +1757,7 @@ 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++ = i915_scratch_offset(engine->i915) + 256; + *batch++ = intel_gt_scratch_offset(engine->gt) + 256; *batch++ = 0; *batch++ = MI_LOAD_REGISTER_IMM(1); @@ -1770,7 +1771,7 @@ 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++ = i915_scratch_offset(engine->i915) + 256; + *batch++ = intel_gt_scratch_offset(engine->gt) + 256; *batch++ = 0; return batch; @@ -1807,7 +1808,7 @@ 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, - i915_scratch_offset(engine->i915) + + intel_gt_scratch_offset(engine->gt) + 2 * CACHELINE_BYTES); *batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -2501,7 +2502,7 @@ static int gen8_emit_flush_render(struct i915_request *request, { struct intel_engine_cs *engine = request->engine; u32 scratch_addr = - i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES; + intel_gt_scratch_offset(engine->gt) + 2 * CACHELINE_BYTES; 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 aa483bba04bf..d65b8cba1a8f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -33,6 +33,8 @@ #include "gem/i915_gem_context.h" +#include "gt/intel_gt.h" + #include "i915_drv.h" #include "i915_gem_render_state.h" #include "i915_trace.h" @@ -75,7 +77,7 @@ 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++ = i915_scratch_offset(rq->i915); + *cs++ = intel_gt_scratch_offset(rq->engine->gt); *cs++ = 0; } *cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH; @@ -148,7 +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++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -156,7 +159,8 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; } @@ -208,7 +212,8 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) static int gen6_emit_post_sync_nonzero_flush(struct i915_request *rq) { - u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; + u32 scratch_addr = + intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; u32 *cs; cs = intel_ring_begin(rq, 6); @@ -241,7 +246,8 @@ gen6_emit_post_sync_nonzero_flush(struct i915_request *rq) static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; + u32 scratch_addr = + intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; int ret; @@ -299,7 +305,8 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) *cs++ = GFX_OP_PIPE_CONTROL(4); *cs++ = PIPE_CONTROL_QW_WRITE; - *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = intel_gt_scratch_offset(rq->engine->gt) | + PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; /* Finally we can flush and with it emit the breadcrumb */ @@ -342,7 +349,8 @@ gen7_render_ring_cs_stall_wa(struct i915_request *rq) static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; + u32 scratch_addr = + intel_gt_scratch_offset(rq->engine->gt) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; /* @@ -1071,9 +1079,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = i915_scratch_offset(rq->i915); + u32 *cs, cs_offset = intel_gt_scratch_offset(rq->engine->gt); - GEM_BUG_ON(rq->i915->gt.scratch->size < I830_WA_SIZE); + GEM_BUG_ON(rq->engine->gt->scratch->size < I830_WA_SIZE); cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1513,7 +1521,7 @@ 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++ = i915_scratch_offset(rq->i915); + *cs++ = intel_gt_scratch_offset(rq->engine->gt); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1629,7 +1637,7 @@ 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++ = i915_scratch_offset(rq->i915); + *cs++ = intel_gt_scratch_offset(rq->engine->gt); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 89a21fa4eac2..4077d15fe429 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2783,11 +2783,6 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) return I915_HWS_CSB_WRITE_INDEX; } -static inline u32 i915_scratch_offset(const struct drm_i915_private *i915) -{ - return i915_ggtt_offset(i915->gt.scratch); -} - static inline enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 6e07127242d9..8dff3b8f12c3 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1424,39 +1424,12 @@ err_active: static int i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size) { - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - int ret; - - obj = i915_gem_object_create_stolen(i915, size); - if (!obj) - obj = i915_gem_object_create_internal(i915, size); - if (IS_ERR(obj)) { - DRM_ERROR("Failed to allocate scratch page\n"); - return PTR_ERR(obj); - } - - vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unref; - } - - ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); - if (ret) - goto err_unref; - - i915->gt.scratch = vma; - return 0; - -err_unref: - i915_gem_object_put(obj); - return ret; + return intel_gt_init_scratch(&i915->gt, size); } static void i915_gem_fini_scratch(struct drm_i915_private *i915) { - i915_vma_unpin_and_release(&i915->gt.scratch, 0); + intel_gt_fini_scratch(&i915->gt); } static int intel_engines_verify_workarounds(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 330a25c5db6a..59f5b0265ee3 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1441,8 +1441,8 @@ static void gem_record_rings(struct i915_gpu_state *error) if (HAS_BROKEN_CS_TLB(i915)) ee->wa_batchbuffer = - i915_error_object_create(i915, - i915->gt.scratch); + i915_error_object_create(i915, + engine->gt->scratch); request_record_user_bo(request, ee); ee->ctx =