From 54939ea0bd85e128bdd5bca579508dd4701c5ce9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 18 Mar 2019 09:51:51 +0000 Subject: [PATCH] drm/i915: Switch to use HWS indices rather than addresses If we use the STORE_DATA_INDEX function we can use a fixed offset and avoid having to lookup up the engine HWS address. A step closer to being able to emit the final breadcrumb during request_add rather than later in the submission interrupt handler. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190318095204.9913-9-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_guc_submission.c | 3 ++- drivers/gpu/drm/i915/intel_lrc.c | 17 +++++++---------- drivers/gpu/drm/i915/intel_ringbuffer.c | 16 ++++++---------- drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++-- 4 files changed, 17 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c index 4a5727233419..c4ad73980988 100644 --- a/drivers/gpu/drm/i915/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/intel_guc_submission.c @@ -583,7 +583,8 @@ static void inject_preempt_context(struct work_struct *work) } else { cs = gen8_emit_ggtt_write(cs, GUC_PREEMPT_FINISHED, - addr); + addr, + 0); *cs++ = MI_NOOP; *cs++ = MI_NOOP; } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index e54e0064b2d6..29042060b42c 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -173,12 +173,6 @@ static void execlists_init_reg_state(u32 *reg_state, struct intel_engine_cs *engine, struct intel_ring *ring); -static inline u32 intel_hws_hangcheck_address(struct intel_engine_cs *engine) -{ - return (i915_ggtt_offset(engine->status_page.vma) + - I915_GEM_HWS_HANGCHECK_ADDR); -} - static inline struct i915_priolist *to_priolist(struct rb_node *rb) { return rb_entry(rb, struct i915_priolist, node); @@ -2214,11 +2208,14 @@ static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs) { cs = gen8_emit_ggtt_write(cs, request->fence.seqno, - request->timeline->hwsp_offset); + request->timeline->hwsp_offset, + 0); cs = gen8_emit_ggtt_write(cs, intel_engine_next_hangcheck_seqno(request->engine), - intel_hws_hangcheck_address(request->engine)); + I915_GEM_HWS_HANGCHECK_ADDR, + MI_FLUSH_DW_STORE_INDEX); + *cs++ = MI_USER_INTERRUPT; *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -2242,8 +2239,8 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) cs = gen8_emit_ggtt_write_rcs(cs, intel_engine_next_hangcheck_seqno(request->engine), - intel_hws_hangcheck_address(request->engine), - 0); + I915_GEM_HWS_HANGCHECK_ADDR, + PIPE_CONTROL_STORE_DATA_INDEX); *cs++ = MI_USER_INTERRUPT; *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index f26f5cc1584c..366be3d67e15 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -43,12 +43,6 @@ */ #define LEGACY_REQUEST_SIZE 200 -static inline u32 hws_hangcheck_address(struct intel_engine_cs *engine) -{ - return (i915_ggtt_offset(engine->status_page.vma) + - I915_GEM_HWS_HANGCHECK_ADDR); -} - unsigned int intel_ring_update_space(struct intel_ring *ring) { unsigned int space; @@ -317,8 +311,8 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) *cs++ = rq->fence.seqno; *cs++ = GFX_OP_PIPE_CONTROL(4); - *cs++ = PIPE_CONTROL_QW_WRITE; - *cs++ = hws_hangcheck_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_STORE_DATA_INDEX; + *cs++ = I915_GEM_HWS_HANGCHECK_ADDR | PIPE_CONTROL_GLOBAL_GTT; *cs++ = intel_engine_next_hangcheck_seqno(rq->engine); *cs++ = MI_USER_INTERRUPT; @@ -423,8 +417,10 @@ static u32 *gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) *cs++ = rq->fence.seqno; *cs++ = GFX_OP_PIPE_CONTROL(4); - *cs++ = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB; - *cs++ = hws_hangcheck_address(rq->engine); + *cs++ = (PIPE_CONTROL_QW_WRITE | + PIPE_CONTROL_STORE_DATA_INDEX | + PIPE_CONTROL_GLOBAL_GTT_IVB); + *cs++ = I915_GEM_HWS_HANGCHECK_ADDR; *cs++ = intel_engine_next_hangcheck_seqno(rq->engine); *cs++ = MI_USER_INTERRUPT; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index e612bdca9fd9..f9593e2e070d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -408,14 +408,14 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags) } static inline u32 * -gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset) +gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags) { /* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */ GEM_BUG_ON(gtt_offset & (1 << 5)); /* Offset should be aligned to 8 bytes for both (QW/DW) write types */ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); - *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW; + *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags; *cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT; *cs++ = 0; *cs++ = value;