From patchwork Tue Jun 18 13:03:45 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tvrtko Ursulin X-Patchwork-Id: 11001665 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 443D113AF for ; Tue, 18 Jun 2019 13:04:48 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 319CB28AEF for ; Tue, 18 Jun 2019 13:04:48 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 2FDC228AFD; Tue, 18 Jun 2019 13:04:48 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-4.2 required=2.0 tests=BAYES_00,HK_RANDOM_FROM, MAILING_LIST_MULTI,RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 67E6228985 for ; Tue, 18 Jun 2019 13:04:47 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 9203D6E1BE; Tue, 18 Jun 2019 13:04:40 +0000 (UTC) X-Original-To: Intel-gfx@lists.freedesktop.org Delivered-To: Intel-gfx@lists.freedesktop.org Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by gabe.freedesktop.org (Postfix) with ESMTPS id 38A206E19C for ; Tue, 18 Jun 2019 13:04:38 +0000 (UTC) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by fmsmga101.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 18 Jun 2019 06:04:38 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.63,389,1557212400"; d="scan'208";a="160053434" Received: from yyosef-mobl.ger.corp.intel.com (HELO localhost.localdomain) ([10.252.23.42]) by fmsmga008.fm.intel.com with ESMTP; 18 Jun 2019 06:04:36 -0700 From: Tvrtko Ursulin To: Intel-gfx@lists.freedesktop.org Date: Tue, 18 Jun 2019 14:03:45 +0100 Message-Id: <20190618130345.6135-34-tvrtko.ursulin@linux.intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190618130345.6135-1-tvrtko.ursulin@linux.intel.com> References: <20190618130345.6135-1-tvrtko.ursulin@linux.intel.com> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH 33/33] drm/i915: Eliminate dual personality of i915_scratch_offset X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP From: Tvrtko Ursulin Scratch vma lives under gt but the API used to work on i915. Make this consistent by renaming the function to intel_gt_scratch_offset and make it take struct intel_gt. v2: * Move to intel_gt. (Chris) Signed-off-by: Tvrtko Ursulin Reviewed-by: Chris Wilson --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 2 +- drivers/gpu/drm/i915/gt/intel_gt.c | 38 ++++++++++++++++++++++ drivers/gpu/drm/i915/gt/intel_gt.h | 8 +++++ drivers/gpu/drm/i915/gt/intel_lrc.c | 9 ++--- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 29 ++++++++++------- drivers/gpu/drm/i915/i915_drv.h | 5 --- drivers/gpu/drm/i915/i915_gem.c | 31 ++---------------- drivers/gpu/drm/i915/i915_gpu_error.c | 2 +- 8 files changed, 73 insertions(+), 51 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 90c65269eadd..d1a4ef2b03ac 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -730,7 +730,7 @@ 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 204e7039ca32..c74fa55668c7 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 091ded4deead..c9ea3fdc21b0 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -22,4 +22,12 @@ 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 7cc3ab38768f..6daaba9b99bc 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" @@ -1681,7 +1682,7 @@ 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); @@ -1695,7 +1696,7 @@ 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; @@ -1732,7 +1733,7 @@ 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; @@ -2439,7 +2440,7 @@ 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 a5e6e2bb2376..19d52381b98f 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 +305,7 @@ 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 +348,8 @@ 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 +1078,9 @@ 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)) @@ -1504,7 +1511,7 @@ 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); @@ -1620,7 +1627,7 @@ 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 7d024c77eb5f..964653b41463 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2788,11 +2788,6 @@ 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 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915) 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 f47e774e9a43..741597d7e829 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1447,7 +1447,7 @@ 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); + engine->gt->scratch); request_record_user_bo(request, ee); ee->ctx =