diff options
| author | Dave Airlie <airlied@redhat.com> | 2018-06-22 11:34:41 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2018-06-22 11:34:53 +1000 |
| commit | 3069290d9d6a9afa93661c299419089eea57164b (patch) | |
| tree | 97332731398879b501471ab61b7fd44048c94c63 /drivers/gpu | |
| parent | ce397d215ccd07b8ae3f71db689aedb85d56ab40 (diff) | |
| parent | 14c3f8425080a1ff97df7b81f7c339bf42c427a3 (diff) | |
| download | blackbird-op-linux-3069290d9d6a9afa93661c299419089eea57164b.tar.gz blackbird-op-linux-3069290d9d6a9afa93661c299419089eea57164b.zip | |
Merge tag 'drm-intel-next-2018-06-06' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
- Ice Lake's display enabling patches (Jose, Mahesh, Dhinakaran, Paulo, Manasi, Anusha, Arkadiusz)
- Ice Lake's workarounds (Oscar and Yunwei)
- Ice Lake interrupt registers fixes (Oscar)
- Context switch timeline fixes and improvements (Chris)
- Spelling fixes (Colin)
- GPU reset fixes and improvements (Chris)
- Including fixes on execlist and preemption for a proper GPU reset (Chris)
- Clean-up the port pipe select bits (Ville)
- Other execlist improvements (Chris)
- Remove unused enable_cmd_parser parameter (Chris)
- Fix order of enabling pipe/transcoder/planes on HSW+ to avoid hang on ICL (Paulo)
- Simplification and changes on intel_context (Chris)
- Disable LVDS on Radiant P845 (Ondrej)
- Improve HSW/BDW voltage swing handling (Ville)
- Cleanup and renames on few parts of intel_dp code to make code clear and less confusing (Ville)
- Move acpi lid notification code for fixing LVDS (Chris)
- Speed up GPU idle detection (Chris)
- Make intel_engine_dump irqsafe (Chris)
- Fix GVT crash (Zhenyu)
- Move GEM BO inside drm_framebuffer and use intel_fb_obj everywhere (Chris)
- Revert edp's alternate fixed mode (Jani)
- Protect tainted function pointer lookup (Chris)
- And subsequent unsigned long size fix (Chris)
- Allow page directory allocation to fail (Chris)
- VBT's edp and lvds fix and clean-up (Ville)
- Many other reorganizations and cleanups on DDI and DP code, as well on scaler and planes (Ville)
- Selftest pin the mock kernel context (Chris)
- Many PSR Fixes, clean-up and improvements (Dhinakaran)
- PSR VBT fix (Vathsala)
- Fix i915_scheduler and intel_context declaration (Tvrtko)
- Improve PCH underruns detection on ILK-IVB (Ville)
- Few s/drm_priv/i915 (Chris, Michal)
- Notify opregion of the sanitized encoder state (Maarten)
- Guc's event handling improvements and fixes on initialization failures (Michal)
- Many gtt fixes and improvements (Chris)
- Fixes and improvements for Suspend and Freeze safely (Chris)
- i915_gem init and fini cleanup and fixes (Michal)
- Remove obsolete switch_mm for gen8+ (Chris)
- hw and context id fixes for GuC (Lionel)
- Add new vGPU cap info bit VGT_CAPS_HUGE_GTT (Changbin)
- Make context pin/unpin symmetric (Chris)
- vma: Move the bind_count vs pin_count assertion to a helper (Chris)
- Use available SZ_1M instead of 1 << 20 (Chris)
- Trace and PMU fixes and improvements (Tvrtko)
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611162737.GA2378@intel.com
Diffstat (limited to 'drivers/gpu')
84 files changed, 3165 insertions, 2228 deletions
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 7c9ec4f4f36c..380eeb2a0e83 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -61,7 +61,7 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) } mutex_lock(&dev_priv->drm.struct_mutex); - ret = i915_gem_gtt_insert(&dev_priv->ggtt.base, node, + ret = i915_gem_gtt_insert(&dev_priv->ggtt.vm, node, size, I915_GTT_PAGE_SIZE, I915_COLOR_UNEVICTABLE, start, end, flags); diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 6d8180e8d1e2..120e24c3fc62 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -273,8 +273,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) for_each_pipe(dev_priv, pipe) { vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE; vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE; - vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE; - vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE; + vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~MCURSOR_MODE; + vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= MCURSOR_MODE_DISABLE; } vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE; diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 1c120683e958..00b788cf8b13 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -300,16 +300,16 @@ static int cursor_mode_to_drm(int mode) int cursor_pixel_formats_index = 4; switch (mode) { - case CURSOR_MODE_128_ARGB_AX: + case MCURSOR_MODE_128_ARGB_AX: cursor_pixel_formats_index = 0; break; - case CURSOR_MODE_256_ARGB_AX: + case MCURSOR_MODE_256_ARGB_AX: cursor_pixel_formats_index = 1; break; - case CURSOR_MODE_64_ARGB_AX: + case MCURSOR_MODE_64_ARGB_AX: cursor_pixel_formats_index = 2; break; - case CURSOR_MODE_64_32B_AX: + case MCURSOR_MODE_64_32B_AX: cursor_pixel_formats_index = 3; break; @@ -342,8 +342,8 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu, return -ENODEV; val = vgpu_vreg_t(vgpu, CURCNTR(pipe)); - mode = val & CURSOR_MODE; - plane->enabled = (mode != CURSOR_MODE_DISABLE); + mode = val & MCURSOR_MODE; + plane->enabled = (mode != MCURSOR_MODE_DISABLE); if (!plane->enabled) return -ENODEV; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 05d15a095310..2ff0d40281a9 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -361,9 +361,9 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt); #define gvt_aperture_sz(gvt) (gvt->dev_priv->ggtt.mappable_end) #define gvt_aperture_pa_base(gvt) (gvt->dev_priv->ggtt.gmadr.start) -#define gvt_ggtt_gm_sz(gvt) (gvt->dev_priv->ggtt.base.total) +#define gvt_ggtt_gm_sz(gvt) (gvt->dev_priv->ggtt.vm.total) #define gvt_ggtt_sz(gvt) \ - ((gvt->dev_priv->ggtt.base.total >> PAGE_SHIFT) << 3) + ((gvt->dev_priv->ggtt.vm.total >> PAGE_SHIFT) << 3) #define gvt_hidden_sz(gvt) (gvt_ggtt_gm_sz(gvt) - gvt_aperture_sz(gvt)) #define gvt_aperture_gmadr_base(gvt) (0) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 0f949554d118..708170e61625 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -446,9 +446,9 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next, #define CTX_CONTEXT_CONTROL_VAL 0x03 -bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id) +bool is_inhibit_context(struct intel_context *ce) { - u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state; + const u32 *reg_state = ce->lrc_reg_state; u32 inhibit_mask = _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); @@ -501,7 +501,7 @@ static void switch_mmio(struct intel_vgpu *pre, * itself. */ if (mmio->in_context && - !is_inhibit_context(s->shadow_ctx, ring_id)) + !is_inhibit_context(&s->shadow_ctx->__engine[ring_id])) continue; if (mmio->mask) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h index 0439eb8057a8..5c3b9ff9f96a 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.h +++ b/drivers/gpu/drm/i915/gvt/mmio_context.h @@ -49,7 +49,7 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt); -bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id); +bool is_inhibit_context(struct intel_context *ce); int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu, struct i915_request *req); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index c2d183b91500..7f5e01df95ee 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -54,11 +54,8 @@ static void set_context_pdp_root_pointer( static void update_shadow_pdps(struct intel_vgpu_workload *workload) { - struct intel_vgpu *vgpu = workload->vgpu; - int ring_id = workload->ring_id; - struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->__engine[ring_id].state->obj; + workload->req->hw_context->state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; @@ -128,9 +125,8 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) struct intel_vgpu *vgpu = workload->vgpu; struct intel_gvt *gvt = vgpu->gvt; int ring_id = workload->ring_id; - struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->__engine[ring_id].state->obj; + workload->req->hw_context->state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; void *dst; @@ -205,7 +201,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) static inline bool is_gvt_request(struct i915_request *req) { - return i915_gem_context_force_single_submission(req->ctx); + return i915_gem_context_force_single_submission(req->gem_context); } static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id) @@ -280,10 +276,8 @@ static int shadow_context_status_change(struct notifier_block *nb, return NOTIFY_OK; } -static void shadow_context_descriptor_update(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) +static void shadow_context_descriptor_update(struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); u64 desc = 0; desc = ce->lrc_desc; @@ -292,7 +286,7 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx, * like GEN8_CTX_* cached in desc_template */ desc &= U64_MAX << 12; - desc |= ctx->desc_template & ((1ULL << 12) - 1); + desc |= ce->gem_context->desc_template & ((1ULL << 12) - 1); ce->lrc_desc = desc; } @@ -300,12 +294,11 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx, static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; + struct i915_request *req = workload->req; void *shadow_ring_buffer_va; u32 *cs; - struct i915_request *req = workload->req; - if (IS_KABYLAKE(req->i915) && - is_inhibit_context(req->ctx, req->engine->id)) + if (IS_KABYLAKE(req->i915) && is_inhibit_context(req->hw_context)) intel_vgpu_restore_inhibit_context(vgpu, req); /* allocate shadow ring buffer */ @@ -353,92 +346,67 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) struct intel_vgpu_submission *s = &vgpu->submission; struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - int ring_id = workload->ring_id; - struct intel_engine_cs *engine = dev_priv->engine[ring_id]; - struct intel_ring *ring; + struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id]; + struct intel_context *ce; + struct i915_request *rq; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); - if (workload->shadowed) + if (workload->req) return 0; + /* pin shadow context by gvt even the shadow context will be pinned + * when i915 alloc request. That is because gvt will update the guest + * context from shadow context when workload is completed, and at that + * moment, i915 may already unpined the shadow context to make the + * shadow_ctx pages invalid. So gvt need to pin itself. After update + * the guest context, gvt can unpin the shadow_ctx safely. + */ + ce = intel_context_pin(shadow_ctx, engine); + if (IS_ERR(ce)) { + gvt_vgpu_err("fail to pin shadow context\n"); + return PTR_ERR(ce); + } + shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT); shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - if (!test_and_set_bit(ring_id, s->shadow_ctx_desc_updated)) - shadow_context_descriptor_update(shadow_ctx, - dev_priv->engine[ring_id]); + if (!test_and_set_bit(workload->ring_id, s->shadow_ctx_desc_updated)) + shadow_context_descriptor_update(ce); ret = intel_gvt_scan_and_shadow_ringbuffer(workload); if (ret) - goto err_scan; + goto err_unpin; if ((workload->ring_id == RCS) && (workload->wa_ctx.indirect_ctx.size != 0)) { ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx); if (ret) - goto err_scan; + goto err_shadow; } - /* pin shadow context by gvt even the shadow context will be pinned - * when i915 alloc request. That is because gvt will update the guest - * context from shadow context when workload is completed, and at that - * moment, i915 may already unpined the shadow context to make the - * shadow_ctx pages invalid. So gvt need to pin itself. After update - * the guest context, gvt can unpin the shadow_ctx safely. - */ - ring = intel_context_pin(shadow_ctx, engine); - if (IS_ERR(ring)) { - ret = PTR_ERR(ring); - gvt_vgpu_err("fail to pin shadow context\n"); + rq = i915_request_alloc(engine, shadow_ctx); + if (IS_ERR(rq)) { + gvt_vgpu_err("fail to allocate gem request\n"); + ret = PTR_ERR(rq); goto err_shadow; } + workload->req = i915_request_get(rq); ret = populate_shadow_context(workload); if (ret) - goto err_unpin; - workload->shadowed = true; - return 0; + goto err_req; -err_unpin: - intel_context_unpin(shadow_ctx, engine); + return 0; +err_req: + rq = fetch_and_zero(&workload->req); + i915_request_put(rq); err_shadow: release_shadow_wa_ctx(&workload->wa_ctx); -err_scan: - return ret; -} - -static int intel_gvt_generate_request(struct intel_vgpu_workload *workload) -{ - int ring_id = workload->ring_id; - struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv; - struct intel_engine_cs *engine = dev_priv->engine[ring_id]; - struct i915_request *rq; - struct intel_vgpu *vgpu = workload->vgpu; - struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; - int ret; - - rq = i915_request_alloc(dev_priv->engine[ring_id], shadow_ctx); - if (IS_ERR(rq)) { - gvt_vgpu_err("fail to allocate gem request\n"); - ret = PTR_ERR(rq); - goto err_unpin; - } - - gvt_dbg_sched("ring id %d get i915 gem request %p\n", ring_id, rq); - - workload->req = i915_request_get(rq); - ret = copy_workload_to_ring_buffer(workload); - if (ret) - goto err_unpin; - return 0; - err_unpin: - intel_context_unpin(shadow_ctx, engine); - release_shadow_wa_ctx(&workload->wa_ctx); + intel_context_unpin(ce); return ret; } @@ -517,21 +485,13 @@ err: return ret; } -static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx) +static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx) { - struct intel_vgpu_workload *workload = container_of(wa_ctx, - struct intel_vgpu_workload, - wa_ctx); - int ring_id = workload->ring_id; - struct intel_vgpu_submission *s = &workload->vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; - struct drm_i915_gem_object *ctx_obj = - shadow_ctx->__engine[ring_id].state->obj; - struct execlist_ring_context *shadow_ring_context; - struct page *page; - - page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); - shadow_ring_context = kmap_atomic(page); + struct intel_vgpu_workload *workload = + container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx); + struct i915_request *rq = workload->req; + struct execlist_ring_context *shadow_ring_context = + (struct execlist_ring_context *)rq->hw_context->lrc_reg_state; shadow_ring_context->bb_per_ctx_ptr.val = (shadow_ring_context->bb_per_ctx_ptr.val & @@ -539,9 +499,6 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx) shadow_ring_context->rcs_indirect_ctx.val = (shadow_ring_context->rcs_indirect_ctx.val & (~INDIRECT_CTX_ADDR_MASK)) | wa_ctx->indirect_ctx.shadow_gma; - - kunmap_atomic(shadow_ring_context); - return 0; } static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) @@ -633,7 +590,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload) goto err_unpin_mm; } - ret = intel_gvt_generate_request(workload); + ret = copy_workload_to_ring_buffer(workload); if (ret) { gvt_vgpu_err("fail to generate request\n"); goto err_unpin_mm; @@ -670,12 +627,9 @@ err_unpin_mm: static int dispatch_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; - struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; int ring_id = workload->ring_id; - struct intel_engine_cs *engine = dev_priv->engine[ring_id]; - int ret = 0; + int ret; gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n", ring_id, workload); @@ -687,10 +641,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) goto out; ret = prepare_workload(workload); - if (ret) { - intel_context_unpin(shadow_ctx, engine); - goto out; - } out: if (ret) @@ -765,27 +715,23 @@ out: static void update_guest_context(struct intel_vgpu_workload *workload) { + struct i915_request *rq = workload->req; struct intel_vgpu *vgpu = workload->vgpu; struct intel_gvt *gvt = vgpu->gvt; - struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; - int ring_id = workload->ring_id; - struct drm_i915_gem_object *ctx_obj = - shadow_ctx->__engine[ring_id].state->obj; + struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; void *src; unsigned long context_gpa, context_page_num; int i; - gvt_dbg_sched("ring id %d workload lrca %x\n", ring_id, - workload->ctx_desc.lrca); - - context_page_num = gvt->dev_priv->engine[ring_id]->context_size; + gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id, + workload->ctx_desc.lrca); + context_page_num = rq->engine->context_size; context_page_num = context_page_num >> PAGE_SHIFT; - if (IS_BROADWELL(gvt->dev_priv) && ring_id == RCS) + if (IS_BROADWELL(gvt->dev_priv) && rq->engine->id == RCS) context_page_num = 19; i = 2; @@ -858,6 +804,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) scheduler->current_workload[ring_id]; struct intel_vgpu *vgpu = workload->vgpu; struct intel_vgpu_submission *s = &vgpu->submission; + struct i915_request *rq = workload->req; int event; mutex_lock(&gvt->lock); @@ -866,11 +813,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) * switch to make sure request is completed. * For the workload w/o request, directly complete the workload. */ - if (workload->req) { - struct drm_i915_private *dev_priv = - workload->vgpu->gvt->dev_priv; - struct intel_engine_cs *engine = - dev_priv->engine[workload->ring_id]; + if (rq) { wait_event(workload->shadow_ctx_status_wq, !atomic_read(&workload->shadow_ctx_active)); @@ -886,8 +829,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) workload->status = 0; } - i915_request_put(fetch_and_zero(&workload->req)); - if (!workload->status && !(vgpu->resetting_eng & ENGINE_MASK(ring_id))) { update_guest_context(workload); @@ -896,10 +837,13 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) INTEL_GVT_EVENT_MAX) intel_vgpu_trigger_virtual_event(vgpu, event); } - mutex_lock(&dev_priv->drm.struct_mutex); + /* unpin shadow ctx as the shadow_ctx update is done */ - intel_context_unpin(s->shadow_ctx, engine); - mutex_unlock(&dev_priv->drm.struct_mutex); + mutex_lock(&rq->i915->drm.struct_mutex); + intel_context_unpin(rq->hw_context); + mutex_unlock(&rq->i915->drm.struct_mutex); + + i915_request_put(fetch_and_zero(&workload->req)); } gvt_dbg_sched("ring id %d complete workload %p status %d\n", @@ -1270,7 +1214,6 @@ alloc_workload(struct intel_vgpu *vgpu) atomic_set(&workload->shadow_ctx_active, 0); workload->status = -EINPROGRESS; - workload->shadowed = false; workload->vgpu = vgpu; return workload; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 6c644782193e..21eddab4a9cd 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -83,7 +83,6 @@ struct intel_vgpu_workload { struct i915_request *req; /* if this workload has been dispatched to i915? */ bool dispatched; - bool shadowed; int status; struct intel_vgpu_mm *shadow_mm; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 13e7b9e4a6e6..698af45e229c 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -328,7 +328,7 @@ static int per_file_stats(int id, void *ptr, void *data) } else { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm); - if (ppgtt->base.file != stats->file_priv) + if (ppgtt->vm.file != stats->file_priv) continue; } @@ -508,7 +508,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data) dpy_count, dpy_size); seq_printf(m, "%llu [%pa] gtt total\n", - ggtt->base.total, &ggtt->mappable_end); + ggtt->vm.total, &ggtt->mappable_end); seq_printf(m, "Supported page sizes: %s\n", stringify_page_sizes(INTEL_INFO(dev_priv)->page_sizes, buf, sizeof(buf))); @@ -542,8 +542,8 @@ static int i915_gem_object_info(struct seq_file *m, void *data) struct i915_request, client_link); rcu_read_lock(); - task = pid_task(request && request->ctx->pid ? - request->ctx->pid : file->pid, + task = pid_task(request && request->gem_context->pid ? + request->gem_context->pid : file->pid, PIDTYPE_PID); print_file_stats(m, task ? task->comm : "<unknown>", stats); rcu_read_unlock(); @@ -1162,19 +1162,28 @@ static int i915_frequency_info(struct seq_file *m, void *unused) intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) { - pm_ier = I915_READ(GEN6_PMIER); - pm_imr = I915_READ(GEN6_PMIMR); - pm_isr = I915_READ(GEN6_PMISR); - pm_iir = I915_READ(GEN6_PMIIR); - pm_mask = I915_READ(GEN6_PMINTRMSK); - } else { + if (INTEL_GEN(dev_priv) >= 11) { + pm_ier = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE); + pm_imr = I915_READ(GEN11_GPM_WGBOXPERF_INTR_MASK); + /* + * The equivalent to the PM ISR & IIR cannot be read + * without affecting the current state of the system + */ + pm_isr = 0; + pm_iir = 0; + } else if (INTEL_GEN(dev_priv) >= 8) { pm_ier = I915_READ(GEN8_GT_IER(2)); pm_imr = I915_READ(GEN8_GT_IMR(2)); pm_isr = I915_READ(GEN8_GT_ISR(2)); pm_iir = I915_READ(GEN8_GT_IIR(2)); - pm_mask = I915_READ(GEN6_PMINTRMSK); + } else { + pm_ier = I915_READ(GEN6_PMIER); + pm_imr = I915_READ(GEN6_PMIMR); + pm_isr = I915_READ(GEN6_PMISR); + pm_iir = I915_READ(GEN6_PMIIR); } + pm_mask = I915_READ(GEN6_PMINTRMSK); + seq_printf(m, "Video Turbo Mode: %s\n", yesno(rpmodectl & GEN6_RP_MEDIA_TURBO)); seq_printf(m, "HW control enabled: %s\n", @@ -1182,8 +1191,12 @@ static int i915_frequency_info(struct seq_file *m, void *unused) seq_printf(m, "SW control enabled: %s\n", yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); - seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n", - pm_ier, pm_imr, pm_isr, pm_iir, pm_mask); + + seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", + pm_ier, pm_imr, pm_mask); + if (INTEL_GEN(dev_priv) <= 10) + seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n", + pm_isr, pm_iir); seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n", rps->pm_intrmsk_mbz); seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); @@ -1895,7 +1908,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) fbdev_fb->base.format->cpp[0] * 8, fbdev_fb->base.modifier, drm_framebuffer_read_refcount(&fbdev_fb->base)); - describe_obj(m, fbdev_fb->obj); + describe_obj(m, intel_fb_obj(&fbdev_fb->base)); seq_putc(m, '\n'); } #endif @@ -1913,7 +1926,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) fb->base.format->cpp[0] * 8, fb->base.modifier, drm_framebuffer_read_refcount(&fb->base)); - describe_obj(m, fb->obj); + describe_obj(m, intel_fb_obj(&fb->base)); seq_putc(m, '\n'); } mutex_unlock(&dev->mode_config.fb_lock); @@ -2630,8 +2643,6 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); u32 psrperf = 0; - u32 stat[3]; - enum pipe pipe; bool enabled = false; bool sink_support; @@ -2652,47 +2663,17 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) seq_printf(m, "Re-enable work scheduled: %s\n", yesno(work_busy(&dev_priv->psr.work.work))); - if (HAS_DDI(dev_priv)) { - if (dev_priv->psr.psr2_enabled) - enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE; - else - enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE; - } else { - for_each_pipe(dev_priv, pipe) { - enum transcoder cpu_transcoder = - intel_pipe_to_cpu_transcoder(dev_priv, pipe); - enum intel_display_power_domain power_domain; - - power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); - if (!intel_display_power_get_if_enabled(dev_priv, - power_domain)) - continue; - - stat[pipe] = I915_READ(VLV_PSRSTAT(pipe)) & - VLV_EDP_PSR_CURR_STATE_MASK; - if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) || - (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE)) - enabled = true; - - intel_display_power_put(dev_priv, power_domain); - } - } + if (dev_priv->psr.psr2_enabled) + enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE; + else + enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE; seq_printf(m, "Main link in standby mode: %s\n", yesno(dev_priv->psr.link_standby)); - seq_printf(m, "HW Enabled & Active bit: %s", yesno(enabled)); - - if (!HAS_DDI(dev_priv)) - for_each_pipe(dev_priv, pipe) { - if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) || - (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE)) - seq_printf(m, " pipe %c", pipe_name(pipe)); - } - seq_puts(m, "\n"); + seq_printf(m, "HW Enabled & Active bit: %s\n", yesno(enabled)); /* - * VLV/CHV PSR has no kind of performance counter * SKL+ Perf counter is reset to 0 everytime DC state is entered */ if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { @@ -4245,8 +4226,13 @@ i915_drop_caches_set(void *data, u64 val) i915_gem_shrink_all(dev_priv); fs_reclaim_release(GFP_KERNEL); - if (val & DROP_IDLE) - drain_delayed_work(&dev_priv->gt.idle_work); + if (val & DROP_IDLE) { + do { + if (READ_ONCE(dev_priv->gt.active_requests)) + flush_delayed_work(&dev_priv->gt.retire_work); + drain_delayed_work(&dev_priv->gt.idle_work); + } while (READ_ONCE(dev_priv->gt.awake)); + } if (val & DROP_FREED) i915_gem_drain_freed_objects(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 9c449b8d8eab..be71fdf8d92e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -67,6 +67,7 @@ bool __i915_inject_load_failure(const char *func, int line) if (++i915_load_fail_count == i915_modparams.inject_load_failure) { DRM_INFO("Injecting failure at checkpoint %u [%s:%d]\n", i915_modparams.inject_load_failure, func, line); + i915_modparams.inject_load_failure = 0; return true; } @@ -117,16 +118,15 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level, static bool i915_error_injected(struct drm_i915_private *dev_priv) { #if IS_ENABLED(CONFIG_DRM_I915_DEBUG) - return i915_modparams.inject_load_failure && - i915_load_fail_count == i915_modparams.inject_load_failure; + return i915_load_fail_count && !i915_modparams.inject_load_failure; #else return false; #endif } -#define i915_load_error(dev_priv, fmt, ...) \ - __i915_printk(dev_priv, \ - i915_error_injected(dev_priv) ? KERN_DEBUG : KERN_ERR, \ +#define i915_load_error(i915, fmt, ...) \ + __i915_printk(i915, \ + i915_error_injected(i915) ? KERN_DEBUG : KERN_ERR, \ fmt, ##__VA_ARGS__) /* Map PCH device id to PCH type, or PCH_NONE if unknown. */ @@ -233,6 +233,8 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv) id = INTEL_PCH_SPT_DEVICE_ID_TYPE; else if (IS_COFFEELAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) id = INTEL_PCH_CNP_DEVICE_ID_TYPE; + else if (IS_ICELAKE(dev_priv)) + id = INTEL_PCH_ICP_DEVICE_ID_TYPE; if (id) DRM_DEBUG_KMS("Assuming PCH ID %04x\n", id); @@ -634,26 +636,6 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = { .can_switch = i915_switcheroo_can_switch, }; -static void i915_gem_fini(struct drm_i915_private *dev_priv) -{ - /* Flush any outstanding unpin_work. */ - i915_gem_drain_workqueue(dev_priv); - - mutex_lock(&dev_priv->drm.struct_mutex); - intel_uc_fini_hw(dev_priv); - intel_uc_fini(dev_priv); - i915_gem_cleanup_engines(dev_priv); - i915_gem_contexts_fini(dev_priv); - mutex_unlock(&dev_priv->drm.struct_mutex); - - intel_uc_fini_misc(dev_priv); - i915_gem_cleanup_userptr(dev_priv); - - i915_gem_drain_freed_objects(dev_priv); - - WARN_ON(!list_empty(&dev_priv->contexts.list)); -} - static int i915_load_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -1553,12 +1535,30 @@ static bool suspend_to_idle(struct drm_i915_private *dev_priv) return false; } +static int i915_drm_prepare(struct drm_device *dev) +{ + struct drm_i915_private *i915 = to_i915(dev); + int err; + + /* + * NB intel_display_suspend() may issue new requests after we've + * ostensibly marked the GPU as ready-to-sleep here. We need to + * split out that work and pull it forward so that after point, + * the GPU is not woken again. + */ + err = i915_gem_suspend(i915); + if (err) + dev_err(&i915->drm.pdev->dev, + "GEM idle failed, suspend/resume might fail\n"); + + return err; +} + static int i915_drm_suspend(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); struct pci_dev *pdev = dev_priv->drm.pdev; pci_power_t opregion_target_state; - int error; /* ignore lid events during suspend */ mutex_lock(&dev_priv->modeset_restore_lock); @@ -1575,13 +1575,6 @@ static int i915_drm_suspend(struct drm_device *dev) pci_save_state(pdev); - error = i915_gem_suspend(dev_priv); - if (error) { - dev_err(&pdev->dev, - "GEM idle failed, resume might fail\n"); - goto out; - } - intel_display_suspend(dev); intel_dp_mst_suspend(dev); @@ -1600,7 +1593,6 @@ static int i915_drm_suspend(struct drm_device *dev) opregion_target_state = suspend_to_idle(dev_priv) ? PCI_D1 : PCI_D3cold; intel_opregion_notify_adapter(dev_priv, opregion_target_state); - intel_uncore_suspend(dev_priv); intel_opregion_unregister(dev_priv); intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true); @@ -1609,10 +1601,9 @@ static int i915_drm_suspend(struct drm_device *dev) intel_csr_ucode_suspend(dev_priv); -out: enable_rpm_wakeref_asserts(dev_priv); - return error; + return 0; } static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) @@ -1623,7 +1614,10 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) disable_rpm_wakeref_asserts(dev_priv); + i915_gem_suspend_late(dev_priv); + intel_display_set_init_power(dev_priv, false); + intel_uncore_suspend(dev_priv); /* * In case of firmware assisted context save/restore don't manually @@ -2081,6 +2075,22 @@ out: return ret; } +static int i915_pm_prepare(struct device *kdev) +{ + struct pci_dev *pdev = to_pci_dev(kdev); + struct drm_device *dev = pci_get_drvdata(pdev); + + if (!dev) { + dev_err(kdev, "DRM not initialized, aborting suspend.\n"); + return -ENODEV; + } + + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_prepare(dev); +} + static int i915_pm_suspend(struct device *kdev) { struct pci_dev *pdev = to_pci_dev(kdev); @@ -2731,6 +2741,7 @@ const struct dev_pm_ops i915_pm_ops = { * S0ix (via system suspend) and S3 event handlers [PMSG_SUSPEND, * PMSG_RESUME] */ + .prepare = i915_pm_prepare, .suspend = i915_pm_suspend, .suspend_late = i915_pm_suspend_late, .resume_early = i915_pm_resume_early, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 34c125e2d90c..79209ee25c21 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -85,8 +85,8 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20180514" -#define DRIVER_TIMESTAMP 1526300884 +#define DRIVER_DATE "20180606" +#define DRIVER_TIMESTAMP 1528323047 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and * WARN_ON()) for hw state sanity checks to check for unexpected conditions @@ -607,7 +607,6 @@ struct i915_psr { bool link_standby; bool colorimetry_support; bool alpm; - bool has_hw_tracking; bool psr2_enabled; u8 sink_sync_latency; bool debug; @@ -1049,9 +1048,9 @@ struct intel_vbt_data { /* Feature bits */ unsigned int int_tv_support:1; unsigned int lvds_dither:1; - unsigned int lvds_vbt:1; unsigned int int_crt_support:1; unsigned int lvds_use_ssc:1; + unsigned int int_lvds_support:1; unsigned int display_clock_mode:1; unsigned int fdi_rx_polarity_inverted:1; unsigned int panel_type:4; @@ -1067,7 +1066,6 @@ struct intel_vbt_data { int vswing; bool low_vswing; bool initialized; - bool support; int bpp; struct edp_power_seq pps; } edp; @@ -1078,8 +1076,8 @@ struct intel_vbt_data { bool require_aux_wakeup; int idle_frames; enum psr_lines_to_wait lines_to_wait; - int tp1_wakeup_time; - int tp2_tp3_wakeup_time; + int tp1_wakeup_time_us; + int tp2_tp3_wakeup_time_us; } psr; struct { @@ -1843,6 +1841,7 @@ struct drm_i915_private { */ struct ida hw_ida; #define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */ +#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */ #define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */ } contexts; @@ -1950,7 +1949,9 @@ struct drm_i915_private { */ struct i915_perf_stream *exclusive_stream; + struct intel_context *pinned_ctx; u32 specific_ctx_id; + u32 specific_ctx_id_mask; struct hrtimer poll_check_timer; wait_queue_head_t poll_wq; @@ -2743,6 +2744,8 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on); int intel_engines_init_mmio(struct drm_i915_private *dev_priv); int intel_engines_init(struct drm_i915_private *dev_priv); +u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv); + /* intel_hotplug.c */ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 pin_mask, u32 long_mask); @@ -3164,10 +3167,12 @@ void i915_gem_init_mmio(struct drm_i915_private *i915); int __must_check i915_gem_init(struct drm_i915_private *dev_priv); int __must_check i915_gem_init_hw(struct drm_i915_private *dev_priv); void i915_gem_init_swizzling(struct drm_i915_private *dev_priv); +void i915_gem_fini(struct drm_i915_private *dev_priv); void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv); int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv, unsigned int flags); int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv); +void i915_gem_suspend_late(struct drm_i915_private *dev_priv); void i915_gem_resume(struct drm_i915_private *dev_priv); int i915_gem_fault(struct vm_fault *vmf); int i915_gem_object_wait(struct drm_i915_gem_object *obj, @@ -3208,7 +3213,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, static inline struct i915_hw_ppgtt * i915_vm_to_ppgtt(struct i915_address_space *vm) { - return container_of(vm, struct i915_hw_ppgtt, base); + return container_of(vm, struct i915_hw_ppgtt, vm); } /* i915_gem_fence_reg.c */ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3704f4c0c2c9..86f1f9aaa119 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -65,7 +65,7 @@ insert_mappable_node(struct i915_ggtt *ggtt, struct drm_mm_node *node, u32 size) { memset(node, 0, sizeof(*node)); - return drm_mm_insert_node_in_range(&ggtt->base.mm, node, + return drm_mm_insert_node_in_range(&ggtt->vm.mm, node, size, 0, I915_COLOR_UNEVICTABLE, 0, ggtt->mappable_end, DRM_MM_INSERT_LOW); @@ -139,6 +139,8 @@ int i915_mutex_lock_interruptible(struct drm_device *dev) static u32 __i915_gem_park(struct drm_i915_private *i915) { + GEM_TRACE("\n"); + lockdep_assert_held(&i915->drm.struct_mutex); GEM_BUG_ON(i915->gt.active_requests); GEM_BUG_ON(!list_empty(&i915->gt.active_rings)); @@ -181,6 +183,8 @@ static u32 __i915_gem_park(struct drm_i915_private *i915) void i915_gem_park(struct drm_i915_private *i915) { + GEM_TRACE("\n"); + lockdep_assert_held(&i915->drm.struct_mutex); GEM_BUG_ON(i915->gt.active_requests); @@ -193,6 +197,8 @@ void i915_gem_park(struct drm_i915_private *i915) void i915_gem_unpark(struct drm_i915_private *i915) { + GEM_TRACE("\n"); + lockdep_assert_held(&i915->drm.struct_mutex); GEM_BUG_ON(!i915->gt.active_requests); @@ -243,17 +249,17 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, struct i915_vma *vma; u64 pinned; - pinned = ggtt->base.reserved; + pinned = ggtt->vm.reserved; mutex_lock(&dev->struct_mutex); - list_for_each_entry(vma, &ggtt->base.active_list, vm_link) + list_for_each_entry(vma, &ggtt->vm.active_list, vm_link) if (i915_vma_is_pinned(vma)) pinned += vma->node.size; - list_for_each_entry(vma, &ggtt->base.inactive_list, vm_link) + list_for_each_entry(vma, &ggtt->vm.inactive_list, vm_link) if (i915_vma_is_pinned(vma)) pinned += vma->node.size; mutex_unlock(&dev->struct_mutex); - args->aper_size = ggtt->base.total; + args->aper_size = ggtt->vm.total; args->aper_available_size = args->aper_size - pinned; return 0; @@ -1217,9 +1223,9 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj, page_length = remain < page_length ? remain : page_length; if (node.allocated) { wmb(); - ggtt->base.insert_page(&ggtt->base, - i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), - node.start, I915_CACHE_NONE, 0); + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), + node.start, I915_CACHE_NONE, 0); wmb(); } else { page_base += offset & PAGE_MASK; @@ -1240,8 +1246,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj, out_unpin: if (node.allocated) { wmb(); - ggtt->base.clear_range(&ggtt->base, - node.start, node.size); + ggtt->vm.clear_range(&ggtt->vm, node.start, node.size); remove_mappable_node(&node); } else { i915_vma_unpin(vma); @@ -1420,9 +1425,9 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj, page_length = remain < page_length ? remain : page_length; if (node.allocated) { wmb(); /* flush the write before we modify the GGTT */ - ggtt->base.insert_page(&ggtt->base, - i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), - node.start, I915_CACHE_NONE, 0); + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), + node.start, I915_CACHE_NONE, 0); wmb(); /* flush modifications to the GGTT (insert_page) */ } else { page_base += offset & PAGE_MASK; @@ -1449,8 +1454,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj, out_unpin: if (node.allocated) { wmb(); - ggtt->base.clear_range(&ggtt->base, - node.start, node.size); + ggtt->vm.clear_range(&ggtt->vm, node.start, node.size); remove_mappable_node(&node); } else { i915_vma_unpin(vma); @@ -1993,7 +1997,7 @@ compute_partial_view(struct drm_i915_gem_object *obj, */ int i915_gem_fault(struct vm_fault *vmf) { -#define MIN_CHUNK_PAGES ((1 << 20) >> PAGE_SHIFT) /* 1 MiB */ +#define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) struct vm_area_struct *area = vmf->vma; struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data); struct drm_device *dev = obj->base.dev; @@ -3003,7 +3007,7 @@ i915_gem_find_active_request(struct intel_engine_cs *engine) struct i915_request * i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) { - struct i915_request *request = NULL; + struct i915_request *request; /* * During the reset sequence, we must prevent the engine from @@ -3014,52 +3018,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) */ intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL); - /* - * Prevent the signaler thread from updating the request - * state (by calling dma_fence_signal) as we are processing - * the reset. The write from the GPU of the seqno is - * asynchronous and the signaler thread may see a different - * value to us and declare the request complete, even though - * the reset routine have picked that request as the active - * (incomplete) request. This conflict is not handled - * gracefully! - */ - kthread_park(engine->breadcrumbs.signaler); - - /* - * Prevent request submission to the hardware until we have - * completed the reset in i915_gem_reset_finish(). If a request - * is completed by one engine, it may then queue a request - * to a second via its execlists->tasklet *just* as we are - * calling engine->init_hw() and also writing the ELSP. - * Turning off the execlists->tasklet until the reset is over - * prevents the race. - * - * Note that this needs to be a single atomic operation on the - * tasklet (flush existing tasks, prevent new tasks) to prevent - * a race between reset and set-wedged. It is not, so we do the best - * we can atm and make sure we don't lock the machine up in the more - * common case of recursively being called from set-wedged from inside - * i915_reset. - */ - if (!atomic_read(&engine->execlists.tasklet.count)) - tasklet_kill(&engine->execlists.tasklet); - tasklet_disable(&engine->execlists.tasklet); - - /* - * We're using worker to queue preemption requests from the tasklet in - * GuC submission mode. - * Even though tasklet was disabled, we may still have a worker queued. - * Let's make sure that all workers scheduled before disabling the - * tasklet are completed before continuing with the reset. - */ - if (engine->i915->guc.preempt_wq) - flush_workqueue(engine->i915->guc.preempt_wq); - - if (engine->irq_seqno_barrier) - engine->irq_seqno_barrier(engine); - - request = i915_gem_find_active_request(engine); + request = engine->reset.prepare(engine); if (request && request->fence.error == -EIO) request = ERR_PTR(-EIO); /* Previous reset failed! */ @@ -3111,7 +3070,7 @@ static void skip_request(struct i915_request *request) static void engine_skip_context(struct i915_request *request) { struct intel_engine_cs *engine = request->engine; - struct i915_gem_context *hung_ctx = request->ctx; + struct i915_gem_context *hung_ctx = request->gem_context; struct i915_timeline *timeline = request->timeline; unsigned long flags; @@ -3121,7 +3080,7 @@ static void engine_skip_context(struct i915_request *request) spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING); list_for_each_entry_continue(request, &engine->timeline.requests, link) - if (request->ctx == hung_ctx) + if (request->gem_context == hung_ctx) skip_request(request); list_for_each_entry(request, &timeline->requests, link) @@ -3167,11 +3126,11 @@ i915_gem_reset_request(struct intel_engine_cs *engine, } if (stalled) { - i915_gem_context_mark_guilty(request->ctx); + i915_gem_context_mark_guilty(request->gem_context); skip_request(request); /* If this context is now banned, skip all pending requests. */ - if (i915_gem_context_is_banned(request->ctx)) + if (i915_gem_context_is_banned(request->gem_context)) engine_skip_context(request); } else { /* @@ -3181,7 +3140,7 @@ i915_gem_reset_request(struct intel_engine_cs *engine, */ request = i915_gem_find_active_request(engine); if (request) { - i915_gem_context_mark_innocent(request->ctx); + i915_gem_context_mark_innocent(request->gem_context); dma_fence_set_error(&request->fence, -EAGAIN); /* Rewind the engine to replay the incomplete rq */ @@ -3210,13 +3169,8 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine, if (request) request = i915_gem_reset_request(engine, request, stalled); - if (request) { - DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n", - engine->name, request->global_seqno); - } - /* Setup the CS to resume from the breadcrumb of the hung request */ - engine->reset_hw(engine, request); + engine->reset.reset(engine, request); } void i915_gem_reset(struct drm_i915_private *dev_priv, @@ -3230,14 +3184,14 @@ void i915_gem_reset(struct drm_i915_private *dev_priv, i915_retire_requests(dev_priv); for_each_engine(engine, dev_priv, id) { - struct i915_gem_context *ctx; + struct intel_context *ce; i915_gem_reset_engine(engine, engine->hangcheck.active_request, stalled_mask & ENGINE_MASK(id)); - ctx = fetch_and_zero(&engine->last_retired_context); - if (ctx) - intel_context_unpin(ctx, engine); + ce = fetch_and_zero(&engine->last_retired_context); + if (ce) + intel_context_unpin(ce); /* * Ostensibily, we always want a context loaded for powersaving, @@ -3264,8 +3218,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv, void i915_gem_reset_finish_engine(struct intel_engine_cs *engine) { - tasklet_enable(&engine->execlists.tasklet); - kthread_unpark(engine->breadcrumbs.signaler); + engine->reset.finish(engine); intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL); } @@ -3543,6 +3496,22 @@ new_requests_since_last_retire(const struct drm_i915_private *i915) work_pending(&i915->gt.idle_work.work)); } +static void assert_kernel_context_is_current(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + if (i915_terminally_wedged(&i915->gpu_error)) + return; + + GEM_BUG_ON(i915->gt.active_requests); + for_each_engine(engine, i915, id) { + GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request)); + GEM_BUG_ON(engine->last_retired_context != + to_intel_context(i915->kernel_context, engine)); + } +} + static void i915_gem_idle_work_handler(struct work_struct *work) { @@ -3554,6 +3523,24 @@ i915_gem_idle_work_handler(struct work_struct *work) if (!READ_ONCE(dev_priv->gt.awake)) return; + if (READ_ONCE(dev_priv->gt.active_requests)) + return; + + /* + * Flush out the last user context, leaving only the pinned + * kernel context resident. When we are idling on the kernel_context, + * no more new requests (with a context switch) are emitted and we + * can finally rest. A consequence is that the idle work handler is + * always called at least twice before idling (and if the system is + * idle that implies a round trip through the retire worker). + */ + mutex_lock(&dev_priv->drm.struct_mutex); + i915_gem_switch_to_kernel_context(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); + + GEM_TRACE("active_requests=%d (after switch-to-kernel-context)\n", + READ_ONCE(dev_priv->gt.active_requests)); + /* * Wait for last execlists context complete, but bail out in case a * new request is submitted. As we don't trust the hardware, we @@ -3587,6 +3574,8 @@ i915_gem_idle_work_handler(struct work_struct *work) epoch = __i915_gem_park(dev_priv); + assert_kernel_context_is_current(dev_priv); + rearm_hangcheck = false; out_unlock: mutex_unlock(&dev_priv->drm.struct_mutex); @@ -3735,7 +3724,29 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags) { - return i915_gem_active_wait(&tl->last_request, flags); + struct i915_request *rq; + long ret; + + rq = i915_gem_active_get_unlocked(&tl->last_request); + if (!rq) + return 0; + + /* + * "Race-to-idle". + * + * Switching to the kernel context is often used a synchronous + * step prior to idling, e.g. in suspend for flushing all + * current operations to memory before sleeping. These we + * want to complete as quickly as possible to avoid prolonged + * stalls, so allow the gpu to boost to maximum clocks. + */ + if (flags & I915_WAIT_FOR_IDLE_BOOST) + gen6_rps_boost(rq, NULL); + + ret = i915_request_wait(rq, flags, MAX_SCHEDULE_TIMEOUT); + i915_request_put(rq); + + return ret < 0 ? ret : 0; } static int wait_for_engines(struct drm_i915_private *i915) @@ -3753,6 +3764,9 @@ static int wait_for_engines(struct drm_i915_private *i915) int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags) { + GEM_TRACE("flags=%x (%s)\n", + flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked"); + /* If the device is asleep, we have no requests outstanding */ if (!READ_ONCE(i915->gt.awake)) return 0; @@ -3769,6 +3783,7 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags) return err; } i915_retire_requests(i915); + GEM_BUG_ON(i915->gt.active_requests); return wait_for_engines(i915); } else { @@ -4357,7 +4372,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, u64 flags) { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - struct i915_address_space *vm = &dev_priv->ggtt.base; + struct i915_address_space *vm = &dev_priv->ggtt.vm; struct i915_vma *vma; int ret; @@ -4945,25 +4960,26 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj) i915_gem_object_put(obj); } -static void assert_kernel_context_is_current(struct drm_i915_private *i915) +void i915_gem_sanitize(struct drm_i915_private *i915) { - struct i915_gem_context *kernel_context = i915->kernel_context; struct intel_engine_cs *engine; enum intel_engine_id id; - for_each_engine(engine, i915, id) { - GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request)); - GEM_BUG_ON(engine->last_retired_context != kernel_context); - } -} + GEM_TRACE("\n"); -void i915_gem_sanitize(struct drm_i915_private *i915) -{ - if (i915_terminally_wedged(&i915->gpu_error)) { - mutex_lock(&i915->drm.struct_mutex); + mutex_lock(&i915->drm.struct_mutex); + + intel_runtime_pm_get(i915); + intel_uncore_forcewake_get(i915, FORCEWAKE_ALL); + + /* + * As we have just resumed the machine and woken the device up from + * deep PCI sleep (presumably D3_cold), assume the HW has been reset + * back to defaults, recovering from whatever wedged state we left it + * in and so worth trying to use the device once more. + */ + if (i915_terminally_wedged(&i915->gpu_error)) i915_gem_unset_wedged(i915); - mutex_unlock(&i915->drm.struct_mutex); - } /* * If we inherit context state from the BIOS or earlier occupants @@ -4975,6 +4991,18 @@ void i915_gem_sanitize(struct drm_i915_private *i915) */ if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915)) WARN_ON(intel_gpu_reset(i915, ALL_ENGINES)); + + /* Reset the submission backend after resume as well as the GPU reset */ + for_each_engine(engine, i915, id) { + if (engine->reset.reset) + engine->reset.reset(engine, NULL); + } + + intel_uncore_forcewake_put(i915, FORCEWAKE_ALL); + intel_runtime_pm_put(i915); + + i915_gem_contexts_lost(i915); + mutex_unlock(&i915->drm.struct_mutex); } int i915_gem_suspend(struct drm_i915_private *dev_priv) @@ -4982,6 +5010,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) struct drm_device *dev = &dev_priv->drm; int ret; + GEM_TRACE("\n"); + intel_runtime_pm_get(dev_priv); intel_suspend_gt_powersave(dev_priv); @@ -5002,13 +5032,13 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) ret = i915_gem_wait_for_idle(dev_priv, I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED); + I915_WAIT_LOCKED | + I915_WAIT_FOR_IDLE_BOOST); if (ret && ret != -EIO) goto err_unlock; assert_kernel_context_is_current(dev_priv); } - i915_gem_contexts_lost(dev_priv); mutex_unlock(&dev->struct_mutex); intel_uc_suspend(dev_priv); @@ -5028,6 +5058,24 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) if (WARN_ON(!intel_engines_are_idle(dev_priv))) i915_gem_set_wedged(dev_priv); /* no hope, discard everything */ + intel_runtime_pm_put(dev_priv); + return 0; + +err_unlock: + mutex_unlock(&dev->struct_mutex); + intel_runtime_pm_put(dev_priv); + return ret; +} + +void i915_gem_suspend_late(struct drm_i915_private *i915) +{ + struct drm_i915_gem_object *obj; + struct list_head *phases[] = { + &i915->mm.unbound_list, + &i915->mm.bound_list, + NULL + }, **phase; + /* * Neither the BIOS, ourselves or any other kernel * expects the system to be in execlists mode on startup, @@ -5047,20 +5095,22 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) * machines is a good idea, we don't - just in case it leaves the * machine in an unusable condition. */ - intel_uc_sanitize(dev_priv); - i915_gem_sanitize(dev_priv); - intel_runtime_pm_put(dev_priv); - return 0; + mutex_lock(&i915->drm.struct_mutex); + for (phase = phases; *phase; phase++) { + list_for_each_entry(obj, *phase, mm.link) + WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false)); + } + mutex_unlock(&i915->drm.struct_mutex); -err_unlock: - mutex_unlock(&dev->struct_mutex); - intel_runtime_pm_put(dev_priv); - return ret; + intel_uc_sanitize(i915); + i915_gem_sanitize(i915); } void i915_gem_resume(struct drm_i915_private *i915) { + GEM_TRACE("\n"); + WARN_ON(i915->gt.awake); mutex_lock(&i915->drm.struct_mutex); @@ -5234,9 +5284,15 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) /* Only when the HW is re-initialised, can we replay the requests */ ret = __i915_gem_restart_engines(dev_priv); + if (ret) + goto cleanup_uc; out: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); return ret; + +cleanup_uc: + intel_uc_fini_hw(dev_priv); + goto out; } static int __intel_engines_record_defaults(struct drm_i915_private *i915) @@ -5357,12 +5413,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; - /* - * We need to fallback to 4K pages since gvt gtt handling doesn't - * support huge page entries - we will need to check either hypervisor - * mm can support huge guest page or just do emulation in gvt. - */ - if (intel_vgpu_active(dev_priv)) + /* We need to fallback to 4K pages if host doesn't support huge gtt. */ + if (intel_vgpu_active(dev_priv) && !intel_vgpu_has_huge_gtt(dev_priv)) mkwrite_device_info(dev_priv)->page_sizes = I915_GTT_PAGE_SIZE_4K; @@ -5502,6 +5554,28 @@ err_unlock: return ret; } +void i915_gem_fini(struct drm_i915_private *dev_priv) +{ + i915_gem_suspend_late(dev_priv); + + /* Flush any outstanding unpin_work. */ + i915_gem_drain_workqueue(dev_priv); + + mutex_lock(&dev_priv->drm.struct_mutex); + intel_uc_fini_hw(dev_priv); + intel_uc_fini(dev_priv); + i915_gem_cleanup_engines(dev_priv); + i915_gem_contexts_fini(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); + + intel_uc_fini_misc(dev_priv); + i915_gem_cleanup_userptr(dev_priv); + + i915_gem_drain_freed_objects(dev_priv); + + WARN_ON(!list_empty(&dev_priv->contexts.list)); +} + void i915_gem_init_mmio(struct drm_i915_private *i915) { i915_gem_sanitize(i915); @@ -5666,16 +5740,17 @@ int i915_gem_freeze(struct drm_i915_private *dev_priv) return 0; } -int i915_gem_freeze_late(struct drm_i915_private *dev_priv) +int i915_gem_freeze_late(struct drm_i915_private *i915) { struct drm_i915_gem_object *obj; struct list_head *phases[] = { - &dev_priv->mm.unbound_list, - &dev_priv->mm.bound_list, + &i915->mm.unbound_list, + &i915->mm.bound_list, NULL - }, **p; + }, **phase; - /* Called just before we write the hibernation image. + /* + * Called just before we write the hibernation image. * * We need to update the domain tracking to reflect that the CPU * will be accessing all the pages to create and restore from the @@ -5689,15 +5764,15 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv) * the objects as well, see i915_gem_freeze() */ - i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND); - i915_gem_drain_freed_objects(dev_priv); + i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_UNBOUND); + i915_gem_drain_freed_objects(i915); - spin_lock(&dev_priv->mm.obj_lock); - for (p = phases; *p; p++) { - list_for_each_entry(obj, *p, mm.link) - __start_cpu_write(obj); + mutex_lock(&i915->drm.struct_mutex); + for (phase = phases; *phase; phase++) { + list_for_each_entry(obj, *phase, mm.link) + WARN_ON(i915_gem_object_set_to_cpu_domain(obj, true)); } - spin_unlock(&dev_priv->mm.obj_lock); + mutex_unlock(&i915->drm.struct_mutex); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h index 525920404ede..261da577829a 100644 --- a/drivers/gpu/drm/i915/i915_gem.h +++ b/drivers/gpu/drm/i915/i915_gem.h @@ -26,6 +26,7 @@ #define __I915_GEM_H__ #include <linux/bug.h> +#include <linux/interrupt.h> struct drm_i915_private; @@ -62,9 +63,12 @@ struct drm_i915_private; #if IS_ENABLED(CONFIG_DRM_I915_TRACE_GEM) #define GEM_TRACE(...) trace_printk(__VA_ARGS__) #define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL) +#define GEM_TRACE_DUMP_ON(expr) \ + do { if (expr) ftrace_dump(DUMP_ALL); } while (0) #else #define GEM_TRACE(...) do { } while (0) #define GEM_TRACE_DUMP() do { } while (0) +#define GEM_TRACE_DUMP_ON(expr) BUILD_BUG_ON_INVALID(expr) #endif #define I915_NUM_ENGINES 8 @@ -72,4 +76,16 @@ struct drm_i915_private; void i915_gem_park(struct drm_i915_private *i915); void i915_gem_unpark(struct drm_i915_private *i915); +static inline void __tasklet_disable_sync_once(struct tasklet_struct *t) +{ + if (atomic_inc_return(&t->count) == 1) + tasklet_unlock_wait(t); +} + +static inline void __tasklet_enable_sync_once(struct tasklet_struct *t) +{ + if (atomic_dec_return(&t->count) == 0) + tasklet_kill(t); +} + #endif /* __I915_GEM_H__ */ diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 33f8a4b3c981..b2c7ac1b074d 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -127,14 +127,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx) for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { struct intel_context *ce = &ctx->__engine[n]; - if (!ce->state) - continue; - - WARN_ON(ce->pin_count); - if (ce->ring) - intel_ring_free(ce->ring); - - __i915_gem_object_release_unless_active(ce->state->obj); + if (ce->ops) + ce->ops->destroy(ce); } kfree(ctx->name); @@ -203,7 +197,7 @@ static void context_close(struct i915_gem_context *ctx) */ lut_close(ctx); if (ctx->ppgtt) - i915_ppgtt_close(&ctx->ppgtt->base); + i915_ppgtt_close(&ctx->ppgtt->vm); ctx->file_priv = ERR_PTR(-EBADF); i915_gem_context_put(ctx); @@ -214,10 +208,19 @@ static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out) int ret; unsigned int max; - if (INTEL_GEN(dev_priv) >= 11) + if (INTEL_GEN(dev_priv) >= 11) { max = GEN11_MAX_CONTEXT_HW_ID; - else - max = MAX_CONTEXT_HW_ID; + } else { + /* + * When using GuC in proxy submission, GuC consumes the + * highest bit in the context id to indicate proxy submission. + */ + if (USES_GUC_SUBMISSION(dev_priv)) + max = MAX_GUC_CONTEXT_HW_ID; + else + max = MAX_CONTEXT_HW_ID; + } + ret = ida_simple_get(&dev_priv->contexts.hw_ida, 0, max, GFP_KERNEL); @@ -246,7 +249,7 @@ static u32 default_desc_template(const struct drm_i915_private *i915, desc = GEN8_CTX_VALID | GEN8_CTX_PRIVILEGE; address_mode = INTEL_LEGACY_32B_CONTEXT; - if (ppgtt && i915_vm_is_48bit(&ppgtt->base)) + if (ppgtt && i915_vm_is_48bit(&ppgtt->vm)) address_mode = INTEL_LEGACY_64B_CONTEXT; desc |= address_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; @@ -266,6 +269,7 @@ __create_hw_context(struct drm_i915_private *dev_priv, struct drm_i915_file_private *file_priv) { struct i915_gem_context *ctx; + unsigned int n; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -283,6 +287,12 @@ __create_hw_context(struct drm_i915_private *dev_priv, ctx->i915 = dev_priv; ctx->sched.priority = I915_PRIORITY_NORMAL; + for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { + struct intel_context *ce = &ctx->__engine[n]; + + ce->gem_context = ctx; + } + INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL); INIT_LIST_HEAD(&ctx->handles_list); @@ -514,16 +524,8 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv) lockdep_assert_held(&dev_priv->drm.struct_mutex); - for_each_engine(engine, dev_priv, id) { - engine->legacy_active_context = NULL; - engine->legacy_active_ppgtt = NULL; - - if (!engine->last_retired_context) - continue; - - intel_context_unpin(engine->last_retired_context, engine); - engine->last_retired_context = NULL; - } + for_each_engine(engine, dev_priv, id) + intel_engine_lost_context(engine); } void i915_gem_contexts_fini(struct drm_i915_private *i915) @@ -583,58 +585,119 @@ last_request_on_engine(struct i915_timeline *timeline, { struct i915_request *rq; - if (timeline == &engine->timeline) - return NULL; + GEM_BUG_ON(timeline == &engine->timeline); rq = i915_gem_active_raw(&timeline->last_request, &engine->i915->drm.struct_mutex); - if (rq && rq->engine == engine) + if (rq && rq->engine == engine) { + GEM_TRACE("last request for %s on engine %s: %llx:%d\n", + timeline->name, engine->name, + rq->fence.context, rq->fence.seqno); + GEM_BUG_ON(rq->timeline != timeline); return rq; + } return NULL; } -static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine) +static bool engine_has_kernel_context_barrier(struct intel_engine_cs *engine) { - struct i915_timeline *timeline; + struct drm_i915_private *i915 = engine->i915; + const struct intel_context * const ce = + to_intel_context(i915->kernel_context, engine); + struct i915_timeline *barrier = ce->ring->timeline; + struct intel_ring *ring; + bool any_active = false; - list_for_each_entry(timeline, &engine->i915->gt.timelines, link) { - if (last_request_on_engine(timeline, engine)) + lockdep_assert_held(&i915->drm.struct_mutex); + list_for_each_entry(ring, &i915->gt.active_rings, active_link) { + struct i915_request *rq; + + rq = last_request_on_engine(ring->timeline, engine); + if (!rq) + continue; + + any_active = true; + + if (rq->hw_context == ce) + continue; + + /* + * Was this request submitted after the previous + * switch-to-kernel-context? + */ + if (!i915_timeline_sync_is_later(barrier, &rq->fence)) { + GEM_TRACE("%s needs barrier for %llx:%d\n", + ring->timeline->name, + rq->fence.context, + rq->fence.seqno); return false; + } + + GEM_TRACE("%s has barrier after %llx:%d\n", + ring->timeline->name, + rq->fence.context, + rq->fence.seqno); } - return intel_engine_has_kernel_context(engine); + /* + * If any other timeline was still active and behind the last barrier, + * then our last switch-to-kernel-context must still be queued and + * will run last (leaving the engine in the kernel context when it + * eventually idles). + */ + if (any_active) + return true; + + /* The engine is idle; check that it is idling in the kernel context. */ + return engine->last_retired_context == ce; } -int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv) +int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915) { struct intel_engine_cs *engine; - struct i915_timeline *timeline; enum intel_engine_id id; - lockdep_assert_held(&dev_priv->drm.struct_mutex); + GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake)); + + lockdep_assert_held(&i915->drm.struct_mutex); + GEM_BUG_ON(!i915->kernel_context); - i915_retire_requests(dev_priv); + i915_retire_requests(i915); - for_each_engine(engine, dev_priv, id) { + for_each_engine(engine, i915, id) { + struct intel_ring *ring; struct i915_request *rq; - if (engine_has_idle_kernel_context(engine)) + GEM_BUG_ON(!to_intel_context(i915->kernel_context, engine)); + if (engine_has_kernel_context_barrier(engine)) continue; - rq = i915_request_alloc(engine, dev_priv->kernel_context); + GEM_TRACE("emit barrier on %s\n", engine->name); + + rq = i915_request_alloc(engine, i915->kernel_context); if (IS_ERR(rq)) return PTR_ERR(rq); /* Queue this switch after all other activity */ - list_for_each_entry(timeline, &dev_priv->gt.timelines, link) { + list_for_each_entry(ring, &i915->gt.active_rings, active_link) { struct i915_request *prev; - prev = last_request_on_engine(timeline, engine); - if (prev) - i915_sw_fence_await_sw_fence_gfp(&rq->submit, - &prev->submit, - I915_FENCE_GFP); + prev = last_request_on_engine(ring->timeline, engine); + if (!prev) + continue; + + if (prev->gem_context == i915->kernel_context) + continue; + + GEM_TRACE("add barrier on %s for %llx:%d\n", + engine->name, + prev->fence.context, + prev->fence.seqno); + i915_sw_fence_await_sw_fence_gfp(&rq->submit, + &prev->submit, + I915_FENCE_GFP); + i915_timeline_sync_set(rq->timeline, &prev->fence); } /* @@ -747,11 +810,11 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, break; case I915_CONTEXT_PARAM_GTT_SIZE: if (ctx->ppgtt) - args->value = ctx->ppgtt->base.total; + args->value = ctx->ppgtt->vm.total; else if (to_i915(dev)->mm.aliasing_ppgtt) - args->value = to_i915(dev)->mm.aliasing_ppgtt->base.total; + args->value = to_i915(dev)->mm.aliasing_ppgtt->vm.total; else - args->value = to_i915(dev)->ggtt.base.total; + args->value = to_i915(dev)->ggtt.vm.total; break; case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE: args->value = i915_gem_context_no_error_capture(ctx); diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h index ace3b129c189..b116e4942c10 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.h +++ b/drivers/gpu/drm/i915/i915_gem_context.h @@ -30,6 +30,7 @@ #include <linux/radix-tree.h> #include "i915_gem.h" +#include "i915_scheduler.h" struct pid; @@ -45,6 +46,13 @@ struct intel_ring; #define DEFAULT_CONTEXT_HANDLE 0 +struct intel_context; + +struct intel_context_ops { + void (*unpin)(struct intel_context *ce); + void (*destroy)(struct intel_context *ce); +}; + /** * struct i915_gem_context - client state * @@ -144,11 +152,14 @@ struct i915_gem_context { /** engine: per-engine logical HW state */ struct intel_context { + struct i915_gem_context *gem_context; struct i915_vma *state; struct intel_ring *ring; u32 *lrc_reg_state; u64 lrc_desc; int pin_count; + + const struct intel_context_ops *ops; } __engine[I915_NUM_ENGINES]; /** ring_size: size for allocating the per-engine ring buffer */ @@ -263,25 +274,26 @@ to_intel_context(struct i915_gem_context *ctx, return &ctx->__engine[engine->id]; } -static inline struct intel_ring * +static inline struct intel_context * intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { return engine->context_pin(engine, ctx); } -static inline void __intel_context_pin(struct i915_gem_context *ctx, - const struct intel_engine_cs *engine) +static inline void __intel_context_pin(struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); - GEM_BUG_ON(!ce->pin_count); ce->pin_count++; } -static inline void intel_context_unpin(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) +static inline void intel_context_unpin(struct intel_context *ce) { - engine->context_unpin(engine, ctx); + GEM_BUG_ON(!ce->pin_count); + if (--ce->pin_count) + return; + + GEM_BUG_ON(!ce->ops); + ce->ops->unpin(ce); } /* i915_gem_context.c */ diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index f627a8c47c58..eefd449502e2 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -703,7 +703,7 @@ static int eb_select_context(struct i915_execbuffer *eb) return -ENOENT; eb->ctx = ctx; - eb->vm = ctx->ppgtt ? &ctx->ppgtt->base : &eb->i915->ggtt.base; + eb->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &eb->i915->ggtt.vm; eb->context_flags = 0; if (ctx->flags & CONTEXT_NO_ZEROMAP) @@ -943,9 +943,9 @@ static void reloc_cache_reset(struct reloc_cache *cache) if (cache->node.allocated) { struct i915_ggtt *ggtt = cache_to_ggtt(cache); - ggtt->base.clear_range(&ggtt->base, - cache->node.start, - cache->node.size); + ggtt->vm.clear_range(&ggtt->vm, + cache->node.start, + cache->node.size); drm_mm_remove_node(&cache->node); } else { i915_vma_unpin((struct i915_vma *)cache->node.mm); @@ -1016,7 +1016,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, if (IS_ERR(vma)) { memset(&cache->node, 0, sizeof(cache->node)); err = drm_mm_insert_node_in_range - (&ggtt->base.mm, &cache->node, + (&ggtt->vm.mm, &cache->node, PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, 0, ggtt->mappable_end, DRM_MM_INSERT_LOW); @@ -1037,9 +1037,9 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, offset = cache->node.start; if (cache->node.allocated) { wmb(); - ggtt->base.insert_page(&ggtt->base, - i915_gem_object_get_dma_address(obj, page), - offset, I915_CACHE_NONE, 0); + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, page), + offset, I915_CACHE_NONE, 0); } else { offset += page << PAGE_SHIFT; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 996ab2ad6c45..2b4a40a32b76 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -42,7 +42,7 @@ #include "intel_drv.h" #include "intel_frontbuffer.h" -#define I915_GFP_DMA (GFP_KERNEL | __GFP_HIGHMEM) +#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) /** * DOC: Global GTT views @@ -190,19 +190,11 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, return 1; } -static int ppgtt_bind_vma(struct i915_vma *vma, - enum i915_cache_level cache_level, - u32 unused) +static int gen6_ppgtt_bind_vma(struct i915_vma *vma, + enum i915_cache_level cache_level, + u32 unused) { u32 pte_flags; - int ret; - - if (!(vma->flags & I915_VMA_LOCAL_BIND)) { - ret = vma->vm->allocate_va_range(vma->vm, vma->node.start, - vma->size); - if (ret) - return ret; - } /* Currently applicable only to VLV */ pte_flags = 0; @@ -214,6 +206,22 @@ static int ppgtt_bind_vma(struct i915_vma *vma, return 0; } +static int gen8_ppgtt_bind_vma(struct i915_vma *vma, + enum i915_cache_level cache_level, + u32 unused) +{ + int ret; + + if (!(vma->flags & I915_VMA_LOCAL_BIND)) { + ret = vma->vm->allocate_va_range(vma->vm, + vma->node.start, vma->size); + if (ret) + return ret; + } + + return gen6_ppgtt_bind_vma(vma, cache_level, unused); +} + static void ppgtt_unbind_vma(struct i915_vma *vma) { vma->vm->clear_range(vma->vm, vma->node.start, vma->size); @@ -489,7 +497,7 @@ static int __setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p, gfp_t gfp) { - p->page = vm_alloc_page(vm, gfp | __GFP_NOWARN | __GFP_NORETRY); + p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL); if (unlikely(!p->page)) return -ENOMEM; @@ -506,7 +514,7 @@ static int __setup_page_dma(struct i915_address_space *vm, static int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p) { - return __setup_page_dma(vm, p, I915_GFP_DMA); + return __setup_page_dma(vm, p, __GFP_HIGHMEM); } static void cleanup_page_dma(struct i915_address_space *vm, @@ -520,8 +528,8 @@ static void cleanup_page_dma(struct i915_address_space *vm, #define setup_px(vm, px) setup_page_dma((vm), px_base(px)) #define cleanup_px(vm, px) cleanup_page_dma((vm), px_base(px)) -#define fill_px(ppgtt, px, v) fill_page_dma((vm), px_base(px), (v)) -#define fill32_px(ppgtt, px, v) fill_page_dma_32((vm), px_base(px), (v)) +#define fill_px(vm, px, v) fill_page_dma((vm), px_base(px), (v)) +#define fill32_px(vm, px, v) fill_page_dma_32((vm), px_base(px), (v)) static void fill_page_dma(struct i915_address_space *vm, struct i915_page_dma *p, @@ -614,7 +622,7 @@ static struct i915_page_table *alloc_pt(struct i915_address_space *vm) { struct i915_page_table *pt; - pt = kmalloc(sizeof(*pt), GFP_KERNEL | __GFP_NOWARN); + pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL); if (unlikely(!pt)) return ERR_PTR(-ENOMEM); @@ -651,7 +659,7 @@ static struct i915_page_directory *alloc_pd(struct i915_address_space *vm) { struct i915_page_directory *pd; - pd = kzalloc(sizeof(*pd), GFP_KERNEL | __GFP_NOWARN); + pd = kzalloc(sizeof(*pd), I915_GFP_ALLOW_FAIL); if (unlikely(!pd)) return ERR_PTR(-ENOMEM); @@ -685,7 +693,7 @@ static int __pdp_init(struct i915_address_space *vm, const unsigned int pdpes = i915_pdpes_per_pdp(vm); pdp->page_directory = kmalloc_array(pdpes, sizeof(*pdp->page_directory), - GFP_KERNEL | __GFP_NOWARN); + I915_GFP_ALLOW_FAIL); if (unlikely(!pdp->page_directory)) return -ENOMEM; @@ -765,53 +773,6 @@ static void gen8_initialize_pml4(struct i915_address_space *vm, memset_p((void **)pml4->pdps, vm->scratch_pdp, GEN8_PML4ES_PER_PML4); } -/* Broadwell Page Directory Pointer Descriptors */ -static int gen8_write_pdp(struct i915_request *rq, - unsigned entry, - dma_addr_t addr) -{ - struct intel_engine_cs *engine = rq->engine; - u32 *cs; - - BUG_ON(entry >= 4); - - cs = intel_ring_begin(rq, 6); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(engine, entry)); - *cs++ = upper_32_bits(addr); - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, entry)); - *cs++ = lower_32_bits(addr); - intel_ring_advance(rq, cs); - - return 0; -} - -static int gen8_mm_switch_3lvl(struct i915_hw_ppgtt *ppgtt, - struct i915_request *rq) -{ - int i, ret; - - for (i = GEN8_3LVL_PDPES - 1; i >= 0; i--) { - const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); - - ret = gen8_write_pdp(rq, i, pd_daddr); - if (ret) - return ret; - } - - return 0; -} - -static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt, - struct i915_request *rq) -{ - return gen8_write_pdp(rq, 0, px_dma(&ppgtt->pml4)); -} - /* PDE TLBs are a pain to invalidate on GEN8+. When we modify * the page table structures, we mark them dirty so that * context switching/execlist queuing code takes extra steps @@ -819,7 +780,7 @@ static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt, */ static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt) { - ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.i915)->ring_mask; + ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->vm.i915)->ring_mask; } /* Removes entries from a single page table, releasing it if it's empty. @@ -1012,7 +973,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, gen8_pte_t *vaddr; bool ret; - GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base)); + GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm)); pd = pdp->page_directory[idx->pdpe]; vaddr = kmap_atomic_px(pd->page_table[idx->pde]); do { @@ -1043,7 +1004,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, break; } - GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base)); + GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm)); pd = pdp->page_directory[idx->pdpe]; } @@ -1229,7 +1190,7 @@ static int gen8_init_scratch(struct i915_address_space *vm) { int ret; - ret = setup_scratch_page(vm, I915_GFP_DMA); + ret = setup_scratch_page(vm, __GFP_HIGHMEM); if (ret) return ret; @@ -1272,7 +1233,7 @@ free_scratch_page: static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; struct drm_i915_private *dev_priv = vm->i915; enum vgt_g2v_type msg; int i; @@ -1333,13 +1294,13 @@ static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt) int i; for (i = 0; i < GEN8_PML4ES_PER_PML4; i++) { - if (ppgtt->pml4.pdps[i] == ppgtt->base.scratch_pdp) + if (ppgtt->pml4.pdps[i] == ppgtt->vm.scratch_pdp) continue; - gen8_ppgtt_cleanup_3lvl(&ppgtt->base, ppgtt->pml4.pdps[i]); + gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, ppgtt->pml4.pdps[i]); } - cleanup_px(&ppgtt->base, &ppgtt->pml4); + cleanup_px(&ppgtt->vm, &ppgtt->pml4); } static void gen8_ppgtt_cleanup(struct i915_address_space *vm) @@ -1353,7 +1314,7 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) if (use_4lvl(vm)) gen8_ppgtt_cleanup_4lvl(ppgtt); else - gen8_ppgtt_cleanup_3lvl(&ppgtt->base, &ppgtt->pdp); + gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, &ppgtt->pdp); gen8_free_scratch(vm); } @@ -1489,7 +1450,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt, gen8_pte_t scratch_pte, struct seq_file *m) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; struct i915_page_directory *pd; u32 pdpe; @@ -1499,7 +1460,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt, u64 pd_start = start; u32 pde; - if (pdp->page_directory[pdpe] == ppgtt->base.scratch_pd) + if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd) continue; seq_printf(m, "\tPDPE #%d\n", pdpe); @@ -1507,7 +1468,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt, u32 pte; gen8_pte_t *pt_vaddr; - if (pd->page_table[pde] == ppgtt->base.scratch_pt) + if (pd->page_table[pde] == ppgtt->vm.scratch_pt) continue; pt_vaddr = kmap_atomic_px(pt); @@ -1540,10 +1501,10 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt, static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; const gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); - u64 start = 0, length = ppgtt->base.total; + u64 start = 0, length = ppgtt->vm.total; if (use_4lvl(vm)) { u64 pml4e; @@ -1551,7 +1512,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) struct i915_page_directory_pointer *pdp; gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) { - if (pml4->pdps[pml4e] == ppgtt->base.scratch_pdp) + if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp) continue; seq_printf(m, " PML4E #%llu\n", pml4e); @@ -1564,10 +1525,10 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; struct i915_page_directory_pointer *pdp = &ppgtt->pdp; struct i915_page_directory *pd; - u64 start = 0, length = ppgtt->base.total; + u64 start = 0, length = ppgtt->vm.total; u64 from = start; unsigned int pdpe; @@ -1603,11 +1564,11 @@ unwind: */ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; struct drm_i915_private *dev_priv = vm->i915; int ret; - ppgtt->base.total = USES_FULL_48BIT_PPGTT(dev_priv) ? + ppgtt->vm.total = USES_FULL_48BIT_PPGTT(dev_priv) ? 1ULL << 48 : 1ULL << 32; @@ -1615,27 +1576,26 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) * And we are not sure about the latter so play safe for now. */ if (IS_CHERRYVIEW(dev_priv) || IS_BROXTON(dev_priv)) - ppgtt->base.pt_kmap_wc = true; + ppgtt->vm.pt_kmap_wc = true; - ret = gen8_init_scratch(&ppgtt->base); + ret = gen8_init_scratch(&ppgtt->vm); if (ret) { - ppgtt->base.total = 0; + ppgtt->vm.total = 0; return ret; } if (use_4lvl(vm)) { - ret = setup_px(&ppgtt->base, &ppgtt->pml4); + ret = setup_px(&ppgtt->vm, &ppgtt->pml4); if (ret) goto free_scratch; - gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4); + gen8_initialize_pml4(&ppgtt->vm, &ppgtt->pml4); - ppgtt->switch_mm = gen8_mm_switch_4lvl; - ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_4lvl; - ppgtt->base.insert_entries = gen8_ppgtt_insert_4lvl; - ppgtt->base.clear_range = gen8_ppgtt_clear_4lvl; + ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_4lvl; + ppgtt->vm.insert_entries = gen8_ppgtt_insert_4lvl; + ppgtt->vm.clear_range = gen8_ppgtt_clear_4lvl; } else { - ret = __pdp_init(&ppgtt->base, &ppgtt->pdp); + ret = __pdp_init(&ppgtt->vm, &ppgtt->pdp); if (ret) goto free_scratch; @@ -1647,36 +1607,35 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) } } - ppgtt->switch_mm = gen8_mm_switch_3lvl; - ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_3lvl; - ppgtt->base.insert_entries = gen8_ppgtt_insert_3lvl; - ppgtt->base.clear_range = gen8_ppgtt_clear_3lvl; + ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_3lvl; + ppgtt->vm.insert_entries = gen8_ppgtt_insert_3lvl; + ppgtt->vm.clear_range = gen8_ppgtt_clear_3lvl; } if (intel_vgpu_active(dev_priv)) gen8_ppgtt_notify_vgt(ppgtt, true); - ppgtt->base.cleanup = gen8_ppgtt_cleanup; - ppgtt->base.unbind_vma = ppgtt_unbind_vma; - ppgtt->base.bind_vma = ppgtt_bind_vma; - ppgtt->base.set_pages = ppgtt_set_pages; - ppgtt->base.clear_pages = clear_pages; + ppgtt->vm.cleanup = gen8_ppgtt_cleanup; + ppgtt->vm.bind_vma = gen8_ppgtt_bind_vma; + ppgtt->vm.unbind_vma = ppgtt_unbind_vma; + ppgtt->vm.set_pages = ppgtt_set_pages; + ppgtt->vm.clear_pages = clear_pages; ppgtt->debug_dump = gen8_dump_ppgtt; return 0; free_scratch: - gen8_free_scratch(&ppgtt->base); + gen8_free_scratch(&ppgtt->vm); return ret; } static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) { - struct i915_address_space *vm = &ppgtt->base; + struct i915_address_space *vm = &ppgtt->vm; struct i915_page_table *unused; gen6_pte_t scratch_pte; u32 pd_entry, pte, pde; - u32 start = 0, length = ppgtt->base.total; + u32 start = 0, length = ppgtt->vm.total; scratch_pte = vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); @@ -1974,7 +1933,7 @@ static int gen6_init_scratch(struct i915_address_space *vm) { int ret; - ret = setup_scratch_page(vm, I915_GFP_DMA); + ret = setup_scratch_page(vm, __GFP_HIGHMEM); if (ret) return ret; @@ -2013,8 +1972,8 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt) { - struct i915_address_space *vm = &ppgtt->base; - struct drm_i915_private *dev_priv = ppgtt->base.i915; + struct i915_address_space *vm = &ppgtt->vm; + struct drm_i915_private *dev_priv = ppgtt->vm.i915; struct i915_ggtt *ggtt = &dev_priv->ggtt; int ret; @@ -2022,16 +1981,16 @@ static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt) * allocator works in address space sizes, so it's multiplied by page * size. We allocate at the top of the GTT to avoid fragmentation. */ - BUG_ON(!drm_mm_initialized(&ggtt->base.mm)); + BUG_ON(!drm_mm_initialized(&ggtt->vm.mm)); ret = gen6_init_scratch(vm); if (ret) return ret; - ret = i915_gem_gtt_insert(&ggtt->base, &ppgtt->node, + ret = i915_gem_gtt_insert(&ggtt->vm, &ppgtt->node, GEN6_PD_SIZE, GEN6_PD_ALIGN, I915_COLOR_UNEVICTABLE, - 0, ggtt->base.total, + 0, ggtt->vm.total, PIN_HIGH); if (ret) goto err_out; @@ -2064,16 +2023,16 @@ static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt, u32 pde; gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) - ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt; + ppgtt->pd.page_table[pde] = ppgtt->vm.scratch_pt; } static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) { - struct drm_i915_private *dev_priv = ppgtt->base.i915; + struct drm_i915_private *dev_priv = ppgtt->vm.i915; struct i915_ggtt *ggtt = &dev_priv->ggtt; int ret; - ppgtt->base.pte_encode = ggtt->base.pte_encode; + ppgtt->vm.pte_encode = ggtt->vm.pte_encode; if (intel_vgpu_active(dev_priv) || IS_GEN6(dev_priv)) ppgtt->switch_mm = gen6_mm_switch; else if (IS_HASWELL(dev_priv)) @@ -2087,24 +2046,24 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) if (ret) return ret; - ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE; + ppgtt->vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE; - gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total); - gen6_write_page_range(ppgtt, 0, ppgtt->base.total); + gen6_scratch_va_range(ppgtt, 0, ppgtt->vm.total); + gen6_write_page_range(ppgtt, 0, ppgtt->vm.total); - ret = gen6_alloc_va_range(&ppgtt->base, 0, ppgtt->base.total); + ret = gen6_alloc_va_range(&ppgtt->vm, 0, ppgtt->vm.total); if (ret) { - gen6_ppgtt_cleanup(&ppgtt->base); + gen6_ppgtt_cleanup(&ppgtt->vm); return ret; } - ppgtt->base.clear_range = gen6_ppgtt_clear_range; - ppgtt->base.insert_entries = gen6_ppgtt_insert_entries; - ppgtt->base.unbind_vma = ppgtt_unbind_vma; - ppgtt->base.bind_vma = ppgtt_bind_vma; - ppgtt->base.set_pages = ppgtt_set_pages; - ppgtt->base.clear_pages = clear_pages; - ppgtt->base.cleanup = gen6_ppgtt_cleanup; + ppgtt->vm.clear_range = gen6_ppgtt_clear_range; + ppgtt->vm.insert_entries = gen6_ppgtt_insert_entries; + ppgtt->vm.bind_vma = gen6_ppgtt_bind_vma; + ppgtt->vm.unbind_vma = ppgtt_unbind_vma; + ppgtt->vm.set_pages = ppgtt_set_pages; + ppgtt->vm.clear_pages = clear_pages; + ppgtt->vm.cleanup = gen6_ppgtt_cleanup; ppgtt->debug_dump = gen6_dump_ppgtt; DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n", @@ -2120,8 +2079,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt, struct drm_i915_private *dev_priv) { - ppgtt->base.i915 = dev_priv; - ppgtt->base.dma = &dev_priv->drm.pdev->dev; + ppgtt->vm.i915 = dev_priv; + ppgtt->vm.dma = &dev_priv->drm.pdev->dev; if (INTEL_GEN(dev_priv) < 8) return gen6_ppgtt_init(ppgtt); @@ -2231,10 +2190,10 @@ i915_ppgtt_create(struct drm_i915_private *dev_priv, } kref_init(&ppgtt->ref); - i915_address_space_init(&ppgtt->base, dev_priv, name); - ppgtt->base.file = fpriv; + i915_address_space_init(&ppgtt->vm, dev_priv, name); + ppgtt->vm.file = fpriv; - trace_i915_ppgtt_create(&ppgtt->base); + trace_i915_ppgtt_create(&ppgtt->vm); return ppgtt; } @@ -2268,16 +2227,16 @@ void i915_ppgtt_release(struct kref *kref) struct i915_hw_ppgtt *ppgtt = container_of(kref, struct i915_hw_ppgtt, ref); - trace_i915_ppgtt_release(&ppgtt->base); + trace_i915_ppgtt_release(&ppgtt->vm); - ppgtt_destroy_vma(&ppgtt->base); + ppgtt_destroy_vma(&ppgtt->vm); - GEM_BUG_ON(!list_empty(&ppgtt->base.active_list)); - GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list)); - GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list)); + GEM_BUG_ON(!list_empty(&ppgtt->vm.active_list)); + GEM_BUG_ON(!list_empty(&ppgtt->vm.inactive_list)); + GEM_BUG_ON(!list_empty(&ppgtt->vm.unbound_list)); - ppgtt->base.cleanup(&ppgtt->base); - i915_address_space_fini(&ppgtt->base); + ppgtt->vm.cleanup(&ppgtt->vm); + i915_address_space_fini(&ppgtt->vm); kfree(ppgtt); } @@ -2373,7 +2332,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv) i915_check_and_clear_faults(dev_priv); - ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total); + ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total); i915_ggtt_invalidate(dev_priv); } @@ -2716,16 +2675,16 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt; if (!(vma->flags & I915_VMA_LOCAL_BIND) && - appgtt->base.allocate_va_range) { - ret = appgtt->base.allocate_va_range(&appgtt->base, - vma->node.start, - vma->size); + appgtt->vm.allocate_va_range) { + ret = appgtt->vm.allocate_va_range(&appgtt->vm, + vma->node.start, + vma->size); if (ret) return ret; } - appgtt->base.insert_entries(&appgtt->base, vma, cache_level, - pte_flags); + appgtt->vm.insert_entries(&appgtt->vm, vma, cache_level, + pte_flags); } if (flags & I915_VMA_GLOBAL_BIND) { @@ -2748,7 +2707,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma) } if (vma->flags & I915_VMA_LOCAL_BIND) { - struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->base; + struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->vm; vm->clear_range(vm, vma->node.start, vma->size); } @@ -2815,30 +2774,30 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915) if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); - if (WARN_ON(ppgtt->base.total < ggtt->base.total)) { + if (WARN_ON(ppgtt->vm.total < ggtt->vm.total)) { err = -ENODEV; goto err_ppgtt; } - if (ppgtt->base.allocate_va_range) { + if (ppgtt->vm.allocate_va_range) { /* Note we only pre-allocate as far as the end of the global * GTT. On 48b / 4-level page-tables, the difference is very, * very significant! We have to preallocate as GVT/vgpu does * not like the page directory disappearing. */ - err = ppgtt->base.allocate_va_range(&ppgtt->base, - 0, ggtt->base.total); + err = ppgtt->vm.allocate_va_range(&ppgtt->vm, + 0, ggtt->vm.total); if (err) goto err_ppgtt; } i915->mm.aliasing_ppgtt = ppgtt; - GEM_BUG_ON(ggtt->base.bind_vma != ggtt_bind_vma); - ggtt->base.bind_vma = aliasing_gtt_bind_vma; + GEM_BUG_ON(ggtt->vm.bind_vma != ggtt_bind_vma); + ggtt->vm.bind_vma = aliasing_gtt_bind_vma; - GEM_BUG_ON(ggtt->base.unbind_vma != ggtt_unbind_vma); - ggtt->base.unbind_vma = aliasing_gtt_unbind_vma; + GEM_BUG_ON(ggtt->vm.unbind_vma != ggtt_unbind_vma); + ggtt->vm.unbind_vma = aliasing_gtt_unbind_vma; return 0; @@ -2858,8 +2817,8 @@ void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915) i915_ppgtt_put(ppgtt); - ggtt->base.bind_vma = ggtt_bind_vma; - ggtt->base.unbind_vma = ggtt_unbind_vma; + ggtt->vm.bind_vma = ggtt_bind_vma; + ggtt->vm.unbind_vma = ggtt_unbind_vma; } int i915_gem_init_ggtt(struct drm_i915_private *dev_priv) @@ -2883,7 +2842,7 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv) return ret; /* Reserve a mappable slot for our lockless error capture */ - ret = drm_mm_insert_node_in_range(&ggtt->base.mm, &ggtt->error_capture, + ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture, PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, 0, ggtt->mappable_end, DRM_MM_INSERT_LOW); @@ -2891,16 +2850,15 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv) return ret; /* Clear any non-preallocated blocks */ - drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) { + drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) { DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n", hole_start, hole_end); - ggtt->base.clear_range(&ggtt->base, hole_start, - hole_end - hole_start); + ggtt->vm.clear_range(&ggtt->vm, hole_start, + hole_end - hole_start); } /* And finally clear the reserved guard page */ - ggtt->base.clear_range(&ggtt->base, - ggtt->base.total - PAGE_SIZE, PAGE_SIZE); + ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE); if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) { ret = i915_gem_init_aliasing_ppgtt(dev_priv); @@ -2925,11 +2883,11 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv) struct i915_vma *vma, *vn; struct pagevec *pvec; - ggtt->base.closed = true; + ggtt->vm.closed = true; mutex_lock(&dev_priv->drm.struct_mutex); - GEM_BUG_ON(!list_empty(&ggtt->base.active_list)); - list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link) + GEM_BUG_ON(!list_empty(&ggtt->vm.active_list)); + list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link) WARN_ON(i915_vma_unbind(vma)); mutex_unlock(&dev_priv->drm.struct_mutex); @@ -2941,12 +2899,12 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv) if (drm_mm_node_allocated(&ggtt->error_capture)) drm_mm_remove_node(&ggtt->error_capture); - if (drm_mm_initialized(&ggtt->base.mm)) { + if (drm_mm_initialized(&ggtt->vm.mm)) { intel_vgt_deballoon(dev_priv); - i915_address_space_fini(&ggtt->base); + i915_address_space_fini(&ggtt->vm); } - ggtt->base.cleanup(&ggtt->base); + ggtt->vm.cleanup(&ggtt->vm); pvec = &dev_priv->mm.wc_stash; if (pvec->nr) { @@ -2996,7 +2954,7 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl) static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) { - struct drm_i915_private *dev_priv = ggtt->base.i915; + struct drm_i915_private *dev_priv = ggtt->vm.i915; struct pci_dev *pdev = dev_priv->drm.pdev; phys_addr_t phys_addr; int ret; @@ -3020,7 +2978,7 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) return -ENOMEM; } - ret = setup_scratch_page(&ggtt->base, GFP_DMA32); + ret = setup_scratch_page(&ggtt->vm, GFP_DMA32); if (ret) { DRM_ERROR("Scratch setup failed\n"); /* iounmap will also get called at remove, but meh */ @@ -3326,7 +3284,7 @@ static void setup_private_pat(struct drm_i915_private *dev_priv) static int gen8_gmch_probe(struct i915_ggtt *ggtt) { - struct drm_i915_private *dev_priv = ggtt->base.i915; + struct drm_i915_private *dev_priv = ggtt->vm.i915; struct pci_dev *pdev = dev_priv->drm.pdev; unsigned int size; u16 snb_gmch_ctl; @@ -3350,25 +3308,25 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) else size = gen8_get_total_gtt_size(snb_gmch_ctl); - ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT; - ggtt->base.cleanup = gen6_gmch_remove; - ggtt->base.bind_vma = ggtt_bind_vma; - ggtt->base.unbind_vma = ggtt_unbind_vma; - ggtt->base.set_pages = ggtt_set_pages; - ggtt->base.clear_pages = clear_pages; - ggtt->base.insert_page = gen8_ggtt_insert_page; - ggtt->base.clear_range = nop_clear_range; + ggtt->vm.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT; + ggtt->vm.cleanup = gen6_gmch_remove; + ggtt->vm.bind_vma = ggtt_bind_vma; + ggtt->vm.unbind_vma = ggtt_unbind_vma; + ggtt->vm.set_pages = ggtt_set_pages; + ggtt->vm.clear_pages = clear_pages; + ggtt->vm.insert_page = gen8_ggtt_insert_page; + ggtt->vm.clear_range = nop_clear_range; if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv)) - ggtt->base.clear_range = gen8_ggtt_clear_range; + ggtt->vm.clear_range = gen8_ggtt_clear_range; - ggtt->base.insert_entries = gen8_ggtt_insert_entries; + ggtt->vm.insert_entries = gen8_ggtt_insert_entries; /* Serialize GTT updates with aperture access on BXT if VT-d is on. */ if (intel_ggtt_update_needs_vtd_wa(dev_priv)) { - ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL; - ggtt->base.insert_page = bxt_vtd_ggtt_insert_page__BKL; - if (ggtt->base.clear_range != nop_clear_range) - ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL; + ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL; + ggtt->vm.insert_page = bxt_vtd_ggtt_insert_page__BKL; + if (ggtt->vm.clear_range != nop_clear_range) + ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL; } ggtt->invalidate = gen6_ggtt_invalidate; @@ -3380,7 +3338,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) static int gen6_gmch_probe(struct i915_ggtt *ggtt) { - struct drm_i915_private *dev_priv = ggtt->base.i915; + struct drm_i915_private *dev_priv = ggtt->vm.i915; struct pci_dev *pdev = dev_priv->drm.pdev; unsigned int size; u16 snb_gmch_ctl; @@ -3407,29 +3365,29 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); size = gen6_get_total_gtt_size(snb_gmch_ctl); - ggtt->base.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT; + ggtt->vm.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT; - ggtt->base.clear_range = gen6_ggtt_clear_range; - ggtt->base.insert_page = gen6_ggtt_insert_page; - ggtt->base.insert_entries = gen6_ggtt_insert_entries; - ggtt->base.bind_vma = ggtt_bind_vma; - ggtt->base.unbind_vma = ggtt_unbind_vma; - ggtt->base.set_pages = ggtt_set_pages; - ggtt->base.clear_pages = clear_pages; - ggtt->base.cleanup = gen6_gmch_remove; + ggtt->vm.clear_range = gen6_ggtt_clear_range; + ggtt->vm.insert_page = gen6_ggtt_insert_page; + ggtt->vm.insert_entries = gen6_ggtt_insert_entries; + ggtt->vm.bind_vma = ggtt_bind_vma; + ggtt->vm.unbind_vma = ggtt_unbind_vma; + ggtt->vm.set_pages = ggtt_set_pages; + ggtt->vm.clear_pages = clear_pages; + ggtt->vm.cleanup = gen6_gmch_remove; ggtt->invalidate = gen6_ggtt_invalidate; if (HAS_EDRAM(dev_priv)) - ggtt->base.pte_encode = iris_pte_encode; + ggtt->vm.pte_encode = iris_pte_encode; else if (IS_HASWELL(dev_priv)) - ggtt->base.pte_encode = hsw_pte_encode; + ggtt->vm.pte_encode = hsw_pte_encode; else if (IS_VALLEYVIEW(dev_priv)) - ggtt->base.pte_encode = byt_pte_encode; + ggtt->vm.pte_encode = byt_pte_encode; else if (INTEL_GEN(dev_priv) >= 7) - ggtt->base.pte_encode = ivb_pte_encode; + ggtt->vm.pte_encode = ivb_pte_encode; else - ggtt->base.pte_encode = snb_pte_encode; + ggtt->vm.pte_encode = snb_pte_encode; return ggtt_probe_common(ggtt, size); } @@ -3441,7 +3399,7 @@ static void i915_gmch_remove(struct i915_address_space *vm) static int i915_gmch_probe(struct i915_ggtt *ggtt) { - struct drm_i915_private *dev_priv = ggtt->base.i915; + struct drm_i915_private *dev_priv = ggtt->vm.i915; phys_addr_t gmadr_base; int ret; @@ -3451,23 +3409,21 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) return -EIO; } - intel_gtt_get(&ggtt->base.total, - &gmadr_base, - &ggtt->mappable_end); + intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end); ggtt->gmadr = (struct resource) DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end); ggtt->do_idle_maps = needs_idle_maps(dev_priv); - ggtt->base.insert_page = i915_ggtt_insert_page; - ggtt->base.insert_entries = i915_ggtt_insert_entries; - ggtt->base.clear_range = i915_ggtt_clear_range; - ggtt->base.bind_vma = ggtt_bind_vma; - ggtt->base.unbind_vma = ggtt_unbind_vma; - ggtt->base.set_pages = ggtt_set_pages; - ggtt->base.clear_pages = clear_pages; - ggtt->base.cleanup = i915_gmch_remove; + ggtt->vm.insert_page = i915_ggtt_insert_page; + ggtt->vm.insert_entries = i915_ggtt_insert_entries; + ggtt->vm.clear_range = i915_ggtt_clear_range; + ggtt->vm.bind_vma = ggtt_bind_vma; + ggtt->vm.unbind_vma = ggtt_unbind_vma; + ggtt->vm.set_pages = ggtt_set_pages; + ggtt->vm.clear_pages = clear_pages; + ggtt->vm.cleanup = i915_gmch_remove; ggtt->invalidate = gmch_ggtt_invalidate; @@ -3486,8 +3442,8 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv) struct i915_ggtt *ggtt = &dev_priv->ggtt; int ret; - ggtt->base.i915 = dev_priv; - ggtt->base.dma = &dev_priv->drm.pdev->dev; + ggtt->vm.i915 = dev_priv; + ggtt->vm.dma = &dev_priv->drm.pdev->dev; if (INTEL_GEN(dev_priv) <= 5) ret = i915_gmch_probe(ggtt); @@ -3504,27 +3460,29 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv) * restriction! */ if (USES_GUC(dev_priv)) { - ggtt->base.total = min_t(u64, ggtt->base.total, GUC_GGTT_TOP); - ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total); + ggtt->vm.total = min_t(u64, ggtt->vm.total, GUC_GGTT_TOP); + ggtt->mappable_end = + min_t(u64, ggtt->mappable_end, ggtt->vm.total); } - if ((ggtt->base.total - 1) >> 32) { + if ((ggtt->vm.total - 1) >> 32) { DRM_ERROR("We never expected a Global GTT with more than 32bits" " of address space! Found %lldM!\n", - ggtt->base.total >> 20); - ggtt->base.total = 1ULL << 32; - ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total); + ggtt->vm.total >> 20); + ggtt->vm.total = 1ULL << 32; + ggtt->mappable_end = + min_t(u64, ggtt->mappable_end, ggtt->vm.total); } - if (ggtt->mappable_end > ggtt->base.total) { + if (ggtt->mappable_end > ggtt->vm.total) { DRM_ERROR("mappable aperture extends past end of GGTT," " aperture=%pa, total=%llx\n", - &ggtt->mappable_end, ggtt->base.total); - ggtt->mappable_end = ggtt->base.total; + &ggtt->mappable_end, ggtt->vm.total); + ggtt->mappable_end = ggtt->vm.total; } /* GMADR is the PCI mmio aperture into the global GTT. */ - DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->base.total >> 20); + DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20); DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20); DRM_DEBUG_DRIVER("DSM size = %lluM\n", (u64)resource_size(&intel_graphics_stolen_res) >> 20); @@ -3551,9 +3509,9 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv) * and beyond the end of the GTT if we do not provide a guard. */ mutex_lock(&dev_priv->drm.struct_mutex); - i915_address_space_init(&ggtt->base, dev_priv, "[global]"); + i915_address_space_init(&ggtt->vm, dev_priv, "[global]"); if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv)) - ggtt->base.mm.color_adjust = i915_gtt_color_adjust; + ggtt->vm.mm.color_adjust = i915_gtt_color_adjust; mutex_unlock(&dev_priv->drm.struct_mutex); if (!io_mapping_init_wc(&dev_priv->ggtt.iomap, @@ -3576,7 +3534,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv) return 0; out_gtt_cleanup: - ggtt->base.cleanup(&ggtt->base); + ggtt->vm.cleanup(&ggtt->vm); return ret; } @@ -3610,34 +3568,31 @@ void i915_ggtt_disable_guc(struct drm_i915_private *i915) void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv) { struct i915_ggtt *ggtt = &dev_priv->ggtt; - struct drm_i915_gem_object *obj, *on; + struct i915_vma *vma, *vn; i915_check_and_clear_faults(dev_priv); /* First fill our portion of the GTT with scratch pages */ - ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total); + ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total); - ggtt->base.closed = true; /* skip rewriting PTE on VMA unbind */ + ggtt->vm.closed = true; /* skip rewriting PTE on VMA unbind */ /* clflush objects bound into the GGTT and rebind them. */ - list_for_each_entry_safe(obj, on, &dev_priv->mm.bound_list, mm.link) { - bool ggtt_bound = false; - struct i915_vma *vma; + GEM_BUG_ON(!list_empty(&ggtt->vm.active_list)); + list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link) { + struct drm_i915_gem_object *obj = vma->obj; - for_each_ggtt_vma(vma, obj) { - if (!i915_vma_unbind(vma)) - continue; + if (!(vma->flags & I915_VMA_GLOBAL_BIND)) + continue; - WARN_ON(i915_vma_bind(vma, obj->cache_level, - PIN_UPDATE)); - ggtt_bound = true; - } + if (!i915_vma_unbind(vma)) + continue; - if (ggtt_bound) - WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false)); + WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE)); + WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false)); } - ggtt->base.closed = false; + ggtt->vm.closed = false; if (INTEL_GEN(dev_priv) >= 8) { struct intel_ppat *ppat = &dev_priv->ppat; @@ -3657,8 +3612,10 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv) ppgtt = dev_priv->mm.aliasing_ppgtt; else ppgtt = i915_vm_to_ppgtt(vm); + if (!ppgtt) + continue; - gen6_write_page_range(ppgtt, 0, ppgtt->base.total); + gen6_write_page_range(ppgtt, 0, ppgtt->vm.total); } } @@ -3880,7 +3837,7 @@ int i915_gem_gtt_reserve(struct i915_address_space *vm, GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)); GEM_BUG_ON(!IS_ALIGNED(offset, I915_GTT_MIN_ALIGNMENT)); GEM_BUG_ON(range_overflows(offset, size, vm->total)); - GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base); + GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm); GEM_BUG_ON(drm_mm_node_allocated(node)); node->size = size; @@ -3977,7 +3934,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, GEM_BUG_ON(start >= end); GEM_BUG_ON(start > 0 && !IS_ALIGNED(start, I915_GTT_PAGE_SIZE)); GEM_BUG_ON(end < U64_MAX && !IS_ALIGNED(end, I915_GTT_PAGE_SIZE)); - GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base); + GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm); GEM_BUG_ON(drm_mm_node_allocated(node)); if (unlikely(range_overflows(start, size, end))) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index aec4f73574f4..197c2c06ecb7 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -65,7 +65,7 @@ typedef u64 gen8_pde_t; typedef u64 gen8_ppgtt_pdpe_t; typedef u64 gen8_ppgtt_pml4e_t; -#define ggtt_total_entries(ggtt) ((ggtt)->base.total >> PAGE_SHIFT) +#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT) /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */ #define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) @@ -367,7 +367,7 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm) * the spec. */ struct i915_ggtt { - struct i915_address_space base; + struct i915_address_space vm; struct io_mapping iomap; /* Mapping to our CPU mappable region */ struct resource gmadr; /* GMADR resource */ @@ -385,7 +385,7 @@ struct i915_ggtt { }; struct i915_hw_ppgtt { - struct i915_address_space base; + struct i915_address_space vm; struct kref ref; struct drm_mm_node node; unsigned long pd_dirty_rings; @@ -543,7 +543,7 @@ static inline struct i915_ggtt * i915_vm_to_ggtt(struct i915_address_space *vm) { GEM_BUG_ON(!i915_is_ggtt(vm)); - return container_of(vm, struct i915_ggtt, base); + return container_of(vm, struct i915_ggtt, vm); } #define INTEL_MAX_PPAT_ENTRIES 8 diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c index 1036e8686916..3210cedfa46c 100644 --- a/drivers/gpu/drm/i915/i915_gem_render_state.c +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c @@ -194,7 +194,7 @@ int i915_gem_render_state_emit(struct i915_request *rq) if (IS_ERR(so.obj)) return PTR_ERR(so.obj); - so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.base, NULL); + so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.vm, NULL); if (IS_ERR(so.vma)) { err = PTR_ERR(so.vma); goto err_obj; diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 5757fb7c4b5a..55e84e71f526 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -480,7 +480,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr /* We also want to clear any cached iomaps as they wrap vmap */ list_for_each_entry_safe(vma, next, - &i915->ggtt.base.inactive_list, vm_link) { + &i915->ggtt.vm.inactive_list, vm_link) { unsigned long count = vma->node.size >> PAGE_SHIFT; if (vma->iomap && i915_vma_unbind(vma) == 0) freed_pages += count; diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index ad949cc30928..79a347295e00 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -642,7 +642,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv if (ret) goto err; - vma = i915_vma_instance(obj, &ggtt->base, NULL); + vma = i915_vma_instance(obj, &ggtt->vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err_pages; @@ -653,7 +653,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv * setting up the GTT space. The actual reservation will occur * later. */ - ret = i915_gem_gtt_reserve(&ggtt->base, &vma->node, + ret = i915_gem_gtt_reserve(&ggtt->vm, &vma->node, size, gtt_offset, obj->cache_level, 0); if (ret) { @@ -666,7 +666,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv vma->pages = obj->mm.pages; vma->flags |= I915_VMA_GLOBAL_BIND; __i915_vma_set_map_and_fenceable(vma); - list_move_tail(&vma->vm_link, &ggtt->base.inactive_list); + list_move_tail(&vma->vm_link, &ggtt->vm.inactive_list); spin_lock(&dev_priv->mm.obj_lock); list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index df234dc23274..758234d20f4e 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -973,8 +973,7 @@ i915_error_object_create(struct drm_i915_private *i915, void __iomem *s; int ret; - ggtt->base.insert_page(&ggtt->base, dma, slot, - I915_CACHE_NONE, 0); + ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0); s = io_mapping_map_atomic_wc(&ggtt->iomap, slot); ret = compress_page(&compress, (void __force *)s, dst); @@ -993,7 +992,7 @@ unwind: out: compress_fini(&compress, dst); - ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE); + ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE); return dst; } @@ -1287,9 +1286,11 @@ static void error_record_engine_registers(struct i915_gpu_state *error, static void record_request(struct i915_request *request, struct drm_i915_error_request *erq) { - erq->context = request->ctx->hw_id; + struct i915_gem_context *ctx = request->gem_context; + + erq->context = ctx->hw_id; erq->sched_attr = request->sched.attr; - erq->ban_score = atomic_read(&request->ctx->ban_score); + erq->ban_score = atomic_read(&ctx->ban_score); erq->seqno = request->global_seqno; erq->jiffies = request->emitted_jiffies; erq->start = i915_ggtt_offset(request->ring->vma); @@ -1297,7 +1298,7 @@ static void record_request(struct i915_request *request, erq->tail = request->tail; rcu_read_lock(); - erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0; + erq->pid = ctx->pid ? pid_nr(ctx->pid) : 0; rcu_read_unlock(); } @@ -1461,12 +1462,12 @@ static void gem_record_rings(struct i915_gpu_state *error) request = i915_gem_find_active_request(engine); if (request) { + struct i915_gem_context *ctx = request->gem_context; struct intel_ring *ring; - ee->vm = request->ctx->ppgtt ? - &request->ctx->ppgtt->base : &ggtt->base; + ee->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &ggtt->vm; - record_context(&ee->context, request->ctx); + record_context(&ee->context, ctx); /* We need to copy these to an anonymous buffer * as the simplest method to avoid being overwritten @@ -1483,11 +1484,10 @@ static void gem_record_rings(struct i915_gpu_state *error) ee->ctx = i915_error_object_create(i915, - to_intel_context(request->ctx, - engine)->state); + request->hw_context->state); error->simulated |= - i915_gem_context_no_error_capture(request->ctx); + i915_gem_context_no_error_capture(ctx); ee->rq_head = request->head; ee->rq_post = request->postfix; @@ -1563,17 +1563,17 @@ static void capture_active_buffers(struct i915_gpu_state *error) static void capture_pinned_buffers(struct i915_gpu_state *error) { - struct i915_address_space *vm = &error->i915->ggtt.base; + struct i915_address_space *vm = &error->i915->ggtt.vm; struct drm_i915_error_buffer *bo; struct i915_vma *vma; int count_inactive, count_active; count_inactive = 0; - list_for_each_entry(vma, &vm->active_list, vm_link) + list_for_each_entry(vma, &vm->inactive_list, vm_link) count_inactive++; count_active = 0; - list_for_each_entry(vma, &vm->inactive_list, vm_link) + list_for_each_entry(vma, &vm->active_list, vm_link) count_active++; bo = NULL; @@ -1667,7 +1667,16 @@ static void capture_reg_state(struct i915_gpu_state *error) } /* 4: Everything else */ - if (INTEL_GEN(dev_priv) >= 8) { + if (INTEL_GEN(dev_priv) >= 11) { + error->ier = I915_READ(GEN8_DE_MISC_IER); + error->gtier[0] = I915_READ(GEN11_RENDER_COPY_INTR_ENABLE); + error->gtier[1] = I915_READ(GEN11_VCS_VECS_INTR_ENABLE); + error->gtier[2] = I915_READ(GEN11_GUC_SG_INTR_ENABLE); + error->gtier[3] = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE); + error->gtier[4] = I915_READ(GEN11_CRYPTO_RSVD_INTR_ENABLE); + error->gtier[5] = I915_READ(GEN11_GUNIT_CSME_INTR_ENABLE); + error->ngtier = 6; + } else if (INTEL_GEN(dev_priv) >= 8) { error->ier = I915_READ(GEN8_DE_MISC_IER); for (i = 0; i < 4; i++) error->gtier[i] = I915_READ(GEN8_GT_IER(i)); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index dac0f8c4c1cf..58910f1dc67c 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -58,7 +58,7 @@ struct i915_gpu_state { u32 eir; u32 pgtbl_er; u32 ier; - u32 gtier[4], ngtier; + u32 gtier[6], ngtier; u32 ccid; u32 derrmr; u32 forcewake; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index f9bc3aaa90d0..2fd92a886789 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2640,7 +2640,8 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) GEN9_AUX_CHANNEL_C | GEN9_AUX_CHANNEL_D; - if (IS_CNL_WITH_PORT_F(dev_priv)) + if (IS_CNL_WITH_PORT_F(dev_priv) || + INTEL_GEN(dev_priv) >= 11) tmp_mask |= CNL_AUX_CHANNEL_F; if (iir & tmp_mask) { @@ -3920,7 +3921,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS; } - if (IS_CNL_WITH_PORT_F(dev_priv)) + if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11) de_port_masked |= CNL_AUX_CHANNEL_F; de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 66ea3552c63e..49fcc4679db6 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -130,9 +130,6 @@ i915_param_named_unsafe(invert_brightness, int, 0600, i915_param_named(disable_display, bool, 0400, "Disable display (default: false)"); -i915_param_named_unsafe(enable_cmd_parser, bool, 0400, - "Enable command parsing (true=enabled [default], false=disabled)"); - i915_param_named(mmio_debug, int, 0600, "Enable the MMIO debug code for the first N failures (default: off). " "This may negatively affect performance."); diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index 6684025b7af8..aebe0469ddaa 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -58,7 +58,6 @@ struct drm_printer; param(unsigned int, inject_load_failure, 0) \ /* leave bools at the end to not create holes */ \ param(bool, alpha_support, IS_ENABLED(CONFIG_DRM_I915_ALPHA_SUPPORT)) \ - param(bool, enable_cmd_parser, true) \ param(bool, enable_hangcheck, true) \ param(bool, fastboot, false) \ param(bool, prefault_disable, false) \ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 4364922e935d..97a91e6af7e3 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -340,7 +340,6 @@ static const struct intel_device_info intel_valleyview_info = { GEN(7), .is_lp = 1, .num_pipes = 2, - .has_psr = 1, .has_runtime_pm = 1, .has_rc6 = 1, .has_gmch_display = 1, @@ -433,7 +432,6 @@ static const struct intel_device_info intel_cherryview_info = { .is_lp = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, .has_64bit_reloc = 1, - .has_psr = 1, .has_runtime_pm = 1, .has_resource_streamer = 1, .has_rc6 = 1, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 019bd2d073ad..a6c8d61add0c 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -737,12 +737,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, continue; } - /* - * XXX: Just keep the lower 21 bits for now since I'm not - * entirely sure if the HW touches any of the higher bits in - * this field - */ - ctx_id = report32[2] & 0x1fffff; + ctx_id = report32[2] & dev_priv->perf.oa.specific_ctx_id_mask; /* * Squash whatever is in the CTX_ID field if it's marked as @@ -1203,6 +1198,33 @@ static int i915_oa_read(struct i915_perf_stream *stream, return dev_priv->perf.oa.ops.read(stream, buf, count, offset); } +static struct intel_context *oa_pin_context(struct drm_i915_private *i915, + struct i915_gem_context *ctx) +{ + struct intel_engine_cs *engine = i915->engine[RCS]; + struct intel_context *ce; + int ret; + + ret = i915_mutex_lock_interruptible(&i915->drm); + if (ret) + return ERR_PTR(ret); + + /* + * As the ID is the gtt offset of the context's vma we + * pin the vma to ensure the ID remains fixed. + * + * NB: implied RCS engine... + */ + ce = intel_context_pin(ctx, engine); + mutex_unlock(&i915->drm.struct_mutex); + if (IS_ERR(ce)) + return ce; + + i915->perf.oa.pinned_ctx = ce; + + return ce; +} + /** * oa_get_render_ctx_id - determine and hold ctx hw id * @stream: An i915-perf stream opened for OA metrics @@ -1215,40 +1237,76 @@ static int i915_oa_read(struct i915_perf_stream *stream, */ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) { - struct drm_i915_private *dev_priv = stream->dev_priv; + struct drm_i915_private *i915 = stream->dev_priv; + struct intel_context *ce; - if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) { - dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id; - } else { - struct intel_engine_cs *engine = dev_priv->engine[RCS]; - struct intel_ring *ring; - int ret; - - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - return ret; + ce = oa_pin_context(i915, stream->ctx); + if (IS_ERR(ce)) + return PTR_ERR(ce); + switch (INTEL_GEN(i915)) { + case 7: { /* - * As the ID is the gtt offset of the context's vma we - * pin the vma to ensure the ID remains fixed. - * - * NB: implied RCS engine... + * On Haswell we don't do any post processing of the reports + * and don't need to use the mask. */ - ring = intel_context_pin(stream->ctx, engine); - mutex_unlock(&dev_priv->drm.struct_mutex); - if (IS_ERR(ring)) - return PTR_ERR(ring); + i915->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state); + i915->perf.oa.specific_ctx_id_mask = 0; + break; + } + case 8: + case 9: + case 10: + if (USES_GUC_SUBMISSION(i915)) { + /* + * When using GuC, the context descriptor we write in + * i915 is read by GuC and rewritten before it's + * actually written into the hardware. The LRCA is + * what is put into the context id field of the + * context descriptor by GuC. Because it's aligned to + * a page, the lower 12bits are always at 0 and + * dropped by GuC. They won't be part of the context + * ID in the OA reports, so squash those lower bits. + */ + i915->perf.oa.specific_ctx_id = + lower_32_bits(ce->lrc_desc) >> 12; - /* - * Explicitly track the ID (instead of calling - * i915_ggtt_offset() on the fly) considering the difference - * with gen8+ and execlists - */ - dev_priv->perf.oa.specific_ctx_id = - i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state); + /* + * GuC uses the top bit to signal proxy submission, so + * ignore that bit. + */ + i915->perf.oa.specific_ctx_id_mask = + (1U << (GEN8_CTX_ID_WIDTH - 1)) - 1; + } else { + i915->perf.oa.specific_ctx_id = stream->ctx->hw_id; + i915->perf.oa.specific_ctx_id_mask = + (1U << GEN8_CTX_ID_WIDTH) - 1; + } + break; + + case 11: { + struct intel_engine_cs *engine = i915->engine[RCS]; + + i915->perf.oa.specific_ctx_id = + stream->ctx->hw_id << (GEN11_SW_CTX_ID_SHIFT - 32) | + engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32) | + engine->class << (GEN11_ENGINE_INSTANCE_SHIFT - 32); + i915->perf.oa.specific_ctx_id_mask = + ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) | + ((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) | + ((1 << GEN11_ENGINE_CLASS_WIDTH) - 1) << (GEN11_ENGINE_CLASS_SHIFT - 32); + break; + } + + default: + MISSING_CASE(INTEL_GEN(i915)); } + DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n", + i915->perf.oa.specific_ctx_id, + i915->perf.oa.specific_ctx_id_mask); + return 0; } @@ -1262,17 +1320,15 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) static void oa_put_render_ctx_id(struct i915_perf_stream *stream) { struct drm_i915_private *dev_priv = stream->dev_priv; + struct intel_context *ce; - if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) { - dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID; - } else { - struct intel_engine_cs *engine = dev_priv->engine[RCS]; + dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID; + dev_priv->perf.oa.specific_ctx_id_mask = 0; + ce = fetch_and_zero(&dev_priv->perf.oa.pinned_ctx); + if (ce) { mutex_lock(&dev_priv->drm.struct_mutex); - - dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID; - intel_context_unpin(stream->ctx, engine); - + intel_context_unpin(ce); mutex_unlock(&dev_priv->drm.struct_mutex); } } diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index dc87797db500..c39541ed2219 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -127,6 +127,7 @@ static void __i915_pmu_maybe_start_timer(struct drm_i915_private *i915) { if (!i915->pmu.timer_enabled && pmu_needs_timer(i915, true)) { i915->pmu.timer_enabled = true; + i915->pmu.timer_last = ktime_get(); hrtimer_start_range_ns(&i915->pmu.timer, ns_to_ktime(PERIOD), 0, HRTIMER_MODE_REL_PINNED); @@ -155,12 +156,13 @@ static bool grab_forcewake(struct drm_i915_private *i915, bool fw) } static void -update_sample(struct i915_pmu_sample *sample, u32 unit, u32 val) +add_sample(struct i915_pmu_sample *sample, u32 val) { - sample->cur += mul_u32_u32(val, unit); + sample->cur += val; } -static void engines_sample(struct drm_i915_private *dev_priv) +static void +engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns) { struct intel_engine_cs *engine; enum intel_engine_id id; @@ -182,8 +184,9 @@ static void engines_sample(struct drm_i915_private *dev_priv) val = !i915_seqno_passed(current_seqno, last_seqno); - update_sample(&engine->pmu.sample[I915_SAMPLE_BUSY], - PERIOD, val); + if (val) + add_sample(&engine->pmu.sample[I915_SAMPLE_BUSY], + period_ns); if (val && (engine->pmu.enable & (BIT(I915_SAMPLE_WAIT) | BIT(I915_SAMPLE_SEMA)))) { @@ -194,11 +197,13 @@ static void engines_sample(struct drm_i915_private *dev_priv) val = 0; } - update_sample(&engine->pmu.sample[I915_SAMPLE_WAIT], - PERIOD, !!(val & RING_WAIT)); + if (val & RING_WAIT) + add_sample(&engine->pmu.sample[I915_SAMPLE_WAIT], + period_ns); - update_sample(&engine->pmu.sample[I915_SAMPLE_SEMA], - PERIOD, !!(val & RING_WAIT_SEMAPHORE)); + if (val & RING_WAIT_SEMAPHORE) + add_sample(&engine->pmu.sample[I915_SAMPLE_SEMA], + period_ns); } if (fw) @@ -207,7 +212,14 @@ static void engines_sample(struct drm_i915_private *dev_priv) intel_runtime_pm_put(dev_priv); } -static void frequency_sample(struct drm_i915_private *dev_priv) +static void +add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul) +{ + sample->cur += mul_u32_u32(val, mul); +} + +static void +frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns) { if (dev_priv->pmu.enable & config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) { @@ -221,15 +233,17 @@ static void frequency_sample(struct drm_i915_private *dev_priv) intel_runtime_pm_put(dev_priv); } - update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT], - 1, intel_gpu_freq(dev_priv, val)); + add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT], + intel_gpu_freq(dev_priv, val), + period_ns / 1000); } if (dev_priv->pmu.enable & config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) { - update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ], 1, - intel_gpu_freq(dev_priv, - dev_priv->gt_pm.rps.cur_freq)); + add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ], + intel_gpu_freq(dev_priv, + dev_priv->gt_pm.rps.cur_freq), + period_ns / 1000); } } @@ -237,14 +251,27 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer) { struct drm_i915_private *i915 = container_of(hrtimer, struct drm_i915_private, pmu.timer); + unsigned int period_ns; + ktime_t now; if (!READ_ONCE(i915->pmu.timer_enabled)) return HRTIMER_NORESTART; - engines_sample(i915); - frequency_sample(i915); + now = ktime_get(); + period_ns = ktime_to_ns(ktime_sub(now, i915->pmu.timer_last)); + i915->pmu.timer_last = now; + + /* + * Strictly speaking the passed in period may not be 100% accurate for + * all internal calculation, since some amount of time can be spent on + * grabbing the forcewake. However the potential error from timer call- + * back delay greatly dominates this so we keep it simple. + */ + engines_sample(i915, period_ns); + frequency_sample(i915, period_ns); + + hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD)); - hrtimer_forward_now(hrtimer, ns_to_ktime(PERIOD)); return HRTIMER_RESTART; } @@ -519,12 +546,12 @@ static u64 __i915_pmu_event_read(struct perf_event *event) case I915_PMU_ACTUAL_FREQUENCY: val = div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_ACT].cur, - FREQUENCY); + USEC_PER_SEC /* to MHz */); break; case I915_PMU_REQUESTED_FREQUENCY: val = div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_REQ].cur, - FREQUENCY); + USEC_PER_SEC /* to MHz */); break; case I915_PMU_INTERRUPTS: val = count_interrupts(i915); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 2ba735299f7c..7f164ca3db12 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -65,6 +65,14 @@ struct i915_pmu { * event types. */ u64 enable; + + /** + * @timer_last: + * + * Timestmap of the previous timer invocation. + */ + ktime_t timer_last; + /** * @enable_count: Reference counts for the enabled events. * diff --git a/drivers/gpu/drm/i915/i915_pvinfo.h b/drivers/gpu/drm/i915/i915_pvinfo.h index 195203f298df..55bde4a02289 100644 --- a/drivers/gpu/drm/i915/i915_pvinfo.h +++ b/drivers/gpu/drm/i915/i915_pvinfo.h @@ -54,6 +54,7 @@ enum vgt_g2v_type { */ #define VGT_CAPS_FULL_48BIT_PPGTT BIT(2) #define VGT_CAPS_HWSP_EMULATION BIT(3) +#define VGT_CAPS_HUGE_GTT BIT(4) struct vgt_if { u64 magic; /* VGT_MAGIC */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f11bb213ec07..f0317bde3aab 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1990,6 +1990,11 @@ enum i915_power_well_id { _ICL_PORT_COMP_DW10_A, \ _ICL_PORT_COMP_DW10_B) +/* ICL PHY DFLEX registers */ +#define PORT_TX_DFLEXDPMLE1 _MMIO(0x1638C0) +#define DFLEXDPMLE1_DPMLETC_MASK(n) (0xf << (4 * (n))) +#define DFLEXDPMLE1_DPMLETC(n, x) ((x) << (4 * (n))) + /* BXT PHY Ref registers */ #define _PORT_REF_DW3_A 0x16218C #define _PORT_REF_DW3_BC 0x6C18C @@ -2306,8 +2311,9 @@ enum i915_power_well_id { #define GAMW_ECO_ENABLE_64K_IPS_FIELD 0xF #define GAMT_CHKN_BIT_REG _MMIO(0x4ab8) -#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1<<28) -#define GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT (1<<24) +#define GAMT_CHKN_DISABLE_L3_COH_PIPE (1 << 31) +#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1 << 28) +#define GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT (1 << 24) #if 0 #define PRB0_TAIL _MMIO(0x2030) @@ -2663,6 +2669,9 @@ enum i915_power_well_id { #define GEN8_4x4_STC_OPTIMIZATION_DISABLE (1<<6) #define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE (1<<1) +#define GEN10_CACHE_MODE_SS _MMIO(0xe420) +#define FLOAT_BLEND_OPTIMIZATION_ENABLE (1 << 4) + #define GEN6_BLITTER_ECOSKPD _MMIO(0x221d0) #define GEN6_BLITTER_LOCK_SHIFT 16 #define GEN6_BLITTER_FBC_NOTIFY (1<<3) @@ -2709,6 +2718,10 @@ enum i915_power_well_id { #define GEN10_F2_SS_DIS_SHIFT 18 #define GEN10_F2_SS_DIS_MASK (0xf << GEN10_F2_SS_DIS_SHIFT) +#define GEN10_MIRROR_FUSE3 _MMIO(0x9118) +#define GEN10_L3BANK_PAIR_COUNT 4 +#define GEN10_L3BANK_MASK 0x0F + #define GEN8_EU_DISABLE0 _MMIO(0x9134) #define GEN8_EU_DIS0_S0_MASK 0xffffff #define GEN8_EU_DIS0_S1_SHIFT 24 @@ -4088,10 +4101,10 @@ enum { #define EDP_Y_COORDINATE_ENABLE (1<<25) /* GLK and CNL+ */ #define EDP_MAX_SU_DISABLE_TIME(t) ((t)<<20) #define EDP_MAX_SU_DISABLE_TIME_MASK (0x1f<<20) -#define EDP_PSR2_TP2_TIME_500 (0<<8) -#define EDP_PSR2_TP2_TIME_100 (1<<8) -#define EDP_PSR2_TP2_TIME_2500 (2<<8) -#define EDP_PSR2_TP2_TIME_50 (3<<8) +#define EDP_PSR2_TP2_TIME_500us (0<<8) +#define EDP_PSR2_TP2_TIME_100us (1<<8) +#define EDP_PSR2_TP2_TIME_2500us (2<<8) +#define EDP_PSR2_TP2_TIME_50us (3<<8) #define EDP_PSR2_TP2_TIME_MASK (3<<8) #define EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4 #define EDP_PSR2_FRAME_BEFORE_SU_MASK (0xf<<4) @@ -4133,11 +4146,12 @@ enum { #define ADPA_DAC_ENABLE (1<<31) #define ADPA_DAC_DISABLE 0 -#define ADPA_PIPE_SELECT_MASK (1<<30) -#define ADPA_PIPE_A_SELECT 0 -#define ADPA_PIPE_B_SELECT (1<<30) -#define ADPA_PIPE_SELECT(pipe) ((pipe) << 30) -/* CPT uses bits 29:30 for pch transcoder select */ +#define ADPA_PIPE_SEL_SHIFT 30 +#define ADPA_PIPE_SEL_MASK (1<<30) +#define ADPA_PIPE_SEL(pipe) ((pipe) << 30) +#define ADPA_PIPE_SEL_SHIFT_CPT 29 +#define ADPA_PIPE_SEL_MASK_CPT (3<<29) +#define ADPA_PIPE_SEL_CPT(pipe) ((pipe) << 29) #define ADPA_CRT_HOTPLUG_MASK 0x03ff0000 /* bit 25-16 */ #define ADPA_CRT_HOTPLUG_MONITOR_NONE (0<<24) #define ADPA_CRT_HOTPLUG_MONITOR_MASK (3<<24) @@ -4296,9 +4310,9 @@ enum { /* Gen 3 SDVO bits: */ #define SDVO_ENABLE (1 << 31) -#define SDVO_PIPE_SEL(pipe) ((pipe) << 30) +#define SDVO_PIPE_SEL_SHIFT 30 #define SDVO_PIPE_SEL_MASK (1 << 30) -#define SDVO_PIPE_B_SELECT (1 << 30) +#define SDVO_PIPE_SEL(pipe) ((pipe) << 30) #define SDVO_STALL_SELECT (1 << 29) #define SDVO_INTERRUPT_ENABLE (1 << 26) /* @@ -4338,12 +4352,14 @@ enum { #define SDVOB_HOTPLUG_ENABLE (1 << 23) /* SDVO only */ /* Gen 6 (CPT) SDVO/HDMI bits: */ -#define SDVO_PIPE_SEL_CPT(pipe) ((pipe) << 29) +#define SDVO_PIPE_SEL_SHIFT_CPT 29 #define SDVO_PIPE_SEL_MASK_CPT (3 << 29) +#define SDVO_PIPE_SEL_CPT(pipe) ((pipe) << 29) /* CHV SDVO/HDMI bits: */ -#define SDVO_PIPE_SEL_CHV(pipe) ((pipe) << 24) +#define SDVO_PIPE_SEL_SHIFT_CHV 24 #define SDVO_PIPE_SEL_MASK_CHV (3 << 24) +#define SDVO_PIPE_SEL_CHV(pipe) ((pipe) << 24) /* DVO port control */ @@ -4354,7 +4370,9 @@ enum { #define _DVOC 0x61160 #define DVOC _MMIO(_DVOC) #define DVO_ENABLE (1 << 31) -#define DVO_PIPE_B_SELECT (1 << 30) +#define DVO_PIPE_SEL_SHIFT 30 +#define DVO_PIPE_SEL_MASK (1 << 30) +#define DVO_PIPE_SEL(pipe) ((pipe) << 30) #define DVO_PIPE_STALL_UNUSED (0 << 28) #define DVO_PIPE_STALL (1 << 28) #define DVO_PIPE_STALL_TV (2 << 28) @@ -4391,9 +4409,12 @@ enum { */ #define LVDS_PORT_EN (1 << 31) /* Selects pipe B for LVDS data. Must be set on pre-965. */ -#define LVDS_PIPEB_SELECT (1 << 30) -#define LVDS_PIPE_MASK (1 << 30) -#define LVDS_PIPE(pipe) ((pipe) << 30) +#define LVDS_PIPE_SEL_SHIFT 30 +#define LVDS_PIPE_SEL_MASK (1 << 30) +#define LVDS_PIPE_SEL(pipe) ((pipe) << 30) +#define LVDS_PIPE_SEL_SHIFT_CPT 29 +#define LVDS_PIPE_SEL_MASK_CPT (3 << 29) +#define LVDS_PIPE_SEL_CPT(pipe) ((pipe) << 29) /* LVDS dithering flag on 965/g4x platform */ #define LVDS_ENABLE_DITHER (1 << 25) /* LVDS sync polarity flags. Set to invert (i.e. negative) */ @@ -4690,7 +4711,9 @@ enum { /* Enables the TV encoder */ # define TV_ENC_ENABLE (1 << 31) /* Sources the TV encoder input from pipe B instead of A. */ -# define TV_ENC_PIPEB_SELECT (1 << 30) +# define TV_ENC_PIPE_SEL_SHIFT 30 +# define TV_ENC_PIPE_SEL_MASK (1 << 30) +# define TV_ENC_PIPE_SEL(pipe) ((pipe) << 30) /* Outputs composite video (DAC A only) */ # define TV_ENC_OUTPUT_COMPOSITE (0 << 28) /* Outputs SVideo video (DAC B/C) */ @@ -5172,10 +5195,15 @@ enum { #define CHV_DP_D _MMIO(VLV_DISPLAY_BASE + 0x64300) #define DP_PORT_EN (1 << 31) -#define DP_PIPEB_SELECT (1 << 30) -#define DP_PIPE_MASK (1 << 30) -#define DP_PIPE_SELECT_CHV(pipe) ((pipe) << 16) -#define DP_PIPE_MASK_CHV (3 << 16) +#define DP_PIPE_SEL_SHIFT 30 +#define DP_PIPE_SEL_MASK (1 << 30) +#define DP_PIPE_SEL(pipe) ((pipe) << 30) +#define DP_PIPE_SEL_SHIFT_IVB 29 +#define DP_PIPE_SEL_MASK_IVB (3 << 29) +#define DP_PIPE_SEL_IVB(pipe) ((pipe) << 29) +#define DP_PIPE_SEL_SHIFT_CHV 16 +#define DP_PIPE_SEL_MASK_CHV (3 << 16) +#define DP_PIPE_SEL_CHV(pipe) ((pipe) << 16) /* Link training mode - select a suitable mode for each stage */ #define DP_LINK_TRAIN_PAT_1 (0 << 28) @@ -5896,7 +5924,6 @@ enum { #define CURSOR_GAMMA_ENABLE 0x40000000 #define CURSOR_STRIDE_SHIFT 28 #define CURSOR_STRIDE(x) ((ffs(x)-9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */ -#define CURSOR_PIPE_CSC_ENABLE (1<<24) #define CURSOR_FORMAT_SHIFT 24 #define CURSOR_FORMAT_MASK (0x07 << CURSOR_FORMAT_SHIFT) #define CURSOR_FORMAT_2C (0x00 << CURSOR_FORMAT_SHIFT) @@ -5905,18 +5932,21 @@ enum { #define CURSOR_FORMAT_ARGB (0x04 << CURSOR_FORMAT_SHIFT) #define CURSOR_FORMAT_XRGB (0x05 << CURSOR_FORMAT_SHIFT) /* New style CUR*CNTR flags */ -#define CURSOR_MODE 0x27 -#define CURSOR_MODE_DISABLE 0x00 -#define CURSOR_MODE_128_32B_AX 0x02 -#define CURSOR_MODE_256_32B_AX 0x03 -#define CURSOR_MODE_64_32B_AX 0x07 -#define CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX) -#define CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX) -#define CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX) +#define MCURSOR_MODE 0x27 +#define MCURSOR_MODE_DISABLE 0x00 +#define MCURSOR_MODE_128_32B_AX 0x02 +#define MCURSOR_MODE_256_32B_AX 0x03 +#define MCURSOR_MODE_64_32B_AX 0x07 +#define MCURSOR_MODE_128_ARGB_AX ((1 << 5) | MCURSOR_MODE_128_32B_AX) +#define MCURSOR_MODE_256_ARGB_AX ((1 << 5) | MCURSOR_MODE_256_32B_AX) +#define MCURSOR_MODE_64_ARGB_AX ((1 << 5) | MCURSOR_MODE_64_32B_AX) +#define MCURSOR_PIPE_SELECT_MASK (0x3 << 28) +#define MCURSOR_PIPE_SELECT_SHIFT 28 #define MCURSOR_PIPE_SELECT(pipe) ((pipe) << 28) #define MCURSOR_GAMMA_ENABLE (1 << 26) -#define CURSOR_ROTATE_180 (1<<15) -#define CURSOR_TRICKLE_FEED_DISABLE (1 << 14) +#define MCURSOR_PIPE_CSC_ENABLE (1<<24) +#define MCURSOR_ROTATE_180 (1<<15) +#define MCURSOR_TRICKLE_FEED_DISABLE (1 << 14) #define _CURABASE 0x70084 #define _CURAPOS 0x70088 #define CURSOR_POS_MASK 0x007FF @@ -6764,6 +6794,10 @@ enum { #define _PS_VPHASE_1B 0x68988 #define _PS_VPHASE_2B 0x68A88 #define _PS_VPHASE_1C 0x69188 +#define PS_Y_PHASE(x) ((x) << 16) +#define PS_UV_RGB_PHASE(x) ((x) << 0) +#define PS_PHASE_MASK (0x7fff << 1) /* u2.13 */ +#define PS_PHASE_TRIP (1 << 0) #define _PS_HPHASE_1A 0x68194 #define _PS_HPHASE_2A 0x68294 @@ -7192,13 +7226,17 @@ enum { /* GEN7 chicken */ #define GEN7_COMMON_SLICE_CHICKEN1 _MMIO(0x7010) -# define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1<<10) | (1<<26)) -# define GEN9_RHWO_OPTIMIZATION_DISABLE (1<<14) -#define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) -# define GEN9_PBE_COMPRESSED_HASH_SELECTION (1<<13) -# define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE (1<<12) -# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8) -# define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1<<0) + #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1 << 10) | (1 << 26)) + #define GEN9_RHWO_OPTIMIZATION_DISABLE (1 << 14) + +#define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) + #define GEN9_PBE_COMPRESSED_HASH_SELECTION (1 << 13) + #define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE (1 << 12) + #define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1 << 8) + #define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1 << 0) + +#define GEN11_COMMON_SLICE_CHICKEN3 _MMIO(0x7304) + #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC (1 << 11) #define HIZ_CHICKEN _MMIO(0x7018) # define CHV_HZ_8X8_MODE_IN_1X (1<<15) @@ -7208,6 +7246,7 @@ enum { #define DISABLE_PIXEL_MASK_CAMMING (1<<14) #define GEN9_SLICE_COMMON_ECO_CHICKEN1 _MMIO(0x731c) +#define GEN11_STATE_CACHE_REDIRECT_TO_CS (1 << 11) #define GEN7_L3SQCREG1 _MMIO(0xB010) #define VLV_B0_WA_L3SQCREG1_VALUE 0x00D30000 @@ -7862,27 +7901,14 @@ enum { #define PCH_DP_AUX_CH_DATA(aux_ch, i) _MMIO(_PORT((aux_ch) - AUX_CH_B, _PCH_DPB_AUX_CH_DATA1, _PCH_DPC_AUX_CH_DATA1) + (i) * 4) /* 5 registers */ /* CPT */ -#define PORT_TRANS_A_SEL_CPT 0 -#define PORT_TRANS_B_SEL_CPT (1<<29) -#define PORT_TRANS_C_SEL_CPT (2<<29) -#define PORT_TRANS_SEL_MASK (3<<29) -#define PORT_TRANS_SEL_CPT(pipe) ((pipe) << 29) -#define PORT_TO_PIPE(val) (((val) & (1<<30)) >> 30) -#define PORT_TO_PIPE_CPT(val) (((val) & PORT_TRANS_SEL_MASK) >> 29) -#define SDVO_PORT_TO_PIPE_CHV(val) (((val) & (3<<24)) >> 24) -#define DP_PORT_TO_PIPE_CHV(val) (((val) & (3<<16)) >> 16) - #define _TRANS_DP_CTL_A 0xe0300 #define _TRANS_DP_CTL_B 0xe1300 #define _TRANS_DP_CTL_C 0xe2300 #define TRANS_DP_CTL(pipe) _MMIO_PIPE(pipe, _TRANS_DP_CTL_A, _TRANS_DP_CTL_B) #define TRANS_DP_OUTPUT_ENABLE (1<<31) -#define TRANS_DP_PORT_SEL_B (0<<29) -#define TRANS_DP_PORT_SEL_C (1<<29) -#define TRANS_DP_PORT_SEL_D (2<<29) -#define TRANS_DP_PORT_SEL_NONE (3<<29) -#define TRANS_DP_PORT_SEL_MASK (3<<29) -#define TRANS_DP_PIPE_TO_PORT(val) ((((val) & TRANS_DP_PORT_SEL_MASK) >> 29) + PORT_B) +#define TRANS_DP_PORT_SEL_MASK (3 << 29) +#define TRANS_DP_PORT_SEL_NONE (3 << 29) +#define TRANS_DP_PORT_SEL(port) (((port) - PORT_B) << 29) #define TRANS_DP_AUDIO_ONLY (1<<26) #define TRANS_DP_ENH_FRAMING (1<<18) #define TRANS_DP_8BPC (0<<9) @@ -8322,8 +8348,9 @@ enum { #define GEN7_ROW_CHICKEN2 _MMIO(0xe4f4) #define GEN7_ROW_CHICKEN2_GT2 _MMIO(0xf4f4) -#define DOP_CLOCK_GATING_DISABLE (1<<0) -#define PUSH_CONSTANT_DEREF_DISABLE (1<<8) +#define DOP_CLOCK_GATING_DISABLE (1 << 0) +#define PUSH_CONSTANT_DEREF_DISABLE (1 << 8) +#define GEN11_TDL_CLOCK_GATING_FIX_DISABLE (1 << 1) #define HSW_ROW_CHICKEN3 _MMIO(0xe49c) #define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6) @@ -9100,13 +9127,16 @@ enum skl_power_gate { #define DPLL_CFGCR1_QDIV_RATIO_MASK (0xff << 10) #define DPLL_CFGCR1_QDIV_RATIO_SHIFT (10) #define DPLL_CFGCR1_QDIV_RATIO(x) ((x) << 10) +#define DPLL_CFGCR1_QDIV_MODE_SHIFT (9) #define DPLL_CFGCR1_QDIV_MODE(x) ((x) << 9) #define DPLL_CFGCR1_KDIV_MASK (7 << 6) +#define DPLL_CFGCR1_KDIV_SHIFT (6) #define DPLL_CFGCR1_KDIV(x) ((x) << 6) #define DPLL_CFGCR1_KDIV_1 (1 << 6) #define DPLL_CFGCR1_KDIV_2 (2 << 6) #define DPLL_CFGCR1_KDIV_4 (4 << 6) #define DPLL_CFGCR1_PDIV_MASK (0xf << 2) +#define DPLL_CFGCR1_PDIV_SHIFT (2) #define DPLL_CFGCR1_PDIV(x) ((x) << 2) #define DPLL_CFGCR1_PDIV_2 (1 << 2) #define DPLL_CFGCR1_PDIV_3 (2 << 2) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 8928894dd9c7..f187250e60c6 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -320,6 +320,7 @@ static void advance_ring(struct i915_request *request) * is just about to be. Either works, if we miss the last two * noops - they are safe to be replayed on a reset. */ + GEM_TRACE("marking %s as inactive\n", ring->timeline->name); tail = READ_ONCE(request->tail); list_del(&ring->active_link); } else { @@ -383,8 +384,8 @@ static void __retire_engine_request(struct intel_engine_cs *engine, * the subsequent request. */ if (engine->last_retired_context) - intel_context_unpin(engine->last_retired_context, engine); - engine->last_retired_context = rq->ctx; + intel_context_unpin(engine->last_retired_context); + engine->last_retired_context = rq->hw_context; } static void __retire_engine_upto(struct intel_engine_cs *engine, @@ -455,8 +456,8 @@ static void i915_request_retire(struct i915_request *request) i915_request_remove_from_client(request); /* Retirement decays the ban score as it is a sign of ctx progress */ - atomic_dec_if_positive(&request->ctx->ban_score); - intel_context_unpin(request->ctx, request->engine); + atomic_dec_if_positive(&request->gem_context->ban_score); + intel_context_unpin(request->hw_context); __retire_engine_upto(request->engine, request); @@ -657,7 +658,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { struct drm_i915_private *i915 = engine->i915; struct i915_request *rq; - struct intel_ring *ring; + struct intel_context *ce; int ret; lockdep_assert_held(&i915->drm.struct_mutex); @@ -681,22 +682,21 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) * GGTT space, so do this first before we reserve a seqno for * ourselves. */ - ring = intel_context_pin(ctx, engine); - if (IS_ERR(ring)) - return ERR_CAST(ring); - GEM_BUG_ON(!ring); + ce = intel_context_pin(ctx, engine); + if (IS_ERR(ce)) + return ERR_CAST(ce); ret = reserve_gt(i915); if (ret) goto err_unpin; - ret = intel_ring_wait_for_space(ring, MIN_SPACE_FOR_ADD_REQUEST); + ret = intel_ring_wait_for_space(ce->ring, MIN_SPACE_FOR_ADD_REQUEST); if (ret) goto err_unreserve; /* Move our oldest request to the slab-cache (if not in use!) */ - rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link); - if (!list_is_last(&rq->ring_link, &ring->request_list) && + rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link); + if (!list_is_last(&rq->ring_link, &ce->ring->request_list) && i915_request_completed(rq)) i915_request_retire(rq); @@ -760,9 +760,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) INIT_LIST_HEAD(&rq->active_list); rq->i915 = i915; rq->engine = engine; - rq->ctx = ctx; - rq->ring = ring; - rq->timeline = ring->timeline; + rq->gem_context = ctx; + rq->hw_context = ce; + rq->ring = ce->ring; + rq->timeline = ce->ring->timeline; GEM_BUG_ON(rq->timeline == &engine->timeline); spin_lock_init(&rq->lock); @@ -814,14 +815,14 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) goto err_unwind; /* Keep a second pin for the dual retirement along engine and ring */ - __intel_context_pin(rq->ctx, engine); + __intel_context_pin(ce); /* Check that we didn't interrupt ourselves with a new request */ GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno); return rq; err_unwind: - rq->ring->emit = rq->head; + ce->ring->emit = rq->head; /* Make sure we didn't add ourselves to external state before freeing */ GEM_BUG_ON(!list_empty(&rq->active_list)); @@ -832,7 +833,7 @@ err_unwind: err_unreserve: unreserve_gt(i915); err_unpin: - intel_context_unpin(ctx, engine); + intel_context_unpin(ce); return ERR_PTR(ret); } @@ -1018,8 +1019,8 @@ i915_request_await_object(struct i915_request *to, void __i915_request_add(struct i915_request *request, bool flush_caches) { struct intel_engine_cs *engine = request->engine; - struct intel_ring *ring = request->ring; struct i915_timeline *timeline = request->timeline; + struct intel_ring *ring = request->ring; struct i915_request *prev; u32 *cs; int err; @@ -1095,8 +1096,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) i915_gem_active_set(&timeline->last_request, request); list_add_tail(&request->ring_link, &ring->request_list); - if (list_is_first(&request->ring_link, &ring->request_list)) + if (list_is_first(&request->ring_link, &ring->request_list)) { + GEM_TRACE("marking %s as active\n", ring->timeline->name); list_add(&ring->active_link, &request->i915->gt.active_rings); + } request->emitted_jiffies = jiffies; /* @@ -1113,7 +1116,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) local_bh_disable(); rcu_read_lock(); /* RCU serialisation for set-wedged protection */ if (engine->schedule) - engine->schedule(request, &request->ctx->sched); + engine->schedule(request, &request->gem_context->sched); rcu_read_unlock(); i915_sw_fence_commit(&request->submit); local_bh_enable(); /* Kick the execlists tasklet if just scheduled */ diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index eddbd4245cb3..491ff81d0fea 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -93,8 +93,9 @@ struct i915_request { * i915_request_free() will then decrement the refcount on the * context. */ - struct i915_gem_context *ctx; + struct i915_gem_context *gem_context; struct intel_engine_cs *engine; + struct intel_context *hw_context; struct intel_ring *ring; struct i915_timeline *timeline; struct intel_signal_node signaling; @@ -266,6 +267,7 @@ long i915_request_wait(struct i915_request *rq, #define I915_WAIT_INTERRUPTIBLE BIT(0) #define I915_WAIT_LOCKED BIT(1) /* struct_mutex held, handle GPU reset */ #define I915_WAIT_ALL BIT(2) /* used by i915_gem_object_wait() */ +#define I915_WAIT_FOR_IDLE_BOOST BIT(3) static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 8cc3a256f29d..1472f48ab2e8 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -591,21 +591,26 @@ TRACE_EVENT(i915_gem_ring_sync_to, TP_STRUCT__entry( __field(u32, dev) - __field(u32, sync_from) - __field(u32, sync_to) + __field(u32, from_class) + __field(u32, from_instance) + __field(u32, to_class) + __field(u32, to_instance) __field(u32, seqno) ), TP_fast_assign( __entry->dev = from->i915->drm.primary->index; - __entry->sync_from = from->engine->id; - __entry->sync_to = to->engine->id; + __entry->from_class = from->engine->uabi_class; + __entry->from_instance = from->engine->instance; + __entry->to_class = to->engine->uabi_class; + __entry->to_instance = to->engine->instance; __entry->seqno = from->global_seqno; ), - TP_printk("dev=%u, sync-from=%u, sync-to=%u, seqno=%u", + TP_printk("dev=%u, sync-from=%u:%u, sync-to=%u:%u, seqno=%u", __entry->dev, - __entry->sync_from, __entry->sync_to, + __entry->from_class, __entry->from_instance, + __entry->to_class, __entry->to_instance, __entry->seqno) ); @@ -616,24 +621,27 @@ TRACE_EVENT(i915_request_queue, TP_STRUCT__entry( __field(u32, dev) __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) + __field(u64, ctx) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(u32, flags) ), TP_fast_assign( __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; + __entry->hw_id = rq->gem_context->hw_id; + __entry->class = rq->engine->uabi_class; + __entry->instance = rq->engine->instance; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->flags = flags; ), - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, flags=0x%x", - __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx, - __entry->seqno, __entry->flags) + TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, flags=0x%x", + __entry->dev, __entry->class, __entry->instance, + __entry->hw_id, __entry->ctx, __entry->seqno, + __entry->flags) ); DECLARE_EVENT_CLASS(i915_request, @@ -643,24 +651,27 @@ DECLARE_EVENT_CLASS(i915_request, TP_STRUCT__entry( __field(u32, dev) __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) + __field(u64, ctx) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(u32, global) ), TP_fast_assign( __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; + __entry->hw_id = rq->gem_context->hw_id; + __entry->class = rq->engine->uabi_class; + __entry->instance = rq->engine->instance; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->global = rq->global_seqno; ), - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u", - __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx, - __entry->seqno, __entry->global) + TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u", + __entry->dev, __entry->class, __entry->instance, + __entry->hw_id, __entry->ctx, __entry->seqno, + __entry->global) ); DEFINE_EVENT(i915_request, i915_request_add, @@ -686,8 +697,9 @@ TRACE_EVENT(i915_request_in, TP_STRUCT__entry( __field(u32, dev) __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) + __field(u64, ctx) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(u32, global_seqno) __field(u32, port) @@ -696,8 +708,9 @@ TRACE_EVENT(i915_request_in, TP_fast_assign( __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; + __entry->hw_id = rq->gem_context->hw_id; + __entry->class = rq->engine->uabi_class; + __entry->instance = rq->engine->instance; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->global_seqno = rq->global_seqno; @@ -705,10 +718,10 @@ TRACE_EVENT(i915_request_in, __entry->port = port; ), - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u", - __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx, - __entry->seqno, __entry->prio, __entry->global_seqno, - __entry->port) + TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, global=%u, port=%u", + __entry->dev, __entry->class, __entry->instance, + __entry->hw_id, __entry->ctx, __entry->seqno, + __entry->prio, __entry->global_seqno, __entry->port) ); TRACE_EVENT(i915_request_out, @@ -718,8 +731,9 @@ TRACE_EVENT(i915_request_out, TP_STRUCT__entry( __field(u32, dev) __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) + __field(u64, ctx) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(u32, global_seqno) __field(u32, completed) @@ -727,17 +741,18 @@ TRACE_EVENT(i915_request_out, TP_fast_assign( __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; + __entry->hw_id = rq->gem_context->hw_id; + __entry->class = rq->engine->uabi_class; + __entry->instance = rq->engine->instance; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->global_seqno = rq->global_seqno; __entry->completed = i915_request_completed(rq); ), - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%u", - __entry->dev, __entry->hw_id, __entry->ring, - __entry->ctx, __entry->seqno, + TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, completed?=%u", + __entry->dev, __entry->class, __entry->instance, + __entry->hw_id, __entry->ctx, __entry->seqno, __entry->global_seqno, __entry->completed) ); @@ -771,21 +786,23 @@ TRACE_EVENT(intel_engine_notify, TP_STRUCT__entry( __field(u32, dev) - __field(u32, ring) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(bool, waiters) ), TP_fast_assign( __entry->dev = engine->i915->drm.primary->index; - __entry->ring = engine->id; + __entry->class = engine->uabi_class; + __entry->instance = engine->instance; __entry->seqno = intel_engine_get_seqno(engine); __entry->waiters = waiters; ), - TP_printk("dev=%u, ring=%u, seqno=%u, waiters=%u", - __entry->dev, __entry->ring, __entry->seqno, - __entry->waiters) + TP_printk("dev=%u, engine=%u:%u, seqno=%u, waiters=%u", + __entry->dev, __entry->class, __entry->instance, + __entry->seqno, __entry->waiters) ); DEFINE_EVENT(i915_request, i915_request_retire, @@ -800,8 +817,9 @@ TRACE_EVENT(i915_request_wait_begin, TP_STRUCT__entry( __field(u32, dev) __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) + __field(u64, ctx) + __field(u16, class) + __field(u16, instance) __field(u32, seqno) __field(u32, global) __field(unsigned int, flags) @@ -815,18 +833,20 @@ TRACE_EVENT(i915_request_wait_begin, */ TP_fast_assign( __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; + __entry->hw_id = rq->gem_context->hw_id; + __entry->class = rq->engine->uabi_class; + __entry->instance = rq->engine->instance; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->global = rq->global_seqno; __entry->flags = flags; ), - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x", - __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx, - __entry->seqno, __entry->global, - !!(__entry->flags & I915_WAIT_LOCKED), __entry->flags) + TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, blocking=%u, flags=0x%x", + __entry->dev, __entry->class, __entry->instance, + __entry->hw_id, __entry->ctx, __entry->seqno, + __entry->global, !!(__entry->flags & I915_WAIT_LOCKED), + __entry->flags) ); DEFINE_EVENT(i915_request, i915_request_wait_end, @@ -936,7 +956,7 @@ DECLARE_EVENT_CLASS(i915_context, __entry->dev = ctx->i915->drm.primary->index; __entry->ctx = ctx; __entry->hw_id = ctx->hw_id; - __entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL; + __entry->vm = ctx->ppgtt ? &ctx->ppgtt->vm : NULL; ), TP_printk("dev=%u, ctx=%p, ctx_vm=%p, hw_id=%u", @@ -966,21 +986,24 @@ TRACE_EVENT(switch_mm, TP_ARGS(engine, to), TP_STRUCT__entry( - __field(u32, ring) + __field(u16, class) + __field(u16, instance) __field(struct i915_gem_context *, to) __field(struct i915_address_space *, vm) __field(u32, dev) ), TP_fast_assign( - __entry->ring = engine->id; + __entry->class = engine->uabi_class; + __entry->instance = engine->instance; __entry->to = to; - __entry->vm = to->ppgtt? &to->ppgtt->base : NULL; + __entry->vm = to->ppgtt ? &to->ppgtt->vm : NULL; __entry->dev = engine->i915->drm.primary->index; ), - TP_printk("dev=%u, ring=%u, ctx=%p, ctx_vm=%p", - __entry->dev, __entry->ring, __entry->to, __entry->vm) + TP_printk("dev=%u, engine=%u:%u, ctx=%p, ctx_vm=%p", + __entry->dev, __entry->class, __entry->instance, __entry->to, + __entry->vm) ); #endif /* _I915_TRACE_H_ */ diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c index 5fe9f3f39467..869cf4a3b6de 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.c +++ b/drivers/gpu/drm/i915/i915_vgpu.c @@ -105,7 +105,7 @@ static void vgt_deballoon_space(struct i915_ggtt *ggtt, node->start + node->size, node->size / 1024); - ggtt->base.reserved -= node->size; + ggtt->vm.reserved -= node->size; drm_mm_remove_node(node); } @@ -141,11 +141,11 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt, DRM_INFO("balloon space: range [ 0x%lx - 0x%lx ] %lu KiB.\n", start, end, size / 1024); - ret = i915_gem_gtt_reserve(&ggtt->base, node, + ret = i915_gem_gtt_reserve(&ggtt->vm, node, size, start, I915_COLOR_UNEVICTABLE, 0); if (!ret) - ggtt->base.reserved += size; + ggtt->vm.reserved += size; return ret; } @@ -197,7 +197,7 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt, int intel_vgt_balloon(struct drm_i915_private *dev_priv) { struct i915_ggtt *ggtt = &dev_priv->ggtt; - unsigned long ggtt_end = ggtt->base.total; + unsigned long ggtt_end = ggtt->vm.total; unsigned long mappable_base, mappable_size, mappable_end; unsigned long unmappable_base, unmappable_size, unmappable_end; diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h index bb8338450dc1..551acc390046 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.h +++ b/drivers/gpu/drm/i915/i915_vgpu.h @@ -36,6 +36,12 @@ intel_vgpu_has_hwsp_emulation(struct drm_i915_private *dev_priv) return dev_priv->vgpu.caps & VGT_CAPS_HWSP_EMULATION; } +static inline bool +intel_vgpu_has_huge_gtt(struct drm_i915_private *dev_priv) +{ + return dev_priv->vgpu.caps & VGT_CAPS_HUGE_GTT; +} + int intel_vgt_balloon(struct drm_i915_private *dev_priv); void intel_vgt_deballoon(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 9324d476e0a7..912f16ffe7ee 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -85,7 +85,7 @@ vma_create(struct drm_i915_gem_object *obj, int i; /* The aliasing_ppgtt should never be used directly! */ - GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base); + GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm); vma = kmem_cache_zalloc(vm->i915->vmas, GFP_KERNEL); if (vma == NULL) @@ -459,6 +459,18 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level) return true; } +static void assert_bind_count(const struct drm_i915_gem_object *obj) +{ + /* + * Combine the assertion that the object is bound and that we have + * pinned its pages. But we should never have bound the object + * more than we have pinned its pages. (For complete accuracy, we + * assume that no else is pinning the pages, but as a rough assertion + * that we will not run into problems later, this will do!) + */ + GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count); +} + /** * i915_vma_insert - finds a slot for the vma in its address space * @vma: the vma @@ -595,7 +607,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) obj->bind_count++; spin_unlock(&dev_priv->mm.obj_lock); - GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count); + assert_bind_count(obj); return 0; @@ -633,7 +645,7 @@ i915_vma_remove(struct i915_vma *vma) * reaped by the shrinker. */ i915_gem_object_unpin_pages(obj); - GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count); + assert_bind_count(obj); } int __i915_vma_do_pin(struct i915_vma *vma, diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 54270bdde100..465dff4780fe 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -267,8 +267,6 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, if (!lvds_lfp_data_ptrs) return; - dev_priv->vbt.lvds_vbt = 1; - panel_dvo_timing = get_lvds_dvo_timing(lvds_lfp_data, lvds_lfp_data_ptrs, panel_type); @@ -518,8 +516,31 @@ parse_driver_features(struct drm_i915_private *dev_priv, if (!driver) return; - if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP) - dev_priv->vbt.edp.support = 1; + if (INTEL_GEN(dev_priv) >= 5) { + /* + * Note that we consider BDB_DRIVER_FEATURE_INT_SDVO_LVDS + * to mean "eDP". The VBT spec doesn't agree with that + * interpretation, but real world VBTs seem to. + */ + if (driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS) + dev_priv->vbt.int_lvds_support = 0; + } else { + /* + * FIXME it's not clear which BDB version has the LVDS config + * bits defined. Revision history in the VBT spec says: + * "0.92 | Add two definitions for VBT value of LVDS Active + * Config (00b and 11b values defined) | 06/13/2005" + * but does not the specify the BDB version. + * + * So far version 134 (on i945gm) is the oldest VBT observed + * in the wild with the bits correctly populated. Version + * 108 (on i85x) does not have the bits correctly populated. + */ + if (bdb->version >= 134 && + driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS && + driver->lvds_config != BDB_DRIVER_FEATURE_INT_SDVO_LVDS) + dev_priv->vbt.int_lvds_support = 0; + } DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled); /* @@ -542,11 +563,8 @@ parse_edp(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) int panel_type = dev_priv->vbt.panel_type; edp = find_section(bdb, BDB_EDP); - if (!edp) { - if (dev_priv->vbt.edp.support) - DRM_DEBUG_KMS("No eDP BDB found but eDP panel supported.\n"); + if (!edp) return; - } switch ((edp->color_depth >> (panel_type * 2)) & 3) { case EDP_18BPP: @@ -688,8 +706,52 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) break; } - dev_priv->vbt.psr.tp1_wakeup_time = psr_table->tp1_wakeup_time; - dev_priv->vbt.psr.tp2_tp3_wakeup_time = psr_table->tp2_tp3_wakeup_time; + /* + * New psr options 0=500us, 1=100us, 2=2500us, 3=0us + * Old decimal value is wake up time in multiples of 100 us. + */ + if (bdb->version >= 209 && IS_GEN9_BC(dev_priv)) { + switch (psr_table->tp1_wakeup_time) { + case 0: + dev_priv->vbt.psr.tp1_wakeup_time_us = 500; + break; + case 1: + dev_priv->vbt.psr.tp1_wakeup_time_us = 100; + break; + case 3: + dev_priv->vbt.psr.tp1_wakeup_time_us = 0; + break; + default: + DRM_DEBUG_KMS("VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", + psr_table->tp1_wakeup_time); + /* fallthrough */ + case 2: + dev_priv->vbt.psr.tp1_wakeup_time_us = 2500; + break; + } + + switch (psr_table->tp2_tp3_wakeup_time) { + case 0: + dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 500; + break; + case 1: + dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 100; + break; + case 3: + dev_priv->vbt.psr.tp1_wakeup_time_us = 0; + break; + default: + DRM_DEBUG_KMS("VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n", + psr_table->tp2_tp3_wakeup_time); + /* fallthrough */ + case 2: + dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500; + break; + } + } else { + dev_priv->vbt.psr.tp1_wakeup_time_us = psr_table->tp1_wakeup_time * 100; + dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = psr_table->tp2_tp3_wakeup_time * 100; + } } static void parse_dsi_backlight_ports(struct drm_i915_private *dev_priv, @@ -1197,18 +1259,37 @@ static const u8 cnp_ddc_pin_map[] = { [DDC_BUS_DDI_F] = GMBUS_PIN_3_BXT, /* sic */ }; +static const u8 icp_ddc_pin_map[] = { + [ICL_DDC_BUS_DDI_A] = GMBUS_PIN_1_BXT, + [ICL_DDC_BUS_DDI_B] = GMBUS_PIN_2_BXT, + [ICL_DDC_BUS_PORT_1] = GMBUS_PIN_9_TC1_ICP, + [ICL_DDC_BUS_PORT_2] = GMBUS_PIN_10_TC2_ICP, + [ICL_DDC_BUS_PORT_3] = GMBUS_PIN_11_TC3_ICP, + [ICL_DDC_BUS_PORT_4] = GMBUS_PIN_12_TC4_ICP, +}; + static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin) { - if (HAS_PCH_CNP(dev_priv)) { - if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) { - return cnp_ddc_pin_map[vbt_pin]; - } else { - DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin); - return 0; - } + const u8 *ddc_pin_map; + int n_entries; + + if (HAS_PCH_ICP(dev_priv)) { + ddc_pin_map = icp_ddc_pin_map; + n_entries = ARRAY_SIZE(icp_ddc_pin_map); + } else if (HAS_PCH_CNP(dev_priv)) { + ddc_pin_map = cnp_ddc_pin_map; + n_entries = ARRAY_SIZE(cnp_ddc_pin_map); + } else { + /* Assuming direct map */ + return vbt_pin; } - return vbt_pin; + if (vbt_pin < n_entries && ddc_pin_map[vbt_pin] != 0) + return ddc_pin_map[vbt_pin]; + + DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", + vbt_pin); + return 0; } static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, @@ -1504,7 +1585,6 @@ init_vbt_defaults(struct drm_i915_private *dev_priv) /* LFP panel data */ dev_priv->vbt.lvds_dither = 1; - dev_priv->vbt.lvds_vbt = 0; /* SDVO panel data */ dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; @@ -1513,6 +1593,9 @@ init_vbt_defaults(struct drm_i915_private *dev_priv) dev_priv->vbt.int_tv_support = 1; dev_priv->vbt.int_crt_support = 1; + /* driver features */ + dev_priv->vbt.int_lvds_support = 1; + /* Default to using SSC */ dev_priv->vbt.lvds_use_ssc = 1; /* diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 18e643df523e..86a987b8ac66 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -846,8 +846,9 @@ static void cancel_fake_irq(struct intel_engine_cs *engine) void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine) { struct intel_breadcrumbs *b = &engine->breadcrumbs; + unsigned long flags; - spin_lock_irq(&b->irq_lock); + spin_lock_irqsave(&b->irq_lock, flags); /* * Leave the fake_irq timer enabled (if it is running), but clear the @@ -871,7 +872,7 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine) */ clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); - spin_unlock_irq(&b->irq_lock); + spin_unlock_irqrestore(&b->irq_lock, flags); } void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index de0e22322c76..211d601cd1b1 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -63,33 +63,35 @@ static struct intel_crt *intel_attached_crt(struct drm_connector *connector) return intel_encoder_to_crt(intel_attached_encoder(connector)); } +bool intel_crt_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t adpa_reg, enum pipe *pipe) +{ + u32 val; + + val = I915_READ(adpa_reg); + + /* asserts want to know the pipe even if the port is disabled */ + if (HAS_PCH_CPT(dev_priv)) + *pipe = (val & ADPA_PIPE_SEL_MASK_CPT) >> ADPA_PIPE_SEL_SHIFT_CPT; + else + *pipe = (val & ADPA_PIPE_SEL_MASK) >> ADPA_PIPE_SEL_SHIFT; + + return val & ADPA_DAC_ENABLE; +} + static bool intel_crt_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_crt *crt = intel_encoder_to_crt(encoder); - u32 tmp; bool ret; if (!intel_display_power_get_if_enabled(dev_priv, encoder->power_domain)) return false; - ret = false; - - tmp = I915_READ(crt->adpa_reg); - - if (!(tmp & ADPA_DAC_ENABLE)) - goto out; + ret = intel_crt_port_enabled(dev_priv, crt->adpa_reg, pipe); - if (HAS_PCH_CPT(dev_priv)) - *pipe = PORT_TO_PIPE_CPT(tmp); - else - *pipe = PORT_TO_PIPE(tmp); - - ret = true; -out: intel_display_power_put(dev_priv, encoder->power_domain); return ret; @@ -168,11 +170,9 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, if (HAS_PCH_LPT(dev_priv)) ; /* Those bits don't exist here */ else if (HAS_PCH_CPT(dev_priv)) - adpa |= PORT_TRANS_SEL_CPT(crtc->pipe); - else if (crtc->pipe == 0) - adpa |= ADPA_PIPE_A_SELECT; + adpa |= ADPA_PIPE_SEL_CPT(crtc->pipe); else - adpa |= ADPA_PIPE_B_SELECT; + adpa |= ADPA_PIPE_SEL(crtc->pipe); if (!HAS_PCH_SPLIT(dev_priv)) I915_WRITE(BCLRPAT(crtc->pipe), 0); diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f4a8598a2d39..b344e0fe08fd 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1243,35 +1243,6 @@ intel_ddi_get_crtc_encoder(struct intel_crtc *crtc) return ret; } -/* Finds the only possible encoder associated with the given CRTC. */ -struct intel_encoder * -intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - struct intel_encoder *ret = NULL; - struct drm_atomic_state *state; - struct drm_connector *connector; - struct drm_connector_state *connector_state; - int num_encoders = 0; - int i; - - state = crtc_state->base.state; - - for_each_new_connector_in_state(state, connector, connector_state, i) { - if (connector_state->crtc != crtc_state->base.crtc) - continue; - - ret = to_intel_encoder(connector_state->best_encoder); - num_encoders++; - } - - WARN(num_encoders != 1, "%d encoders on crtc for pipe %c\n", num_encoders, - pipe_name(crtc->pipe)); - - BUG_ON(ret == NULL); - return ret; -} - #define LC_FREQ 2700 static int hsw_ddi_calc_wrpll_link(struct drm_i915_private *dev_priv, @@ -1374,8 +1345,13 @@ static int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv, uint32_t cfgcr0, cfgcr1; uint32_t p0, p1, p2, dco_freq, ref_clock; - cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id)); - cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id)); + if (INTEL_GEN(dev_priv) >= 11) { + cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id)); + cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id)); + } else { + cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id)); + cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id)); + } p0 = cfgcr1 & DPLL_CFGCR1_PDIV_MASK; p2 = cfgcr1 & DPLL_CFGCR1_KDIV_MASK; @@ -1451,6 +1427,30 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config) pipe_config->base.adjusted_mode.crtc_clock = dotclock; } +static void icl_ddi_clock_get(struct intel_encoder *encoder, + struct intel_crtc_state *pipe_config) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum port port = encoder->port; + int link_clock = 0; + uint32_t pll_id; + + pll_id = intel_get_shared_dpll_id(dev_priv, pipe_config->shared_dpll); + if (port == PORT_A || port == PORT_B) { + if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI)) + link_clock = cnl_calc_wrpll_link(dev_priv, pll_id); + else + link_clock = icl_calc_dp_combo_pll_link(dev_priv, + pll_id); + } else { + /* FIXME - Add for MG PLL */ + WARN(1, "MG PLL clock_get code not implemented yet\n"); + } + + pipe_config->port_clock = link_clock; + ddi_dotclock_get(pipe_config); +} + static void cnl_ddi_clock_get(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -1644,6 +1644,8 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder, bxt_ddi_clock_get(encoder, pipe_config); else if (IS_CANNONLAKE(dev_priv)) cnl_ddi_clock_get(encoder, pipe_config); + else if (IS_ICELAKE(dev_priv)) + icl_ddi_clock_get(encoder, pipe_config); } void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state) @@ -2115,6 +2117,26 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) DP_TRAIN_VOLTAGE_SWING_MASK; } +/* + * We assume that the full set of pre-emphasis values can be + * used on all DDI platforms. Should that change we need to + * rethink this code. + */ +u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder, u8 voltage_swing) +{ + switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_LEVEL_0: + return DP_TRAIN_PRE_EMPH_LEVEL_3; + case DP_TRAIN_VOLTAGE_SWING_LEVEL_1: + return DP_TRAIN_PRE_EMPH_LEVEL_2; + case DP_TRAIN_VOLTAGE_SWING_LEVEL_2: + return DP_TRAIN_PRE_EMPH_LEVEL_1; + case DP_TRAIN_VOLTAGE_SWING_LEVEL_3: + default: + return DP_TRAIN_PRE_EMPH_LEVEL_0; + } +} + static void cnl_ddi_vswing_program(struct intel_encoder *encoder, int level, enum intel_output_type type) { diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index dee3a8e659f1..17c590b42fd7 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1202,7 +1202,7 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe) { i915_reg_t pp_reg; u32 val; - enum pipe panel_pipe = PIPE_A; + enum pipe panel_pipe = INVALID_PIPE; bool locked = true; if (WARN_ON(HAS_DDI(dev_priv))) @@ -1214,18 +1214,35 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe) pp_reg = PP_CONTROL(0); port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; - if (port_sel == PANEL_PORT_SELECT_LVDS && - I915_READ(PCH_LVDS) & LVDS_PIPEB_SELECT) - panel_pipe = PIPE_B; - /* XXX: else fix for eDP */ + switch (port_sel) { + case PANEL_PORT_SELECT_LVDS: + intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPA: + intel_dp_port_enabled(dev_priv, DP_A, PORT_A, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPC: + intel_dp_port_enabled(dev_priv, PCH_DP_C, PORT_C, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPD: + intel_dp_port_enabled(dev_priv, PCH_DP_D, PORT_D, &panel_pipe); + break; + default: + MISSING_CASE(port_sel); + break; + } } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { /* presumably write lock depends on pipe, not port select */ pp_reg = PP_CONTROL(pipe); panel_pipe = pipe; } else { + u32 port_sel; + pp_reg = PP_CONTROL(0); - if (I915_READ(LVDS) & LVDS_PIPEB_SELECT) - panel_pipe = PIPE_B; + port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; + + WARN_ON(port_sel != PANEL_PORT_SELECT_LVDS); + intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe); } val = I915_READ(pp_reg); @@ -1267,7 +1284,10 @@ void assert_pipe(struct drm_i915_private *dev_priv, static void assert_plane(struct intel_plane *plane, bool state) { - bool cur_state = plane->get_hw_state(plane); + enum pipe pipe; + bool cur_state; + + cur_state = plane->get_hw_state(plane, &pipe); I915_STATE_WARN(cur_state != state, "%s assertion failure (expected %s, current %s)\n", @@ -1305,125 +1325,64 @@ void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv, pipe_name(pipe)); } -static bool dp_pipe_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe, u32 port_sel, u32 val) +static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe, enum port port, + i915_reg_t dp_reg) { - if ((val & DP_PORT_EN) == 0) - return false; + enum pipe port_pipe; + bool state; - if (HAS_PCH_CPT(dev_priv)) { - u32 trans_dp_ctl = I915_READ(TRANS_DP_CTL(pipe)); - if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel) - return false; - } else if (IS_CHERRYVIEW(dev_priv)) { - if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe)) - return false; - } else { - if ((val & DP_PIPE_MASK) != (pipe << 30)) - return false; - } - return true; -} + state = intel_dp_port_enabled(dev_priv, dp_reg, port, &port_pipe); -static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe, u32 val) -{ - if ((val & SDVO_ENABLE) == 0) - return false; + I915_STATE_WARN(state && port_pipe == pipe, + "PCH DP %c enabled on transcoder %c, should be disabled\n", + port_name(port), pipe_name(pipe)); - if (HAS_PCH_CPT(dev_priv)) { - if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe)) - return false; - } else if (IS_CHERRYVIEW(dev_priv)) { - if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe)) - return false; - } else { - if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe)) - return false; - } - return true; + I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, + "IBX PCH DP %c still using transcoder B\n", + port_name(port)); } -static bool lvds_pipe_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe, u32 val) -{ - if ((val & LVDS_PORT_EN) == 0) - return false; - - if (HAS_PCH_CPT(dev_priv)) { - if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe)) - return false; - } else { - if ((val & LVDS_PIPE_MASK) != LVDS_PIPE(pipe)) - return false; - } - return true; -} - -static bool adpa_pipe_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe, u32 val) -{ - if ((val & ADPA_DAC_ENABLE) == 0) - return false; - if (HAS_PCH_CPT(dev_priv)) { - if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe)) - return false; - } else { - if ((val & ADPA_PIPE_SELECT_MASK) != ADPA_PIPE_SELECT(pipe)) - return false; - } - return true; -} - -static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe, i915_reg_t reg, - u32 port_sel) +static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, + enum pipe pipe, enum port port, + i915_reg_t hdmi_reg) { - u32 val = I915_READ(reg); - I915_STATE_WARN(dp_pipe_enabled(dev_priv, pipe, port_sel, val), - "PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n", - i915_mmio_reg_offset(reg), pipe_name(pipe)); + enum pipe port_pipe; + bool state; - I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & DP_PORT_EN) == 0 - && (val & DP_PIPEB_SELECT), - "IBX PCH dp port still using transcoder B\n"); -} + state = intel_sdvo_port_enabled(dev_priv, hdmi_reg, &port_pipe); -static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe, i915_reg_t reg) -{ - u32 val = I915_READ(reg); - I915_STATE_WARN(hdmi_pipe_enabled(dev_priv, pipe, val), - "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n", - i915_mmio_reg_offset(reg), pipe_name(pipe)); + I915_STATE_WARN(state && port_pipe == pipe, + "PCH HDMI %c enabled on transcoder %c, should be disabled\n", + port_name(port), pipe_name(pipe)); - I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & SDVO_ENABLE) == 0 - && (val & SDVO_PIPE_B_SELECT), - "IBX PCH hdmi port still using transcoder B\n"); + I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B, + "IBX PCH HDMI %c still using transcoder B\n", + port_name(port)); } static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, enum pipe pipe) { - u32 val; + enum pipe port_pipe; - assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B); - assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C); - assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL_D); + assert_pch_dp_disabled(dev_priv, pipe, PORT_B, PCH_DP_B); + assert_pch_dp_disabled(dev_priv, pipe, PORT_C, PCH_DP_C); + assert_pch_dp_disabled(dev_priv, pipe, PORT_D, PCH_DP_D); - val = I915_READ(PCH_ADPA); - I915_STATE_WARN(adpa_pipe_enabled(dev_priv, pipe, val), - "PCH VGA enabled on transcoder %c, should be disabled\n", - pipe_name(pipe)); + I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) && + port_pipe == pipe, + "PCH VGA enabled on transcoder %c, should be disabled\n", + pipe_name(pipe)); - val = I915_READ(PCH_LVDS); - I915_STATE_WARN(lvds_pipe_enabled(dev_priv, pipe, val), - "PCH LVDS enabled on transcoder %c, should be disabled\n", - pipe_name(pipe)); + I915_STATE_WARN(intel_lvds_port_enabled(dev_priv, PCH_LVDS, &port_pipe) && + port_pipe == pipe, + "PCH LVDS enabled on transcoder %c, should be disabled\n", + pipe_name(pipe)); - assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIB); - assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIC); - assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID); + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_B, PCH_HDMIB); + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_C, PCH_HDMIC); + assert_pch_hdmi_disabled(dev_priv, pipe, PORT_D, PCH_HDMID); } static void _vlv_enable_pll(struct intel_crtc *crtc, @@ -2521,6 +2480,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, { struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct intel_rotation_info *rot_info = &intel_fb->rot_info; + struct drm_i915_gem_object *obj = intel_fb_obj(fb); u32 gtt_offset_rotated = 0; unsigned int max_size = 0; int i, num_planes = fb->format->num_planes; @@ -2585,7 +2545,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * fb layout agrees with the fence layout. We already check that the * fb stride matches the fence stride elsewhere. */ - if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) && + if (i == 0 && i915_gem_object_is_tiled(obj) && (x + width) * cpp > fb->pitches[i]) { DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n", i, fb->offsets[i]); @@ -2670,9 +2630,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, max_size = max(max_size, offset + size); } - if (max_size * tile_size > intel_fb->obj->base.size) { + if (max_size * tile_size > obj->base.size) { DRM_DEBUG_KMS("fb too big for bo (need %u bytes, have %zu bytes)\n", - max_size * tile_size, intel_fb->obj->base.size); + max_size * tile_size, obj->base.size); return -EINVAL; } @@ -3430,24 +3390,33 @@ static void i9xx_disable_plane(struct intel_plane *plane, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static bool i9xx_plane_get_hw_state(struct intel_plane *plane) +static bool i9xx_plane_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; - enum pipe pipe = plane->pipe; bool ret; + u32 val; /* * Not 100% correct for planes that can move between pipes, * but that's only the case for gen2-4 which don't have any * display power wells. */ - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(DSPCNTR(i9xx_plane)) & DISPLAY_PLANE_ENABLE; + val = I915_READ(DSPCNTR(i9xx_plane)); + + ret = val & DISPLAY_PLANE_ENABLE; + + if (INTEL_GEN(dev_priv) >= 5) + *pipe = plane->pipe; + else + *pipe = (val & DISPPLANE_SEL_PIPE_MASK) >> + DISPPLANE_SEL_PIPE_SHIFT; intel_display_power_put(dev_priv, power_domain); @@ -4631,20 +4600,33 @@ static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc) } } -/* Return which DP Port should be selected for Transcoder DP control */ -static enum port -intel_trans_dp_port_sel(struct intel_crtc *crtc) +/* + * Finds the encoder associated with the given CRTC. This can only be + * used when we know that the CRTC isn't feeding multiple encoders! + */ +static struct intel_encoder * +intel_get_crtc_new_encoder(const struct intel_atomic_state *state, + const struct intel_crtc_state *crtc_state) { - struct drm_device *dev = crtc->base.dev; - struct intel_encoder *encoder; + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + const struct drm_connector_state *connector_state; + const struct drm_connector *connector; + struct intel_encoder *encoder = NULL; + int num_encoders = 0; + int i; + + for_each_new_connector_in_state(&state->base, connector, connector_state, i) { + if (connector_state->crtc != &crtc->base) + continue; - for_each_encoder_on_crtc(dev, &crtc->base, encoder) { - if (encoder->type == INTEL_OUTPUT_DP || - encoder->type == INTEL_OUTPUT_EDP) - return encoder->port; + encoder = to_intel_encoder(connector_state->best_encoder); + num_encoders++; } - return -1; + WARN(num_encoders != 1, "%d encoders for pipe %c\n", + num_encoders, pipe_name(crtc->pipe)); + + return encoder; } /* @@ -4655,7 +4637,8 @@ intel_trans_dp_port_sel(struct intel_crtc *crtc) * - DP transcoding bits * - transcoder */ -static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state) +static void ironlake_pch_enable(const struct intel_atomic_state *state, + const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); struct drm_device *dev = crtc->base.dev; @@ -4714,6 +4697,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state) &crtc_state->base.adjusted_mode; u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5; i915_reg_t reg = TRANS_DP_CTL(pipe); + enum port port; + temp = I915_READ(reg); temp &= ~(TRANS_DP_PORT_SEL_MASK | TRANS_DP_SYNC_MASK | @@ -4726,19 +4711,9 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state) if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) temp |= TRANS_DP_VSYNC_ACTIVE_HIGH; - switch (intel_trans_dp_port_sel(crtc)) { - case PORT_B: - temp |= TRANS_DP_PORT_SEL_B; - break; - case PORT_C: - temp |= TRANS_DP_PORT_SEL_C; - break; - case PORT_D: - temp |= TRANS_DP_PORT_SEL_D; - break; - default: - BUG(); - } + port = intel_get_crtc_new_encoder(state, crtc_state)->port; + WARN_ON(port < PORT_B || port > PORT_D); + temp |= TRANS_DP_PORT_SEL(port); I915_WRITE(reg, temp); } @@ -4746,7 +4721,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state) ironlake_enable_pch_transcoder(dev_priv, pipe); } -static void lpt_pch_enable(const struct intel_crtc_state *crtc_state) +static void lpt_pch_enable(const struct intel_atomic_state *state, + const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -4776,6 +4752,39 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe) } } +/* + * The hardware phase 0.0 refers to the center of the pixel. + * We want to start from the top/left edge which is phase + * -0.5. That matches how the hardware calculates the scaling + * factors (from top-left of the first pixel to bottom-right + * of the last pixel, as opposed to the pixel centers). + * + * For 4:2:0 subsampled chroma planes we obviously have to + * adjust that so that the chroma sample position lands in + * the right spot. + * + * Note that for packed YCbCr 4:2:2 formats there is no way to + * control chroma siting. The hardware simply replicates the + * chroma samples for both of the luma samples, and thus we don't + * actually get the expected MPEG2 chroma siting convention :( + * The same behaviour is observed on pre-SKL platforms as well. + */ +u16 skl_scaler_calc_phase(int sub, bool chroma_cosited) +{ + int phase = -0x8000; + u16 trip = 0; + + if (chroma_cosited) + phase += (sub - 1) * 0x8000 / sub; + + if (phase < 0) + phase = 0x10000 + phase; + else + trip = PS_PHASE_TRIP; + + return ((phase >> 2) & PS_PHASE_MASK) | trip; +} + static int skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, unsigned int scaler_user, int *scaler_id, @@ -4975,14 +4984,22 @@ static void skylake_pfit_enable(struct intel_crtc *crtc) &crtc->config->scaler_state; if (crtc->config->pch_pfit.enabled) { + u16 uv_rgb_hphase, uv_rgb_vphase; int id; if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) return; + uv_rgb_hphase = skl_scaler_calc_phase(1, false); + uv_rgb_vphase = skl_scaler_calc_phase(1, false); + id = scaler_state->scaler_id; I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN | PS_FILTER_MEDIUM | scaler_state->scalers[id].mode); + I915_WRITE_FW(SKL_PS_VPHASE(pipe, id), + PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase)); + I915_WRITE_FW(SKL_PS_HPHASE(pipe, id), + PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase)); I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos); I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size); } @@ -5501,10 +5518,8 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config, * * Spurious PCH underruns also occur during PCH enabling. */ - if (intel_crtc->config->has_pch_encoder || IS_GEN5(dev_priv)) - intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); - if (intel_crtc->config->has_pch_encoder) - intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false); + intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); + intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false); if (intel_crtc->config->has_pch_encoder) intel_prepare_shared_dpll(intel_crtc); @@ -5549,7 +5564,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config, intel_enable_pipe(pipe_config); if (intel_crtc->config->has_pch_encoder) - ironlake_pch_enable(pipe_config); + ironlake_pch_enable(old_intel_state, pipe_config); assert_vblank_disabled(crtc); drm_crtc_vblank_on(crtc); @@ -5559,9 +5574,16 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config, if (HAS_PCH_CPT(dev_priv)) cpt_verify_modeset(dev, intel_crtc->pipe); - /* Must wait for vblank to avoid spurious PCH FIFO underruns */ - if (intel_crtc->config->has_pch_encoder) + /* + * Must wait for vblank to avoid spurious PCH FIFO underruns. + * And a second vblank wait is needed at least on ILK with + * some interlaced HDMI modes. Let's do the double wait always + * in case there are more corner cases we don't know about. + */ + if (intel_crtc->config->has_pch_encoder) { + intel_wait_for_vblank(dev_priv, pipe); intel_wait_for_vblank(dev_priv, pipe); + } intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true); } @@ -5623,6 +5645,11 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, if (INTEL_GEN(dev_priv) >= 11) icl_map_plls_to_ports(crtc, pipe_config, old_state); + intel_encoders_pre_enable(crtc, pipe_config, old_state); + + if (!transcoder_is_dsi(cpu_transcoder)) + intel_ddi_enable_pipe_clock(pipe_config); + if (intel_crtc_has_dp_encoder(intel_crtc->config)) intel_dp_set_m_n(intel_crtc, M1_N1); @@ -5651,11 +5678,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, intel_crtc->active = true; - intel_encoders_pre_enable(crtc, pipe_config, old_state); - - if (!transcoder_is_dsi(cpu_transcoder)) - intel_ddi_enable_pipe_clock(pipe_config); - /* Display WA #1180: WaDisableScalarClockGating: glk, cnl */ psl_clkgate_wa = (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) && intel_crtc->config->pch_pfit.enabled; @@ -5688,7 +5710,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, intel_enable_pipe(pipe_config); if (intel_crtc->config->has_pch_encoder) - lpt_pch_enable(pipe_config); + lpt_pch_enable(old_intel_state, pipe_config); if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DP_MST)) intel_ddi_set_vc_payload_alloc(pipe_config, true); @@ -5741,10 +5763,8 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state, * pipe is already disabled, but FDI RX/TX is still enabled. * Happens at least with VGA+HDMI cloning. Suppress them. */ - if (intel_crtc->config->has_pch_encoder) { - intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); - intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false); - } + intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); + intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false); intel_encoders_disable(crtc, old_crtc_state, old_state); @@ -5849,6 +5869,22 @@ static void i9xx_pfit_enable(struct intel_crtc *crtc) I915_WRITE(BCLRPAT(crtc->pipe), 0); } +bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port) +{ + if (IS_ICELAKE(dev_priv)) + return port >= PORT_C && port <= PORT_F; + + return false; +} + +enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, enum port port) +{ + if (!intel_port_is_tc(dev_priv, port)) + return PORT_TC_NONE; + + return port - PORT_C; +} + enum intel_display_power_domain intel_port_to_power_domain(enum port port) { switch (port) { @@ -7675,16 +7711,18 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, struct drm_i915_private *dev_priv = to_i915(dev); struct intel_plane *plane = to_intel_plane(crtc->base.primary); enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; - enum pipe pipe = crtc->pipe; + enum pipe pipe; u32 val, base, offset; int fourcc, pixel_format; unsigned int aligned_height; struct drm_framebuffer *fb; struct intel_framebuffer *intel_fb; - if (!plane->get_hw_state(plane)) + if (!plane->get_hw_state(plane, &pipe)) return; + WARN_ON(pipe != crtc->pipe); + intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL); if (!intel_fb) { DRM_DEBUG_KMS("failed to alloc fb\n"); @@ -8705,16 +8743,18 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, struct drm_i915_private *dev_priv = to_i915(dev); struct intel_plane *plane = to_intel_plane(crtc->base.primary); enum plane_id plane_id = plane->id; - enum pipe pipe = crtc->pipe; + enum pipe pipe; u32 val, base, offset, stride_mult, tiling, alpha; int fourcc, pixel_format; unsigned int aligned_height; struct drm_framebuffer *fb; struct intel_framebuffer *intel_fb; - if (!plane->get_hw_state(plane)) + if (!plane->get_hw_state(plane, &pipe)) return; + WARN_ON(pipe != crtc->pipe); + intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL); if (!intel_fb) { DRM_DEBUG_KMS("failed to alloc fb\n"); @@ -9142,9 +9182,12 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) static int haswell_crtc_compute_clock(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state) { + struct intel_atomic_state *state = + to_intel_atomic_state(crtc_state->base.state); + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) { struct intel_encoder *encoder = - intel_ddi_get_crtc_new_encoder(crtc_state); + intel_get_crtc_new_encoder(state, crtc_state); if (!intel_get_shared_dpll(crtc, crtc_state, encoder)) { DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n", @@ -9692,7 +9735,8 @@ static void i845_disable_cursor(struct intel_plane *plane, i845_update_cursor(plane, NULL, NULL); } -static bool i845_cursor_get_hw_state(struct intel_plane *plane) +static bool i845_cursor_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; @@ -9704,6 +9748,8 @@ static bool i845_cursor_get_hw_state(struct intel_plane *plane) ret = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; + *pipe = PIPE_A; + intel_display_power_put(dev_priv, power_domain); return ret; @@ -9715,25 +9761,30 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev); struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - u32 cntl; + u32 cntl = 0; - cntl = MCURSOR_GAMMA_ENABLE; + if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) + cntl |= MCURSOR_TRICKLE_FEED_DISABLE; - if (HAS_DDI(dev_priv)) - cntl |= CURSOR_PIPE_CSC_ENABLE; + if (INTEL_GEN(dev_priv) <= 10) { + cntl |= MCURSOR_GAMMA_ENABLE; + + if (HAS_DDI(dev_priv)) + cntl |= MCURSOR_PIPE_CSC_ENABLE; + } if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) cntl |= MCURSOR_PIPE_SELECT(crtc->pipe); switch (plane_state->base.crtc_w) { case 64: - cntl |= CURSOR_MODE_64_ARGB_AX; + cntl |= MCURSOR_MODE_64_ARGB_AX; break; case 128: - cntl |= CURSOR_MODE_128_ARGB_AX; + cntl |= MCURSOR_MODE_128_ARGB_AX; break; case 256: - cntl |= CURSOR_MODE_256_ARGB_AX; + cntl |= MCURSOR_MODE_256_ARGB_AX; break; default: MISSING_CASE(plane_state->base.crtc_w); @@ -9741,7 +9792,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, } if (plane_state->base.rotation & DRM_MODE_ROTATE_180) - cntl |= CURSOR_ROTATE_180; + cntl |= MCURSOR_ROTATE_180; return cntl; } @@ -9903,23 +9954,32 @@ static void i9xx_disable_cursor(struct intel_plane *plane, i9xx_update_cursor(plane, NULL, NULL); } -static bool i9xx_cursor_get_hw_state(struct intel_plane *plane) +static bool i9xx_cursor_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; - enum pipe pipe = plane->pipe; bool ret; + u32 val; /* * Not 100% correct for planes that can move between pipes, * but that's only the case for gen2-3 which don't have any * display power wells. */ - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; + val = I915_READ(CURCNTR(plane->pipe)); + + ret = val & MCURSOR_MODE; + + if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) + *pipe = plane->pipe; + else + *pipe = (val & MCURSOR_PIPE_SELECT_MASK) >> + MCURSOR_PIPE_SELECT_SHIFT; intel_display_power_put(dev_priv, power_domain); @@ -14124,14 +14184,15 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb) { struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); + struct drm_i915_gem_object *obj = intel_fb_obj(fb); drm_framebuffer_cleanup(fb); - i915_gem_object_lock(intel_fb->obj); - WARN_ON(!intel_fb->obj->framebuffer_references--); - i915_gem_object_unlock(intel_fb->obj); + i915_gem_object_lock(obj); + WARN_ON(!obj->framebuffer_references--); + i915_gem_object_unlock(obj); - i915_gem_object_put(intel_fb->obj); + i915_gem_object_put(obj); kfree(intel_fb); } @@ -14140,8 +14201,7 @@ static int intel_user_framebuffer_create_handle(struct drm_framebuffer *fb, struct drm_file *file, unsigned int *handle) { - struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); - struct drm_i915_gem_object *obj = intel_fb->obj; + struct drm_i915_gem_object *obj = intel_fb_obj(fb); if (obj->userptr.mm) { DRM_DEBUG("attempting to use a userptr for a framebuffer, denied\n"); @@ -14411,9 +14471,9 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, i, fb->pitches[i], stride_alignment); goto err; } - } - intel_fb->obj = obj; + fb->obj[i] = &obj->base; + } ret = intel_fill_fb_info(dev_priv, fb); if (ret) @@ -15095,8 +15155,8 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) WARN_ON(I915_READ(DSPCNTR(PLANE_A)) & DISPLAY_PLANE_ENABLE); WARN_ON(I915_READ(DSPCNTR(PLANE_B)) & DISPLAY_PLANE_ENABLE); WARN_ON(I915_READ(DSPCNTR(PLANE_C)) & DISPLAY_PLANE_ENABLE); - WARN_ON(I915_READ(CURCNTR(PIPE_A)) & CURSOR_MODE); - WARN_ON(I915_READ(CURCNTR(PIPE_B)) & CURSOR_MODE); + WARN_ON(I915_READ(CURCNTR(PIPE_A)) & MCURSOR_MODE); + WARN_ON(I915_READ(CURCNTR(PIPE_B)) & MCURSOR_MODE); I915_WRITE(PIPECONF(pipe), 0); POSTING_READ(PIPECONF(pipe)); @@ -15110,12 +15170,12 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) static bool intel_plane_mapping_ok(struct intel_crtc *crtc, struct intel_plane *plane) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; - u32 val = I915_READ(DSPCNTR(i9xx_plane)); + enum pipe pipe; - return (val & DISPLAY_PLANE_ENABLE) == 0 || - (val & DISPPLANE_SEL_PIPE_MASK) == DISPPLANE_SEL_PIPE(crtc->pipe); + if (!plane->get_hw_state(plane, &pipe)) + return true; + + return pipe == crtc->pipe; } static void @@ -15274,6 +15334,9 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) connector->base.dpms = DRM_MODE_DPMS_OFF; connector->base.encoder = NULL; } + + /* notify opregion of the sanitized encoder state */ + intel_opregion_notify_encoder(encoder, connector && has_active_crtc); } void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv) @@ -15314,7 +15377,10 @@ static void readout_plane_state(struct intel_crtc *crtc) for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { struct intel_plane_state *plane_state = to_intel_plane_state(plane->base.state); - bool visible = plane->get_hw_state(plane); + enum pipe pipe; + bool visible; + + visible = plane->get_hw_state(plane, &pipe); intel_set_plane_visible(crtc_state, plane_state, visible); } diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h index 2ef31617614a..c88185ed7594 100644 --- a/drivers/gpu/drm/i915/intel_display.h +++ b/drivers/gpu/drm/i915/intel_display.h @@ -126,6 +126,17 @@ enum port { #define port_name(p) ((p) + 'A') +enum tc_port { + PORT_TC_NONE = -1, + + PORT_TC1 = 0, + PORT_TC2, + PORT_TC3, + PORT_TC4, + + I915_MAX_TC_PORTS +}; + enum dpio_channel { DPIO_CH0, DPIO_CH1 diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 8320f0e8e3be..37b9f62aeb6e 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -56,7 +56,7 @@ struct dp_link_dpll { struct dpll dpll; }; -static const struct dp_link_dpll gen4_dpll[] = { +static const struct dp_link_dpll g4x_dpll[] = { { 162000, { .p1 = 2, .p2 = 10, .n = 2, .m1 = 23, .m2 = 8 } }, { 270000, @@ -513,7 +513,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) uint32_t DP; if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN, - "skipping pipe %c power seqeuncer kick due to port %c being active\n", + "skipping pipe %c power sequencer kick due to port %c being active\n", pipe_name(pipe), port_name(intel_dig_port->base.port))) return; @@ -529,9 +529,9 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) DP |= DP_LINK_TRAIN_PAT_1; if (IS_CHERRYVIEW(dev_priv)) - DP |= DP_PIPE_SELECT_CHV(pipe); - else if (pipe == PIPE_B) - DP |= DP_PIPEB_SELECT; + DP |= DP_PIPE_SEL_CHV(pipe); + else + DP |= DP_PIPE_SEL(pipe); pll_enabled = I915_READ(DPLL(pipe)) & DPLL_VCO_ENABLE; @@ -554,7 +554,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) /* * Similar magic as in intel_dp_enable_port(). * We _must_ do this port enable + disable trick - * to make this power seqeuencer lock onto the port. + * to make this power sequencer lock onto the port. * Otherwise even VDD force bit won't work. */ I915_WRITE(intel_dp->output_reg, DP); @@ -1550,8 +1550,8 @@ intel_dp_set_clock(struct intel_encoder *encoder, int i, count = 0; if (IS_G4X(dev_priv)) { - divisor = gen4_dpll; - count = ARRAY_SIZE(gen4_dpll); + divisor = g4x_dpll; + count = ARRAY_SIZE(g4x_dpll); } else if (HAS_PCH_SPLIT(dev_priv)) { divisor = pch_dpll; count = ARRAY_SIZE(pch_dpll); @@ -1964,7 +1964,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, /* Split out the IBX/CPU vs CPT settings */ - if (IS_GEN7(dev_priv) && port == PORT_A) { + if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) { if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) intel_dp->DP |= DP_SYNC_HS_HIGH; if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) @@ -1974,7 +1974,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) intel_dp->DP |= DP_ENHANCED_FRAMING; - intel_dp->DP |= crtc->pipe << 29; + intel_dp->DP |= DP_PIPE_SEL_IVB(crtc->pipe); } else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) { u32 trans_dp; @@ -2000,9 +2000,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_dp->DP |= DP_ENHANCED_FRAMING; if (IS_CHERRYVIEW(dev_priv)) - intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe); - else if (crtc->pipe == PIPE_B) - intel_dp->DP |= DP_PIPEB_SELECT; + intel_dp->DP |= DP_PIPE_SEL_CHV(crtc->pipe); + else + intel_dp->DP |= DP_PIPE_SEL(crtc->pipe); } } @@ -2624,52 +2624,66 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode) mode == DRM_MODE_DPMS_ON ? "enable" : "disable"); } +static bool cpt_dp_port_selected(struct drm_i915_private *dev_priv, + enum port port, enum pipe *pipe) +{ + enum pipe p; + + for_each_pipe(dev_priv, p) { + u32 val = I915_READ(TRANS_DP_CTL(p)); + + if ((val & TRANS_DP_PORT_SEL_MASK) == TRANS_DP_PORT_SEL(port)) { + *pipe = p; + return true; + } + } + + DRM_DEBUG_KMS("No pipe for DP port %c found\n", port_name(port)); + + /* must initialize pipe to something for the asserts */ + *pipe = PIPE_A; + + return false; +} + +bool intel_dp_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t dp_reg, enum port port, + enum pipe *pipe) +{ + bool ret; + u32 val; + + val = I915_READ(dp_reg); + + ret = val & DP_PORT_EN; + + /* asserts want to know the pipe even if the port is disabled */ + if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) + *pipe = (val & DP_PIPE_SEL_MASK_IVB) >> DP_PIPE_SEL_SHIFT_IVB; + else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) + ret &= cpt_dp_port_selected(dev_priv, port, pipe); + else if (IS_CHERRYVIEW(dev_priv)) + *pipe = (val & DP_PIPE_SEL_MASK_CHV) >> DP_PIPE_SEL_SHIFT_CHV; + else + *pipe = (val & DP_PIPE_SEL_MASK) >> DP_PIPE_SEL_SHIFT; + + return ret; +} + static bool intel_dp_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - enum port port = encoder->port; - u32 tmp; bool ret; if (!intel_display_power_get_if_enabled(dev_priv, encoder->power_domain)) return false; - ret = false; - - tmp = I915_READ(intel_dp->output_reg); - - if (!(tmp & DP_PORT_EN)) - goto out; - - if (IS_GEN7(dev_priv) && port == PORT_A) { - *pipe = PORT_TO_PIPE_CPT(tmp); - } else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) { - enum pipe p; - - for_each_pipe(dev_priv, p) { - u32 trans_dp = I915_READ(TRANS_DP_CTL(p)); - if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) { - *pipe = p; - ret = true; - - goto out; - } - } - - DRM_DEBUG_KMS("No pipe for dp port 0x%x found\n", - i915_mmio_reg_offset(intel_dp->output_reg)); - } else if (IS_CHERRYVIEW(dev_priv)) { - *pipe = DP_PORT_TO_PIPE_CHV(tmp); - } else { - *pipe = PORT_TO_PIPE(tmp); - } + ret = intel_dp_port_enabled(dev_priv, intel_dp->output_reg, + encoder->port, pipe); - ret = true; - -out: intel_display_power_put(dev_priv, encoder->power_domain); return ret; @@ -2883,7 +2897,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp, } I915_WRITE(DP_TP_CTL(port), temp); - } else if ((IS_GEN7(dev_priv) && port == PORT_A) || + } else if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) || (HAS_PCH_CPT(dev_priv) && port != PORT_A)) { *DP &= ~DP_LINK_TRAIN_MASK_CPT; @@ -3041,11 +3055,11 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp) edp_panel_vdd_off_sync(intel_dp); /* - * VLV seems to get confused when multiple power seqeuencers + * VLV seems to get confused when multiple power sequencers * have the same port selected (even if only one has power/vdd * enabled). The failure manifests as vlv_wait_port_ready() failing * CHV on the other hand doesn't seem to mind having the same port - * selected in multiple power seqeuencers, but let's clear the + * selected in multiple power sequencers, but let's clear the * port select always when logically disconnecting a power sequencer * from a port. */ @@ -3195,14 +3209,14 @@ uint8_t intel_dp_voltage_max(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); - enum port port = dp_to_dig_port(intel_dp)->base.port; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + enum port port = encoder->port; - if (INTEL_GEN(dev_priv) >= 9) { - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + if (HAS_DDI(dev_priv)) return intel_ddi_dp_voltage_max(encoder); - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) return DP_TRAIN_VOLTAGE_SWING_LEVEL_3; - else if (IS_GEN7(dev_priv) && port == PORT_A) + else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) return DP_TRAIN_VOLTAGE_SWING_LEVEL_2; else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) return DP_TRAIN_VOLTAGE_SWING_LEVEL_3; @@ -3214,33 +3228,11 @@ uint8_t intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing) { struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); - enum port port = dp_to_dig_port(intel_dp)->base.port; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + enum port port = encoder->port; - if (INTEL_GEN(dev_priv) >= 9) { - switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { - case DP_TRAIN_VOLTAGE_SWING_LEVEL_0: - return DP_TRAIN_PRE_EMPH_LEVEL_3; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_1: - return DP_TRAIN_PRE_EMPH_LEVEL_2; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_2: - return DP_TRAIN_PRE_EMPH_LEVEL_1; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_3: - return DP_TRAIN_PRE_EMPH_LEVEL_0; - default: - return DP_TRAIN_PRE_EMPH_LEVEL_0; - } - } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { - switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { - case DP_TRAIN_VOLTAGE_SWING_LEVEL_0: - return DP_TRAIN_PRE_EMPH_LEVEL_3; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_1: - return DP_TRAIN_PRE_EMPH_LEVEL_2; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_2: - return DP_TRAIN_PRE_EMPH_LEVEL_1; - case DP_TRAIN_VOLTAGE_SWING_LEVEL_3: - default: - return DP_TRAIN_PRE_EMPH_LEVEL_0; - } + if (HAS_DDI(dev_priv)) { + return intel_ddi_dp_pre_emphasis_max(encoder, voltage_swing); } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { case DP_TRAIN_VOLTAGE_SWING_LEVEL_0: @@ -3253,7 +3245,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing) default: return DP_TRAIN_PRE_EMPH_LEVEL_0; } - } else if (IS_GEN7(dev_priv) && port == PORT_A) { + } else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) { switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { case DP_TRAIN_VOLTAGE_SWING_LEVEL_0: return DP_TRAIN_PRE_EMPH_LEVEL_2; @@ -3448,7 +3440,7 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp) } static uint32_t -gen4_signal_levels(uint8_t train_set) +g4x_signal_levels(uint8_t train_set) { uint32_t signal_levels = 0; @@ -3485,9 +3477,9 @@ gen4_signal_levels(uint8_t train_set) return signal_levels; } -/* Gen6's DP voltage swing and pre-emphasis control */ +/* SNB CPU eDP voltage swing and pre-emphasis control */ static uint32_t -gen6_edp_signal_levels(uint8_t train_set) +snb_cpu_edp_signal_levels(uint8_t train_set) { int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK | DP_TRAIN_PRE_EMPHASIS_MASK); @@ -3513,9 +3505,9 @@ gen6_edp_signal_levels(uint8_t train_set) } } -/* Gen7's DP voltage swing and pre-emphasis control */ +/* IVB CPU eDP voltage swing and pre-emphasis control */ static uint32_t -gen7_edp_signal_levels(uint8_t train_set) +ivb_cpu_edp_signal_levels(uint8_t train_set) { int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK | DP_TRAIN_PRE_EMPHASIS_MASK); @@ -3562,14 +3554,14 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp) signal_levels = chv_signal_levels(intel_dp); } else if (IS_VALLEYVIEW(dev_priv)) { signal_levels = vlv_signal_levels(intel_dp); - } else if (IS_GEN7(dev_priv) && port == PORT_A) { - signal_levels = gen7_edp_signal_levels(train_set); + } else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) { + signal_levels = ivb_cpu_edp_signal_levels(train_set); mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB; } else if (IS_GEN6(dev_priv) && port == PORT_A) { - signal_levels = gen6_edp_signal_levels(train_set); + signal_levels = snb_cpu_edp_signal_levels(train_set); mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB; } else { - signal_levels = gen4_signal_levels(train_set); + signal_levels = g4x_signal_levels(train_set); mask = DP_VOLTAGE_MASK | DP_PRE_EMPHASIS_MASK; } @@ -3652,7 +3644,7 @@ intel_dp_link_down(struct intel_encoder *encoder, DRM_DEBUG_KMS("\n"); - if ((IS_GEN7(dev_priv) && port == PORT_A) || + if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) || (HAS_PCH_CPT(dev_priv) && port != PORT_A)) { DP &= ~DP_LINK_TRAIN_MASK_CPT; DP |= DP_LINK_TRAIN_PAT_IDLE_CPT; @@ -3681,8 +3673,9 @@ intel_dp_link_down(struct intel_encoder *encoder, intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); /* always enable with pattern 1 (as per spec) */ - DP &= ~(DP_PIPEB_SELECT | DP_LINK_TRAIN_MASK); - DP |= DP_PORT_EN | DP_LINK_TRAIN_PAT_1; + DP &= ~(DP_PIPE_SEL_MASK | DP_LINK_TRAIN_MASK); + DP |= DP_PORT_EN | DP_PIPE_SEL(PIPE_A) | + DP_LINK_TRAIN_PAT_1; I915_WRITE(intel_dp->output_reg, DP); POSTING_READ(intel_dp->output_reg); @@ -3737,8 +3730,6 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) dev_priv->no_aux_handshake = intel_dp->dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING; - intel_psr_init_dpcd(intel_dp); - /* * Read the eDP display control registers. * @@ -3754,6 +3745,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) DRM_DEBUG_KMS("eDP DPCD: %*ph\n", (int) sizeof(intel_dp->edp_dpcd), intel_dp->edp_dpcd); + /* + * This has to be called after intel_dp->edp_dpcd is filled, PSR checks + * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1] + */ + intel_psr_init_dpcd(intel_dp); + /* Read the eDP 1.4+ supported link rates. */ if (intel_dp->edp_dpcd[0] >= DP_EDP_14) { __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; @@ -5317,14 +5314,14 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) static enum pipe vlv_active_pipe(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + enum pipe pipe; - if ((intel_dp->DP & DP_PORT_EN) == 0) - return INVALID_PIPE; + if (intel_dp_port_enabled(dev_priv, intel_dp->output_reg, + encoder->port, &pipe)) + return pipe; - if (IS_CHERRYVIEW(dev_priv)) - return DP_PORT_TO_PIPE_CHV(intel_dp->DP); - else - return PORT_TO_PIPE(intel_dp->DP); + return INVALID_PIPE; } void intel_dp_encoder_reset(struct drm_encoder *encoder) @@ -5673,7 +5670,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp, /* * On some VLV machines the BIOS can leave the VDD - * enabled even on power seqeuencers which aren't + * enabled even on power sequencers which aren't * hooked up to any port. This would mess up the * power domain tracking the first time we pick * one of these power sequencers for use since @@ -5681,7 +5678,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp, * already on and therefore wouldn't grab the power * domain reference. Disable VDD first to avoid this. * This also avoids spuriously turning the VDD on as - * soon as the new power seqeuencer gets initialized. + * soon as the new power sequencer gets initialized. */ if (force_disable_vdd) { u32 pp = ironlake_get_pp_control(intel_dp); @@ -5719,10 +5716,20 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp, if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { port_sel = PANEL_PORT_SELECT_VLV(port); } else if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) { - if (port == PORT_A) + switch (port) { + case PORT_A: port_sel = PANEL_PORT_SELECT_DPA; - else + break; + case PORT_C: + port_sel = PANEL_PORT_SELECT_DPC; + break; + case PORT_D: port_sel = PANEL_PORT_SELECT_DPD; + break; + default: + MISSING_CASE(port); + break; + } } pp_on |= port_sel; diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index 383fbc15113d..07bdbf2582ba 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -2525,6 +2525,76 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state, return true; } +int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv, + uint32_t pll_id) +{ + uint32_t cfgcr0, cfgcr1; + uint32_t pdiv, kdiv, qdiv_mode, qdiv_ratio, dco_integer, dco_fraction; + const struct skl_wrpll_params *params; + int index, n_entries, link_clock; + + /* Read back values from DPLL CFGCR registers */ + cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id)); + cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id)); + + dco_integer = cfgcr0 & DPLL_CFGCR0_DCO_INTEGER_MASK; + dco_fraction = (cfgcr0 & DPLL_CFGCR0_DCO_FRACTION_MASK) >> + DPLL_CFGCR0_DCO_FRACTION_SHIFT; + pdiv = (cfgcr1 & DPLL_CFGCR1_PDIV_MASK) >> DPLL_CFGCR1_PDIV_SHIFT; + kdiv = (cfgcr1 & DPLL_CFGCR1_KDIV_MASK) >> DPLL_CFGCR1_KDIV_SHIFT; + qdiv_mode = (cfgcr1 & DPLL_CFGCR1_QDIV_MODE(1)) >> + DPLL_CFGCR1_QDIV_MODE_SHIFT; + qdiv_ratio = (cfgcr1 & DPLL_CFGCR1_QDIV_RATIO_MASK) >> + DPLL_CFGCR1_QDIV_RATIO_SHIFT; + + params = dev_priv->cdclk.hw.ref == 24000 ? + icl_dp_combo_pll_24MHz_values : + icl_dp_combo_pll_19_2MHz_values; + n_entries = ARRAY_SIZE(icl_dp_combo_pll_24MHz_values); + + for (index = 0; index < n_entries; index++) { + if (dco_integer == params[index].dco_integer && + dco_fraction == params[index].dco_fraction && + pdiv == params[index].pdiv && + kdiv == params[index].kdiv && + qdiv_mode == params[index].qdiv_mode && + qdiv_ratio == params[index].qdiv_ratio) + break; + } + + /* Map PLL Index to Link Clock */ + switch (index) { + default: + MISSING_CASE(index); + case 0: + link_clock = 540000; + break; + case 1: + link_clock = 270000; + break; + case 2: + link_clock = 162000; + break; + case 3: + link_clock = 324000; + break; + case 4: + link_clock = 216000; + break; + case 5: + link_clock = 432000; + break; + case 6: + link_clock = 648000; + break; + case 7: + link_clock = 810000; + break; + } + + return link_clock; +} + static enum port icl_mg_pll_id_to_port(enum intel_dpll_id id) { return id - DPLL_ID_ICL_MGPLL1 + PORT_C; diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h index 7a0cd564a9ee..78915057d2e6 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h @@ -336,5 +336,7 @@ void intel_shared_dpll_init(struct drm_device *dev); void intel_dpll_dump_hw_state(struct drm_i915_private *dev_priv, struct intel_dpll_hw_state *hw_state); +int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv, + uint32_t pll_id); #endif /* _INTEL_DPLL_MGR_H_ */ diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0361130500a6..8641583842be 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -194,7 +194,6 @@ enum intel_output_type { struct intel_framebuffer { struct drm_framebuffer base; - struct drm_i915_gem_object *obj; struct intel_rotation_info rot_info; /* for each plane in the normal GTT view */ @@ -971,7 +970,7 @@ struct intel_plane { const struct intel_plane_state *plane_state); void (*disable_plane)(struct intel_plane *plane, struct intel_crtc *crtc); - bool (*get_hw_state)(struct intel_plane *plane); + bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe); int (*check_plane)(struct intel_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state); @@ -1004,7 +1003,7 @@ struct cxsr_latency { #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base) #define to_intel_plane(x) container_of(x, struct intel_plane, base) #define to_intel_plane_state(x) container_of(x, struct intel_plane_state, base) -#define intel_fb_obj(x) (x ? to_intel_framebuffer(x)->obj : NULL) +#define intel_fb_obj(x) ((x) ? to_intel_bo((x)->obj[0]) : NULL) struct intel_hdmi { i915_reg_t hdmi_reg; @@ -1376,6 +1375,8 @@ void gen9_enable_guc_interrupts(struct drm_i915_private *dev_priv); void gen9_disable_guc_interrupts(struct drm_i915_private *dev_priv); /* intel_crt.c */ +bool intel_crt_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t adpa_reg, enum pipe *pipe); void intel_crt_init(struct drm_i915_private *dev_priv); void intel_crt_reset(struct drm_encoder *encoder); @@ -1392,8 +1393,6 @@ void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, enum transcoder cpu_transcoder); void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state); -struct intel_encoder * -intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state); void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state); void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp); bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector); @@ -1407,6 +1406,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, u32 bxt_signal_levels(struct intel_dp *intel_dp); uint32_t ddi_signal_levels(struct intel_dp *intel_dp); u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder); +u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder, + u8 voltage_swing); int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, bool enable); void icl_map_plls_to_ports(struct drm_crtc *crtc, @@ -1488,6 +1489,9 @@ void intel_connector_attach_encoder(struct intel_connector *connector, struct intel_encoder *encoder); struct drm_display_mode * intel_encoder_current_mode(struct intel_encoder *encoder); +bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port); +enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, + enum port port); enum pipe intel_get_pipe_from_connector(struct intel_connector *connector); int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data, @@ -1615,6 +1619,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode, void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); +u16 skl_scaler_calc_phase(int sub, bool chroma_center); int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, uint32_t pixel_format); @@ -1644,6 +1649,9 @@ void intel_csr_ucode_suspend(struct drm_i915_private *); void intel_csr_ucode_resume(struct drm_i915_private *); /* intel_dp.c */ +bool intel_dp_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t dp_reg, enum port port, + enum pipe *pipe); bool intel_dp_init(struct drm_i915_private *dev_priv, i915_reg_t output_reg, enum port port); bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port, @@ -1821,6 +1829,8 @@ void intel_infoframe_init(struct intel_digital_port *intel_dig_port); /* intel_lvds.c */ +bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t lvds_reg, enum pipe *pipe); void intel_lvds_init(struct drm_i915_private *dev_priv); struct intel_encoder *intel_get_lvds_encoder(struct drm_device *dev); bool intel_is_dual_link_lvds(struct drm_device *dev); @@ -1911,8 +1921,6 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, unsigned frontbuffer_bits, enum fb_op_origin origin); void intel_psr_init(struct drm_i915_private *dev_priv); -void intel_psr_single_frame_update(struct drm_i915_private *dev_priv, - unsigned frontbuffer_bits); void intel_psr_compute_config(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state); void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug); @@ -2058,6 +2066,8 @@ void intel_init_ipc(struct drm_i915_private *dev_priv); void intel_enable_ipc(struct drm_i915_private *dev_priv); /* intel_sdvo.c */ +bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t sdvo_reg, enum pipe *pipe); bool intel_sdvo_init(struct drm_i915_private *dev_priv, i915_reg_t reg, enum port port); @@ -2076,7 +2086,7 @@ void skl_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc); -bool skl_plane_get_hw_state(struct intel_plane *plane); +bool skl_plane_get_hw_state(struct intel_plane *plane, enum pipe *pipe); bool skl_plane_has_ccs(struct drm_i915_private *dev_priv, enum pipe pipe, enum plane_id plane_id); bool intel_format_is_yuv(uint32_t format); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index cf39ca90d887..cf1231f9c33b 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -1665,16 +1665,16 @@ static int intel_dsi_get_panel_orientation(struct intel_connector *connector) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL; - enum i9xx_plane_id plane; + enum i9xx_plane_id i9xx_plane; u32 val; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { if (connector->encoder->crtc_mask == BIT(PIPE_B)) - plane = PLANE_B; + i9xx_plane = PLANE_B; else - plane = PLANE_A; + i9xx_plane = PLANE_A; - val = I915_READ(DSPCNTR(plane)); + val = I915_READ(DSPCNTR(i9xx_plane)); if (val & DISPPLANE_ROTATE_180) orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP; } diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index a70d767313aa..7b942b6c1700 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -137,19 +137,15 @@ static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector) static bool intel_dvo_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dvo *intel_dvo = enc_to_dvo(encoder); u32 tmp; tmp = I915_READ(intel_dvo->dev.dvo_reg); - if (!(tmp & DVO_ENABLE)) - return false; - - *pipe = PORT_TO_PIPE(tmp); + *pipe = (tmp & DVO_PIPE_SEL_MASK) >> DVO_PIPE_SEL_SHIFT; - return true; + return tmp & DVO_ENABLE; } static void intel_dvo_get_config(struct intel_encoder *encoder, @@ -276,8 +272,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder, dvo_val |= DVO_DATA_ORDER_FP | DVO_BORDER_ENABLE | DVO_BLANK_ACTIVE_HIGH; - if (pipe == 1) - dvo_val |= DVO_PIPE_B_SELECT; + dvo_val |= DVO_PIPE_SEL(pipe); dvo_val |= DVO_PIPE_STALL; if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) dvo_val |= DVO_HSYNC_ACTIVE_HIGH; diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 1590375f31cb..2ec2e60dc670 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -515,7 +515,7 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size) return PTR_ERR(obj); } - vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err_unref; @@ -585,7 +585,7 @@ static int init_status_page(struct intel_engine_cs *engine) if (ret) goto err; - vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err; @@ -645,6 +645,12 @@ static int init_phys_status_page(struct intel_engine_cs *engine) return 0; } +static void __intel_context_unpin(struct i915_gem_context *ctx, + struct intel_engine_cs *engine) +{ + intel_context_unpin(to_intel_context(ctx, engine)); +} + /** * intel_engines_init_common - initialize cengine state which might require hw access * @engine: Engine to initialize. @@ -658,7 +664,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine) */ int intel_engine_init_common(struct intel_engine_cs *engine) { - struct intel_ring *ring; + struct drm_i915_private *i915 = engine->i915; + struct intel_context *ce; int ret; engine->set_default_submission(engine); @@ -670,18 +677,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine) * be available. To avoid this we always pin the default * context. */ - ring = intel_context_pin(engine->i915->kernel_context, engine); - if (IS_ERR(ring)) - return PTR_ERR(ring); + ce = intel_context_pin(i915->kernel_context, engine); + if (IS_ERR(ce)) + return PTR_ERR(ce); /* * Similarly the preempt context must always be available so that * we can interrupt the engine at any time. */ - if (engine->i915->preempt_context) { - ring = intel_context_pin(engine->i915->preempt_context, engine); - if (IS_ERR(ring)) { - ret = PTR_ERR(ring); + if (i915->preempt_context) { + ce = intel_context_pin(i915->preempt_context, engine); + if (IS_ERR(ce)) { + ret = PTR_ERR(ce); goto err_unpin_kernel; } } @@ -690,7 +697,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine) if (ret) goto err_unpin_preempt; - if (HWS_NEEDS_PHYSICAL(engine->i915)) + if (HWS_NEEDS_PHYSICAL(i915)) ret = init_phys_status_page(engine); else ret = init_status_page(engine); @@ -702,10 +709,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine) err_breadcrumbs: intel_engine_fini_breadcrumbs(engine); err_unpin_preempt: - if (engine->i915->preempt_context) - intel_context_unpin(engine->i915->preempt_context, engine); + if (i915->preempt_context) + __intel_context_unpin(i915->preempt_context, engine); + err_unpin_kernel: - intel_context_unpin(engine->i915->kernel_context, engine); + __intel_context_unpin(i915->kernel_context, engine); return ret; } @@ -718,6 +726,8 @@ err_unpin_kernel: */ void intel_engine_cleanup_common(struct intel_engine_cs *engine) { + struct drm_i915_private *i915 = engine->i915; + intel_engine_cleanup_scratch(engine); if (HWS_NEEDS_PHYSICAL(engine->i915)) @@ -732,9 +742,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) if (engine->default_state) i915_gem_object_put(engine->default_state); - if (engine->i915->preempt_context) - intel_context_unpin(engine->i915->preempt_context, engine); - intel_context_unpin(engine->i915->kernel_context, engine); + if (i915->preempt_context) + __intel_context_unpin(i915->preempt_context, engine); + __intel_context_unpin(i915->kernel_context, engine); i915_timeline_fini(&engine->timeline); } @@ -769,6 +779,35 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine) return bbaddr; } +int intel_engine_stop_cs(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + const u32 base = engine->mmio_base; + const i915_reg_t mode = RING_MI_MODE(base); + int err; + + if (INTEL_GEN(dev_priv) < 3) + return -ENODEV; + + GEM_TRACE("%s\n", engine->name); + + I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING)); + + err = 0; + if (__intel_wait_for_register_fw(dev_priv, + mode, MODE_IDLE, MODE_IDLE, + 1000, 0, + NULL)) { + GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name); + err = -ETIMEDOUT; + } + + /* A final mmio read to let GPU writes be hopefully flushed to memory */ + POSTING_READ_FW(mode); + + return err; +} + const char *i915_cache_level_str(struct drm_i915_private *i915, int type) { switch (type) { @@ -780,12 +819,32 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type) } } +u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv) +{ + const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); + u32 mcr_s_ss_select; + u32 slice = fls(sseu->slice_mask); + u32 subslice = fls(sseu->subslice_mask[slice]); + + if (INTEL_GEN(dev_priv) == 10) + mcr_s_ss_select = GEN8_MCR_SLICE(slice) | + GEN8_MCR_SUBSLICE(subslice); + else if (INTEL_GEN(dev_priv) >= 11) + mcr_s_ss_select = GEN11_MCR_SLICE(slice) | + GEN11_MCR_SUBSLICE(subslice); + else + mcr_s_ss_select = 0; + + return mcr_s_ss_select; +} + static inline uint32_t read_subslice_reg(struct drm_i915_private *dev_priv, int slice, int subslice, i915_reg_t reg) { uint32_t mcr_slice_subslice_mask; uint32_t mcr_slice_subslice_select; + uint32_t default_mcr_s_ss_select; uint32_t mcr; uint32_t ret; enum forcewake_domains fw_domains; @@ -802,6 +861,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice, GEN8_MCR_SUBSLICE(subslice); } + default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv); + fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ); fw_domains |= intel_uncore_forcewake_for_reg(dev_priv, @@ -812,11 +873,10 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice, intel_uncore_forcewake_get__locked(dev_priv, fw_domains); mcr = I915_READ_FW(GEN8_MCR_SELECTOR); - /* - * The HW expects the slice and sublice selectors to be reset to 0 - * after reading out the registers. - */ - WARN_ON_ONCE(mcr & mcr_slice_subslice_mask); + + WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) != + default_mcr_s_ss_select); + mcr &= ~mcr_slice_subslice_mask; mcr |= mcr_slice_subslice_select; I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); @@ -824,6 +884,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice, ret = I915_READ_FW(reg); mcr &= ~mcr_slice_subslice_mask; + mcr |= default_mcr_s_ss_select; + I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); intel_uncore_forcewake_put__locked(dev_priv, fw_domains); @@ -934,10 +996,19 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine) return true; /* Waiting to drain ELSP? */ - if (READ_ONCE(engine->execlists.active)) - return false; + if (READ_ONCE(engine->execlists.active)) { + struct intel_engine_execlists *execlists = &engine->execlists; + + if (tasklet_trylock(&execlists->tasklet)) { + execlists->tasklet.func(execlists->tasklet.data); + tasklet_unlock(&execlists->tasklet); + } - /* ELSP is empty, but there are ready requests? */ + if (READ_ONCE(execlists->active)) + return false; + } + + /* ELSP is empty, but there are ready requests? E.g. after reset */ if (READ_ONCE(engine->execlists.first)) return false; @@ -978,8 +1049,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv) */ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine) { - const struct i915_gem_context * const kernel_context = - engine->i915->kernel_context; + const struct intel_context *kernel_context = + to_intel_context(engine->i915->kernel_context, engine); struct i915_request *rq; lockdep_assert_held(&engine->i915->drm.struct_mutex); @@ -991,7 +1062,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine) */ rq = __i915_gem_active_peek(&engine->timeline.last_request); if (rq) - return rq->ctx == kernel_context; + return rq->hw_context == kernel_context; else return engine->last_retired_context == kernel_context; } @@ -1043,6 +1114,11 @@ void intel_engines_park(struct drm_i915_private *i915) if (engine->park) engine->park(engine); + if (engine->pinned_default_state) { + i915_gem_object_unpin_map(engine->default_state); + engine->pinned_default_state = NULL; + } + i915_gem_batch_pool_fini(&engine->batch_pool); engine->execlists.no_priolist = false; } @@ -1060,6 +1136,16 @@ void intel_engines_unpark(struct drm_i915_private *i915) enum intel_engine_id id; for_each_engine(engine, i915, id) { + void *map; + + /* Pin the default state for fast resets from atomic context. */ + map = NULL; + if (engine->default_state) + map = i915_gem_object_pin_map(engine->default_state, + I915_MAP_WB); + if (!IS_ERR_OR_NULL(map)) + engine->pinned_default_state = map; + if (engine->unpark) engine->unpark(engine); @@ -1067,6 +1153,29 @@ void intel_engines_unpark(struct drm_i915_private *i915) } } +/** + * intel_engine_lost_context: called when the GPU is reset into unknown state + * @engine: the engine + * + * We have either reset the GPU or otherwise about to lose state tracking of + * the current GPU logical state (e.g. suspend). On next use, it is therefore + * imperative that we make no presumptions about the current state and load + * from scratch. + */ +void intel_engine_lost_context(struct intel_engine_cs *engine) +{ + struct intel_context *ce; + + lockdep_assert_held(&engine->i915->drm.struct_mutex); + + engine->legacy_active_context = NULL; + engine->legacy_active_ppgtt = NULL; + + ce = fetch_and_zero(&engine->last_retired_context); + if (ce) + intel_context_unpin(ce); +} + bool intel_engine_can_store_dword(struct intel_engine_cs *engine) { switch (INTEL_GEN(engine->i915)) { @@ -1296,6 +1405,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, const struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq, *last; + unsigned long flags; struct rb_node *rb; int count; @@ -1362,7 +1472,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, drm_printf(m, "\tDevice is asleep; skipping register dump\n"); } - spin_lock_irq(&engine->timeline.lock); + local_irq_save(flags); + spin_lock(&engine->timeline.lock); last = NULL; count = 0; @@ -1404,16 +1515,17 @@ void intel_engine_dump(struct intel_engine_cs *engine, print_request(m, last, "\t\tQ "); } - spin_unlock_irq(&engine->timeline.lock); + spin_unlock(&engine->timeline.lock); - spin_lock_irq(&b->rb_lock); + spin_lock(&b->rb_lock); for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) { struct intel_wait *w = rb_entry(rb, typeof(*w), node); drm_printf(m, "\t%s [%d] waiting for %x\n", w->tsk->comm, w->tsk->pid, w->seqno); } - spin_unlock_irq(&b->rb_lock); + spin_unlock(&b->rb_lock); + local_irq_restore(flags); drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n", engine->irq_posted, diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index e9e02b58b7be..fb2f9fce34cd 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -47,7 +47,7 @@ static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev) { - struct drm_i915_gem_object *obj = ifbdev->fb->obj; + struct drm_i915_gem_object *obj = intel_fb_obj(&ifbdev->fb->base); unsigned int origin = ifbdev->vma_flags & PLANE_HAS_FENCE ? ORIGIN_GTT : ORIGIN_CPU; @@ -193,7 +193,7 @@ static int intelfb_create(struct drm_fb_helper *helper, drm_framebuffer_put(&intel_fb->base); intel_fb = ifbdev->fb = NULL; } - if (!intel_fb || WARN_ON(!intel_fb->obj)) { + if (!intel_fb || WARN_ON(!intel_fb_obj(&intel_fb->base))) { DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n"); ret = intelfb_alloc(helper, sizes); if (ret) @@ -265,7 +265,7 @@ static int intelfb_create(struct drm_fb_helper *helper, * If the object is stolen however, it will be full of whatever * garbage was left in there. */ - if (intel_fb->obj->stolen && !prealloc) + if (intel_fb_obj(fb)->stolen && !prealloc) memset_io(info->screen_base, 0, info->screen_size); /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ @@ -792,7 +792,8 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous * been restored from swap. If the object is stolen however, it will be * full of whatever garbage was left in there. */ - if (state == FBINFO_STATE_RUNNING && ifbdev->fb->obj->stolen) + if (state == FBINFO_STATE_RUNNING && + intel_fb_obj(&ifbdev->fb->base)->stolen) memset_io(info->screen_base, 0, info->screen_size); drm_fb_helper_set_suspend(&ifbdev->helper, state); diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c index 7fff0a0eceb4..c3379bde266f 100644 --- a/drivers/gpu/drm/i915/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/intel_frontbuffer.c @@ -153,8 +153,6 @@ void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv, /* Remove stale busy bits due to the old buffer. */ dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits; spin_unlock(&dev_priv->fb_tracking.lock); - - intel_psr_single_frame_update(dev_priv, frontbuffer_bits); } /** diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c index 116f4ccf1bbd..29fd95c1306b 100644 --- a/drivers/gpu/drm/i915/intel_guc.c +++ b/drivers/gpu/drm/i915/intel_guc.c @@ -346,10 +346,8 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len, ret = -EIO; if (ret) { - DRM_DEBUG_DRIVER("INTEL_GUC_SEND: Action 0x%X failed;" - " ret=%d status=0x%08X response=0x%08X\n", - action[0], ret, status, - I915_READ(SOFT_SCRATCH(15))); + DRM_ERROR("MMIO: GuC action %#x failed with error %d %#x\n", + action[0], ret, status); goto out; } @@ -572,7 +570,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size) if (IS_ERR(obj)) return ERR_CAST(obj); - vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL); + vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL); if (IS_ERR(vma)) goto err; diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c index 2feb65096966..f3945258fe1b 100644 --- a/drivers/gpu/drm/i915/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/intel_guc_submission.c @@ -513,8 +513,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) { struct intel_guc_client *client = guc->execbuf_client; struct intel_engine_cs *engine = rq->engine; - u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(rq->ctx, - engine)); + u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc); u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64); spin_lock(&client->wq_lock); @@ -537,7 +536,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) */ static void flush_ggtt_writes(struct i915_vma *vma) { - struct drm_i915_private *dev_priv = to_i915(vma->obj->base.dev); + struct drm_i915_private *dev_priv = vma->vm->i915; if (i915_vma_is_map_and_fenceable(vma)) POSTING_READ_FW(GUC_STATUS); @@ -552,8 +551,8 @@ static void inject_preempt_context(struct work_struct *work) preempt_work[engine->id]); struct intel_guc_client *client = guc->preempt_client; struct guc_stage_desc *stage_desc = __get_stage_desc(client); - u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(client->owner, - engine)); + u32 ctx_desc = lower_32_bits(to_intel_context(client->owner, + engine)->lrc_desc); u32 data[7]; /* @@ -623,6 +622,21 @@ static void wait_for_guc_preempt_report(struct intel_engine_cs *engine) report->report_return_status = INTEL_GUC_REPORT_STATUS_UNKNOWN; } +static void complete_preempt_context(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists *execlists = &engine->execlists; + + GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)); + + execlists_cancel_port_requests(execlists); + execlists_unwind_incomplete_requests(execlists); + + wait_for_guc_preempt_report(engine); + intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0); + + execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT); +} + /** * guc_submit() - Submit commands through GuC * @engine: engine associated with the commands @@ -710,7 +724,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine) struct i915_request *rq, *rn; list_for_each_entry_safe(rq, rn, &p->requests, sched.link) { - if (last && rq->ctx != last->ctx) { + if (last && rq->hw_context != last->hw_context) { if (port == last_port) { __list_del_many(&p->requests, &rq->sched.link); @@ -793,20 +807,44 @@ static void guc_submission_tasklet(unsigned long data) if (execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT) && intel_read_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX) == - GUC_PREEMPT_FINISHED) { - execlists_cancel_port_requests(&engine->execlists); - execlists_unwind_incomplete_requests(execlists); - - wait_for_guc_preempt_report(engine); - - execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT); - intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0); - } + GUC_PREEMPT_FINISHED) + complete_preempt_context(engine); if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)) guc_dequeue(engine); } +static struct i915_request * +guc_reset_prepare(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists * const execlists = &engine->execlists; + + GEM_TRACE("%s\n", engine->name); + + /* + * Prevent request submission to the hardware until we have + * completed the reset in i915_gem_reset_finish(). If a request + * is completed by one engine, it may then queue a request + * to a second via its execlists->tasklet *just* as we are + * calling engine->init_hw() and also writing the ELSP. + * Turning off the execlists->tasklet until the reset is over + * prevents the race. + */ + __tasklet_disable_sync_once(&execlists->tasklet); + + /* + * We're using worker to queue preemption requests from the tasklet in + * GuC submission mode. + * Even though tasklet was disabled, we may still have a worker queued. + * Let's make sure that all workers scheduled before disabling the + * tasklet are completed before continuing with the reset. + */ + if (engine->i915->guc.preempt_wq) + flush_workqueue(engine->i915->guc.preempt_wq); + + return i915_gem_find_active_request(engine); +} + /* * Everything below here is concerned with setup & teardown, and is * therefore not part of the somewhat time-critical batch-submission @@ -1119,7 +1157,7 @@ int intel_guc_submission_init(struct intel_guc *guc) WARN_ON(!guc_verify_doorbells(guc)); ret = guc_clients_create(guc); if (ret) - return ret; + goto err_pool; for_each_engine(engine, dev_priv, id) { guc->preempt_work[id].engine = engine; @@ -1128,6 +1166,9 @@ int intel_guc_submission_init(struct intel_guc *guc) return 0; +err_pool: + guc_stage_desc_pool_destroy(guc); + return ret; } void intel_guc_submission_fini(struct intel_guc *guc) @@ -1267,6 +1308,9 @@ int intel_guc_submission_enable(struct intel_guc *guc) &engine->execlists; execlists->tasklet.func = guc_submission_tasklet; + + engine->reset.prepare = guc_reset_prepare; + engine->park = guc_submission_park; engine->unpark = guc_submission_unpark; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index ee929f31f7db..ba5ea61fb7b9 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1161,33 +1161,16 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder, static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); - u32 tmp; bool ret; if (!intel_display_power_get_if_enabled(dev_priv, encoder->power_domain)) return false; - ret = false; - - tmp = I915_READ(intel_hdmi->hdmi_reg); - - if (!(tmp & SDVO_ENABLE)) - goto out; - - if (HAS_PCH_CPT(dev_priv)) - *pipe = PORT_TO_PIPE_CPT(tmp); - else if (IS_CHERRYVIEW(dev_priv)) - *pipe = SDVO_PORT_TO_PIPE_CHV(tmp); - else - *pipe = PORT_TO_PIPE(tmp); - - ret = true; + ret = intel_sdvo_port_enabled(dev_priv, intel_hdmi->hdmi_reg, pipe); -out: intel_display_power_put(dev_priv, encoder->power_domain); return ret; @@ -1421,8 +1404,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder, intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false); intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); - temp &= ~SDVO_PIPE_B_SELECT; - temp |= SDVO_ENABLE; + temp &= ~SDVO_PIPE_SEL_MASK; + temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A); /* * HW workaround, need to write this twice for issue * that may result in first write getting masked. diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 15434cad5430..091e28f0e024 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -164,7 +164,8 @@ #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS) static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, - struct intel_engine_cs *engine); + struct intel_engine_cs *engine, + struct intel_context *ce); static void execlists_init_reg_state(u32 *reg_state, struct i915_gem_context *ctx, struct intel_engine_cs *engine, @@ -189,12 +190,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine, !i915_request_completed(last)); } -/** - * intel_lr_context_descriptor_update() - calculate & cache the descriptor - * descriptor for a pinned context - * @ctx: Context to work on - * @engine: Engine the descriptor will be used with - * +/* * The context descriptor encodes various attributes of a context, * including its GTT address and some flags. Because it's fairly * expensive to calculate, we'll just do it once and cache the result, @@ -204,7 +200,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine, * * bits 0-11: flags, GEN8_CTX_* (cached in ctx->desc_template) * bits 12-31: LRCA, GTT address of (the HWSP of) this context - * bits 32-52: ctx ID, a globally unique tag + * bits 32-52: ctx ID, a globally unique tag (highest bit used by GuC) * bits 53-54: mbz, reserved for use by hardware * bits 55-63: group ID, currently unused and set to 0 * @@ -222,9 +218,9 @@ static inline bool need_preempt(const struct intel_engine_cs *engine, */ static void intel_lr_context_descriptor_update(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) + struct intel_engine_cs *engine, + struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); u64 desc; BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH))); @@ -237,6 +233,11 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx, /* bits 12-31 */ GEM_BUG_ON(desc & GENMASK_ULL(63, 32)); + /* + * The following 32bits are copied into the OA reports (dword 2). + * Consider updating oa_get_render_ctx_id in i915_perf.c when changing + * anything below. + */ if (INTEL_GEN(ctx->i915) >= 11) { GEM_BUG_ON(ctx->hw_id >= BIT(GEN11_SW_CTX_ID_WIDTH)); desc |= (u64)ctx->hw_id << GEN11_SW_CTX_ID_SHIFT; @@ -418,9 +419,9 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state) static u64 execlists_update_context(struct i915_request *rq) { - struct intel_context *ce = to_intel_context(rq->ctx, rq->engine); + struct intel_context *ce = rq->hw_context; struct i915_hw_ppgtt *ppgtt = - rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; + rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt; u32 *reg_state = ce->lrc_reg_state; reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail); @@ -430,7 +431,7 @@ static u64 execlists_update_context(struct i915_request *rq) * PML4 is allocated during ppgtt init, so this is not needed * in 48-bit mode. */ - if (ppgtt && !i915_vm_is_48bit(&ppgtt->base)) + if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm)) execlists_update_context_pdps(ppgtt, reg_state); return ce->lrc_desc; @@ -495,14 +496,14 @@ static void execlists_submit_ports(struct intel_engine_cs *engine) execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK); } -static bool ctx_single_port_submission(const struct i915_gem_context *ctx) +static bool ctx_single_port_submission(const struct intel_context *ce) { return (IS_ENABLED(CONFIG_DRM_I915_GVT) && - i915_gem_context_force_single_submission(ctx)); + i915_gem_context_force_single_submission(ce->gem_context)); } -static bool can_merge_ctx(const struct i915_gem_context *prev, - const struct i915_gem_context *next) +static bool can_merge_ctx(const struct intel_context *prev, + const struct intel_context *next) { if (prev != next) return false; @@ -552,8 +553,18 @@ static void inject_preempt_context(struct intel_engine_cs *engine) if (execlists->ctrl_reg) writel(EL_CTRL_LOAD, execlists->ctrl_reg); - execlists_clear_active(&engine->execlists, EXECLISTS_ACTIVE_HWACK); - execlists_set_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT); + execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK); + execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT); +} + +static void complete_preempt_context(struct intel_engine_execlists *execlists) +{ + GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)); + + execlists_cancel_port_requests(execlists); + execlists_unwind_incomplete_requests(execlists); + + execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT); } static bool __execlists_dequeue(struct intel_engine_cs *engine) @@ -602,8 +613,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine) GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_USER)); GEM_BUG_ON(!port_count(&port[0])); - if (port_count(&port[0]) > 1) - return false; /* * If we write to ELSP a second time before the HW has had @@ -671,7 +680,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine) * second request, and so we never need to tell the * hardware about the first. */ - if (last && !can_merge_ctx(rq->ctx, last->ctx)) { + if (last && + !can_merge_ctx(rq->hw_context, last->hw_context)) { /* * If we are on the second port and cannot * combine this request with the last, then we @@ -690,14 +700,14 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine) * the same context (even though a different * request) to the second port. */ - if (ctx_single_port_submission(last->ctx) || - ctx_single_port_submission(rq->ctx)) { + if (ctx_single_port_submission(last->hw_context) || + ctx_single_port_submission(rq->hw_context)) { __list_del_many(&p->requests, &rq->sched.link); goto done; } - GEM_BUG_ON(last->ctx == rq->ctx); + GEM_BUG_ON(last->hw_context == rq->hw_context); if (submit) port_assign(port, last); @@ -947,34 +957,14 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) local_irq_restore(flags); } -/* - * Check the unread Context Status Buffers and manage the submission of new - * contexts to the ELSP accordingly. - */ -static void execlists_submission_tasklet(unsigned long data) +static void process_csb(struct intel_engine_cs *engine) { - struct intel_engine_cs * const engine = (struct intel_engine_cs *)data; struct intel_engine_execlists * const execlists = &engine->execlists; struct execlist_port *port = execlists->port; - struct drm_i915_private *dev_priv = engine->i915; + struct drm_i915_private *i915 = engine->i915; bool fw = false; - /* - * We can skip acquiring intel_runtime_pm_get() here as it was taken - * on our behalf by the request (see i915_gem_mark_busy()) and it will - * not be relinquished until the device is idle (see - * i915_gem_idle_work_handler()). As a precaution, we make sure - * that all ELSP are drained i.e. we have processed the CSB, - * before allowing ourselves to idle and calling intel_runtime_pm_put(). - */ - GEM_BUG_ON(!dev_priv->gt.awake); - - /* - * Prefer doing test_and_clear_bit() as a two stage operation to avoid - * imposing the cost of a locked atomic transaction when submitting a - * new request (outside of the context-switch interrupt). - */ - while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) { + do { /* The HWSP contains a (cacheable) mirror of the CSB */ const u32 *buf = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX]; @@ -982,28 +972,27 @@ static void execlists_submission_tasklet(unsigned long data) if (unlikely(execlists->csb_use_mmio)) { buf = (u32 * __force) - (dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0))); - execlists->csb_head = -1; /* force mmio read of CSB ptrs */ + (i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0))); + execlists->csb_head = -1; /* force mmio read of CSB */ } /* Clear before reading to catch new interrupts */ clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); smp_mb__after_atomic(); - if (unlikely(execlists->csb_head == -1)) { /* following a reset */ + if (unlikely(execlists->csb_head == -1)) { /* after a reset */ if (!fw) { - intel_uncore_forcewake_get(dev_priv, - execlists->fw_domains); + intel_uncore_forcewake_get(i915, execlists->fw_domains); fw = true; } - head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine))); + head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine))); tail = GEN8_CSB_WRITE_PTR(head); head = GEN8_CSB_READ_PTR(head); execlists->csb_head = head; } else { const int write_idx = - intel_hws_csb_write_index(dev_priv) - + intel_hws_csb_write_index(i915) - I915_HWS_CSB_BUF0_INDEX; head = execlists->csb_head; @@ -1012,8 +1001,8 @@ static void execlists_submission_tasklet(unsigned long data) } GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n", engine->name, - head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?", - tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?"); + head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?", + tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?"); while (head != tail) { struct i915_request *rq; @@ -1023,7 +1012,8 @@ static void execlists_submission_tasklet(unsigned long data) if (++head == GEN8_CSB_ENTRIES) head = 0; - /* We are flying near dragons again. + /* + * We are flying near dragons again. * * We hold a reference to the request in execlist_port[] * but no more than that. We are operating in softirq @@ -1063,14 +1053,7 @@ static void execlists_submission_tasklet(unsigned long data) if (status & GEN8_CTX_STATUS_COMPLETE && buf[2*head + 1] == execlists->preempt_complete_status) { GEM_TRACE("%s preempt-idle\n", engine->name); - - execlists_cancel_port_requests(execlists); - execlists_unwind_incomplete_requests(execlists); - - GEM_BUG_ON(!execlists_is_active(execlists, - EXECLISTS_ACTIVE_PREEMPT)); - execlists_clear_active(execlists, - EXECLISTS_ACTIVE_PREEMPT); + complete_preempt_context(execlists); continue; } @@ -1139,15 +1122,48 @@ static void execlists_submission_tasklet(unsigned long data) if (head != execlists->csb_head) { execlists->csb_head = head; writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8), - dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine))); + i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine))); } - } + } while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)); - if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)) - execlists_dequeue(engine); + if (unlikely(fw)) + intel_uncore_forcewake_put(i915, execlists->fw_domains); +} + +/* + * Check the unread Context Status Buffers and manage the submission of new + * contexts to the ELSP accordingly. + */ +static void execlists_submission_tasklet(unsigned long data) +{ + struct intel_engine_cs * const engine = (struct intel_engine_cs *)data; + + GEM_TRACE("%s awake?=%d, active=%x, irq-posted?=%d\n", + engine->name, + engine->i915->gt.awake, + engine->execlists.active, + test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)); + + /* + * We can skip acquiring intel_runtime_pm_get() here as it was taken + * on our behalf by the request (see i915_gem_mark_busy()) and it will + * not be relinquished until the device is idle (see + * i915_gem_idle_work_handler()). As a precaution, we make sure + * that all ELSP are drained i.e. we have processed the CSB, + * before allowing ourselves to idle and calling intel_runtime_pm_put(). + */ + GEM_BUG_ON(!engine->i915->gt.awake); - if (fw) - intel_uncore_forcewake_put(dev_priv, execlists->fw_domains); + /* + * Prefer doing test_and_clear_bit() as a two stage operation to avoid + * imposing the cost of a locked atomic transaction when submitting a + * new request (outside of the context-switch interrupt). + */ + if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) + process_csb(engine); + + if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT)) + execlists_dequeue(engine); /* If the engine is now idle, so should be the flag; and vice versa. */ GEM_BUG_ON(execlists_is_active(&engine->execlists, @@ -1322,6 +1338,26 @@ static void execlists_schedule(struct i915_request *request, spin_unlock_irq(&engine->timeline.lock); } +static void execlists_context_destroy(struct intel_context *ce) +{ + GEM_BUG_ON(!ce->state); + GEM_BUG_ON(ce->pin_count); + + intel_ring_free(ce->ring); + __i915_gem_object_release_unless_active(ce->state->obj); +} + +static void execlists_context_unpin(struct intel_context *ce) +{ + intel_ring_unpin(ce->ring); + + ce->state->obj->pin_global--; + i915_gem_object_unpin_map(ce->state->obj); + i915_vma_unpin(ce->state); + + i915_gem_context_put(ce->gem_context); +} + static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma) { unsigned int flags; @@ -1345,21 +1381,15 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma) return i915_vma_pin(vma, 0, GEN8_LR_CONTEXT_ALIGN, flags); } -static struct intel_ring * -execlists_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static struct intel_context * +__execlists_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx, + struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); void *vaddr; int ret; - lockdep_assert_held(&ctx->i915->drm.struct_mutex); - - if (likely(ce->pin_count++)) - goto out; - GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ - - ret = execlists_context_deferred_alloc(ctx, engine); + ret = execlists_context_deferred_alloc(ctx, engine, ce); if (ret) goto err; GEM_BUG_ON(!ce->state); @@ -1378,7 +1408,7 @@ execlists_context_pin(struct intel_engine_cs *engine, if (ret) goto unpin_map; - intel_lr_context_descriptor_update(ctx, engine); + intel_lr_context_descriptor_update(ctx, engine, ce); ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; ce->lrc_reg_state[CTX_RING_BUFFER_START+1] = @@ -1387,8 +1417,7 @@ execlists_context_pin(struct intel_engine_cs *engine, ce->state->obj->pin_global++; i915_gem_context_get(ctx); -out: - return ce->ring; + return ce; unpin_map: i915_gem_object_unpin_map(ce->state->obj); @@ -1399,33 +1428,33 @@ err: return ERR_PTR(ret); } -static void execlists_context_unpin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static const struct intel_context_ops execlists_context_ops = { + .unpin = execlists_context_unpin, + .destroy = execlists_context_destroy, +}; + +static struct intel_context * +execlists_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { struct intel_context *ce = to_intel_context(ctx, engine); lockdep_assert_held(&ctx->i915->drm.struct_mutex); - GEM_BUG_ON(ce->pin_count == 0); - if (--ce->pin_count) - return; - - intel_ring_unpin(ce->ring); + if (likely(ce->pin_count++)) + return ce; + GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ - ce->state->obj->pin_global--; - i915_gem_object_unpin_map(ce->state->obj); - i915_vma_unpin(ce->state); + ce->ops = &execlists_context_ops; - i915_gem_context_put(ctx); + return __execlists_context_pin(engine, ctx, ce); } static int execlists_request_alloc(struct i915_request *request) { - struct intel_context *ce = - to_intel_context(request->ctx, request->engine); int ret; - GEM_BUG_ON(!ce->pin_count); + GEM_BUG_ON(!request->hw_context->pin_count); /* Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just @@ -1642,7 +1671,7 @@ static int lrc_setup_wa_ctx(struct intel_engine_cs *engine) if (IS_ERR(obj)) return PTR_ERR(obj); - vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; @@ -1757,12 +1786,25 @@ static void enable_execlists(struct intel_engine_cs *engine) I915_WRITE(RING_MODE_GEN7(engine), _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)); + I915_WRITE(RING_MI_MODE(engine->mmio_base), + _MASKED_BIT_DISABLE(STOP_RING)); + I915_WRITE(RING_HWS_PGA(engine->mmio_base), engine->status_page.ggtt_offset); POSTING_READ(RING_HWS_PGA(engine->mmio_base)); +} - /* Following the reset, we need to reload the CSB read/write pointers */ - engine->execlists.csb_head = -1; +static bool unexpected_starting_state(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + bool unexpected = false; + + if (I915_READ(RING_MI_MODE(engine->mmio_base)) & STOP_RING) { + DRM_DEBUG_DRIVER("STOP_RING still set in RING_MI_MODE\n"); + unexpected = true; + } + + return unexpected; } static int gen8_init_common_ring(struct intel_engine_cs *engine) @@ -1777,6 +1819,12 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) intel_engine_reset_breadcrumbs(engine); intel_engine_init_hangcheck(engine); + if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) { + struct drm_printer p = drm_debug_printer(__func__); + + intel_engine_dump(engine, &p, NULL); + } + enable_execlists(engine); /* After a GPU reset, we may have requests to replay */ @@ -1823,8 +1871,69 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine) return 0; } -static void reset_common_ring(struct intel_engine_cs *engine, - struct i915_request *request) +static struct i915_request * +execlists_reset_prepare(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists * const execlists = &engine->execlists; + struct i915_request *request, *active; + + GEM_TRACE("%s\n", engine->name); + + /* + * Prevent request submission to the hardware until we have + * completed the reset in i915_gem_reset_finish(). If a request + * is completed by one engine, it may then queue a request + * to a second via its execlists->tasklet *just* as we are + * calling engine->init_hw() and also writing the ELSP. + * Turning off the execlists->tasklet until the reset is over + * prevents the race. + */ + __tasklet_disable_sync_once(&execlists->tasklet); + + /* + * We want to flush the pending context switches, having disabled + * the tasklet above, we can assume exclusive access to the execlists. + * For this allows us to catch up with an inflight preemption event, + * and avoid blaming an innocent request if the stall was due to the + * preemption itself. + */ + if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) + process_csb(engine); + + /* + * The last active request can then be no later than the last request + * now in ELSP[0]. So search backwards from there, so that if the GPU + * has advanced beyond the last CSB update, it will be pardoned. + */ + active = NULL; + request = port_request(execlists->port); + if (request) { + unsigned long flags; + + /* + * Prevent the breadcrumb from advancing before we decide + * which request is currently active. + */ + intel_engine_stop_cs(engine); + + spin_lock_irqsave(&engine->timeline.lock, flags); + list_for_each_entry_from_reverse(request, + &engine->timeline.requests, + link) { + if (__i915_request_completed(request, + request->global_seqno)) + break; + + active = request; + } + spin_unlock_irqrestore(&engine->timeline.lock, flags); + } + + return active; +} + +static void execlists_reset(struct intel_engine_cs *engine, + struct i915_request *request) { struct intel_engine_execlists * const execlists = &engine->execlists; unsigned long flags; @@ -1854,6 +1963,9 @@ static void reset_common_ring(struct intel_engine_cs *engine, __unwind_incomplete_requests(engine); spin_unlock(&engine->timeline.lock); + /* Following the reset, we need to reload the CSB read/write pointers */ + engine->execlists.csb_head = -1; + local_irq_restore(flags); /* @@ -1878,20 +1990,14 @@ static void reset_common_ring(struct intel_engine_cs *engine, * future request will be after userspace has had the opportunity * to recreate its own state. */ - regs = to_intel_context(request->ctx, engine)->lrc_reg_state; - if (engine->default_state) { - void *defaults; - - defaults = i915_gem_object_pin_map(engine->default_state, - I915_MAP_WB); - if (!IS_ERR(defaults)) { - memcpy(regs, /* skip restoring the vanilla PPHWSP */ - defaults + LRC_STATE_PN * PAGE_SIZE, - engine->context_size - PAGE_SIZE); - i915_gem_object_unpin_map(engine->default_state); - } + regs = request->hw_context->lrc_reg_state; + if (engine->pinned_default_state) { + memcpy(regs, /* skip restoring the vanilla PPHWSP */ + engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE, + engine->context_size - PAGE_SIZE); } - execlists_init_reg_state(regs, request->ctx, engine, request->ring); + execlists_init_reg_state(regs, + request->gem_context, engine, request->ring); /* Move the RING_HEAD onto the breadcrumb, past the hanging batch */ regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma); @@ -1904,9 +2010,25 @@ static void reset_common_ring(struct intel_engine_cs *engine, unwind_wa_tail(request); } +static void execlists_reset_finish(struct intel_engine_cs *engine) +{ + /* + * Flush the tasklet while we still have the forcewake to be sure + * that it is not allowed to sleep before we restart and reload a + * context. + * + * As before (with execlists_reset_prepare) we rely on the caller + * serialising multiple attempts to reset so that we know that we + * are the only one manipulating tasklet state. + */ + __tasklet_enable_sync_once(&engine->execlists.tasklet); + + GEM_TRACE("%s\n", engine->name); +} + static int intel_logical_ring_emit_pdps(struct i915_request *rq) { - struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt; + struct i915_hw_ppgtt *ppgtt = rq->gem_context->ppgtt; struct intel_engine_cs *engine = rq->engine; const int num_lri_cmds = GEN8_3LVL_PDPES * 2; u32 *cs; @@ -1945,15 +2067,15 @@ static int gen8_emit_bb_start(struct i915_request *rq, * it is unsafe in case of lite-restore (because the ctx is * not idle). PML4 is allocated during ppgtt init so this is * not needed in 48-bit.*/ - if (rq->ctx->ppgtt && - (intel_engine_flag(rq->engine) & rq->ctx->ppgtt->pd_dirty_rings) && - !i915_vm_is_48bit(&rq->ctx->ppgtt->base) && + if (rq->gem_context->ppgtt && + (intel_engine_flag(rq->engine) & rq->gem_context->ppgtt->pd_dirty_rings) && + !i915_vm_is_48bit(&rq->gem_context->ppgtt->vm) && !intel_vgpu_active(rq->i915)) { ret = intel_logical_ring_emit_pdps(rq); if (ret) return ret; - rq->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine); + rq->gem_context->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine); } cs = intel_ring_begin(rq, 6); @@ -2214,6 +2336,8 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine) engine->schedule = execlists_schedule; engine->execlists.tasklet.func = execlists_submission_tasklet; + engine->reset.prepare = execlists_reset_prepare; + engine->park = NULL; engine->unpark = NULL; @@ -2233,11 +2357,12 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) { /* Default vfuncs which can be overriden by each engine. */ engine->init_hw = gen8_init_common_ring; - engine->reset_hw = reset_common_ring; - engine->context_pin = execlists_context_pin; - engine->context_unpin = execlists_context_unpin; + engine->reset.prepare = execlists_reset_prepare; + engine->reset.reset = execlists_reset; + engine->reset.finish = execlists_reset_finish; + engine->context_pin = execlists_context_pin; engine->request_alloc = execlists_request_alloc; engine->emit_flush = gen8_emit_flush; @@ -2340,6 +2465,8 @@ static int logical_ring_init(struct intel_engine_cs *engine) upper_32_bits(ce->lrc_desc); } + engine->execlists.csb_head = -1; + return 0; error: @@ -2472,7 +2599,7 @@ static void execlists_init_reg_state(u32 *regs, struct drm_i915_private *dev_priv = engine->i915; struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: dev_priv->mm.aliasing_ppgtt; u32 base = engine->mmio_base; - bool rcs = engine->id == RCS; + bool rcs = engine->class == RENDER_CLASS; /* A context is actually a big batch buffer with several * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The @@ -2540,7 +2667,7 @@ static void execlists_init_reg_state(u32 *regs, CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(engine, 0), 0); CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(engine, 0), 0); - if (ppgtt && i915_vm_is_48bit(&ppgtt->base)) { + if (ppgtt && i915_vm_is_48bit(&ppgtt->vm)) { /* 64b PPGTT (48bit canonical) * PDP0_DESCRIPTOR contains the base address to PML4 and * other PDP Descriptors are ignored. @@ -2619,10 +2746,10 @@ err_unpin_ctx: } static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) + struct intel_engine_cs *engine, + struct intel_context *ce) { struct drm_i915_gem_object *ctx_obj; - struct intel_context *ce = to_intel_context(ctx, engine); struct i915_vma *vma; uint32_t context_size; struct intel_ring *ring; @@ -2646,7 +2773,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, goto error_deref_obj; } - vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL); + vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto error_deref_obj; diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 4ec7d8dd13c8..1593194e930c 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -104,11 +104,4 @@ struct i915_gem_context; void intel_lr_context_resume(struct drm_i915_private *dev_priv); -static inline uint64_t -intel_lr_context_descriptor(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) -{ - return to_intel_context(ctx, engine)->lrc_desc; -} - #endif /* _INTEL_LRC_H_ */ diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index d278f24ba6ae..e05c12e7629c 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -85,34 +85,35 @@ static struct intel_lvds_connector *to_lvds_connector(struct drm_connector *conn return container_of(connector, struct intel_lvds_connector, base.base); } +bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t lvds_reg, enum pipe *pipe) +{ + u32 val; + + val = I915_READ(lvds_reg); + + /* asserts want to know the pipe even if the port is disabled */ + if (HAS_PCH_CPT(dev_priv)) + *pipe = (val & LVDS_PIPE_SEL_MASK_CPT) >> LVDS_PIPE_SEL_SHIFT_CPT; + else + *pipe = (val & LVDS_PIPE_SEL_MASK) >> LVDS_PIPE_SEL_SHIFT; + + return val & LVDS_PORT_EN; +} + static bool intel_lvds_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); - u32 tmp; bool ret; if (!intel_display_power_get_if_enabled(dev_priv, encoder->power_domain)) return false; - ret = false; - - tmp = I915_READ(lvds_encoder->reg); - - if (!(tmp & LVDS_PORT_EN)) - goto out; + ret = intel_lvds_port_enabled(dev_priv, lvds_encoder->reg, pipe); - if (HAS_PCH_CPT(dev_priv)) - *pipe = PORT_TO_PIPE_CPT(tmp); - else - *pipe = PORT_TO_PIPE(tmp); - - ret = true; - -out: intel_display_power_put(dev_priv, encoder->power_domain); return ret; @@ -255,14 +256,11 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder, temp |= LVDS_PORT_EN | LVDS_A0A2_CLKA_POWER_UP; if (HAS_PCH_CPT(dev_priv)) { - temp &= ~PORT_TRANS_SEL_MASK; - temp |= PORT_TRANS_SEL_CPT(pipe); + temp &= ~LVDS_PIPE_SEL_MASK_CPT; + temp |= LVDS_PIPE_SEL_CPT(pipe); } else { - if (pipe == 1) { - temp |= LVDS_PIPEB_SELECT; - } else { - temp &= ~LVDS_PIPEB_SELECT; - } + temp &= ~LVDS_PIPE_SEL_MASK; + temp |= LVDS_PIPE_SEL(pipe); } /* set the corresponsding LVDS_BORDER bit */ @@ -943,7 +941,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder) * register is uninitialized. */ val = I915_READ(lvds_encoder->reg); - if (!(val & ~(LVDS_PIPE_MASK | LVDS_DETECTED))) + if (HAS_PCH_CPT(dev_priv)) + val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK_CPT); + else + val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK); + if (val == 0) val = dev_priv->vbt.bios_lvds_val; return (val & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP; @@ -998,8 +1000,16 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) return; /* Skip init on machines we know falsely report LVDS */ - if (dmi_check_system(intel_no_lvds)) + if (dmi_check_system(intel_no_lvds)) { + WARN(!dev_priv->vbt.int_lvds_support, + "Useless DMI match. Internal LVDS support disabled by VBT\n"); return; + } + + if (!dev_priv->vbt.int_lvds_support) { + DRM_DEBUG_KMS("Internal LVDS support disabled by VBT\n"); + return; + } if (HAS_PCH_SPLIT(dev_priv)) lvds_reg = PCH_LVDS; @@ -1011,10 +1021,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) if (HAS_PCH_SPLIT(dev_priv)) { if ((lvds & LVDS_DETECTED) == 0) return; - if (dev_priv->vbt.edp.support) { - DRM_DEBUG_KMS("disable LVDS for eDP support\n"); - return; - } } pin = GMBUS_PIN_PANEL; diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index db27f2faa1de..71dfe541740f 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -97,10 +97,6 @@ void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug) { u32 debug_mask, mask; - /* No PSR interrupts on VLV/CHV */ - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - return; - mask = EDP_PSR_ERROR(TRANSCODER_EDP); debug_mask = EDP_PSR_POST_EXIT(TRANSCODER_EDP) | EDP_PSR_PRE_ENTRY(TRANSCODER_EDP); @@ -201,15 +197,6 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) } } -static bool intel_dp_get_y_coord_required(struct intel_dp *intel_dp) -{ - uint8_t psr_caps = 0; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_CAPS, &psr_caps) != 1) - return false; - return psr_caps & DP_PSR2_SU_Y_COORDINATE_REQUIRED; -} - static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) { uint8_t dprx = 0; @@ -232,13 +219,13 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp) static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp) { - u8 val = 0; + u8 val = 8; /* assume the worst if we can't read the value */ if (drm_dp_dpcd_readb(&intel_dp->aux, DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1) val &= DP_MAX_RESYNC_FRAME_COUNT_MASK; else - DRM_ERROR("Unable to get sink synchronization latency\n"); + DRM_DEBUG_KMS("Unable to get sink synchronization latency, assuming 8 frames\n"); return val; } @@ -250,13 +237,25 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp) drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd, sizeof(intel_dp->psr_dpcd)); - if (intel_dp->psr_dpcd[0]) { - dev_priv->psr.sink_support = true; - DRM_DEBUG_KMS("Detected EDP PSR Panel.\n"); + if (!intel_dp->psr_dpcd[0]) + return; + DRM_DEBUG_KMS("eDP panel supports PSR version %x\n", + intel_dp->psr_dpcd[0]); + + if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) { + DRM_DEBUG_KMS("Panel lacks power state control, PSR cannot be enabled\n"); + return; } + dev_priv->psr.sink_support = true; + dev_priv->psr.sink_sync_latency = + intel_dp_get_sink_sync_latency(intel_dp); if (INTEL_GEN(dev_priv) >= 9 && (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) { + bool y_req = intel_dp->psr_dpcd[1] & + DP_PSR2_SU_Y_COORDINATE_REQUIRED; + bool alpm = intel_dp_get_alpm_status(intel_dp); + /* * All panels that supports PSR version 03h (PSR2 + * Y-coordinate) can handle Y-coordinates in VSC but we are @@ -268,47 +267,17 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp) * Y-coordinate requirement panels we would need to enable * GTC first. */ - dev_priv->psr.sink_psr2_support = - intel_dp_get_y_coord_required(intel_dp); - DRM_DEBUG_KMS("PSR2 %s on sink", dev_priv->psr.sink_psr2_support - ? "supported" : "not supported"); + dev_priv->psr.sink_psr2_support = y_req && alpm; + DRM_DEBUG_KMS("PSR2 %ssupported\n", + dev_priv->psr.sink_psr2_support ? "" : "not "); if (dev_priv->psr.sink_psr2_support) { dev_priv->psr.colorimetry_support = intel_dp_get_colorimetry_status(intel_dp); - dev_priv->psr.alpm = - intel_dp_get_alpm_status(intel_dp); - dev_priv->psr.sink_sync_latency = - intel_dp_get_sink_sync_latency(intel_dp); } } } -static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe) -{ - struct drm_i915_private *dev_priv = to_i915(dev); - uint32_t val; - - val = I915_READ(VLV_PSRSTAT(pipe)) & - VLV_EDP_PSR_CURR_STATE_MASK; - return (val == VLV_EDP_PSR_ACTIVE_NORFB_UP) || - (val == VLV_EDP_PSR_ACTIVE_SF_UPDATE); -} - -static void vlv_psr_setup_vsc(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - uint32_t val; - - /* VLV auto-generate VSC package as per EDP 1.3 spec, Table 3.10 */ - val = I915_READ(VLV_VSCSDP(crtc->pipe)); - val &= ~VLV_EDP_PSR_SDP_FREQ_MASK; - val |= VLV_EDP_PSR_SDP_FREQ_EVFRAME; - I915_WRITE(VLV_VSCSDP(crtc->pipe), val); -} - static void hsw_psr_setup_vsc(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { @@ -341,12 +310,6 @@ static void hsw_psr_setup_vsc(struct intel_dp *intel_dp, DP_SDP_VSC, &psr_vsc, sizeof(psr_vsc)); } -static void vlv_psr_enable_sink(struct intel_dp *intel_dp) -{ - drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, - DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE); -} - static void hsw_psr_setup_aux(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); @@ -389,13 +352,12 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp) u8 dpcd_val = DP_PSR_ENABLE; /* Enable ALPM at sink for psr2 */ - if (dev_priv->psr.psr2_enabled && dev_priv->psr.alpm) - drm_dp_dpcd_writeb(&intel_dp->aux, - DP_RECEIVER_ALPM_CONFIG, - DP_ALPM_ENABLE); - - if (dev_priv->psr.psr2_enabled) + if (dev_priv->psr.psr2_enabled) { + drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG, + DP_ALPM_ENABLE); dpcd_val |= DP_PSR_ENABLE_PSR2; + } + if (dev_priv->psr.link_standby) dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE; drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val); @@ -403,81 +365,49 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp) drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0); } -static void vlv_psr_enable_source(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - - /* Transition from PSR_state 0 (disabled) to PSR_state 1 (inactive) */ - I915_WRITE(VLV_PSRCTL(crtc->pipe), - VLV_EDP_PSR_MODE_SW_TIMER | - VLV_EDP_PSR_SRC_TRANSMITTER_STATE | - VLV_EDP_PSR_ENABLE); -} - -static void vlv_psr_activate(struct intel_dp *intel_dp) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = dig_port->base.base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct drm_crtc *crtc = dig_port->base.base.crtc; - enum pipe pipe = to_intel_crtc(crtc)->pipe; - - /* - * Let's do the transition from PSR_state 1 (inactive) to - * PSR_state 2 (transition to active - static frame transmission). - * Then Hardware is responsible for the transition to - * PSR_state 3 (active - no Remote Frame Buffer (RFB) update). - */ - I915_WRITE(VLV_PSRCTL(pipe), I915_READ(VLV_PSRCTL(pipe)) | - VLV_EDP_PSR_ACTIVE_ENTRY); -} - static void hsw_activate_psr1(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_device *dev = dig_port->base.base.dev; struct drm_i915_private *dev_priv = to_i915(dev); + u32 max_sleep_time = 0x1f; + u32 val = EDP_PSR_ENABLE; - uint32_t max_sleep_time = 0x1f; - /* - * Let's respect VBT in case VBT asks a higher idle_frame value. - * Let's use 6 as the minimum to cover all known cases including - * the off-by-one issue that HW has in some cases. Also there are - * cases where sink should be able to train - * with the 5 or 6 idle patterns. + /* Let's use 6 as the minimum to cover all known cases including the + * off-by-one issue that HW has in some cases. */ - uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames); - uint32_t val = EDP_PSR_ENABLE; + int idle_frames = max(6, dev_priv->vbt.psr.idle_frames); - val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT; + /* sink_sync_latency of 8 means source has to wait for more than 8 + * frames, we'll go with 9 frames for now + */ + idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1); val |= idle_frames << EDP_PSR_IDLE_FRAME_SHIFT; + val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT; if (IS_HASWELL(dev_priv)) val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES; if (dev_priv->psr.link_standby) val |= EDP_PSR_LINK_STANDBY; - if (dev_priv->vbt.psr.tp1_wakeup_time > 5) - val |= EDP_PSR_TP1_TIME_2500us; - else if (dev_priv->vbt.psr.tp1_wakeup_time > 1) - val |= EDP_PSR_TP1_TIME_500us; - else if (dev_priv->vbt.psr.tp1_wakeup_time > 0) + if (dev_priv->vbt.psr.tp1_wakeup_time_us == 0) + val |= EDP_PSR_TP1_TIME_0us; + else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 100) val |= EDP_PSR_TP1_TIME_100us; + else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 500) + val |= EDP_PSR_TP1_TIME_500us; else - val |= EDP_PSR_TP1_TIME_0us; + val |= EDP_PSR_TP1_TIME_2500us; - if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5) - val |= EDP_PSR_TP2_TP3_TIME_2500us; - else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1) - val |= EDP_PSR_TP2_TP3_TIME_500us; - else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0) + if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us == 0) + val |= EDP_PSR_TP2_TP3_TIME_0us; + else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100) val |= EDP_PSR_TP2_TP3_TIME_100us; + else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500) + val |= EDP_PSR_TP2_TP3_TIME_500us; else - val |= EDP_PSR_TP2_TP3_TIME_0us; + val |= EDP_PSR_TP2_TP3_TIME_2500us; if (intel_dp_source_supports_hbr2(intel_dp) && drm_dp_tps3_supported(intel_dp->dpcd)) @@ -494,15 +424,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_device *dev = dig_port->base.base.dev; struct drm_i915_private *dev_priv = to_i915(dev); - /* - * Let's respect VBT in case VBT asks a higher idle_frame value. - * Let's use 6 as the minimum to cover all known cases including - * the off-by-one issue that HW has in some cases. Also there are - * cases where sink should be able to train - * with the 5 or 6 idle patterns. + u32 val; + + /* Let's use 6 as the minimum to cover all known cases including the + * off-by-one issue that HW has in some cases. */ - uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames); - u32 val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT; + int idle_frames = max(6, dev_priv->vbt.psr.idle_frames); + + idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1); + val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT; /* FIXME: selective update is probably totally broken because it doesn't * mesh at all with our frontbuffer tracking. And the hw alone isn't @@ -513,14 +443,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) val |= EDP_PSR2_FRAME_BEFORE_SU(dev_priv->psr.sink_sync_latency + 1); - if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5) - val |= EDP_PSR2_TP2_TIME_2500; - else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1) - val |= EDP_PSR2_TP2_TIME_500; - else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0) - val |= EDP_PSR2_TP2_TIME_100; + if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us >= 0 && + dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 50) + val |= EDP_PSR2_TP2_TIME_50us; + else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100) + val |= EDP_PSR2_TP2_TIME_100us; + else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500) + val |= EDP_PSR2_TP2_TIME_500us; else - val |= EDP_PSR2_TP2_TIME_50; + val |= EDP_PSR2_TP2_TIME_2500us; I915_WRITE(EDP_PSR2_CTL, val); } @@ -602,17 +533,11 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, * ones. Since by Display design transcoder EDP is tied to port A * we can safely escape based on the port A. */ - if (HAS_DDI(dev_priv) && dig_port->base.port != PORT_A) { + if (dig_port->base.port != PORT_A) { DRM_DEBUG_KMS("PSR condition failed: Port not supported\n"); return; } - if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && - !dev_priv->psr.link_standby) { - DRM_ERROR("PSR condition failed: Link off requested but not supported on this platform\n"); - return; - } - if (IS_HASWELL(dev_priv) && I915_READ(HSW_STEREO_3D_CTL(crtc_state->cpu_transcoder)) & S3D_ENABLE) { @@ -640,11 +565,6 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, return; } - if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) { - DRM_DEBUG_KMS("PSR condition failed: panel lacks power state control\n"); - return; - } - crtc_state->has_psr = true; crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state); DRM_DEBUG_KMS("Enabling PSR%s\n", crtc_state->has_psr2 ? "2" : ""); @@ -760,7 +680,6 @@ void intel_psr_enable(struct intel_dp *intel_dp, * enabled. * However on some platforms we face issues when first * activation follows a modeset so quickly. - * - On VLV/CHV we get bank screen on first activation * - On HSW/BDW we get a recoverable frozen screen until * next exit-activate sequence. */ @@ -772,36 +691,6 @@ unlock: mutex_unlock(&dev_priv->psr.lock); } -static void vlv_psr_disable(struct intel_dp *intel_dp, - const struct intel_crtc_state *old_crtc_state) -{ - struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = intel_dig_port->base.base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc); - uint32_t val; - - if (dev_priv->psr.active) { - /* Put VLV PSR back to PSR_state 0 (disabled). */ - if (intel_wait_for_register(dev_priv, - VLV_PSRSTAT(crtc->pipe), - VLV_EDP_PSR_IN_TRANS, - 0, - 1)) - WARN(1, "PSR transition took longer than expected\n"); - - val = I915_READ(VLV_PSRCTL(crtc->pipe)); - val &= ~VLV_EDP_PSR_ACTIVE_ENTRY; - val &= ~VLV_EDP_PSR_ENABLE; - val &= ~VLV_EDP_PSR_MODE_MASK; - I915_WRITE(VLV_PSRCTL(crtc->pipe), val); - - dev_priv->psr.active = false; - } else { - WARN_ON(vlv_is_psr_active_on_pipe(dev, crtc->pipe)); - } -} - static void hsw_psr_disable(struct intel_dp *intel_dp, const struct intel_crtc_state *old_crtc_state) { @@ -894,21 +783,12 @@ static bool psr_wait_for_idle(struct drm_i915_private *dev_priv) if (!intel_dp) return false; - if (HAS_DDI(dev_priv)) { - if (dev_priv->psr.psr2_enabled) { - reg = EDP_PSR2_STATUS; - mask = EDP_PSR2_STATUS_STATE_MASK; - } else { - reg = EDP_PSR_STATUS; - mask = EDP_PSR_STATUS_STATE_MASK; - } + if (dev_priv->psr.psr2_enabled) { + reg = EDP_PSR2_STATUS; + mask = EDP_PSR2_STATUS_STATE_MASK; } else { - struct drm_crtc *crtc = - dp_to_dig_port(intel_dp)->base.base.crtc; - enum pipe pipe = to_intel_crtc(crtc)->pipe; - - reg = VLV_PSRSTAT(pipe); - mask = VLV_EDP_PSR_IN_TRANS; + reg = EDP_PSR_STATUS; + mask = EDP_PSR_STATUS_STATE_MASK; } mutex_unlock(&dev_priv->psr.lock); @@ -953,103 +833,24 @@ unlock: static void intel_psr_exit(struct drm_i915_private *dev_priv) { - struct intel_dp *intel_dp = dev_priv->psr.enabled; - struct drm_crtc *crtc = dp_to_dig_port(intel_dp)->base.base.crtc; - enum pipe pipe = to_intel_crtc(crtc)->pipe; u32 val; if (!dev_priv->psr.active) return; - if (HAS_DDI(dev_priv)) { - if (dev_priv->psr.psr2_enabled) { - val = I915_READ(EDP_PSR2_CTL); - WARN_ON(!(val & EDP_PSR2_ENABLE)); - I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE); - } else { - val = I915_READ(EDP_PSR_CTL); - WARN_ON(!(val & EDP_PSR_ENABLE)); - I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE); - } + if (dev_priv->psr.psr2_enabled) { + val = I915_READ(EDP_PSR2_CTL); + WARN_ON(!(val & EDP_PSR2_ENABLE)); + I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE); } else { - val = I915_READ(VLV_PSRCTL(pipe)); - - /* - * Here we do the transition drirectly from - * PSR_state 3 (active - no Remote Frame Buffer (RFB) update) to - * PSR_state 5 (exit). - * PSR State 4 (active with single frame update) can be skipped. - * On PSR_state 5 (exit) Hardware is responsible to transition - * back to PSR_state 1 (inactive). - * Now we are at Same state after vlv_psr_enable_source. - */ - val &= ~VLV_EDP_PSR_ACTIVE_ENTRY; - I915_WRITE(VLV_PSRCTL(pipe), val); - - /* - * Send AUX wake up - Spec says after transitioning to PSR - * active we have to send AUX wake up by writing 01h in DPCD - * 600h of sink device. - * XXX: This might slow down the transition, but without this - * HW doesn't complete the transition to PSR_state 1 and we - * never get the screen updated. - */ - drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, - DP_SET_POWER_D0); + val = I915_READ(EDP_PSR_CTL); + WARN_ON(!(val & EDP_PSR_ENABLE)); + I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE); } - dev_priv->psr.active = false; } /** - * intel_psr_single_frame_update - Single Frame Update - * @dev_priv: i915 device - * @frontbuffer_bits: frontbuffer plane tracking bits - * - * Some platforms support a single frame update feature that is used to - * send and update only one frame on Remote Frame Buffer. - * So far it is only implemented for Valleyview and Cherryview because - * hardware requires this to be done before a page flip. - */ -void intel_psr_single_frame_update(struct drm_i915_private *dev_priv, - unsigned frontbuffer_bits) -{ - struct drm_crtc *crtc; - enum pipe pipe; - u32 val; - - if (!CAN_PSR(dev_priv)) - return; - - /* - * Single frame update is already supported on BDW+ but it requires - * many W/A and it isn't really needed. - */ - if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) - return; - - mutex_lock(&dev_priv->psr.lock); - if (!dev_priv->psr.enabled) { - mutex_unlock(&dev_priv->psr.lock); - return; - } - - crtc = dp_to_dig_port(dev_priv->psr.enabled)->base.base.crtc; - pipe = to_intel_crtc(crtc)->pipe; - - if (frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)) { - val = I915_READ(VLV_PSRCTL(pipe)); - - /* - * We need to set this bit before writing registers for a flip. - * This bit will be self-clear when it gets to the PSR active state. - */ - I915_WRITE(VLV_PSRCTL(pipe), val | VLV_EDP_PSR_SINGLE_FRAME_UPDATE); - } - mutex_unlock(&dev_priv->psr.lock); -} - -/** * intel_psr_invalidate - Invalidade PSR * @dev_priv: i915 device * @frontbuffer_bits: frontbuffer plane tracking bits @@ -1071,7 +872,7 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv, if (!CAN_PSR(dev_priv)) return; - if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP) + if (origin == ORIGIN_FLIP) return; mutex_lock(&dev_priv->psr.lock); @@ -1114,7 +915,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, if (!CAN_PSR(dev_priv)) return; - if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP) + if (origin == ORIGIN_FLIP) return; mutex_lock(&dev_priv->psr.lock); @@ -1131,8 +932,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, /* By definition flush = invalidate + flush */ if (frontbuffer_bits) { - if (dev_priv->psr.psr2_enabled || - IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { + if (dev_priv->psr.psr2_enabled) { intel_psr_exit(dev_priv); } else { /* @@ -1184,9 +984,6 @@ void intel_psr_init(struct drm_i915_private *dev_priv) if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) /* HSW and BDW require workarounds that we don't implement. */ dev_priv->psr.link_standby = false; - else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - /* On VLV and CHV only standby mode is supported. */ - dev_priv->psr.link_standby = true; else /* For new platforms let's respect VBT back again */ dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link; @@ -1204,18 +1001,10 @@ void intel_psr_init(struct drm_i915_private *dev_priv) INIT_DELAYED_WORK(&dev_priv->psr.work, intel_psr_work); mutex_init(&dev_priv->psr.lock); - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - dev_priv->psr.enable_source = vlv_psr_enable_source; - dev_priv->psr.disable_source = vlv_psr_disable; - dev_priv->psr.enable_sink = vlv_psr_enable_sink; - dev_priv->psr.activate = vlv_psr_activate; - dev_priv->psr.setup_vsc = vlv_psr_setup_vsc; - } else { - dev_priv->psr.has_hw_tracking = true; - dev_priv->psr.enable_source = hsw_psr_enable_source; - dev_priv->psr.disable_source = hsw_psr_disable; - dev_priv->psr.enable_sink = hsw_psr_enable_sink; - dev_priv->psr.activate = hsw_psr_activate; - dev_priv->psr.setup_vsc = hsw_psr_setup_vsc; - } + dev_priv->psr.enable_source = hsw_psr_enable_source; + dev_priv->psr.disable_source = hsw_psr_disable; + dev_priv->psr.enable_sink = hsw_psr_enable_sink; + dev_priv->psr.activate = hsw_psr_activate; + dev_priv->psr.setup_vsc = hsw_psr_setup_vsc; + } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 8f19349a6055..6496c1d00dbb 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -531,9 +531,22 @@ out: return ret; } -static void reset_ring_common(struct intel_engine_cs *engine, - struct i915_request *request) +static struct i915_request *reset_prepare(struct intel_engine_cs *engine) { + intel_engine_stop_cs(engine); + + if (engine->irq_seqno_barrier) + engine->irq_seqno_barrier(engine); + + return i915_gem_find_active_request(engine); +} + +static void reset_ring(struct intel_engine_cs *engine, + struct i915_request *request) +{ + GEM_TRACE("%s seqno=%x\n", + engine->name, request ? request->global_seqno : 0); + /* * RC6 must be prevented until the reset is complete and the engine * reinitialised. If it occurs in the middle of this sequence, the @@ -558,8 +571,7 @@ static void reset_ring_common(struct intel_engine_cs *engine, */ if (request) { struct drm_i915_private *dev_priv = request->i915; - struct intel_context *ce = to_intel_context(request->ctx, - engine); + struct intel_context *ce = request->hw_context; struct i915_hw_ppgtt *ppgtt; if (ce->state) { @@ -571,7 +583,7 @@ static void reset_ring_common(struct intel_engine_cs *engine, CCID_EN); } - ppgtt = request->ctx->ppgtt ?: engine->i915->mm.aliasing_ppgtt; + ppgtt = request->gem_context->ppgtt ?: engine->i915->mm.aliasing_ppgtt; if (ppgtt) { u32 pd_offset = ppgtt->pd.base.ggtt_offset << 10; @@ -597,6 +609,10 @@ static void reset_ring_common(struct intel_engine_cs *engine, } } +static void reset_finish(struct intel_engine_cs *engine) +{ +} + static int intel_rcs_ctx_init(struct i915_request *rq) { int ret; @@ -1105,7 +1121,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) /* mark ring buffers as read-only from GPU side by default */ obj->gt_ro = 1; - vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL); + vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL); if (IS_ERR(vma)) goto err; @@ -1169,10 +1185,22 @@ intel_ring_free(struct intel_ring *ring) kfree(ring); } -static int context_pin(struct intel_context *ce) +static void intel_ring_context_destroy(struct intel_context *ce) { - struct i915_vma *vma = ce->state; - int ret; + GEM_BUG_ON(ce->pin_count); + + if (ce->state) + __i915_gem_object_release_unless_active(ce->state->obj); +} + +static int __context_pin(struct intel_context *ce) +{ + struct i915_vma *vma; + int err; + + vma = ce->state; + if (!vma) + return 0; /* * Clear this page out of any CPU caches for coherent swap-in/out. @@ -1180,13 +1208,42 @@ static int context_pin(struct intel_context *ce) * on an active context (which by nature is already on the GPU). */ if (!(vma->flags & I915_VMA_GLOBAL_BIND)) { - ret = i915_gem_object_set_to_gtt_domain(vma->obj, true); - if (ret) - return ret; + err = i915_gem_object_set_to_gtt_domain(vma->obj, true); + if (err) + return err; } - return i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT, - PIN_GLOBAL | PIN_HIGH); + err = i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT, + PIN_GLOBAL | PIN_HIGH); + if (err) + return err; + + /* + * And mark is as a globally pinned object to let the shrinker know + * it cannot reclaim the object until we release it. + */ + vma->obj->pin_global++; + + return 0; +} + +static void __context_unpin(struct intel_context *ce) +{ + struct i915_vma *vma; + + vma = ce->state; + if (!vma) + return; + + vma->obj->pin_global--; + i915_vma_unpin(vma); +} + +static void intel_ring_context_unpin(struct intel_context *ce) +{ + __context_unpin(ce); + + i915_gem_context_put(ce->gem_context); } static struct i915_vma * @@ -1243,7 +1300,7 @@ alloc_context_vma(struct intel_engine_cs *engine) i915_gem_object_set_cache_level(obj, I915_CACHE_L3_LLC); } - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err_obj; @@ -1258,67 +1315,62 @@ err_obj: return ERR_PTR(err); } -static struct intel_ring * -intel_ring_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static struct intel_context * +__ring_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx, + struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); - int ret; - - lockdep_assert_held(&ctx->i915->drm.struct_mutex); - - if (likely(ce->pin_count++)) - goto out; - GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ + int err; if (!ce->state && engine->context_size) { struct i915_vma *vma; vma = alloc_context_vma(engine); if (IS_ERR(vma)) { - ret = PTR_ERR(vma); + err = PTR_ERR(vma); goto err; } ce->state = vma; } - if (ce->state) { - ret = context_pin(ce); - if (ret) - goto err; - - ce->state->obj->pin_global++; - } + err = __context_pin(ce); + if (err) + goto err; i915_gem_context_get(ctx); -out: /* One ringbuffer to rule them all */ - return engine->buffer; + GEM_BUG_ON(!engine->buffer); + ce->ring = engine->buffer; + + return ce; err: ce->pin_count = 0; - return ERR_PTR(ret); + return ERR_PTR(err); } -static void intel_ring_context_unpin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static const struct intel_context_ops ring_context_ops = { + .unpin = intel_ring_context_unpin, + .destroy = intel_ring_context_destroy, +}; + +static struct intel_context * +intel_ring_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { struct intel_context *ce = to_intel_context(ctx, engine); lockdep_assert_held(&ctx->i915->drm.struct_mutex); - GEM_BUG_ON(ce->pin_count == 0); - if (--ce->pin_count) - return; + if (likely(ce->pin_count++)) + return ce; + GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ - if (ce->state) { - ce->state->obj->pin_global--; - i915_vma_unpin(ce->state); - } + ce->ops = &ring_context_ops; - i915_gem_context_put(ctx); + return __ring_context_pin(engine, ctx, ce); } static int intel_init_ring_buffer(struct intel_engine_cs *engine) @@ -1329,10 +1381,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) intel_engine_setup_common(engine); - err = intel_engine_init_common(engine); - if (err) - goto err; - timeline = i915_timeline_create(engine->i915, engine->name); if (IS_ERR(timeline)) { err = PTR_ERR(timeline); @@ -1354,8 +1402,14 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) GEM_BUG_ON(engine->buffer); engine->buffer = ring; + err = intel_engine_init_common(engine); + if (err) + goto err_unpin; + return 0; +err_unpin: + intel_ring_unpin(ring); err_ring: intel_ring_free(ring); err: @@ -1441,7 +1495,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) *cs++ = MI_NOOP; *cs++ = MI_SET_CONTEXT; - *cs++ = i915_ggtt_offset(to_intel_context(rq->ctx, engine)->state) | flags; + *cs++ = i915_ggtt_offset(rq->hw_context->state) | flags; /* * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP * WaMiSetContext_Hang:snb,ivb,vlv @@ -1509,7 +1563,7 @@ static int remap_l3(struct i915_request *rq, int slice) static int switch_context(struct i915_request *rq) { struct intel_engine_cs *engine = rq->engine; - struct i915_gem_context *to_ctx = rq->ctx; + struct i915_gem_context *to_ctx = rq->gem_context; struct i915_hw_ppgtt *to_mm = to_ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; struct i915_gem_context *from_ctx = engine->legacy_active_context; @@ -1532,7 +1586,7 @@ static int switch_context(struct i915_request *rq) hw_flags = MI_FORCE_RESTORE; } - if (to_intel_context(to_ctx, engine)->state && + if (rq->hw_context->state && (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) { GEM_BUG_ON(engine->id != RCS); @@ -1580,7 +1634,7 @@ static int ring_request_alloc(struct i915_request *request) { int ret; - GEM_BUG_ON(!to_intel_context(request->ctx, request->engine)->pin_count); + GEM_BUG_ON(!request->hw_context->pin_count); /* Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just @@ -2006,11 +2060,11 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv, intel_ring_init_semaphores(dev_priv, engine); engine->init_hw = init_ring_common; - engine->reset_hw = reset_ring_common; + engine->reset.prepare = reset_prepare; + engine->reset.reset = reset_ring; + engine->reset.finish = reset_finish; engine->context_pin = intel_ring_context_pin; - engine->context_unpin = intel_ring_context_unpin; - engine->request_alloc = ring_request_alloc; engine->emit_breadcrumb = i9xx_emit_breadcrumb; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 010750e8ee44..acef385c4c80 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -342,6 +342,7 @@ struct intel_engine_cs { struct i915_timeline timeline; struct drm_i915_gem_object *default_state; + void *pinned_default_state; atomic_t irq_count; unsigned long irq_posted; @@ -423,18 +424,22 @@ struct intel_engine_cs { void (*irq_disable)(struct intel_engine_cs *engine); int (*init_hw)(struct intel_engine_cs *engine); - void (*reset_hw)(struct intel_engine_cs *engine, - struct i915_request *rq); + + struct { + struct i915_request *(*prepare)(struct intel_engine_cs *engine); + void (*reset)(struct intel_engine_cs *engine, + struct i915_request *rq); + void (*finish)(struct intel_engine_cs *engine); + } reset; void (*park)(struct intel_engine_cs *engine); void (*unpark)(struct intel_engine_cs *engine); void (*set_default_submission)(struct intel_engine_cs *engine); - struct intel_ring *(*context_pin)(struct intel_engine_cs *engine, - struct i915_gem_context *ctx); - void (*context_unpin)(struct intel_engine_cs *engine, - struct i915_gem_context *ctx); + struct intel_context *(*context_pin)(struct intel_engine_cs *engine, + struct i915_gem_context *ctx); + int (*request_alloc)(struct i915_request *rq); int (*init_context)(struct i915_request *rq); @@ -550,7 +555,7 @@ struct intel_engine_cs { * to the kernel context and trash it as the save may not happen * before the hardware is powered down. */ - struct i915_gem_context *last_retired_context; + struct intel_context *last_retired_context; /* We track the current MI_SET_CONTEXT in order to eliminate * redudant context switches. This presumes that requests are not @@ -873,6 +878,8 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine); int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine); +int intel_engine_stop_cs(struct intel_engine_cs *engine); + u64 intel_engine_get_active_head(const struct intel_engine_cs *engine); u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine); @@ -1046,6 +1053,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine); bool intel_engines_are_idle(struct drm_i915_private *dev_priv); bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine); +void intel_engine_lost_context(struct intel_engine_cs *engine); void intel_engines_park(struct drm_i915_private *i915); void intel_engines_unpark(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 25005023c243..a02e4d73c7a4 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1403,27 +1403,37 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector) return false; } +bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv, + i915_reg_t sdvo_reg, enum pipe *pipe) +{ + u32 val; + + val = I915_READ(sdvo_reg); + + /* asserts want to know the pipe even if the port is disabled */ + if (HAS_PCH_CPT(dev_priv)) + *pipe = (val & SDVO_PIPE_SEL_MASK_CPT) >> SDVO_PIPE_SEL_SHIFT_CPT; + else if (IS_CHERRYVIEW(dev_priv)) + *pipe = (val & SDVO_PIPE_SEL_MASK_CHV) >> SDVO_PIPE_SEL_SHIFT_CHV; + else + *pipe = (val & SDVO_PIPE_SEL_MASK) >> SDVO_PIPE_SEL_SHIFT; + + return val & SDVO_ENABLE; +} + static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_sdvo *intel_sdvo = to_sdvo(encoder); u16 active_outputs = 0; - u32 tmp; + bool ret; - tmp = I915_READ(intel_sdvo->sdvo_reg); intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs); - if (!(tmp & SDVO_ENABLE) && (active_outputs == 0)) - return false; - - if (HAS_PCH_CPT(dev_priv)) - *pipe = PORT_TO_PIPE_CPT(tmp); - else - *pipe = PORT_TO_PIPE(tmp); + ret = intel_sdvo_port_enabled(dev_priv, intel_sdvo->sdvo_reg, pipe); - return true; + return ret || active_outputs; } static void intel_sdvo_get_config(struct intel_encoder *encoder, @@ -1550,8 +1560,8 @@ static void intel_disable_sdvo(struct intel_encoder *encoder, intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false); intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); - temp &= ~SDVO_PIPE_B_SELECT; - temp |= SDVO_ENABLE; + temp &= ~SDVO_PIPE_SEL_MASK; + temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A); intel_sdvo_write_sdvox(intel_sdvo, temp); temp &= ~SDVO_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index ee23613f9fd4..d474065ed2dd 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -284,13 +284,35 @@ skl_update_plane(struct intel_plane *plane, /* program plane scaler */ if (plane_state->scaler_id >= 0) { int scaler_id = plane_state->scaler_id; - const struct intel_scaler *scaler; + const struct intel_scaler *scaler = + &crtc_state->scaler_state.scalers[scaler_id]; + u16 y_hphase, uv_rgb_hphase; + u16 y_vphase, uv_rgb_vphase; + + /* TODO: handle sub-pixel coordinates */ + if (fb->format->format == DRM_FORMAT_NV12) { + y_hphase = skl_scaler_calc_phase(1, false); + y_vphase = skl_scaler_calc_phase(1, false); + + /* MPEG2 chroma siting convention */ + uv_rgb_hphase = skl_scaler_calc_phase(2, true); + uv_rgb_vphase = skl_scaler_calc_phase(2, false); + } else { + /* not used */ + y_hphase = 0; + y_vphase = 0; - scaler = &crtc_state->scaler_state.scalers[scaler_id]; + uv_rgb_hphase = skl_scaler_calc_phase(1, false); + uv_rgb_vphase = skl_scaler_calc_phase(1, false); + } I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id), PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode); I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0); + I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id), + PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase)); + I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id), + PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase)); I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y); I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id), ((crtc_w + 1) << 16)|(crtc_h + 1)); @@ -327,19 +349,21 @@ skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) } bool -skl_plane_get_hw_state(struct intel_plane *plane) +skl_plane_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; enum plane_id plane_id = plane->id; - enum pipe pipe = plane->pipe; bool ret; - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(PLANE_CTL(pipe, plane_id)) & PLANE_CTL_ENABLE; + ret = I915_READ(PLANE_CTL(plane->pipe, plane_id)) & PLANE_CTL_ENABLE; + + *pipe = plane->pipe; intel_display_power_put(dev_priv, power_domain); @@ -588,19 +612,21 @@ vlv_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) } static bool -vlv_plane_get_hw_state(struct intel_plane *plane) +vlv_plane_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; enum plane_id plane_id = plane->id; - enum pipe pipe = plane->pipe; bool ret; - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(SPCNTR(pipe, plane_id)) & SP_ENABLE; + ret = I915_READ(SPCNTR(plane->pipe, plane_id)) & SP_ENABLE; + + *pipe = plane->pipe; intel_display_power_put(dev_priv, power_domain); @@ -754,18 +780,20 @@ ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) } static bool -ivb_plane_get_hw_state(struct intel_plane *plane) +ivb_plane_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; - enum pipe pipe = plane->pipe; bool ret; - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(SPRCTL(pipe)) & SPRITE_ENABLE; + ret = I915_READ(SPRCTL(plane->pipe)) & SPRITE_ENABLE; + + *pipe = plane->pipe; intel_display_power_put(dev_priv, power_domain); @@ -910,18 +938,20 @@ g4x_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) } static bool -g4x_plane_get_hw_state(struct intel_plane *plane) +g4x_plane_get_hw_state(struct intel_plane *plane, + enum pipe *pipe) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum intel_display_power_domain power_domain; - enum pipe pipe = plane->pipe; bool ret; - power_domain = POWER_DOMAIN_PIPE(pipe); + power_domain = POWER_DOMAIN_PIPE(plane->pipe); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - ret = I915_READ(DVSCNTR(pipe)) & DVS_ENABLE; + ret = I915_READ(DVSCNTR(plane->pipe)) & DVS_ENABLE; + + *pipe = plane->pipe; intel_display_power_put(dev_priv, power_domain); @@ -1303,8 +1333,8 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier) } static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane, - uint32_t format, - uint64_t modifier) + uint32_t format, + uint64_t modifier) { struct drm_i915_private *dev_priv = to_i915(plane->dev); @@ -1326,14 +1356,14 @@ static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane, } static const struct drm_plane_funcs intel_sprite_plane_funcs = { - .update_plane = drm_atomic_helper_update_plane, - .disable_plane = drm_atomic_helper_disable_plane, - .destroy = intel_plane_destroy, - .atomic_get_property = intel_plane_atomic_get_property, - .atomic_set_property = intel_plane_atomic_set_property, - .atomic_duplicate_state = intel_plane_duplicate_state, - .atomic_destroy_state = intel_plane_destroy_state, - .format_mod_supported = intel_sprite_plane_format_mod_supported, + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .destroy = intel_plane_destroy, + .atomic_get_property = intel_plane_atomic_get_property, + .atomic_set_property = intel_plane_atomic_set_property, + .atomic_duplicate_state = intel_plane_duplicate_state, + .atomic_destroy_state = intel_plane_destroy_state, + .format_mod_supported = intel_sprite_plane_format_mod_supported, }; bool skl_plane_has_ccs(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 885fc3809f7f..99bc2368dda0 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -798,16 +798,12 @@ static struct intel_tv *intel_attached_tv(struct drm_connector *connector) static bool intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); u32 tmp = I915_READ(TV_CTL); - if (!(tmp & TV_ENC_ENABLE)) - return false; + *pipe = (tmp & TV_ENC_PIPE_SEL_MASK) >> TV_ENC_PIPE_SEL_SHIFT; - *pipe = PORT_TO_PIPE(tmp); - - return true; + return tmp & TV_ENC_ENABLE; } static void @@ -1024,8 +1020,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder, break; } - if (intel_crtc->pipe == 1) - tv_ctl |= TV_ENC_PIPEB_SELECT; + tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe); tv_ctl |= tv_mode->oversample; if (tv_mode->progressive) @@ -1149,12 +1144,9 @@ intel_tv_detect_type(struct intel_tv *intel_tv, save_tv_ctl = tv_ctl = I915_READ(TV_CTL); /* Poll for TV detection */ - tv_ctl &= ~(TV_ENC_ENABLE | TV_TEST_MODE_MASK); + tv_ctl &= ~(TV_ENC_ENABLE | TV_ENC_PIPE_SEL_MASK | TV_TEST_MODE_MASK); tv_ctl |= TV_TEST_MODE_MONITOR_DETECT; - if (intel_crtc->pipe == 1) - tv_ctl |= TV_ENC_PIPEB_SELECT; - else - tv_ctl &= ~TV_ENC_PIPEB_SELECT; + tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe); tv_dac &= ~(TVDAC_SENSE_MASK | DAC_A_MASK | DAC_B_MASK | DAC_C_MASK); tv_dac |= (TVDAC_STATE_CHG_EN | diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c index 1cffaf7b5dbe..6a73e81f373b 100644 --- a/drivers/gpu/drm/i915/intel_uc.c +++ b/drivers/gpu/drm/i915/intel_uc.c @@ -50,10 +50,10 @@ static int __intel_uc_reset_hw(struct drm_i915_private *dev_priv) return ret; } -static int __get_platform_enable_guc(struct drm_i915_private *dev_priv) +static int __get_platform_enable_guc(struct drm_i915_private *i915) { - struct intel_uc_fw *guc_fw = &dev_priv->guc.fw; - struct intel_uc_fw *huc_fw = &dev_priv->huc.fw; + struct intel_uc_fw *guc_fw = &i915->guc.fw; + struct intel_uc_fw *huc_fw = &i915->huc.fw; int enable_guc = 0; /* Default is to enable GuC/HuC if we know their firmwares */ @@ -67,11 +67,11 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv) return enable_guc; } -static int __get_default_guc_log_level(struct drm_i915_private *dev_priv) +static int __get_default_guc_log_level(struct drm_i915_private *i915) { int guc_log_level; - if (!HAS_GUC(dev_priv) || !intel_uc_is_using_guc()) + if (!HAS_GUC(i915) || !intel_uc_is_using_guc()) guc_log_level = GUC_LOG_LEVEL_DISABLED; else if (IS_ENABLED(CONFIG_DRM_I915_DEBUG) || IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) @@ -86,7 +86,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv) /** * sanitize_options_early - sanitize uC related modparam options - * @dev_priv: device private + * @i915: device private * * In case of "enable_guc" option this function will attempt to modify * it only if it was initially set to "auto(-1)". Default value for this @@ -101,14 +101,14 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv) * unless GuC is enabled on given platform and the driver is compiled with * debug config when this modparam will default to "enable(1..4)". */ -static void sanitize_options_early(struct drm_i915_private *dev_priv) +static void sanitize_options_early(struct drm_i915_private *i915) { - struct intel_uc_fw *guc_fw = &dev_priv->guc.fw; - struct intel_uc_fw *huc_fw = &dev_priv->huc.fw; + struct intel_uc_fw *guc_fw = &i915->guc.fw; + struct intel_uc_fw *huc_fw = &i915->huc.fw; /* A negative value means "use platform default" */ if (i915_modparams.enable_guc < 0) - i915_modparams.enable_guc = __get_platform_enable_guc(dev_priv); + i915_modparams.enable_guc = __get_platform_enable_guc(i915); DRM_DEBUG_DRIVER("enable_guc=%d (submission:%s huc:%s)\n", i915_modparams.enable_guc, @@ -119,28 +119,28 @@ static void sanitize_options_early(struct drm_i915_private *dev_priv) if (intel_uc_is_using_guc() && !intel_uc_fw_is_selected(guc_fw)) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "enable_guc", i915_modparams.enable_guc, - !HAS_GUC(dev_priv) ? "no GuC hardware" : - "no GuC firmware"); + !HAS_GUC(i915) ? "no GuC hardware" : + "no GuC firmware"); } /* Verify HuC firmware availability */ if (intel_uc_is_using_huc() && !intel_uc_fw_is_selected(huc_fw)) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "enable_guc", i915_modparams.enable_guc, - !HAS_HUC(dev_priv) ? "no HuC hardware" : - "no HuC firmware"); + !HAS_HUC(i915) ? "no HuC hardware" : + "no HuC firmware"); } /* A negative value means "use platform/config default" */ if (i915_modparams.guc_log_level < 0) i915_modparams.guc_log_level = - __get_default_guc_log_level(dev_priv); + __get_default_guc_log_level(i915); if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc()) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "guc_log_level", i915_modparams.guc_log_level, - !HAS_GUC(dev_priv) ? "no GuC hardware" : - "GuC not enabled"); + !HAS_GUC(i915) ? "no GuC hardware" : + "GuC not enabled"); i915_modparams.guc_log_level = 0; } @@ -195,15 +195,14 @@ void intel_uc_cleanup_early(struct drm_i915_private *i915) /** * intel_uc_init_mmio - setup uC MMIO access - * - * @dev_priv: device private + * @i915: device private * * Setup minimal state necessary for MMIO accesses later in the * initialization sequence. */ -void intel_uc_init_mmio(struct drm_i915_private *dev_priv) +void intel_uc_init_mmio(struct drm_i915_private *i915) { - intel_guc_init_send_regs(&dev_priv->guc); + intel_guc_init_send_regs(&i915->guc); } static void guc_capture_load_err_log(struct intel_guc *guc) @@ -225,11 +224,11 @@ static void guc_free_load_err_log(struct intel_guc *guc) static int guc_enable_communication(struct intel_guc *guc) { - struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct drm_i915_private *i915 = guc_to_i915(guc); - gen9_enable_guc_interrupts(dev_priv); + gen9_enable_guc_interrupts(i915); - if (HAS_GUC_CT(dev_priv)) + if (HAS_GUC_CT(i915)) return intel_guc_ct_enable(&guc->ct); guc->send = intel_guc_send_mmio; @@ -239,23 +238,23 @@ static int guc_enable_communication(struct intel_guc *guc) static void guc_disable_communication(struct intel_guc *guc) { - struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct drm_i915_private *i915 = guc_to_i915(guc); - if (HAS_GUC_CT(dev_priv)) + if (HAS_GUC_CT(i915)) intel_guc_ct_disable(&guc->ct); - gen9_disable_guc_interrupts(dev_priv); + gen9_disable_guc_interrupts(i915); guc->send = intel_guc_send_nop; guc->handler = intel_guc_to_host_event_handler_nop; } -int intel_uc_init_misc(struct drm_i915_private *dev_priv) +int intel_uc_init_misc(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; + struct intel_guc *guc = &i915->guc; int ret; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return 0; intel_guc_init_ggtt_pin_bias(guc); @@ -267,32 +266,32 @@ int intel_uc_init_misc(struct drm_i915_private *dev_priv) return 0; } -void intel_uc_fini_misc(struct drm_i915_private *dev_priv) +void intel_uc_fini_misc(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; + struct intel_guc *guc = &i915->guc; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return; intel_guc_fini_wq(guc); } -int intel_uc_init(struct drm_i915_private *dev_priv) +int intel_uc_init(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; + struct intel_guc *guc = &i915->guc; int ret; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return 0; - if (!HAS_GUC(dev_priv)) + if (!HAS_GUC(i915)) return -ENODEV; ret = intel_guc_init(guc); if (ret) return ret; - if (USES_GUC_SUBMISSION(dev_priv)) { + if (USES_GUC_SUBMISSION(i915)) { /* * This is stuff we need to have available at fw load time * if we are planning to enable submission later @@ -307,16 +306,16 @@ int intel_uc_init(struct drm_i915_private *dev_priv) return 0; } -void intel_uc_fini(struct drm_i915_private *dev_priv) +void intel_uc_fini(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; + struct intel_guc *guc = &i915->guc; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return; - GEM_BUG_ON(!HAS_GUC(dev_priv)); + GEM_BUG_ON(!HAS_GUC(i915)); - if (USES_GUC_SUBMISSION(dev_priv)) + if (USES_GUC_SUBMISSION(i915)) intel_guc_submission_fini(guc); intel_guc_fini(guc); @@ -340,22 +339,22 @@ void intel_uc_sanitize(struct drm_i915_private *i915) __intel_uc_reset_hw(i915); } -int intel_uc_init_hw(struct drm_i915_private *dev_priv) +int intel_uc_init_hw(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; - struct intel_huc *huc = &dev_priv->huc; + struct intel_guc *guc = &i915->guc; + struct intel_huc *huc = &i915->huc; int ret, attempts; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return 0; - GEM_BUG_ON(!HAS_GUC(dev_priv)); + GEM_BUG_ON(!HAS_GUC(i915)); - gen9_reset_guc_interrupts(dev_priv); + gen9_reset_guc_interrupts(i915); /* WaEnableuKernelHeaderValidFix:skl */ /* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */ - if (IS_GEN9(dev_priv)) + if (IS_GEN9(i915)) attempts = 3; else attempts = 1; @@ -365,11 +364,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv) * Always reset the GuC just before (re)loading, so * that the state and timing are fairly predictable */ - ret = __intel_uc_reset_hw(dev_priv); + ret = __intel_uc_reset_hw(i915); if (ret) goto err_out; - if (USES_HUC(dev_priv)) { + if (USES_HUC(i915)) { ret = intel_huc_fw_upload(huc); if (ret) goto err_out; @@ -392,24 +391,24 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv) if (ret) goto err_log_capture; - if (USES_HUC(dev_priv)) { + if (USES_HUC(i915)) { ret = intel_huc_auth(huc); if (ret) goto err_communication; } - if (USES_GUC_SUBMISSION(dev_priv)) { + if (USES_GUC_SUBMISSION(i915)) { ret = intel_guc_submission_enable(guc); if (ret) goto err_communication; } - dev_info(dev_priv->drm.dev, "GuC firmware version %u.%u\n", + dev_info(i915->drm.dev, "GuC firmware version %u.%u\n", guc->fw.major_ver_found, guc->fw.minor_ver_found); - dev_info(dev_priv->drm.dev, "GuC submission %s\n", - enableddisabled(USES_GUC_SUBMISSION(dev_priv))); - dev_info(dev_priv->drm.dev, "HuC %s\n", - enableddisabled(USES_HUC(dev_priv))); + dev_info(i915->drm.dev, "GuC submission %s\n", + enableddisabled(USES_GUC_SUBMISSION(i915))); + dev_info(i915->drm.dev, "HuC %s\n", + enableddisabled(USES_HUC(i915))); return 0; @@ -428,20 +427,20 @@ err_out: if (GEM_WARN_ON(ret == -EIO)) ret = -EINVAL; - dev_err(dev_priv->drm.dev, "GuC initialization failed %d\n", ret); + dev_err(i915->drm.dev, "GuC initialization failed %d\n", ret); return ret; } -void intel_uc_fini_hw(struct drm_i915_private *dev_priv) +void intel_uc_fini_hw(struct drm_i915_private *i915) { - struct intel_guc *guc = &dev_priv->guc; + struct intel_guc *guc = &i915->guc; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return; - GEM_BUG_ON(!HAS_GUC(dev_priv)); + GEM_BUG_ON(!HAS_GUC(i915)); - if (USES_GUC_SUBMISSION(dev_priv)) + if (USES_GUC_SUBMISSION(i915)) intel_guc_submission_disable(guc); guc_disable_communication(guc); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 448293eb638d..b36a3b5736a0 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1702,15 +1702,9 @@ static void gen3_stop_engine(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; const u32 base = engine->mmio_base; - const i915_reg_t mode = RING_MI_MODE(base); - - I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING)); - if (__intel_wait_for_register_fw(dev_priv, - mode, MODE_IDLE, MODE_IDLE, - 500, 0, - NULL)) - DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", - engine->name); + + if (intel_engine_stop_cs(engine)) + DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", engine->name); I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base))); POSTING_READ_FW(RING_HEAD(base)); /* paranoia */ diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h index 458468237b5f..c132d0c3a500 100644 --- a/drivers/gpu/drm/i915/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/intel_vbt_defs.h @@ -318,6 +318,12 @@ enum vbt_gmbus_ddi { DDC_BUS_DDI_C, DDC_BUS_DDI_D, DDC_BUS_DDI_F, + ICL_DDC_BUS_DDI_A = 0x1, + ICL_DDC_BUS_DDI_B, + ICL_DDC_BUS_PORT_1 = 0x4, + ICL_DDC_BUS_PORT_2, + ICL_DDC_BUS_PORT_3, + ICL_DDC_BUS_PORT_4, }; #define VBT_DP_MAX_LINK_RATE_HBR3 0 @@ -635,7 +641,7 @@ struct bdb_sdvo_lvds_options { #define BDB_DRIVER_FEATURE_NO_LVDS 0 #define BDB_DRIVER_FEATURE_INT_LVDS 1 #define BDB_DRIVER_FEATURE_SDVO_LVDS 2 -#define BDB_DRIVER_FEATURE_EDP 3 +#define BDB_DRIVER_FEATURE_INT_SDVO_LVDS 3 struct bdb_driver_features { u8 boot_dev_algorithm:1; diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index 2df3538ceba5..b1ab56a1ec31 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -463,6 +463,25 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) */ WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); + /* Wa_2006611047:icl (pre-prod) + * Formerly known as WaDisableImprovedTdlClkGating + */ + if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) + WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, + GEN11_TDL_CLOCK_GATING_FIX_DISABLE); + + /* WaEnableStateCacheRedirectToCS:icl */ + WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN1, + GEN11_STATE_CACHE_REDIRECT_TO_CS); + + /* Wa_2006665173:icl (pre-prod) */ + if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) + WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3, + GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC); + + /* WaEnableFloatBlendOptimization:icl */ + WA_SET_BIT_MASKED(GEN10_CACHE_MODE_SS, FLOAT_BLEND_OPTIMIZATION_ENABLE); + return 0; } @@ -672,8 +691,74 @@ static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv) GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } +static void wa_init_mcr(struct drm_i915_private *dev_priv) +{ + const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); + u32 mcr; + u32 mcr_slice_subslice_mask; + + /* + * WaProgramMgsrForL3BankSpecificMmioReads: cnl,icl + * L3Banks could be fused off in single slice scenario. If that is + * the case, we might need to program MCR select to a valid L3Bank + * by default, to make sure we correctly read certain registers + * later on (in the range 0xB100 - 0xB3FF). + * This might be incompatible with + * WaProgramMgsrForCorrectSliceSpecificMmioReads. + * Fortunately, this should not happen in production hardware, so + * we only assert that this is the case (instead of implementing + * something more complex that requires checking the range of every + * MMIO read). + */ + if (INTEL_GEN(dev_priv) >= 10 && + is_power_of_2(sseu->slice_mask)) { + /* + * read FUSE3 for enabled L3 Bank IDs, if L3 Bank matches + * enabled subslice, no need to redirect MCR packet + */ + u32 slice = fls(sseu->slice_mask); + u32 fuse3 = I915_READ(GEN10_MIRROR_FUSE3); + u8 ss_mask = sseu->subslice_mask[slice]; + + u8 enabled_mask = (ss_mask | ss_mask >> + GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK; + u8 disabled_mask = fuse3 & GEN10_L3BANK_MASK; + + /* + * Production silicon should have matched L3Bank and + * subslice enabled + */ + WARN_ON((enabled_mask & disabled_mask) != enabled_mask); + } + + mcr = I915_READ(GEN8_MCR_SELECTOR); + + if (INTEL_GEN(dev_priv) >= 11) + mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK | + GEN11_MCR_SUBSLICE_MASK; + else + mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK | + GEN8_MCR_SUBSLICE_MASK; + /* + * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl,icl + * Before any MMIO read into slice/subslice specific registers, MCR + * packet control register needs to be programmed to point to any + * enabled s/ss pair. Otherwise, incorrect values will be returned. + * This means each subsequent MMIO read will be forwarded to an + * specific s/ss combination, but this is OK since these registers + * are consistent across s/ss in almost all cases. In the rare + * occasions, such as INSTDONE, where this value is dependent + * on s/ss combo, the read should be done with read_subslice_reg. + */ + mcr &= ~mcr_slice_subslice_mask; + mcr |= intel_calculate_mcr_s_ss_select(dev_priv); + I915_WRITE(GEN8_MCR_SELECTOR, mcr); +} + static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) { + wa_init_mcr(dev_priv); + /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) I915_WRITE(GAMT_CHKN_BIT_REG, @@ -692,6 +777,8 @@ static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) { + wa_init_mcr(dev_priv); + /* This is not an Wa. Enable for better image quality */ I915_WRITE(_3D_CHICKEN3, _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE)); @@ -772,6 +859,13 @@ static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) PMFLUSHDONE_LNICRSDROP | PMFLUSH_GAPL3UNBLOCK | PMFLUSHDONE_LNEBLK); + + /* Wa_1406463099:icl + * Formerly known as WaGamTlbPendError + */ + I915_WRITE(GAMT_CHKN_BIT_REG, + I915_READ(GAMT_CHKN_BIT_REG) | + GAMT_CHKN_DISABLE_L3_COH_PIPE); } void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 91c72911be3c..7846ea4a99bc 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -338,7 +338,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single) static int igt_check_page_sizes(struct i915_vma *vma) { - struct drm_i915_private *i915 = to_i915(vma->obj->base.dev); + struct drm_i915_private *i915 = vma->vm->i915; unsigned int supported = INTEL_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj = vma->obj; int err = 0; @@ -379,7 +379,7 @@ static int igt_check_page_sizes(struct i915_vma *vma) static int igt_mock_exhaust_device_supported_pages(void *arg) { struct i915_hw_ppgtt *ppgtt = arg; - struct drm_i915_private *i915 = ppgtt->base.i915; + struct drm_i915_private *i915 = ppgtt->vm.i915; unsigned int saved_mask = INTEL_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -415,7 +415,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg) goto out_put; } - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out_put; @@ -458,7 +458,7 @@ out_device: static int igt_mock_ppgtt_misaligned_dma(void *arg) { struct i915_hw_ppgtt *ppgtt = arg; - struct drm_i915_private *i915 = ppgtt->base.i915; + struct drm_i915_private *i915 = ppgtt->vm.i915; unsigned long supported = INTEL_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj; int bit; @@ -500,7 +500,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) /* Force the page size for this object */ obj->mm.page_sizes.sg = page_size; - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out_unpin; @@ -591,7 +591,7 @@ static void close_object_list(struct list_head *objects, list_for_each_entry_safe(obj, on, objects, st_link) { struct i915_vma *vma; - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (!IS_ERR(vma)) i915_vma_close(vma); @@ -604,8 +604,8 @@ static void close_object_list(struct list_head *objects, static int igt_mock_ppgtt_huge_fill(void *arg) { struct i915_hw_ppgtt *ppgtt = arg; - struct drm_i915_private *i915 = ppgtt->base.i915; - unsigned long max_pages = ppgtt->base.total >> PAGE_SHIFT; + struct drm_i915_private *i915 = ppgtt->vm.i915; + unsigned long max_pages = ppgtt->vm.total >> PAGE_SHIFT; unsigned long page_num; bool single = false; LIST_HEAD(objects); @@ -641,7 +641,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg) list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); break; @@ -725,7 +725,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg) static int igt_mock_ppgtt_64K(void *arg) { struct i915_hw_ppgtt *ppgtt = arg; - struct drm_i915_private *i915 = ppgtt->base.i915; + struct drm_i915_private *i915 = ppgtt->vm.i915; struct drm_i915_gem_object *obj; const struct object_info { unsigned int size; @@ -819,7 +819,7 @@ static int igt_mock_ppgtt_64K(void *arg) */ obj->mm.page_sizes.sg &= ~I915_GTT_PAGE_SIZE_2M; - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out_object_unpin; @@ -887,8 +887,8 @@ out_object_put: static struct i915_vma * gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val) { - struct drm_i915_private *i915 = to_i915(vma->obj->base.dev); - const int gen = INTEL_GEN(vma->vm->i915); + struct drm_i915_private *i915 = vma->vm->i915; + const int gen = INTEL_GEN(i915); unsigned int count = vma->size >> PAGE_SHIFT; struct drm_i915_gem_object *obj; struct i915_vma *batch; @@ -1047,7 +1047,8 @@ static int __igt_write_huge(struct i915_gem_context *ctx, u32 dword, u32 val) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; unsigned int flags = PIN_USER | PIN_OFFSET_FIXED; struct i915_vma *vma; int err; @@ -1100,7 +1101,8 @@ static int igt_write_huge(struct i915_gem_context *ctx, struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; static struct intel_engine_cs *engines[I915_NUM_ENGINES]; struct intel_engine_cs *engine; I915_RND_STATE(prng); @@ -1439,7 +1441,7 @@ static int igt_ppgtt_pin_update(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out_put; @@ -1493,7 +1495,7 @@ static int igt_ppgtt_pin_update(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); - vma = i915_vma_instance(obj, &ppgtt->base, NULL); + vma = i915_vma_instance(obj, &ppgtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out_put; @@ -1531,7 +1533,8 @@ static int igt_tmpfs_fallback(void *arg) struct i915_gem_context *ctx = arg; struct drm_i915_private *i915 = ctx->i915; struct vfsmount *gemfs = i915->mm.gemfs; - struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; struct drm_i915_gem_object *obj; struct i915_vma *vma; u32 *vaddr; @@ -1587,7 +1590,8 @@ static int igt_shrink_thp(void *arg) { struct i915_gem_context *ctx = arg; struct drm_i915_private *i915 = ctx->i915; - struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; struct drm_i915_gem_object *obj; struct i915_vma *vma; unsigned int flags = PIN_USER; @@ -1696,14 +1700,14 @@ int i915_gem_huge_page_mock_selftests(void) goto out_unlock; } - if (!i915_vm_is_48bit(&ppgtt->base)) { + if (!i915_vm_is_48bit(&ppgtt->vm)) { pr_err("failed to create 48b PPGTT\n"); err = -EINVAL; goto out_close; } /* If we were ever hit this then it's time to mock the 64K scratch */ - if (!i915_vm_has_scratch_64K(&ppgtt->base)) { + if (!i915_vm_has_scratch_64K(&ppgtt->vm)) { pr_err("PPGTT missing 64K scratch page\n"); err = -EINVAL; goto out_close; @@ -1712,7 +1716,7 @@ int i915_gem_huge_page_mock_selftests(void) err = i915_subtests(tests, ppgtt); out_close: - i915_ppgtt_close(&ppgtt->base); + i915_ppgtt_close(&ppgtt->vm); i915_ppgtt_put(ppgtt); out_unlock: @@ -1758,7 +1762,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv) } if (ctx->ppgtt) - ctx->ppgtt->base.scrub_64K = true; + ctx->ppgtt->vm.scrub_64K = true; err = i915_subtests(tests, ctx); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index ddb03f009232..708e8d721448 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -26,6 +26,7 @@ #include "igt_flush_test.h" #include "mock_drm.h" +#include "mock_gem_device.h" #include "huge_gem_object.h" #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32)) @@ -114,7 +115,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj, { struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_address_space *vm = - ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; struct i915_request *rq; struct i915_vma *vma; struct i915_vma *batch; @@ -289,7 +290,7 @@ create_test_object(struct i915_gem_context *ctx, { struct drm_i915_gem_object *obj; struct i915_address_space *vm = - ctx->ppgtt ? &ctx->ppgtt->base : &ctx->i915->ggtt.base; + ctx->ppgtt ? &ctx->ppgtt->vm : &ctx->i915->ggtt.vm; u64 size; int err; @@ -420,6 +421,130 @@ out_unlock: return err; } +static __maybe_unused const char * +__engine_name(struct drm_i915_private *i915, unsigned int engines) +{ + struct intel_engine_cs *engine; + unsigned int tmp; + + if (engines == ALL_ENGINES) + return "all"; + + for_each_engine_masked(engine, i915, engines, tmp) + return engine->name; + + return "none"; +} + +static int __igt_switch_to_kernel_context(struct drm_i915_private *i915, + struct i915_gem_context *ctx, + unsigned int engines) +{ + struct intel_engine_cs *engine; + unsigned int tmp; + int err; + + GEM_TRACE("Testing %s\n", __engine_name(i915, engines)); + for_each_engine_masked(engine, i915, engines, tmp) { + struct i915_request *rq; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_add(rq); + } + + err = i915_gem_switch_to_kernel_context(i915); + if (err) + return err; + + for_each_engine_masked(engine, i915, engines, tmp) { + if (!engine_has_kernel_context_barrier(engine)) { + pr_err("kernel context not last on engine %s!\n", + engine->name); + return -EINVAL; + } + } + + err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED); + if (err) + return err; + + GEM_BUG_ON(i915->gt.active_requests); + for_each_engine_masked(engine, i915, engines, tmp) { + if (engine->last_retired_context->gem_context != i915->kernel_context) { + pr_err("engine %s not idling in kernel context!\n", + engine->name); + return -EINVAL; + } + } + + err = i915_gem_switch_to_kernel_context(i915); + if (err) + return err; + + if (i915->gt.active_requests) { + pr_err("switch-to-kernel-context emitted %d requests even though it should already be idling in the kernel context\n", + i915->gt.active_requests); + return -EINVAL; + } + + for_each_engine_masked(engine, i915, engines, tmp) { + if (!intel_engine_has_kernel_context(engine)) { + pr_err("kernel context not last on engine %s!\n", + engine->name); + return -EINVAL; + } + } + + return 0; +} + +static int igt_switch_to_kernel_context(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + enum intel_engine_id id; + int err; + + /* + * A core premise of switching to the kernel context is that + * if an engine is already idling in the kernel context, we + * do not emit another request and wake it up. The other being + * that we do indeed end up idling in the kernel context. + */ + + mutex_lock(&i915->drm.struct_mutex); + ctx = kernel_context(i915); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out_unlock; + } + + /* First check idling each individual engine */ + for_each_engine(engine, i915, id) { + err = __igt_switch_to_kernel_context(i915, ctx, BIT(id)); + if (err) + goto out_unlock; + } + + /* Now en masse */ + err = __igt_switch_to_kernel_context(i915, ctx, ALL_ENGINES); + if (err) + goto out_unlock; + +out_unlock: + GEM_TRACE_DUMP_ON(err); + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; + mutex_unlock(&i915->drm.struct_mutex); + + kernel_context_close(ctx); + return err; +} + static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915) { struct drm_i915_gem_object *obj; @@ -432,7 +557,7 @@ static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915) list_for_each_entry(obj, &i915->mm.bound_list, mm.link) { struct i915_vma *vma; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) continue; @@ -447,9 +572,28 @@ static void fake_aliasing_ppgtt_disable(struct drm_i915_private *i915) i915_gem_fini_aliasing_ppgtt(i915); } +int i915_gem_context_mock_selftests(void) +{ + static const struct i915_subtest tests[] = { + SUBTEST(igt_switch_to_kernel_context), + }; + struct drm_i915_private *i915; + int err; + + i915 = mock_gem_device(); + if (!i915) + return -ENOMEM; + + err = i915_subtests(tests, i915); + + drm_dev_unref(&i915->drm); + return err; +} + int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv) { static const struct i915_subtest tests[] = { + SUBTEST(igt_switch_to_kernel_context), SUBTEST(igt_ctx_exec), }; bool fake_alias = false; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index ab9d7bee0aae..2dc72a984d45 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -35,7 +35,7 @@ static int populate_ggtt(struct drm_i915_private *i915) u64 size; for (size = 0; - size + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total; + size + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total; size += I915_GTT_PAGE_SIZE) { struct i915_vma *vma; @@ -57,7 +57,7 @@ static int populate_ggtt(struct drm_i915_private *i915) return -EINVAL; } - if (list_empty(&i915->ggtt.base.inactive_list)) { + if (list_empty(&i915->ggtt.vm.inactive_list)) { pr_err("No objects on the GGTT inactive list!\n"); return -EINVAL; } @@ -69,7 +69,7 @@ static void unpin_ggtt(struct drm_i915_private *i915) { struct i915_vma *vma; - list_for_each_entry(vma, &i915->ggtt.base.inactive_list, vm_link) + list_for_each_entry(vma, &i915->ggtt.vm.inactive_list, vm_link) i915_vma_unpin(vma); } @@ -103,7 +103,7 @@ static int igt_evict_something(void *arg) goto cleanup; /* Everything is pinned, nothing should happen */ - err = i915_gem_evict_something(&ggtt->base, + err = i915_gem_evict_something(&ggtt->vm, I915_GTT_PAGE_SIZE, 0, 0, 0, U64_MAX, 0); @@ -116,7 +116,7 @@ static int igt_evict_something(void *arg) unpin_ggtt(i915); /* Everything is unpinned, we should be able to evict something */ - err = i915_gem_evict_something(&ggtt->base, + err = i915_gem_evict_something(&ggtt->vm, I915_GTT_PAGE_SIZE, 0, 0, 0, U64_MAX, 0); @@ -181,7 +181,7 @@ static int igt_evict_for_vma(void *arg) goto cleanup; /* Everything is pinned, nothing should happen */ - err = i915_gem_evict_for_node(&ggtt->base, &target, 0); + err = i915_gem_evict_for_node(&ggtt->vm, &target, 0); if (err != -ENOSPC) { pr_err("i915_gem_evict_for_node on a full GGTT returned err=%d\n", err); @@ -191,7 +191,7 @@ static int igt_evict_for_vma(void *arg) unpin_ggtt(i915); /* Everything is unpinned, we should be able to evict the node */ - err = i915_gem_evict_for_node(&ggtt->base, &target, 0); + err = i915_gem_evict_for_node(&ggtt->vm, &target, 0); if (err) { pr_err("i915_gem_evict_for_node returned err=%d\n", err); @@ -229,7 +229,7 @@ static int igt_evict_for_cache_color(void *arg) * i915_gtt_color_adjust throughout our driver, so using a mock color * adjust will work just fine for our purposes. */ - ggtt->base.mm.color_adjust = mock_color_adjust; + ggtt->vm.mm.color_adjust = mock_color_adjust; obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE); if (IS_ERR(obj)) { @@ -265,7 +265,7 @@ static int igt_evict_for_cache_color(void *arg) i915_vma_unpin(vma); /* Remove just the second vma */ - err = i915_gem_evict_for_node(&ggtt->base, &target, 0); + err = i915_gem_evict_for_node(&ggtt->vm, &target, 0); if (err) { pr_err("[0]i915_gem_evict_for_node returned err=%d\n", err); goto cleanup; @@ -276,7 +276,7 @@ static int igt_evict_for_cache_color(void *arg) */ target.color = I915_CACHE_L3_LLC; - err = i915_gem_evict_for_node(&ggtt->base, &target, 0); + err = i915_gem_evict_for_node(&ggtt->vm, &target, 0); if (!err) { pr_err("[1]i915_gem_evict_for_node returned err=%d\n", err); err = -EINVAL; @@ -288,7 +288,7 @@ static int igt_evict_for_cache_color(void *arg) cleanup: unpin_ggtt(i915); cleanup_objects(i915); - ggtt->base.mm.color_adjust = NULL; + ggtt->vm.mm.color_adjust = NULL; return err; } @@ -305,7 +305,7 @@ static int igt_evict_vm(void *arg) goto cleanup; /* Everything is pinned, nothing should happen */ - err = i915_gem_evict_vm(&ggtt->base); + err = i915_gem_evict_vm(&ggtt->vm); if (err) { pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n", err); @@ -314,7 +314,7 @@ static int igt_evict_vm(void *arg) unpin_ggtt(i915); - err = i915_gem_evict_vm(&ggtt->base); + err = i915_gem_evict_vm(&ggtt->vm); if (err) { pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n", err); @@ -359,9 +359,9 @@ static int igt_evict_contexts(void *arg) /* Reserve a block so that we know we have enough to fit a few rq */ memset(&hole, 0, sizeof(hole)); - err = i915_gem_gtt_insert(&i915->ggtt.base, &hole, + err = i915_gem_gtt_insert(&i915->ggtt.vm, &hole, PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE, - 0, i915->ggtt.base.total, + 0, i915->ggtt.vm.total, PIN_NOEVICT); if (err) goto out_locked; @@ -377,9 +377,9 @@ static int igt_evict_contexts(void *arg) goto out_locked; } - if (i915_gem_gtt_insert(&i915->ggtt.base, &r->node, + if (i915_gem_gtt_insert(&i915->ggtt.vm, &r->node, 1ul << 20, 0, I915_COLOR_UNEVICTABLE, - 0, i915->ggtt.base.total, + 0, i915->ggtt.vm.total, PIN_NOEVICT)) { kfree(r); break; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index f7dc926f4ef1..58ab5e84ceb7 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -151,14 +151,14 @@ static int igt_ppgtt_alloc(void *arg) if (err) goto err_ppgtt; - if (!ppgtt->base.allocate_va_range) + if (!ppgtt->vm.allocate_va_range) goto err_ppgtt_cleanup; /* Check we can allocate the entire range */ for (size = 4096; - size <= ppgtt->base.total; + size <= ppgtt->vm.total; size <<= 2) { - err = ppgtt->base.allocate_va_range(&ppgtt->base, 0, size); + err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size); if (err) { if (err == -ENOMEM) { pr_info("[1] Ran out of memory for va_range [0 + %llx] [bit %d]\n", @@ -168,15 +168,15 @@ static int igt_ppgtt_alloc(void *arg) goto err_ppgtt_cleanup; } - ppgtt->base.clear_range(&ppgtt->base, 0, size); + ppgtt->vm.clear_range(&ppgtt->vm, 0, size); } /* Check we can incrementally allocate the entire range */ for (last = 0, size = 4096; - size <= ppgtt->base.total; + size <= ppgtt->vm.total; last = size, size <<= 2) { - err = ppgtt->base.allocate_va_range(&ppgtt->base, - last, size - last); + err = ppgtt->vm.allocate_va_range(&ppgtt->vm, + last, size - last); if (err) { if (err == -ENOMEM) { pr_info("[2] Ran out of memory for va_range [%llx + %llx] [bit %d]\n", @@ -188,7 +188,7 @@ static int igt_ppgtt_alloc(void *arg) } err_ppgtt_cleanup: - ppgtt->base.cleanup(&ppgtt->base); + ppgtt->vm.cleanup(&ppgtt->vm); err_ppgtt: mutex_unlock(&dev_priv->drm.struct_mutex); kfree(ppgtt); @@ -987,12 +987,12 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv, err = PTR_ERR(ppgtt); goto out_unlock; } - GEM_BUG_ON(offset_in_page(ppgtt->base.total)); - GEM_BUG_ON(ppgtt->base.closed); + GEM_BUG_ON(offset_in_page(ppgtt->vm.total)); + GEM_BUG_ON(ppgtt->vm.closed); - err = func(dev_priv, &ppgtt->base, 0, ppgtt->base.total, end_time); + err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time); - i915_ppgtt_close(&ppgtt->base); + i915_ppgtt_close(&ppgtt->vm); i915_ppgtt_put(ppgtt); out_unlock: mutex_unlock(&dev_priv->drm.struct_mutex); @@ -1061,18 +1061,18 @@ static int exercise_ggtt(struct drm_i915_private *i915, mutex_lock(&i915->drm.struct_mutex); restart: - list_sort(NULL, &ggtt->base.mm.hole_stack, sort_holes); - drm_mm_for_each_hole(node, &ggtt->base.mm, hole_start, hole_end) { + list_sort(NULL, &ggtt->vm.mm.hole_stack, sort_holes); + drm_mm_for_each_hole(node, &ggtt->vm.mm, hole_start, hole_end) { if (hole_start < last) continue; - if (ggtt->base.mm.color_adjust) - ggtt->base.mm.color_adjust(node, 0, - &hole_start, &hole_end); + if (ggtt->vm.mm.color_adjust) + ggtt->vm.mm.color_adjust(node, 0, + &hole_start, &hole_end); if (hole_start >= hole_end) continue; - err = func(i915, &ggtt->base, hole_start, hole_end, end_time); + err = func(i915, &ggtt->vm, hole_start, hole_end, end_time); if (err) break; @@ -1134,7 +1134,7 @@ static int igt_ggtt_page(void *arg) goto out_free; memset(&tmp, 0, sizeof(tmp)); - err = drm_mm_insert_node_in_range(&ggtt->base.mm, &tmp, + err = drm_mm_insert_node_in_range(&ggtt->vm.mm, &tmp, count * PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, 0, ggtt->mappable_end, @@ -1147,9 +1147,9 @@ static int igt_ggtt_page(void *arg) for (n = 0; n < count; n++) { u64 offset = tmp.start + n * PAGE_SIZE; - ggtt->base.insert_page(&ggtt->base, - i915_gem_object_get_dma_address(obj, 0), - offset, I915_CACHE_NONE, 0); + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, 0), + offset, I915_CACHE_NONE, 0); } order = i915_random_order(count, &prng); @@ -1188,7 +1188,7 @@ static int igt_ggtt_page(void *arg) kfree(order); out_remove: - ggtt->base.clear_range(&ggtt->base, tmp.start, tmp.size); + ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size); intel_runtime_pm_put(i915); drm_mm_remove_node(&tmp); out_unpin: @@ -1229,7 +1229,7 @@ static int exercise_mock(struct drm_i915_private *i915, ppgtt = ctx->ppgtt; GEM_BUG_ON(!ppgtt); - err = func(i915, &ppgtt->base, 0, ppgtt->base.total, end_time); + err = func(i915, &ppgtt->vm, 0, ppgtt->vm.total, end_time); mock_context_close(ctx); return err; @@ -1270,7 +1270,7 @@ static int igt_gtt_reserve(void *arg) /* Start by filling the GGTT */ for (total = 0; - total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total; + total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total; total += 2*I915_GTT_PAGE_SIZE) { struct i915_vma *vma; @@ -1288,20 +1288,20 @@ static int igt_gtt_reserve(void *arg) list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; } - err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node, obj->base.size, total, obj->cache_level, 0); if (err) { pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1319,7 +1319,7 @@ static int igt_gtt_reserve(void *arg) /* Now we start forcing evictions */ for (total = I915_GTT_PAGE_SIZE; - total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total; + total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total; total += 2*I915_GTT_PAGE_SIZE) { struct i915_vma *vma; @@ -1337,20 +1337,20 @@ static int igt_gtt_reserve(void *arg) list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; } - err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node, obj->base.size, total, obj->cache_level, 0); if (err) { pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1371,7 +1371,7 @@ static int igt_gtt_reserve(void *arg) struct i915_vma *vma; u64 offset; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; @@ -1383,18 +1383,18 @@ static int igt_gtt_reserve(void *arg) goto out; } - offset = random_offset(0, i915->ggtt.base.total, + offset = random_offset(0, i915->ggtt.vm.total, 2*I915_GTT_PAGE_SIZE, I915_GTT_MIN_ALIGNMENT); - err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node, obj->base.size, offset, obj->cache_level, 0); if (err) { pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1429,8 +1429,8 @@ static int igt_gtt_insert(void *arg) u64 start, end; } invalid_insert[] = { { - i915->ggtt.base.total + I915_GTT_PAGE_SIZE, 0, - 0, i915->ggtt.base.total, + i915->ggtt.vm.total + I915_GTT_PAGE_SIZE, 0, + 0, i915->ggtt.vm.total, }, { 2*I915_GTT_PAGE_SIZE, 0, @@ -1460,7 +1460,7 @@ static int igt_gtt_insert(void *arg) /* Check a couple of obviously invalid requests */ for (ii = invalid_insert; ii->size; ii++) { - err = i915_gem_gtt_insert(&i915->ggtt.base, &tmp, + err = i915_gem_gtt_insert(&i915->ggtt.vm, &tmp, ii->size, ii->alignment, I915_COLOR_UNEVICTABLE, ii->start, ii->end, @@ -1475,7 +1475,7 @@ static int igt_gtt_insert(void *arg) /* Start by filling the GGTT */ for (total = 0; - total + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total; + total + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total; total += I915_GTT_PAGE_SIZE) { struct i915_vma *vma; @@ -1493,15 +1493,15 @@ static int igt_gtt_insert(void *arg) list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; } - err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node, obj->base.size, 0, obj->cache_level, - 0, i915->ggtt.base.total, + 0, i915->ggtt.vm.total, 0); if (err == -ENOSPC) { /* maxed out the GGTT space */ @@ -1510,7 +1510,7 @@ static int igt_gtt_insert(void *arg) } if (err) { pr_err("i915_gem_gtt_insert (pass 1) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1522,7 +1522,7 @@ static int igt_gtt_insert(void *arg) list_for_each_entry(obj, &objects, st_link) { struct i915_vma *vma; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; @@ -1542,7 +1542,7 @@ static int igt_gtt_insert(void *arg) struct i915_vma *vma; u64 offset; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; @@ -1557,13 +1557,13 @@ static int igt_gtt_insert(void *arg) goto out; } - err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node, obj->base.size, 0, obj->cache_level, - 0, i915->ggtt.base.total, + 0, i915->ggtt.vm.total, 0); if (err) { pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1579,7 +1579,7 @@ static int igt_gtt_insert(void *arg) /* And then force evictions */ for (total = 0; - total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total; + total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total; total += 2*I915_GTT_PAGE_SIZE) { struct i915_vma *vma; @@ -1597,19 +1597,19 @@ static int igt_gtt_insert(void *arg) list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; } - err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node, + err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node, obj->base.size, 0, obj->cache_level, - 0, i915->ggtt.base.total, + 0, i915->ggtt.vm.total, 0); if (err) { pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n", - total, i915->ggtt.base.total, err); + total, i915->ggtt.vm.total, err); goto out; } track_vma_bind(vma); @@ -1669,7 +1669,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_ggtt_page), }; - GEM_BUG_ON(offset_in_page(i915->ggtt.base.total)); + GEM_BUG_ON(offset_in_page(i915->ggtt.vm.total)); return i915_subtests(tests, i915); } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index fbdb2419d418..2b2dde94526f 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -113,7 +113,7 @@ static int igt_gem_huge(void *arg) obj = huge_gem_object(i915, nreal * PAGE_SIZE, - i915->ggtt.base.total + PAGE_SIZE); + i915->ggtt.vm.total + PAGE_SIZE); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -311,7 +311,7 @@ static int igt_partial_tiling(void *arg) obj = huge_gem_object(i915, nreal << PAGE_SHIFT, - (1 + next_prime_number(i915->ggtt.base.total >> PAGE_SHIFT)) << PAGE_SHIFT); + (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -440,7 +440,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj) struct i915_vma *vma; int err; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) return PTR_ERR(vma); diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h index d16d74178e9d..1b70208eeea7 100644 --- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h @@ -24,3 +24,4 @@ selftest(vma, i915_vma_mock_selftests) selftest(evict, i915_gem_evict_mock_selftests) selftest(gtt, i915_gem_gtt_mock_selftests) selftest(hugepages, i915_gem_huge_page_mock_selftests) +selftest(contexts, i915_gem_context_mock_selftests) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 94bc2e1898a4..a3a89aadeccb 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -430,7 +430,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915) if (err) goto err; - vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; @@ -555,7 +555,8 @@ out_unlock: static struct i915_vma *recursive_batch(struct drm_i915_private *i915) { struct i915_gem_context *ctx = i915->kernel_context; - struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm; struct drm_i915_gem_object *obj; const int gen = INTEL_GEN(i915); struct i915_vma *vma; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index e90f97236e50..8400a8cc5cf2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -35,7 +35,7 @@ static bool assert_vma(struct i915_vma *vma, { bool ok = true; - if (vma->vm != &ctx->ppgtt->base) { + if (vma->vm != &ctx->ppgtt->vm) { pr_err("VMA created with wrong VM\n"); ok = false; } @@ -110,8 +110,7 @@ static int create_vmas(struct drm_i915_private *i915, list_for_each_entry(obj, objects, st_link) { for (pinned = 0; pinned <= 1; pinned++) { list_for_each_entry(ctx, contexts, link) { - struct i915_address_space *vm = - &ctx->ppgtt->base; + struct i915_address_space *vm = &ctx->ppgtt->vm; struct i915_vma *vma; int err; @@ -259,12 +258,12 @@ static int igt_vma_pin1(void *arg) VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | 8192), VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)), VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)), - VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)), + VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)), VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)), INVALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | i915->ggtt.mappable_end), - VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)), - INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.base.total), + VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)), + INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.vm.total), INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | round_down(U64_MAX, PAGE_SIZE)), VALID(4096, PIN_GLOBAL), @@ -272,12 +271,12 @@ static int igt_vma_pin1(void *arg) VALID(i915->ggtt.mappable_end - 4096, PIN_GLOBAL | PIN_MAPPABLE), VALID(i915->ggtt.mappable_end, PIN_GLOBAL | PIN_MAPPABLE), NOSPACE(i915->ggtt.mappable_end + 4096, PIN_GLOBAL | PIN_MAPPABLE), - VALID(i915->ggtt.base.total - 4096, PIN_GLOBAL), - VALID(i915->ggtt.base.total, PIN_GLOBAL), - NOSPACE(i915->ggtt.base.total + 4096, PIN_GLOBAL), + VALID(i915->ggtt.vm.total - 4096, PIN_GLOBAL), + VALID(i915->ggtt.vm.total, PIN_GLOBAL), + NOSPACE(i915->ggtt.vm.total + 4096, PIN_GLOBAL), NOSPACE(round_down(U64_MAX, PAGE_SIZE), PIN_GLOBAL), INVALID(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)), - INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)), + INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)), INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (round_down(U64_MAX, PAGE_SIZE) - 4096)), VALID(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)), @@ -289,9 +288,9 @@ static int igt_vma_pin1(void *arg) * variable start, end and size. */ NOSPACE(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | i915->ggtt.mappable_end), - NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.base.total), + NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.vm.total), NOSPACE(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)), - NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)), + NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)), #endif { }, #undef NOSPACE @@ -307,13 +306,13 @@ static int igt_vma_pin1(void *arg) * focusing on error handling of boundary conditions. */ - GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.base.mm)); + GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.vm.mm)); obj = i915_gem_object_create_internal(i915, PAGE_SIZE); if (IS_ERR(obj)) return PTR_ERR(obj); - vma = checked_vma_instance(obj, &i915->ggtt.base, NULL); + vma = checked_vma_instance(obj, &i915->ggtt.vm, NULL); if (IS_ERR(vma)) goto out; @@ -405,7 +404,7 @@ static unsigned int rotated_size(const struct intel_rotation_plane_info *a, static int igt_vma_rotate(void *arg) { struct drm_i915_private *i915 = arg; - struct i915_address_space *vm = &i915->ggtt.base; + struct i915_address_space *vm = &i915->ggtt.vm; struct drm_i915_gem_object *obj; const struct intel_rotation_plane_info planes[] = { { .width = 1, .height = 1, .stride = 1 }, @@ -604,7 +603,7 @@ static bool assert_pin(struct i915_vma *vma, static int igt_vma_partial(void *arg) { struct drm_i915_private *i915 = arg; - struct i915_address_space *vm = &i915->ggtt.base; + struct i915_address_space *vm = &i915->ggtt.vm; const unsigned int npages = 1021; /* prime! */ struct drm_i915_gem_object *obj; const struct phase { diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index 438e0b045a2c..390a157b37c3 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -105,7 +105,10 @@ static int emit_recurse_batch(struct hang *h, struct i915_request *rq) { struct drm_i915_private *i915 = h->i915; - struct i915_address_space *vm = rq->ctx->ppgtt ? &rq->ctx->ppgtt->base : &i915->ggtt.base; + struct i915_address_space *vm = + rq->gem_context->ppgtt ? + &rq->gem_context->ppgtt->vm : + &i915->ggtt.vm; struct i915_vma *hws, *vma; unsigned int flags; u32 *batch; @@ -560,6 +563,30 @@ struct active_engine { #define TEST_SELF BIT(2) #define TEST_PRIORITY BIT(3) +static int active_request_put(struct i915_request *rq) +{ + int err = 0; + + if (!rq) + return 0; + + if (i915_request_wait(rq, 0, 5 * HZ) < 0) { + GEM_TRACE("%s timed out waiting for completion of fence %llx:%d, seqno %d.\n", + rq->engine->name, + rq->fence.context, + rq->fence.seqno, + i915_request_global_seqno(rq)); + GEM_TRACE_DUMP(); + + i915_gem_set_wedged(rq->i915); + err = -EIO; + } + + i915_request_put(rq); + + return err; +} + static int active_engine(void *data) { I915_RND_STATE(prng); @@ -608,24 +635,20 @@ static int active_engine(void *data) i915_request_add(new); mutex_unlock(&engine->i915->drm.struct_mutex); - if (old) { - if (i915_request_wait(old, 0, HZ) < 0) { - GEM_TRACE("%s timed out.\n", engine->name); - GEM_TRACE_DUMP(); - - i915_gem_set_wedged(engine->i915); - i915_request_put(old); - err = -EIO; - break; - } - i915_request_put(old); - } + err = active_request_put(old); + if (err) + break; cond_resched(); } - for (count = 0; count < ARRAY_SIZE(rq); count++) - i915_request_put(rq[count]); + for (count = 0; count < ARRAY_SIZE(rq); count++) { + int err__ = active_request_put(rq[count]); + + /* Keep the first error */ + if (!err) + err = err__; + } err_file: mock_file_free(engine->i915, file); diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 1b8a07125150..0b6da08c8cae 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -83,7 +83,7 @@ static int emit_recurse_batch(struct spinner *spin, struct i915_request *rq, u32 arbitration_command) { - struct i915_address_space *vm = &rq->ctx->ppgtt->base; + struct i915_address_space *vm = &rq->gem_context->ppgtt->vm; struct i915_vma *hws, *vma; u32 *batch; int err; diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c index 17444a3abbb9..f1cfb0fb6bea 100644 --- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c @@ -33,7 +33,7 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine) memset(cs, 0xc5, PAGE_SIZE); i915_gem_object_unpin_map(result); - vma = i915_vma_instance(result, &engine->i915->ggtt.base, NULL); + vma = i915_vma_instance(result, &engine->i915->ggtt.vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err_obj; diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c index 501becc47c0c..8904f1ce64e3 100644 --- a/drivers/gpu/drm/i915/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/selftests/mock_context.c @@ -30,6 +30,7 @@ mock_context(struct drm_i915_private *i915, const char *name) { struct i915_gem_context *ctx; + unsigned int n; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -43,6 +44,12 @@ mock_context(struct drm_i915_private *i915, INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL); INIT_LIST_HEAD(&ctx->handles_list); + for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { + struct intel_context *ce = &ctx->__engine[n]; + + ce->gem_context = ctx; + } + ret = ida_simple_get(&i915->contexts.hw_ida, 0, MAX_CONTEXT_HW_ID, GFP_KERNEL); if (ret < 0) diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c index 26bf29d97007..c2a0451336cf 100644 --- a/drivers/gpu/drm/i915/selftests/mock_engine.c +++ b/drivers/gpu/drm/i915/selftests/mock_engine.c @@ -72,25 +72,34 @@ static void hw_delay_complete(struct timer_list *t) spin_unlock(&engine->hw_lock); } -static struct intel_ring * -mock_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static void mock_context_unpin(struct intel_context *ce) { - struct intel_context *ce = to_intel_context(ctx, engine); - - if (!ce->pin_count++) - i915_gem_context_get(ctx); + i915_gem_context_put(ce->gem_context); +} - return engine->buffer; +static void mock_context_destroy(struct intel_context *ce) +{ + GEM_BUG_ON(ce->pin_count); } -static void mock_context_unpin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static const struct intel_context_ops mock_context_ops = { + .unpin = mock_context_unpin, + .destroy = mock_context_destroy, +}; + +static struct intel_context * +mock_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { struct intel_context *ce = to_intel_context(ctx, engine); - if (!--ce->pin_count) - i915_gem_context_put(ctx); + if (!ce->pin_count++) { + i915_gem_context_get(ctx); + ce->ring = engine->buffer; + ce->ops = &mock_context_ops; + } + + return ce; } static int mock_request_alloc(struct i915_request *request) @@ -185,7 +194,6 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, engine->base.status_page.page_addr = (void *)(engine + 1); engine->base.context_pin = mock_context_pin; - engine->base.context_unpin = mock_context_unpin; engine->base.request_alloc = mock_request_alloc; engine->base.emit_flush = mock_emit_flush; engine->base.emit_breadcrumb = mock_emit_breadcrumb; @@ -204,8 +212,13 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, if (!engine->base.buffer) goto err_breadcrumbs; + if (IS_ERR(intel_context_pin(i915->kernel_context, &engine->base))) + goto err_ring; + return &engine->base; +err_ring: + mock_ring_free(engine->base.buffer); err_breadcrumbs: intel_engine_fini_breadcrumbs(&engine->base); i915_timeline_fini(&engine->base.timeline); @@ -238,11 +251,15 @@ void mock_engine_free(struct intel_engine_cs *engine) { struct mock_engine *mock = container_of(engine, typeof(*mock), base); + struct intel_context *ce; GEM_BUG_ON(timer_pending(&mock->hw_delay)); - if (engine->last_retired_context) - intel_context_unpin(engine->last_retired_context, engine); + ce = fetch_and_zero(&engine->last_retired_context); + if (ce) + intel_context_unpin(ce); + + __intel_context_unpin(engine->i915->kernel_context, engine); mock_ring_free(engine->buffer); diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 94baedfa0f74..c97075c5ccaf 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -136,8 +136,6 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { struct drm_i915_private *i915; - struct intel_engine_cs *engine; - enum intel_engine_id id; struct pci_dev *pdev; int err; @@ -233,13 +231,13 @@ struct drm_i915_private *mock_gem_device(void) mock_init_ggtt(i915); mkwrite_device_info(i915)->ring_mask = BIT(0); - i915->engine[RCS] = mock_engine(i915, "mock", RCS); - if (!i915->engine[RCS]) - goto err_unlock; - i915->kernel_context = mock_context(i915, NULL); if (!i915->kernel_context) - goto err_engine; + goto err_unlock; + + i915->engine[RCS] = mock_engine(i915, "mock", RCS); + if (!i915->engine[RCS]) + goto err_context; mutex_unlock(&i915->drm.struct_mutex); @@ -247,9 +245,8 @@ struct drm_i915_private *mock_gem_device(void) return i915; -err_engine: - for_each_engine(engine, i915, id) - mock_engine_free(engine); +err_context: + i915_gem_contexts_fini(i915); err_unlock: mutex_unlock(&i915->drm.struct_mutex); kmem_cache_destroy(i915->priorities); diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c index 36c112088940..556c546f2715 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.c +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c @@ -66,25 +66,25 @@ mock_ppgtt(struct drm_i915_private *i915, return NULL; kref_init(&ppgtt->ref); - ppgtt->base.i915 = i915; - ppgtt->base.total = round_down(U64_MAX, PAGE_SIZE); - ppgtt->base.file = ERR_PTR(-ENODEV); - - INIT_LIST_HEAD(&ppgtt->base.active_list); - INIT_LIST_HEAD(&ppgtt->base.inactive_list); - INIT_LIST_HEAD(&ppgtt->base.unbound_list); - - INIT_LIST_HEAD(&ppgtt->base.global_link); - drm_mm_init(&ppgtt->base.mm, 0, ppgtt->base.total); - - ppgtt->base.clear_range = nop_clear_range; - ppgtt->base.insert_page = mock_insert_page; - ppgtt->base.insert_entries = mock_insert_entries; - ppgtt->base.bind_vma = mock_bind_ppgtt; - ppgtt->base.unbind_vma = mock_unbind_ppgtt; - ppgtt->base.set_pages = ppgtt_set_pages; - ppgtt->base.clear_pages = clear_pages; - ppgtt->base.cleanup = mock_cleanup; + ppgtt->vm.i915 = i915; + ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE); + ppgtt->vm.file = ERR_PTR(-ENODEV); + + INIT_LIST_HEAD(&ppgtt->vm.active_list); + INIT_LIST_HEAD(&ppgtt->vm.inactive_list); + INIT_LIST_HEAD(&ppgtt->vm.unbound_list); + + INIT_LIST_HEAD(&ppgtt->vm.global_link); + drm_mm_init(&ppgtt->vm.mm, 0, ppgtt->vm.total); + + ppgtt->vm.clear_range = nop_clear_range; + ppgtt->vm.insert_page = mock_insert_page; + ppgtt->vm.insert_entries = mock_insert_entries; + ppgtt->vm.bind_vma = mock_bind_ppgtt; + ppgtt->vm.unbind_vma = mock_unbind_ppgtt; + ppgtt->vm.set_pages = ppgtt_set_pages; + ppgtt->vm.clear_pages = clear_pages; + ppgtt->vm.cleanup = mock_cleanup; return ppgtt; } @@ -107,27 +107,27 @@ void mock_init_ggtt(struct drm_i915_private *i915) INIT_LIST_HEAD(&i915->vm_list); - ggtt->base.i915 = i915; + ggtt->vm.i915 = i915; ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE); ggtt->mappable_end = resource_size(&ggtt->gmadr); - ggtt->base.total = 4096 * PAGE_SIZE; - - ggtt->base.clear_range = nop_clear_range; - ggtt->base.insert_page = mock_insert_page; - ggtt->base.insert_entries = mock_insert_entries; - ggtt->base.bind_vma = mock_bind_ggtt; - ggtt->base.unbind_vma = mock_unbind_ggtt; - ggtt->base.set_pages = ggtt_set_pages; - ggtt->base.clear_pages = clear_pages; - ggtt->base.cleanup = mock_cleanup; - - i915_address_space_init(&ggtt->base, i915, "global"); + ggtt->vm.total = 4096 * PAGE_SIZE; + + ggtt->vm.clear_range = nop_clear_range; + ggtt->vm.insert_page = mock_insert_page; + ggtt->vm.insert_entries = mock_insert_entries; + ggtt->vm.bind_vma = mock_bind_ggtt; + ggtt->vm.unbind_vma = mock_unbind_ggtt; + ggtt->vm.set_pages = ggtt_set_pages; + ggtt->vm.clear_pages = clear_pages; + ggtt->vm.cleanup = mock_cleanup; + + i915_address_space_init(&ggtt->vm, i915, "global"); } void mock_fini_ggtt(struct drm_i915_private *i915) { struct i915_ggtt *ggtt = &i915->ggtt; - i915_address_space_fini(&ggtt->base); + i915_address_space_fini(&ggtt->vm); } |
