diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 20:42:10 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 20:42:10 -0800 |
commit | e60e1ee60630cafef5e430c2ae364877e061d980 (patch) | |
tree | 816aeef8fe8d4a2c6a1ebbc7a350839bac8dd4c2 /drivers/gpu/drm/i915/intel_engine_cs.c | |
parent | 5d352e69c60e54b5f04d6e337a1d2bf0dbf3d94a (diff) | |
parent | f150891fd9878ef0d9197c4e8451ce67c3bdd014 (diff) | |
download | linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.tar.gz linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.tar.bz2 linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.zip |
Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie:
"This is the main drm pull request for v4.15.
Core:
- Atomic object lifetime fixes
- Atomic iterator improvements
- Sparse/smatch fixes
- Legacy kms ioctls to be interruptible
- EDID override improvements
- fb/gem helper cleanups
- Simple outreachy patches
- Documentation improvements
- Fix dma-buf rcu races
- DRM mode object leasing for improving VR use cases.
- vgaarb improvements for non-x86 platforms.
New driver:
- tve200: Faraday Technology TVE200 block.
This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
the StorLink SL3516 (later Cortina Systems CS3516) as well as the
Grain Media GM8180.
New bridges:
- SiI9234 support
New panels:
- S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
LT089AC19000, Innolux AT043TN24
i915:
- Remove Coffeelake from alpha support
- Cannonlake workarounds
- Infoframe refactoring for DisplayPort
- VBT updates
- DisplayPort vswing/emph/buffer translation refactoring
- CCS fixes
- Restore GPU clock boost on missed vblanks
- Scatter list updates for userptr allocations
- Gen9+ transition watermarks
- Display IPC (Isochronous Priority Control)
- Private PAT management
- GVT: improved error handling and pci config sanitizing
- Execlist refactoring
- Transparent Huge Page support
- User defined priorities support
- HuC/GuC firmware refactoring
- DP MST fixes
- eDP power sequencing fixes
- Use RCU instead of stop_machine
- PSR state tracking support
- Eviction fixes
- BDW DP aux channel timeout fixes
- LSPCON fixes
- Cannonlake PLL fixes
amdgpu:
- Per VM BO support
- Powerplay cleanups
- CI powerplay support
- PASID mgr for kfd
- SR-IOV fixes
- initial GPU reset for vega10
- Prime mmap support
- TTM updates
- Clock query interface for Raven
- Fence to handle ioctl
- UVD encode ring support on Polaris
- Transparent huge page DMA support
- Compute LRU pipe tweaks
- BO flag to allow buffers to opt out of implicit sync
- CTX priority setting API
- VRAM lost infrastructure plumbing
qxl:
- fix flicker since atomic rework
amdkfd:
- Further improvements from internal AMD tree
- Usermode events
- Drop radeon support
nouveau:
- Pascal temperature sensor support
- Improved BAR2 handling
- MMU rework to support Pascal MMU
exynos:
- Improved HDMI/mixer support
- HDMI audio interface support
tegra:
- Prep work for tegra186
- Cleanup/fixes
msm:
- Preemption support for a5xx
- Display fixes for 8x96 (snapdragon 820)
- Async cursor plane fixes
- FW loading rework
- GPU debugging improvements
vc4:
- Prep for DSI panels
- fix T-format tiling scanout
- New madvise ioctl
Rockchip:
- LVDS support
omapdrm:
- omap4 HDMI CEC support
etnaviv:
- GPU performance counters groundwork
sun4i:
- refactor driver load + TCON backend
- HDMI improvements
- A31 support
- Misc fixes
udl:
- Probe/EDID read fixes.
tilcdc:
- Misc fixes.
pl111:
- Support more variants
adv7511:
- Improve EDID handling.
- HDMI CEC support
sii8620:
- Add remote control support"
* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
drm/rockchip: analogix_dp: Use mutex rather than spinlock
drm/mode_object: fix documentation for object lookups.
drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
drm/i915: Move init_clock_gating() back to where it was
drm/i915: Prune the reservation shared fence array
drm/i915: Idle the GPU before shinking everything
drm/i915: Lock llist_del_first() vs llist_del_all()
drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
drm/i915: Disable lazy PPGTT page table optimization for vGPU
drm/i915/execlists: Remove the priority "optimisation"
drm/i915: Filter out spurious execlists context-switch interrupts
drm/amdgpu: use irq-safe lock for kiq->ring_lock
drm/amdgpu: bypass lru touch for KIQ ring submission
drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
drm/amd/powerplay: initialize a variable before using it
drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
drm/rockchip: add CONFIG_OF dependency for lvds
...
Diffstat (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c')
-rw-r--r-- | drivers/gpu/drm/i915/intel_engine_cs.c | 534 |
1 files changed, 490 insertions, 44 deletions
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 3c2d9cf22ed5..ab5bf4e2e28e 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -22,7 +22,10 @@ * */ +#include <drm/drm_print.h> + #include "i915_drv.h" +#include "i915_vgpu.h" #include "intel_ringbuffer.h" #include "intel_lrc.h" @@ -39,6 +42,7 @@ #define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE) #define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE) +#define GEN10_LR_CONTEXT_RENDER_SIZE (18 * PAGE_SIZE) #define GEN8_LR_CONTEXT_OTHER_SIZE ( 2 * PAGE_SIZE) @@ -150,10 +154,11 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class) default: MISSING_CASE(INTEL_GEN(dev_priv)); case 10: + return GEN10_LR_CONTEXT_RENDER_SIZE; case 9: return GEN9_LR_CONTEXT_RENDER_SIZE; case 8: - return i915.enable_execlists ? + return i915_modparams.enable_execlists ? GEN8_LR_CONTEXT_RENDER_SIZE : GEN8_CXT_TOTAL_SIZE; case 7: @@ -301,7 +306,7 @@ int intel_engines_init(struct drm_i915_private *dev_priv) &intel_engine_classes[engine->class]; int (*init)(struct intel_engine_cs *engine); - if (i915.enable_execlists) + if (i915_modparams.enable_execlists) init = class_info->init_execlists; else init = class_info->init_legacy; @@ -380,6 +385,37 @@ static void intel_engine_init_timeline(struct intel_engine_cs *engine) engine->timeline = &engine->i915->gt.global_timeline.engine[engine->id]; } +static bool csb_force_mmio(struct drm_i915_private *i915) +{ + /* + * IOMMU adds unpredictable latency causing the CSB write (from the + * GPU into the HWSP) to only be visible some time after the interrupt + * (missed breadcrumb syndrome). + */ + if (intel_vtd_active()) + return true; + + /* Older GVT emulation depends upon intercepting CSB mmio */ + if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915)) + return true; + + return false; +} + +static void intel_engine_init_execlist(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists * const execlists = &engine->execlists; + + execlists->csb_use_mmio = csb_force_mmio(engine->i915); + + execlists->port_mask = 1; + BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists)); + GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS); + + execlists->queue = RB_ROOT; + execlists->first = NULL; +} + /** * intel_engines_setup_common - setup engine state not requiring hw access * @engine: Engine to setup. @@ -391,8 +427,7 @@ static void intel_engine_init_timeline(struct intel_engine_cs *engine) */ void intel_engine_setup_common(struct intel_engine_cs *engine) { - engine->execlist_queue = RB_ROOT; - engine->execlist_first = NULL; + intel_engine_init_execlist(engine); intel_engine_init_timeline(engine); intel_engine_init_hangcheck(engine); @@ -442,6 +477,116 @@ static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine) i915_vma_unpin_and_release(&engine->scratch); } +static void cleanup_phys_status_page(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + + if (!dev_priv->status_page_dmah) + return; + + drm_pci_free(&dev_priv->drm, dev_priv->status_page_dmah); + engine->status_page.page_addr = NULL; +} + +static void cleanup_status_page(struct intel_engine_cs *engine) +{ + struct i915_vma *vma; + struct drm_i915_gem_object *obj; + + vma = fetch_and_zero(&engine->status_page.vma); + if (!vma) + return; + + obj = vma->obj; + + i915_vma_unpin(vma); + i915_vma_close(vma); + + i915_gem_object_unpin_map(obj); + __i915_gem_object_release_unless_active(obj); +} + +static int init_status_page(struct intel_engine_cs *engine) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + unsigned int flags; + void *vaddr; + int ret; + + obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE); + if (IS_ERR(obj)) { + DRM_ERROR("Failed to allocate status page\n"); + return PTR_ERR(obj); + } + + ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + if (ret) + goto err; + + vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err; + } + + flags = PIN_GLOBAL; + if (!HAS_LLC(engine->i915)) + /* On g33, we cannot place HWS above 256MiB, so + * restrict its pinning to the low mappable arena. + * Though this restriction is not documented for + * gen4, gen5, or byt, they also behave similarly + * and hang if the HWS is placed at the top of the + * GTT. To generalise, it appears that all !llc + * platforms have issues with us placing the HWS + * above the mappable region (even though we never + * actually map it). + */ + flags |= PIN_MAPPABLE; + else + flags |= PIN_HIGH; + ret = i915_vma_pin(vma, 0, 4096, flags); + if (ret) + goto err; + + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + if (IS_ERR(vaddr)) { + ret = PTR_ERR(vaddr); + goto err_unpin; + } + + engine->status_page.vma = vma; + engine->status_page.ggtt_offset = i915_ggtt_offset(vma); + engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE); + + DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n", + engine->name, i915_ggtt_offset(vma)); + return 0; + +err_unpin: + i915_vma_unpin(vma); +err: + i915_gem_object_put(obj); + return ret; +} + +static int init_phys_status_page(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + + GEM_BUG_ON(engine->id != RCS); + + dev_priv->status_page_dmah = + drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE); + if (!dev_priv->status_page_dmah) + return -ENOMEM; + + engine->status_page.page_addr = dev_priv->status_page_dmah->vaddr; + memset(engine->status_page.page_addr, 0, PAGE_SIZE); + + return 0; +} + /** * intel_engines_init_common - initialize cengine state which might require hw access * @engine: Engine to initialize. @@ -471,17 +616,44 @@ int intel_engine_init_common(struct intel_engine_cs *engine) if (IS_ERR(ring)) return PTR_ERR(ring); + /* + * Similarly the preempt context must always be available so that + * we can interrupt the engine at any time. + */ + if (INTEL_INFO(engine->i915)->has_logical_ring_preemption) { + ring = engine->context_pin(engine, + engine->i915->preempt_context); + if (IS_ERR(ring)) { + ret = PTR_ERR(ring); + goto err_unpin_kernel; + } + } + ret = intel_engine_init_breadcrumbs(engine); if (ret) - goto err_unpin; + goto err_unpin_preempt; ret = i915_gem_render_state_init(engine); if (ret) - goto err_unpin; + goto err_breadcrumbs; + + if (HWS_NEEDS_PHYSICAL(engine->i915)) + ret = init_phys_status_page(engine); + else + ret = init_status_page(engine); + if (ret) + goto err_rs_fini; return 0; -err_unpin: +err_rs_fini: + i915_gem_render_state_fini(engine); +err_breadcrumbs: + intel_engine_fini_breadcrumbs(engine); +err_unpin_preempt: + if (INTEL_INFO(engine->i915)->has_logical_ring_preemption) + engine->context_unpin(engine, engine->i915->preempt_context); +err_unpin_kernel: engine->context_unpin(engine, engine->i915->kernel_context); return ret; } @@ -497,11 +669,18 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) { intel_engine_cleanup_scratch(engine); + if (HWS_NEEDS_PHYSICAL(engine->i915)) + cleanup_phys_status_page(engine); + else + cleanup_status_page(engine); + i915_gem_render_state_fini(engine); intel_engine_fini_breadcrumbs(engine); intel_engine_cleanup_cmd_parser(engine); i915_gem_batch_pool_fini(&engine->batch_pool); + if (INTEL_INFO(engine->i915)->has_logical_ring_preemption) + engine->context_unpin(engine, engine->i915->preempt_context); engine->context_unpin(engine, engine->i915->kernel_context); } @@ -672,11 +851,6 @@ static int wa_add(struct drm_i915_private *dev_priv, #define WA_SET_FIELD_MASKED(addr, mask, value) \ WA_REG(addr, mask, _MASKED_FIELD(mask, value)) -#define WA_SET_BIT(addr, mask) WA_REG(addr, mask, I915_READ(addr) | (mask)) -#define WA_CLR_BIT(addr, mask) WA_REG(addr, mask, I915_READ(addr) & ~(mask)) - -#define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val) - static int wa_ring_whitelist_reg(struct intel_engine_cs *engine, i915_reg_t reg) { @@ -687,8 +861,8 @@ static int wa_ring_whitelist_reg(struct intel_engine_cs *engine, if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS)) return -EINVAL; - WA_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index), - i915_mmio_reg_offset(reg)); + I915_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index), + i915_mmio_reg_offset(reg)); wa->hw_whitelist_count[engine->id]++; return 0; @@ -812,6 +986,23 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | ECOCHK_DIS_TLB); + if (HAS_LLC(dev_priv)) { + /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl + * + * Must match Display Engine. See + * WaCompressedResourceDisplayNewHashMode. + */ + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN9_PBE_COMPRESSED_HASH_SELECTION); + WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, + GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR); + + I915_WRITE(MMCD_MISC_CTRL, + I915_READ(MMCD_MISC_CTRL) | + MMCD_PCLA | + MMCD_HOTSPOT_EN); + } + /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, @@ -900,13 +1091,33 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES)); + /* + * Supporting preemption with fine-granularity requires changes in the + * batch buffer programming. Since we can't break old userspace, we + * need to set our default preemption level to safe value. Userspace is + * still able to use more fine-grained preemption levels, since in + * WaEnablePreemptionGranularityControlByUMD we're whitelisting the + * per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are + * not real HW workarounds, but merely a way to start using preemption + * while maintaining old contract with userspace. + */ + + /* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */ + WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL); + + /* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */ + WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, + GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); if (ret) return ret; - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl */ - ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ + I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, + _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); if (ret) return ret; @@ -968,25 +1179,19 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) if (ret) return ret; - /* - * Actual WA is to disable percontext preemption granularity control - * until D0 which is the default case so this is equivalent to - * !WaDisablePerCtxtPreemptionGranularityControl:skl - */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); - /* WaEnableGapsTsvCreditFix:skl */ I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE)); /* WaDisableGafsUnitClkGating:skl */ - WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); /* WaInPlaceDecompressionHang:skl */ if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER)) - WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA, - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, + (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); /* WaDisableLSQCROPERFforOCL:skl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); @@ -1022,8 +1227,8 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) /* WaDisablePooledEuLoadBalancingFix:bxt */ if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) { - WA_SET_BIT_MASKED(FF_SLICE_CS_CHICKEN2, - GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); + I915_WRITE(FF_SLICE_CS_CHICKEN2, + _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE)); } /* WaDisableSbeCacheDispatchPortSharing:bxt */ @@ -1062,8 +1267,65 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) /* WaInPlaceDecompressionHang:bxt */ if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER)) - WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA, - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, + (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); + + return 0; +} + +static int cnl_init_workarounds(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + int ret; + + /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ + if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) + I915_WRITE(GAMT_CHKN_BIT_REG, + (I915_READ(GAMT_CHKN_BIT_REG) | + GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT)); + + /* WaForceContextSaveRestoreNonCoherent:cnl */ + WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0, + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT); + + /* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */ + if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) + WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5); + + /* WaDisableReplayBufferBankArbitrationOptimization:cnl */ + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + /* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */ + if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE); + + /* WaInPlaceDecompressionHang:cnl */ + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, + (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); + + /* WaPushConstantDereferenceHoldDisable:cnl */ + WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE); + + /* FtrEnableFastAnisoL1BankingFix: cnl */ + WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX); + + /* WaDisable3DMidCmdPreemption:cnl */ + WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL); + + /* WaDisableGPGPUMidCmdPreemption:cnl */ + WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, + GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); + + /* WaEnablePreemptionGranularityControlByUMD:cnl */ + I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, + _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); + if (ret) + return ret; return 0; } @@ -1083,8 +1345,9 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) /* WaDisableDynamicCreditSharing:kbl */ if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) - WA_SET_BIT(GAMT_CHKN_BIT_REG, - GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + I915_WRITE(GAMT_CHKN_BIT_REG, + (I915_READ(GAMT_CHKN_BIT_REG) | + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING)); /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) @@ -1097,7 +1360,8 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableGafsUnitClkGating:kbl */ - WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); /* WaDisableSbeCacheDispatchPortSharing:kbl */ WA_SET_BIT_MASKED( @@ -1105,8 +1369,9 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); /* WaInPlaceDecompressionHang:kbl */ - WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA, - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, + (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); /* WaDisableLSQCROPERFforOCL:kbl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); @@ -1150,7 +1415,8 @@ static int cfl_init_workarounds(struct intel_engine_cs *engine) GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableGafsUnitClkGating:cfl */ - WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) | + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE)); /* WaDisableSbeCacheDispatchPortSharing:cfl */ WA_SET_BIT_MASKED( @@ -1158,8 +1424,9 @@ static int cfl_init_workarounds(struct intel_engine_cs *engine) GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); /* WaInPlaceDecompressionHang:cfl */ - WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA, - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, + (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS)); return 0; } @@ -1188,6 +1455,8 @@ int init_workarounds_ring(struct intel_engine_cs *engine) err = glk_init_workarounds(engine); else if (IS_COFFEELAKE(dev_priv)) err = cfl_init_workarounds(engine); + else if (IS_CANNONLAKE(dev_priv)) + err = cnl_init_workarounds(engine); else err = 0; if (err) @@ -1279,12 +1548,12 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine) if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) return false; - /* Both ports drained, no more ELSP submission? */ - if (port_request(&engine->execlist_port[0])) + /* Waiting to drain ELSP? */ + if (READ_ONCE(engine->execlists.active)) return false; /* ELSP is empty, but there are ready requests? */ - if (READ_ONCE(engine->execlist_first)) + if (READ_ONCE(engine->execlists.first)) return false; /* Ring stopped? */ @@ -1333,11 +1602,188 @@ void intel_engines_mark_idle(struct drm_i915_private *i915) for_each_engine(engine, i915, id) { intel_engine_disarm_breadcrumbs(engine); i915_gem_batch_pool_fini(&engine->batch_pool); - tasklet_kill(&engine->irq_tasklet); - engine->no_priolist = false; + tasklet_kill(&engine->execlists.irq_tasklet); + engine->execlists.no_priolist = false; + } +} + +bool intel_engine_can_store_dword(struct intel_engine_cs *engine) +{ + switch (INTEL_GEN(engine->i915)) { + case 2: + return false; /* uses physical not virtual addresses */ + case 3: + /* maybe only uses physical not virtual addresses */ + return !(IS_I915G(engine->i915) || IS_I915GM(engine->i915)); + case 6: + return engine->class != VIDEO_DECODE_CLASS; /* b0rked */ + default: + return true; } } +static void print_request(struct drm_printer *m, + struct drm_i915_gem_request *rq, + const char *prefix) +{ + drm_printf(m, "%s%x%s [%x:%x] prio=%d @ %dms: %s\n", prefix, + rq->global_seqno, + i915_gem_request_completed(rq) ? "!" : "", + rq->ctx->hw_id, rq->fence.seqno, + rq->priotree.priority, + jiffies_to_msecs(jiffies - rq->emitted_jiffies), + rq->timeline->common->name); +} + +void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m) +{ + struct intel_breadcrumbs * const b = &engine->breadcrumbs; + const struct intel_engine_execlists * const execlists = &engine->execlists; + struct i915_gpu_error * const error = &engine->i915->gpu_error; + struct drm_i915_private *dev_priv = engine->i915; + struct drm_i915_gem_request *rq; + struct rb_node *rb; + u64 addr; + + drm_printf(m, "%s\n", engine->name); + drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n", + intel_engine_get_seqno(engine), + intel_engine_last_submit(engine), + engine->hangcheck.seqno, + jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp), + engine->timeline->inflight_seqnos); + drm_printf(m, "\tReset count: %d\n", + i915_reset_engine_count(error, engine)); + + rcu_read_lock(); + + drm_printf(m, "\tRequests:\n"); + + rq = list_first_entry(&engine->timeline->requests, + struct drm_i915_gem_request, link); + if (&rq->link != &engine->timeline->requests) + print_request(m, rq, "\t\tfirst "); + + rq = list_last_entry(&engine->timeline->requests, + struct drm_i915_gem_request, link); + if (&rq->link != &engine->timeline->requests) + print_request(m, rq, "\t\tlast "); + + rq = i915_gem_find_active_request(engine); + if (rq) { + print_request(m, rq, "\t\tactive "); + drm_printf(m, + "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n", + rq->head, rq->postfix, rq->tail, + rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u, + rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u); + } + + drm_printf(m, "\tRING_START: 0x%08x [0x%08x]\n", + I915_READ(RING_START(engine->mmio_base)), + rq ? i915_ggtt_offset(rq->ring->vma) : 0); + drm_printf(m, "\tRING_HEAD: 0x%08x [0x%08x]\n", + I915_READ(RING_HEAD(engine->mmio_base)) & HEAD_ADDR, + rq ? rq->ring->head : 0); + drm_printf(m, "\tRING_TAIL: 0x%08x [0x%08x]\n", + I915_READ(RING_TAIL(engine->mmio_base)) & TAIL_ADDR, + rq ? rq->ring->tail : 0); + drm_printf(m, "\tRING_CTL: 0x%08x [%s]\n", + I915_READ(RING_CTL(engine->mmio_base)), + I915_READ(RING_CTL(engine->mmio_base)) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? "waiting" : ""); + + rcu_read_unlock(); + + addr = intel_engine_get_active_head(engine); + drm_printf(m, "\tACTHD: 0x%08x_%08x\n", + upper_32_bits(addr), lower_32_bits(addr)); + addr = intel_engine_get_last_batch_head(engine); + drm_printf(m, "\tBBADDR: 0x%08x_%08x\n", + upper_32_bits(addr), lower_32_bits(addr)); + + if (i915_modparams.enable_execlists) { + const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX]; + u32 ptr, read, write; + unsigned int idx; + + drm_printf(m, "\tExeclist status: 0x%08x %08x\n", + I915_READ(RING_EXECLIST_STATUS_LO(engine)), + I915_READ(RING_EXECLIST_STATUS_HI(engine))); + + ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine)); + read = GEN8_CSB_READ_PTR(ptr); + write = GEN8_CSB_WRITE_PTR(ptr); + drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n", + read, execlists->csb_head, + write, + intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)), + yesno(test_bit(ENGINE_IRQ_EXECLIST, + &engine->irq_posted))); + if (read >= GEN8_CSB_ENTRIES) + read = 0; + if (write >= GEN8_CSB_ENTRIES) + write = 0; + if (read > write) + write += GEN8_CSB_ENTRIES; + while (read < write) { + idx = ++read % GEN8_CSB_ENTRIES; + drm_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n", + idx, + I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)), + hws[idx * 2], + I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)), + hws[idx * 2 + 1]); + } + + rcu_read_lock(); + for (idx = 0; idx < execlists_num_ports(execlists); idx++) { + unsigned int count; + + rq = port_unpack(&execlists->port[idx], &count); + if (rq) { + drm_printf(m, "\t\tELSP[%d] count=%d, ", + idx, count); + print_request(m, rq, "rq: "); + } else { + drm_printf(m, "\t\tELSP[%d] idle\n", + idx); + } + } + drm_printf(m, "\t\tHW active? 0x%x\n", execlists->active); + rcu_read_unlock(); + } else if (INTEL_GEN(dev_priv) > 6) { + drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n", + I915_READ(RING_PP_DIR_BASE(engine))); + drm_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n", + I915_READ(RING_PP_DIR_BASE_READ(engine))); + drm_printf(m, "\tPP_DIR_DCLV: 0x%08x\n", + I915_READ(RING_PP_DIR_DCLV(engine))); + } + + spin_lock_irq(&engine->timeline->lock); + list_for_each_entry(rq, &engine->timeline->requests, link) + print_request(m, rq, "\t\tE "); + for (rb = execlists->first; rb; rb = rb_next(rb)) { + struct i915_priolist *p = + rb_entry(rb, typeof(*p), node); + + list_for_each_entry(rq, &p->requests, priotree.link) + print_request(m, rq, "\t\tQ "); + } + spin_unlock_irq(&engine->timeline->lock); + + spin_lock_irq(&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); + + drm_printf(m, "\n"); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/mock_engine.c" #endif |