diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_gtt.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gtt.c | 146 |
1 files changed, 118 insertions, 28 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 2eaeba14319e..afbc5c769308 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -12,12 +12,21 @@ #include "gem/i915_gem_internal.h" #include "gem/i915_gem_lmem.h" +#include "i915_reg.h" #include "i915_trace.h" #include "i915_utils.h" #include "intel_gt.h" +#include "intel_gt_mcr.h" +#include "intel_gt_print.h" #include "intel_gt_regs.h" #include "intel_gtt.h" +bool i915_ggtt_require_binder(struct drm_i915_private *i915) +{ + /* Wa_13010847436 & Wa_14019519902 */ + return !i915_direct_stolen_access(i915) && + MEDIA_VER_FULL(i915) == IP_VER(13, 0); +} static bool intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *i915) { @@ -55,6 +64,9 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz) if (!IS_ERR(obj)) { obj->base.resv = i915_vm_resv_get(vm); obj->shares_resv_from = vm; + + if (vm->fpriv) + i915_drm_client_add_object(vm->fpriv->client, obj); } return obj; @@ -76,6 +88,9 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) if (!IS_ERR(obj)) { obj->base.resv = i915_vm_resv_get(vm); obj->shares_resv_from = vm; + + if (vm->fpriv) + i915_drm_client_add_object(vm->fpriv->client, obj); } return obj; @@ -86,7 +101,17 @@ int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) enum i915_map_type type; void *vaddr; - type = i915_coherent_map_type(vm->i915, obj, true); + type = intel_gt_coherent_map_type(vm->gt, obj, true); + /* + * FIXME: It is suspected that some Address Translation Service (ATS) + * issue on IOMMU is causing CAT errors to occur on some MTL workloads. + * Applying a write barrier to the ppgtt set entry functions appeared + * to have no effect, so we must temporarily use I915_MAP_WC here on + * MTL until a proper ATS solution is found. + */ + if (IS_METEORLAKE(vm->i915)) + type = I915_MAP_WC; + vaddr = i915_gem_object_pin_map_unlocked(obj, type); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); @@ -100,7 +125,17 @@ int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object enum i915_map_type type; void *vaddr; - type = i915_coherent_map_type(vm->i915, obj, true); + type = intel_gt_coherent_map_type(vm->gt, obj, true); + /* + * FIXME: It is suspected that some Address Translation Service (ATS) + * issue on IOMMU is causing CAT errors to occur on some MTL workloads. + * Applying a write barrier to the ppgtt set entry functions appeared + * to have no effect, so we must temporarily use I915_MAP_WC here on + * MTL until a proper ATS solution is found. + */ + if (IS_METEORLAKE(vm->i915)) + type = I915_MAP_WC; + vaddr = i915_gem_object_pin_map(obj, type); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); @@ -141,7 +176,6 @@ static void clear_vm_list(struct list_head *list) i915_vma_destroy_locked(vma); i915_gem_object_put(obj); } - } } @@ -269,11 +303,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) memset64(vm->min_alignment, I915_GTT_MIN_ALIGNMENT, ARRAY_SIZE(vm->min_alignment)); - if (HAS_64K_PAGES(vm->i915) && NEEDS_COMPACT_PT(vm->i915) && - subclass == VM_CLASS_PPGTT) { - vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_2M; - vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_2M; - } else if (HAS_64K_PAGES(vm->i915)) { + if (HAS_64K_PAGES(vm->i915)) { vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_64K; vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_64K; } @@ -343,7 +373,8 @@ int setup_scratch_page(struct i915_address_space *vm) */ size = I915_GTT_PAGE_SIZE_4K; if (i915_vm_is_4lvl(vm) && - HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) + HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K) && + !HAS_64K_PAGES(vm->i915)) size = I915_GTT_PAGE_SIZE_64K; do { @@ -385,18 +416,6 @@ skip: if (size == I915_GTT_PAGE_SIZE_4K) return -ENOMEM; - /* - * If we need 64K minimum GTT pages for device local-memory, - * like on XEHPSDV, then we need to fail the allocation here, - * otherwise we can't safely support the insertion of - * local-memory pages for this vm, since the HW expects the - * correct physical alignment and size when the page-table is - * operating in 64K GTT mode, which includes any scratch PTEs, - * since userspace can still touch them. - */ - if (HAS_64K_PAGES(vm->i915)) - return -ENOMEM; - size = I915_GTT_PAGE_SIZE_4K; } while (1); } @@ -474,12 +493,50 @@ void gtt_write_workarounds(struct intel_gt *gt) intel_uncore_write(uncore, HSW_GTT_CACHE_EN, can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0); - drm_WARN_ON_ONCE(&i915->drm, can_use_gtt_cache && - intel_uncore_read(uncore, - HSW_GTT_CACHE_EN) == 0); + gt_WARN_ON_ONCE(gt, can_use_gtt_cache && + intel_uncore_read(uncore, + HSW_GTT_CACHE_EN) == 0); } } +static void xelpmp_setup_private_ppat(struct intel_uncore *uncore) +{ + intel_uncore_write(uncore, XELPMP_PAT_INDEX(0), + MTL_PPAT_L4_0_WB); + intel_uncore_write(uncore, XELPMP_PAT_INDEX(1), + MTL_PPAT_L4_1_WT); + intel_uncore_write(uncore, XELPMP_PAT_INDEX(2), + MTL_PPAT_L4_3_UC); + intel_uncore_write(uncore, XELPMP_PAT_INDEX(3), + MTL_PPAT_L4_0_WB | MTL_2_COH_1W); + intel_uncore_write(uncore, XELPMP_PAT_INDEX(4), + MTL_PPAT_L4_0_WB | MTL_3_COH_2W); + + /* + * Remaining PAT entries are left at the hardware-default + * fully-cached setting + */ +} + +static void xelpg_setup_private_ppat(struct intel_gt *gt) +{ + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0), + MTL_PPAT_L4_0_WB); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1), + MTL_PPAT_L4_1_WT); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2), + MTL_PPAT_L4_3_UC); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3), + MTL_PPAT_L4_0_WB | MTL_2_COH_1W); + intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4), + MTL_PPAT_L4_0_WB | MTL_3_COH_2W); + + /* + * Remaining PAT entries are left at the hardware-default + * fully-cached setting + */ +} + static void tgl_setup_private_ppat(struct intel_uncore *uncore) { /* TGL doesn't support LLC or AGE settings */ @@ -493,6 +550,29 @@ static void tgl_setup_private_ppat(struct intel_uncore *uncore) intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB); } +static void xehp_setup_private_ppat(struct intel_gt *gt) +{ + enum forcewake_domains fw; + unsigned long flags; + + fw = intel_uncore_forcewake_for_reg(gt->uncore, _MMIO(XEHP_PAT_INDEX(0).reg), + FW_REG_WRITE); + intel_uncore_forcewake_get(gt->uncore, fw); + + intel_gt_mcr_lock(gt, &flags); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(0), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(1), GEN8_PPAT_WC); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(2), GEN8_PPAT_WT); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(3), GEN8_PPAT_UC); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(4), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(5), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(6), GEN8_PPAT_WB); + intel_gt_mcr_multicast_write_fw(gt, XEHP_PAT_INDEX(7), GEN8_PPAT_WB); + intel_gt_mcr_unlock(gt, flags); + + intel_uncore_forcewake_put(gt->uncore, fw); +} + static void icl_setup_private_ppat(struct intel_uncore *uncore) { intel_uncore_write(uncore, @@ -585,13 +665,23 @@ static void chv_setup_private_ppat(struct intel_uncore *uncore) intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat)); } -void setup_private_pat(struct intel_uncore *uncore) +void setup_private_pat(struct intel_gt *gt) { - struct drm_i915_private *i915 = uncore->i915; + struct intel_uncore *uncore = gt->uncore; + struct drm_i915_private *i915 = gt->i915; GEM_BUG_ON(GRAPHICS_VER(i915) < 8); - if (GRAPHICS_VER(i915) >= 12) + if (gt->type == GT_MEDIA) { + xelpmp_setup_private_ppat(gt->uncore); + return; + } + + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + xelpg_setup_private_ppat(gt); + else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) + xehp_setup_private_ppat(gt); + else if (GRAPHICS_VER(i915) >= 12) tgl_setup_private_ppat(uncore); else if (GRAPHICS_VER(i915) >= 11) icl_setup_private_ppat(uncore); @@ -611,7 +701,7 @@ __vm_create_scratch_for_read(struct i915_address_space *vm, unsigned long size) if (IS_ERR(obj)) return ERR_CAST(obj); - i915_gem_object_set_cache_coherency(obj, I915_CACHING_CACHED); + i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC); vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { |