diff options
Diffstat (limited to 'drivers')
45 files changed, 518 insertions, 694 deletions
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index ffc15d278a39..e9c6105cb32a 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -20,6 +20,7 @@ #include "skl_scaler.h" #include "skl_universal_plane.h" #include "skl_watermark.h" +#include "gt/intel_gt.h" #include "pxp/intel_pxp.h" static const u32 skl_plane_formats[] = { @@ -2168,11 +2169,6 @@ skl_plane_disable_flip_done(struct intel_plane *plane) static bool skl_plane_has_rc_ccs(struct drm_i915_private *i915, enum pipe pipe, enum plane_id plane_id) { - /* Wa_14017240301 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) - return false; - /* Wa_22011186057 */ if (IS_ALDERLAKE_P(i915) && IS_DISPLAY_STEP(i915, STEP_A0, STEP_B0)) return false; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index d24c0ce8805c..19156ba4b9ef 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -405,8 +405,8 @@ static int ext_set_pat(struct i915_user_extension __user *base, void *data) BUILD_BUG_ON(sizeof(struct drm_i915_gem_create_ext_set_pat) != offsetofend(struct drm_i915_gem_create_ext_set_pat, rsvd)); - /* Limiting the extension only to Meteor Lake */ - if (!IS_METEORLAKE(i915)) + /* Limiting the extension only to Xe_LPG and beyond */ + if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 70)) return -ENODEV; if (copy_from_user(&ext, base, sizeof(ext))) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 5a687a3686bd..a4b32567c519 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -321,7 +321,7 @@ static int eb_pin_engine(struct i915_execbuffer *eb, bool throttle); static void eb_unpin_engine(struct i915_execbuffer *eb); static void eb_capture_release(struct i915_execbuffer *eb); -static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) +static bool eb_use_cmdparser(const struct i915_execbuffer *eb) { return intel_engine_requires_cmd_parser(eb->context->engine) || (intel_engine_using_cmd_parser(eb->context->engine) && @@ -433,7 +433,7 @@ static u64 eb_pin_flags(const struct drm_i915_gem_exec_object2 *entry, return pin_flags; } -static inline int +static int eb_pin_vma(struct i915_execbuffer *eb, const struct drm_i915_gem_exec_object2 *entry, struct eb_vma *ev) @@ -486,7 +486,7 @@ eb_pin_vma(struct i915_execbuffer *eb, return 0; } -static inline void +static void eb_unreserve_vma(struct eb_vma *ev) { if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE)) @@ -548,7 +548,7 @@ eb_validate_vma(struct i915_execbuffer *eb, return 0; } -static inline bool +static bool is_batch_buffer(struct i915_execbuffer *eb, unsigned int buffer_idx) { return eb->args->flags & I915_EXEC_BATCH_FIRST ? @@ -628,8 +628,8 @@ eb_add_vma(struct i915_execbuffer *eb, return 0; } -static inline int use_cpu_reloc(const struct reloc_cache *cache, - const struct drm_i915_gem_object *obj) +static int use_cpu_reloc(const struct reloc_cache *cache, + const struct drm_i915_gem_object *obj) { if (!i915_gem_object_has_struct_page(obj)) return false; @@ -1107,7 +1107,7 @@ static void eb_destroy(const struct i915_execbuffer *eb) kfree(eb->buckets); } -static inline u64 +static u64 relocation_target(const struct drm_i915_gem_relocation_entry *reloc, const struct i915_vma *target) { @@ -1128,19 +1128,19 @@ static void reloc_cache_init(struct reloc_cache *cache, cache->node.flags = 0; } -static inline void *unmask_page(unsigned long p) +static void *unmask_page(unsigned long p) { return (void *)(uintptr_t)(p & PAGE_MASK); } -static inline unsigned int unmask_flags(unsigned long p) +static unsigned int unmask_flags(unsigned long p) { return p & ~PAGE_MASK; } #define KMAP 0x4 /* after CLFLUSH_FLAGS */ -static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) +static struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) { struct drm_i915_private *i915 = container_of(cache, struct i915_execbuffer, reloc_cache)->i915; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 8f1633c3fb93..73a4a4eb29e0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -100,6 +100,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, st->nents = 0; for (i = 0; i < page_count; i++) { struct folio *folio; + unsigned long nr_pages; const unsigned int shrink[] = { I915_SHRINK_BOUND | I915_SHRINK_UNBOUND, 0, @@ -150,6 +151,8 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, } } while (1); + nr_pages = min_t(unsigned long, + folio_nr_pages(folio), page_count - i); if (!i || sg->length >= max_segment || folio_pfn(folio) != next_pfn) { @@ -157,13 +160,13 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, sg = sg_next(sg); st->nents++; - sg_set_folio(sg, folio, folio_size(folio), 0); + sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0); } else { /* XXX: could overflow? */ - sg->length += folio_size(folio); + sg->length += nr_pages * PAGE_SIZE; } - next_pfn = folio_pfn(folio) + folio_nr_pages(folio); - i += folio_nr_pages(folio) - 1; + next_pfn = folio_pfn(folio) + nr_pages; + i += nr_pages - 1; /* Check that the i965g/gm workaround works. */ GEM_BUG_ON(gfp & __GFP_DMA32 && next_pfn >= 0x00100000UL); diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c index 8ac6726ec16b..e199d7dbb876 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c @@ -36,7 +36,7 @@ mock_context(struct drm_i915_private *i915, if (name) { struct i915_ppgtt *ppgtt; - strncpy(ctx->name, name, sizeof(ctx->name) - 1); + strscpy(ctx->name, name, sizeof(ctx->name)); ppgtt = mock_ppgtt(i915, name); if (!ppgtt) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index a4ff55aa5e55..ba4c2422b340 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -4,9 +4,9 @@ */ #include "gen8_engine_cs.h" -#include "i915_drv.h" #include "intel_engine_regs.h" #include "intel_gpu_commands.h" +#include "intel_gt.h" #include "intel_lrc.h" #include "intel_ring.h" @@ -226,8 +226,8 @@ u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) static int mtl_dummy_pipe_control(struct i915_request *rq) { /* Wa_14016712196 */ - if (IS_MTL_GRAPHICS_STEP(rq->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(rq->i915, P, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 71)) || + IS_DG2(rq->i915)) { u32 *cs; /* dummy PIPE_CONTROL + depth flush */ @@ -271,8 +271,17 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70)) bit_group_0 |= PIPE_CONTROL_CCS_FLUSH; + /* + * L3 fabric flush is needed for AUX CCS invalidation + * which happens as part of pipe-control so we can + * ignore PIPE_CONTROL_FLUSH_L3. Also PIPE_CONTROL_FLUSH_L3 + * deals with Protected Memory which is not needed for + * AUX CCS invalidation and lead to unwanted side effects. + */ + if (mode & EMIT_FLUSH) + bit_group_1 |= PIPE_CONTROL_FLUSH_L3; + bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH; - bit_group_1 |= PIPE_CONTROL_FLUSH_L3; bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; bit_group_1 |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; /* Wa_1409600907:tgl,adl-p */ @@ -799,6 +808,7 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs) u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { struct drm_i915_private *i915 = rq->i915; + struct intel_gt *gt = rq->engine->gt; u32 flags = (PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TLB_INVALIDATE | PIPE_CONTROL_TILE_CACHE_FLUSH | @@ -809,8 +819,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) PIPE_CONTROL_FLUSH_ENABLE); /* Wa_14016712196 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915)) /* dummy PIPE_CONTROL + depth flush */ cs = gen12_emit_pipe_control(cs, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index ee15486fed0d..84a75c95f3f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -558,7 +558,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, DRIVER_CAPS(i915)->has_logical_contexts = true; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.execlists.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); @@ -1617,9 +1616,7 @@ static int __intel_engine_stop_cs(struct intel_engine_cs *engine, * Wa_22011802037: Prior to doing a reset, ensure CS is * stopped, set ring stop bit and prefetch disable bit to halt CS */ - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(engine->i915) >= 11 && - GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(engine->gt)) intel_uncore_write_fw(uncore, RING_MODE_GEN7(engine->mmio_base), _MASKED_BIT_ENABLE(GEN12_GFX_PREFETCH_DISABLE)); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index b538b5c04948..e91fc881dbf1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -21,7 +21,7 @@ static void intel_gsc_idle_msg_enable(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - if (IS_METEORLAKE(i915) && engine->id == GSC0) { + if (MEDIA_VER(i915) >= 13 && engine->id == GSC0) { intel_uncore_write(engine->gt->uncore, RC_PSMI_CTRL_GSCCS, _MASKED_BIT_DISABLE(IDLE_MSG_DISABLE)); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h index 6b9d9f837669..fdd4ddd3a978 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h @@ -177,6 +177,7 @@ #define CTX_CTRL_RS_CTX_ENABLE REG_BIT(1) #define CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT REG_BIT(2) #define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH REG_BIT(3) +#define GEN12_CTX_CTRL_RUNALONE_MODE REG_BIT(7) #define GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE REG_BIT(8) #define RING_CTX_SR_CTL(base) _MMIO((base) + 0x244) #define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 8a641bcf777c..e8f42ec6b1b4 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3001,9 +3001,7 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine) * Wa_22011802037: In addition to stopping the cs, we need * to wait for any pending mi force wakeups */ - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(engine->i915) >= 11 && - GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(engine->gt)) intel_engine_wait_for_pending_mi_fw(engine); engine->execlists.reset_ccid = active_ccid(engine); @@ -3550,6 +3548,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) logical_ring_default_vfuncs(engine); logical_ring_default_irqs(engine); + seqcount_init(&engine->stats.execlists.lock); + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index dd0ed941441a..da21f2786b5d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -511,20 +511,31 @@ void intel_ggtt_unbind_vma(struct i915_address_space *vm, vm->clear_range(vm, vma_res->start, vma_res->vma_size); } +/* + * Reserve the top of the GuC address space for firmware images. Addresses + * beyond GUC_GGTT_TOP in the GuC address space are inaccessible by GuC, + * which makes for a suitable range to hold GuC/HuC firmware images if the + * size of the GGTT is 4G. However, on a 32-bit platform the size of the GGTT + * is limited to 2G, which is less than GUC_GGTT_TOP, but we reserve a chunk + * of the same size anyway, which is far more than needed, to keep the logic + * in uc_fw_ggtt_offset() simple. + */ +#define GUC_TOP_RESERVE_SIZE (SZ_4G - GUC_GGTT_TOP) + static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt) { - u64 size; + u64 offset; int ret; if (!intel_uc_uses_guc(&ggtt->vm.gt->uc)) return 0; - GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP); - size = ggtt->vm.total - GUC_GGTT_TOP; + GEM_BUG_ON(ggtt->vm.total <= GUC_TOP_RESERVE_SIZE); + offset = ggtt->vm.total - GUC_TOP_RESERVE_SIZE; - ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, size, - GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE, - PIN_NOEVICT); + ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, + GUC_TOP_RESERVE_SIZE, offset, + I915_COLOR_UNEVICTABLE, PIN_NOEVICT); if (ret) drm_dbg(&ggtt->vm.i915->drm, "Failed to reserve top of GGTT for GuC\n"); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 449f0b7fc843..93062c35e072 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -1019,3 +1019,8 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt, else return I915_MAP_WC; } + +bool intel_gt_needs_wa_22016122933(struct intel_gt *gt) +{ + return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA; +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 6c34547b58b5..2cac499d5aa3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -6,7 +6,6 @@ #ifndef __INTEL_GT__ #define __INTEL_GT__ -#include "i915_drv.h" #include "intel_engine_types.h" #include "intel_gt_types.h" #include "intel_reset.h" @@ -14,6 +13,69 @@ struct drm_i915_private; struct drm_printer; +/* + * Check that the GT is a graphics GT and has an IP version within the + * specified range (inclusive). + */ +#define IS_GFX_GT_IP_RANGE(gt, from, until) ( \ + BUILD_BUG_ON_ZERO((from) < IP_VER(2, 0)) + \ + BUILD_BUG_ON_ZERO((until) < (from)) + \ + ((gt)->type != GT_MEDIA && \ + GRAPHICS_VER_FULL((gt)->i915) >= (from) && \ + GRAPHICS_VER_FULL((gt)->i915) <= (until))) + +/* + * Check that the GT is a media GT and has an IP version within the + * specified range (inclusive). + * + * Only usable on platforms with a standalone media design (i.e., IP version 13 + * and higher). + */ +#define IS_MEDIA_GT_IP_RANGE(gt, from, until) ( \ + BUILD_BUG_ON_ZERO((from) < IP_VER(13, 0)) + \ + BUILD_BUG_ON_ZERO((until) < (from)) + \ + ((gt) && (gt)->type == GT_MEDIA && \ + MEDIA_VER_FULL((gt)->i915) >= (from) && \ + MEDIA_VER_FULL((gt)->i915) <= (until))) + +/* + * Check that the GT is a graphics GT with a specific IP version and has + * a stepping in the range [from, until). The lower stepping bound is + * inclusive, the upper bound is exclusive. The most common use-case of this + * macro is for checking bounds for workarounds, which usually have a stepping + * ("from") at which the hardware issue is first present and another stepping + * ("until") at which a hardware fix is present and the software workaround is + * no longer necessary. E.g., + * + * IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) + * IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B1, STEP_FOREVER) + * + * "STEP_FOREVER" can be passed as "until" for workarounds that have no upper + * stepping bound for the specified IP version. + */ +#define IS_GFX_GT_IP_STEP(gt, ipver, from, until) ( \ + BUILD_BUG_ON_ZERO((until) <= (from)) + \ + (IS_GFX_GT_IP_RANGE((gt), (ipver), (ipver)) && \ + IS_GRAPHICS_STEP((gt)->i915, (from), (until)))) + +/* + * Check that the GT is a media GT with a specific IP version and has + * a stepping in the range [from, until). The lower stepping bound is + * inclusive, the upper bound is exclusive. The most common use-case of this + * macro is for checking bounds for workarounds, which usually have a stepping + * ("from") at which the hardware issue is first present and another stepping + * ("until") at which a hardware fix is present and the software workaround is + * no longer necessary. "STEP_FOREVER" can be passed as "until" for + * workarounds that have no upper stepping bound for the specified IP version. + * + * This macro may only be used to match on platforms that have a standalone + * media design (i.e., media version 13 or higher). + */ +#define IS_MEDIA_GT_IP_STEP(gt, ipver, from, until) ( \ + BUILD_BUG_ON_ZERO((until) <= (from)) + \ + (IS_MEDIA_GT_IP_RANGE((gt), (ipver), (ipver)) && \ + IS_MEDIA_STEP((gt)->i915, (from), (until)))) + #define GT_TRACE(gt, fmt, ...) do { \ const struct intel_gt *gt__ __maybe_unused = (gt); \ GEM_TRACE("%s " fmt, dev_name(gt__->i915->drm.dev), \ @@ -25,10 +87,7 @@ static inline bool gt_is_root(struct intel_gt *gt) return !gt->info.id; } -static inline bool intel_gt_needs_wa_22016122933(struct intel_gt *gt) -{ - return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA; -} +bool intel_gt_needs_wa_22016122933(struct intel_gt *gt); static inline struct intel_gt *uc_to_gt(struct intel_uc *uc) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c index 0b414eae1683..bf4a933de03a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c @@ -4,7 +4,7 @@ */ #include "i915_drv.h" - +#include "intel_gt.h" #include "intel_gt_mcr.h" #include "intel_gt_print.h" #include "intel_gt_regs.h" @@ -166,8 +166,8 @@ void intel_gt_mcr_init(struct intel_gt *gt) gt->steering_table[OADDRM] = xelpmp_oaddrm_steering_table; } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { /* Wa_14016747170 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) fuse = REG_FIELD_GET(MTL_GT_L3_EXC_MASK, intel_uncore_read(gt->uncore, MTL_GT_ACTIVITY_FACTOR)); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index 357e2f865727..f900cc68d6d9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -290,7 +290,6 @@ static int mtl_drpc(struct seq_file *m) seq_puts(m, "RC6\n"); break; default: - MISSING_CASE(REG_FIELD_GET(MTL_CC_MASK, gt_core_status)); seq_puts(m, "Unknown\n"); break; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 2cdfb2f713d0..cca4bac8f8b0 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -26,7 +26,7 @@ #define MTL_CAGF_MASK REG_GENMASK(8, 0) #define MTL_CC0 0x0 #define MTL_CC6 0x3 -#define MTL_CC_MASK REG_GENMASK(12, 9) +#define MTL_CC_MASK REG_GENMASK(10, 9) /* RPM unit config (Gen8+) */ #define RPM_CONFIG0 _MMIO(0xd00) @@ -164,6 +164,8 @@ #define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20d4) #define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) #define GEN11_ENABLE_32_PLANE_MODE (1 << 7) +#define GEN12_CS_DEBUG_MODE2 _MMIO(0x20d8) +#define INSTRUCTION_STATE_CACHE_INVALIDATE REG_BIT(6) #define GEN7_FF_SLICE_CS_CHICKEN1 _MMIO(0x20e0) #define GEN9_FFSC_PERCTX_PREEMPT_CTRL (1 << 14) @@ -412,9 +414,6 @@ #define XEHP_CULLBIT1 MCR_REG(0x6100) -#define CHICKEN_RASTER_1 MCR_REG(0x6204) -#define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8) - #define CHICKEN_RASTER_2 MCR_REG(0x6208) #define TBIMR_FAST_CLIP REG_BIT(5) @@ -1221,6 +1220,8 @@ #define XEHP_HDC_CHICKEN0 MCR_REG(0xe5f0) #define LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK REG_GENMASK(13, 11) +#define DIS_ATOMIC_CHAINING_TYPED_WRITES REG_BIT(3) + #define ICL_HDC_MODE MCR_REG(0xe5f4) #define EU_PERF_CNTL2 PERF_REG(0xe658) @@ -1231,6 +1232,7 @@ #define DISABLE_D8_D16_COASLESCE REG_BIT(30) #define FORCE_1_SUB_MESSAGE_PER_FRAGMENT REG_BIT(15) #define LSC_CHICKEN_BIT_0_UDW MCR_REG(0xe7c8 + 4) +#define UGM_FRAGMENT_THRESHOLD_TO_3 REG_BIT(58 - 32) #define DIS_CHAIN_2XSIMD8 REG_BIT(55 - 32) #define FORCE_SLM_FENCE_SCOPE_TO_TILE REG_BIT(42 - 32) #define FORCE_UGM_FENCE_SCOPE_TO_TILE REG_BIT(41 - 32) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 957d0aeb0c02..eaf66d903166 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -845,6 +845,27 @@ lrc_setup_indirect_ctx(u32 *regs, lrc_ring_indirect_offset_default(engine) << 6; } +static bool ctx_needs_runalone(const struct intel_context *ce) +{ + struct i915_gem_context *gem_ctx; + bool ctx_is_protected = false; + + /* + * On MTL and newer platforms, protected contexts require setting + * the LRC run-alone bit or else the encryption will not happen. + */ + if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 70) && + (ce->engine->class == COMPUTE_CLASS || ce->engine->class == RENDER_CLASS)) { + rcu_read_lock(); + gem_ctx = rcu_dereference(ce->gem_context); + if (gem_ctx) + ctx_is_protected = gem_ctx->uses_protected_content; + rcu_read_unlock(); + } + + return ctx_is_protected; +} + static void init_common_regs(u32 * const regs, const struct intel_context *ce, const struct intel_engine_cs *engine, @@ -860,6 +881,8 @@ static void init_common_regs(u32 * const regs, if (GRAPHICS_VER(engine->i915) < 11) ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT | CTX_CTRL_RS_CTX_ENABLE); + if (ctx_needs_runalone(ce)) + ctl |= _MASKED_BIT_ENABLE(GEN12_CTX_CTRL_RUNALONE_MODE); regs[CTX_CONTEXT_CONTROL] = ctl; |